From 967fc04671feea4dbf780c9e55a0bc8fcf68a14e Mon Sep 17 00:00:00 2001 From: Gregory Haskins Date: Mon, 29 Dec 2008 09:39:52 -0500 Subject: sched: add sched_class->needs_post_schedule() member We currently run class->post_schedule() outside of the rq->lock, which means that we need to test for the need to post_schedule outside of the lock to avoid a forced reacquistion. This is currently not a problem as we only look at rq->rt.overloaded. However, we want to enhance this going forward to look at more state to reduce the need to post_schedule to a bare minimum set. Therefore, we introduce a new member-func called needs_post_schedule() which tests for the post_schedule condtion without actually performing the work. Therefore it is safe to call this function before the rq->lock is released, because we are guaranteed not to drop the lock at an intermediate point (such as what post_schedule() may do). We will use this later in the series [ rostedt: removed paranoid BUG_ON ] Signed-off-by: Gregory Haskins --- include/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index e5f928a079e..836a86c32a6 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1012,6 +1012,7 @@ struct sched_class { struct rq *busiest, struct sched_domain *sd, enum cpu_idle_type idle); void (*pre_schedule) (struct rq *this_rq, struct task_struct *task); + int (*needs_post_schedule) (struct rq *this_rq); void (*post_schedule) (struct rq *this_rq); void (*task_wake_up) (struct rq *this_rq, struct task_struct *task); -- cgit v1.2.3 From 4075134e40804821f90866d7de56802e4dcecb1e Mon Sep 17 00:00:00 2001 From: Gregory Haskins Date: Mon, 29 Dec 2008 09:39:53 -0500 Subject: plist: fix PLIST_NODE_INIT to work with debug enabled It seems that PLIST_NODE_INIT breaks if used and DEBUG_PI_LIST is defined. Since there are no current users of PLIST_NODE_INIT, this has gone undetected. This patch fixes the build issue that enables the DEBUG_PI_LIST later in the series when we use it in init_task.h Signed-off-by: Gregory Haskins --- include/linux/plist.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/plist.h b/include/linux/plist.h index 85de2f05587..45926d77d6a 100644 --- a/include/linux/plist.h +++ b/include/linux/plist.h @@ -96,6 +96,10 @@ struct plist_node { # define PLIST_HEAD_LOCK_INIT(_lock) #endif +#define _PLIST_HEAD_INIT(head) \ + .prio_list = LIST_HEAD_INIT((head).prio_list), \ + .node_list = LIST_HEAD_INIT((head).node_list) + /** * PLIST_HEAD_INIT - static struct plist_head initializer * @head: struct plist_head variable name @@ -103,8 +107,7 @@ struct plist_node { */ #define PLIST_HEAD_INIT(head, _lock) \ { \ - .prio_list = LIST_HEAD_INIT((head).prio_list), \ - .node_list = LIST_HEAD_INIT((head).node_list), \ + _PLIST_HEAD_INIT(head), \ PLIST_HEAD_LOCK_INIT(&(_lock)) \ } @@ -116,7 +119,7 @@ struct plist_node { #define PLIST_NODE_INIT(node, __prio) \ { \ .prio = (__prio), \ - .plist = PLIST_HEAD_INIT((node).plist, NULL), \ + .plist = { _PLIST_HEAD_INIT((node).plist) }, \ } /** -- cgit v1.2.3 From 917b627d4d981dc614519d7b34ea31a976b14e12 Mon Sep 17 00:00:00 2001 From: Gregory Haskins Date: Mon, 29 Dec 2008 09:39:53 -0500 Subject: sched: create "pushable_tasks" list to limit pushing to one attempt The RT scheduler employs a "push/pull" design to actively balance tasks within the system (on a per disjoint cpuset basis). When a task is awoken, it is immediately determined if there are any lower priority cpus which should be preempted. This is opposed to the way normal SCHED_OTHER tasks behave, which will wait for a periodic rebalancing operation to occur before spreading out load. When a particular RQ has more than 1 active RT task, it is said to be in an "overloaded" state. Once this occurs, the system enters the active balancing mode, where it will try to push the task away, or persuade a different cpu to pull it over. The system will stay in this state until the system falls back below the <= 1 queued RT task per RQ. However, the current implementation suffers from a limitation in the push logic. Once overloaded, all tasks (other than current) on the RQ are analyzed on every push operation, even if it was previously unpushable (due to affinity, etc). Whats more, the operation stops at the first task that is unpushable and will not look at items lower in the queue. This causes two problems: 1) We can have the same tasks analyzed over and over again during each push, which extends out the fast path in the scheduler for no gain. Consider a RQ that has dozens of tasks that are bound to a core. Each one of those tasks will be encountered and skipped for each push operation while they are queued. 2) There may be lower-priority tasks under the unpushable task that could have been successfully pushed, but will never be considered until either the unpushable task is cleared, or a pull operation succeeds. The net result is a potential latency source for mid priority tasks. This patch aims to rectify these two conditions by introducing a new priority sorted list: "pushable_tasks". A task is added to the list each time a task is activated or preempted. It is removed from the list any time it is deactivated, made current, or fails to push. This works because a task only needs to be attempted to push once. After an initial failure to push, the other cpus will eventually try to pull the task when the conditions are proper. This also solves the problem that we don't completely analyze all tasks due to encountering an unpushable tasks. Now every task will have a push attempted (when appropriate). This reduces latency both by shorting the critical section of the rq->lock for certain workloads, and by making sure the algorithm considers all eligible tasks in the system. [ rostedt: added a couple more BUG_ONs ] Signed-off-by: Gregory Haskins Acked-by: Steven Rostedt --- include/linux/init_task.h | 1 + include/linux/sched.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 23fd8909b9e..6851225f44a 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -140,6 +140,7 @@ extern struct group_info init_groups; .nr_cpus_allowed = NR_CPUS, \ }, \ .tasks = LIST_HEAD_INIT(tsk.tasks), \ + .pushable_tasks = PLIST_NODE_INIT(tsk.pushable_tasks, MAX_PRIO), \ .ptraced = LIST_HEAD_INIT(tsk.ptraced), \ .ptrace_entry = LIST_HEAD_INIT(tsk.ptrace_entry), \ .real_parent = &tsk, \ diff --git a/include/linux/sched.h b/include/linux/sched.h index 836a86c32a6..440cabb2d43 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1179,6 +1179,7 @@ struct task_struct { #endif struct list_head tasks; + struct plist_node pushable_tasks; struct mm_struct *mm, *active_mm; -- cgit v1.2.3 From f0402a262e1a4c03fc66b83659823bdcaac3c41a Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Mon, 5 Jan 2009 23:59:01 +0900 Subject: generic: add common struct for dma map operations This adds struct dma_map_ops include/linux/dma-mapping.h, which, is used to handle multiple sets of dma mapping API. Signed-off-by: FUJITA Tomonori Signed-off-by: Ingo Molnar --- include/linux/dma-mapping.h | 48 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 48 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index ba9114ec5d3..d7d090d2103 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -3,6 +3,8 @@ #include #include +#include +#include /* These definitions mirror those in pci.h, so they can be used * interchangeably with their PCI_ counterparts */ @@ -13,6 +15,52 @@ enum dma_data_direction { DMA_NONE = 3, }; +struct dma_map_ops { + void* (*alloc_coherent)(struct device *dev, size_t size, + dma_addr_t *dma_handle, gfp_t gfp); + void (*free_coherent)(struct device *dev, size_t size, + void *vaddr, dma_addr_t dma_handle); + dma_addr_t (*map_page)(struct device *dev, struct page *page, + unsigned long offset, size_t size, + enum dma_data_direction dir, + struct dma_attrs *attrs); + void (*unmap_page)(struct device *dev, dma_addr_t dma_handle, + size_t size, enum dma_data_direction dir, + struct dma_attrs *attrs); + int (*map_sg)(struct device *dev, struct scatterlist *sg, + int nents, enum dma_data_direction dir, + struct dma_attrs *attrs); + void (*unmap_sg)(struct device *dev, + struct scatterlist *sg, int nents, + enum dma_data_direction dir, + struct dma_attrs *attrs); + void (*sync_single_for_cpu)(struct device *dev, + dma_addr_t dma_handle, size_t size, + enum dma_data_direction dir); + void (*sync_single_for_device)(struct device *dev, + dma_addr_t dma_handle, size_t size, + enum dma_data_direction dir); + void (*sync_single_range_for_cpu)(struct device *dev, + dma_addr_t dma_handle, + unsigned long offset, + size_t size, + enum dma_data_direction dir); + void (*sync_single_range_for_device)(struct device *dev, + dma_addr_t dma_handle, + unsigned long offset, + size_t size, + enum dma_data_direction dir); + void (*sync_sg_for_cpu)(struct device *dev, + struct scatterlist *sg, int nents, + enum dma_data_direction dir); + void (*sync_sg_for_device)(struct device *dev, + struct scatterlist *sg, int nents, + enum dma_data_direction dir); + int (*mapping_error)(struct device *dev, dma_addr_t dma_addr); + int (*dma_supported)(struct device *dev, u64 mask); + int is_phys; +}; + #define DMA_BIT_MASK(n) (((n) == 64) ? ~0ULL : ((1ULL<<(n))-1)) /* -- cgit v1.2.3 From 160c1d8e40866edfeae7d68816b7005d70acf391 Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Mon, 5 Jan 2009 23:59:02 +0900 Subject: x86, ia64: convert to use generic dma_map_ops struct This converts X86 and IA64 to use include/linux/dma-mapping.h. It's a bit large but pretty boring. The major change for X86 is converting 'int dir' to 'enum dma_data_direction dir' in DMA mapping operations. The major changes for IA64 is using map_page and unmap_page instead of map_single and unmap_single. Signed-off-by: FUJITA Tomonori Acked-by: Tony Luck Signed-off-by: Ingo Molnar --- include/linux/intel-iommu.h | 6 ++++-- include/linux/swiotlb.h | 18 ++++++++++-------- 2 files changed, 14 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index c4f6c101dbc..a254db1decd 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -334,7 +334,9 @@ extern void *intel_alloc_coherent(struct device *, size_t, dma_addr_t *, gfp_t); extern void intel_free_coherent(struct device *, size_t, void *, dma_addr_t); extern dma_addr_t intel_map_single(struct device *, phys_addr_t, size_t, int); extern void intel_unmap_single(struct device *, dma_addr_t, size_t, int); -extern int intel_map_sg(struct device *, struct scatterlist *, int, int); -extern void intel_unmap_sg(struct device *, struct scatterlist *, int, int); +extern int intel_map_sg(struct device *, struct scatterlist *, int, + enum dma_data_direction, struct dma_attrs *); +extern void intel_unmap_sg(struct device *, struct scatterlist *, int, + enum dma_data_direction, struct dma_attrs *); #endif diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index dedd3c0cfe3..0567c3d8633 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -66,36 +66,38 @@ swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sg, int nents, extern int swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems, - int dir, struct dma_attrs *attrs); + enum dma_data_direction dir, struct dma_attrs *attrs); extern void swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl, - int nelems, int dir, struct dma_attrs *attrs); + int nelems, enum dma_data_direction dir, + struct dma_attrs *attrs); extern void swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr, - size_t size, int dir); + size_t size, enum dma_data_direction dir); extern void swiotlb_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg, - int nelems, int dir); + int nelems, enum dma_data_direction dir); extern void swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr, - size_t size, int dir); + size_t size, enum dma_data_direction dir); extern void swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg, - int nelems, int dir); + int nelems, enum dma_data_direction dir); extern void swiotlb_sync_single_range_for_cpu(struct device *hwdev, dma_addr_t dev_addr, - unsigned long offset, size_t size, int dir); + unsigned long offset, size_t size, + enum dma_data_direction dir); extern void swiotlb_sync_single_range_for_device(struct device *hwdev, dma_addr_t dev_addr, unsigned long offset, size_t size, - int dir); + enum dma_data_direction dir); extern int swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr); -- cgit v1.2.3 From f98eee8ea99fe74ee9c4e867ba178ec3072793be Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Mon, 5 Jan 2009 23:59:03 +0900 Subject: x86, ia64: remove duplicated swiotlb code This adds swiotlb_map_page and swiotlb_unmap_page to lib/swiotlb.c and remove IA64 and X86's swiotlb_map_page and swiotlb_unmap_page. This also removes unnecessary swiotlb_map_single, swiotlb_map_single_attrs, swiotlb_unmap_single and swiotlb_unmap_single_attrs. Signed-off-by: FUJITA Tomonori Acked-by: Tony Luck Signed-off-by: Ingo Molnar --- include/linux/swiotlb.h | 21 +++++++-------------- 1 file changed, 7 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 0567c3d8633..493dc17e7c8 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -41,20 +41,13 @@ extern void swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr, dma_addr_t dma_handle); -extern dma_addr_t -swiotlb_map_single(struct device *hwdev, void *ptr, size_t size, int dir); - -extern void -swiotlb_unmap_single(struct device *hwdev, dma_addr_t dev_addr, - size_t size, int dir); - -extern dma_addr_t -swiotlb_map_single_attrs(struct device *hwdev, void *ptr, size_t size, - int dir, struct dma_attrs *attrs); - -extern void -swiotlb_unmap_single_attrs(struct device *hwdev, dma_addr_t dev_addr, - size_t size, int dir, struct dma_attrs *attrs); +extern dma_addr_t swiotlb_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, + enum dma_data_direction dir, + struct dma_attrs *attrs); +extern void swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr, + size_t size, enum dma_data_direction dir, + struct dma_attrs *attrs); extern int swiotlb_map_sg(struct device *hwdev, struct scatterlist *sg, int nents, -- cgit v1.2.3 From d506fc322ec2af04fc47be83d796a1c9e1a16022 Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Wed, 7 Jan 2009 11:54:25 +0200 Subject: ALSA: Add support for video out to the jack reporting API Add support for reporting new jack types SND_JACK_VIDEOOUT and SND_JACK_AVOUT (a combination of LINEOUT and VIDEOOUT) to the jack reporting API. Also add the corresponding SW_VIDEOOUT_INSERT switch to the input system header. Signed-off-by: Jani Nikula Signed-off-by: Mark Brown --- include/linux/input.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/input.h b/include/linux/input.h index 9a6355f74db..adc13322d1d 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -661,6 +661,7 @@ struct input_absinfo { #define SW_DOCK 0x05 /* set = plugged into dock */ #define SW_LINEOUT_INSERT 0x06 /* set = inserted */ #define SW_JACK_PHYSICAL_INSERT 0x07 /* set = mechanical switch set */ +#define SW_VIDEOOUT_INSERT 0x08 /* set = inserted */ #define SW_MAX 0x0f #define SW_CNT (SW_MAX+1) -- cgit v1.2.3 From 01d07820a0df6b6134c1bb75b1e84c9d0cdab3be Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Sun, 4 Jan 2009 03:11:05 +0900 Subject: sparseirq: make for_each_irq_desc() more robust Raja reported for_each_irq_desc() has possibility unsafeness: if anyone write folliwing code, for_each_irq_desc() doesn't work as intended: (right now this code does not exist at all) if (safe) for_each_irq_desc(irq, desc) { ... } else panic(); Reported-by: Raja R Harinath Signed-off-by: KOSAKI Motohiro Signed-off-by: Ingo Molnar --- include/linux/irqnr.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqnr.h b/include/linux/irqnr.h index 86af92e9e84..52ebbb4b161 100644 --- a/include/linux/irqnr.h +++ b/include/linux/irqnr.h @@ -28,13 +28,17 @@ extern struct irq_desc *irq_to_desc(unsigned int irq); # define for_each_irq_desc(irq, desc) \ for (irq = 0, desc = irq_to_desc(irq); irq < nr_irqs; \ irq++, desc = irq_to_desc(irq)) \ - if (desc) + if (!desc) \ + ; \ + else # define for_each_irq_desc_reverse(irq, desc) \ for (irq = nr_irqs - 1, desc = irq_to_desc(irq); irq >= 0; \ irq--, desc = irq_to_desc(irq)) \ - if (desc) + if (!desc) \ + ; \ + else #endif /* CONFIG_GENERIC_HARDIRQS */ -- cgit v1.2.3 From a6ba2b2dabb583e7820e567fb309d771b50cb9ff Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 8 Jan 2009 15:16:16 +0000 Subject: ASoC: Implement WM8350 headphone jack detection Signed-off-by: Mark Brown --- include/linux/mfd/wm8350/audio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/wm8350/audio.h b/include/linux/mfd/wm8350/audio.h index af95a1d2f3a..d899dc0223b 100644 --- a/include/linux/mfd/wm8350/audio.h +++ b/include/linux/mfd/wm8350/audio.h @@ -490,6 +490,7 @@ /* * R231 (0xE7) - Jack Status */ +#define WM8350_JACK_L_LVL 0x0800 #define WM8350_JACK_R_LVL 0x0400 /* -- cgit v1.2.3 From d7e51e66899f95dabc89b4d4c6674a6e50fa37fc Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Wed, 7 Jan 2009 15:03:13 -0800 Subject: sparseirq: make some func to be used with genirq Impact: clean up sparseirq fallout on random.c Ingo suggested to change some ifdef from SPARSE_IRQ to GENERIC_HARDIRQS so we could some #ifdef later if all arch support genirq Signed-off-by: Yinghai Lu Acked-by: Matt Mackall Signed-off-by: Ingo Molnar --- include/linux/irq.h | 6 ++---- include/linux/kernel_stat.h | 6 +++--- 2 files changed, 5 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index f899b502f18..e9a878978c8 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -160,12 +160,10 @@ struct irq_2_iommu; */ struct irq_desc { unsigned int irq; -#ifdef CONFIG_SPARSE_IRQ struct timer_rand_state *timer_rand_state; unsigned int *kstat_irqs; -# ifdef CONFIG_INTR_REMAP +#ifdef CONFIG_INTR_REMAP struct irq_2_iommu *irq_2_iommu; -# endif #endif irq_flow_handler_t handle_irq; struct irq_chip *chip; @@ -202,13 +200,13 @@ extern void arch_free_chip_data(struct irq_desc *old_desc, struct irq_desc *desc extern struct irq_desc irq_desc[NR_IRQS]; #else /* CONFIG_SPARSE_IRQ */ extern struct irq_desc *move_irq_desc(struct irq_desc *old_desc, int cpu); +#endif /* CONFIG_SPARSE_IRQ */ #define kstat_irqs_this_cpu(DESC) \ ((DESC)->kstat_irqs[smp_processor_id()]) #define kstat_incr_irqs_this_cpu(irqno, DESC) \ ((DESC)->kstat_irqs[smp_processor_id()]++) -#endif /* CONFIG_SPARSE_IRQ */ extern struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu); diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h index 570d2041311..a3431b164be 100644 --- a/include/linux/kernel_stat.h +++ b/include/linux/kernel_stat.h @@ -28,7 +28,7 @@ struct cpu_usage_stat { struct kernel_stat { struct cpu_usage_stat cpustat; -#ifndef CONFIG_SPARSE_IRQ +#ifndef CONFIG_GENERIC_HARDIRQS unsigned int irqs[NR_IRQS]; #endif }; @@ -41,7 +41,7 @@ DECLARE_PER_CPU(struct kernel_stat, kstat); extern unsigned long long nr_context_switches(void); -#ifndef CONFIG_SPARSE_IRQ +#ifndef CONFIG_GENERIC_HARDIRQS #define kstat_irqs_this_cpu(irq) \ (kstat_this_cpu.irqs[irq]) @@ -55,7 +55,7 @@ static inline void kstat_incr_irqs_this_cpu(unsigned int irq, #endif -#ifndef CONFIG_SPARSE_IRQ +#ifndef CONFIG_GENERIC_HARDIRQS static inline unsigned int kstat_irqs_cpu(unsigned int irq, int cpu) { return kstat_cpu(cpu).irqs[irq]; -- cgit v1.2.3 From 0b8698ab5847cbe25775083659f00c658a8161c9 Mon Sep 17 00:00:00 2001 From: Ian Campbell Date: Fri, 9 Jan 2009 18:32:09 +0000 Subject: swiotlb: range_needs_mapping should take a physical address. The swiotlb_arch_range_needs_mapping() hook should take a physical address rather than a virtual address in order to support highmem pages. Signed-off-by: Ian Campbell Signed-off-by: Ingo Molnar --- include/linux/swiotlb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 493dc17e7c8..ac9ff54f7cb 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -31,7 +31,7 @@ extern dma_addr_t swiotlb_phys_to_bus(struct device *hwdev, phys_addr_t address); extern phys_addr_t swiotlb_bus_to_phys(dma_addr_t address); -extern int swiotlb_arch_range_needs_mapping(void *ptr, size_t size); +extern int swiotlb_arch_range_needs_mapping(phys_addr_t paddr, size_t size); extern void *swiotlb_alloc_coherent(struct device *hwdev, size_t size, -- cgit v1.2.3 From 831451ac4e44d3a20b581ce726ef1d1144373f7d Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 14 Jan 2009 12:39:18 +0100 Subject: sched: introduce avg_wakeup Introduce a new avg_wakeup statistic. avg_wakeup is a measure of how frequently a task wakes up other tasks, it represents the average time between wakeups, with a limit of avg_runtime for when it doesn't wake up anybody. Signed-off-by: Peter Zijlstra Signed-off-by: Mike Galbraith Signed-off-by: Ingo Molnar --- include/linux/sched.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 4cae9b81a1f..daf4e07bc97 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1046,6 +1046,9 @@ struct sched_entity { u64 exec_max; u64 slice_max; + u64 start_runtime; + u64 avg_wakeup; + u64 nr_migrations; u64 nr_migrations_cold; u64 nr_failed_migrations_affine; -- cgit v1.2.3 From 34cb61359b503d7aff6447acb037a5efd6ce93b2 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 16 Jan 2009 13:36:06 +0100 Subject: sched: fix !CONFIG_SCHEDSTATS build failure Stephen Rothwell reported this linux-next build failure with !CONFIG_SCHEDSTATS: | In file included from kernel/sched.c:1703: | kernel/sched_fair.c: In function 'adaptive_gran': | kernel/sched_fair.c:1324: error: 'struct sched_entity' has no member named 'avg_wakeup' The start_runtime and avg_wakeup metrics are now not just for statistics, but also for scheduling - so they always need to be available. (Also move out the nr_migrations fields - for future perfcounters usage.) Reported-by: Stephen Rothwell Signed-off-by: Ingo Molnar --- include/linux/sched.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index daf4e07bc97..5d56b54350a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1031,6 +1031,10 @@ struct sched_entity { u64 last_wakeup; u64 avg_overlap; + u64 start_runtime; + u64 avg_wakeup; + u64 nr_migrations; + #ifdef CONFIG_SCHEDSTATS u64 wait_start; u64 wait_max; @@ -1046,10 +1050,6 @@ struct sched_entity { u64 exec_max; u64 slice_max; - u64 start_runtime; - u64 avg_wakeup; - - u64 nr_migrations; u64 nr_migrations_cold; u64 nr_failed_migrations_affine; u64 nr_failed_migrations_running; -- cgit v1.2.3 From 74296a8ed6aa3c5bf672808ada690de7ba323ecc Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 16 Jan 2009 17:43:50 +0100 Subject: irq: provide debug_poll_all_shared_irqs() method under CONFIG_DEBUG_SHIRQ Provide a shared interrupt debug facility under CONFIG_DEBUG_SHIRQ: it uses the existing irqpoll facilities to iterate through all registered interrupt handlers and call those which can handle shared IRQ lines. This can be handy for suspend/resume debugging: if we call this function early during resume we can trigger crashes in those drivers which have incorrect assumptions about when exactly their ISRs will be called during suspend/resume. Signed-off-by: Ingo Molnar --- include/linux/interrupt.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 9127f6b51a3..468e3a25a4a 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -462,6 +462,12 @@ static inline void init_irq_proc(void) } #endif +#if defined(CONFIG_GENERIC_HARDIRQS) && defined(CONFIG_DEBUG_SHIRQ) +extern void debug_poll_all_shared_irqs(void); +#else +static inline void debug_poll_all_shared_irqs(void) { } +#endif + int show_interrupts(struct seq_file *p, void *v); struct irq_desc; -- cgit v1.2.3 From 5803c5122acb31ebf5f76b1a9925e2c72c4436e1 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Fri, 9 Jan 2009 13:01:08 +0000 Subject: arcnet: convert to internal stats Use pre-existing network_device_stats inside network_device rather than own private structure. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/arcdevice.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/arcdevice.h b/include/linux/arcdevice.h index a1916078fd0..ef0d6b7df44 100644 --- a/include/linux/arcdevice.h +++ b/include/linux/arcdevice.h @@ -235,8 +235,6 @@ struct Outgoing { struct arcnet_local { - struct net_device_stats stats; - uint8_t config, /* current value of CONFIG register */ timeout, /* Extended timeout for COM20020 */ backplane, /* Backplane flag for COM20020 */ -- cgit v1.2.3 From bca5b8939f107e498b3fdc92b3a2d286a868d347 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Fri, 9 Jan 2009 13:01:09 +0000 Subject: arcnet: convert to net_device_ops Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/arcdevice.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/arcdevice.h b/include/linux/arcdevice.h index ef0d6b7df44..cd4bcb6989c 100644 --- a/include/linux/arcdevice.h +++ b/include/linux/arcdevice.h @@ -333,7 +333,12 @@ void arcnet_dump_skb(struct net_device *dev, struct sk_buff *skb, char *desc); void arcnet_unregister_proto(struct ArcProto *proto); irqreturn_t arcnet_interrupt(int irq, void *dev_id); -struct net_device *alloc_arcdev(char *name); +struct net_device *alloc_arcdev(const char *name); + +int arcnet_open(struct net_device *dev); +int arcnet_close(struct net_device *dev); +int arcnet_send_packet(struct sk_buff *skb, struct net_device *dev); +void arcnet_timeout(struct net_device *dev); #endif /* __KERNEL__ */ #endif /* _LINUX_ARCDEVICE_H */ -- cgit v1.2.3 From a1799af4d7deefccdaa9d222a886fa1373dbb49a Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Fri, 9 Jan 2009 13:01:10 +0000 Subject: com20020: convert to net_devic_ops Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/com20020.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/com20020.h b/include/linux/com20020.h index ac6d9a43e08..350afa773f8 100644 --- a/include/linux/com20020.h +++ b/include/linux/com20020.h @@ -29,6 +29,7 @@ int com20020_check(struct net_device *dev); int com20020_found(struct net_device *dev, int shared); +const struct net_device_ops com20020_netdev_ops; /* The number of low I/O ports used by the card. */ #define ARCNET_TOTAL_SIZE 8 -- cgit v1.2.3 From 9fd3238e95046b61d518ddacaa767fa09f31b0d0 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Fri, 9 Jan 2009 13:01:19 +0000 Subject: ibmtr: convert to internal network_device_stats Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/ibmtr.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ibmtr.h b/include/linux/ibmtr.h index 1c7a0dd5536..06695b74d40 100644 --- a/include/linux/ibmtr.h +++ b/include/linux/ibmtr.h @@ -207,7 +207,7 @@ struct tok_info { unsigned short exsap_station_id; unsigned short global_int_enable; struct sk_buff *current_skb; - struct net_device_stats tr_stats; + unsigned char auto_speedsave; open_state open_status, sap_status; enum {MANUAL, AUTOMATIC} open_mode; -- cgit v1.2.3 From 5a7616af604caf0d436a1ed0d4298bb25cd77d67 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Fri, 9 Jan 2009 13:01:35 +0000 Subject: hdlcdrv: convert to internal net_device_stats Signed-off-by: Stephen Hemminger Acked-by: Thomas Sailer Signed-off-by: David S. Miller --- include/linux/hdlcdrv.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hdlcdrv.h b/include/linux/hdlcdrv.h index bf6302f6b5f..0821bac62b8 100644 --- a/include/linux/hdlcdrv.h +++ b/include/linux/hdlcdrv.h @@ -241,7 +241,6 @@ struct hdlcdrv_state { struct hdlcdrv_bitbuffer bitbuf_hdlc; #endif /* HDLCDRV_DEBUG */ - struct net_device_stats stats; int ptt_keyed; /* queued skb for transmission */ -- cgit v1.2.3 From 7cdc15f5f9db71e9c92422918ab9f8df0d31f81f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Krzysztof=20Ha=C5=82asa?= Date: Thu, 8 Jan 2009 19:46:54 +0100 Subject: WAN: Generic HDLC now uses IFF_WAN_HDLC private flag. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Krzysztof Hałasa Signed-off-by: David S. Miller --- include/linux/if.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/if.h b/include/linux/if.h index 2a6e29620a9..1108f3e099e 100644 --- a/include/linux/if.h +++ b/include/linux/if.h @@ -66,6 +66,7 @@ #define IFF_SLAVE_NEEDARP 0x40 /* need ARPs for validation */ #define IFF_ISATAP 0x80 /* ISATAP interface (RFC4214) */ #define IFF_MASTER_ARPMON 0x100 /* bonding master, ARP mon in use */ +#define IFF_WAN_HDLC 0x200 /* WAN HDLC device */ #define IF_GET_IFACE 0x0001 /* for querying only */ #define IF_GET_PROTO 0x0002 -- cgit v1.2.3 From 991990a12de42281f81b4e3a6471586d2d0caf6a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Krzysztof=20Ha=C5=82asa?= Date: Thu, 8 Jan 2009 22:52:11 +0100 Subject: WAN: Convert generic HDLC drivers to netdev_ops. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Also remove unneeded last_rx update from Synclink drivers. Synclink part mostly by Stephen Hemminger. Signed-off-by: Krzysztof Hałasa Signed-off-by: David S. Miller --- include/linux/hdlc.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hdlc.h b/include/linux/hdlc.h index fd47a151665..6a6e701f163 100644 --- a/include/linux/hdlc.h +++ b/include/linux/hdlc.h @@ -38,6 +38,7 @@ struct hdlc_proto { int (*ioctl)(struct net_device *dev, struct ifreq *ifr); __be16 (*type_trans)(struct sk_buff *skb, struct net_device *dev); int (*netif_rx)(struct sk_buff *skb); + int (*xmit)(struct sk_buff *skb, struct net_device *dev); struct module *module; struct hdlc_proto *next; /* next protocol in the list */ }; @@ -102,6 +103,10 @@ static __inline__ void debug_frame(const struct sk_buff *skb) int hdlc_open(struct net_device *dev); /* Must be called by hardware driver when HDLC device is being closed */ void hdlc_close(struct net_device *dev); +/* May be used by hardware driver */ +int hdlc_change_mtu(struct net_device *dev, int new_mtu); +/* Must be pointed to by hw driver's dev->netdev_ops->ndo_start_xmit */ +int hdlc_start_xmit(struct sk_buff *skb, struct net_device *dev); int attach_hdlc_protocol(struct net_device *dev, struct hdlc_proto *proto, size_t size); -- cgit v1.2.3 From 5ec99fdf8e1a6ee90fce22c2fce94871ab44e8ba Mon Sep 17 00:00:00 2001 From: Cesar Eduardo Barros Date: Wed, 14 Jan 2009 20:34:04 -0800 Subject: sc92031: use device id directly instead of made-up name Instead of making up a name for the device ids, put them directly in the device id table. Also move the vendor id to pci_ids.h. Signed-off-by: Cesar Eduardo Barros Signed-off-by: David S. Miller --- include/linux/pci_ids.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index d56ad9c21c0..302423afa13 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2209,6 +2209,8 @@ #define PCI_VENDOR_ID_TOPSPIN 0x1867 +#define PCI_VENDOR_ID_SILAN 0x1904 + #define PCI_VENDOR_ID_TDI 0x192E #define PCI_DEVICE_ID_TDI_EHCI 0x0101 -- cgit v1.2.3 From 288379f050284087578b77e04f040b57db3db3f8 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Mon, 19 Jan 2009 16:43:59 -0800 Subject: net: Remove redundant NAPI functions Following the removal of the unused struct net_device * parameter from the NAPI functions named *netif_rx_* in commit 908a7a1, they are exactly equivalent to the corresponding *napi_* functions and are therefore redundant. Signed-off-by: Ben Hutchings Acked-by: Neil Horman Signed-off-by: David S. Miller --- include/linux/netdevice.h | 50 ----------------------------------------------- 1 file changed, 50 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ec54785d34f..dd8a35b3e8b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1574,56 +1574,6 @@ static inline u32 netif_msg_init(int debug_value, int default_msg_enable_bits) return (1 << debug_value) - 1; } -/* Test if receive needs to be scheduled but only if up */ -static inline int netif_rx_schedule_prep(struct napi_struct *napi) -{ - return napi_schedule_prep(napi); -} - -/* Add interface to tail of rx poll list. This assumes that _prep has - * already been called and returned 1. - */ -static inline void __netif_rx_schedule(struct napi_struct *napi) -{ - __napi_schedule(napi); -} - -/* Try to reschedule poll. Called by irq handler. */ - -static inline void netif_rx_schedule(struct napi_struct *napi) -{ - if (netif_rx_schedule_prep(napi)) - __netif_rx_schedule(napi); -} - -/* Try to reschedule poll. Called by dev->poll() after netif_rx_complete(). */ -static inline int netif_rx_reschedule(struct napi_struct *napi) -{ - if (napi_schedule_prep(napi)) { - __netif_rx_schedule(napi); - return 1; - } - return 0; -} - -/* same as netif_rx_complete, except that local_irq_save(flags) - * has already been issued - */ -static inline void __netif_rx_complete(struct napi_struct *napi) -{ - __napi_complete(napi); -} - -/* Remove interface from poll list: it must be in the poll list - * on current cpu. This primitive is called by dev->poll(), when - * it completes the work. The device cannot be out of poll list at this - * moment, it is BUG(). - */ -static inline void netif_rx_complete(struct napi_struct *napi) -{ - napi_complete(napi); -} - static inline void __netif_tx_lock(struct netdev_queue *txq, int cpu) { spin_lock(&txq->_xmit_lock); -- cgit v1.2.3 From f90f92eed74251034f251e3cdf4fa5c4c1f09df0 Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Fri, 16 Jan 2009 23:36:30 +0000 Subject: dccp: Initialisation framework for feature negotiation This initialises feature negotiation from two tables, which are in turn are initialised from sysctls. As a novel feature, specifics of the implementation (e.g. that short seqnos and ECN are not yet available) are advertised for robustness. Signed-off-by: Gerrit Renker Acked-by: Ian McDonald Signed-off-by: David S. Miller --- include/linux/dccp.h | 19 ------------------- 1 file changed, 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 61734e27abb..990e97fa1f0 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -369,28 +369,9 @@ static inline unsigned int dccp_hdr_len(const struct sk_buff *skb) * Will be used to pass the state from dccp_request_sock to dccp_sock. * * @dccpms_sequence_window - Sequence Window Feature (section 7.5.2) - * @dccpms_pending - List of features being negotiated - * @dccpms_conf - */ struct dccp_minisock { __u64 dccpms_sequence_window; - struct list_head dccpms_pending; - struct list_head dccpms_conf; -}; - -struct dccp_opt_conf { - __u8 *dccpoc_val; - __u8 dccpoc_len; -}; - -struct dccp_opt_pend { - struct list_head dccpop_node; - __u8 dccpop_type; - __u8 dccpop_feat; - __u8 *dccpop_val; - __u8 dccpop_len; - int dccpop_conf; - struct dccp_opt_conf *dccpop_sc; }; extern void dccp_minisock_init(struct dccp_minisock *dmsk); -- cgit v1.2.3 From 792b48780e8b6435d017cef4b5c304876a48653e Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Fri, 16 Jan 2009 23:36:31 +0000 Subject: dccp: Implement both feature-local and feature-remote Sequence Window feature This adds full support for local/remote Sequence Window feature, from which the * sequence-number-validity (W) and * acknowledgment-number-validity (W') windows derive as specified in RFC 4340, 7.5.3. Specifically, the following is contained in this patch: * integrated new socket fields into dccp_sk; * updated the update_gsr/gss routines with regard to these fields; * updated handler code: the Sequence Window feature is located at the TX side, so the local feature is meant if the handler-rx flag is false; * the initialisation of `rcv_wnd' in reqsk is removed, since - rcv_wnd is not used by the code anywhere; - sequence number checks are not done in the LISTEN state (cf. 7.5.3); - dccp_check_req checks the Ack number validity more rigorously; * the `struct dccp_minisock' became empty and is now removed. Signed-off-by: Gerrit Renker Acked-by: Ian McDonald Signed-off-by: David S. Miller --- include/linux/dccp.h | 24 ++++-------------------- 1 file changed, 4 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 990e97fa1f0..7a0502ab383 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -363,19 +363,6 @@ static inline unsigned int dccp_hdr_len(const struct sk_buff *skb) /* FIXME: for now we're default to 1 but it should really be 0 */ #define DCCPF_INITIAL_SEND_NDP_COUNT 1 -/** - * struct dccp_minisock - Minimal DCCP connection representation - * - * Will be used to pass the state from dccp_request_sock to dccp_sock. - * - * @dccpms_sequence_window - Sequence Window Feature (section 7.5.2) - */ -struct dccp_minisock { - __u64 dccpms_sequence_window; -}; - -extern void dccp_minisock_init(struct dccp_minisock *dmsk); - /** * struct dccp_request_sock - represent DCCP-specific connection request * @dreq_inet_rsk: structure inherited from @@ -464,13 +451,14 @@ struct dccp_ackvec; * @dccps_timestamp_time - time of receiving latest @dccps_timestamp_echo * @dccps_l_ack_ratio - feature-local Ack Ratio * @dccps_r_ack_ratio - feature-remote Ack Ratio + * @dccps_l_seq_win - local Sequence Window (influences ack number validity) + * @dccps_r_seq_win - remote Sequence Window (influences seq number validity) * @dccps_pcslen - sender partial checksum coverage (via sockopt) * @dccps_pcrlen - receiver partial checksum coverage (via sockopt) * @dccps_send_ndp_count - local Send NDP Count feature (7.7.2) * @dccps_ndp_count - number of Non Data Packets since last data packet * @dccps_mss_cache - current value of MSS (path MTU minus header sizes) * @dccps_rate_last - timestamp for rate-limiting DCCP-Sync (RFC 4340, 7.5.4) - * @dccps_minisock - associated minisock (accessed via dccp_msk) * @dccps_featneg - tracks feature-negotiation state (mostly during handshake) * @dccps_hc_rx_ackvec - rx half connection ack vector * @dccps_hc_rx_ccid - CCID used for the receiver (or receiving half-connection) @@ -504,12 +492,13 @@ struct dccp_sock { __u32 dccps_timestamp_time; __u16 dccps_l_ack_ratio; __u16 dccps_r_ack_ratio; + __u64 dccps_l_seq_win:48; + __u64 dccps_r_seq_win:48; __u8 dccps_pcslen:4; __u8 dccps_pcrlen:4; __u8 dccps_send_ndp_count:1; __u64 dccps_ndp_count:48; unsigned long dccps_rate_last; - struct dccp_minisock dccps_minisock; struct list_head dccps_featneg; struct dccp_ackvec *dccps_hc_rx_ackvec; struct ccid *dccps_hc_rx_ccid; @@ -527,11 +516,6 @@ static inline struct dccp_sock *dccp_sk(const struct sock *sk) return (struct dccp_sock *)sk; } -static inline struct dccp_minisock *dccp_msk(const struct sock *sk) -{ - return (struct dccp_minisock *)&dccp_sk(sk)->dccps_minisock; -} - static inline const char *dccp_role(const struct sock *sk) { switch (dccp_sk(sk)->dccps_role) { -- cgit v1.2.3 From 883ca833e5fb814fb03426c9d35e5489ce43e8da Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Fri, 16 Jan 2009 23:36:32 +0000 Subject: dccp: Initialisation and type-checking of feature sysctls This patch takes care of initialising and type-checking sysctls related to feature negotiation. Type checking is important since some of the sysctls now directly impact the feature-negotiation process. The sysctls are initialised with the known default values for each feature. For the type-checking the value constraints from RFC 4340 are used: * Sequence Window uses the specified Wmin=32, the maximum is ulong (4 bytes), tested and confirmed that it works up to 4294967295 - for Gbps speed; * Ack Ratio is between 0 .. 0xffff (2-byte unsigned integer); * CCIDs are between 0 .. 255; * request_retries, retries1, retries2 also between 0..255 for good measure; * tx_qlen is checked to be non-negative; * sync_ratelimit remains as before. Notes: ------ 1. Die s@sysctl_dccp_feat@sysctl_dccp@g since the sysctls are now in feat.c. 2. As pointed out by Arnaldo, the pattern of type-checking repeats itself in other places, sometimes with exactly the same kind of definitions (e.g. "static int zero;"). It may be a good idea (kernel janitors?) to consolidate type checking. For the sake of keeping the changeset small and in order not to affect other subsystems, I have not strived to generalise here. Signed-off-by: Gerrit Renker Acked-by: Ian McDonald Signed-off-by: David S. Miller --- include/linux/dccp.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 7a0502ab383..7434a8353e2 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -355,14 +355,6 @@ static inline unsigned int dccp_hdr_len(const struct sk_buff *skb) return __dccp_hdr_len(dccp_hdr(skb)); } - -/* initial values for each feature */ -#define DCCPF_INITIAL_SEQUENCE_WINDOW 100 -#define DCCPF_INITIAL_ACK_RATIO 2 -#define DCCPF_INITIAL_CCID DCCPC_CCID2 -/* FIXME: for now we're default to 1 but it should really be 0 */ -#define DCCPF_INITIAL_SEND_NDP_COUNT 1 - /** * struct dccp_request_sock - represent DCCP-specific connection request * @dreq_inet_rsk: structure inherited from -- cgit v1.2.3 From 9f4d26d0f3016cf8813977d624751b94465fa317 Mon Sep 17 00:00:00 2001 From: Mark McLoughlin Date: Mon, 19 Jan 2009 17:09:49 -0800 Subject: virtio_net: add link status handling Allow the host to inform us that the link is down by adding a VIRTIO_NET_F_STATUS which indicates that device status is available in virtio_net config. This is currently useful for simulating link down conditions (e.g. using proposed qemu 'set_link' monitor command) but would also be needed if we were to support device assignment via virtio. Signed-off-by: Mark McLoughlin Signed-off-by: Rusty Russell (added future masking) Signed-off-by: David S. Miller --- include/linux/virtio_net.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 5cdd0aa8bde..f76bd4a753e 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -21,11 +21,16 @@ #define VIRTIO_NET_F_HOST_ECN 13 /* Host can handle TSO[6] w/ ECN in. */ #define VIRTIO_NET_F_HOST_UFO 14 /* Host can handle UFO in. */ #define VIRTIO_NET_F_MRG_RXBUF 15 /* Host can merge receive buffers. */ +#define VIRTIO_NET_F_STATUS 16 /* virtio_net_config.status available */ + +#define VIRTIO_NET_S_LINK_UP 1 /* Link is up */ struct virtio_net_config { /* The config defining mac address (if VIRTIO_NET_F_MAC) */ __u8 mac[6]; + /* See VIRTIO_NET_F_STATUS and VIRTIO_NET_S_* above */ + __u16 status; } __attribute__((packed)); /* This is the first element of the scatter-gather list. If you don't -- cgit v1.2.3 From 273ec51dd7ceaa76e038875d85061ec856d8905e Mon Sep 17 00:00:00 2001 From: Cyrill Gorcunov Date: Wed, 21 Jan 2009 15:55:35 -0800 Subject: net: ppp_generic - introduce net-namespace functionality v2 - Each namespace contains ppp channels and units separately with appropriate locks Signed-off-by: Cyrill Gorcunov Signed-off-by: David S. Miller --- include/linux/ppp_channel.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ppp_channel.h b/include/linux/ppp_channel.h index a942892d6df..9d64bdf1477 100644 --- a/include/linux/ppp_channel.h +++ b/include/linux/ppp_channel.h @@ -22,6 +22,7 @@ #include #include #include +#include struct ppp_channel; @@ -56,6 +57,9 @@ extern void ppp_input(struct ppp_channel *, struct sk_buff *); that we may have missed a packet. */ extern void ppp_input_error(struct ppp_channel *, int code); +/* Attach a channel to a given PPP unit in specified net. */ +extern int ppp_register_net_channel(struct net *, struct ppp_channel *); + /* Attach a channel to a given PPP unit. */ extern int ppp_register_channel(struct ppp_channel *); -- cgit v1.2.3 From d52a61c04c6c0814ca270a088feedb126436598e Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Thu, 22 Jan 2009 00:38:56 -0800 Subject: irq: clean up irq stat methods David Miller suggested, related to a kstat_irqs related build breakage: > Either linux/kernel_stat.h provides the kstat_incr_irqs_this_cpu > interface or linux/irq.h does, not both. So move them to kernel_stat.h. Signed-off-by: Ingo Molnar --- include/linux/irq.h | 6 ------ include/linux/kernel_stat.h | 9 ++++++--- 2 files changed, 6 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index e9a878978c8..48901e9a33b 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -202,12 +202,6 @@ extern struct irq_desc irq_desc[NR_IRQS]; extern struct irq_desc *move_irq_desc(struct irq_desc *old_desc, int cpu); #endif /* CONFIG_SPARSE_IRQ */ -#define kstat_irqs_this_cpu(DESC) \ - ((DESC)->kstat_irqs[smp_processor_id()]) -#define kstat_incr_irqs_this_cpu(irqno, DESC) \ - ((DESC)->kstat_irqs[smp_processor_id()]++) - - extern struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu); static inline struct irq_desc * diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h index a3431b164be..0c8b89f28a9 100644 --- a/include/linux/kernel_stat.h +++ b/include/linux/kernel_stat.h @@ -52,16 +52,19 @@ static inline void kstat_incr_irqs_this_cpu(unsigned int irq, { kstat_this_cpu.irqs[irq]++; } -#endif - -#ifndef CONFIG_GENERIC_HARDIRQS static inline unsigned int kstat_irqs_cpu(unsigned int irq, int cpu) { return kstat_cpu(cpu).irqs[irq]; } #else +#include extern unsigned int kstat_irqs_cpu(unsigned int irq, int cpu); +#define kstat_irqs_this_cpu(DESC) \ + ((DESC)->kstat_irqs[smp_processor_id()]) +#define kstat_incr_irqs_this_cpu(irqno, DESC) \ + ((DESC)->kstat_irqs[smp_processor_id()]++) + #endif /* -- cgit v1.2.3 From 5c0a66f5f3c9c59e2c341400048e2cff768e67a9 Mon Sep 17 00:00:00 2001 From: Benjamin Thery Date: Thu, 22 Jan 2009 04:56:17 +0000 Subject: netns: ipmr: store netns in struct mfc_cache This patch stores into struct mfc_cache the network namespace each mfc_cache belongs to. The new member is mfc_net. mfc_net is assigned at cache allocation and doesn't change during the rest of the cache entry life. A new net parameter is added to ipmr_cache_alloc/ipmr_cache_alloc_unres. This will help to retrieve the current netns around the IPv4 multicast routing code. At the moment, all mfc_cache are allocated in init_net. Signed-off-by: Benjamin Thery Signed-off-by: David S. Miller --- include/linux/mroute.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mroute.h b/include/linux/mroute.h index 8a455694d68..beaf3aae8aa 100644 --- a/include/linux/mroute.h +++ b/include/linux/mroute.h @@ -193,6 +193,9 @@ struct vif_device struct mfc_cache { struct mfc_cache *next; /* Next entry on cache line */ +#ifdef CONFIG_NET_NS + struct net *mfc_net; +#endif __be32 mfc_mcastgrp; /* Group the entry belongs to */ __be32 mfc_origin; /* Source of packet */ vifi_t mfc_parent; /* Source interface */ @@ -215,6 +218,18 @@ struct mfc_cache } mfc_un; }; +static inline +struct net *mfc_net(const struct mfc_cache *mfc) +{ + return read_pnet(&mfc->mfc_net); +} + +static inline +void mfc_net_set(struct mfc_cache *mfc, struct net *net) +{ + write_pnet(&mfc->mfc_net, hold_net(net)); +} + #define MFC_STATIC 1 #define MFC_NOTIFY 2 -- cgit v1.2.3 From 4feb88e5c694bfe414cbc3ce0e383f7f7038f90b Mon Sep 17 00:00:00 2001 From: Benjamin Thery Date: Thu, 22 Jan 2009 04:56:23 +0000 Subject: netns: ipmr: enable namespace support in ipv4 multicast routing code This last patch makes the appropriate changes to use and propagate the network namespace where needed in IPv4 multicast routing code. This consists mainly in replacing all the remaining init_net occurences with current netns pointer retrieved from sockets, net devices or mfc_caches depending on the routines' contexts. Some routines receive a new 'struct net' parameter to propagate the current netns: * vif_add/vif_delete * ipmr_new_tunnel * mroute_clean_tables * ipmr_cache_find * ipmr_cache_report * ipmr_cache_unresolved * ipmr_mfc_add/ipmr_mfc_delete * ipmr_get_route * rt_fill_info (in route.c) Signed-off-by: Benjamin Thery Signed-off-by: David S. Miller --- include/linux/mroute.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mroute.h b/include/linux/mroute.h index beaf3aae8aa..0d45b4e8d36 100644 --- a/include/linux/mroute.h +++ b/include/linux/mroute.h @@ -256,7 +256,8 @@ void mfc_net_set(struct mfc_cache *mfc, struct net *net) #ifdef __KERNEL__ struct rtmsg; -extern int ipmr_get_route(struct sk_buff *skb, struct rtmsg *rtm, int nowait); +extern int ipmr_get_route(struct net *net, struct sk_buff *skb, + struct rtmsg *rtm, int nowait); #endif #endif -- cgit v1.2.3 From fd8757aed16470e088ecdad96ffd30f86c34424d Mon Sep 17 00:00:00 2001 From: Matthew Ranostay Date: Wed, 21 Jan 2009 17:45:12 -0500 Subject: Add PCI DFI vendor ID Add a define for DFI PCI vendor id. Signed-off-by: Matthew Ranostay Signed-off-by: Takashi Iwai --- include/linux/pci_ids.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index d543365518a..6b339766b7a 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2106,6 +2106,8 @@ #define PCI_DEVICE_ID_MELLANOX_SINAI_OLD 0x5e8c #define PCI_DEVICE_ID_MELLANOX_SINAI 0x6274 +#define PCI_VENDOR_ID_DFI 0x15bd + #define PCI_VENDOR_ID_QUICKNET 0x15e2 #define PCI_DEVICE_ID_QUICKNET_XJ 0x0500 -- cgit v1.2.3 From 0db155de988031f925096a7df1bf9633790a2c18 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Fri, 23 Jan 2009 22:28:48 -0800 Subject: com20020: Fix allyesconfig build failure. Reported by Stephen Rothwell. Due to missing 'extern' in the com20020_netdev_ops declaration, each file that includes linux/com20020.h gets another copy defined in it's resulting object file. Signed-off-by: David S. Miller --- include/linux/com20020.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/com20020.h b/include/linux/com20020.h index 350afa773f8..5dcfb944b6c 100644 --- a/include/linux/com20020.h +++ b/include/linux/com20020.h @@ -29,7 +29,7 @@ int com20020_check(struct net_device *dev); int com20020_found(struct net_device *dev, int shared); -const struct net_device_ops com20020_netdev_ops; +extern const struct net_device_ops com20020_netdev_ops; /* The number of low I/O ports used by the card. */ #define ARCNET_TOTAL_SIZE 8 -- cgit v1.2.3 From d5a9e24afb4ab38110ebb777588ea0bd0eacbd0a Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 27 Jan 2009 16:22:11 -0800 Subject: net: Allow RX queue selection to seed TX queue hashing. The idea is that drivers which implement multiqueue RX pre-seed the SKB by recording the RX queue selected by the hardware. If such a seed is found on TX, we'll use that to select the outgoing TX queue. This helps get more consistent load balancing on router and firewall loads. Signed-off-by: David S. Miller --- include/linux/skbuff.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index cf2cb50f77d..a2c2378a9c5 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1904,6 +1904,21 @@ static inline void skb_copy_queue_mapping(struct sk_buff *to, const struct sk_bu to->queue_mapping = from->queue_mapping; } +static inline void skb_record_rx_queue(struct sk_buff *skb, u16 rx_queue) +{ + skb->queue_mapping = rx_queue + 1; +} + +static inline u16 skb_get_rx_queue(struct sk_buff *skb) +{ + return skb->queue_mapping - 1; +} + +static inline bool skb_rx_queue_recorded(struct sk_buff *skb) +{ + return (skb->queue_mapping != 0); +} + #ifdef CONFIG_XFRM static inline struct sec_path *skb_sec_path(struct sk_buff *skb) { -- cgit v1.2.3 From 598804cd041c395ce87302af9088b2f227196185 Mon Sep 17 00:00:00 2001 From: Anton Vorontsov Date: Fri, 9 Jan 2009 00:55:39 +0300 Subject: powerpc/fsl_pci: Add MPC83xx PCI-E controller RC mode support This patch adds support for PCI-Express controllers as found on the newer MPC83xx chips. The work is loosely based on the Tony Li's patch[1], but unlike the original patch, this patch implements sliding window for the Type 1 transactions using outbound window translations, so we don't have to ioremap the whole PCI-E configuration space. [1] http://ozlabs.org/pipermail/linuxppc-dev/2008-January/049028.html Signed-off-by: Tony Li Signed-off-by: Anton Vorontsov Signed-off-by: Kumar Gala --- include/linux/pci_ids.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index febc10ed385..ff9b7be2b79 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2217,6 +2217,14 @@ #define PCI_DEVICE_ID_TDI_EHCI 0x0101 #define PCI_VENDOR_ID_FREESCALE 0x1957 +#define PCI_DEVICE_ID_MPC8315E 0x00b4 +#define PCI_DEVICE_ID_MPC8315 0x00b5 +#define PCI_DEVICE_ID_MPC8314E 0x00b6 +#define PCI_DEVICE_ID_MPC8314 0x00b7 +#define PCI_DEVICE_ID_MPC8378E 0x00c4 +#define PCI_DEVICE_ID_MPC8378 0x00c5 +#define PCI_DEVICE_ID_MPC8377E 0x00c6 +#define PCI_DEVICE_ID_MPC8377 0x00c7 #define PCI_DEVICE_ID_MPC8548E 0x0012 #define PCI_DEVICE_ID_MPC8548 0x0013 #define PCI_DEVICE_ID_MPC8543E 0x0014 -- cgit v1.2.3 From 3fb1b6ad0679ad671bd496712b2a088550ee86b2 Mon Sep 17 00:00:00 2001 From: Magnus Damm Date: Thu, 22 Jan 2009 09:55:59 +0000 Subject: sh: CMT clockevent platform driver SuperH CMT clockevent driver. Both 16-bit and 32-bit CMT versions are supported, but only 32-bit is tested. This driver contains support for both clockevents and clocksources, but no unregistration is supported at this point. Works fine as clock source and/or event in periodic or oneshot mode. Tested on sh7722 and sh7723, but should work with any cpu/architecture. This version is lacking clocksource and early platform driver support for now - this to minimize the amount of dependencies. Signed-off-by: Magnus Damm Signed-off-by: Paul Mundt --- include/linux/sh_cmt.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) create mode 100644 include/linux/sh_cmt.h (limited to 'include/linux') diff --git a/include/linux/sh_cmt.h b/include/linux/sh_cmt.h new file mode 100644 index 00000000000..68cacde5954 --- /dev/null +++ b/include/linux/sh_cmt.h @@ -0,0 +1,13 @@ +#ifndef __SH_CMT_H__ +#define __SH_CMT_H__ + +struct sh_cmt_config { + char *name; + unsigned long channel_offset; + int timer_bit; + char *clk; + unsigned long clockevent_rating; + unsigned long clocksource_rating; +}; + +#endif /* __SH_CMT_H__ */ -- cgit v1.2.3 From d7ab5c46ae2743079a40bb4060e510418c0842b4 Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Wed, 28 Jan 2009 21:53:18 +0900 Subject: intel-iommu: make dma mapping functions static The dma ops unification enables X86 and IA64 to share intel_dma_ops so we can make dma mapping functions static. This also remove unused intel_map_single(). Signed-off-by: FUJITA Tomonori Signed-off-by: Ingo Molnar --- include/linux/intel-iommu.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index a254db1decd..43412aeddb5 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -330,13 +330,4 @@ extern int qi_flush_iotlb(struct intel_iommu *iommu, u16 did, u64 addr, extern void qi_submit_sync(struct qi_desc *desc, struct intel_iommu *iommu); -extern void *intel_alloc_coherent(struct device *, size_t, dma_addr_t *, gfp_t); -extern void intel_free_coherent(struct device *, size_t, void *, dma_addr_t); -extern dma_addr_t intel_map_single(struct device *, phys_addr_t, size_t, int); -extern void intel_unmap_single(struct device *, dma_addr_t, size_t, int); -extern int intel_map_sg(struct device *, struct scatterlist *, int, - enum dma_data_direction, struct dma_attrs *); -extern void intel_unmap_sg(struct device *, struct scatterlist *, int, - enum dma_data_direction, struct dma_attrs *); - #endif -- cgit v1.2.3 From 9ee677c2276bfcbcf68042ec2718a504af0c5fd7 Mon Sep 17 00:00:00 2001 From: David Kilroy Date: Tue, 23 Dec 2008 14:03:38 +0000 Subject: wireless: Add channel/frequency conversions to ieee80211.h Added mappings for FHSS, DSSS and OFDM channels - with macros to point HR DSSS and ERP to the DSSS mappings. Currently just static inline functions. Use the new functions in the older fullmac drivers. This eliminates a number of const static buffers and removes a couple of range checks that are now redundant. Signed-off-by: David Kilroy Acked-by: Arnaldo Carvalho de Melo Acked-by: Richard Farina Acked-by: Jeroen Vreeken Signed-off-by: John W. Linville --- include/linux/ieee80211.h | 116 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 116 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index c4e6ca1a630..cade2556af0 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1185,4 +1185,120 @@ static inline u8 *ieee80211_get_DA(struct ieee80211_hdr *hdr) return hdr->addr1; } +/** + * ieee80211_fhss_chan_to_freq - get channel frequency + * @channel: the FHSS channel + * + * Convert IEEE802.11 FHSS channel to frequency (MHz) + * Ref IEEE 802.11-2007 section 14.6 + */ +static inline int ieee80211_fhss_chan_to_freq(int channel) +{ + if ((channel > 1) && (channel < 96)) + return channel + 2400; + else + return -1; +} + +/** + * ieee80211_freq_to_fhss_chan - get channel + * @freq: the channels frequency + * + * Convert frequency (MHz) to IEEE802.11 FHSS channel + * Ref IEEE 802.11-2007 section 14.6 + */ +static inline int ieee80211_freq_to_fhss_chan(int freq) +{ + if ((freq > 2401) && (freq < 2496)) + return freq - 2400; + else + return -1; +} + +/** + * ieee80211_dsss_chan_to_freq - get channel center frequency + * @channel: the DSSS channel + * + * Convert IEEE802.11 DSSS channel to the center frequency (MHz). + * Ref IEEE 802.11-2007 section 15.6 + */ +static inline int ieee80211_dsss_chan_to_freq(int channel) +{ + if ((channel > 0) && (channel < 14)) + return 2407 + (channel * 5); + else if (channel == 14) + return 2484; + else + return -1; +} + +/** + * ieee80211_freq_to_dsss_chan - get channel + * @freq: the frequency + * + * Convert frequency (MHz) to IEEE802.11 DSSS channel + * Ref IEEE 802.11-2007 section 15.6 + * + * This routine selects the channel with the closest center frequency. + */ +static inline int ieee80211_freq_to_dsss_chan(int freq) +{ + if ((freq >= 2410) && (freq < 2475)) + return (freq - 2405) / 5; + else if ((freq >= 2482) && (freq < 2487)) + return 14; + else + return -1; +} + +/* Convert IEEE802.11 HR DSSS channel to frequency (MHz) and back + * Ref IEEE 802.11-2007 section 18.4.6.2 + * + * The channels and frequencies are the same as those defined for DSSS + */ +#define ieee80211_hr_chan_to_freq(chan) ieee80211_dsss_chan_to_freq(chan) +#define ieee80211_freq_to_hr_chan(freq) ieee80211_freq_to_dsss_chan(freq) + +/* Convert IEEE802.11 ERP channel to frequency (MHz) and back + * Ref IEEE 802.11-2007 section 19.4.2 + */ +#define ieee80211_erp_chan_to_freq(chan) ieee80211_hr_chan_to_freq(chan) +#define ieee80211_freq_to_erp_chan(freq) ieee80211_freq_to_hr_chan(freq) + +/** + * ieee80211_ofdm_chan_to_freq - get channel center frequency + * @s_freq: starting frequency == (dotChannelStartingFactor/2) MHz + * @channel: the OFDM channel + * + * Convert IEEE802.11 OFDM channel to center frequency (MHz) + * Ref IEEE 802.11-2007 section 17.3.8.3.2 + */ +static inline int ieee80211_ofdm_chan_to_freq(int s_freq, int channel) +{ + if ((channel > 0) && (channel <= 200) && + (s_freq >= 4000)) + return s_freq + (channel * 5); + else + return -1; +} + +/** + * ieee80211_freq_to_ofdm_channel - get channel + * @s_freq: starting frequency == (dotChannelStartingFactor/2) MHz + * @freq: the frequency + * + * Convert frequency (MHz) to IEEE802.11 OFDM channel + * Ref IEEE 802.11-2007 section 17.3.8.3.2 + * + * This routine selects the channel with the closest center frequency. + */ +static inline int ieee80211_freq_to_ofdm_chan(int s_freq, int freq) +{ + if ((freq > (s_freq + 2)) && (freq <= (s_freq + 1202)) && + (s_freq >= 4000)) + return (freq + 2 - s_freq) / 5; + else + return -1; +} + #endif /* LINUX_IEEE80211_H */ -- cgit v1.2.3 From 6b1c7c67603efdf0b39f6056989b0f8194cdc1f3 Mon Sep 17 00:00:00 2001 From: Michael Buesch Date: Thu, 25 Dec 2008 00:39:28 +0100 Subject: b43/ssb: Add SPROM8 extraction and LP-PHY detection This adds detection code for the LP-PHY and SPROM extraction code for version 8, which is needed by the LP-PHY and newer N-PHY. Signed-off-by: Michael Buesch Signed-off-by: John W. Linville --- include/linux/ssb/ssb_regs.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ssb/ssb_regs.h b/include/linux/ssb/ssb_regs.h index 99a0f991e85..a01b982b578 100644 --- a/include/linux/ssb/ssb_regs.h +++ b/include/linux/ssb/ssb_regs.h @@ -326,6 +326,42 @@ #define SSB_SPROM5_GPIOB_P3 0xFF00 /* Pin 3 */ #define SSB_SPROM5_GPIOB_P3_SHIFT 8 +/* SPROM Revision 8 */ +#define SSB_SPROM8_BFLLO 0x1084 /* Boardflags (low 16 bits) */ +#define SSB_SPROM8_BFLHI 0x1086 /* Boardflags Hi */ +#define SSB_SPROM8_IL0MAC 0x108C /* 6 byte MAC address */ +#define SSB_SPROM8_CCODE 0x1092 /* 2 byte country code */ +#define SSB_SPROM8_ANTAVAIL 0x109C /* Antenna available bitfields*/ +#define SSB_SPROM8_ANTAVAIL_A 0xFF00 /* A-PHY bitfield */ +#define SSB_SPROM8_ANTAVAIL_A_SHIFT 8 +#define SSB_SPROM8_ANTAVAIL_BG 0x00FF /* B-PHY and G-PHY bitfield */ +#define SSB_SPROM8_ANTAVAIL_BG_SHIFT 0 +#define SSB_SPROM8_AGAIN01 0x109E /* Antenna Gain (in dBm Q5.2) */ +#define SSB_SPROM8_AGAIN0 0x00FF /* Antenna 0 */ +#define SSB_SPROM8_AGAIN0_SHIFT 0 +#define SSB_SPROM8_AGAIN1 0xFF00 /* Antenna 1 */ +#define SSB_SPROM8_AGAIN1_SHIFT 8 +#define SSB_SPROM8_AGAIN23 0x10A0 +#define SSB_SPROM8_AGAIN2 0x00FF /* Antenna 2 */ +#define SSB_SPROM8_AGAIN2_SHIFT 0 +#define SSB_SPROM8_AGAIN3 0xFF00 /* Antenna 3 */ +#define SSB_SPROM8_AGAIN3_SHIFT 8 +#define SSB_SPROM8_GPIOA 0x1096 /*Gen. Purpose IO # 0 and 1 */ +#define SSB_SPROM8_GPIOA_P0 0x00FF /* Pin 0 */ +#define SSB_SPROM8_GPIOA_P1 0xFF00 /* Pin 1 */ +#define SSB_SPROM8_GPIOA_P1_SHIFT 8 +#define SSB_SPROM8_GPIOB 0x1098 /* Gen. Purpose IO # 2 and 3 */ +#define SSB_SPROM8_GPIOB_P2 0x00FF /* Pin 2 */ +#define SSB_SPROM8_GPIOB_P3 0xFF00 /* Pin 3 */ +#define SSB_SPROM8_GPIOB_P3_SHIFT 8 +#define SSB_SPROM8_MAXP_BG 0x10C0 /* Max Power BG in path 1 */ +#define SSB_SPROM8_MAXP_BG_MASK 0x00FF /* Mask for Max Power BG */ +#define SSB_SPROM8_ITSSI_BG 0xFF00 /* Mask for path 1 itssi_bg */ +#define SSB_SPROM8_ITSSI_BG_SHIFT 8 +#define SSB_SPROM8_MAXP_A 0x10C8 /* Max Power A in path 1 */ +#define SSB_SPROM8_MAXP_A_MASK 0x00FF /* Mask for Max Power A */ +#define SSB_SPROM8_ITSSI_A 0xFF00 /* Mask for path 1 itssi_a */ +#define SSB_SPROM8_ITSSI_A_SHIFT 8 /* Values for SSB_SPROM1_BINF_CCODE */ enum { -- cgit v1.2.3 From 63649b6cf0a964582af2b4d4734e28ca90ec8f5c Mon Sep 17 00:00:00 2001 From: Bob Copeland Date: Thu, 1 Jan 2009 15:01:44 -0500 Subject: ath5k: support LEDs on Acer Aspire One netbook Add vendor ID for Foxconn and use it to set the ath5k LED gpio and polarity for Acer branded laptops. base.c: Changes-licensed-under: 3-Clause-BSD Reported-by: Maxim Levitsky Tested-by: Maxim Levitsky Tested-by: Andreas Mohr Signed-off-by: Bob Copeland Signed-off-by: John W. Linville --- include/linux/pci_ids.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 302423afa13..5b7a48c1d61 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -834,6 +834,8 @@ #define PCI_DEVICE_ID_PROMISE_20276 0x5275 #define PCI_DEVICE_ID_PROMISE_20277 0x7275 +#define PCI_VENDOR_ID_FOXCONN 0x105b + #define PCI_VENDOR_ID_UMC 0x1060 #define PCI_DEVICE_ID_UMC_UM8673F 0x0101 #define PCI_DEVICE_ID_UMC_UM8886BF 0x673a -- cgit v1.2.3 From 5394af4d86ae51b369ff243c3f75b6f9a74e164b Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Thu, 8 Jan 2009 13:31:59 +0200 Subject: mac80211: 802.11w - STA flag for MFP Add flags for setting STA entries and struct ieee80211_if_sta to indicate whether management frame protection (MFP) is used. Signed-off-by: Jouni Malinen Acked-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/nl80211.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index e86ed59f9ad..218f0e73a7a 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -412,12 +412,14 @@ enum nl80211_iftype { * @NL80211_STA_FLAG_SHORT_PREAMBLE: station is capable of receiving frames * with short barker preamble * @NL80211_STA_FLAG_WME: station is WME/QoS capable + * @NL80211_STA_FLAG_MFP: station uses management frame protection */ enum nl80211_sta_flags { __NL80211_STA_FLAG_INVALID, NL80211_STA_FLAG_AUTHORIZED, NL80211_STA_FLAG_SHORT_PREAMBLE, NL80211_STA_FLAG_WME, + NL80211_STA_FLAG_MFP, /* keep last */ __NL80211_STA_FLAG_AFTER_LAST, -- cgit v1.2.3 From fb7333367632c67d8b6b06fb8d906cdabb11b02a Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Thu, 8 Jan 2009 13:32:00 +0200 Subject: mac80211: 802.11w - CCMP for management frames Extend CCMP to support encryption and decryption of unicast management frames. Signed-off-by: Jouni Malinen Acked-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/ieee80211.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index cade2556af0..d5165895f31 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1030,6 +1030,7 @@ enum ieee80211_category { WLAN_CATEGORY_QOS = 1, WLAN_CATEGORY_DLS = 2, WLAN_CATEGORY_BACK = 3, + WLAN_CATEGORY_PUBLIC = 4, WLAN_CATEGORY_WMM = 17, }; @@ -1185,6 +1186,35 @@ static inline u8 *ieee80211_get_DA(struct ieee80211_hdr *hdr) return hdr->addr1; } +/** + * ieee80211_is_robust_mgmt_frame - check if frame is a robust management frame + * @hdr: the frame (buffer must include at least the first octet of payload) + */ +static inline bool ieee80211_is_robust_mgmt_frame(struct ieee80211_hdr *hdr) +{ + if (ieee80211_is_disassoc(hdr->frame_control) || + ieee80211_is_deauth(hdr->frame_control)) + return true; + + if (ieee80211_is_action(hdr->frame_control)) { + u8 *category; + + /* + * Action frames, excluding Public Action frames, are Robust + * Management Frames. However, if we are looking at a Protected + * frame, skip the check since the data may be encrypted and + * the frame has already been found to be a Robust Management + * Frame (by the other end). + */ + if (ieee80211_has_protected(hdr->frame_control)) + return true; + category = ((u8 *) hdr) + 24; + return *category != WLAN_CATEGORY_PUBLIC; + } + + return false; +} + /** * ieee80211_fhss_chan_to_freq - get channel frequency * @channel: the FHSS channel -- cgit v1.2.3 From 765cb46a3fc856245ea68a7c961ac87c77e4ae2d Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Thu, 8 Jan 2009 13:32:01 +0200 Subject: mac80211: 802.11w - Add BIP (AES-128-CMAC) Implement Broadcast/Multicast Integrity Protocol for management frame protection. This patch adds the needed definitions for the new information element (MMIE) and implementation for the new "encryption" type (though, BIP is actually not encrypting data, it provides only integrity protection). These routines will be used by a follow-on patch that enables BIP for multicast/broadcast robust management frames. Signed-off-by: Jouni Malinen Acked-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/ieee80211.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index d5165895f31..cceb9e86c74 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -655,6 +655,15 @@ struct ieee80211_mgmt { #define IEEE80211_MIN_ACTION_SIZE offsetof(struct ieee80211_mgmt, u.action.u) +/* Management MIC information element (IEEE 802.11w) */ +struct ieee80211_mmie { + u8 element_id; + u8 length; + __le16 key_id; + u8 sequence_number[6]; + u8 mic[8]; +} __attribute__ ((packed)); + /* Control frames */ struct ieee80211_rts { __le16 frame_control; @@ -1018,6 +1027,7 @@ enum ieee80211_eid { WLAN_EID_HT_INFORMATION = 61, /* 802.11i */ WLAN_EID_RSN = 48, + WLAN_EID_MMIE = 76 /* 802.11w */, WLAN_EID_WPA = 221, WLAN_EID_GENERIC = 221, WLAN_EID_VENDOR_SPECIFIC = 221, -- cgit v1.2.3 From 3cfcf6ac6d69dc290e96416731eea5c88ac7d426 Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Thu, 8 Jan 2009 13:32:02 +0200 Subject: mac80211: 802.11w - Use BIP (AES-128-CMAC) Add mechanism for managing BIP keys (IGTK) and integrate BIP into the TX/RX paths. Signed-off-by: Jouni Malinen Acked-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/ieee80211.h | 1 + include/linux/nl80211.h | 6 ++++-- 2 files changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index cceb9e86c74..df98a8a549a 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1139,6 +1139,7 @@ enum ieee80211_back_parties { /* reserved: 0x000FAC03 */ #define WLAN_CIPHER_SUITE_CCMP 0x000FAC04 #define WLAN_CIPHER_SUITE_WEP104 0x000FAC05 +#define WLAN_CIPHER_SUITE_AES_CMAC 0x000FAC06 #define WLAN_MAX_KEY_LEN 32 diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 218f0e73a7a..ee742bc9761 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -72,8 +72,8 @@ * * @NL80211_CMD_GET_KEY: Get sequence counter information for a key specified * by %NL80211_ATTR_KEY_IDX and/or %NL80211_ATTR_MAC. - * @NL80211_CMD_SET_KEY: Set key attributes %NL80211_ATTR_KEY_DEFAULT or - * %NL80211_ATTR_KEY_THRESHOLD. + * @NL80211_CMD_SET_KEY: Set key attributes %NL80211_ATTR_KEY_DEFAULT, + * %NL80211_ATTR_KEY_DEFAULT_MGMT, or %NL80211_ATTR_KEY_THRESHOLD. * @NL80211_CMD_NEW_KEY: add a key with given %NL80211_ATTR_KEY_DATA, * %NL80211_ATTR_KEY_IDX, %NL80211_ATTR_MAC and %NL80211_ATTR_KEY_CIPHER * attributes. @@ -346,6 +346,8 @@ enum nl80211_attrs { NL80211_ATTR_WIPHY_FREQ, NL80211_ATTR_WIPHY_CHANNEL_TYPE, + NL80211_ATTR_KEY_DEFAULT_MGMT, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, -- cgit v1.2.3 From 54604d3a827b37525ef017adba313c7112e0f484 Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Thu, 8 Jan 2009 13:32:03 +0200 Subject: mac80211: 802.11w - WEXT parameter for setting mgmt cipher Add a new IW_AUTH parameter for setting cipher suite for multicast/broadcast management frames. This is for full-mac drivers that take care of RSN IE generation for (re)association request frames. Signed-off-by: Jouni Malinen Acked-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/wireless.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/wireless.h b/include/linux/wireless.h index d7958f9b52c..d426dce47e7 100644 --- a/include/linux/wireless.h +++ b/include/linux/wireless.h @@ -577,18 +577,21 @@ #define IW_AUTH_RX_UNENCRYPTED_EAPOL 8 #define IW_AUTH_ROAMING_CONTROL 9 #define IW_AUTH_PRIVACY_INVOKED 10 +#define IW_AUTH_CIPHER_GROUP_MGMT 11 /* IW_AUTH_WPA_VERSION values (bit field) */ #define IW_AUTH_WPA_VERSION_DISABLED 0x00000001 #define IW_AUTH_WPA_VERSION_WPA 0x00000002 #define IW_AUTH_WPA_VERSION_WPA2 0x00000004 -/* IW_AUTH_PAIRWISE_CIPHER and IW_AUTH_GROUP_CIPHER values (bit field) */ +/* IW_AUTH_PAIRWISE_CIPHER, IW_AUTH_GROUP_CIPHER, and IW_AUTH_CIPHER_GROUP_MGMT + * values (bit field) */ #define IW_AUTH_CIPHER_NONE 0x00000001 #define IW_AUTH_CIPHER_WEP40 0x00000002 #define IW_AUTH_CIPHER_TKIP 0x00000004 #define IW_AUTH_CIPHER_CCMP 0x00000008 #define IW_AUTH_CIPHER_WEP104 0x00000010 +#define IW_AUTH_CIPHER_AES_CMAC 0x00000020 /* IW_AUTH_KEY_MGMT values (bit field) */ #define IW_AUTH_KEY_MGMT_802_1X 1 -- cgit v1.2.3 From 22787dbaa3b952602542506e0426ea6d5f104042 Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Thu, 8 Jan 2009 13:32:04 +0200 Subject: mac80211: 802.11w - WEXT configuration for IGTK Added new SIOCSIWENCODEEXT algorithm for configuring BIP (AES-CMAC) keys (IGTK). Signed-off-by: Jouni Malinen Acked-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/wireless.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/wireless.h b/include/linux/wireless.h index d426dce47e7..5d1f3fbffd7 100644 --- a/include/linux/wireless.h +++ b/include/linux/wireless.h @@ -615,6 +615,7 @@ #define IW_ENCODE_ALG_TKIP 2 #define IW_ENCODE_ALG_CCMP 3 #define IW_ENCODE_ALG_PMK 4 +#define IW_ENCODE_ALG_AES_CMAC 5 /* struct iw_encode_ext ->ext_flags */ #define IW_ENCODE_EXT_TX_SEQ_VALID 0x00000001 #define IW_ENCODE_EXT_RX_SEQ_VALID 0x00000002 -- cgit v1.2.3 From fdfacf0ae2e8339098b1164d2317b792d7662c0a Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Thu, 8 Jan 2009 13:32:05 +0200 Subject: mac80211: 802.11w - Configuration of MFP disabled/optional/required Add new WEXT IW_AUTH_* parameter for setting MFP disabled/optional/required. Signed-off-by: Jouni Malinen Acked-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/wireless.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/wireless.h b/include/linux/wireless.h index 5d1f3fbffd7..cb24204851f 100644 --- a/include/linux/wireless.h +++ b/include/linux/wireless.h @@ -578,6 +578,7 @@ #define IW_AUTH_ROAMING_CONTROL 9 #define IW_AUTH_PRIVACY_INVOKED 10 #define IW_AUTH_CIPHER_GROUP_MGMT 11 +#define IW_AUTH_MFP 12 /* IW_AUTH_WPA_VERSION values (bit field) */ #define IW_AUTH_WPA_VERSION_DISABLED 0x00000001 @@ -607,6 +608,11 @@ #define IW_AUTH_ROAMING_DISABLE 1 /* user space program used for roaming * control */ +/* IW_AUTH_MFP (management frame protection) values */ +#define IW_AUTH_MFP_DISABLED 0 /* MFP disabled */ +#define IW_AUTH_MFP_OPTIONAL 1 /* MFP optional */ +#define IW_AUTH_MFP_REQUIRED 2 /* MFP required */ + /* SIOCSIWENCODEEXT definitions */ #define IW_ENCODE_SEQ_MAX_SIZE 8 /* struct iw_encode_ext ->alg */ -- cgit v1.2.3 From fea147328908b7e2bfcaf9dc4377909d5507ca35 Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Thu, 8 Jan 2009 13:32:06 +0200 Subject: mac80211: 802.11w - SA Query processing Process SA Query Requests for client mode in mac80211. AP side processing of SA Query Response frames is in user space (hostapd). Signed-off-by: Jouni Malinen Acked-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/ieee80211.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index df98a8a549a..9fe1948d28d 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -527,6 +527,8 @@ struct ieee80211_tim_ie { u8 virtual_map[0]; } __attribute__ ((packed)); +#define WLAN_SA_QUERY_TR_ID_LEN 16 + struct ieee80211_mgmt { __le16 frame_control; __le16 duration; @@ -646,6 +648,10 @@ struct ieee80211_mgmt { u8 action_code; u8 variable[0]; } __attribute__((packed)) mesh_action; + struct { + u8 action; + u8 trans_id[WLAN_SA_QUERY_TR_ID_LEN]; + } __attribute__ ((packed)) sa_query; } u; } __attribute__ ((packed)) action; } u; @@ -1041,6 +1047,7 @@ enum ieee80211_category { WLAN_CATEGORY_DLS = 2, WLAN_CATEGORY_BACK = 3, WLAN_CATEGORY_PUBLIC = 4, + WLAN_CATEGORY_SA_QUERY = 8, WLAN_CATEGORY_WMM = 17, }; @@ -1129,6 +1136,13 @@ enum ieee80211_back_parties { WLAN_BACK_TIMER = 2, }; +/* SA Query action */ +enum ieee80211_sa_query_action { + WLAN_ACTION_SA_QUERY_REQUEST = 0, + WLAN_ACTION_SA_QUERY_RESPONSE = 1, +}; + + /* A-MSDU 802.11n */ #define IEEE80211_QOS_CONTROL_A_MSDU_PRESENT 0x0080 -- cgit v1.2.3 From 63a5ab82255a4ff5d0783f16427210f1d45d7ec8 Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Thu, 8 Jan 2009 13:32:09 +0200 Subject: mac80211: 802.11w - Implement Association Comeback processing When MFP is enabled, the AP does not allow a STA to associate if an existing security association exists without first going through SA Query process. When this happens, the association request is denied with a new status code ("temporarily rejected") ans Association Comeback IE is used to notify when the association may be tried again (i.e., when the SA Query procedure has timed out). Use the comeback time to update the mac80211 client MLME timer for next association attempt to minimize waiting time if association is temporarily rejected. Signed-off-by: Jouni Malinen Acked-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/ieee80211.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 9fe1948d28d..7800e20f197 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -914,6 +914,9 @@ enum ieee80211_statuscode { /* 802.11g */ WLAN_STATUS_ASSOC_DENIED_NOSHORTTIME = 25, WLAN_STATUS_ASSOC_DENIED_NODSSSOFDM = 26, + /* 802.11w */ + WLAN_STATUS_ASSOC_REJECTED_TEMPORARILY = 30, + WLAN_STATUS_ROBUST_MGMT_FRAME_POLICY_VIOLATION = 31, /* 802.11i */ WLAN_STATUS_INVALID_IE = 40, WLAN_STATUS_INVALID_GROUP_CIPHER = 41, @@ -1034,6 +1037,7 @@ enum ieee80211_eid { /* 802.11i */ WLAN_EID_RSN = 48, WLAN_EID_MMIE = 76 /* 802.11w */, + WLAN_EID_ASSOC_COMEBACK_TIME = 77, WLAN_EID_WPA = 221, WLAN_EID_GENERIC = 221, WLAN_EID_VENDOR_SPECIFIC = 221, -- cgit v1.2.3 From d2b21f191753abd12c4063776cb1a3d635397509 Mon Sep 17 00:00:00 2001 From: Colin McCabe Date: Fri, 9 Jan 2009 14:58:09 -0800 Subject: libertas: if_spi, driver for libertas GSPI devices Add initial support for libertas devices using a GSPI interface. This has been tested with the 8686. GSPI is intended to be used on embedded systems. Board-specific parameters are required (see libertas_spi.h). Thanks to everyone who took a look at the earlier versions of the patch. Signed-off-by: Colin McCabe Signed-off-by: Andrey Yurovsky Acked-by: Dan Williams Signed-off-by: John W. Linville --- include/linux/spi/libertas_spi.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) create mode 100644 include/linux/spi/libertas_spi.h (limited to 'include/linux') diff --git a/include/linux/spi/libertas_spi.h b/include/linux/spi/libertas_spi.h new file mode 100644 index 00000000000..ada71b4f378 --- /dev/null +++ b/include/linux/spi/libertas_spi.h @@ -0,0 +1,25 @@ +/* + * board-specific data for the libertas_spi driver. + * + * Copyright 2008 Analog Devices Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or (at + * your option) any later version. + */ +#ifndef _LIBERTAS_SPI_H_ +#define _LIBERTAS_SPI_H_ +struct libertas_spi_platform_data { + /* There are two ways to read data from the WLAN module's SPI + * interface. Setting 0 or 1 here controls which one is used. + * + * Usually you want to set use_dummy_writes = 1. + * However, if that doesn't work or if you are using a slow SPI clock + * speed, you may want to use 0 here. */ + u16 use_dummy_writes; + + /* GPIO number to use as chip select */ + u16 gpio_cs; +}; +#endif -- cgit v1.2.3 From d03415e6771cd709b2b2ec64d3e6315cc3ebfa74 Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Mon, 12 Jan 2009 14:24:40 +0200 Subject: nl80211: Fix documentation errors Couple of '_ATTR's were missing and SEC_CHAN_OFFSET to CHANNEL_TYPE rename was missed in couple of places. Signed-off-by: Jouni Malinen Acked-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/nl80211.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index ee742bc9761..4e7a7986a52 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -47,7 +47,7 @@ * @NL80211_CMD_SET_WIPHY: set wiphy parameters, needs %NL80211_ATTR_WIPHY or * %NL80211_ATTR_IFINDEX; can be used to set %NL80211_ATTR_WIPHY_NAME, * %NL80211_ATTR_WIPHY_TXQ_PARAMS, %NL80211_ATTR_WIPHY_FREQ, and/or - * %NL80211_ATTR_WIPHY_SEC_CHAN_OFFSET. + * %NL80211_ATTR_WIPHY_CHANNEL_TYPE. * @NL80211_CMD_NEW_WIPHY: Newly created wiphy, response to get request * or rename notification. Has attributes %NL80211_ATTR_WIPHY and * %NL80211_ATTR_WIPHY_NAME. @@ -84,7 +84,7 @@ * %NL80222_CMD_NEW_BEACON message) * @NL80211_CMD_SET_BEACON: set the beacon on an access point interface * using the %NL80211_ATTR_BEACON_INTERVAL, %NL80211_ATTR_DTIM_PERIOD, - * %NL80211_BEACON_HEAD and %NL80211_BEACON_TAIL attributes. + * %NL80211_ATTR_BEACON_HEAD and %NL80211_ATTR_BEACON_TAIL attributes. * @NL80211_CMD_NEW_BEACON: add a new beacon to an access point interface, * parameters are like for %NL80211_CMD_SET_BEACON. * @NL80211_CMD_DEL_BEACON: remove the beacon, stop sending it @@ -362,7 +362,7 @@ enum nl80211_attrs { #define NL80211_ATTR_BSS_BASIC_RATES NL80211_ATTR_BSS_BASIC_RATES #define NL80211_ATTR_WIPHY_TXQ_PARAMS NL80211_ATTR_WIPHY_TXQ_PARAMS #define NL80211_ATTR_WIPHY_FREQ NL80211_ATTR_WIPHY_FREQ -#define NL80211_ATTR_WIPHY_SEC_CHAN_OFFSET NL80211_ATTR_WIPHY_SEC_CHAN_OFFSET +#define NL80211_ATTR_WIPHY_CHANNEL_TYPE NL80211_ATTR_WIPHY_CHANNEL_TYPE #define NL80211_MAX_SUPP_RATES 32 #define NL80211_MAX_SUPP_REG_RULES 32 -- cgit v1.2.3 From 9dbeb91a8b97e2892c04461e28d2bdd0198b719d Mon Sep 17 00:00:00 2001 From: Gabor Juhos Date: Wed, 14 Jan 2009 20:17:08 +0100 Subject: ath9k: get EEPROM contents from platform data on AHB bus On the AR913x SOCs we have to provide EEPROM contents via platform_data, because accessing the flash via MMIO is not safe. Additionally different boards may store the radio calibration data at different locations. Changes-licensed-under: ISC Signed-off-by: Gabor Juhos Signed-off-by: Imre Kaloz Tested-by: Pavel Roskin Signed-off-by: John W. Linville --- include/linux/ath9k_platform.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) create mode 100644 include/linux/ath9k_platform.h (limited to 'include/linux') diff --git a/include/linux/ath9k_platform.h b/include/linux/ath9k_platform.h new file mode 100644 index 00000000000..b847fc7b93f --- /dev/null +++ b/include/linux/ath9k_platform.h @@ -0,0 +1,28 @@ +/* + * Copyright (c) 2008 Atheros Communications Inc. + * Copyright (c) 2009 Gabor Juhos + * Copyright (c) 2009 Imre Kaloz + * + * Permission to use, copy, modify, and/or distribute this software for any + * purpose with or without fee is hereby granted, provided that the above + * copyright notice and this permission notice appear in all copies. + * + * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES + * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF + * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR + * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES + * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN + * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF + * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. + */ + +#ifndef _LINUX_ATH9K_PLATFORM_H +#define _LINUX_ATH9K_PLATFORM_H + +#define ATH9K_PLAT_EEP_MAX_WORDS 2048 + +struct ath9k_platform_data { + u16 eeprom_data[ATH9K_PLAT_EEP_MAX_WORDS]; +}; + +#endif /* _LINUX_ATH9K_PLATFORM_H */ -- cgit v1.2.3 From 9aed3cc124343d92be6697e9af3928bdfe8eb03e Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Tue, 13 Jan 2009 16:03:29 +0200 Subject: nl80211: New command for adding extra IE(s) into management frames A new nl80211 command, NL80211_CMD_SET_MGMT_EXTRA_IE, can be used to add arbitrary IE data into the end of management frames. The interface allows extra IEs to be configured for each management frame subtype, but only some of them (ProbeReq, ProbeResp, Auth, (Re)AssocReq, Deauth, Disassoc) are currently accepted in mac80211 implementation. This makes it easier to implement IEEE 802.11 extensions like WPS and FT that add IE(s) into some management frames. In addition, this can be useful for testing and experimentation purposes. Signed-off-by: Jouni Malinen Acked-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/nl80211.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 4e7a7986a52..76aae3d8e97 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -133,6 +133,14 @@ * @NL80211_CMD_SET_MESH_PARAMS: Set mesh networking properties for the * interface identified by %NL80211_ATTR_IFINDEX * + * @NL80211_CMD_SET_MGMT_EXTRA_IE: Set extra IEs for management frames. The + * interface is identified with %NL80211_ATTR_IFINDEX and the management + * frame subtype with %NL80211_ATTR_MGMT_SUBTYPE. The extra IE data to be + * added to the end of the specified management frame is specified with + * %NL80211_ATTR_IE. If the command succeeds, the requested data will be + * added to all specified management frames generated by + * kernel/firmware/driver. + * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use */ @@ -178,6 +186,8 @@ enum nl80211_commands { NL80211_CMD_GET_MESH_PARAMS, NL80211_CMD_SET_MESH_PARAMS, + NL80211_CMD_SET_MGMT_EXTRA_IE, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ @@ -190,6 +200,7 @@ enum nl80211_commands { * here */ #define NL80211_CMD_SET_BSS NL80211_CMD_SET_BSS +#define NL80211_CMD_SET_MGMT_EXTRA_IE NL80211_CMD_SET_MGMT_EXTRA_IE /** * enum nl80211_attrs - nl80211 netlink attributes @@ -284,6 +295,12 @@ enum nl80211_commands { * supported interface types, each a flag attribute with the number * of the interface mode. * + * @NL80211_ATTR_MGMT_SUBTYPE: Management frame subtype for + * %NL80211_CMD_SET_MGMT_EXTRA_IE. + * + * @NL80211_ATTR_IE: Information element(s) data (used, e.g., with + * %NL80211_CMD_SET_MGMT_EXTRA_IE). + * * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use */ @@ -348,6 +365,9 @@ enum nl80211_attrs { NL80211_ATTR_KEY_DEFAULT_MGMT, + NL80211_ATTR_MGMT_SUBTYPE, + NL80211_ATTR_IE, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -363,6 +383,8 @@ enum nl80211_attrs { #define NL80211_ATTR_WIPHY_TXQ_PARAMS NL80211_ATTR_WIPHY_TXQ_PARAMS #define NL80211_ATTR_WIPHY_FREQ NL80211_ATTR_WIPHY_FREQ #define NL80211_ATTR_WIPHY_CHANNEL_TYPE NL80211_ATTR_WIPHY_CHANNEL_TYPE +#define NL80211_ATTR_MGMT_SUBTYPE NL80211_ATTR_MGMT_SUBTYPE +#define NL80211_ATTR_IE NL80211_ATTR_IE #define NL80211_MAX_SUPP_RATES 32 #define NL80211_MAX_SUPP_REG_RULES 32 -- cgit v1.2.3 From f797eb7e2903571e9c0e7e5d64113f51209f8dc4 Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Mon, 19 Jan 2009 18:48:46 +0200 Subject: mac80211: Fix MFP Association Comeback to use Timeout Interval IE The separate Association Comeback Time IE was removed from IEEE 802.11w and the Timeout Interval IE (from IEEE 802.11r) is used instead. The editing on this is still somewhat incomplete in IEEE 802.11w/D7.0, but still, the use of Timeout Interval IE is the expected mechanism. Signed-off-by: Jouni Malinen Signed-off-by: John W. Linville --- include/linux/ieee80211.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 7800e20f197..b1bb817d142 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1036,8 +1036,8 @@ enum ieee80211_eid { WLAN_EID_HT_INFORMATION = 61, /* 802.11i */ WLAN_EID_RSN = 48, + WLAN_EID_TIMEOUT_INTERVAL = 56, WLAN_EID_MMIE = 76 /* 802.11w */, - WLAN_EID_ASSOC_COMEBACK_TIME = 77, WLAN_EID_WPA = 221, WLAN_EID_GENERIC = 221, WLAN_EID_VENDOR_SPECIFIC = 221, @@ -1126,6 +1126,12 @@ struct ieee80211_country_ie_triplet { }; } __attribute__ ((packed)); +enum ieee80211_timeout_interval_type { + WLAN_TIMEOUT_REASSOC_DEADLINE = 1 /* 802.11r */, + WLAN_TIMEOUT_KEY_LIFETIME = 2 /* 802.11r */, + WLAN_TIMEOUT_ASSOC_COMEBACK = 3 /* 802.11w */, +}; + /* BACK action code */ enum ieee80211_back_actioncode { WLAN_ACTION_ADDBA_REQ = 0, -- cgit v1.2.3 From f677d7702d48b7b3dfcce3b2c0db601dbee0aa24 Mon Sep 17 00:00:00 2001 From: Tulio Magno Quites Machado Filho Date: Sun, 25 Jan 2009 23:54:25 +0100 Subject: ath5k: support LED's on emachines E510 notebook Add vendor ID for AMBIT and use it to set the ath5k LED gpio. base.c: Changes-licensed-under: 3-Clause-BSD Signed-off-by: Tulio Magno Quites Machado Filho Acked-by: Bob Copeland Signed-off-by: John W. Linville --- include/linux/pci_ids.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 5b7a48c1d61..b7697c934a4 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1967,6 +1967,8 @@ #define PCI_VENDOR_ID_SAMSUNG 0x144d +#define PCI_VENDOR_ID_AMBIT 0x1468 + #define PCI_VENDOR_ID_MYRICOM 0x14c1 #define PCI_VENDOR_ID_TITAN 0x14D2 -- cgit v1.2.3 From 5d0d9be8ef456afc6c3fb5f8aad06ef19b704b05 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Thu, 29 Jan 2009 14:19:48 +0000 Subject: gro: Move common completion code into helpers Currently VLAN still has a bit of common code handling the aftermath of GRO that's shared with the common path. This patch moves them into shared helpers to reduce code duplication. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index dd8a35b3e8b..20419508eec 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1375,12 +1375,15 @@ extern int netif_receive_skb(struct sk_buff *skb); extern void napi_gro_flush(struct napi_struct *napi); extern int dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb); +extern int napi_skb_finish(int ret, struct sk_buff *skb); extern int napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb); extern void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb); extern struct sk_buff * napi_fraginfo_skb(struct napi_struct *napi, struct napi_gro_fraginfo *info); +extern int napi_frags_finish(struct napi_struct *napi, + struct sk_buff *skb, int ret); extern int napi_gro_frags(struct napi_struct *napi, struct napi_gro_fraginfo *info); extern void netif_nit_deliver(struct sk_buff *skb); -- cgit v1.2.3 From 86911732d3996a9da07914b280621450111bb6da Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Thu, 29 Jan 2009 14:19:50 +0000 Subject: gro: Avoid copying headers of unmerged packets Unfortunately simplicity isn't always the best. The fraginfo interface turned out to be suboptimal. The problem was quite obvious. For every packet, we have to copy the headers from the frags structure into skb->head, even though for 99% of the packets this part is immediately thrown away after the merge. LRO didn't have this problem because it directly read the headers from the frags structure. This patch attempts to address this by creating an interface that allows GRO to access the headers in the first frag without having to copy it. Because all drivers that use frags place the headers in the first frag this optimisation should be enough. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/netdevice.h | 26 ++++++++++++++++++++++++++ include/linux/skbuff.h | 2 -- 2 files changed, 26 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 20419508eec..7a5057fbb7c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -984,6 +984,9 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi, void netif_napi_del(struct napi_struct *napi); struct napi_gro_cb { + /* This indicates where we are processing relative to skb->data. */ + int data_offset; + /* This is non-zero if the packet may be of the same flow. */ int same_flow; @@ -1087,6 +1090,29 @@ extern int dev_restart(struct net_device *dev); #ifdef CONFIG_NETPOLL_TRAP extern int netpoll_trap(void); #endif +extern void *skb_gro_header(struct sk_buff *skb, unsigned int hlen); +extern int skb_gro_receive(struct sk_buff **head, + struct sk_buff *skb); + +static inline unsigned int skb_gro_offset(const struct sk_buff *skb) +{ + return NAPI_GRO_CB(skb)->data_offset; +} + +static inline unsigned int skb_gro_len(const struct sk_buff *skb) +{ + return skb->len - NAPI_GRO_CB(skb)->data_offset; +} + +static inline void skb_gro_pull(struct sk_buff *skb, unsigned int len) +{ + NAPI_GRO_CB(skb)->data_offset += len; +} + +static inline void skb_gro_reset_offset(struct sk_buff *skb) +{ + NAPI_GRO_CB(skb)->data_offset = 0; +} static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a2c2378a9c5..08670d01747 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1687,8 +1687,6 @@ extern int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen); extern struct sk_buff *skb_segment(struct sk_buff *skb, int features); -extern int skb_gro_receive(struct sk_buff **head, - struct sk_buff *skb); static inline void *skb_header_pointer(const struct sk_buff *skb, int offset, int len, void *buffer) -- cgit v1.2.3 From d23f028a4ddce8b783c212bfe911d1d307ff3617 Mon Sep 17 00:00:00 2001 From: Steve Glendinning Date: Tue, 27 Jan 2009 06:51:11 +0000 Subject: smsc911x: add external phy detection overrides On LAN9115/LAN9117/LAN9215/LAN9217, external phys are supported. These are usually indicated by a hardware strap which sets an "external PHY detected" bit in the HW_CFG register. In some cases it is desirable to override this hardware strap and force use of either the internal phy or an external PHY. This patch adds SMSC911X_FORCE_INTERNAL_PHY and SMSC911X_FORCE_EXTERNAL_PHY flags so a platform can indicate this preference via its platform_data. Signed-off-by: Steve Glendinning Acked-by: Sascha Hauer Tested-by: Sascha Hauer Signed-off-by: David S. Miller --- include/linux/smsc911x.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/smsc911x.h b/include/linux/smsc911x.h index 1cbf0313add..170c76b8f7a 100644 --- a/include/linux/smsc911x.h +++ b/include/linux/smsc911x.h @@ -43,5 +43,7 @@ struct smsc911x_platform_config { /* Constants for flags */ #define SMSC911X_USE_16BIT (BIT(0)) #define SMSC911X_USE_32BIT (BIT(1)) +#define SMSC911X_FORCE_INTERNAL_PHY (BIT(2)) +#define SMSC911X_FORCE_EXTERNAL_PHY (BIT(3)) #endif /* __LINUX_SMSC911X_H__ */ -- cgit v1.2.3 From 31f4574774e98aa275aeeee94f41ce042285ed8e Mon Sep 17 00:00:00 2001 From: Steve Glendinning Date: Tue, 27 Jan 2009 06:51:12 +0000 Subject: smsc911x: allow mac address to be saved before device reset Some platforms (for example pcm037) do not have an EEPROM fitted, instead storing their mac address somewhere else. The bootloader fetches this and configures the ethernet adapter before the kernel is started. This patch allows a platform to indicate to the driver via the SMSC911X_SAVE_MAC_ADDRESS flag that the mac address has already been configured via such a mechanism, and should be saved before resetting the chip. Signed-off-by: Steve Glendinning Acked-by: Sascha Hauer Tested-by: Sascha Hauer Signed-off-by: David S. Miller --- include/linux/smsc911x.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/smsc911x.h b/include/linux/smsc911x.h index 170c76b8f7a..b32725075d7 100644 --- a/include/linux/smsc911x.h +++ b/include/linux/smsc911x.h @@ -45,5 +45,6 @@ struct smsc911x_platform_config { #define SMSC911X_USE_32BIT (BIT(1)) #define SMSC911X_FORCE_INTERNAL_PHY (BIT(2)) #define SMSC911X_FORCE_EXTERNAL_PHY (BIT(3)) +#define SMSC911X_SAVE_MAC_ADDRESS (BIT(4)) #endif /* __LINUX_SMSC911X_H__ */ -- cgit v1.2.3 From eefef1cf7653cd4e0aaf743c00ae8345086cdc01 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Sun, 1 Feb 2009 01:04:33 -0800 Subject: net: add ARP notify option for devices This adds another inet device option to enable gratuitous ARP when device is brought up or address change. This is handy for clusters or virtualization. Signed-off-by: Stephen Hemminger Signed-off-by: Jeremy Fitzhardinge Signed-off-by: David S. Miller --- include/linux/inetdevice.h | 1 + include/linux/sysctl.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 06fcdb45106..acef2a770b6 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -108,6 +108,7 @@ static inline void ipv4_devconf_setall(struct in_device *in_dev) #define IN_DEV_ARPFILTER(in_dev) IN_DEV_ORCONF((in_dev), ARPFILTER) #define IN_DEV_ARP_ANNOUNCE(in_dev) IN_DEV_MAXCONF((in_dev), ARP_ANNOUNCE) #define IN_DEV_ARP_IGNORE(in_dev) IN_DEV_MAXCONF((in_dev), ARP_IGNORE) +#define IN_DEV_ARP_NOTIFY(in_dev) IN_DEV_MAXCONF((in_dev), ARP_NOTIFY) struct in_ifaddr { diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 39d471d1163..e76d3b22a46 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -490,6 +490,7 @@ enum NET_IPV4_CONF_ARP_IGNORE=19, NET_IPV4_CONF_PROMOTE_SECONDARIES=20, NET_IPV4_CONF_ARP_ACCEPT=21, + NET_IPV4_CONF_ARP_NOTIFY=22, __NET_IPV4_CONF_MAX }; -- cgit v1.2.3 From 659aaf2bb5496a425ba14036b5b5900f593e4484 Mon Sep 17 00:00:00 2001 From: Rajiv Andrade Date: Mon, 2 Feb 2009 15:23:44 -0200 Subject: TPM: integrity interface This patch adds internal kernel support for: - reading/extending a pcr value - looking up the tpm_chip for a given chip number Signed-off-by: Rajiv Andrade Signed-off-by: Mimi Zohar Signed-off-by: James Morris --- include/linux/tpm.h | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) create mode 100644 include/linux/tpm.h (limited to 'include/linux') diff --git a/include/linux/tpm.h b/include/linux/tpm.h new file mode 100644 index 00000000000..3338b3f5c21 --- /dev/null +++ b/include/linux/tpm.h @@ -0,0 +1,35 @@ +/* + * Copyright (C) 2004,2007,2008 IBM Corporation + * + * Authors: + * Leendert van Doorn + * Dave Safford + * Reiner Sailer + * Kylene Hall + * Debora Velarde + * + * Maintained by: + * + * Device driver for TCG/TCPA TPM (trusted platform module). + * Specifications at www.trustedcomputinggroup.org + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation, version 2 of the + * License. + * + */ +#ifndef __LINUX_TPM_H__ +#define __LINUX_TPM_H__ + +/* + * Chip num is this value or a valid tpm idx + */ +#define TPM_ANY_NUM 0xFFFF + +#if defined(CONFIG_TCG_TPM) + +extern int tpm_pcr_read(u32 chip_num, int pcr_idx, u8 *res_buf); +extern int tpm_pcr_extend(u32 chip_num, int pcr_idx, const u8 *hash); +#endif +#endif -- cgit v1.2.3 From 1a5645bc901aea6f3f446888061b2b084bbf1ba6 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Mon, 2 Feb 2009 23:22:04 -0800 Subject: connector: create connector workqueue only while needed once The netlink connector uses its own workqueue to relay the datas sent from userspace to the appropriate callback. If you launch the test from Documentation/connector and change it a bit to send a high flow of data, you will see thousands of events coming to the "cqueue" workqueue by looking at the workqueue tracer. This flow of events can be sent very quickly. So, to not encumber the kevent workqueue and delay other jobs, the "cqueue" workqueue should remain. But this workqueue is pointless most of the time, it will always be created (assuming you have built it of course) although only developpers with specific needs will use it. So avoid this "most of the time useless task", this patch proposes to create this workqueue only when needed once. The first jobs to be sent to connector callbacks will be sent to kevent while the "cqueue" thread creation will be scheduled to kevent too. The following jobs will continue to be scheduled to keventd until the cqueue workqueue is created, and then the rest of the jobs will continue to perform as usual, through this dedicated workqueue. Each time I tested this patch, only the first event was sent to keventd, the rest has been sent to cqueue which have been created quickly. Also, this patch fixes some trailing whitespaces on the connector files. Signed-off-by: Frederic Weisbecker Acked-by: Evgeniy Polyakov Signed-off-by: David S. Miller --- include/linux/connector.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/connector.h b/include/linux/connector.h index 34f2789d9b9..fc65d219d88 100644 --- a/include/linux/connector.h +++ b/include/linux/connector.h @@ -109,6 +109,12 @@ struct cn_queue_dev { unsigned char name[CN_CBQ_NAMELEN]; struct workqueue_struct *cn_queue; + /* Sent to kevent to create cn_queue only when needed */ + struct work_struct wq_creation; + /* Tell if the wq_creation job is pending/completed */ + atomic_t wq_requested; + /* Wait for cn_queue to be created */ + wait_queue_head_t wq_created; struct list_head queue_list; spinlock_t queue_lock; @@ -164,6 +170,8 @@ int cn_netlink_send(struct cn_msg *, u32, gfp_t); int cn_queue_add_callback(struct cn_queue_dev *dev, char *name, struct cb_id *id, void (*callback)(void *)); void cn_queue_del_callback(struct cn_queue_dev *dev, struct cb_id *id); +int queue_cn_work(struct cn_callback_entry *cbq, struct work_struct *work); + struct cn_queue_dev *cn_queue_alloc_dev(char *name, struct sock *); void cn_queue_free_dev(struct cn_queue_dev *dev); -- cgit v1.2.3 From 2a41f71d3bd97dde3305b4e1c43ab0eca46e7c71 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Wed, 4 Feb 2009 09:02:34 +0000 Subject: virtio_net: Add a virtqueue for outbound control commands This will be used for RX mode, MAC filter table, VLAN filtering, etc... The control transaction consists of one or more "out" sg entries and one or more "in" sg entries. The first out entry contains a header defining the class and command. Additional out entries may provide data for the command. The last in entry provides a status response back from the command. Virtqueues typically run asynchronous, running a callback function when there's data in the channel. We can't readily make use of this in the command paths where we need to use this. Instead, we kick the virtqueue and spin. The kick causes an I/O write, triggering an immediate trap into the hypervisor. Signed-off-by: Alex Williamson Acked-by: Rusty Russell Signed-off-by: David S. Miller --- include/linux/virtio_net.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index d8e362d52fd..245eda829aa 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -23,6 +23,7 @@ #define VIRTIO_NET_F_HOST_UFO 14 /* Host can handle UFO in. */ #define VIRTIO_NET_F_MRG_RXBUF 15 /* Host can merge receive buffers. */ #define VIRTIO_NET_F_STATUS 16 /* virtio_net_config.status available */ +#define VIRTIO_NET_F_CTRL_VQ 17 /* Control channel available */ #define VIRTIO_NET_S_LINK_UP 1 /* Link is up */ @@ -59,4 +60,21 @@ struct virtio_net_hdr_mrg_rxbuf { __u16 num_buffers; /* Number of merged rx buffers */ }; +/* + * Control virtqueue data structures + * + * The control virtqueue expects a header in the first sg entry + * and an ack/status response in the last entry. Data for the + * command goes in between. + */ +struct virtio_net_ctrl_hdr { + __u8 class; + __u8 cmd; +} __attribute__((packed)); + +typedef __u8 virtio_net_ctrl_ack; + +#define VIRTIO_NET_OK 0 +#define VIRTIO_NET_ERR 1 + #endif /* _LINUX_VIRTIO_NET_H */ -- cgit v1.2.3 From 2af7698e2dd698d452ab9d63a9ca5956bbe8fc3b Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Wed, 4 Feb 2009 09:02:40 +0000 Subject: virtio_net: Add a set_rx_mode interface Make use of the RX_MODE control virtqueue class to enable the set_rx_mode netdev interface. This allows us to selectively enable/disable promiscuous and allmulti mode so we don't see packets we don't want. For now, we automatically enable these as needed if additional unicast or multicast addresses are requested. Signed-off-by: Alex Williamson Acked-by: Rusty Russell Signed-off-by: David S. Miller --- include/linux/virtio_net.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 245eda829aa..63b2461a40f 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -24,6 +24,7 @@ #define VIRTIO_NET_F_MRG_RXBUF 15 /* Host can merge receive buffers. */ #define VIRTIO_NET_F_STATUS 16 /* virtio_net_config.status available */ #define VIRTIO_NET_F_CTRL_VQ 17 /* Control channel available */ +#define VIRTIO_NET_F_CTRL_RX 18 /* Control channel RX mode support */ #define VIRTIO_NET_S_LINK_UP 1 /* Link is up */ @@ -77,4 +78,14 @@ typedef __u8 virtio_net_ctrl_ack; #define VIRTIO_NET_OK 0 #define VIRTIO_NET_ERR 1 +/* + * Control the RX mode, ie. promisucous and allmulti. PROMISC and + * ALLMULTI commands require an "out" sg entry containing a 1 byte + * state value, zero = disable, non-zero = enable. These commands + * are supported with the VIRTIO_NET_F_CTRL_RX feature. + */ +#define VIRTIO_NET_CTRL_RX 0 + #define VIRTIO_NET_CTRL_RX_PROMISC 0 + #define VIRTIO_NET_CTRL_RX_ALLMULTI 1 + #endif /* _LINUX_VIRTIO_NET_H */ -- cgit v1.2.3 From f565a7c259d71cc186753653d978c646d2354b36 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Wed, 4 Feb 2009 09:02:45 +0000 Subject: virtio_net: Add a MAC filter table Make use of the MAC control virtqueue class to support a MAC filter table. The filter table is managed by the hypervisor. We consider the table to be available if the CTRL_RX feature bit is set. We leave it to the hypervisor to manage the table and enable promiscuous or all-multi mode as necessary depending on the resources available to it. Signed-off-by: Alex Williamson Acked-by: Rusty Russell Signed-off-by: David S. Miller --- include/linux/virtio_net.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 63b2461a40f..ba82b653cac 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -88,4 +88,27 @@ typedef __u8 virtio_net_ctrl_ack; #define VIRTIO_NET_CTRL_RX_PROMISC 0 #define VIRTIO_NET_CTRL_RX_ALLMULTI 1 +/* + * Control the MAC filter table. + * + * The MAC filter table is managed by the hypervisor, the guest should + * assume the size is infinite. Filtering should be considered + * non-perfect, ie. based on hypervisor resources, the guest may + * received packets from sources not specified in the filter list. + * + * In addition to the class/cmd header, the TABLE_SET command requires + * two out scatterlists. Each contains a 4 byte count of entries followed + * by a concatenated byte stream of the ETH_ALEN MAC addresses. The + * first sg list contains unicast addresses, the second is for multicast. + * This functionality is present if the VIRTIO_NET_F_CTRL_RX feature + * is available. + */ +struct virtio_net_ctrl_mac { + __u32 entries; + __u8 macs[][ETH_ALEN]; +} __attribute__((packed)); + +#define VIRTIO_NET_CTRL_MAC 1 + #define VIRTIO_NET_CTRL_MAC_TABLE_SET 0 + #endif /* _LINUX_VIRTIO_NET_H */ -- cgit v1.2.3 From 0bde95690d65653e420d04856c5d5783155c747c Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Wed, 4 Feb 2009 09:02:50 +0000 Subject: virtio_net: Add support for VLAN filtering in the hypervisor VLAN filtering allows the hypervisor to drop packets from VLANs that we're not a part of, further reducing the number of extraneous packets recieved. This makes use of the VLAN virtqueue command class. The CTRL_VLAN feature bit tells us whether the backend supports VLAN filtering. Signed-off-by: Alex Williamson Acked-by: Rusty Russell Signed-off-by: David S. Miller --- include/linux/virtio_net.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index ba82b653cac..242348bb376 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -25,6 +25,7 @@ #define VIRTIO_NET_F_STATUS 16 /* virtio_net_config.status available */ #define VIRTIO_NET_F_CTRL_VQ 17 /* Control channel available */ #define VIRTIO_NET_F_CTRL_RX 18 /* Control channel RX mode support */ +#define VIRTIO_NET_F_CTRL_VLAN 19 /* Control channel VLAN filtering */ #define VIRTIO_NET_S_LINK_UP 1 /* Link is up */ @@ -111,4 +112,17 @@ struct virtio_net_ctrl_mac { #define VIRTIO_NET_CTRL_MAC 1 #define VIRTIO_NET_CTRL_MAC_TABLE_SET 0 +/* + * Control VLAN filtering + * + * The VLAN filter table is controlled via a simple ADD/DEL interface. + * VLAN IDs not added may be filterd by the hypervisor. Del is the + * opposite of add. Both commands expect an out entry containing a 2 + * byte VLAN ID. VLAN filterting is available with the + * VIRTIO_NET_F_CTRL_VLAN feature bit. + */ +#define VIRTIO_NET_CTRL_VLAN 2 + #define VIRTIO_NET_CTRL_VLAN_ADD 0 + #define VIRTIO_NET_CTRL_VLAN_DEL 1 + #endif /* _LINUX_VIRTIO_NET_H */ -- cgit v1.2.3 From 6146f0d5e47ca4047ffded0fb79b6c25359b386c Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Wed, 4 Feb 2009 09:06:57 -0500 Subject: integrity: IMA hooks This patch replaces the generic integrity hooks, for which IMA registered itself, with IMA integrity hooks in the appropriate places directly in the fs directory. Signed-off-by: Mimi Zohar Acked-by: Serge Hallyn Signed-off-by: James Morris --- include/linux/ima.h | 44 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 44 insertions(+) create mode 100644 include/linux/ima.h (limited to 'include/linux') diff --git a/include/linux/ima.h b/include/linux/ima.h new file mode 100644 index 00000000000..4ed1e4d962e --- /dev/null +++ b/include/linux/ima.h @@ -0,0 +1,44 @@ +/* + * Copyright (C) 2008 IBM Corporation + * Author: Mimi Zohar + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, version 2 of the License. + */ + +#include + +#ifndef _LINUX_IMA_H +#define _LINUX_IMA_H + +static inline int ima_bprm_check(struct linux_binprm *bprm) +{ + return 0; +} + +static inline int ima_inode_alloc(struct inode *inode) +{ + return 0; +} + +static inline void ima_inode_free(struct inode *inode) +{ + return; +} + +static inline int ima_path_check(struct path *path, int mask) +{ + return 0; +} + +static inline void ima_file_free(struct file *file) +{ + return; +} + +static inline int ima_file_mmap(struct file *file, unsigned long prot) +{ + return 0; +} +#endif /* _LINUX_IMA_H */ -- cgit v1.2.3 From 3323eec921efd815178a23107ab63588c605c0b2 Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Wed, 4 Feb 2009 09:06:58 -0500 Subject: integrity: IMA as an integrity service provider IMA provides hardware (TPM) based measurement and attestation for file measurements. As the Trusted Computing (TPM) model requires, IMA measures all files before they are accessed in any way (on the integrity_bprm_check, integrity_path_check and integrity_file_mmap hooks), and commits the measurements to the TPM. Once added to the TPM, measurements can not be removed. In addition, IMA maintains a list of these file measurements, which can be used to validate the aggregate value stored in the TPM. The TPM can sign these measurements, and thus the system can prove, to itself and to a third party, the system's integrity in a way that cannot be circumvented by malicious or compromised software. - alloc ima_template_entry before calling ima_store_template() - log ima_add_boot_aggregate() failure - removed unused IMA_TEMPLATE_NAME_LEN - replaced hard coded string length with #define name Signed-off-by: Mimi Zohar Signed-off-by: James Morris --- include/linux/audit.h | 5 +++++ include/linux/ima.h | 10 ++++++++++ 2 files changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 26c4f6f65a4..8d1f67789b5 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -125,6 +125,11 @@ #define AUDIT_LAST_KERN_ANOM_MSG 1799 #define AUDIT_ANOM_PROMISCUOUS 1700 /* Device changed promiscuous mode */ #define AUDIT_ANOM_ABEND 1701 /* Process ended abnormally */ +#define AUDIT_INTEGRITY_DATA 1800 /* Data integrity verification */ +#define AUDIT_INTEGRITY_METADATA 1801 /* Metadata integrity verification */ +#define AUDIT_INTEGRITY_STATUS 1802 /* Integrity enable status */ +#define AUDIT_INTEGRITY_HASH 1803 /* Integrity HASH type */ +#define AUDIT_INTEGRITY_PCR 1804 /* PCR invalidation msgs */ #define AUDIT_KERNEL 2000 /* Asynchronous audit record. NOT A REQUEST. */ diff --git a/include/linux/ima.h b/include/linux/ima.h index 4ed1e4d962e..dcc3664feee 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -12,6 +12,15 @@ #ifndef _LINUX_IMA_H #define _LINUX_IMA_H +#ifdef CONFIG_IMA +extern int ima_bprm_check(struct linux_binprm *bprm); +extern int ima_inode_alloc(struct inode *inode); +extern void ima_inode_free(struct inode *inode); +extern int ima_path_check(struct path *path, int mask); +extern void ima_file_free(struct file *file); +extern int ima_file_mmap(struct file *file, unsigned long prot); + +#else static inline int ima_bprm_check(struct linux_binprm *bprm) { return 0; @@ -41,4 +50,5 @@ static inline int ima_file_mmap(struct file *file, unsigned long prot) { return 0; } +#endif /* CONFIG_IMA_H */ #endif /* _LINUX_IMA_H */ -- cgit v1.2.3 From 1df9f0a73178718969ae47d813b8e7aab2cf073c Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Wed, 4 Feb 2009 09:07:02 -0500 Subject: Integrity: IMA file free imbalance The number of calls to ima_path_check()/ima_file_free() should be balanced. An extra call to fput(), indicates the file could have been accessed without first being measured. Although f_count is incremented/decremented in places other than fget/fput, like fget_light/fput_light and get_file, the current task must already hold a file refcnt. The call to __fput() is delayed until the refcnt becomes 0, resulting in ima_file_free() flagging any changes. - add hook to increment opencount for IPC shared memory(SYSV), shmat files, and /dev/zero - moved NULL iint test in opencount_get() Signed-off-by: Mimi Zohar Acked-by: Serge Hallyn Signed-off-by: James Morris --- include/linux/ima.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ima.h b/include/linux/ima.h index dcc3664feee..6db30a328d9 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -19,6 +19,7 @@ extern void ima_inode_free(struct inode *inode); extern int ima_path_check(struct path *path, int mask); extern void ima_file_free(struct file *file); extern int ima_file_mmap(struct file *file, unsigned long prot); +extern void ima_shm_check(struct file *file); #else static inline int ima_bprm_check(struct linux_binprm *bprm) @@ -50,5 +51,10 @@ static inline int ima_file_mmap(struct file *file, unsigned long prot) { return 0; } + +static inline void ima_shm_check(struct file *file) +{ + return; +} #endif /* CONFIG_IMA_H */ #endif /* _LINUX_IMA_H */ -- cgit v1.2.3 From 33dccbb050bbe35b88ca8cf1228dcf3e4d4b3554 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Thu, 5 Feb 2009 21:25:32 -0800 Subject: tun: Limit amount of queued packets per device Unlike a normal socket path, the tuntap device send path does not have any accounting. This means that the user-space sender may be able to pin down arbitrary amounts of kernel memory by continuing to send data to an end-point that is congested. Even when this isn't an issue because of limited queueing at most end points, this can also be a problem because its only response to congestion is packet loss. That is, when those local queues at the end-point fills up, the tuntap device will start wasting system time because it will continue to send data there which simply gets dropped straight away. Of course one could argue that everybody should do congestion control end-to-end, unfortunately there are people in this world still hooked on UDP, and they don't appear to be going away anywhere fast. In fact, we've always helped them by performing accounting in our UDP code, the sole purpose of which is to provide congestion feedback other than through packet loss. This patch attempts to apply the same bandaid to the tuntap device. It creates a pseudo-socket object which is used to account our packets just as a normal socket does for UDP. Of course things are a little complex because we're actually reinjecting traffic back into the stack rather than out of the stack. The stack complexities however should have been resolved by preceding patches. So this one can simply start using skb_set_owner_w. For now the accounting is essentially disabled by default for backwards compatibility. In particular, we set the cap to INT_MAX. This is so that existing applications don't get confused by the sudden arrival EAGAIN errors. In future we may wish (or be forced to) do this by default. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/if_tun.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_tun.h b/include/linux/if_tun.h index 8529f57ba26..049d6c9428d 100644 --- a/include/linux/if_tun.h +++ b/include/linux/if_tun.h @@ -46,6 +46,8 @@ #define TUNSETOFFLOAD _IOW('T', 208, unsigned int) #define TUNSETTXFILTER _IOW('T', 209, unsigned int) #define TUNGETIFF _IOR('T', 210, unsigned int) +#define TUNGETSNDBUF _IOR('T', 211, int) +#define TUNSETSNDBUF _IOW('T', 212, int) /* TUNSETIFF ifr flags */ #define IFF_TUN 0x0001 -- cgit v1.2.3 From fe2918b098cdbf55b69ba8762bd3de0ae64f33ff Mon Sep 17 00:00:00 2001 From: Graf Yang Date: Thu, 5 Feb 2009 21:26:19 -0800 Subject: net: fix some trailing whitespaces Signed-off-by: Graf Yang Signed-off-by: Bryan Wu Signed-off-by: David S. Miller --- include/linux/if_ether.h | 8 ++++---- include/linux/netdevice.h | 10 +++++----- 2 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_ether.h b/include/linux/if_ether.h index 7f3c735f422..0216e1bdbc5 100644 --- a/include/linux/if_ether.h +++ b/include/linux/if_ether.h @@ -17,7 +17,7 @@ * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. */ - + #ifndef _LINUX_IF_ETHER_H #define _LINUX_IF_ETHER_H @@ -25,7 +25,7 @@ /* * IEEE 802.3 Ethernet magic constants. The frame sizes omit the preamble - * and FCS/CRC (frame check sequence). + * and FCS/CRC (frame check sequence). */ #define ETH_ALEN 6 /* Octets in one ethernet addr */ @@ -83,7 +83,7 @@ /* * Non DIX types. Won't clash for 1500 types. */ - + #define ETH_P_802_3 0x0001 /* Dummy type for 802.3 frames */ #define ETH_P_AX25 0x0002 /* Dummy protocol id for AX.25 */ #define ETH_P_ALL 0x0003 /* Every packet (be careful!!!) */ @@ -109,7 +109,7 @@ /* * This is an Ethernet frame header. */ - + struct ethhdr { unsigned char h_dest[ETH_ALEN]; /* destination eth addr */ unsigned char h_source[ETH_ALEN]; /* source ether addr */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7a5057fbb7c..864519e585f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -96,7 +96,7 @@ struct wireless_dev; * Compute the worst case header length according to the protocols * used. */ - + #if defined(CONFIG_WLAN_80211) || defined(CONFIG_AX25) || defined(CONFIG_AX25_MODULE) # if defined(CONFIG_MAC80211_MESH) # define LL_MAX_HEADER 128 @@ -124,7 +124,7 @@ struct wireless_dev; * Network device statistics. Akin to the 2.0 ether stats but * with byte counters. */ - + struct net_device_stats { unsigned long rx_packets; /* total packets received */ @@ -285,7 +285,7 @@ enum netdev_state_t /* * This structure holds at boot time configured netdevice settings. They - * are then used in the device probing. + * are then used in the device probing. */ struct netdev_boot_setup { char name[IFNAMSIZ]; @@ -740,7 +740,7 @@ struct net_device void *dsa_ptr; /* dsa specific data */ #endif void *atalk_ptr; /* AppleTalk link */ - void *ip_ptr; /* IPv4 specific data */ + void *ip_ptr; /* IPv4 specific data */ void *dn_ptr; /* DECnet specific data */ void *ip6_ptr; /* IPv6 specific data */ void *ec_ptr; /* Econet specific data */ @@ -753,7 +753,7 @@ struct net_device */ unsigned long last_rx; /* Time of last Rx */ /* Interface address info used in eth_type_trans() */ - unsigned char dev_addr[MAX_ADDR_LEN]; /* hw address, (before bcast + unsigned char dev_addr[MAX_ADDR_LEN]; /* hw address, (before bcast because most packets are unicast) */ unsigned char broadcast[MAX_ADDR_LEN]; /* hw bcast add */ -- cgit v1.2.3 From d6301d3dd1c287b32132dda15272a50c11e92a14 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Sun, 8 Feb 2009 19:24:13 -0800 Subject: net: Increase default NET_SKB_PAD to 32. Several devices need to insert some "pre headers" in front of the main packet data when they transmit a packet. Currently we allocate only 16 bytes of pad room and this ends up not being enough for some types of hardware (NIU, usb-net, s390 qeth, etc.) So increase this to 32. Note that drivers still need to check in their transmit routine whether enough headroom exists, and if not use skb_realloc_headroom(). Tunneling, IPSEC, and other encapsulation methods can cause the padding area to be used up. Signed-off-by: David S. Miller --- include/linux/skbuff.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 08670d01747..5eba4007e07 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1287,7 +1287,7 @@ static inline int skb_network_offset(const struct sk_buff *skb) * The networking layer reserves some headroom in skb data (via * dev_alloc_skb). This is used to avoid having to reallocate skb data when * the header has to grow. In the default case, if the header has to grow - * 16 bytes or less we avoid the reallocation. + * 32 bytes or less we avoid the reallocation. * * Unfortunately this headroom changes the DMA alignment of the resulting * network packet. As for NET_IP_ALIGN, this unaligned DMA is expensive @@ -1295,11 +1295,11 @@ static inline int skb_network_offset(const struct sk_buff *skb) * perhaps setting it to a cacheline in size (since that will maintain * cacheline alignment of the DMA). It must be a power of 2. * - * Various parts of the networking layer expect at least 16 bytes of + * Various parts of the networking layer expect at least 32 bytes of * headroom, you should not reduce this. */ #ifndef NET_SKB_PAD -#define NET_SKB_PAD 16 +#define NET_SKB_PAD 32 #endif extern int ___pskb_trim(struct sk_buff *skb, unsigned int len); -- cgit v1.2.3 From 4ae5544f9a33e4ae306e337f96951eb3ff2df6d9 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Sun, 8 Feb 2009 18:00:36 +0000 Subject: gro: Remember number of held packets instead of counting every time This patch prepares for the move of the same_flow checks out of dev_gro_receive. As such we need to remember the number of held packets since doing a loop just to count them every time is silly. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 864519e585f..9ee344bc6c1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -314,6 +314,9 @@ struct napi_struct { spinlock_t poll_lock; int poll_owner; #endif + + unsigned int gro_count; + struct net_device *dev; struct list_head dev_list; struct sk_buff *gro_list; -- cgit v1.2.3 From aa4b9f533ed5a22952e038b9fac2447ccc682124 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Sun, 8 Feb 2009 18:00:37 +0000 Subject: gro: Optimise Ethernet header comparison This patch optimises the Ethernet header comparison to use 2-byte and 4-byte xors instead of memcmp. In order to facilitate this, the actual comparison is now carried out by the callers of the shared dev_gro_receive function. This has a significant impact when receiving 1500B packets through 10GbE. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/etherdevice.h | 21 +++++++++++++++++++++ include/linux/netdevice.h | 7 +++++++ 2 files changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 1cb0f0b9092..a1f17abba7d 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -184,4 +184,25 @@ static inline unsigned compare_ether_addr_64bits(const u8 addr1[6+2], } #endif /* __KERNEL__ */ +/** + * compare_ether_header - Compare two Ethernet headers + * @a: Pointer to Ethernet header + * @b: Pointer to Ethernet header + * + * Compare two ethernet headers, returns 0 if equal. + * This assumes that the network header (i.e., IP header) is 4-byte + * aligned OR the platform can handle unaligned access. This is the + * case for all packets coming into netif_receive_skb or similar + * entry points. + */ + +static inline int compare_ether_header(const void *a, const void *b) +{ + u32 *a32 = (u32 *)((u8 *)a + 2); + u32 *b32 = (u32 *)((u8 *)b + 2); + + return (*(u16 *)a ^ *(u16 *)b) | (a32[0] ^ b32[0]) | + (a32[1] ^ b32[1]) | (a32[2] ^ b32[2]); +} + #endif /* _LINUX_ETHERDEVICE_H */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9ee344bc6c1..355662aac94 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1117,6 +1117,13 @@ static inline void skb_gro_reset_offset(struct sk_buff *skb) NAPI_GRO_CB(skb)->data_offset = 0; } +static inline void *skb_gro_mac_header(struct sk_buff *skb) +{ + return skb_mac_header(skb) < skb->data ? skb_mac_header(skb) : + page_address(skb_shinfo(skb)->frags[0].page) + + skb_shinfo(skb)->frags[0].page_offset; +} + static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, -- cgit v1.2.3 From f130347c2dd8e7ce0757cd3cf80bedbc6ed63c4c Mon Sep 17 00:00:00 2001 From: "Luis R. Rodriguez" Date: Fri, 30 Jan 2009 09:26:42 -0800 Subject: cfg80211: add get reg command This lets userspace request to get the currently set regulatory domain. Signed-off-by: Luis R. Rodriguez Signed-off-by: John W. Linville --- include/linux/nl80211.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 76aae3d8e97..4bc27049f4e 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -113,6 +113,8 @@ * @NL80211_CMD_SET_BSS: Set BSS attributes for BSS identified by * %NL80211_ATTR_IFINDEX. * + * @NL80211_CMD_GET_REG: ask the wireless core to send us its currently set + * regulatory domain. * @NL80211_CMD_SET_REG: Set current regulatory domain. CRDA sends this command * after being queried by the kernel. CRDA replies by sending a regulatory * domain structure which consists of %NL80211_ATTR_REG_ALPHA set to our @@ -188,6 +190,8 @@ enum nl80211_commands { NL80211_CMD_SET_MGMT_EXTRA_IE, + NL80211_CMD_GET_REG, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ -- cgit v1.2.3 From 0c2bec96945ccfc4a58a88d73531e392972ba6c5 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 3 Feb 2009 09:04:20 +0200 Subject: libertas: if_spi: add ability to call board specific setup/teardown methods In certain cases it is required to perform board specific actions before activating libertas G-SPI interface. These actions may include power up of the chip, GPIOs setup, proper pin-strapping and SPI controller config. This patch adds ability to call board specific setup/teardown methods Signed-off-by: Mike Rapoport Acked-by: Andrey Yurovsky Acked-by: Dan Williams Signed-off-by: John W. Linville --- include/linux/spi/libertas_spi.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/libertas_spi.h b/include/linux/spi/libertas_spi.h index ada71b4f378..79506f5f9e6 100644 --- a/include/linux/spi/libertas_spi.h +++ b/include/linux/spi/libertas_spi.h @@ -10,6 +10,9 @@ */ #ifndef _LIBERTAS_SPI_H_ #define _LIBERTAS_SPI_H_ + +struct spi_device; + struct libertas_spi_platform_data { /* There are two ways to read data from the WLAN module's SPI * interface. Setting 0 or 1 here controls which one is used. @@ -21,5 +24,9 @@ struct libertas_spi_platform_data { /* GPIO number to use as chip select */ u16 gpio_cs; + + /* Board specific setup/teardown */ + int (*setup)(struct spi_device *spi); + int (*teardown)(struct spi_device *spi); }; #endif -- cgit v1.2.3 From c9703146158c0415a60799570397e488bc982af5 Mon Sep 17 00:00:00 2001 From: Michael Buesch Date: Tue, 3 Feb 2009 19:23:18 +0100 Subject: ssb: Add PMU support This adds support for the SSB PMU. A PMU is found on Low-Power devices. Signed-off-by: Michael Buesch Signed-off-by: John W. Linville --- include/linux/ssb/ssb_driver_chipcommon.h | 224 ++++++++++++++++++++++++++++++ 1 file changed, 224 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ssb/ssb_driver_chipcommon.h b/include/linux/ssb/ssb_driver_chipcommon.h index 7d7e03dcf77..d3b1d18922f 100644 --- a/include/linux/ssb/ssb_driver_chipcommon.h +++ b/include/linux/ssb/ssb_driver_chipcommon.h @@ -181,6 +181,16 @@ #define SSB_CHIPCO_PROG_WAITCNT 0x0124 #define SSB_CHIPCO_FLASH_CFG 0x0128 #define SSB_CHIPCO_FLASH_WAITCNT 0x012C +#define SSB_CHIPCO_CLKCTLST 0x01E0 /* Clock control and status (rev >= 20) */ +#define SSB_CHIPCO_CLKCTLST_FORCEALP 0x00000001 /* Force ALP request */ +#define SSB_CHIPCO_CLKCTLST_FORCEHT 0x00000002 /* Force HT request */ +#define SSB_CHIPCO_CLKCTLST_FORCEILP 0x00000004 /* Force ILP request */ +#define SSB_CHIPCO_CLKCTLST_HAVEALPREQ 0x00000008 /* ALP available request */ +#define SSB_CHIPCO_CLKCTLST_HAVEHTREQ 0x00000010 /* HT available request */ +#define SSB_CHIPCO_CLKCTLST_HWCROFF 0x00000020 /* Force HW clock request off */ +#define SSB_CHIPCO_CLKCTLST_HAVEHT 0x00010000 /* HT available */ +#define SSB_CHIPCO_CLKCTLST_HAVEALP 0x00020000 /* APL available */ +#define SSB_CHIPCO_HW_WORKAROUND 0x01E4 /* Hardware workaround (rev >= 20) */ #define SSB_CHIPCO_UART0_DATA 0x0300 #define SSB_CHIPCO_UART0_IMR 0x0304 #define SSB_CHIPCO_UART0_FCR 0x0308 @@ -197,6 +207,196 @@ #define SSB_CHIPCO_UART1_LSR 0x0414 #define SSB_CHIPCO_UART1_MSR 0x0418 #define SSB_CHIPCO_UART1_SCRATCH 0x041C +/* PMU registers (rev >= 20) */ +#define SSB_CHIPCO_PMU_CTL 0x0600 /* PMU control */ +#define SSB_CHIPCO_PMU_CTL_ILP_DIV 0xFFFF0000 /* ILP div mask */ +#define SSB_CHIPCO_PMU_CTL_ILP_DIV_SHIFT 16 +#define SSB_CHIPCO_PMU_CTL_NOILPONW 0x00000200 /* No ILP on wait */ +#define SSB_CHIPCO_PMU_CTL_HTREQEN 0x00000100 /* HT req enable */ +#define SSB_CHIPCO_PMU_CTL_ALPREQEN 0x00000080 /* ALP req enable */ +#define SSB_CHIPCO_PMU_CTL_XTALFREQ 0x0000007C /* Crystal freq */ +#define SSB_CHIPCO_PMU_CTL_XTALFREQ_SHIFT 2 +#define SSB_CHIPCO_PMU_CTL_ILPDIVEN 0x00000002 /* ILP div enable */ +#define SSB_CHIPCO_PMU_CTL_LPOSEL 0x00000001 /* LPO sel */ +#define SSB_CHIPCO_PMU_CAP 0x0604 /* PMU capabilities */ +#define SSB_CHIPCO_PMU_CAP_REVISION 0x000000FF /* Revision mask */ +#define SSB_CHIPCO_PMU_STAT 0x0608 /* PMU status */ +#define SSB_CHIPCO_PMU_STAT_INTPEND 0x00000040 /* Interrupt pending */ +#define SSB_CHIPCO_PMU_STAT_SBCLKST 0x00000030 /* Backplane clock status? */ +#define SSB_CHIPCO_PMU_STAT_HAVEALP 0x00000008 /* ALP available */ +#define SSB_CHIPCO_PMU_STAT_HAVEHT 0x00000004 /* HT available */ +#define SSB_CHIPCO_PMU_STAT_RESINIT 0x00000003 /* Res init */ +#define SSB_CHIPCO_PMU_RES_STAT 0x060C /* PMU res status */ +#define SSB_CHIPCO_PMU_RES_PEND 0x0610 /* PMU res pending */ +#define SSB_CHIPCO_PMU_TIMER 0x0614 /* PMU timer */ +#define SSB_CHIPCO_PMU_MINRES_MSK 0x0618 /* PMU min res mask */ +#define SSB_CHIPCO_PMU_MAXRES_MSK 0x061C /* PMU max res mask */ +#define SSB_CHIPCO_PMU_RES_TABSEL 0x0620 /* PMU res table sel */ +#define SSB_CHIPCO_PMU_RES_DEPMSK 0x0624 /* PMU res dep mask */ +#define SSB_CHIPCO_PMU_RES_UPDNTM 0x0628 /* PMU res updown timer */ +#define SSB_CHIPCO_PMU_RES_TIMER 0x062C /* PMU res timer */ +#define SSB_CHIPCO_PMU_CLKSTRETCH 0x0630 /* PMU clockstretch */ +#define SSB_CHIPCO_PMU_WATCHDOG 0x0634 /* PMU watchdog */ +#define SSB_CHIPCO_PMU_RES_REQTS 0x0640 /* PMU res req timer sel */ +#define SSB_CHIPCO_PMU_RES_REQT 0x0644 /* PMU res req timer */ +#define SSB_CHIPCO_PMU_RES_REQM 0x0648 /* PMU res req mask */ +#define SSB_CHIPCO_CHIPCTL_ADDR 0x0650 +#define SSB_CHIPCO_CHIPCTL_DATA 0x0654 +#define SSB_CHIPCO_REGCTL_ADDR 0x0658 +#define SSB_CHIPCO_REGCTL_DATA 0x065C +#define SSB_CHIPCO_PLLCTL_ADDR 0x0660 +#define SSB_CHIPCO_PLLCTL_DATA 0x0664 + + + +/** PMU PLL registers */ + +/* PMU rev 0 PLL registers */ +#define SSB_PMU0_PLLCTL0 0 +#define SSB_PMU0_PLLCTL0_PDIV_MSK 0x00000001 +#define SSB_PMU0_PLLCTL0_PDIV_FREQ 25000 /* kHz */ +#define SSB_PMU0_PLLCTL1 1 +#define SSB_PMU0_PLLCTL1_WILD_IMSK 0xF0000000 /* Wild int mask (low nibble) */ +#define SSB_PMU0_PLLCTL1_WILD_IMSK_SHIFT 28 +#define SSB_PMU0_PLLCTL1_WILD_FMSK 0x0FFFFF00 /* Wild frac mask */ +#define SSB_PMU0_PLLCTL1_WILD_FMSK_SHIFT 8 +#define SSB_PMU0_PLLCTL1_STOPMOD 0x00000040 /* Stop mod */ +#define SSB_PMU0_PLLCTL2 2 +#define SSB_PMU0_PLLCTL2_WILD_IMSKHI 0x0000000F /* Wild int mask (high nibble) */ +#define SSB_PMU0_PLLCTL2_WILD_IMSKHI_SHIFT 0 + +/* PMU rev 1 PLL registers */ +#define SSB_PMU1_PLLCTL0 0 +#define SSB_PMU1_PLLCTL0_P1DIV 0x00F00000 /* P1 div */ +#define SSB_PMU1_PLLCTL0_P1DIV_SHIFT 20 +#define SSB_PMU1_PLLCTL0_P2DIV 0x0F000000 /* P2 div */ +#define SSB_PMU1_PLLCTL0_P2DIV_SHIFT 24 +#define SSB_PMU1_PLLCTL1 1 +#define SSB_PMU1_PLLCTL1_M1DIV 0x000000FF /* M1 div */ +#define SSB_PMU1_PLLCTL1_M1DIV_SHIFT 0 +#define SSB_PMU1_PLLCTL1_M2DIV 0x0000FF00 /* M2 div */ +#define SSB_PMU1_PLLCTL1_M2DIV_SHIFT 8 +#define SSB_PMU1_PLLCTL1_M3DIV 0x00FF0000 /* M3 div */ +#define SSB_PMU1_PLLCTL1_M3DIV_SHIFT 16 +#define SSB_PMU1_PLLCTL1_M4DIV 0xFF000000 /* M4 div */ +#define SSB_PMU1_PLLCTL1_M4DIV_SHIFT 24 +#define SSB_PMU1_PLLCTL2 2 +#define SSB_PMU1_PLLCTL2_M5DIV 0x000000FF /* M5 div */ +#define SSB_PMU1_PLLCTL2_M5DIV_SHIFT 0 +#define SSB_PMU1_PLLCTL2_M6DIV 0x0000FF00 /* M6 div */ +#define SSB_PMU1_PLLCTL2_M6DIV_SHIFT 8 +#define SSB_PMU1_PLLCTL2_NDIVMODE 0x000E0000 /* NDIV mode */ +#define SSB_PMU1_PLLCTL2_NDIVMODE_SHIFT 17 +#define SSB_PMU1_PLLCTL2_NDIVINT 0x1FF00000 /* NDIV int */ +#define SSB_PMU1_PLLCTL2_NDIVINT_SHIFT 20 +#define SSB_PMU1_PLLCTL3 3 +#define SSB_PMU1_PLLCTL3_NDIVFRAC 0x00FFFFFF /* NDIV frac */ +#define SSB_PMU1_PLLCTL3_NDIVFRAC_SHIFT 0 +#define SSB_PMU1_PLLCTL4 4 +#define SSB_PMU1_PLLCTL5 5 +#define SSB_PMU1_PLLCTL5_CLKDRV 0xFFFFFF00 /* clk drv */ +#define SSB_PMU1_PLLCTL5_CLKDRV_SHIFT 8 + +/* BCM4312 PLL resource numbers. */ +#define SSB_PMURES_4312_SWITCHER_BURST 0 +#define SSB_PMURES_4312_SWITCHER_PWM 1 +#define SSB_PMURES_4312_PA_REF_LDO 2 +#define SSB_PMURES_4312_CORE_LDO_BURST 3 +#define SSB_PMURES_4312_CORE_LDO_PWM 4 +#define SSB_PMURES_4312_RADIO_LDO 5 +#define SSB_PMURES_4312_ILP_REQUEST 6 +#define SSB_PMURES_4312_BG_FILTBYP 7 +#define SSB_PMURES_4312_TX_FILTBYP 8 +#define SSB_PMURES_4312_RX_FILTBYP 9 +#define SSB_PMURES_4312_XTAL_PU 10 +#define SSB_PMURES_4312_ALP_AVAIL 11 +#define SSB_PMURES_4312_BB_PLL_FILTBYP 12 +#define SSB_PMURES_4312_RF_PLL_FILTBYP 13 +#define SSB_PMURES_4312_HT_AVAIL 14 + +/* BCM4325 PLL resource numbers. */ +#define SSB_PMURES_4325_BUCK_BOOST_BURST 0 +#define SSB_PMURES_4325_CBUCK_BURST 1 +#define SSB_PMURES_4325_CBUCK_PWM 2 +#define SSB_PMURES_4325_CLDO_CBUCK_BURST 3 +#define SSB_PMURES_4325_CLDO_CBUCK_PWM 4 +#define SSB_PMURES_4325_BUCK_BOOST_PWM 5 +#define SSB_PMURES_4325_ILP_REQUEST 6 +#define SSB_PMURES_4325_ABUCK_BURST 7 +#define SSB_PMURES_4325_ABUCK_PWM 8 +#define SSB_PMURES_4325_LNLDO1_PU 9 +#define SSB_PMURES_4325_LNLDO2_PU 10 +#define SSB_PMURES_4325_LNLDO3_PU 11 +#define SSB_PMURES_4325_LNLDO4_PU 12 +#define SSB_PMURES_4325_XTAL_PU 13 +#define SSB_PMURES_4325_ALP_AVAIL 14 +#define SSB_PMURES_4325_RX_PWRSW_PU 15 +#define SSB_PMURES_4325_TX_PWRSW_PU 16 +#define SSB_PMURES_4325_RFPLL_PWRSW_PU 17 +#define SSB_PMURES_4325_LOGEN_PWRSW_PU 18 +#define SSB_PMURES_4325_AFE_PWRSW_PU 19 +#define SSB_PMURES_4325_BBPLL_PWRSW_PU 20 +#define SSB_PMURES_4325_HT_AVAIL 21 + +/* BCM4328 PLL resource numbers. */ +#define SSB_PMURES_4328_EXT_SWITCHER_PWM 0 +#define SSB_PMURES_4328_BB_SWITCHER_PWM 1 +#define SSB_PMURES_4328_BB_SWITCHER_BURST 2 +#define SSB_PMURES_4328_BB_EXT_SWITCHER_BURST 3 +#define SSB_PMURES_4328_ILP_REQUEST 4 +#define SSB_PMURES_4328_RADIO_SWITCHER_PWM 5 +#define SSB_PMURES_4328_RADIO_SWITCHER_BURST 6 +#define SSB_PMURES_4328_ROM_SWITCH 7 +#define SSB_PMURES_4328_PA_REF_LDO 8 +#define SSB_PMURES_4328_RADIO_LDO 9 +#define SSB_PMURES_4328_AFE_LDO 10 +#define SSB_PMURES_4328_PLL_LDO 11 +#define SSB_PMURES_4328_BG_FILTBYP 12 +#define SSB_PMURES_4328_TX_FILTBYP 13 +#define SSB_PMURES_4328_RX_FILTBYP 14 +#define SSB_PMURES_4328_XTAL_PU 15 +#define SSB_PMURES_4328_XTAL_EN 16 +#define SSB_PMURES_4328_BB_PLL_FILTBYP 17 +#define SSB_PMURES_4328_RF_PLL_FILTBYP 18 +#define SSB_PMURES_4328_BB_PLL_PU 19 + +/* BCM5354 PLL resource numbers. */ +#define SSB_PMURES_5354_EXT_SWITCHER_PWM 0 +#define SSB_PMURES_5354_BB_SWITCHER_PWM 1 +#define SSB_PMURES_5354_BB_SWITCHER_BURST 2 +#define SSB_PMURES_5354_BB_EXT_SWITCHER_BURST 3 +#define SSB_PMURES_5354_ILP_REQUEST 4 +#define SSB_PMURES_5354_RADIO_SWITCHER_PWM 5 +#define SSB_PMURES_5354_RADIO_SWITCHER_BURST 6 +#define SSB_PMURES_5354_ROM_SWITCH 7 +#define SSB_PMURES_5354_PA_REF_LDO 8 +#define SSB_PMURES_5354_RADIO_LDO 9 +#define SSB_PMURES_5354_AFE_LDO 10 +#define SSB_PMURES_5354_PLL_LDO 11 +#define SSB_PMURES_5354_BG_FILTBYP 12 +#define SSB_PMURES_5354_TX_FILTBYP 13 +#define SSB_PMURES_5354_RX_FILTBYP 14 +#define SSB_PMURES_5354_XTAL_PU 15 +#define SSB_PMURES_5354_XTAL_EN 16 +#define SSB_PMURES_5354_BB_PLL_FILTBYP 17 +#define SSB_PMURES_5354_RF_PLL_FILTBYP 18 +#define SSB_PMURES_5354_BB_PLL_PU 19 + + + +/** Chip specific Chip-Status register contents. */ +#define SSB_CHIPCO_CHST_4325_SPROM_OTP_SEL 0x00000003 +#define SSB_CHIPCO_CHST_4325_DEFCIS_SEL 0 /* OTP is powered up, use def. CIS, no SPROM */ +#define SSB_CHIPCO_CHST_4325_SPROM_SEL 1 /* OTP is powered up, SPROM is present */ +#define SSB_CHIPCO_CHST_4325_OTP_SEL 2 /* OTP is powered up, no SPROM */ +#define SSB_CHIPCO_CHST_4325_OTP_PWRDN 3 /* OTP is powered down, SPROM is present */ +#define SSB_CHIPCO_CHST_4325_SDIO_USB_MODE 0x00000004 +#define SSB_CHIPCO_CHST_4325_SDIO_USB_MODE_SHIFT 2 +#define SSB_CHIPCO_CHST_4325_RCAL_VALID 0x00000008 +#define SSB_CHIPCO_CHST_4325_RCAL_VALID_SHIFT 3 +#define SSB_CHIPCO_CHST_4325_RCAL_VALUE 0x000001F0 +#define SSB_CHIPCO_CHST_4325_RCAL_VALUE_SHIFT 4 +#define SSB_CHIPCO_CHST_4325_PMUTOP_2B 0x00000200 /* 1 for 2b, 0 for to 2a */ @@ -353,11 +553,20 @@ struct ssb_device; struct ssb_serial_port; +/* Data for the PMU, if available. + * Check availability with ((struct ssb_chipcommon)->capabilities & SSB_CHIPCO_CAP_PMU) + */ +struct ssb_chipcommon_pmu { + u8 rev; /* PMU revision */ + u32 crystalfreq; /* The active crystal frequency (in kHz) */ +}; + struct ssb_chipcommon { struct ssb_device *dev; u32 capabilities; /* Fast Powerup Delay constant */ u16 fast_pwrup_delay; + struct ssb_chipcommon_pmu pmu; }; static inline bool ssb_chipco_available(struct ssb_chipcommon *cc) @@ -365,6 +574,17 @@ static inline bool ssb_chipco_available(struct ssb_chipcommon *cc) return (cc->dev != NULL); } +/* Register access */ +#define chipco_read32(cc, offset) ssb_read32((cc)->dev, offset) +#define chipco_write32(cc, offset, val) ssb_write32((cc)->dev, offset, val) + +#define chipco_mask32(cc, offset, mask) \ + chipco_write32(cc, offset, chipco_read32(cc, offset) & (mask)) +#define chipco_set32(cc, offset, set) \ + chipco_write32(cc, offset, chipco_read32(cc, offset) | (set)) +#define chipco_maskset32(cc, offset, mask, set) \ + chipco_write32(cc, offset, (chipco_read32(cc, offset) & (mask)) | (set)) + extern void ssb_chipcommon_init(struct ssb_chipcommon *cc); extern void ssb_chipco_suspend(struct ssb_chipcommon *cc); @@ -406,4 +626,8 @@ extern int ssb_chipco_serial_init(struct ssb_chipcommon *cc, struct ssb_serial_port *ports); #endif /* CONFIG_SSB_SERIAL */ +/* PMU support */ +extern void ssb_pmu_init(struct ssb_chipcommon *cc); + + #endif /* LINUX_SSB_CHIPCO_H_ */ -- cgit v1.2.3 From d54e6d872767ae6512978f86a35d623a8ed948c5 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Mon, 9 Feb 2009 23:45:29 -0800 Subject: net: Kill skbuff macros from the stone ages. This kills of HAVE_ALLOC_SKB and HAVE_ALIGNABLE_SKB. Nothing in-tree uses them and nothing in-tree has used them since 2.0.x times. Signed-off-by: David S. Miller --- include/linux/skbuff.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 5eba4007e07..92470084458 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -29,9 +29,6 @@ #include #include -#define HAVE_ALLOC_SKB /* For the drivers to know */ -#define HAVE_ALIGNABLE_SKB /* Ditto 8) */ - /* Don't change this without changing skb_csum_unnecessary! */ #define CHECKSUM_NONE 0 #define CHECKSUM_UNNECESSARY 1 -- cgit v1.2.3 From ed850a52af971528b048812c4215cef298af0d3b Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Tue, 10 Feb 2009 23:01:19 -0500 Subject: integrity: shmem zero fix Based on comments from Mike Frysinger and Randy Dunlap: (http://lkml.org/lkml/2009/2/9/262) - moved ima.h include before CONFIG_SHMEM test to fix compiler error on Blackfin: mm/shmem.c: In function 'shmem_zero_setup': mm/shmem.c:2670: error: implicit declaration of function 'ima_shm_check' - added 'struct linux_binprm' in ima.h to fix compiler warning on Blackfin: In file included from mm/shmem.c:32: include/linux/ima.h:25: warning: 'struct linux_binprm' declared inside parameter list include/linux/ima.h:25: warning: its scope is only this definition or declaration, which is probably not what you want - moved fs.h include within _LINUX_IMA_H definition Signed-off-by: Mimi Zohar Signed-off-by: Mike Frysinger Signed-off-by: James Morris --- include/linux/ima.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ima.h b/include/linux/ima.h index 6db30a328d9..0e2aa45cb0c 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -7,11 +7,12 @@ * the Free Software Foundation, version 2 of the License. */ -#include - #ifndef _LINUX_IMA_H #define _LINUX_IMA_H +#include +struct linux_binprm; + #ifdef CONFIG_IMA extern int ima_bprm_check(struct linux_binprm *bprm); extern int ima_inode_alloc(struct inode *inode); -- cgit v1.2.3 From ad0b0fd554dfc126b5750d14908dccc3bbf602be Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Tue, 10 Feb 2009 11:42:26 -0800 Subject: sched, latencytop: incorporate review feedback from Andrew Morton Andrew had some suggestions for the latencytop file; this patch takes care of most of these: * Add documentation * Turn account_scheduler_latency into an inline function * Don't report negative values to userspace * Make the file operations struct const * Fix a few checkpatch.pl warnings Signed-off-by: Arjan van de Ven Signed-off-by: Andrew Morton Signed-off-by: Ingo Molnar --- include/linux/latencytop.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/latencytop.h b/include/linux/latencytop.h index 901c2d6377a..b0e99898527 100644 --- a/include/linux/latencytop.h +++ b/include/linux/latencytop.h @@ -9,6 +9,7 @@ #ifndef _INCLUDE_GUARD_LATENCYTOP_H_ #define _INCLUDE_GUARD_LATENCYTOP_H_ +#include #ifdef CONFIG_LATENCYTOP #define LT_SAVECOUNT 32 @@ -24,7 +25,14 @@ struct latency_record { struct task_struct; -void account_scheduler_latency(struct task_struct *task, int usecs, int inter); +extern int latencytop_enabled; +void __account_scheduler_latency(struct task_struct *task, int usecs, int inter); +static inline void +account_scheduler_latency(struct task_struct *task, int usecs, int inter) +{ + if (unlikely(latencytop_enabled)) + __account_scheduler_latency(task, usecs, inter); +} void clear_all_latency_tracing(struct task_struct *p); -- cgit v1.2.3 From 523979adfa0b79d4e3aa053220c37a9233294206 Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Wed, 11 Feb 2009 11:12:28 -0500 Subject: integrity: audit update Based on discussions on linux-audit, as per Steve Grubb's request http://lkml.org/lkml/2009/2/6/269, the following changes were made: - forced audit result to be either 0 or 1. - made template names const - Added new stand-alone message type: AUDIT_INTEGRITY_RULE Signed-off-by: Mimi Zohar Acked-by: Steve Grubb Signed-off-by: James Morris --- include/linux/audit.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 930939abfbc..4fa2810b675 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -36,7 +36,8 @@ * 1500 - 1599 kernel LSPP events * 1600 - 1699 kernel crypto events * 1700 - 1799 kernel anomaly records - * 1800 - 1999 future kernel use (maybe integrity labels and related events) + * 1800 - 1899 kernel integrity events + * 1900 - 1999 future kernel use * 2000 is for otherwise unclassified kernel audit messages (legacy) * 2001 - 2099 unused (kernel) * 2100 - 2199 user space anomaly records @@ -130,6 +131,7 @@ #define AUDIT_INTEGRITY_STATUS 1802 /* Integrity enable status */ #define AUDIT_INTEGRITY_HASH 1803 /* Integrity HASH type */ #define AUDIT_INTEGRITY_PCR 1804 /* PCR invalidation msgs */ +#define AUDIT_INTEGRITY_RULE 1805 /* policy rule */ #define AUDIT_KERNEL 2000 /* Asynchronous audit record. NOT A REQUEST. */ -- cgit v1.2.3 From f9ce1f1cda8b73a36f47e424975a9dfa78b7840c Mon Sep 17 00:00:00 2001 From: Kentaro Takeda Date: Thu, 5 Feb 2009 17:18:11 +0900 Subject: Add in_execve flag into task_struct. This patch allows LSM modules to determine whether current process is in an execve operation or not so that they can behave differently while an execve operation is in progress. This patch is needed by TOMOYO. Please see another patch titled "LSM adapter functions." for backgrounds. Signed-off-by: Tetsuo Handa Signed-off-by: David Howells Signed-off-by: James Morris --- include/linux/sched.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 2127e959e0f..397c20cfb6a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1158,6 +1158,8 @@ struct task_struct { /* ??? */ unsigned int personality; unsigned did_exec:1; + unsigned in_execve:1; /* Tell the LSMs that the process is doing an + * execve */ pid_t pid; pid_t tgid; -- cgit v1.2.3 From 2a5193119269062608582418deba7af82844159a Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 10 Feb 2009 21:25:55 +0100 Subject: cfg80211/nl80211: scanning (and mac80211 update to use it) This patch adds basic scan capability to cfg80211/nl80211 and changes mac80211 to use it. The BSS list that cfg80211 maintains is made driver-accessible with a private area in each BSS struct, but mac80211 doesn't yet use it. That's another large project. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/nl80211.h | 65 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 65 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 4bc27049f4e..8802d1bda38 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -143,6 +143,13 @@ * added to all specified management frames generated by * kernel/firmware/driver. * + * @NL80211_CMD_GET_SCAN: get scan results + * @NL80211_CMD_TRIGGER_SCAN: trigger a new scan with the given parameters + * @NL80211_CMD_NEW_SCAN_RESULTS: scan notification (as a reply to + * NL80211_CMD_GET_SCAN and on the "scan" multicast group) + * @NL80211_CMD_SCAN_ABORTED: scan was aborted, for unspecified reasons, + * partial scan results may be available + * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use */ @@ -192,6 +199,11 @@ enum nl80211_commands { NL80211_CMD_GET_REG, + NL80211_CMD_GET_SCAN, + NL80211_CMD_TRIGGER_SCAN, + NL80211_CMD_NEW_SCAN_RESULTS, + NL80211_CMD_SCAN_ABORTED, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ @@ -305,6 +317,18 @@ enum nl80211_commands { * @NL80211_ATTR_IE: Information element(s) data (used, e.g., with * %NL80211_CMD_SET_MGMT_EXTRA_IE). * + * @NL80211_ATTR_MAX_NUM_SCAN_SSIDS: number of SSIDs you can scan with + * a single scan request, a wiphy attribute. + * + * @NL80211_ATTR_SCAN_FREQUENCIES: nested attribute with frequencies (in MHz) + * @NL80211_ATTR_SCAN_SSIDS: nested attribute with SSIDs, leave out for passive + * scanning and include a zero-length SSID (wildcard) for wildcard scan + * @NL80211_ATTR_SCAN_GENERATION: the scan generation increases whenever the + * scan result list changes (BSS expired or added) so that applications + * can verify that they got a single, consistent snapshot (when all dump + * messages carried the same generation number) + * @NL80211_ATTR_BSS: scan result BSS + * * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use */ @@ -372,6 +396,13 @@ enum nl80211_attrs { NL80211_ATTR_MGMT_SUBTYPE, NL80211_ATTR_IE, + NL80211_ATTR_MAX_NUM_SCAN_SSIDS, + + NL80211_ATTR_SCAN_FREQUENCIES, + NL80211_ATTR_SCAN_SSIDS, + NL80211_ATTR_SCAN_GENERATION, + NL80211_ATTR_BSS, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -841,4 +872,38 @@ enum nl80211_channel_type { NL80211_CHAN_HT40MINUS, NL80211_CHAN_HT40PLUS }; + +/** + * enum nl80211_bss - netlink attributes for a BSS + * + * @__NL80211_BSS_INVALID: invalid + * @NL80211_BSS_FREQUENCY: frequency in MHz (u32) + * @NL80211_BSS_TSF: TSF of the received probe response/beacon (u64) + * @NL80211_BSS_BEACON_INTERVAL: beacon interval of the (I)BSS (u16) + * @NL80211_BSS_CAPABILITY: capability field (CPU order, u16) + * @NL80211_BSS_INFORMATION_ELEMENTS: binary attribute containing the + * raw information elements from the probe response/beacon (bin) + * @NL80211_BSS_SIGNAL_MBM: signal strength of probe response/beacon + * in mBm (100 * dBm) (s32) + * @NL80211_BSS_SIGNAL_UNSPEC: signal strength of the probe response/beacon + * in unspecified units, scaled to 0..100 (u8) + * @__NL80211_BSS_AFTER_LAST: internal + * @NL80211_BSS_MAX: highest BSS attribute + */ +enum nl80211_bss { + __NL80211_BSS_INVALID, + NL80211_BSS_BSSID, + NL80211_BSS_FREQUENCY, + NL80211_BSS_TSF, + NL80211_BSS_BEACON_INTERVAL, + NL80211_BSS_CAPABILITY, + NL80211_BSS_INFORMATION_ELEMENTS, + NL80211_BSS_SIGNAL_MBM, + NL80211_BSS_SIGNAL_UNSPEC, + + /* keep last */ + __NL80211_BSS_AFTER_LAST, + NL80211_BSS_MAX = __NL80211_BSS_AFTER_LAST - 1 +}; + #endif /* __LINUX_NL80211_H */ -- cgit v1.2.3 From 35c26c2cf6a6a2d1c48add732d8ba002bd90784c Mon Sep 17 00:00:00 2001 From: Harvey Harrison Date: Sat, 14 Feb 2009 22:56:56 -0800 Subject: rndis: remove private wrapper of __constant_cpu_to_le32 Use cpu_to_le32 directly as it handles constant folding now, replace direct uses of __constant_cpu_to_{endian} as well. Signed-off-by: Harvey Harrison Acked-by: David Brownell Signed-off-by: David S. Miller --- include/linux/usb/rndis_host.h | 85 ++++++++++++++++++++---------------------- 1 file changed, 41 insertions(+), 44 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/rndis_host.h b/include/linux/usb/rndis_host.h index 0a6e6d4b929..37836b937d9 100644 --- a/include/linux/usb/rndis_host.h +++ b/include/linux/usb/rndis_host.h @@ -49,48 +49,45 @@ struct rndis_msg_hdr { */ #define RNDIS_CONTROL_TIMEOUT_MS (5 * 1000) - -#define ccpu2 __constant_cpu_to_le32 - -#define RNDIS_MSG_COMPLETION ccpu2(0x80000000) +#define RNDIS_MSG_COMPLETION cpu_to_le32(0x80000000) /* codes for "msg_type" field of rndis messages; * only the data channel uses packet messages (maybe batched); * everything else goes on the control channel. */ -#define RNDIS_MSG_PACKET ccpu2(0x00000001) /* 1-N packets */ -#define RNDIS_MSG_INIT ccpu2(0x00000002) +#define RNDIS_MSG_PACKET cpu_to_le32(0x00000001) /* 1-N packets */ +#define RNDIS_MSG_INIT cpu_to_le32(0x00000002) #define RNDIS_MSG_INIT_C (RNDIS_MSG_INIT|RNDIS_MSG_COMPLETION) -#define RNDIS_MSG_HALT ccpu2(0x00000003) -#define RNDIS_MSG_QUERY ccpu2(0x00000004) +#define RNDIS_MSG_HALT cpu_to_le32(0x00000003) +#define RNDIS_MSG_QUERY cpu_to_le32(0x00000004) #define RNDIS_MSG_QUERY_C (RNDIS_MSG_QUERY|RNDIS_MSG_COMPLETION) -#define RNDIS_MSG_SET ccpu2(0x00000005) +#define RNDIS_MSG_SET cpu_to_le32(0x00000005) #define RNDIS_MSG_SET_C (RNDIS_MSG_SET|RNDIS_MSG_COMPLETION) -#define RNDIS_MSG_RESET ccpu2(0x00000006) +#define RNDIS_MSG_RESET cpu_to_le32(0x00000006) #define RNDIS_MSG_RESET_C (RNDIS_MSG_RESET|RNDIS_MSG_COMPLETION) -#define RNDIS_MSG_INDICATE ccpu2(0x00000007) -#define RNDIS_MSG_KEEPALIVE ccpu2(0x00000008) +#define RNDIS_MSG_INDICATE cpu_to_le32(0x00000007) +#define RNDIS_MSG_KEEPALIVE cpu_to_le32(0x00000008) #define RNDIS_MSG_KEEPALIVE_C (RNDIS_MSG_KEEPALIVE|RNDIS_MSG_COMPLETION) /* codes for "status" field of completion messages */ -#define RNDIS_STATUS_SUCCESS ccpu2(0x00000000) -#define RNDIS_STATUS_FAILURE ccpu2(0xc0000001) -#define RNDIS_STATUS_INVALID_DATA ccpu2(0xc0010015) -#define RNDIS_STATUS_NOT_SUPPORTED ccpu2(0xc00000bb) -#define RNDIS_STATUS_MEDIA_CONNECT ccpu2(0x4001000b) -#define RNDIS_STATUS_MEDIA_DISCONNECT ccpu2(0x4001000c) +#define RNDIS_STATUS_SUCCESS cpu_to_le32(0x00000000) +#define RNDIS_STATUS_FAILURE cpu_to_le32(0xc0000001) +#define RNDIS_STATUS_INVALID_DATA cpu_to_le32(0xc0010015) +#define RNDIS_STATUS_NOT_SUPPORTED cpu_to_le32(0xc00000bb) +#define RNDIS_STATUS_MEDIA_CONNECT cpu_to_le32(0x4001000b) +#define RNDIS_STATUS_MEDIA_DISCONNECT cpu_to_le32(0x4001000c) /* codes for OID_GEN_PHYSICAL_MEDIUM */ -#define RNDIS_PHYSICAL_MEDIUM_UNSPECIFIED ccpu2(0x00000000) -#define RNDIS_PHYSICAL_MEDIUM_WIRELESS_LAN ccpu2(0x00000001) -#define RNDIS_PHYSICAL_MEDIUM_CABLE_MODEM ccpu2(0x00000002) -#define RNDIS_PHYSICAL_MEDIUM_PHONE_LINE ccpu2(0x00000003) -#define RNDIS_PHYSICAL_MEDIUM_POWER_LINE ccpu2(0x00000004) -#define RNDIS_PHYSICAL_MEDIUM_DSL ccpu2(0x00000005) -#define RNDIS_PHYSICAL_MEDIUM_FIBRE_CHANNEL ccpu2(0x00000006) -#define RNDIS_PHYSICAL_MEDIUM_1394 ccpu2(0x00000007) -#define RNDIS_PHYSICAL_MEDIUM_WIRELESS_WAN ccpu2(0x00000008) -#define RNDIS_PHYSICAL_MEDIUM_MAX ccpu2(0x00000009) +#define RNDIS_PHYSICAL_MEDIUM_UNSPECIFIED cpu_to_le32(0x00000000) +#define RNDIS_PHYSICAL_MEDIUM_WIRELESS_LAN cpu_to_le32(0x00000001) +#define RNDIS_PHYSICAL_MEDIUM_CABLE_MODEM cpu_to_le32(0x00000002) +#define RNDIS_PHYSICAL_MEDIUM_PHONE_LINE cpu_to_le32(0x00000003) +#define RNDIS_PHYSICAL_MEDIUM_POWER_LINE cpu_to_le32(0x00000004) +#define RNDIS_PHYSICAL_MEDIUM_DSL cpu_to_le32(0x00000005) +#define RNDIS_PHYSICAL_MEDIUM_FIBRE_CHANNEL cpu_to_le32(0x00000006) +#define RNDIS_PHYSICAL_MEDIUM_1394 cpu_to_le32(0x00000007) +#define RNDIS_PHYSICAL_MEDIUM_WIRELESS_WAN cpu_to_le32(0x00000008) +#define RNDIS_PHYSICAL_MEDIUM_MAX cpu_to_le32(0x00000009) struct rndis_data_hdr { __le32 msg_type; /* RNDIS_MSG_PACKET */ @@ -228,24 +225,24 @@ struct rndis_keepalive_c { /* IN (optionally OUT) */ * there are gobs more that may optionally be supported. We'll avoid as much * of that mess as possible. */ -#define OID_802_3_PERMANENT_ADDRESS ccpu2(0x01010101) -#define OID_GEN_MAXIMUM_FRAME_SIZE ccpu2(0x00010106) -#define OID_GEN_CURRENT_PACKET_FILTER ccpu2(0x0001010e) -#define OID_GEN_PHYSICAL_MEDIUM ccpu2(0x00010202) +#define OID_802_3_PERMANENT_ADDRESS cpu_to_le32(0x01010101) +#define OID_GEN_MAXIMUM_FRAME_SIZE cpu_to_le32(0x00010106) +#define OID_GEN_CURRENT_PACKET_FILTER cpu_to_le32(0x0001010e) +#define OID_GEN_PHYSICAL_MEDIUM cpu_to_le32(0x00010202) /* packet filter bits used by OID_GEN_CURRENT_PACKET_FILTER */ -#define RNDIS_PACKET_TYPE_DIRECTED ccpu2(0x00000001) -#define RNDIS_PACKET_TYPE_MULTICAST ccpu2(0x00000002) -#define RNDIS_PACKET_TYPE_ALL_MULTICAST ccpu2(0x00000004) -#define RNDIS_PACKET_TYPE_BROADCAST ccpu2(0x00000008) -#define RNDIS_PACKET_TYPE_SOURCE_ROUTING ccpu2(0x00000010) -#define RNDIS_PACKET_TYPE_PROMISCUOUS ccpu2(0x00000020) -#define RNDIS_PACKET_TYPE_SMT ccpu2(0x00000040) -#define RNDIS_PACKET_TYPE_ALL_LOCAL ccpu2(0x00000080) -#define RNDIS_PACKET_TYPE_GROUP ccpu2(0x00001000) -#define RNDIS_PACKET_TYPE_ALL_FUNCTIONAL ccpu2(0x00002000) -#define RNDIS_PACKET_TYPE_FUNCTIONAL ccpu2(0x00004000) -#define RNDIS_PACKET_TYPE_MAC_FRAME ccpu2(0x00008000) +#define RNDIS_PACKET_TYPE_DIRECTED cpu_to_le32(0x00000001) +#define RNDIS_PACKET_TYPE_MULTICAST cpu_to_le32(0x00000002) +#define RNDIS_PACKET_TYPE_ALL_MULTICAST cpu_to_le32(0x00000004) +#define RNDIS_PACKET_TYPE_BROADCAST cpu_to_le32(0x00000008) +#define RNDIS_PACKET_TYPE_SOURCE_ROUTING cpu_to_le32(0x00000010) +#define RNDIS_PACKET_TYPE_PROMISCUOUS cpu_to_le32(0x00000020) +#define RNDIS_PACKET_TYPE_SMT cpu_to_le32(0x00000040) +#define RNDIS_PACKET_TYPE_ALL_LOCAL cpu_to_le32(0x00000080) +#define RNDIS_PACKET_TYPE_GROUP cpu_to_le32(0x00001000) +#define RNDIS_PACKET_TYPE_ALL_FUNCTIONAL cpu_to_le32(0x00002000) +#define RNDIS_PACKET_TYPE_FUNCTIONAL cpu_to_le32(0x00004000) +#define RNDIS_PACKET_TYPE_MAC_FRAME cpu_to_le32(0x00008000) /* default filter used with RNDIS devices */ #define RNDIS_DEFAULT_FILTER ( \ -- cgit v1.2.3 From f3a7c66b5ce0b75a9774a50b5dcce93e5ba28370 Mon Sep 17 00:00:00 2001 From: Harvey Harrison Date: Sat, 14 Feb 2009 22:58:35 -0800 Subject: net: replace __constant_{endian} uses in net headers Base versions handle constant folding now. For headers exposed to userspace, we must only expose the __ prefixed versions. Signed-off-by: Harvey Harrison Signed-off-by: David S. Miller --- include/linux/if_pppox.h | 20 ++++----- include/linux/if_tunnel.h | 16 +++---- include/linux/ncp_no.h | 26 ++++++------ include/linux/netdevice.h | 4 +- include/linux/netfilter_bridge.h | 4 +- include/linux/pim.h | 4 +- include/linux/sctp.h | 90 ++++++++++++++++++++-------------------- include/linux/tcp.h | 20 ++++----- 8 files changed, 92 insertions(+), 92 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_pppox.h b/include/linux/if_pppox.h index 30c88b2245f..90b5fae5d71 100644 --- a/include/linux/if_pppox.h +++ b/include/linux/if_pppox.h @@ -95,16 +95,16 @@ struct pppoe_tag { } __attribute ((packed)); /* Tag identifiers */ -#define PTT_EOL __constant_htons(0x0000) -#define PTT_SRV_NAME __constant_htons(0x0101) -#define PTT_AC_NAME __constant_htons(0x0102) -#define PTT_HOST_UNIQ __constant_htons(0x0103) -#define PTT_AC_COOKIE __constant_htons(0x0104) -#define PTT_VENDOR __constant_htons(0x0105) -#define PTT_RELAY_SID __constant_htons(0x0110) -#define PTT_SRV_ERR __constant_htons(0x0201) -#define PTT_SYS_ERR __constant_htons(0x0202) -#define PTT_GEN_ERR __constant_htons(0x0203) +#define PTT_EOL __cpu_to_be16(0x0000) +#define PTT_SRV_NAME __cpu_to_be16(0x0101) +#define PTT_AC_NAME __cpu_to_be16(0x0102) +#define PTT_HOST_UNIQ __cpu_to_be16(0x0103) +#define PTT_AC_COOKIE __cpu_to_be16(0x0104) +#define PTT_VENDOR __cpu_to_be16(0x0105) +#define PTT_RELAY_SID __cpu_to_be16(0x0110) +#define PTT_SRV_ERR __cpu_to_be16(0x0201) +#define PTT_SYS_ERR __cpu_to_be16(0x0202) +#define PTT_GEN_ERR __cpu_to_be16(0x0203) struct pppoe_hdr { #if defined(__LITTLE_ENDIAN_BITFIELD) diff --git a/include/linux/if_tunnel.h b/include/linux/if_tunnel.h index 82c43624c06..5a9aae4adb4 100644 --- a/include/linux/if_tunnel.h +++ b/include/linux/if_tunnel.h @@ -16,14 +16,14 @@ #define SIOCDELPRL (SIOCDEVPRIVATE + 6) #define SIOCCHGPRL (SIOCDEVPRIVATE + 7) -#define GRE_CSUM __constant_htons(0x8000) -#define GRE_ROUTING __constant_htons(0x4000) -#define GRE_KEY __constant_htons(0x2000) -#define GRE_SEQ __constant_htons(0x1000) -#define GRE_STRICT __constant_htons(0x0800) -#define GRE_REC __constant_htons(0x0700) -#define GRE_FLAGS __constant_htons(0x00F8) -#define GRE_VERSION __constant_htons(0x0007) +#define GRE_CSUM __cpu_to_be16(0x8000) +#define GRE_ROUTING __cpu_to_be16(0x4000) +#define GRE_KEY __cpu_to_be16(0x2000) +#define GRE_SEQ __cpu_to_be16(0x1000) +#define GRE_STRICT __cpu_to_be16(0x0800) +#define GRE_REC __cpu_to_be16(0x0700) +#define GRE_FLAGS __cpu_to_be16(0x00F8) +#define GRE_VERSION __cpu_to_be16(0x0007) struct ip_tunnel_parm { diff --git a/include/linux/ncp_no.h b/include/linux/ncp_no.h index f56a696a7cc..cddaa48fb18 100644 --- a/include/linux/ncp_no.h +++ b/include/linux/ncp_no.h @@ -2,18 +2,18 @@ #define _NCP_NO /* these define the attribute byte as seen by NCP */ -#define aRONLY (__constant_cpu_to_le32(1)) -#define aHIDDEN (__constant_cpu_to_le32(2)) -#define aSYSTEM (__constant_cpu_to_le32(4)) -#define aEXECUTE (__constant_cpu_to_le32(8)) -#define aDIR (__constant_cpu_to_le32(0x10)) -#define aARCH (__constant_cpu_to_le32(0x20)) -#define aSHARED (__constant_cpu_to_le32(0x80)) -#define aDONTSUBALLOCATE (__constant_cpu_to_le32(1L<<11)) -#define aTRANSACTIONAL (__constant_cpu_to_le32(1L<<12)) -#define aPURGE (__constant_cpu_to_le32(1L<<16)) -#define aRENAMEINHIBIT (__constant_cpu_to_le32(1L<<17)) -#define aDELETEINHIBIT (__constant_cpu_to_le32(1L<<18)) -#define aDONTCOMPRESS (__constant_cpu_to_le32(1L<<27)) +#define aRONLY (__cpu_to_le32(1)) +#define aHIDDEN (__cpu_to_le32(2)) +#define aSYSTEM (__cpu_to_le32(4)) +#define aEXECUTE (__cpu_to_le32(8)) +#define aDIR (__cpu_to_le32(0x10)) +#define aARCH (__cpu_to_le32(0x20)) +#define aSHARED (__cpu_to_le32(0x80)) +#define aDONTSUBALLOCATE (__cpu_to_le32(1L<<11)) +#define aTRANSACTIONAL (__cpu_to_le32(1L<<12)) +#define aPURGE (__cpu_to_le32(1L<<16)) +#define aRENAMEINHIBIT (__cpu_to_le32(1L<<17)) +#define aDELETEINHIBIT (__cpu_to_le32(1L<<18)) +#define aDONTCOMPRESS (__cpu_to_le32(1L<<27)) #endif /* _NCP_NO */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 355662aac94..bd8b4ca85a2 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1863,7 +1863,7 @@ static inline int skb_bond_should_drop(struct sk_buff *skb) if (dev->priv_flags & IFF_SLAVE_INACTIVE) { if ((dev->priv_flags & IFF_SLAVE_NEEDARP) && - skb->protocol == __constant_htons(ETH_P_ARP)) + skb->protocol == __cpu_to_be16(ETH_P_ARP)) return 0; if (master->priv_flags & IFF_MASTER_ALB) { @@ -1872,7 +1872,7 @@ static inline int skb_bond_should_drop(struct sk_buff *skb) return 0; } if (master->priv_flags & IFF_MASTER_8023AD && - skb->protocol == __constant_htons(ETH_P_SLOW)) + skb->protocol == __cpu_to_be16(ETH_P_SLOW)) return 0; return 1; diff --git a/include/linux/netfilter_bridge.h b/include/linux/netfilter_bridge.h index 499aa937590..f8105e54716 100644 --- a/include/linux/netfilter_bridge.h +++ b/include/linux/netfilter_bridge.h @@ -59,9 +59,9 @@ static inline int nf_bridge_maybe_copy_header(struct sk_buff *skb) static inline unsigned int nf_bridge_encap_header_len(const struct sk_buff *skb) { switch (skb->protocol) { - case __constant_htons(ETH_P_8021Q): + case __cpu_to_be16(ETH_P_8021Q): return VLAN_HLEN; - case __constant_htons(ETH_P_PPP_SES): + case __cpu_to_be16(ETH_P_PPP_SES): return PPPOE_SES_HLEN; default: return 0; diff --git a/include/linux/pim.h b/include/linux/pim.h index 1ba0661561a..252bf6644c5 100644 --- a/include/linux/pim.h +++ b/include/linux/pim.h @@ -4,14 +4,14 @@ #include /* Message types - V1 */ -#define PIM_V1_VERSION __constant_htonl(0x10000000) +#define PIM_V1_VERSION cpu_to_be32(0x10000000) #define PIM_V1_REGISTER 1 /* Message types - V2 */ #define PIM_VERSION 2 #define PIM_REGISTER 1 -#define PIM_NULL_REGISTER __constant_htonl(0x40000000) +#define PIM_NULL_REGISTER cpu_to_be32(0x40000000) /* PIMv2 register message header layout (ietf-draft-idmr-pimvsm-v2-00.ps */ struct pimreghdr diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 8ba1c320f97..bd50b371ffa 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -172,35 +172,35 @@ typedef struct sctp_paramhdr { typedef enum { /* RFC 2960 Section 3.3.5 */ - SCTP_PARAM_HEARTBEAT_INFO = __constant_htons(1), + SCTP_PARAM_HEARTBEAT_INFO = cpu_to_be16(1), /* RFC 2960 Section 3.3.2.1 */ - SCTP_PARAM_IPV4_ADDRESS = __constant_htons(5), - SCTP_PARAM_IPV6_ADDRESS = __constant_htons(6), - SCTP_PARAM_STATE_COOKIE = __constant_htons(7), - SCTP_PARAM_UNRECOGNIZED_PARAMETERS = __constant_htons(8), - SCTP_PARAM_COOKIE_PRESERVATIVE = __constant_htons(9), - SCTP_PARAM_HOST_NAME_ADDRESS = __constant_htons(11), - SCTP_PARAM_SUPPORTED_ADDRESS_TYPES = __constant_htons(12), - SCTP_PARAM_ECN_CAPABLE = __constant_htons(0x8000), + SCTP_PARAM_IPV4_ADDRESS = cpu_to_be16(5), + SCTP_PARAM_IPV6_ADDRESS = cpu_to_be16(6), + SCTP_PARAM_STATE_COOKIE = cpu_to_be16(7), + SCTP_PARAM_UNRECOGNIZED_PARAMETERS = cpu_to_be16(8), + SCTP_PARAM_COOKIE_PRESERVATIVE = cpu_to_be16(9), + SCTP_PARAM_HOST_NAME_ADDRESS = cpu_to_be16(11), + SCTP_PARAM_SUPPORTED_ADDRESS_TYPES = cpu_to_be16(12), + SCTP_PARAM_ECN_CAPABLE = cpu_to_be16(0x8000), /* AUTH Extension Section 3 */ - SCTP_PARAM_RANDOM = __constant_htons(0x8002), - SCTP_PARAM_CHUNKS = __constant_htons(0x8003), - SCTP_PARAM_HMAC_ALGO = __constant_htons(0x8004), + SCTP_PARAM_RANDOM = cpu_to_be16(0x8002), + SCTP_PARAM_CHUNKS = cpu_to_be16(0x8003), + SCTP_PARAM_HMAC_ALGO = cpu_to_be16(0x8004), /* Add-IP: Supported Extensions, Section 4.2 */ - SCTP_PARAM_SUPPORTED_EXT = __constant_htons(0x8008), + SCTP_PARAM_SUPPORTED_EXT = cpu_to_be16(0x8008), /* PR-SCTP Sec 3.1 */ - SCTP_PARAM_FWD_TSN_SUPPORT = __constant_htons(0xc000), + SCTP_PARAM_FWD_TSN_SUPPORT = cpu_to_be16(0xc000), /* Add-IP Extension. Section 3.2 */ - SCTP_PARAM_ADD_IP = __constant_htons(0xc001), - SCTP_PARAM_DEL_IP = __constant_htons(0xc002), - SCTP_PARAM_ERR_CAUSE = __constant_htons(0xc003), - SCTP_PARAM_SET_PRIMARY = __constant_htons(0xc004), - SCTP_PARAM_SUCCESS_REPORT = __constant_htons(0xc005), - SCTP_PARAM_ADAPTATION_LAYER_IND = __constant_htons(0xc006), + SCTP_PARAM_ADD_IP = cpu_to_be16(0xc001), + SCTP_PARAM_DEL_IP = cpu_to_be16(0xc002), + SCTP_PARAM_ERR_CAUSE = cpu_to_be16(0xc003), + SCTP_PARAM_SET_PRIMARY = cpu_to_be16(0xc004), + SCTP_PARAM_SUCCESS_REPORT = cpu_to_be16(0xc005), + SCTP_PARAM_ADAPTATION_LAYER_IND = cpu_to_be16(0xc006), } sctp_param_t; /* enum */ @@ -212,13 +212,13 @@ typedef enum { * */ typedef enum { - SCTP_PARAM_ACTION_DISCARD = __constant_htons(0x0000), - SCTP_PARAM_ACTION_DISCARD_ERR = __constant_htons(0x4000), - SCTP_PARAM_ACTION_SKIP = __constant_htons(0x8000), - SCTP_PARAM_ACTION_SKIP_ERR = __constant_htons(0xc000), + SCTP_PARAM_ACTION_DISCARD = cpu_to_be16(0x0000), + SCTP_PARAM_ACTION_DISCARD_ERR = cpu_to_be16(0x4000), + SCTP_PARAM_ACTION_SKIP = cpu_to_be16(0x8000), + SCTP_PARAM_ACTION_SKIP_ERR = cpu_to_be16(0xc000), } sctp_param_action_t; -enum { SCTP_PARAM_ACTION_MASK = __constant_htons(0xc000), }; +enum { SCTP_PARAM_ACTION_MASK = cpu_to_be16(0xc000), }; /* RFC 2960 Section 3.3.1 Payload Data (DATA) (0) */ @@ -457,17 +457,17 @@ typedef struct sctp_operr_chunk { */ typedef enum { - SCTP_ERROR_NO_ERROR = __constant_htons(0x00), - SCTP_ERROR_INV_STRM = __constant_htons(0x01), - SCTP_ERROR_MISS_PARAM = __constant_htons(0x02), - SCTP_ERROR_STALE_COOKIE = __constant_htons(0x03), - SCTP_ERROR_NO_RESOURCE = __constant_htons(0x04), - SCTP_ERROR_DNS_FAILED = __constant_htons(0x05), - SCTP_ERROR_UNKNOWN_CHUNK = __constant_htons(0x06), - SCTP_ERROR_INV_PARAM = __constant_htons(0x07), - SCTP_ERROR_UNKNOWN_PARAM = __constant_htons(0x08), - SCTP_ERROR_NO_DATA = __constant_htons(0x09), - SCTP_ERROR_COOKIE_IN_SHUTDOWN = __constant_htons(0x0a), + SCTP_ERROR_NO_ERROR = cpu_to_be16(0x00), + SCTP_ERROR_INV_STRM = cpu_to_be16(0x01), + SCTP_ERROR_MISS_PARAM = cpu_to_be16(0x02), + SCTP_ERROR_STALE_COOKIE = cpu_to_be16(0x03), + SCTP_ERROR_NO_RESOURCE = cpu_to_be16(0x04), + SCTP_ERROR_DNS_FAILED = cpu_to_be16(0x05), + SCTP_ERROR_UNKNOWN_CHUNK = cpu_to_be16(0x06), + SCTP_ERROR_INV_PARAM = cpu_to_be16(0x07), + SCTP_ERROR_UNKNOWN_PARAM = cpu_to_be16(0x08), + SCTP_ERROR_NO_DATA = cpu_to_be16(0x09), + SCTP_ERROR_COOKIE_IN_SHUTDOWN = cpu_to_be16(0x0a), /* SCTP Implementation Guide: @@ -476,9 +476,9 @@ typedef enum { * 13 Protocol Violation */ - SCTP_ERROR_RESTART = __constant_htons(0x0b), - SCTP_ERROR_USER_ABORT = __constant_htons(0x0c), - SCTP_ERROR_PROTO_VIOLATION = __constant_htons(0x0d), + SCTP_ERROR_RESTART = cpu_to_be16(0x0b), + SCTP_ERROR_USER_ABORT = cpu_to_be16(0x0c), + SCTP_ERROR_PROTO_VIOLATION = cpu_to_be16(0x0d), /* ADDIP Section 3.3 New Error Causes * @@ -493,11 +493,11 @@ typedef enum { * 0x0103 Association Aborted due to illegal ASCONF-ACK * 0x0104 Request refused - no authorization. */ - SCTP_ERROR_DEL_LAST_IP = __constant_htons(0x0100), - SCTP_ERROR_RSRC_LOW = __constant_htons(0x0101), - SCTP_ERROR_DEL_SRC_IP = __constant_htons(0x0102), - SCTP_ERROR_ASCONF_ACK = __constant_htons(0x0103), - SCTP_ERROR_REQ_REFUSED = __constant_htons(0x0104), + SCTP_ERROR_DEL_LAST_IP = cpu_to_be16(0x0100), + SCTP_ERROR_RSRC_LOW = cpu_to_be16(0x0101), + SCTP_ERROR_DEL_SRC_IP = cpu_to_be16(0x0102), + SCTP_ERROR_ASCONF_ACK = cpu_to_be16(0x0103), + SCTP_ERROR_REQ_REFUSED = cpu_to_be16(0x0104), /* AUTH Section 4. New Error Cause * @@ -509,7 +509,7 @@ typedef enum { * -------------------------------------------------------------- * 0x0105 Unsupported HMAC Identifier */ - SCTP_ERROR_UNSUP_HMAC = __constant_htons(0x0105) + SCTP_ERROR_UNSUP_HMAC = cpu_to_be16(0x0105) } sctp_error_t; diff --git a/include/linux/tcp.h b/include/linux/tcp.h index fe77e1499ab..0cd99e6baca 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -69,16 +69,16 @@ union tcp_word_hdr { #define tcp_flag_word(tp) ( ((union tcp_word_hdr *)(tp))->words [3]) enum { - TCP_FLAG_CWR = __constant_htonl(0x00800000), - TCP_FLAG_ECE = __constant_htonl(0x00400000), - TCP_FLAG_URG = __constant_htonl(0x00200000), - TCP_FLAG_ACK = __constant_htonl(0x00100000), - TCP_FLAG_PSH = __constant_htonl(0x00080000), - TCP_FLAG_RST = __constant_htonl(0x00040000), - TCP_FLAG_SYN = __constant_htonl(0x00020000), - TCP_FLAG_FIN = __constant_htonl(0x00010000), - TCP_RESERVED_BITS = __constant_htonl(0x0F000000), - TCP_DATA_OFFSET = __constant_htonl(0xF0000000) + TCP_FLAG_CWR = __cpu_to_be32(0x00800000), + TCP_FLAG_ECE = __cpu_to_be32(0x00400000), + TCP_FLAG_URG = __cpu_to_be32(0x00200000), + TCP_FLAG_ACK = __cpu_to_be32(0x00100000), + TCP_FLAG_PSH = __cpu_to_be32(0x00080000), + TCP_FLAG_RST = __cpu_to_be32(0x00040000), + TCP_FLAG_SYN = __cpu_to_be32(0x00020000), + TCP_FLAG_FIN = __cpu_to_be32(0x00010000), + TCP_RESERVED_BITS = __cpu_to_be32(0x0F000000), + TCP_DATA_OFFSET = __cpu_to_be32(0xF0000000) }; /* TCP socket options */ -- cgit v1.2.3 From a038a353c3de4040d8445ec568acebdac144436f Mon Sep 17 00:00:00 2001 From: Patrick Ohly Date: Thu, 12 Feb 2009 05:03:34 +0000 Subject: clocksource: allow usage independent of timekeeping.c So far struct clocksource acted as the interface between time/timekeeping.c and hardware. This patch generalizes the concept so that a similar interface can also be used in other contexts. For that it introduces new structures and related functions *without* touching the existing struct clocksource. The reasons for adding these new structures to clocksource.[ch] are * the APIs are clearly related * struct clocksource could be cleaned up to use the new structs * avoids proliferation of files with similar names (timesource.h? timecounter.h?) As outlined in the discussion with John Stultz, this patch adds * struct cyclecounter: stateless API to hardware which counts clock cycles * struct timecounter: stateful utility code built on a cyclecounter which provides a nanosecond counter * only the function to read the nanosecond counter; deltas are used internally and not exposed to users of timecounter The code does no locking of the shared state. It must be called at least as often as the cycle counter wraps around to detect these wrap arounds. Both is the responsibility of the timecounter user. Acked-by: John Stultz Signed-off-by: Patrick Ohly Signed-off-by: David S. Miller --- include/linux/clocksource.h | 101 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 101 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index f88d32f8ff7..573819ef4cc 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -21,9 +21,110 @@ typedef u64 cycle_t; struct clocksource; +/** + * struct cyclecounter - hardware abstraction for a free running counter + * Provides completely state-free accessors to the underlying hardware. + * Depending on which hardware it reads, the cycle counter may wrap + * around quickly. Locking rules (if necessary) have to be defined + * by the implementor and user of specific instances of this API. + * + * @read: returns the current cycle value + * @mask: bitmask for two's complement + * subtraction of non 64 bit counters, + * see CLOCKSOURCE_MASK() helper macro + * @mult: cycle to nanosecond multiplier + * @shift: cycle to nanosecond divisor (power of two) + */ +struct cyclecounter { + cycle_t (*read)(const struct cyclecounter *cc); + cycle_t mask; + u32 mult; + u32 shift; +}; + +/** + * struct timecounter - layer above a %struct cyclecounter which counts nanoseconds + * Contains the state needed by timecounter_read() to detect + * cycle counter wrap around. Initialize with + * timecounter_init(). Also used to convert cycle counts into the + * corresponding nanosecond counts with timecounter_cyc2time(). Users + * of this code are responsible for initializing the underlying + * cycle counter hardware, locking issues and reading the time + * more often than the cycle counter wraps around. The nanosecond + * counter will only wrap around after ~585 years. + * + * @cc: the cycle counter used by this instance + * @cycle_last: most recent cycle counter value seen by + * timecounter_read() + * @nsec: continuously increasing count + */ +struct timecounter { + const struct cyclecounter *cc; + cycle_t cycle_last; + u64 nsec; +}; + +/** + * cyclecounter_cyc2ns - converts cycle counter cycles to nanoseconds + * @tc: Pointer to cycle counter. + * @cycles: Cycles + * + * XXX - This could use some mult_lxl_ll() asm optimization. Same code + * as in cyc2ns, but with unsigned result. + */ +static inline u64 cyclecounter_cyc2ns(const struct cyclecounter *cc, + cycle_t cycles) +{ + u64 ret = (u64)cycles; + ret = (ret * cc->mult) >> cc->shift; + return ret; +} + +/** + * timecounter_init - initialize a time counter + * @tc: Pointer to time counter which is to be initialized/reset + * @cc: A cycle counter, ready to be used. + * @start_tstamp: Arbitrary initial time stamp. + * + * After this call the current cycle register (roughly) corresponds to + * the initial time stamp. Every call to timecounter_read() increments + * the time stamp counter by the number of elapsed nanoseconds. + */ +extern void timecounter_init(struct timecounter *tc, + const struct cyclecounter *cc, + u64 start_tstamp); + +/** + * timecounter_read - return nanoseconds elapsed since timecounter_init() + * plus the initial time stamp + * @tc: Pointer to time counter. + * + * In other words, keeps track of time since the same epoch as + * the function which generated the initial time stamp. + */ +extern u64 timecounter_read(struct timecounter *tc); + +/** + * timecounter_cyc2time - convert a cycle counter to same + * time base as values returned by + * timecounter_read() + * @tc: Pointer to time counter. + * @cycle: a value returned by tc->cc->read() + * + * Cycle counts that are converted correctly as long as they + * fall into the interval [-1/2 max cycle count, +1/2 max cycle count], + * with "max cycle count" == cs->mask+1. + * + * This allows conversion of cycle counter values which were generated + * in the past. + */ +extern u64 timecounter_cyc2time(struct timecounter *tc, + cycle_t cycle_tstamp); + /** * struct clocksource - hardware abstraction for a free running counter * Provides mostly state-free accessors to the underlying hardware. + * This is the structure used for system time. * * @name: ptr to clocksource name * @list: list head for registration -- cgit v1.2.3 From a75244c3d519fcb490ca2bf3f123c98017f1e8d0 Mon Sep 17 00:00:00 2001 From: Patrick Ohly Date: Thu, 12 Feb 2009 05:03:35 +0000 Subject: timecompare: generic infrastructure to map between two time bases Mapping from a struct timecounter to a time returned by functions like ktime_get_real() is implemented. This is sufficient to use this code in a network device driver which wants to support hardware time stamping and transformation of hardware time stamps to system time. The interface could have been made more versatile by not depending on a time counter, but this wasn't done to avoid writing glue code elsewhere. The method implemented here is the one used and analyzed under the name "assisted PTP" in the LCI PTP paper: http://www.linuxclustersinstitute.org/conferences/archive/2008/PDF/Ohly_92221.pdf Acked-by: John Stultz Signed-off-by: Patrick Ohly Signed-off-by: David S. Miller --- include/linux/timecompare.h | 125 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 125 insertions(+) create mode 100644 include/linux/timecompare.h (limited to 'include/linux') diff --git a/include/linux/timecompare.h b/include/linux/timecompare.h new file mode 100644 index 00000000000..546e2234e4b --- /dev/null +++ b/include/linux/timecompare.h @@ -0,0 +1,125 @@ +/* + * Utility code which helps transforming between two different time + * bases, called "source" and "target" time in this code. + * + * Source time has to be provided via the timecounter API while target + * time is accessed via a function callback whose prototype + * intentionally matches ktime_get() and ktime_get_real(). These + * interfaces where chosen like this so that the code serves its + * initial purpose without additional glue code. + * + * This purpose is synchronizing a hardware clock in a NIC with system + * time, in order to implement the Precision Time Protocol (PTP, + * IEEE1588) with more accurate hardware assisted time stamping. In + * that context only synchronization against system time (= + * ktime_get_real()) is currently needed. But this utility code might + * become useful in other situations, which is why it was written as + * general purpose utility code. + * + * The source timecounter is assumed to return monotonically + * increasing time (but this code does its best to compensate if that + * is not the case) whereas target time may jump. + * + * The target time corresponding to a source time is determined by + * reading target time, reading source time, reading target time + * again, then assuming that average target time corresponds to source + * time. In other words, the assumption is that reading the source + * time is slow and involves equal time for sending the request and + * receiving the reply, whereas reading target time is assumed to be + * fast. + * + * Copyright (C) 2009 Intel Corporation. + * Author: Patrick Ohly + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. * See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program; if not, write to the Free Software Foundation, Inc., + * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + */ +#ifndef _LINUX_TIMECOMPARE_H +#define _LINUX_TIMECOMPARE_H + +#include +#include + +/** + * struct timecompare - stores state and configuration for the two clocks + * + * Initialize to zero, then set source/target/num_samples. + * + * Transformation between source time and target time is done with: + * target_time = source_time + offset + + * (source_time - last_update) * skew / + * TIMECOMPARE_SKEW_RESOLUTION + * + * @source: used to get source time stamps via timecounter_read() + * @target: function returning target time (for example, ktime_get + * for monotonic time, or ktime_get_real for wall clock) + * @num_samples: number of times that source time and target time are to + * be compared when determining their offset + * @offset: (target time - source time) at the time of the last update + * @skew: average (target time - source time) / delta source time * + * TIMECOMPARE_SKEW_RESOLUTION + * @last_update: last source time stamp when time offset was measured + */ +struct timecompare { + struct timecounter *source; + ktime_t (*target)(void); + int num_samples; + + s64 offset; + s64 skew; + u64 last_update; +}; + +/** + * timecompare_transform - transform source time stamp into target time base + * @sync: context for time sync + * @source_tstamp: the result of timecounter_read() or + * timecounter_cyc2time() + */ +extern ktime_t timecompare_transform(struct timecompare *sync, + u64 source_tstamp); + +/** + * timecompare_offset - measure current (target time - source time) offset + * @sync: context for time sync + * @offset: average offset during sample period returned here + * @source_tstamp: average source time during sample period returned here + * + * Returns number of samples used. Might be zero (= no result) in the + * unlikely case that target time was monotonically decreasing for all + * samples (= broken). + */ +extern int timecompare_offset(struct timecompare *sync, + s64 *offset, + u64 *source_tstamp); + +extern void __timecompare_update(struct timecompare *sync, + u64 source_tstamp); + +/** + * timecompare_update - update offset and skew by measuring current offset + * @sync: context for time sync + * @source_tstamp: the result of timecounter_read() or + * timecounter_cyc2time(), pass zero to force update + * + * Updates are only done at most once per second. + */ +static inline void timecompare_update(struct timecompare *sync, + u64 source_tstamp) +{ + if (!source_tstamp || + (s64)(source_tstamp - sync->last_update) >= NSEC_PER_SEC) + __timecompare_update(sync, source_tstamp); +} + +#endif /* _LINUX_TIMECOMPARE_H */ -- cgit v1.2.3 From cb9eff097831007afb30d64373f29d99825d0068 Mon Sep 17 00:00:00 2001 From: Patrick Ohly Date: Thu, 12 Feb 2009 05:03:36 +0000 Subject: net: new user space API for time stamping of incoming and outgoing packets User space can request hardware and/or software time stamping. Reporting of the result(s) via a new control message is enabled separately for each field in the message because some of the fields may require additional computation and thus cause overhead. User space can tell the different kinds of time stamps apart and choose what suits its needs. When a TX timestamp operation is requested, the TX skb will be cloned and the clone will be time stamped (in hardware or software) and added to the socket error queue of the skb, if the skb has a socket associated with it. The actual TX timestamp will reach userspace as a RX timestamp on the cloned packet. If timestamping is requested and no timestamping is done in the device driver (potentially this may use hardware timestamping), it will be done in software after the device's start_hard_xmit routine. Signed-off-by: Patrick Ohly Signed-off-by: David S. Miller --- include/linux/errqueue.h | 1 + include/linux/net_tstamp.h | 104 +++++++++++++++++++++++++++++++++++++++++++++ include/linux/sockios.h | 3 ++ 3 files changed, 108 insertions(+) create mode 100644 include/linux/net_tstamp.h (limited to 'include/linux') diff --git a/include/linux/errqueue.h b/include/linux/errqueue.h index ceb1454b697..ec12cc74366 100644 --- a/include/linux/errqueue.h +++ b/include/linux/errqueue.h @@ -18,6 +18,7 @@ struct sock_extended_err #define SO_EE_ORIGIN_LOCAL 1 #define SO_EE_ORIGIN_ICMP 2 #define SO_EE_ORIGIN_ICMP6 3 +#define SO_EE_ORIGIN_TIMESTAMPING 4 #define SO_EE_OFFENDER(ee) ((struct sockaddr*)((ee)+1)) diff --git a/include/linux/net_tstamp.h b/include/linux/net_tstamp.h new file mode 100644 index 00000000000..a3b8546354a --- /dev/null +++ b/include/linux/net_tstamp.h @@ -0,0 +1,104 @@ +/* + * Userspace API for hardware time stamping of network packets + * + * Copyright (C) 2008,2009 Intel Corporation + * Author: Patrick Ohly + * + */ + +#ifndef _NET_TIMESTAMPING_H +#define _NET_TIMESTAMPING_H + +#include /* for SO_TIMESTAMPING */ + +/* SO_TIMESTAMPING gets an integer bit field comprised of these values */ +enum { + SOF_TIMESTAMPING_TX_HARDWARE = (1<<0), + SOF_TIMESTAMPING_TX_SOFTWARE = (1<<1), + SOF_TIMESTAMPING_RX_HARDWARE = (1<<2), + SOF_TIMESTAMPING_RX_SOFTWARE = (1<<3), + SOF_TIMESTAMPING_SOFTWARE = (1<<4), + SOF_TIMESTAMPING_SYS_HARDWARE = (1<<5), + SOF_TIMESTAMPING_RAW_HARDWARE = (1<<6), + SOF_TIMESTAMPING_MASK = + (SOF_TIMESTAMPING_RAW_HARDWARE - 1) | + SOF_TIMESTAMPING_RAW_HARDWARE +}; + +/** + * struct hwtstamp_config - %SIOCSHWTSTAMP parameter + * + * @flags: no flags defined right now, must be zero + * @tx_type: one of HWTSTAMP_TX_* + * @rx_type: one of one of HWTSTAMP_FILTER_* + * + * %SIOCSHWTSTAMP expects a &struct ifreq with a ifr_data pointer to + * this structure. dev_ifsioc() in the kernel takes care of the + * translation between 32 bit userspace and 64 bit kernel. The + * structure is intentionally chosen so that it has the same layout on + * 32 and 64 bit systems, don't break this! + */ +struct hwtstamp_config { + int flags; + int tx_type; + int rx_filter; +}; + +/* possible values for hwtstamp_config->tx_type */ +enum { + /* + * No outgoing packet will need hardware time stamping; + * should a packet arrive which asks for it, no hardware + * time stamping will be done. + */ + HWTSTAMP_TX_OFF, + + /* + * Enables hardware time stamping for outgoing packets; + * the sender of the packet decides which are to be + * time stamped by setting %SOF_TIMESTAMPING_TX_SOFTWARE + * before sending the packet. + */ + HWTSTAMP_TX_ON, +}; + +/* possible values for hwtstamp_config->rx_filter */ +enum { + /* time stamp no incoming packet at all */ + HWTSTAMP_FILTER_NONE, + + /* time stamp any incoming packet */ + HWTSTAMP_FILTER_ALL, + + /* return value: time stamp all packets requested plus some others */ + HWTSTAMP_FILTER_SOME, + + /* PTP v1, UDP, any kind of event packet */ + HWTSTAMP_FILTER_PTP_V1_L4_EVENT, + /* PTP v1, UDP, Sync packet */ + HWTSTAMP_FILTER_PTP_V1_L4_SYNC, + /* PTP v1, UDP, Delay_req packet */ + HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ, + /* PTP v2, UDP, any kind of event packet */ + HWTSTAMP_FILTER_PTP_V2_L4_EVENT, + /* PTP v2, UDP, Sync packet */ + HWTSTAMP_FILTER_PTP_V2_L4_SYNC, + /* PTP v2, UDP, Delay_req packet */ + HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ, + + /* 802.AS1, Ethernet, any kind of event packet */ + HWTSTAMP_FILTER_PTP_V2_L2_EVENT, + /* 802.AS1, Ethernet, Sync packet */ + HWTSTAMP_FILTER_PTP_V2_L2_SYNC, + /* 802.AS1, Ethernet, Delay_req packet */ + HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ, + + /* PTP v2/802.AS1, any layer, any kind of event packet */ + HWTSTAMP_FILTER_PTP_V2_EVENT, + /* PTP v2/802.AS1, any layer, Sync packet */ + HWTSTAMP_FILTER_PTP_V2_SYNC, + /* PTP v2/802.AS1, any layer, Delay_req packet */ + HWTSTAMP_FILTER_PTP_V2_DELAY_REQ, +}; + +#endif /* _NET_TIMESTAMPING_H */ diff --git a/include/linux/sockios.h b/include/linux/sockios.h index abef7596655..241f179347d 100644 --- a/include/linux/sockios.h +++ b/include/linux/sockios.h @@ -122,6 +122,9 @@ #define SIOCBRADDIF 0x89a2 /* add interface to bridge */ #define SIOCBRDELIF 0x89a3 /* remove interface from bridge */ +/* hardware time stamping: parameters in linux/net_tstamp.h */ +#define SIOCSHWTSTAMP 0x89b0 + /* Device private ioctl calls */ /* -- cgit v1.2.3 From ac45f602ee3d1b6f326f68bc0c2591ceebf05ba4 Mon Sep 17 00:00:00 2001 From: Patrick Ohly Date: Thu, 12 Feb 2009 05:03:37 +0000 Subject: net: infrastructure for hardware time stamping The additional per-packet information (16 bytes for time stamps, 1 byte for flags) is stored for all packets in the skb_shared_info struct. This implementation detail is hidden from users of that information via skb_* accessor functions. A separate struct resp. union is used for the additional information so that it can be stored/copied easily outside of skb_shared_info. Compared to previous implementations (reusing the tstamp field depending on the context, optional additional structures) this is the simplest solution. It does not extend sk_buff itself. TX time stamping is implemented in software if the device driver doesn't support hardware time stamping. The new semantic for hardware/software time stamping around ndo_start_xmit() is based on two assumptions about existing network device drivers which don't support hardware time stamping and know nothing about it: - they leave the new skb_shared_tx unmodified - the keep the connection to the originating socket in skb->sk alive, i.e., don't call skb_orphan() Given that skb_shared_tx is new, the first assumption is safe. The second is only true for some drivers. As a result, software TX time stamping currently works with the bnx2 driver, but not with the unmodified igb driver (the two drivers this patch series was tested with). Signed-off-by: Patrick Ohly Signed-off-by: David S. Miller --- include/linux/skbuff.h | 91 +++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 90 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 92470084458..f96bc91bf0a 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -132,6 +132,57 @@ struct skb_frag_struct { __u32 size; }; +#define HAVE_HW_TIME_STAMP + +/** + * skb_shared_hwtstamps - hardware time stamps + * + * @hwtstamp: hardware time stamp transformed into duration + * since arbitrary point in time + * @syststamp: hwtstamp transformed to system time base + * + * Software time stamps generated by ktime_get_real() are stored in + * skb->tstamp. The relation between the different kinds of time + * stamps is as follows: + * + * syststamp and tstamp can be compared against each other in + * arbitrary combinations. The accuracy of a + * syststamp/tstamp/"syststamp from other device" comparison is + * limited by the accuracy of the transformation into system time + * base. This depends on the device driver and its underlying + * hardware. + * + * hwtstamps can only be compared against other hwtstamps from + * the same device. + * + * This structure is attached to packets as part of the + * &skb_shared_info. Use skb_hwtstamps() to get a pointer. + */ +struct skb_shared_hwtstamps { + ktime_t hwtstamp; + ktime_t syststamp; +}; + +/** + * skb_shared_tx - instructions for time stamping of outgoing packets + * + * @hardware: generate hardware time stamp + * @software: generate software time stamp + * @in_progress: device driver is going to provide + * hardware time stamp + * + * These flags are attached to packets as part of the + * &skb_shared_info. Use skb_tx() to get a pointer. + */ +union skb_shared_tx { + struct { + __u8 hardware:1, + software:1, + in_progress:1; + }; + __u8 flags; +}; + /* This data is invariant across clones and lives at * the end of the header data, ie. at skb->end. */ @@ -143,10 +194,12 @@ struct skb_shared_info { unsigned short gso_segs; unsigned short gso_type; __be32 ip6_frag_id; + union skb_shared_tx tx_flags; #ifdef CONFIG_HAS_DMA unsigned int num_dma_maps; #endif struct sk_buff *frag_list; + struct skb_shared_hwtstamps hwtstamps; skb_frag_t frags[MAX_SKB_FRAGS]; #ifdef CONFIG_HAS_DMA dma_addr_t dma_maps[MAX_SKB_FRAGS + 1]; @@ -465,6 +518,16 @@ static inline unsigned char *skb_end_pointer(const struct sk_buff *skb) /* Internal */ #define skb_shinfo(SKB) ((struct skb_shared_info *)(skb_end_pointer(SKB))) +static inline struct skb_shared_hwtstamps *skb_hwtstamps(struct sk_buff *skb) +{ + return &skb_shinfo(skb)->hwtstamps; +} + +static inline union skb_shared_tx *skb_tx(struct sk_buff *skb) +{ + return &skb_shinfo(skb)->tx_flags; +} + /** * skb_queue_empty - check if a queue is empty * @list: queue head @@ -1730,6 +1793,11 @@ static inline void skb_copy_to_linear_data_offset(struct sk_buff *skb, extern void skb_init(void); +static inline ktime_t skb_get_ktime(const struct sk_buff *skb) +{ + return skb->tstamp; +} + /** * skb_get_timestamp - get timestamp from a skb * @skb: skb to get stamp from @@ -1739,11 +1807,18 @@ extern void skb_init(void); * This function converts the offset back to a struct timeval and stores * it in stamp. */ -static inline void skb_get_timestamp(const struct sk_buff *skb, struct timeval *stamp) +static inline void skb_get_timestamp(const struct sk_buff *skb, + struct timeval *stamp) { *stamp = ktime_to_timeval(skb->tstamp); } +static inline void skb_get_timestampns(const struct sk_buff *skb, + struct timespec *stamp) +{ + *stamp = ktime_to_timespec(skb->tstamp); +} + static inline void __net_timestamp(struct sk_buff *skb) { skb->tstamp = ktime_get_real(); @@ -1759,6 +1834,20 @@ static inline ktime_t net_invalid_timestamp(void) return ktime_set(0, 0); } +/** + * skb_tstamp_tx - queue clone of skb with send time stamps + * @orig_skb: the original outgoing packet + * @hwtstamps: hardware time stamps, may be NULL if not available + * + * If the skb has a socket associated, then this function clones the + * skb (thus sharing the actual data and optional structures), stores + * the optional hardware time stamping information (if non NULL) or + * generates a software time stamp (otherwise), then queues the clone + * to the error queue of the socket. Errors are silently ignored. + */ +extern void skb_tstamp_tx(struct sk_buff *orig_skb, + struct skb_shared_hwtstamps *hwtstamps); + extern __sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len); extern __sum16 __skb_checksum_complete(struct sk_buff *skb); -- cgit v1.2.3 From 4458f04c02a46c679a90ef71f866a415c192deb4 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Fri, 13 Feb 2009 08:33:42 +0000 Subject: sctp: Clean up sctp checksumming code The sctp crc32c checksum is always generated in little endian. So, we clean up the code to treat it as little endian and remove all the __force casts. Suggested by Herbert Xu. Signed-off-by: Vlad Yasevich Signed-off-by: David S. Miller --- include/linux/sctp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index bd50b371ffa..c2731bfe04d 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -60,7 +60,7 @@ typedef struct sctphdr { __be16 source; __be16 dest; __be32 vtag; - __be32 checksum; + __le32 checksum; } __attribute__((packed)) sctp_sctphdr_t; #ifdef __KERNEL__ -- cgit v1.2.3 From 886a63e865eb346ab20572e802fc3118cb9aee14 Mon Sep 17 00:00:00 2001 From: Hannes Eder Date: Sat, 14 Feb 2009 11:36:20 +0000 Subject: drivers/net/hamradio: fix sparse warnings: fix signedness Fix this sparse warnings: drivers/net/hamradio/hdlcdrv.c:274:34: warning: incorrect type in argument 2 (different signedness) drivers/net/hamradio/hdlcdrv.c:279:47: warning: incorrect type in argument 2 (different signedness) drivers/net/hamradio/hdlcdrv.c:288:39: warning: incorrect type in argument 2 (different signedness) drivers/net/hamradio/hdlcdrv.c:300:47: warning: incorrect type in argument 2 (different signedness) Signed-off-by: Hannes Eder Signed-off-by: David S. Miller --- include/linux/hdlcdrv.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hdlcdrv.h b/include/linux/hdlcdrv.h index 0821bac62b8..c010b4a785b 100644 --- a/include/linux/hdlcdrv.h +++ b/include/linux/hdlcdrv.h @@ -215,7 +215,7 @@ struct hdlcdrv_state { struct hdlcdrv_hdlctx { struct hdlcdrv_hdlcbuffer hbuf; - long in_hdlc_tx; + unsigned long in_hdlc_tx; /* * 0 = send flags * 1 = send txtail (flags) -- cgit v1.2.3 From 3f683d6175748ef9daf4698d9ef5a488dd037063 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Wed, 18 Feb 2009 16:56:59 +0800 Subject: crypto: api - Fix crypto_alloc_tfm/create_create_tfm return convention This is based on a report and patch by Geert Uytterhoeven. The functions crypto_alloc_tfm and create_create_tfm return a pointer that needs to be adjusted by the caller when successful and otherwise an error value. This means that the caller has to check for the error and only perform the adjustment if the pointer returned is valid. Since all callers want to make the adjustment and we know how to adjust it ourselves, it's much easier to just return adjusted pointer directly. The only caveat is that we have to return a void * instead of struct crypto_tfm *. However, this isn't that bad because both of these functions are for internal use only (by types code like shash.c, not even algorithms code). This patch also moves crypto_alloc_tfm into crypto/internal.h (crypto_create_tfm is already there) to reflect this. Signed-off-by: Herbert Xu --- include/linux/crypto.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 1f2e9020acc..29729b83438 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -548,9 +548,6 @@ struct crypto_attr_u32 { * Transform user interface. */ -struct crypto_tfm *crypto_alloc_tfm(const char *alg_name, - const struct crypto_type *frontend, - u32 type, u32 mask); struct crypto_tfm *crypto_alloc_base(const char *alg_name, u32 type, u32 mask); void crypto_destroy_tfm(void *mem, struct crypto_tfm *tfm); -- cgit v1.2.3 From 4a2f965ca5a4e2593744bf75425d85e0e8ff814a Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Wed, 18 Feb 2009 16:29:44 +0100 Subject: netfilter: x_tables: change elements in x_tables Change to proper type on private pointer rather than anonymous void. Keep active elements on same cache line. Signed-off-by: Stephen Hemminger Signed-off-by: Patrick McHardy --- include/linux/netfilter/x_tables.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index c7ee8744d26..9fac88fc0e7 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -349,9 +349,6 @@ struct xt_table { struct list_head list; - /* A unique name... */ - const char name[XT_TABLE_MAXNAMELEN]; - /* What hooks you will enter on */ unsigned int valid_hooks; @@ -359,13 +356,15 @@ struct xt_table rwlock_t lock; /* Man behind the curtain... */ - //struct ip6t_table_info *private; - void *private; + struct xt_table_info *private; /* Set this to THIS_MODULE if you are a module, otherwise NULL */ struct module *me; u_int8_t af; /* address/protocol family */ + + /* A unique name... */ + const char name[XT_TABLE_MAXNAMELEN]; }; #include -- cgit v1.2.3 From 74019224ac34b044b44a31dd89a54e3477db4896 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 18 Feb 2009 12:23:29 +0100 Subject: timers: add mod_timer_pending() Impact: new timer API Based on an idea from Martin Josefsson with the help of Patrick McHardy and Stephen Hemminger: introduce the mod_timer_pending() API which is a mod_timer() offspring that is an invariant on already removed timers. (regular mod_timer() re-activates non-pending timers.) This is useful for the networking code in that it can allow unserialized mod_timer_pending() timer-forwarding calls, but a single del_timer*() will stop the timer from being reactivated again. Also while at it: - optimize the regular mod_timer() path some more, the timer-stat and a debug check was needlessly duplicated in __mod_timer(). - make the exports come straight after the function, as most other exports in timer.c already did. - eliminate __mod_timer() as an external API, change the users to mod_timer(). The regular mod_timer() code path is not impacted significantly, due to inlining optimizations and due to the simplifications. Based-on-patch-from: Stephen Hemminger Acked-by: Stephen Hemminger Cc: "David S. Miller" Cc: Patrick McHardy Cc: netdev@vger.kernel.org Cc: Oleg Nesterov Cc: Andrew Morton Signed-off-by: Ingo Molnar --- include/linux/timer.h | 22 ++-------------------- 1 file changed, 2 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timer.h b/include/linux/timer.h index daf9685b861..e2d662e3416 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -86,8 +86,8 @@ static inline int timer_pending(const struct timer_list * timer) extern void add_timer_on(struct timer_list *timer, int cpu); extern int del_timer(struct timer_list * timer); -extern int __mod_timer(struct timer_list *timer, unsigned long expires); extern int mod_timer(struct timer_list *timer, unsigned long expires); +extern int mod_timer_pending(struct timer_list *timer, unsigned long expires); /* * The jiffies value which is added to now, when there is no timer @@ -146,25 +146,7 @@ static inline void timer_stats_timer_clear_start_info(struct timer_list *timer) } #endif -/** - * add_timer - start a timer - * @timer: the timer to be added - * - * The kernel will do a ->function(->data) callback from the - * timer interrupt at the ->expires point in the future. The - * current time is 'jiffies'. - * - * The timer's ->expires, ->function (and if the handler uses it, ->data) - * fields must be set prior calling this function. - * - * Timers with an ->expires field in the past will be executed in the next - * timer tick. - */ -static inline void add_timer(struct timer_list *timer) -{ - BUG_ON(timer_pending(timer)); - __mod_timer(timer, timer->expires); -} +extern void add_timer(struct timer_list *timer); #ifdef CONFIG_SMP extern int try_to_del_timer_sync(struct timer_list *timer); -- cgit v1.2.3 From 59089d8d162ddcb5c434672e915331964d38a754 Mon Sep 17 00:00:00 2001 From: Santwona Behera Date: Fri, 20 Feb 2009 00:58:13 -0800 Subject: ethtool: Add RX pkt classification interface Signed-off-by: Santwona Behera Signed-off-by: David S. Miller --- include/linux/ethtool.h | 89 +++++++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 83 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 27c67a54223..131b127b70f 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -7,6 +7,7 @@ * Portions Copyright 2002 Intel (eli.kupermann@intel.com, * christopher.leech@intel.com, * scott.feldman@intel.com) + * Portions Copyright (C) Sun Microsystems 2008 */ #ifndef _LINUX_ETHTOOL_H @@ -287,10 +288,75 @@ enum ethtool_flags { ETH_FLAG_LRO = (1 << 15), /* LRO is enabled */ }; -struct ethtool_rxnfc { - __u32 cmd; +/* The following structures are for supporting RX network flow + * classification configuration. Note, all multibyte fields, e.g., + * ip4src, ip4dst, psrc, pdst, spi, etc. are expected to be in network + * byte order. + */ +struct ethtool_tcpip4_spec { + __be32 ip4src; + __be32 ip4dst; + __be16 psrc; + __be16 pdst; + __u8 tos; +}; + +struct ethtool_ah_espip4_spec { + __be32 ip4src; + __be32 ip4dst; + __be32 spi; + __u8 tos; +}; + +struct ethtool_rawip4_spec { + __be32 ip4src; + __be32 ip4dst; + __u8 hdata[64]; +}; + +struct ethtool_ether_spec { + __be16 ether_type; + __u8 frame_size; + __u8 eframe[16]; +}; + +#define ETH_RX_NFC_IP4 1 +#define ETH_RX_NFC_IP6 2 + +struct ethtool_usrip4_spec { + __be32 ip4src; + __be32 ip4dst; + __be32 l4_4_bytes; + __u8 tos; + __u8 ip_ver; + __u8 proto; +}; + +struct ethtool_rx_flow_spec { __u32 flow_type; - __u64 data; + union { + struct ethtool_tcpip4_spec tcp_ip4_spec; + struct ethtool_tcpip4_spec udp_ip4_spec; + struct ethtool_tcpip4_spec sctp_ip4_spec; + struct ethtool_ah_espip4_spec ah_ip4_spec; + struct ethtool_ah_espip4_spec esp_ip4_spec; + struct ethtool_rawip4_spec raw_ip4_spec; + struct ethtool_ether_spec ether_spec; + struct ethtool_usrip4_spec usr_ip4_spec; + __u8 hdata[64]; + } h_u, m_u; /* entry, mask */ + __u64 ring_cookie; + __u32 location; +}; + +struct ethtool_rxnfc { + __u32 cmd; + __u32 flow_type; + /* The rx flow hash value or the rule DB size */ + __u64 data; + struct ethtool_rx_flow_spec fs; + __u32 rule_cnt; + __u32 rule_locs[0]; }; #ifdef __KERNEL__ @@ -417,8 +483,8 @@ struct ethtool_ops { /* the following hooks are obsolete */ int (*self_test_count)(struct net_device *);/* use get_sset_count */ int (*get_stats_count)(struct net_device *);/* use get_sset_count */ - int (*get_rxhash)(struct net_device *, struct ethtool_rxnfc *); - int (*set_rxhash)(struct net_device *, struct ethtool_rxnfc *); + int (*get_rxnfc)(struct net_device *, struct ethtool_rxnfc *, void *); + int (*set_rxnfc)(struct net_device *, struct ethtool_rxnfc *); }; #endif /* __KERNEL__ */ @@ -469,6 +535,12 @@ struct ethtool_ops { #define ETHTOOL_SRXFH 0x0000002a /* Set RX flow hash configuration */ #define ETHTOOL_GGRO 0x0000002b /* Get GRO enable (ethtool_value) */ #define ETHTOOL_SGRO 0x0000002c /* Set GRO enable (ethtool_value) */ +#define ETHTOOL_GRXRINGS 0x0000002d /* Get RX rings available for LB */ +#define ETHTOOL_GRXCLSRLCNT 0x0000002e /* Get RX class rule count */ +#define ETHTOOL_GRXCLSRULE 0x0000002f /* Get RX classification rule */ +#define ETHTOOL_GRXCLSRLALL 0x00000030 /* Get all RX classification rule */ +#define ETHTOOL_SRXCLSRLDEL 0x00000031 /* Delete RX classification rule */ +#define ETHTOOL_SRXCLSRLINS 0x00000032 /* Insert RX classification rule */ /* compatibility with older code */ #define SPARC_ETH_GSET ETHTOOL_GSET @@ -565,9 +637,13 @@ struct ethtool_ops { #define UDP_V6_FLOW 0x06 #define SCTP_V6_FLOW 0x07 #define AH_ESP_V6_FLOW 0x08 +#define AH_V4_FLOW 0x09 +#define ESP_V4_FLOW 0x0a +#define AH_V6_FLOW 0x0b +#define ESP_V6_FLOW 0x0c +#define IP_USER_FLOW 0x0d /* L3-L4 network traffic flow hash options */ -#define RXH_DEV_PORT (1 << 0) #define RXH_L2DA (1 << 1) #define RXH_VLAN (1 << 2) #define RXH_L3_PROTO (1 << 3) @@ -577,5 +653,6 @@ struct ethtool_ops { #define RXH_L4_B_2_3 (1 << 7) /* dst port in case of TCP/UDP/SCTP */ #define RXH_DISCARD (1 << 31) +#define RX_CLS_FLOW_DISC 0xffffffffffffffffULL #endif /* _LINUX_ETHTOOL_H */ -- cgit v1.2.3 From be0c22a46cfb79ab2342bb28fde99afa94ef868e Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 18 Feb 2009 01:40:43 +0000 Subject: netlink: add NETLINK_BROADCAST_ERROR socket option This patch adds NETLINK_BROADCAST_ERROR which is a netlink socket option that the listener can set to make netlink_broadcast() return errors in the delivery to the caller. This option is useful if the caller of netlink_broadcast() do something with the result of the message delivery, like in ctnetlink where it drops a network packet if the event delivery failed, this is used to enable reliable logging and state-synchronization. If this socket option is not set, netlink_broadcast() only reports ESRCH errors and silently ignore ENOBUFS errors, which is what most netlink_broadcast() callers should do. This socket option is based on a suggestion from Patrick McHardy. Patrick McHardy can exchange this patch for a beer from me ;). Signed-off-by: Pablo Neira Ayuso Acked-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 51b09a1f46c..1e6bf995435 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -103,6 +103,7 @@ struct nlmsgerr #define NETLINK_ADD_MEMBERSHIP 1 #define NETLINK_DROP_MEMBERSHIP 2 #define NETLINK_PKTINFO 3 +#define NETLINK_BROADCAST_ERROR 4 struct nl_pktinfo { -- cgit v1.2.3 From 784544739a25c30637397ace5489eeb6e15d7d49 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Fri, 20 Feb 2009 10:35:32 +0100 Subject: netfilter: iptables: lock free counters The reader/writer lock in ip_tables is acquired in the critical path of processing packets and is one of the reasons just loading iptables can cause a 20% performance loss. The rwlock serves two functions: 1) it prevents changes to table state (xt_replace) while table is in use. This is now handled by doing rcu on the xt_table. When table is replaced, the new table(s) are put in and the old one table(s) are freed after RCU period. 2) it provides synchronization when accesing the counter values. This is now handled by swapping in new table_info entries for each cpu then summing the old values, and putting the result back onto one cpu. On a busy system it may cause sampling to occur at different times on each cpu, but no packet/byte counts are lost in the process. Signed-off-by: Stephen Hemminger Sucessfully tested on my dual quad core machine too, but iptables only (no ipv6 here) BTW, my new "tbench 8" result is 2450 MB/s, (it was 2150 MB/s not so long ago) Acked-by: Eric Dumazet Signed-off-by: Patrick McHardy --- include/linux/netfilter/x_tables.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 9fac88fc0e7..e8e08d03675 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -353,7 +353,7 @@ struct xt_table unsigned int valid_hooks; /* Lock for the curtain */ - rwlock_t lock; + struct mutex lock; /* Man behind the curtain... */ struct xt_table_info *private; @@ -385,7 +385,7 @@ struct xt_table_info /* ipt_entry tables: one per CPU */ /* Note : this field MUST be the last one, see XT_TABLE_INFO_SZ */ - char *entries[1]; + void *entries[1]; }; #define XT_TABLE_INFO_SZ (offsetof(struct xt_table_info, entries) \ @@ -432,6 +432,8 @@ extern void xt_proto_fini(struct net *net, u_int8_t af); extern struct xt_table_info *xt_alloc_table_info(unsigned int size); extern void xt_free_table_info(struct xt_table_info *info); +extern void xt_table_entry_swap_rcu(struct xt_table_info *old, + struct xt_table_info *new); #ifdef CONFIG_COMPAT #include -- cgit v1.2.3 From 268cb38e1802db560c73167e643f14a3dcb4b07c Mon Sep 17 00:00:00 2001 From: Adam Nielsen Date: Fri, 20 Feb 2009 10:55:14 +0100 Subject: netfilter: x_tables: add LED trigger target Kernel module providing implementation of LED netfilter target. Each instance of the target appears as a led-trigger device, which can be associated with one or more LEDs in /sys/class/leds/ Signed-off-by: Adam Nielsen Acked-by: Richard Purdie Signed-off-by: Patrick McHardy --- include/linux/netfilter/Kbuild | 1 + include/linux/netfilter/xt_LED.h | 13 +++++++++++++ 2 files changed, 14 insertions(+) create mode 100644 include/linux/netfilter/xt_LED.h (limited to 'include/linux') diff --git a/include/linux/netfilter/Kbuild b/include/linux/netfilter/Kbuild index 5a8af875bce..deeaee5c83f 100644 --- a/include/linux/netfilter/Kbuild +++ b/include/linux/netfilter/Kbuild @@ -7,6 +7,7 @@ header-y += xt_CLASSIFY.h header-y += xt_CONNMARK.h header-y += xt_CONNSECMARK.h header-y += xt_DSCP.h +header-y += xt_LED.h header-y += xt_MARK.h header-y += xt_NFLOG.h header-y += xt_NFQUEUE.h diff --git a/include/linux/netfilter/xt_LED.h b/include/linux/netfilter/xt_LED.h new file mode 100644 index 00000000000..4c91a0d770d --- /dev/null +++ b/include/linux/netfilter/xt_LED.h @@ -0,0 +1,13 @@ +#ifndef _XT_LED_H +#define _XT_LED_H + +struct xt_led_info { + char id[27]; /* Unique ID for this trigger in the LED class */ + __u8 always_blink; /* Blink even if the LED is already on */ + __u32 delay; /* Delay until LED is switched off after trigger */ + + /* Kernel data used in the module */ + void *internal_data __attribute__((aligned(8))); +}; + +#endif /* _XT_LED_H */ -- cgit v1.2.3 From ffadd4d0feb5376c82dc3a4104731b7ce2794edc Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Tue, 17 Feb 2009 12:05:07 -0500 Subject: SLUB: Introduce and use SLUB_MAX_SIZE and SLUB_PAGE_SHIFT constants As a preparational patch to bump up page allocator pass-through threshold, introduce two new constants SLUB_MAX_SIZE and SLUB_PAGE_SHIFT and convert mm/slub.c to use them. Reported-by: "Zhang, Yanmin" Tested-by: "Zhang, Yanmin" Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/slub_def.h | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 2f5c16b1aac..986e09dcfd8 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -120,11 +120,24 @@ struct kmem_cache { #define KMALLOC_SHIFT_LOW ilog2(KMALLOC_MIN_SIZE) +/* + * Maximum kmalloc object size handled by SLUB. Larger object allocations + * are passed through to the page allocator. The page allocator "fastpath" + * is relatively slow so we need this value sufficiently high so that + * performance critical objects are allocated through the SLUB fastpath. + * + * This should be dropped to PAGE_SIZE / 2 once the page allocator + * "fastpath" becomes competitive with the slab allocator fastpaths. + */ +#define SLUB_MAX_SIZE (PAGE_SIZE) + +#define SLUB_PAGE_SHIFT (PAGE_SHIFT + 1) + /* * We keep the general caches in an array of slab caches that are used for * 2^x bytes of allocations. */ -extern struct kmem_cache kmalloc_caches[PAGE_SHIFT + 1]; +extern struct kmem_cache kmalloc_caches[SLUB_PAGE_SHIFT]; /* * Sorry that the following has to be that ugly but some versions of GCC @@ -212,7 +225,7 @@ static __always_inline void *kmalloc_large(size_t size, gfp_t flags) static __always_inline void *kmalloc(size_t size, gfp_t flags) { if (__builtin_constant_p(size)) { - if (size > PAGE_SIZE) + if (size > SLUB_MAX_SIZE) return kmalloc_large(size, flags); if (!(flags & SLUB_DMA)) { @@ -234,7 +247,7 @@ void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node); static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) { if (__builtin_constant_p(size) && - size <= PAGE_SIZE && !(flags & SLUB_DMA)) { + size <= SLUB_MAX_SIZE && !(flags & SLUB_DMA)) { struct kmem_cache *s = kmalloc_slab(size); if (!s) -- cgit v1.2.3 From 51735a7ca67531267a27b57e5fe20f7815192f9c Mon Sep 17 00:00:00 2001 From: Pekka Enberg Date: Fri, 20 Feb 2009 12:21:33 +0200 Subject: SLUB: Do not pass 8k objects through to the page allocator Increase the maximum object size in SLUB so that 8k objects are not passed through to the page allocator anymore. The network stack uses 8k objects for performance critical operations. The patch is motivated by a SLAB vs. SLUB regression in the netperf benchmark. The problem is that the kfree(skb->head) call in skb_release_data() that is subject to page allocator pass-through as the size passed to __alloc_skb() is larger than 4 KB in this test. As explained by Yanmin Zhang: I use 2.6.29-rc2 kernel to run netperf UDP-U-4k CPU_NUM client/server pair loopback testing on x86-64 machines. Comparing with SLUB, SLAB's result is about 2.3 times of SLUB's. After applying the reverting patch, the result difference between SLUB and SLAB becomes 1% which we might consider as fluctuation. [ penberg@cs.helsinki.fi: fix oops in kmalloc() ] Reported-by: "Zhang, Yanmin" Tested-by: "Zhang, Yanmin" Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/slub_def.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 986e09dcfd8..e217a7a68ea 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -129,9 +129,9 @@ struct kmem_cache { * This should be dropped to PAGE_SIZE / 2 once the page allocator * "fastpath" becomes competitive with the slab allocator fastpaths. */ -#define SLUB_MAX_SIZE (PAGE_SIZE) +#define SLUB_MAX_SIZE (2 * PAGE_SIZE) -#define SLUB_PAGE_SHIFT (PAGE_SHIFT + 1) +#define SLUB_PAGE_SHIFT (PAGE_SHIFT + 2) /* * We keep the general caches in an array of slab caches that are used for -- cgit v1.2.3 From 6503e5df08008b9a47022b5e9ebba658c8fa69af Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Thu, 27 Nov 2008 17:48:13 +0000 Subject: thermal: use integers rather than strings for thermal values The thermal API currently uses strings to pass values to userspace. This makes it difficult to use from within the kernel. Change the interface to use integers and fix up the consumers. Signed-off-by: Matthew Garrett Acked-by: Zhang Rui Acked-by: Thomas Renninger Signed-off-by: Len Brown --- include/linux/thermal.h | 32 ++++++++++++++++++++++++-------- 1 file changed, 24 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 917707e6151..4cb3292fb6e 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -31,23 +31,39 @@ struct thermal_zone_device; struct thermal_cooling_device; +enum thermal_device_mode { + THERMAL_DEVICE_DISABLED = 0, + THERMAL_DEVICE_ENABLED, +}; + +enum thermal_trip_type { + THERMAL_TRIP_ACTIVE = 0, + THERMAL_TRIP_PASSIVE, + THERMAL_TRIP_HOT, + THERMAL_TRIP_CRITICAL, +}; + struct thermal_zone_device_ops { int (*bind) (struct thermal_zone_device *, struct thermal_cooling_device *); int (*unbind) (struct thermal_zone_device *, struct thermal_cooling_device *); - int (*get_temp) (struct thermal_zone_device *, char *); - int (*get_mode) (struct thermal_zone_device *, char *); - int (*set_mode) (struct thermal_zone_device *, const char *); - int (*get_trip_type) (struct thermal_zone_device *, int, char *); - int (*get_trip_temp) (struct thermal_zone_device *, int, char *); + int (*get_temp) (struct thermal_zone_device *, unsigned long *); + int (*get_mode) (struct thermal_zone_device *, + enum thermal_device_mode *); + int (*set_mode) (struct thermal_zone_device *, + enum thermal_device_mode); + int (*get_trip_type) (struct thermal_zone_device *, int, + enum thermal_trip_type *); + int (*get_trip_temp) (struct thermal_zone_device *, int, + unsigned long *); int (*get_crit_temp) (struct thermal_zone_device *, unsigned long *); }; struct thermal_cooling_device_ops { - int (*get_max_state) (struct thermal_cooling_device *, char *); - int (*get_cur_state) (struct thermal_cooling_device *, char *); - int (*set_cur_state) (struct thermal_cooling_device *, unsigned int); + int (*get_max_state) (struct thermal_cooling_device *, unsigned long *); + int (*get_cur_state) (struct thermal_cooling_device *, unsigned long *); + int (*set_cur_state) (struct thermal_cooling_device *, unsigned long); }; #define THERMAL_TRIPS_NONE -1 -- cgit v1.2.3 From b1569e99c795bf83b4ddf41c4f1c42761ab7f75e Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Wed, 3 Dec 2008 17:55:32 +0000 Subject: ACPI: move thermal trip handling to generic thermal layer The ACPI code currently carries its own thermal trip handling, meaning that any other thermal implementation will need to reimplement it. Move the code to the generic thermal layer. Signed-off-by: Matthew Garrett Signed-off-by: Len Brown --- include/linux/thermal.h | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 4cb3292fb6e..a81c61521ba 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -27,6 +27,7 @@ #include #include +#include struct thermal_zone_device; struct thermal_cooling_device; @@ -58,6 +59,8 @@ struct thermal_zone_device_ops { int (*get_trip_temp) (struct thermal_zone_device *, int, unsigned long *); int (*get_crit_temp) (struct thermal_zone_device *, unsigned long *); + int (*notify) (struct thermal_zone_device *, int, + enum thermal_trip_type); }; struct thermal_cooling_device_ops { @@ -104,11 +107,18 @@ struct thermal_zone_device { struct device device; void *devdata; int trips; + int tc1; + int tc2; + int passive_delay; + int polling_delay; + int last_temperature; + bool passive; struct thermal_zone_device_ops *ops; struct list_head cooling_devices; struct idr idr; struct mutex lock; /* protect cooling devices list */ struct list_head node; + struct delayed_work poll_queue; #if defined(CONFIG_THERMAL_HWMON) struct list_head hwmon_node; struct thermal_hwmon_device *hwmon; @@ -120,13 +130,16 @@ struct thermal_zone_device { struct thermal_zone_device *thermal_zone_device_register(char *, int, void *, struct thermal_zone_device_ops - *); + *, int tc1, int tc2, + int passive_freq, + int polling_freq); void thermal_zone_device_unregister(struct thermal_zone_device *); int thermal_zone_bind_cooling_device(struct thermal_zone_device *, int, struct thermal_cooling_device *); int thermal_zone_unbind_cooling_device(struct thermal_zone_device *, int, struct thermal_cooling_device *); +void thermal_zone_device_update(struct thermal_zone_device *); struct thermal_cooling_device *thermal_cooling_device_register(char *, void *, struct thermal_cooling_device_ops -- cgit v1.2.3 From 9c3c133b1ed6e6d01bfabb6de29bf3d0f0886354 Mon Sep 17 00:00:00 2001 From: Alexander Clouter Date: Sun, 22 Feb 2009 12:03:56 +0800 Subject: hwrng: timeriomem - New driver Some hardware platforms, the TS-7800[1] is one for example, can supply the kernel with an entropy source, albeit a slow one for TS-7800 users, by just reading a particular IO address. This source must not be read above a certain rate otherwise the quality suffers. The driver is then hooked into by calling platform_device_(register|add|del) passing a structure similar to: ------ static struct timeriomem_rng_data ts78xx_ts_rng_data = { .address = (u32 *__iomem) TS_RNG, .period = 1000000, /* one second */ }; static struct platform_device ts78xx_ts_rng_device = { .name = "timeriomem_rng", .id = -1, .dev = { .platform_data = &ts78xx_ts_rng_data, }, .num_resources = 0, }; ------ [1] http://www.embeddedarm.com/products/board-detail.php?product=TS-7800 Signed-off-by: Alexander Clouter Signed-off-by: Herbert Xu --- include/linux/timeriomem-rng.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) create mode 100644 include/linux/timeriomem-rng.h (limited to 'include/linux') diff --git a/include/linux/timeriomem-rng.h b/include/linux/timeriomem-rng.h new file mode 100644 index 00000000000..dd253177f65 --- /dev/null +++ b/include/linux/timeriomem-rng.h @@ -0,0 +1,21 @@ +/* + * linux/include/linux/timeriomem-rng.h + * + * Copyright (c) 2009 Alexander Clouter + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include + +struct timeriomem_rng_data { + struct completion completion; + unsigned int present:1; + + u32 __iomem *address; + + /* measures in usecs */ + unsigned int period; +}; -- cgit v1.2.3 From 3b89d7d881a1dbb4da158f7eb5d6b3ceefc72810 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Sun, 22 Feb 2009 17:40:07 -0800 Subject: slub: move min_partial to struct kmem_cache Although it allows for better cacheline use, it is unnecessary to save a copy of the cache's min_partial value in each kmem_cache_node. Cc: Christoph Lameter Signed-off-by: David Rientjes Signed-off-by: Pekka Enberg --- include/linux/slub_def.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 2f5c16b1aac..f20a89e4d52 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -46,7 +46,6 @@ struct kmem_cache_cpu { struct kmem_cache_node { spinlock_t list_lock; /* Protect partial list and nr_partial */ unsigned long nr_partial; - unsigned long min_partial; struct list_head partial; #ifdef CONFIG_SLUB_DEBUG atomic_long_t nr_slabs; @@ -89,6 +88,7 @@ struct kmem_cache { void (*ctor)(void *); int inuse; /* Offset to metadata */ int align; /* Alignment */ + unsigned long min_partial; const char *name; /* Name (only for display!) */ struct list_head list; /* List of slab caches */ #ifdef CONFIG_SLUB_DEBUG -- cgit v1.2.3 From d060ffc1840e37100628f520e66600c5ae483b44 Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Tue, 24 Feb 2009 15:23:58 +0100 Subject: netfilter: install missing headers iptables imports headers from (the unifdefed headers of a) kernel tree, but some headers happened to not be installed. Signed-off-by: Jan Engelhardt Signed-off-by: Patrick McHardy --- include/linux/netfilter/Kbuild | 6 ++++++ include/linux/netfilter_ipv6/Kbuild | 1 + 2 files changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/Kbuild b/include/linux/netfilter/Kbuild index deeaee5c83f..947b47d7f6c 100644 --- a/include/linux/netfilter/Kbuild +++ b/include/linux/netfilter/Kbuild @@ -14,8 +14,11 @@ header-y += xt_NFQUEUE.h header-y += xt_RATEEST.h header-y += xt_SECMARK.h header-y += xt_TCPMSS.h +header-y += xt_TCPOPTSTRIP.h +header-y += xt_TPROXY.h header-y += xt_comment.h header-y += xt_connbytes.h +header-y += xt_connlimit.h header-y += xt_connmark.h header-y += xt_conntrack.h header-y += xt_dccp.h @@ -31,6 +34,7 @@ header-y += xt_mark.h header-y += xt_multiport.h header-y += xt_owner.h header-y += xt_pkttype.h +header-y += xt_quota.h header-y += xt_rateest.h header-y += xt_realm.h header-y += xt_recent.h @@ -40,6 +44,8 @@ header-y += xt_statistic.h header-y += xt_string.h header-y += xt_tcpmss.h header-y += xt_tcpudp.h +header-y += xt_time.h +header-y += xt_u32.h unifdef-y += nf_conntrack_common.h unifdef-y += nf_conntrack_ftp.h diff --git a/include/linux/netfilter_ipv6/Kbuild b/include/linux/netfilter_ipv6/Kbuild index 8887a5fcd1d..aca4bd1f6d7 100644 --- a/include/linux/netfilter_ipv6/Kbuild +++ b/include/linux/netfilter_ipv6/Kbuild @@ -11,6 +11,7 @@ header-y += ip6t_length.h header-y += ip6t_limit.h header-y += ip6t_mac.h header-y += ip6t_mark.h +header-y += ip6t_mh.h header-y += ip6t_multiport.h header-y += ip6t_opts.h header-y += ip6t_owner.h -- cgit v1.2.3 From 1ce85fe402137824246bad03ff85f3913d565c17 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 24 Feb 2009 23:18:28 -0800 Subject: netlink: change nlmsg_notify() return value logic This patch changes the return value of nlmsg_notify() as follows: If NETLINK_BROADCAST_ERROR is set by any of the listeners and an error in the delivery happened, return the broadcast error; else if there are no listeners apart from the socket that requested a change with the echo flag, return the result of the unicast notification. Thus, with this patch, the unicast notification is handled in the same way of a broadcast listener that has set the NETLINK_BROADCAST_ERROR socket flag. This patch is useful in case that the caller of nlmsg_notify() wants to know the result of the delivery of a netlink notification (including the broadcast delivery) and take any action in case that the delivery failed. For example, ctnetlink can drop packets if the event delivery failed to provide reliable logging and state-synchronization at the cost of dropping packets. This patch also modifies the rtnetlink code to ignore the return value of rtnl_notify() in all callers. The function rtnl_notify() (before this patch) returned the error of the unicast notification which makes rtnl_set_sk_err() reports errors to all listeners. This is not of any help since the origin of the change (the socket that requested the echoing) notices the ENOBUFS error if the notification fails and should resync itself. Signed-off-by: Pablo Neira Ayuso Acked-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 1e5f6730ff3..35a07c830f7 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -622,8 +622,8 @@ static __inline__ int rtattr_strcmp(const struct rtattr *rta, const char *str) extern int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, u32 group, int echo); extern int rtnl_unicast(struct sk_buff *skb, struct net *net, u32 pid); -extern int rtnl_notify(struct sk_buff *skb, struct net *net, u32 pid, u32 group, - struct nlmsghdr *nlh, gfp_t flags); +extern void rtnl_notify(struct sk_buff *skb, struct net *net, u32 pid, + u32 group, struct nlmsghdr *nlh, gfp_t flags); extern void rtnl_set_sk_err(struct net *net, u32 group, int error); extern int rtnetlink_put_metrics(struct sk_buff *skb, u32 *metrics); extern int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, -- cgit v1.2.3 From 6e2756376c706e4da3454a272947983f92e80a7e Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 25 Feb 2009 13:59:48 +0100 Subject: generic-ipi: remove CSD_FLAG_WAIT Oleg noticed that we don't strictly need CSD_FLAG_WAIT, rework the code so that we can use CSD_FLAG_LOCK for both purposes. Signed-off-by: Peter Zijlstra Cc: Oleg Nesterov Cc: Linus Torvalds Cc: Nick Piggin Cc: Jens Axboe Cc: "Paul E. McKenney" Cc: Rusty Russell Signed-off-by: Ingo Molnar --- include/linux/smp.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/smp.h b/include/linux/smp.h index 715196b09d6..00866d7fdf3 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -82,7 +82,8 @@ smp_call_function_mask(cpumask_t mask, void(*func)(void *info), void *info, return 0; } -void __smp_call_function_single(int cpuid, struct call_single_data *data); +void __smp_call_function_single(int cpuid, struct call_single_data *data, + int wait); /* * Generic and arch helpers -- cgit v1.2.3 From 2b9d1496e7835a603c340e8f0dd81f4b74d5f248 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sun, 22 Feb 2009 15:48:43 +0100 Subject: time: ntp: make 64-bit constants more robust Impact: cleanup, no functionality changed - make PPM_SCALE an explicit s64 constant, to remove (s64) casts from usage sites. kernel/time/ntp.o: text data bss dec hex filename 2536 114 136 2786 ae2 ntp.o.before 2536 114 136 2786 ae2 ntp.o.after md5: 40a7728d1188aa18e83e21a81fa7b150 ntp.o.before.asm 40a7728d1188aa18e83e21a81fa7b150 ntp.o.after.asm Signed-off-by: Ingo Molnar --- include/linux/timex.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/timex.h b/include/linux/timex.h index 998a55d80ac..aa3475fcff6 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -190,7 +190,7 @@ struct timex { * offset and maximum frequency tolerance. */ #define SHIFT_USEC 16 /* frequency offset scale (shift) */ -#define PPM_SCALE (NSEC_PER_USEC << (NTP_SCALE_SHIFT - SHIFT_USEC)) +#define PPM_SCALE ((s64)NSEC_PER_USEC << (NTP_SCALE_SHIFT - SHIFT_USEC)) #define PPM_SCALE_INV_SHIFT 19 #define PPM_SCALE_INV ((1ll << (PPM_SCALE_INV_SHIFT + NTP_SCALE_SHIFT)) / \ PPM_SCALE + 1) -- cgit v1.2.3 From b233b28eac0cc37d07c2d007ea08c86c778c5af4 Mon Sep 17 00:00:00 2001 From: Adrian McMenamin Date: Fri, 27 Feb 2009 16:07:32 +0900 Subject: sh: maple: Support block reads and writes. This patch updates the maple bus to support asynchronous block reads and writes as well as generally improving the quality of the code and supporting concurrency (all needed to support the Dreamcast visual memory unit - a driver will also be posted for that). Changes in the bus driver necessitate some changes in the two maple bus input drivers that are currently in mainline. As well as supporting block reads and writes this code clean up removes some poor handling of locks, uses an atomic status variable to serialise access to devices and more robusly handles the general performance problems of the bus. Signed-off-by: Adrian McMenamin Signed-off-by: Paul Mundt --- include/linux/maple.h | 62 ++++++++++++++++++++++++++++++++++----------------- 1 file changed, 41 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/maple.h b/include/linux/maple.h index c23d3f51ba4..d9a51b9b330 100644 --- a/include/linux/maple.h +++ b/include/linux/maple.h @@ -8,33 +8,49 @@ extern struct bus_type maple_bus_type; /* Maple Bus command and response codes */ enum maple_code { - MAPLE_RESPONSE_FILEERR = -5, - MAPLE_RESPONSE_AGAIN = -4, /* request should be retransmitted */ - MAPLE_RESPONSE_BADCMD = -3, - MAPLE_RESPONSE_BADFUNC = -2, - MAPLE_RESPONSE_NONE = -1, /* unit didn't respond at all */ - MAPLE_COMMAND_DEVINFO = 1, - MAPLE_COMMAND_ALLINFO = 2, - MAPLE_COMMAND_RESET = 3, - MAPLE_COMMAND_KILL = 4, - MAPLE_RESPONSE_DEVINFO = 5, - MAPLE_RESPONSE_ALLINFO = 6, - MAPLE_RESPONSE_OK = 7, - MAPLE_RESPONSE_DATATRF = 8, - MAPLE_COMMAND_GETCOND = 9, - MAPLE_COMMAND_GETMINFO = 10, - MAPLE_COMMAND_BREAD = 11, - MAPLE_COMMAND_BWRITE = 12, - MAPLE_COMMAND_SETCOND = 14 + MAPLE_RESPONSE_FILEERR = -5, + MAPLE_RESPONSE_AGAIN, /* retransmit */ + MAPLE_RESPONSE_BADCMD, + MAPLE_RESPONSE_BADFUNC, + MAPLE_RESPONSE_NONE, /* unit didn't respond*/ + MAPLE_COMMAND_DEVINFO = 1, + MAPLE_COMMAND_ALLINFO, + MAPLE_COMMAND_RESET, + MAPLE_COMMAND_KILL, + MAPLE_RESPONSE_DEVINFO, + MAPLE_RESPONSE_ALLINFO, + MAPLE_RESPONSE_OK, + MAPLE_RESPONSE_DATATRF, + MAPLE_COMMAND_GETCOND, + MAPLE_COMMAND_GETMINFO, + MAPLE_COMMAND_BREAD, + MAPLE_COMMAND_BWRITE, + MAPLE_COMMAND_BSYNC, + MAPLE_COMMAND_SETCOND, + MAPLE_COMMAND_MICCONTROL +}; + +enum maple_file_errors { + MAPLE_FILEERR_INVALID_PARTITION = 0x01000000, + MAPLE_FILEERR_PHASE_ERROR = 0x02000000, + MAPLE_FILEERR_INVALID_BLOCK = 0x04000000, + MAPLE_FILEERR_WRITE_ERROR = 0x08000000, + MAPLE_FILEERR_INVALID_WRITE_LENGTH = 0x10000000, + MAPLE_FILEERR_BAD_CRC = 0x20000000 +}; + +struct maple_buffer { + char bufx[0x400]; + void *buf; }; struct mapleq { struct list_head list; struct maple_device *dev; - void *sendbuf, *recvbuf, *recvbufdcsp; + struct maple_buffer *recvbuf; + void *sendbuf, *recvbuf_p2; unsigned char length; enum maple_code command; - struct mutex mutex; }; struct maple_devinfo { @@ -52,11 +68,15 @@ struct maple_device { struct maple_driver *driver; struct mapleq *mq; void (*callback) (struct mapleq * mq); + void (*fileerr_handler)(struct maple_device *mdev, void *recvbuf); + int (*can_unload)(struct maple_device *mdev); unsigned long when, interval, function; struct maple_devinfo devinfo; unsigned char port, unit; char product_name[32]; char product_licence[64]; + atomic_t busy; + wait_queue_head_t maple_wait; struct device dev; }; @@ -72,7 +92,7 @@ void maple_getcond_callback(struct maple_device *dev, int maple_driver_register(struct maple_driver *); void maple_driver_unregister(struct maple_driver *); -int maple_add_packet_sleeps(struct maple_device *mdev, u32 function, +int maple_add_packet(struct maple_device *mdev, u32 function, u32 command, u32 length, void *data); void maple_clear_dev(struct maple_device *mdev); -- cgit v1.2.3 From 8a7c4c77267b1c77296cd03e6704813cb70706d1 Mon Sep 17 00:00:00 2001 From: Andy Grover Date: Thu, 26 Feb 2009 23:41:38 -0800 Subject: RDS: Add AF and PF #defines for RDS sockets RDS is a reliable datagram protocol used for IPC on Oracle database clusters. This adds address and protocol family numbers for it. Signed-off-by: Andy Grover Signed-off-by: David S. Miller --- include/linux/socket.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index 20fc4bbfca4..9c90dc403ef 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -179,6 +179,7 @@ struct ucred { #define AF_ASH 18 /* Ash */ #define AF_ECONET 19 /* Acorn Econet */ #define AF_ATMSVC 20 /* ATM SVCs */ +#define AF_RDS 21 /* RDS sockets */ #define AF_SNA 22 /* Linux SNA Project (nutters!) */ #define AF_IRDA 23 /* IRDA sockets */ #define AF_PPPOX 24 /* PPPoX sockets */ @@ -217,6 +218,7 @@ struct ucred { #define PF_ASH AF_ASH #define PF_ECONET AF_ECONET #define PF_ATMSVC AF_ATMSVC +#define PF_RDS AF_RDS #define PF_SNA AF_SNA #define PF_IRDA AF_IRDA #define PF_PPPOX AF_PPPOX @@ -298,6 +300,7 @@ struct ucred { #define SOL_PPPOL2TP 273 #define SOL_BLUETOOTH 274 #define SOL_PNPIPE 275 +#define SOL_RDS 276 /* IPX options */ #define IPX_TYPE 1 -- cgit v1.2.3 From db49b9d26c1966c683efced9e1c37f391d8f8182 Mon Sep 17 00:00:00 2001 From: Andy Grover Date: Tue, 24 Feb 2009 15:30:42 +0000 Subject: RDS: Add userspace header Applications include this header in order to use RDS sockets. Signed-off-by: Andy Grover Signed-off-by: David S. Miller --- include/linux/rds.h | 250 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 250 insertions(+) create mode 100644 include/linux/rds.h (limited to 'include/linux') diff --git a/include/linux/rds.h b/include/linux/rds.h new file mode 100644 index 00000000000..d91dc91f544 --- /dev/null +++ b/include/linux/rds.h @@ -0,0 +1,250 @@ +/* + * Copyright (c) 2008 Oracle. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + * + */ + +#ifndef _LINUX_RDS_H +#define _LINUX_RDS_H + +#include + +/* These sparse annotated types shouldn't be in any user + * visible header file. We should clean this up rather + * than kludging around them. */ +#ifndef __KERNEL__ +#define __be16 u_int16_t +#define __be32 u_int32_t +#define __be64 u_int64_t +#endif + +#define RDS_IB_ABI_VERSION 0x301 + +/* + * setsockopt/getsockopt for SOL_RDS + */ +#define RDS_CANCEL_SENT_TO 1 +#define RDS_GET_MR 2 +#define RDS_FREE_MR 3 +/* deprecated: RDS_BARRIER 4 */ +#define RDS_RECVERR 5 +#define RDS_CONG_MONITOR 6 + +/* + * Control message types for SOL_RDS. + * + * CMSG_RDMA_ARGS (sendmsg) + * Request a RDMA transfer to/from the specified + * memory ranges. + * The cmsg_data is a struct rds_rdma_args. + * RDS_CMSG_RDMA_DEST (recvmsg, sendmsg) + * Kernel informs application about intended + * source/destination of a RDMA transfer + * RDS_CMSG_RDMA_MAP (sendmsg) + * Application asks kernel to map the given + * memory range into a IB MR, and send the + * R_Key along in an RDS extension header. + * The cmsg_data is a struct rds_get_mr_args, + * the same as for the GET_MR setsockopt. + * RDS_CMSG_RDMA_STATUS (recvmsg) + * Returns the status of a completed RDMA operation. + */ +#define RDS_CMSG_RDMA_ARGS 1 +#define RDS_CMSG_RDMA_DEST 2 +#define RDS_CMSG_RDMA_MAP 3 +#define RDS_CMSG_RDMA_STATUS 4 +#define RDS_CMSG_CONG_UPDATE 5 + +#define RDS_INFO_FIRST 10000 +#define RDS_INFO_COUNTERS 10000 +#define RDS_INFO_CONNECTIONS 10001 +/* 10002 aka RDS_INFO_FLOWS is deprecated */ +#define RDS_INFO_SEND_MESSAGES 10003 +#define RDS_INFO_RETRANS_MESSAGES 10004 +#define RDS_INFO_RECV_MESSAGES 10005 +#define RDS_INFO_SOCKETS 10006 +#define RDS_INFO_TCP_SOCKETS 10007 +#define RDS_INFO_IB_CONNECTIONS 10008 +#define RDS_INFO_CONNECTION_STATS 10009 +#define RDS_INFO_IWARP_CONNECTIONS 10010 +#define RDS_INFO_LAST 10010 + +struct rds_info_counter { + u_int8_t name[32]; + u_int64_t value; +} __attribute__((packed)); + +#define RDS_INFO_CONNECTION_FLAG_SENDING 0x01 +#define RDS_INFO_CONNECTION_FLAG_CONNECTING 0x02 +#define RDS_INFO_CONNECTION_FLAG_CONNECTED 0x04 + +#define TRANSNAMSIZ 16 + +struct rds_info_connection { + u_int64_t next_tx_seq; + u_int64_t next_rx_seq; + __be32 laddr; + __be32 faddr; + u_int8_t transport[TRANSNAMSIZ]; /* null term ascii */ + u_int8_t flags; +} __attribute__((packed)); + +struct rds_info_flow { + __be32 laddr; + __be32 faddr; + u_int32_t bytes; + __be16 lport; + __be16 fport; +} __attribute__((packed)); + +#define RDS_INFO_MESSAGE_FLAG_ACK 0x01 +#define RDS_INFO_MESSAGE_FLAG_FAST_ACK 0x02 + +struct rds_info_message { + u_int64_t seq; + u_int32_t len; + __be32 laddr; + __be32 faddr; + __be16 lport; + __be16 fport; + u_int8_t flags; +} __attribute__((packed)); + +struct rds_info_socket { + u_int32_t sndbuf; + __be32 bound_addr; + __be32 connected_addr; + __be16 bound_port; + __be16 connected_port; + u_int32_t rcvbuf; + u_int64_t inum; +} __attribute__((packed)); + +#define RDS_IB_GID_LEN 16 +struct rds_info_rdma_connection { + __be32 src_addr; + __be32 dst_addr; + uint8_t src_gid[RDS_IB_GID_LEN]; + uint8_t dst_gid[RDS_IB_GID_LEN]; + + uint32_t max_send_wr; + uint32_t max_recv_wr; + uint32_t max_send_sge; + uint32_t rdma_mr_max; + uint32_t rdma_mr_size; +}; + +/* + * Congestion monitoring. + * Congestion control in RDS happens at the host connection + * level by exchanging a bitmap marking congested ports. + * By default, a process sleeping in poll() is always woken + * up when the congestion map is updated. + * With explicit monitoring, an application can have more + * fine-grained control. + * The application installs a 64bit mask value in the socket, + * where each bit corresponds to a group of ports. + * When a congestion update arrives, RDS checks the set of + * ports that are now uncongested against the list bit mask + * installed in the socket, and if they overlap, we queue a + * cong_notification on the socket. + * + * To install the congestion monitor bitmask, use RDS_CONG_MONITOR + * with the 64bit mask. + * Congestion updates are received via RDS_CMSG_CONG_UPDATE + * control messages. + * + * The correspondence between bits and ports is + * 1 << (portnum % 64) + */ +#define RDS_CONG_MONITOR_SIZE 64 +#define RDS_CONG_MONITOR_BIT(port) (((unsigned int) port) % RDS_CONG_MONITOR_SIZE) +#define RDS_CONG_MONITOR_MASK(port) (1ULL << RDS_CONG_MONITOR_BIT(port)) + +/* + * RDMA related types + */ + +/* + * This encapsulates a remote memory location. + * In the current implementation, it contains the R_Key + * of the remote memory region, and the offset into it + * (so that the application does not have to worry about + * alignment). + */ +typedef u_int64_t rds_rdma_cookie_t; + +struct rds_iovec { + u_int64_t addr; + u_int64_t bytes; +}; + +struct rds_get_mr_args { + struct rds_iovec vec; + u_int64_t cookie_addr; + uint64_t flags; +}; + +struct rds_free_mr_args { + rds_rdma_cookie_t cookie; + u_int64_t flags; +}; + +struct rds_rdma_args { + rds_rdma_cookie_t cookie; + struct rds_iovec remote_vec; + u_int64_t local_vec_addr; + u_int64_t nr_local; + u_int64_t flags; + u_int64_t user_token; +}; + +struct rds_rdma_notify { + u_int64_t user_token; + int32_t status; +}; + +#define RDS_RDMA_SUCCESS 0 +#define RDS_RDMA_REMOTE_ERROR 1 +#define RDS_RDMA_CANCELED 2 +#define RDS_RDMA_DROPPED 3 +#define RDS_RDMA_OTHER_ERROR 4 + +/* + * Common set of flags for all RDMA related structs + */ +#define RDS_RDMA_READWRITE 0x0001 +#define RDS_RDMA_FENCE 0x0002 /* use FENCE for immediate send */ +#define RDS_RDMA_INVALIDATE 0x0004 /* invalidate R_Key after freeing MR */ +#define RDS_RDMA_USE_ONCE 0x0008 /* free MR after use */ +#define RDS_RDMA_DONTWAIT 0x0010 /* Don't wait in SET_BARRIER */ +#define RDS_RDMA_NOTIFY_ME 0x0020 /* Notify when operation completes */ + +#endif /* IB_RDS_H */ -- cgit v1.2.3 From bdaa6e8062d7f8085d8ed94ff88c99406ad53d79 Mon Sep 17 00:00:00 2001 From: Magnus Damm Date: Tue, 24 Feb 2009 22:58:57 +0900 Subject: sh: multiple vectors per irq - base Instead of keeping the single vector -> single linux irq mapping we extend the intc code to support merging of vectors to a single linux irq. This helps processors such as sh7750, sh7780 and sh7785 which have more vectors than masking ability. With this patch in place we can modify the intc tables to use one irq per maskable irq source. Please note the following: - If multiple vectors share the same enum then only the first vector will be available as a linux irq. - Drivers may need to be rewritten to get pending irq source from the hardware block instead of irq number. This patch together with the sh7785 specific intc tables solves DMA controller irq issues related to buggy interrupt masking. Reported-by: Yoshihiro Shimoda Signed-off-by: Magnus Damm Signed-off-by: Paul Mundt --- include/linux/sh_intc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sh_intc.h b/include/linux/sh_intc.h index 68e212ff9dd..eb1423a0078 100644 --- a/include/linux/sh_intc.h +++ b/include/linux/sh_intc.h @@ -85,6 +85,7 @@ struct intc_desc symbol __initdata = { \ } #endif +unsigned int intc_evt2irq(unsigned int vector); void __init register_intc_controller(struct intc_desc *desc); int intc_set_priority(unsigned int irq, unsigned int prio); -- cgit v1.2.3 From 98c8a60a04316e94ccea8221cf16768ce91bd214 Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Tue, 17 Feb 2009 13:24:57 +0200 Subject: nl80211: Provide access to STA TX/RX packet counters The TX/RX packet counters are needed to fill in RADIUS Accounting attributes Acct-Output-Packets and Acct-Input-Packets. We already collect the needed information, but only the TX/RX bytes were previously exposed through nl80211. Allow applications to fetch the packet counters, too, to provide more complete support for accounting. Signed-off-by: Jouni Malinen Acked-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/nl80211.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 8802d1bda38..f6e56370ea6 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -526,6 +526,9 @@ enum nl80211_rate_info { * @NL80211_STA_INFO_SIGNAL: signal strength of last received PPDU (u8, dBm) * @NL80211_STA_INFO_TX_BITRATE: current unicast tx rate, nested attribute * containing info as possible, see &enum nl80211_sta_info_txrate. + * @NL80211_STA_INFO_RX_PACKETS: total received packet (u32, from this station) + * @NL80211_STA_INFO_TX_PACKETS: total transmitted packets (u32, to this + * station) */ enum nl80211_sta_info { __NL80211_STA_INFO_INVALID, @@ -537,6 +540,8 @@ enum nl80211_sta_info { NL80211_STA_INFO_PLINK_STATE, NL80211_STA_INFO_SIGNAL, NL80211_STA_INFO_TX_BITRATE, + NL80211_STA_INFO_RX_PACKETS, + NL80211_STA_INFO_TX_PACKETS, /* keep last */ __NL80211_STA_INFO_AFTER_LAST, -- cgit v1.2.3 From cabeccbd172cc305f4383f5a4808ae254745275f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Sat, 28 Feb 2009 04:44:38 +0000 Subject: tcp: kill eff_sacks "cache", the sole user can calculate itself MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Also fixes insignificant bug that would cause sending of stale SACK block (would occur in some corner cases). Signed-off-by: Ilpo Järvinen Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 0cd99e6baca..4b86ad71e05 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -218,7 +218,6 @@ struct tcp_options_received { snd_wscale : 4, /* Window scaling received from sender */ rcv_wscale : 4; /* Window scaling to send to receiver */ /* SACKs data */ - u8 eff_sacks; /* Size of SACK array to send with next packet */ u8 num_sacks; /* Number of SACK blocks */ u16 user_mss; /* mss requested by user in ioctl */ u16 mss_clamp; /* Maximal mss, negotiated at connection setup */ -- cgit v1.2.3 From 8987691a4aa6622a1b58bb12c56abaf3d2098fad Mon Sep 17 00:00:00 2001 From: Inaky Perez-Gonzalez Date: Sat, 28 Feb 2009 23:42:50 +0000 Subject: wimax/i2400m: allow control of the base-station idle mode timeout For power saving reasons, WiMAX links can be put in idle mode while connected after a certain time of the link not being used for tx or rx. In this mode, the device pages the base-station regularly and when data is ready to be transmitted, the link is revived. This patch allows the user to control the time the device has to be idle before it decides to go to idle mode from a sysfs interace. It also updates the initialization code to acknowledge the module variable 'idle_mode_disabled' when the firmware is a newer version (upcoming 1.4 vs 2.6.29's v1.3). The method for setting the idle mode timeout in the older firmwares is much more limited and can be only done at initialization time. Thus, the sysfs file will return -ENOSYS on older ones. Signed-off-by: Inaky Perez-Gonzalez Signed-off-by: David S. Miller --- include/linux/wimax/i2400m.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/wimax/i2400m.h b/include/linux/wimax/i2400m.h index 74198f5bb4d..686eeb2b970 100644 --- a/include/linux/wimax/i2400m.h +++ b/include/linux/wimax/i2400m.h @@ -381,6 +381,7 @@ enum i2400m_tlv { I2400M_TLV_RF_STATUS = 163, I2400M_TLV_DEVICE_RESET_TYPE = 132, I2400M_TLV_CONFIG_IDLE_PARAMETERS = 601, + I2400M_TLV_CONFIG_IDLE_TIMEOUT = 611, }; @@ -509,4 +510,13 @@ struct i2400m_tlv_media_status { __le32 media_status; } __attribute__((packed)); + +/* New in v1.4 */ +struct i2400m_tlv_config_idle_timeout { + struct i2400m_tlv_hdr hdr; + __le32 timeout; /* 100 to 300000 ms [5min], 100 increments + * 0 disabled */ +} __attribute__((packed)); + + #endif /* #ifndef __LINUX__WIMAX__I2400M_H__ */ -- cgit v1.2.3 From 347707baa77d273d79258303e00200d40cf3b323 Mon Sep 17 00:00:00 2001 From: Kay Sievers Date: Sat, 28 Feb 2009 23:42:51 +0000 Subject: wimax: struct device - replace bus_id with dev_name(), dev_set_name() Cc: inaky.perez-gonzalez@intel.com Cc: linux-wimax@intel.com Acked-by: Greg Kroah-Hartman Signed-off-by: Kay Sievers Signed-off-by: Inaky Perez-Gonzalez Signed-off-by: David S. Miller --- include/linux/wimax/debug.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/wimax/debug.h b/include/linux/wimax/debug.h index ba0c49399a8..c703e034042 100644 --- a/include/linux/wimax/debug.h +++ b/include/linux/wimax/debug.h @@ -178,7 +178,7 @@ void __d_head(char *head, size_t head_size, WARN_ON(1); } else snprintf(head, head_size, "%s %s: ", - dev_driver_string(dev), dev->bus_id); + dev_driver_string(dev), dev_name(dev)); } -- cgit v1.2.3 From fd5c565c0c04d2716cfdac3f1de3c2261d6a457d Mon Sep 17 00:00:00 2001 From: Inaky Perez-Gonzalez Date: Sat, 28 Feb 2009 23:42:52 +0000 Subject: wimax/i2400m: support extended data RX protocol (no need to reallocate skbs) Newer i2400m firmwares (>= v1.4) extend the data RX protocol so that each packet has a 16 byte header. This header is mainly used to implement host reordeing (which is addressed in later commits). However, this header also allows us to overwrite it (once data has been extracted) with an Ethernet header and deliver to the networking stack without having to reallocate the skb (as it happened in fw <= v1.3) to make room for it. - control.c: indicate the device [dev_initialize()] that the driver wants to use the extended data RX protocol. Also involves adding the definition of the needed data types in include/linux/wimax/i2400m.h. - rx.c: handle the new payload type for the extended RX data protocol. Prepares the skb for delivery to netdev.c:i2400m_net_erx(). - netdev.c: Introduce i2400m_net_erx() that adds the fake ethernet address to a prepared skb and delivers it to the networking stack. - cleanup: in most instances in rx.c, the variable 'single' was renamed to 'single_last' for it better conveys its meaning. Signed-off-by: Inaky Perez-Gonzalez Signed-off-by: David S. Miller --- include/linux/wimax/i2400m.h | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) (limited to 'include/linux') diff --git a/include/linux/wimax/i2400m.h b/include/linux/wimax/i2400m.h index 686eeb2b970..ad36e073a70 100644 --- a/include/linux/wimax/i2400m.h +++ b/include/linux/wimax/i2400m.h @@ -207,6 +207,7 @@ enum i2400m_pt { I2400M_PT_TRACE, /* For device debug */ I2400M_PT_RESET_WARM, /* device reset */ I2400M_PT_RESET_COLD, /* USB[transport] reset, like reconnect */ + I2400M_PT_EDATA, /* Extended RX data */ I2400M_PT_ILLEGAL }; @@ -221,6 +222,32 @@ struct i2400m_pl_data_hdr { } __attribute__((packed)); +/* + * Payload for an extended data packet + * + * New in v1.4 + * + * @cs: the type of data in the packet, as defined per (802.16e + * T11.13.19.1). Currently only 2 (IPv4 packet) supported. + * + * This is prefixed to each and every INCOMING DATA packet. + */ +struct i2400m_pl_edata_hdr { + __le32 reorder; + __u8 cs; + __u8 reserved[11]; +} __attribute__((packed)); + +enum i2400m_cs { + I2400M_CS_IPV4_0 = 0, + I2400M_CS_IPV4 = 2, +}; + +enum i2400m_reorder { + I2400M_REORDER_NEEDED = 0x01, +}; + + /* Misc constants */ enum { I2400M_PL_PAD = 16, /* Payload data size alignment */ @@ -382,6 +409,7 @@ enum i2400m_tlv { I2400M_TLV_DEVICE_RESET_TYPE = 132, I2400M_TLV_CONFIG_IDLE_PARAMETERS = 601, I2400M_TLV_CONFIG_IDLE_TIMEOUT = 611, + I2400M_TLV_CONFIG_D2H_DATA_FORMAT = 614, }; @@ -518,5 +546,12 @@ struct i2400m_tlv_config_idle_timeout { * 0 disabled */ } __attribute__((packed)); +/* New in v1.4 -- for backward compat, will be removed */ +struct i2400m_tlv_config_d2h_data_format { + struct i2400m_tlv_hdr hdr; + __u8 format; /* 0 old format, 1 enhanced */ + __u8 reserved[3]; +} __attribute__((packed)); + #endif /* #ifndef __LINUX__WIMAX__I2400M_H__ */ -- cgit v1.2.3 From c747583d19d5d5147a9f0eae480c1fdbc84c4252 Mon Sep 17 00:00:00 2001 From: Inaky Perez-Gonzalez Date: Sat, 28 Feb 2009 23:42:54 +0000 Subject: wimax/i2400m: implement RX reorder support Allow the device to give the driver RX data with reorder information. When that is done, the device will indicate the driver if a packet has to be held in a (sorted) queue. It will also tell the driver when held packets have to be released to the OS. This is done to improve the WiMAX-protocol level retransmission support when missing frames are detected. The code docs provide details about the implementation. In general, this just hooks into the RX path in rx.c; if a packet with the reorder bit in the RX header is detected, the reorder information in the header is extracted and one of the four main reorder operations are executed. In one case (queue) no packet will be delivered to the networking stack, just queued, whereas in the others (reset, update_ws and queue_update_ws), queued packet might be delivered depending on the window start for the specific queue. The modifications to files other than rx.c are: - control.c: during device initialization, enable reordering support if the rx_reorder_disabled module parameter is not enabled - driver.c: expose a rx_reorder_disable module parameter and call i2400m_rx_setup/release() to initialize/shutdown RX reorder support. - i2400m.h: introduce members in 'struct i2400m' needed for implementing reorder support. - linux/i2400m.h: introduce TLVs, commands and constant definitions related to RX reorder Last but not least, the rx reorder code includes an small circular log where the last N reorder operations are recorded to be displayed in case of inconsistency. Otherwise diagnosing issues would be almost impossible. Signed-off-by: Inaky Perez-Gonzalez Signed-off-by: David S. Miller --- include/linux/wimax/i2400m.h | 32 ++++++++++++++++++++++++++++---- 1 file changed, 28 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/wimax/i2400m.h b/include/linux/wimax/i2400m.h index ad36e073a70..d5148a7889a 100644 --- a/include/linux/wimax/i2400m.h +++ b/include/linux/wimax/i2400m.h @@ -225,15 +225,16 @@ struct i2400m_pl_data_hdr { /* * Payload for an extended data packet * - * New in v1.4 + * New in fw v1.4 * + * @reorder: if this payload has to be reorder or not (and how) * @cs: the type of data in the packet, as defined per (802.16e * T11.13.19.1). Currently only 2 (IPv4 packet) supported. * * This is prefixed to each and every INCOMING DATA packet. */ struct i2400m_pl_edata_hdr { - __le32 reorder; + __le32 reorder; /* bits defined in i2400m_ro */ __u8 cs; __u8 reserved[11]; } __attribute__((packed)); @@ -243,8 +244,23 @@ enum i2400m_cs { I2400M_CS_IPV4 = 2, }; -enum i2400m_reorder { - I2400M_REORDER_NEEDED = 0x01, +enum i2400m_ro { + I2400M_RO_NEEDED = 0x01, + I2400M_RO_TYPE = 0x03, + I2400M_RO_TYPE_SHIFT = 1, + I2400M_RO_CIN = 0x0f, + I2400M_RO_CIN_SHIFT = 4, + I2400M_RO_FBN = 0x07ff, + I2400M_RO_FBN_SHIFT = 8, + I2400M_RO_SN = 0x07ff, + I2400M_RO_SN_SHIFT = 21, +}; + +enum i2400m_ro_type { + I2400M_RO_TYPE_RESET = 0, + I2400M_RO_TYPE_PACKET, + I2400M_RO_TYPE_WS, + I2400M_RO_TYPE_PACKET_WS, }; @@ -410,6 +426,7 @@ enum i2400m_tlv { I2400M_TLV_CONFIG_IDLE_PARAMETERS = 601, I2400M_TLV_CONFIG_IDLE_TIMEOUT = 611, I2400M_TLV_CONFIG_D2H_DATA_FORMAT = 614, + I2400M_TLV_CONFIG_DL_HOST_REORDER = 615, }; @@ -553,5 +570,12 @@ struct i2400m_tlv_config_d2h_data_format { __u8 reserved[3]; } __attribute__((packed)); +/* New in v1.4 */ +struct i2400m_tlv_config_dl_host_reorder { + struct i2400m_tlv_hdr hdr; + __u8 reorder; /* 0 disabled, 1 enabled */ + __u8 reserved[3]; +} __attribute__((packed)); + #endif /* #ifndef __LINUX__WIMAX__I2400M_H__ */ -- cgit v1.2.3 From d3a21be86c178964167aa54c39a01260d33e7509 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 2 Mar 2009 03:15:58 -0800 Subject: skbuff.h: fix timestamps kernel-doc Fix skbuff.h kernel-doc for timestamps: must include "struct" keyword, otherwise there are kernel-doc errors: Error(linux-next-20090227//include/linux/skbuff.h:161): cannot understand prototype: 'struct skb_shared_hwtstamps ' Error(linux-next-20090227//include/linux/skbuff.h:177): cannot understand prototype: 'union skb_shared_tx ' Signed-off-by: Randy Dunlap Signed-off-by: David S. Miller --- include/linux/skbuff.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 61ce97a8b86..1f659e8c2b8 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -135,8 +135,7 @@ struct skb_frag_struct { #define HAVE_HW_TIME_STAMP /** - * skb_shared_hwtstamps - hardware time stamps - * + * struct skb_shared_hwtstamps - hardware time stamps * @hwtstamp: hardware time stamp transformed into duration * since arbitrary point in time * @syststamp: hwtstamp transformed to system time base @@ -164,8 +163,7 @@ struct skb_shared_hwtstamps { }; /** - * skb_shared_tx - instructions for time stamping of outgoing packets - * + * struct skb_shared_tx - instructions for time stamping of outgoing packets * @hardware: generate hardware time stamp * @software: generate software time stamp * @in_progress: device driver is going to provide -- cgit v1.2.3 From a1d2f09544065b60598b8167d94a6371bff3e892 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 4 Mar 2009 15:05:33 +0800 Subject: crypto: compress - Add pcomp interface The current "comp" crypto interface supports one-shot (de)compression only, i.e. the whole data buffer to be (de)compressed must be passed at once, and the whole (de)compressed data buffer will be received at once. In several use-cases (e.g. compressed file systems that store files in big compressed blocks), this workflow is not suitable. Furthermore, the "comp" type doesn't provide for the configuration of (de)compression parameters, and always allocates workspace memory for both compression and decompression, which may waste memory. To solve this, add a "pcomp" partial (de)compression interface that provides the following operations: - crypto_compress_{init,update,final}() for compression, - crypto_decompress_{init,update,final}() for decompression, - crypto_{,de}compress_setup(), to configure (de)compression parameters (incl. allocating workspace memory). The (de)compression methods take a struct comp_request, which was mimicked after the z_stream object in zlib, and contains buffer pointer and length pairs for input and output. The setup methods take an opaque parameter pointer and length pair. Parameters are supposed to be encoded using netlink attributes, whose meanings depend on the actual (name of the) (de)compression algorithm. Signed-off-by: Geert Uytterhoeven Signed-off-by: Herbert Xu --- include/linux/crypto.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 29729b83438..ec29fa268b9 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -40,6 +40,7 @@ #define CRYPTO_ALG_TYPE_SHASH 0x00000009 #define CRYPTO_ALG_TYPE_AHASH 0x0000000a #define CRYPTO_ALG_TYPE_RNG 0x0000000c +#define CRYPTO_ALG_TYPE_PCOMPRESS 0x0000000f #define CRYPTO_ALG_TYPE_HASH_MASK 0x0000000e #define CRYPTO_ALG_TYPE_AHASH_MASK 0x0000000c -- cgit v1.2.3 From 0c5c2d3089068d4aa378f7a40d2b5ad9d4f52ce8 Mon Sep 17 00:00:00 2001 From: Eric Biederman Date: Wed, 4 Mar 2009 00:03:08 -0800 Subject: neigh: Allow for user space users of the neighbour table Currently it is possible to do just about everything with the arp table from user space except treat an entry like you are using it. To that end implement and a flag NTF_USE that when set in a netwlink update request treats the neighbour table entry like the kernel does on the output path. This allows user space applications to share the kernel's arp cache. Signed-off-by: Eric Biederman Signed-off-by: David S. Miller --- include/linux/neighbour.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/neighbour.h b/include/linux/neighbour.h index 8730d5dae1b..12c9de13845 100644 --- a/include/linux/neighbour.h +++ b/include/linux/neighbour.h @@ -31,6 +31,7 @@ enum * Neighbor Cache Entry Flags */ +#define NTF_USE 0x01 #define NTF_PROXY 0x08 /* == ATF_PUBL */ #define NTF_ROUTER 0x80 -- cgit v1.2.3 From f2f45e5f3c921c73c913e9a9c00f21ec01c86b4d Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Fri, 9 Jan 2009 12:19:52 +0100 Subject: dma-debug: add header file and core data structures Impact: add groundwork for DMA-API debugging Signed-off-by: Joerg Roedel --- include/linux/dma-debug.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) create mode 100644 include/linux/dma-debug.h (limited to 'include/linux') diff --git a/include/linux/dma-debug.h b/include/linux/dma-debug.h new file mode 100644 index 00000000000..ce4ace707c7 --- /dev/null +++ b/include/linux/dma-debug.h @@ -0,0 +1,25 @@ +/* + * Copyright (C) 2008 Advanced Micro Devices, Inc. + * + * Author: Joerg Roedel + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published + * by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#ifndef __DMA_DEBUG_H +#define __DMA_DEBUG_H + +struct device; + +#endif /* __DMA_DEBUG_H */ -- cgit v1.2.3 From 6bf078715c1998d4d10716251cc10ce45908594c Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Fri, 9 Jan 2009 12:54:42 +0100 Subject: dma-debug: add initialization code Impact: add code to initialize dma-debug core data structures Signed-off-by: Joerg Roedel --- include/linux/dma-debug.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma-debug.h b/include/linux/dma-debug.h index ce4ace707c7..345d5387a30 100644 --- a/include/linux/dma-debug.h +++ b/include/linux/dma-debug.h @@ -20,6 +20,20 @@ #ifndef __DMA_DEBUG_H #define __DMA_DEBUG_H +#include + struct device; +#ifdef CONFIG_DMA_API_DEBUG + +extern void dma_debug_init(u32 num_entries); + +#else /* CONFIG_DMA_API_DEBUG */ + +static inline void dma_debug_init(u32 num_entries) +{ +} + +#endif /* CONFIG_DMA_API_DEBUG */ + #endif /* __DMA_DEBUG_H */ -- cgit v1.2.3 From f62bc980e6fd26434012c0d5676ecb17179d9ee4 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Fri, 9 Jan 2009 14:14:49 +0100 Subject: dma-debug: add checking for map/unmap_page/single Impact: add debug callbacks for dma_{un}map_[page|single] Signed-off-by: Joerg Roedel --- include/linux/dma-debug.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma-debug.h b/include/linux/dma-debug.h index 345d5387a30..65f73526ba2 100644 --- a/include/linux/dma-debug.h +++ b/include/linux/dma-debug.h @@ -28,12 +28,35 @@ struct device; extern void dma_debug_init(u32 num_entries); +extern void debug_dma_map_page(struct device *dev, struct page *page, + size_t offset, size_t size, + int direction, dma_addr_t dma_addr, + bool map_single); + +extern void debug_dma_unmap_page(struct device *dev, dma_addr_t addr, + size_t size, int direction, bool map_single); + + #else /* CONFIG_DMA_API_DEBUG */ static inline void dma_debug_init(u32 num_entries) { } +static inline void debug_dma_map_page(struct device *dev, struct page *page, + size_t offset, size_t size, + int direction, dma_addr_t dma_addr, + bool map_single) +{ +} + +static inline void debug_dma_unmap_page(struct device *dev, dma_addr_t addr, + size_t size, int direction, + bool map_single) +{ +} + + #endif /* CONFIG_DMA_API_DEBUG */ #endif /* __DMA_DEBUG_H */ -- cgit v1.2.3 From 972aa45ceaf65376f33aa75958fcaefc9e752fa4 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Fri, 9 Jan 2009 14:19:54 +0100 Subject: dma-debug: add add checking for map/unmap_sg Impact: add debug callbacks for dma_{un}map_sg Signed-off-by: Joerg Roedel --- include/linux/dma-debug.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma-debug.h b/include/linux/dma-debug.h index 65f73526ba2..ee9fdb32854 100644 --- a/include/linux/dma-debug.h +++ b/include/linux/dma-debug.h @@ -23,6 +23,7 @@ #include struct device; +struct scatterlist; #ifdef CONFIG_DMA_API_DEBUG @@ -36,6 +37,11 @@ extern void debug_dma_map_page(struct device *dev, struct page *page, extern void debug_dma_unmap_page(struct device *dev, dma_addr_t addr, size_t size, int direction, bool map_single); +extern void debug_dma_map_sg(struct device *dev, struct scatterlist *sg, + int nents, int mapped_ents, int direction); + +extern void debug_dma_unmap_sg(struct device *dev, struct scatterlist *sglist, + int nelems, int dir); #else /* CONFIG_DMA_API_DEBUG */ @@ -56,6 +62,16 @@ static inline void debug_dma_unmap_page(struct device *dev, dma_addr_t addr, { } +static inline void debug_dma_map_sg(struct device *dev, struct scatterlist *sg, + int nents, int mapped_ents, int direction) +{ +} + +static inline void debug_dma_unmap_sg(struct device *dev, + struct scatterlist *sglist, + int nelems, int dir) +{ +} #endif /* CONFIG_DMA_API_DEBUG */ -- cgit v1.2.3 From 6bfd4498764d6201399849d2e80fda95db7742c0 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Fri, 9 Jan 2009 14:38:50 +0100 Subject: dma-debug: add checking for [alloc|free]_coherent Impact: add debug callbacks for dma_[alloc|free]_coherent Signed-off-by: Joerg Roedel --- include/linux/dma-debug.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma-debug.h b/include/linux/dma-debug.h index ee9fdb32854..cb72dfd8732 100644 --- a/include/linux/dma-debug.h +++ b/include/linux/dma-debug.h @@ -43,6 +43,12 @@ extern void debug_dma_map_sg(struct device *dev, struct scatterlist *sg, extern void debug_dma_unmap_sg(struct device *dev, struct scatterlist *sglist, int nelems, int dir); +extern void debug_dma_alloc_coherent(struct device *dev, size_t size, + dma_addr_t dma_addr, void *virt); + +extern void debug_dma_free_coherent(struct device *dev, size_t size, + void *virt, dma_addr_t addr); + #else /* CONFIG_DMA_API_DEBUG */ static inline void dma_debug_init(u32 num_entries) @@ -73,6 +79,16 @@ static inline void debug_dma_unmap_sg(struct device *dev, { } +static inline void debug_dma_alloc_coherent(struct device *dev, size_t size, + dma_addr_t dma_addr, void *virt) +{ +} + +static inline void debug_dma_free_coherent(struct device *dev, size_t size, + void *virt, dma_addr_t addr) +{ +} + #endif /* CONFIG_DMA_API_DEBUG */ #endif /* __DMA_DEBUG_H */ -- cgit v1.2.3 From b9d2317e0c4aed02afd20022083b2a485289605d Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Fri, 9 Jan 2009 14:43:04 +0100 Subject: dma-debug: add checks for sync_single_* Impact: add debug callbacks for dma_sync_single_for_* functions Signed-off-by: Joerg Roedel --- include/linux/dma-debug.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma-debug.h b/include/linux/dma-debug.h index cb72dfd8732..0eee7af5143 100644 --- a/include/linux/dma-debug.h +++ b/include/linux/dma-debug.h @@ -49,6 +49,14 @@ extern void debug_dma_alloc_coherent(struct device *dev, size_t size, extern void debug_dma_free_coherent(struct device *dev, size_t size, void *virt, dma_addr_t addr); +extern void debug_dma_sync_single_for_cpu(struct device *dev, + dma_addr_t dma_handle, size_t size, + int direction); + +extern void debug_dma_sync_single_for_device(struct device *dev, + dma_addr_t dma_handle, + size_t size, int direction); + #else /* CONFIG_DMA_API_DEBUG */ static inline void dma_debug_init(u32 num_entries) @@ -89,6 +97,18 @@ static inline void debug_dma_free_coherent(struct device *dev, size_t size, { } +static inline void debug_dma_sync_single_for_cpu(struct device *dev, + dma_addr_t dma_handle, + size_t size, int direction) +{ +} + +static inline void debug_dma_sync_single_for_device(struct device *dev, + dma_addr_t dma_handle, + size_t size, int direction) +{ +} + #endif /* CONFIG_DMA_API_DEBUG */ #endif /* __DMA_DEBUG_H */ -- cgit v1.2.3 From 948408ba3e2a67ed0f95e18ed5be1c622c2c5fc3 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Fri, 9 Jan 2009 14:55:38 +0100 Subject: dma-debug: add checks for sync_single_range_* Impact: add debug callbacks for dma_sync_single_range_for_* functions Signed-off-by: Joerg Roedel --- include/linux/dma-debug.h | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma-debug.h b/include/linux/dma-debug.h index 0eee7af5143..e9b903503ad 100644 --- a/include/linux/dma-debug.h +++ b/include/linux/dma-debug.h @@ -57,6 +57,17 @@ extern void debug_dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle, size_t size, int direction); +extern void debug_dma_sync_single_range_for_cpu(struct device *dev, + dma_addr_t dma_handle, + unsigned long offset, + size_t size, + int direction); + +extern void debug_dma_sync_single_range_for_device(struct device *dev, + dma_addr_t dma_handle, + unsigned long offset, + size_t size, int direction); + #else /* CONFIG_DMA_API_DEBUG */ static inline void dma_debug_init(u32 num_entries) @@ -109,6 +120,22 @@ static inline void debug_dma_sync_single_for_device(struct device *dev, { } +static inline void debug_dma_sync_single_range_for_cpu(struct device *dev, + dma_addr_t dma_handle, + unsigned long offset, + size_t size, + int direction) +{ +} + +static inline void debug_dma_sync_single_range_for_device(struct device *dev, + dma_addr_t dma_handle, + unsigned long offset, + size_t size, + int direction) +{ +} + #endif /* CONFIG_DMA_API_DEBUG */ #endif /* __DMA_DEBUG_H */ -- cgit v1.2.3 From a31fba5d68cebf8f5fefd03e079dab94875e25f5 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Fri, 9 Jan 2009 15:01:12 +0100 Subject: dma-debug: add checks for sync_single_sg_* Impact: add debug callbacks for dma_sync_sg_* functions Signed-off-by: Joerg Roedel --- include/linux/dma-debug.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma-debug.h b/include/linux/dma-debug.h index e9b903503ad..4985c6c5237 100644 --- a/include/linux/dma-debug.h +++ b/include/linux/dma-debug.h @@ -68,6 +68,14 @@ extern void debug_dma_sync_single_range_for_device(struct device *dev, unsigned long offset, size_t size, int direction); +extern void debug_dma_sync_sg_for_cpu(struct device *dev, + struct scatterlist *sg, + int nelems, int direction); + +extern void debug_dma_sync_sg_for_device(struct device *dev, + struct scatterlist *sg, + int nelems, int direction); + #else /* CONFIG_DMA_API_DEBUG */ static inline void dma_debug_init(u32 num_entries) @@ -136,6 +144,18 @@ static inline void debug_dma_sync_single_range_for_device(struct device *dev, { } +static inline void debug_dma_sync_sg_for_cpu(struct device *dev, + struct scatterlist *sg, + int nelems, int direction) +{ +} + +static inline void debug_dma_sync_sg_for_device(struct device *dev, + struct scatterlist *sg, + int nelems, int direction) +{ +} + #endif /* CONFIG_DMA_API_DEBUG */ #endif /* __DMA_DEBUG_H */ -- cgit v1.2.3 From e79c1ba84c68de9161d541bd2bcc8ea65c89955c Mon Sep 17 00:00:00 2001 From: Michael Buesch Date: Fri, 27 Feb 2009 16:59:05 +0100 Subject: ssb: Add SPROM fallback support This adds SSB functionality to register a fallback SPROM image from the architecture setup code. Weird architectures exist that have half-assed SSB devices without SPROM attached to their PCI busses. The architecture can register a fallback SPROM image that is used if no SPROM is found on the SSB device. Signed-off-by: Michael Buesch Cc: Florian Fainelli Signed-off-by: John W. Linville --- include/linux/ssb/ssb.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ssb/ssb.h b/include/linux/ssb/ssb.h index 17d9b58f637..5ae8fa22d33 100644 --- a/include/linux/ssb/ssb.h +++ b/include/linux/ssb/ssb.h @@ -339,6 +339,10 @@ extern int ssb_bus_pcmciabus_register(struct ssb_bus *bus, extern void ssb_bus_unregister(struct ssb_bus *bus); +/* Set a fallback SPROM. + * See kdoc at the function definition for complete documentation. */ +extern int ssb_arch_set_fallback_sprom(const struct ssb_sprom *sprom); + /* Suspend a SSB bus. * Call this from the parent bus suspend routine. */ extern int ssb_bus_suspend(struct ssb_bus *bus); -- cgit v1.2.3 From 6074d5b0a319fe8400ff079a3c289406ca024321 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 10 Mar 2009 16:27:48 +0900 Subject: percpu: more flexibility for @dyn_size of pcpu_setup_first_chunk() Impact: cleanup, more flexibility for first chunk init Non-negative @dyn_size used to be allowed iff @unit_size wasn't auto. This restriction stemmed from implementation detail and made things a bit less intuitive. This patch allows @dyn_size to be specified regardless of @unit_size and swaps the positions of @dyn_size and @unit_size so that the parameter order makes more sense (static, reserved and dyn sizes followed by enclosing unit_size). While at it, add @unit_size >= PCPU_MIN_UNIT_SIZE sanity check. Signed-off-by: Tejun Heo --- include/linux/percpu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 54a968b4b92..fb455dcc59c 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -107,7 +107,7 @@ typedef void (*pcpu_populate_pte_fn_t)(unsigned long addr); extern size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn, size_t static_size, size_t reserved_size, - ssize_t unit_size, ssize_t dyn_size, + ssize_t dyn_size, ssize_t unit_size, void *base_addr, pcpu_populate_pte_fn_t populate_pte_fn); -- cgit v1.2.3 From 66c3a75772247c31feabefb724e082220a1ab060 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 10 Mar 2009 16:27:48 +0900 Subject: percpu: generalize embedding first chunk setup helper Impact: code reorganization Separate out embedding first chunk setup helper from x86 embedding first chunk allocator and put it in mm/percpu.c. This will be used by the default percpu first chunk allocator and possibly by other archs. Signed-off-by: Tejun Heo --- include/linux/percpu.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index fb455dcc59c..ee5615d6521 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -111,6 +111,10 @@ extern size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn, void *base_addr, pcpu_populate_pte_fn_t populate_pte_fn); +extern ssize_t __init pcpu_embed_first_chunk( + size_t static_size, size_t reserved_size, + ssize_t dyn_size, ssize_t unit_size); + /* * Use this to get to a cpu's version of the per-cpu object * dynamically allocated. Non-atomic access to the current CPU's -- cgit v1.2.3 From aaf1e176fa9a96fe1eea33b710684bba066aedc1 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 10 Mar 2009 10:55:15 +0000 Subject: ASoC: Add initial driver for the WM8400 CODEC The WM8400 is a highly integrated audio CODEC and power management unit intended for mobile multimedia application. This driver supports the primary audio CODEC features, including: - 1W speaker driver - Fully differential headphone output - Up to 4 differential microphone inputs Signed-off-by: Mark Brown --- include/linux/mfd/wm8400-audio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/wm8400-audio.h b/include/linux/mfd/wm8400-audio.h index b6640e01804..e06ed3eb1d0 100644 --- a/include/linux/mfd/wm8400-audio.h +++ b/include/linux/mfd/wm8400-audio.h @@ -1181,6 +1181,7 @@ #define WM8400_FLL_OUTDIV_SHIFT 0 /* FLL_OUTDIV - [2:0] */ #define WM8400_FLL_OUTDIV_WIDTH 3 /* FLL_OUTDIV - [2:0] */ +struct wm8400; void wm8400_reset_codec_reg_cache(struct wm8400 *wm8400); #endif -- cgit v1.2.3 From 9e6e70f8d8b6698e0017c56b86525aabe9c7cd4c Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 11 Mar 2009 14:10:24 -0400 Subject: NFSv4: Support NFSv4 optional attributes in the struct nfs_fattr Currently, filling struct nfs_fattr is more or less an all or nothing operation, since NFSv2 and NFSv3 have only mandatory attributes. In NFSv4, some attributes are optional, and so we may simply not be able to fill in those fields. Furthermore, NFSv4 allows you to specify which attributes you are interested in retrieving, thus permitting you to optimise away retrieval of attributes that you know will no change... Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 48 +++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 41 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 2e5f00066af..b99295e07cd 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -27,7 +27,7 @@ static inline int nfs_fsid_equal(const struct nfs_fsid *a, const struct nfs_fsid } struct nfs_fattr { - unsigned short valid; /* which fields are valid */ + unsigned int valid; /* which fields are valid */ __u64 pre_size; /* pre_op_attr.size */ struct timespec pre_mtime; /* pre_op_attr.mtime */ struct timespec pre_ctime; /* pre_op_attr.ctime */ @@ -59,12 +59,46 @@ struct nfs_fattr { unsigned long gencount; }; -#define NFS_ATTR_WCC 0x0001 /* pre-op WCC data */ -#define NFS_ATTR_FATTR 0x0002 /* post-op attributes */ -#define NFS_ATTR_FATTR_V3 0x0004 /* NFSv3 attributes */ -#define NFS_ATTR_FATTR_V4 0x0008 /* NFSv4 change attribute */ -#define NFS_ATTR_WCC_V4 0x0010 /* pre-op change attribute */ -#define NFS_ATTR_FATTR_V4_REFERRAL 0x0020 /* NFSv4 referral */ +#define NFS_ATTR_FATTR_TYPE (1U << 0) +#define NFS_ATTR_FATTR_MODE (1U << 1) +#define NFS_ATTR_FATTR_NLINK (1U << 2) +#define NFS_ATTR_FATTR_OWNER (1U << 3) +#define NFS_ATTR_FATTR_GROUP (1U << 4) +#define NFS_ATTR_FATTR_RDEV (1U << 5) +#define NFS_ATTR_FATTR_SIZE (1U << 6) +#define NFS_ATTR_FATTR_PRESIZE (1U << 7) +#define NFS_ATTR_FATTR_BLOCKS_USED (1U << 8) +#define NFS_ATTR_FATTR_SPACE_USED (1U << 9) +#define NFS_ATTR_FATTR_FSID (1U << 10) +#define NFS_ATTR_FATTR_FILEID (1U << 11) +#define NFS_ATTR_FATTR_ATIME (1U << 12) +#define NFS_ATTR_FATTR_MTIME (1U << 13) +#define NFS_ATTR_FATTR_CTIME (1U << 14) +#define NFS_ATTR_FATTR_PREMTIME (1U << 15) +#define NFS_ATTR_FATTR_PRECTIME (1U << 16) +#define NFS_ATTR_FATTR_CHANGE (1U << 17) +#define NFS_ATTR_FATTR_PRECHANGE (1U << 18) +#define NFS_ATTR_FATTR_V4_REFERRAL (1U << 19) /* NFSv4 referral */ + +#define NFS_ATTR_FATTR (NFS_ATTR_FATTR_TYPE \ + | NFS_ATTR_FATTR_MODE \ + | NFS_ATTR_FATTR_NLINK \ + | NFS_ATTR_FATTR_OWNER \ + | NFS_ATTR_FATTR_GROUP \ + | NFS_ATTR_FATTR_RDEV \ + | NFS_ATTR_FATTR_SIZE \ + | NFS_ATTR_FATTR_FSID \ + | NFS_ATTR_FATTR_FILEID \ + | NFS_ATTR_FATTR_ATIME \ + | NFS_ATTR_FATTR_MTIME \ + | NFS_ATTR_FATTR_CTIME) +#define NFS_ATTR_FATTR_V2 (NFS_ATTR_FATTR \ + | NFS_ATTR_FATTR_BLOCKS_USED) +#define NFS_ATTR_FATTR_V3 (NFS_ATTR_FATTR \ + | NFS_ATTR_FATTR_SPACE_USED) +#define NFS_ATTR_FATTR_V4 (NFS_ATTR_FATTR \ + | NFS_ATTR_FATTR_SPACE_USED \ + | NFS_ATTR_FATTR_CHANGE) /* * Info on the file system -- cgit v1.2.3 From 1ca277d88dafdbc3c5a69d32590e7184b9af6371 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 11 Mar 2009 14:10:25 -0400 Subject: NFS: Shrink the struct nfs_fattr We don't need the bitmap[] field anymore, since the 'valid' field tells us all we need to know about which attributes were filled in... Also move the pre-op attributes in order to improve the structure packing. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index b99295e07cd..6013acb0131 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -28,9 +28,6 @@ static inline int nfs_fsid_equal(const struct nfs_fsid *a, const struct nfs_fsid struct nfs_fattr { unsigned int valid; /* which fields are valid */ - __u64 pre_size; /* pre_op_attr.size */ - struct timespec pre_mtime; /* pre_op_attr.mtime */ - struct timespec pre_ctime; /* pre_op_attr.ctime */ enum nfs_ftype type; /* always use NFSv2 types */ __u32 mode; __u32 nlink; @@ -52,9 +49,11 @@ struct nfs_fattr { struct timespec atime; struct timespec mtime; struct timespec ctime; - __u32 bitmap[2]; /* NFSv4 returned attribute bitmap */ __u64 change_attr; /* NFSv4 change attribute */ __u64 pre_change_attr;/* pre-op NFSv4 change attribute */ + __u64 pre_size; /* pre_op_attr.size */ + struct timespec pre_mtime; /* pre_op_attr.mtime */ + struct timespec pre_ctime; /* pre_op_attr.ctime */ unsigned long time_start; unsigned long gencount; }; -- cgit v1.2.3 From bca794785c2c12ecddeb09e70165b8ff80baa6ae Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 11 Mar 2009 14:10:26 -0400 Subject: NFS: Fix the type of struct nfs_fattr->mode There is no point in using anything other than umode_t, since we copy the content pretty much directly into inode->i_mode. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 6013acb0131..0691b9c188d 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -28,8 +28,7 @@ static inline int nfs_fsid_equal(const struct nfs_fsid *a, const struct nfs_fsid struct nfs_fattr { unsigned int valid; /* which fields are valid */ - enum nfs_ftype type; /* always use NFSv2 types */ - __u32 mode; + umode_t mode; __u32 nlink; __u32 uid; __u32 gid; -- cgit v1.2.3 From a65318bf3afc93ce49227e849d213799b072c5fd Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 11 Mar 2009 14:10:28 -0400 Subject: NFSv4: Simplify some cache consistency post-op GETATTRs Certain asynchronous operations such as write() do not expect (or care) that other metadata such as the file owner, mode, acls, ... change. All they want to do is update and/or check the change attribute, ctime, and mtime. By skipping the file owner and group update, we also avoid having to do a potential idmapper upcall for these asynchronous RPC calls. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs_sb.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 9bb81aec91c..29b1e40dce9 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -106,6 +106,11 @@ struct nfs_server { u32 attr_bitmask[2];/* V4 bitmask representing the set of attributes supported on this filesystem */ + u32 cache_consistency_bitmask[2]; + /* V4 bitmask representing the subset + of change attribute, size, ctime + and mtime attributes supported by + the server */ u32 acl_bitmask; /* V4 bitmask representing the ACEs that are supported on this filesystem */ -- cgit v1.2.3 From fb8a1f11b64e213d94dfa1cebb2a42a7b8c115c4 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 11 Mar 2009 14:10:29 -0400 Subject: NFS: cleanup - remove struct nfs_inode->ncommit Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index db867b04ac3..c9fecd3e8f0 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -166,8 +166,7 @@ struct nfs_inode { */ struct radix_tree_root nfs_page_tree; - unsigned long ncommit, - npages; + unsigned long npages; /* Open contexts for shared mmap writes */ struct list_head open_files; -- cgit v1.2.3 From 72cb77f4a5ace37b12dcb47a0e8637a2c28ad881 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 11 Mar 2009 14:10:30 -0400 Subject: NFS: Throttle page dirtying while we're flushing to disk The following patch is a combination of a patch by myself and Peter Staubach. Trond: If we allow other processes to dirty pages while a process is doing a consistency sync to disk, we can end up never making progress. Peter: Attached is a patch which addresses a continuing problem with the NFS client generating out of order WRITE requests. While this is compliant with all of the current protocol specifications, there are servers in the market which can not handle out of order WRITE requests very well. Also, this may lead to sub-optimal block allocations in the underlying file system on the server. This may cause the read throughputs to be reduced when reading the file from the server. Peter: There has been a lot of work recently done to address out of order issues on a systemic level. However, the NFS client is still susceptible to the problem. Out of order WRITE requests can occur when pdflush is in the middle of writing out pages while the process dirtying the pages calls generic_file_buffered_write which calls generic_perform_write which calls balance_dirty_pages_rate_limited which ends up calling writeback_inodes which ends up calling back into the NFS client to writes out dirty pages for the same file that pdflush happens to be working with. Signed-off-by: Peter Staubach [modification by Trond to merge the two similar patches] Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index c9fecd3e8f0..933bc261c0d 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -206,6 +206,7 @@ struct nfs_inode { #define NFS_INO_STALE (1) /* possible stale inode */ #define NFS_INO_ACL_LRU_SET (2) /* Inode is on the LRU list */ #define NFS_INO_MOUNTPOINT (3) /* inode is remote mountpoint */ +#define NFS_INO_FLUSHING (4) /* inode is flushing out data */ static inline struct nfs_inode *NFS_I(const struct inode *inode) { -- cgit v1.2.3 From 441e3e242903f9b190d5764bed73edb58f977413 Mon Sep 17 00:00:00 2001 From: Tom Talpey Date: Wed, 11 Mar 2009 14:37:56 -0400 Subject: SUNRPC: dynamically load RPC transport modules on-demand Provide an api to attempt to load any necessary kernel RPC client transport module automatically. By convention, the desired module name is "xprt"+"transport name". For example, when NFS mounting with "-o proto=rdma", attempt to load the "xprtrdma" module. Signed-off-by: Tom Talpey Cc: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 11fc71d50c1..2b0d960603b 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -235,6 +235,7 @@ static inline __be32 *xprt_skip_transport_header(struct rpc_xprt *xprt, __be32 * */ int xprt_register_transport(struct xprt_class *type); int xprt_unregister_transport(struct xprt_class *type); +int xprt_load_transport(const char *); void xprt_set_retrans_timeout_def(struct rpc_task *task); void xprt_set_retrans_timeout_rtt(struct rpc_task *task); void xprt_wake_pending_tasks(struct rpc_xprt *xprt, int status); -- cgit v1.2.3 From f21cfb258df6dd3ea0b3e56d75c7e994edb81b35 Mon Sep 17 00:00:00 2001 From: Magnus Damm Date: Thu, 12 Mar 2009 21:05:42 +0900 Subject: irq: add remove_irq() for freeing of setup_irq() irqs Impact: add new API This patch adds a remove_irq() function for releasing interrupts requested with setup_irq(). Without this patch we have no way of releasing such interrupts since free_irq() today tries to kfree() the irqaction passed with setup_irq(). Signed-off-by: Magnus Damm LKML-Reference: <20090312120542.2926.56609.sendpatchset@rx1.opensource.se> Signed-off-by: Ingo Molnar --- include/linux/irq.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index f899b502f18..56f9988362e 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -236,6 +236,7 @@ typedef struct irq_desc irq_desc_t; #include extern int setup_irq(unsigned int irq, struct irqaction *new); +extern struct irqaction *remove_irq(unsigned int irq, void *dev_id); #ifdef CONFIG_GENERIC_HARDIRQS -- cgit v1.2.3 From cbf94f06824780183e4bba165c7c29d5c7bd9a51 Mon Sep 17 00:00:00 2001 From: Magnus Damm Date: Thu, 12 Mar 2009 21:05:51 +0900 Subject: irq: match remove_irq() args with setup_irq() Modify remove_irq() to match setup_irq(). Signed-off-by: Magnus Damm LKML-Reference: <20090312120551.2926.43942.sendpatchset@rx1.opensource.se> Signed-off-by: Ingo Molnar --- include/linux/irq.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index 56f9988362e..737eafbc1f3 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -236,7 +236,7 @@ typedef struct irq_desc irq_desc_t; #include extern int setup_irq(unsigned int irq, struct irqaction *new); -extern struct irqaction *remove_irq(unsigned int irq, void *dev_id); +extern void remove_irq(unsigned int irq, struct irqaction *act); #ifdef CONFIG_GENERIC_HARDIRQS -- cgit v1.2.3 From 71969fd9e2c523d22bf1742eb31f1562247710eb Mon Sep 17 00:00:00 2001 From: Boaz Harrosh Date: Sun, 25 Jan 2009 16:50:02 +0200 Subject: [SCSI] major.h: char-major number for OSD device driver Allocate major 260 for osd. Signed-off-by: Boaz Harrosh CC: Torben Mathiasen Signed-off-by: James Bottomley --- include/linux/major.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/major.h b/include/linux/major.h index 88249452b93..058ec15dd06 100644 --- a/include/linux/major.h +++ b/include/linux/major.h @@ -171,5 +171,6 @@ #define VIOTAPE_MAJOR 230 #define BLOCK_EXT_MAJOR 259 +#define SCSI_OSD_MAJOR 260 /* open-osd's OSD scsi device */ #endif -- cgit v1.2.3 From 4bb9c5c02153dfc89a6c73a6f32091413805ad7d Mon Sep 17 00:00:00 2001 From: "Pallipadi, Venkatesh" Date: Thu, 12 Mar 2009 17:45:27 -0700 Subject: VM, x86, PAT: Change is_linear_pfn_mapping to not use vm_pgoff Impact: fix false positive PAT warnings - also fix VirtalBox hang Use of vma->vm_pgoff to identify the pfnmaps that are fully mapped at mmap time is broken. vm_pgoff is set by generic mmap code even for cases where drivers are setting up the mappings at the fault time. The problem was originally reported here: http://marc.info/?l=linux-kernel&m=123383810628583&w=2 Change is_linear_pfn_mapping logic to overload VM_INSERTPAGE flag along with VM_PFNMAP to mean full PFNMAP setup at mmap time. Problem also tracked at: http://bugzilla.kernel.org/show_bug.cgi?id=12800 Reported-by: Thomas Hellstrom Tested-by: Frans Pop Signed-off-by: Venkatesh Pallipadi Signed-off-by: Suresh Siddha @intel.com> Cc: Nick Piggin Cc: "ebiederm@xmission.com" Cc: # only for 2.6.29.1, not .28 LKML-Reference: <20090313004527.GA7176@linux-os.sc.intel.com> Signed-off-by: Ingo Molnar --- include/linux/mm.h | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 065cdf8c09f..3daa05feed9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -98,7 +98,7 @@ extern unsigned int kobjsize(const void *objp); #define VM_HUGETLB 0x00400000 /* Huge TLB Page VM */ #define VM_NONLINEAR 0x00800000 /* Is non-linear (remap_file_pages) */ #define VM_MAPPED_COPY 0x01000000 /* T if mapped copy of data (nommu mmap) */ -#define VM_INSERTPAGE 0x02000000 /* The vma has had "vm_insert_page()" done on it */ +#define VM_INSERTPAGE 0x02000000 /* The vma has had "vm_insert_page()" done on it. Refer note in VM_PFNMAP_AT_MMAP below */ #define VM_ALWAYSDUMP 0x04000000 /* Always include in core dumps */ #define VM_CAN_NONLINEAR 0x08000000 /* Has ->fault & does nonlinear pages */ @@ -126,6 +126,17 @@ extern unsigned int kobjsize(const void *objp); */ #define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_RESERVED | VM_PFNMAP) +/* + * pfnmap vmas that are fully mapped at mmap time (not mapped on fault). + * Used by x86 PAT to identify such PFNMAP mappings and optimize their handling. + * Note VM_INSERTPAGE flag is overloaded here. i.e, + * VM_INSERTPAGE && !VM_PFNMAP implies + * The vma has had "vm_insert_page()" done on it + * VM_INSERTPAGE && VM_PFNMAP implies + * The vma is PFNMAP with full mapping at mmap time + */ +#define VM_PFNMAP_AT_MMAP (VM_INSERTPAGE | VM_PFNMAP) + /* * mapping from the currently active vm_flags protection bits (the * low four bits) to a page protection mask.. @@ -145,7 +156,7 @@ extern pgprot_t protection_map[16]; */ static inline int is_linear_pfn_mapping(struct vm_area_struct *vma) { - return ((vma->vm_flags & VM_PFNMAP) && vma->vm_pgoff); + return ((vma->vm_flags & VM_PFNMAP_AT_MMAP) == VM_PFNMAP_AT_MMAP); } static inline int is_pfn_mapping(struct vm_area_struct *vma) -- cgit v1.2.3 From a70f730282019f487aa33a84e5ac9a5e89c5abd0 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Fri, 13 Mar 2009 14:49:46 +1030 Subject: cpumask: replace node_to_cpumask with cpumask_of_node. Impact: cleanup node_to_cpumask (and the blecherous node_to_cpumask_ptr which contained a declaration) are replaced now everyone implements cpumask_of_node. Signed-off-by: Rusty Russell --- include/linux/topology.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/topology.h b/include/linux/topology.h index a16b9e06f2e..16b7d6896ce 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -38,11 +38,7 @@ #endif #ifndef nr_cpus_node -#define nr_cpus_node(node) \ - ({ \ - node_to_cpumask_ptr(__tmp__, node); \ - cpus_weight(*__tmp__); \ - }) +#define nr_cpus_node(node) cpumask_weight(cpumask_of_node(node)) #endif #define for_each_node_with_cpus(node) \ -- cgit v1.2.3 From d1dedb52acd98bd5e13e1ff4c4d045d58bbd16fe Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 13 Mar 2009 11:14:06 +0100 Subject: panic, smp: provide smp_send_stop() wrapper on UP too Impact: cleanup, no code changed Remove an ugly #ifdef CONFIG_SMP from panic(), by providing an smp_send_stop() wrapper on UP too. LKML-Reference: <49B91A7E.76E4.0078.0@novell.com> Signed-off-by: Ingo Molnar --- include/linux/smp.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/smp.h b/include/linux/smp.h index 2d3bcb6b37f..a69db820eed 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -38,7 +38,7 @@ int smp_call_function_single(int cpuid, void (*func) (void *info), void *info, /* * main cross-CPU interfaces, handles INIT, TLB flush, STOP, etc. * (defined in asm header): - */ + */ /* * stops all CPUs but the current one: @@ -122,6 +122,8 @@ extern unsigned int setup_max_cpus; #else /* !SMP */ +static inline void smp_send_stop(void) { } + /* * These macros fold the SMP functionality into a single CPU system */ -- cgit v1.2.3 From 3dd3d46b78c22503957230ca5981849b7bb29b9a Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 9 Mar 2009 21:48:32 +0100 Subject: genirq: remove unused hw_irq_controller typedef hw_irq_controller is unused. Remove the typedef Impact: cleanup Signed-off-by: Thomas Gleixner --- include/linux/irq.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index 737eafbc1f3..7c07a09931d 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -226,7 +226,6 @@ irq_remap_to_desc(unsigned int irq, struct irq_desc *desc) * Migration helpers for obsolete names, they will go away: */ #define hw_interrupt_type irq_chip -typedef struct irq_chip hw_irq_controller; #define no_irq_type no_irq_chip typedef struct irq_desc irq_desc_t; -- cgit v1.2.3 From bedd30d986a05e32dc3eab874e4b9ed8a38058bb Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 30 Sep 2008 23:14:27 +0200 Subject: genirq: make irqreturn_t an enum Impact: cleanup Remove the 2.4 compabiliy cruft Signed-off-by: Thomas Gleixner Reviewed-by: Peter Zijlstra --- include/linux/irq.h | 4 ++-- include/linux/irqreturn.h | 28 ++++++++++------------------ 2 files changed, 12 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index 7c07a09931d..19770923bcb 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -280,7 +280,7 @@ static inline int irq_balancing_disabled(unsigned int irq) } /* Handle irq action chains: */ -extern int handle_IRQ_event(unsigned int irq, struct irqaction *action); +extern irqreturn_t handle_IRQ_event(unsigned int irq, struct irqaction *action); /* * Built-in IRQ handlers for various IRQ types, @@ -325,7 +325,7 @@ static inline void generic_handle_irq(unsigned int irq) /* Handling of unhandled and spurious interrupts: */ extern void note_interrupt(unsigned int irq, struct irq_desc *desc, - int action_ret); + irqreturn_t action_ret); /* Resending of interrupts :*/ void check_irq_resend(struct irq_desc *desc, unsigned int irq); diff --git a/include/linux/irqreturn.h b/include/linux/irqreturn.h index 881883c2009..c5584ca5b8c 100644 --- a/include/linux/irqreturn.h +++ b/include/linux/irqreturn.h @@ -1,25 +1,17 @@ -/* irqreturn.h */ #ifndef _LINUX_IRQRETURN_H #define _LINUX_IRQRETURN_H -/* - * For 2.4.x compatibility, 2.4.x can use - * - * typedef void irqreturn_t; - * #define IRQ_NONE - * #define IRQ_HANDLED - * #define IRQ_RETVAL(x) - * - * To mix old-style and new-style irq handler returns. - * - * IRQ_NONE means we didn't handle it. - * IRQ_HANDLED means that we did have a valid interrupt and handled it. - * IRQ_RETVAL(x) selects on the two depending on x being non-zero (for handled) +/** + * enum irqreturn + * @IRQ_NONE interrupt was not from this device + * @IRQ_HANDLED interrupt was handled by this device */ -typedef int irqreturn_t; +enum irqreturn { + IRQ_NONE, + IRQ_HANDLED, +}; -#define IRQ_NONE (0) -#define IRQ_HANDLED (1) -#define IRQ_RETVAL(x) ((x) != 0) +typedef enum irqreturn irqreturn_t; +#define IRQ_RETVAL(x) ((x) != IRQ_NONE) #endif -- cgit v1.2.3 From a9d0a1a38352c4fb8946e73b3e42ba4ada29e733 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 3 Mar 2009 16:58:16 +0100 Subject: genirq: add doc to struct irqaction Impact: documentation struct irqaction is not documented. Add kernel doc comments and add interrupt.h to the genirq docbook. Signed-off-by: Thomas Gleixner --- include/linux/interrupt.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 468e3a25a4a..91658d07659 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -61,6 +61,17 @@ typedef irqreturn_t (*irq_handler_t)(int, void *); +/** + * struct irqaction - per interrupt action descriptor + * @handler: interrupt handler function + * @flags: flags (see IRQF_* above) + * @mask: no comment as it is useless and about to be removed + * @name: name of the device + * @dev_id: cookie to identify the device + * @next: pointer to the next irqaction for shared interrupts + * @irq: interrupt number + * @dir: pointer to the proc/irq/NN/name entry + */ struct irqaction { irq_handler_t handler; unsigned long flags; -- cgit v1.2.3 From 082edb7bf443eb8eda15b482d16ad9dd8137ad24 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Fri, 13 Mar 2009 23:43:37 +1030 Subject: numa, cpumask: move numa_node_id default implementation to topology.h Impact: cleanup, potential bugfix Not sure what changed to expose this, but clearly that numa_node_id() doesn't belong in mmzone.h (the inline in gfp.h is probably overkill, too). In file included from include/linux/topology.h:34, from arch/x86/mm/numa.c:2: /home/rusty/patches-cpumask/linux-2.6/arch/x86/include/asm/topology.h:64:1: warning: "numa_node_id" redefined In file included from include/linux/topology.h:32, from arch/x86/mm/numa.c:2: include/linux/mmzone.h:770:1: warning: this is the location of the previous definition Signed-off-by: Rusty Russell Cc: Mike Travis LKML-Reference: <200903132343.37661.rusty@rustcorp.com.au> Signed-off-by: Ingo Molnar --- include/linux/gfp.h | 1 + include/linux/mmzone.h | 6 ------ include/linux/topology.h | 5 +++++ 3 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index dd20cd78faa..0bbc15f5453 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -4,6 +4,7 @@ #include #include #include +#include struct vm_area_struct; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 1aca6cebbb7..e6aacf77986 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -764,12 +764,6 @@ extern int numa_zonelist_order_handler(struct ctl_table *, int, extern char numa_zonelist_order[]; #define NUMA_ZONELIST_ORDER_LEN 16 /* string buffer size */ -#include -/* Returns the number of the current Node. */ -#ifndef numa_node_id -#define numa_node_id() (cpu_to_node(raw_smp_processor_id())) -#endif - #ifndef CONFIG_NEED_MULTIPLE_NODES extern struct pglist_data contig_page_data; diff --git a/include/linux/topology.h b/include/linux/topology.h index 16b7d6896ce..7402c1a27c4 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -196,4 +196,9 @@ int arch_update_cpu_topology(void); #define topology_core_cpumask(cpu) cpumask_of(cpu) #endif +/* Returns the number of the current Node. */ +#ifndef numa_node_id +#define numa_node_id() (cpu_to_node(raw_smp_processor_id())) +#endif + #endif /* _LINUX_TOPOLOGY_H */ -- cgit v1.2.3 From ead2ceb0ec9f85cff19c43b5cdb2f8a054484431 Mon Sep 17 00:00:00 2001 From: Neil Horman Date: Wed, 11 Mar 2009 09:49:55 +0000 Subject: Network Drop Monitor: Adding kfree_skb_clean for non-drops and modifying end-of-line points for skbs Signed-off-by: Neil Horman include/linux/skbuff.h | 4 +++- net/core/datagram.c | 2 +- net/core/skbuff.c | 22 ++++++++++++++++++++++ net/ipv4/arp.c | 2 +- net/ipv4/udp.c | 2 +- net/packet/af_packet.c | 2 +- 6 files changed, 29 insertions(+), 5 deletions(-) Signed-off-by: David S. Miller --- include/linux/skbuff.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 1f659e8c2b8..1fbab2ae613 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -421,6 +421,7 @@ extern void skb_dma_unmap(struct device *dev, struct sk_buff *skb, #endif extern void kfree_skb(struct sk_buff *skb); +extern void consume_skb(struct sk_buff *skb); extern void __kfree_skb(struct sk_buff *skb); extern struct sk_buff *__alloc_skb(unsigned int size, gfp_t priority, int fclone, int node); @@ -459,7 +460,8 @@ extern int skb_to_sgvec(struct sk_buff *skb, extern int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer); extern int skb_pad(struct sk_buff *skb, int pad); -#define dev_kfree_skb(a) kfree_skb(a) +#define dev_kfree_skb(a) consume_skb(a) +#define dev_consume_skb(a) kfree_skb_clean(a) extern void skb_over_panic(struct sk_buff *skb, int len, void *here); extern void skb_under_panic(struct sk_buff *skb, int len, -- cgit v1.2.3 From 9a8afc8d3962f3ed26fd6b56db34133860ed1e72 Mon Sep 17 00:00:00 2001 From: Neil Horman Date: Wed, 11 Mar 2009 09:51:26 +0000 Subject: Network Drop Monitor: Adding drop monitor implementation & Netlink protocol Signed-off-by: Neil Horman include/linux/net_dropmon.h | 56 +++++++++ net/core/drop_monitor.c | 263 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 319 insertions(+) Signed-off-by: David S. Miller --- include/linux/net_dropmon.h | 56 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 56 insertions(+) create mode 100644 include/linux/net_dropmon.h (limited to 'include/linux') diff --git a/include/linux/net_dropmon.h b/include/linux/net_dropmon.h new file mode 100644 index 00000000000..0217fb81a63 --- /dev/null +++ b/include/linux/net_dropmon.h @@ -0,0 +1,56 @@ +#ifndef __NET_DROPMON_H +#define __NET_DROPMON_H + +#include + +struct net_dm_drop_point { + __u8 pc[8]; + __u32 count; +}; + +#define NET_DM_CFG_VERSION 0 +#define NET_DM_CFG_ALERT_COUNT 1 +#define NET_DM_CFG_ALERT_DELAY 2 +#define NET_DM_CFG_MAX 3 + +struct net_dm_config_entry { + __u32 type; + __u64 data __attribute__((aligned(8))); +}; + +struct net_dm_config_msg { + __u32 entries; + struct net_dm_config_entry options[0]; +}; + +struct net_dm_alert_msg { + __u32 entries; + struct net_dm_drop_point points[0]; +}; + +struct net_dm_user_msg { + union { + struct net_dm_config_msg user; + struct net_dm_alert_msg alert; + } u; +}; + + +/* These are the netlink message types for this protocol */ + +enum { + NET_DM_CMD_UNSPEC = 0, + NET_DM_CMD_ALERT, + NET_DM_CMD_CONFIG, + NET_DM_CMD_START, + NET_DM_CMD_STOP, + _NET_DM_CMD_MAX, +}; + +#define NET_DM_CMD_MAX (_NET_DM_CMD_MAX - 1) + +/* + * Our group identifiers + */ +#define NET_DM_GRP_ALERT 1 +#endif -- cgit v1.2.3 From 273ae44b9cb9443e0b5265cdc99f127ddb95c8db Mon Sep 17 00:00:00 2001 From: Neil Horman Date: Wed, 11 Mar 2009 09:53:16 +0000 Subject: Network Drop Monitor: Adding Build changes to enable drop monitor Network Drop Monitor: Adding Build changes to enable drop monitor Signed-off-by: Neil Horman include/linux/Kbuild | 1 + net/Kconfig | 11 +++++++++++ net/core/Makefile | 1 + 3 files changed, 13 insertions(+) Signed-off-by: David S. Miller --- include/linux/Kbuild | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index 106c3ba5084..e9581fd9fb6 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -115,6 +115,7 @@ header-y += mqueue.h header-y += mtio.h header-y += ncp_no.h header-y += neighbour.h +header-y += net_dropmon.h header-y += netfilter_arp.h header-y += netrom.h header-y += nfs2.h -- cgit v1.2.3 From 211c738d86f3f423f1b218ab3a356c9538e38047 Mon Sep 17 00:00:00 2001 From: Yi Zou Date: Fri, 27 Feb 2009 14:06:37 -0800 Subject: [SCSI] net, fcoe: add ETH_P_FCOE for Fibre Channel over Ethernet (FCoE) This adds eth type ETH_P_FCOE for Fibre Channel over Ethernet (FCoE), consequently, the ETH_P_FCOE from fc_fcoe.h and fcoe skb->protocol is not set as ETH_P_FCOE. Signed-off-by: Yi Zou Acked-by: David Miller Signed-off-by: James Bottomley --- include/linux/if_ether.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/if_ether.h b/include/linux/if_ether.h index 7f3c735f422..59d197cb485 100644 --- a/include/linux/if_ether.h +++ b/include/linux/if_ether.h @@ -78,6 +78,7 @@ #define ETH_P_PAE 0x888E /* Port Access Entity (IEEE 802.1X) */ #define ETH_P_AOE 0x88A2 /* ATA over Ethernet */ #define ETH_P_TIPC 0x88CA /* TIPC */ +#define ETH_P_FCOE 0x8906 /* Fibre Channel over Ethernet */ #define ETH_P_EDSA 0xDADA /* Ethertype DSA [ NOT AN OFFICIALLY REGISTERED ID ] */ /* -- cgit v1.2.3 From 43eb99c5b349b188f82725652f3d1018c619d682 Mon Sep 17 00:00:00 2001 From: Chris Leech Date: Fri, 27 Feb 2009 14:06:43 -0800 Subject: [SCSI] net: reclaim 8 upper bits of the netdev->features from GSO Reclaim 8 upper bits of netdev->features from GSO. Signed-off-by: Chris Leech Signed-off-by: Yi Zou Acked-by: David Miller Signed-off-by: James Bottomley --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ec54785d34f..c8238d9ba37 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -652,7 +652,7 @@ struct net_device /* Segmentation offload features */ #define NETIF_F_GSO_SHIFT 16 -#define NETIF_F_GSO_MASK 0xffff0000 +#define NETIF_F_GSO_MASK 0x00ff0000 #define NETIF_F_TSO (SKB_GSO_TCPV4 << NETIF_F_GSO_SHIFT) #define NETIF_F_UFO (SKB_GSO_UDP << NETIF_F_GSO_SHIFT) #define NETIF_F_GSO_ROBUST (SKB_GSO_DODGY << NETIF_F_GSO_SHIFT) -- cgit v1.2.3 From 01d5b2fca1fa58ed5039239fd531e9f658971ace Mon Sep 17 00:00:00 2001 From: Chris Leech Date: Fri, 27 Feb 2009 14:06:49 -0800 Subject: [SCSI] net: define feature flags for FCoE offloads Define feature flags for FCoE offloads. Signed-off-by: Chris Leech Signed-off-by: Yi Zou Acked-by: David Miller Signed-off-by: James Bottomley --- include/linux/netdevice.h | 3 +++ include/linux/skbuff.h | 2 ++ 2 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c8238d9ba37..5c405571cb6 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -650,6 +650,8 @@ struct net_device #define NETIF_F_GRO 16384 /* Generic receive offload */ #define NETIF_F_LRO 32768 /* large receive offload */ +#define NETIF_F_FCOE_CRC (1 << 24) /* FCoE CRC32 */ + /* Segmentation offload features */ #define NETIF_F_GSO_SHIFT 16 #define NETIF_F_GSO_MASK 0x00ff0000 @@ -658,6 +660,7 @@ struct net_device #define NETIF_F_GSO_ROBUST (SKB_GSO_DODGY << NETIF_F_GSO_SHIFT) #define NETIF_F_TSO_ECN (SKB_GSO_TCP_ECN << NETIF_F_GSO_SHIFT) #define NETIF_F_TSO6 (SKB_GSO_TCPV6 << NETIF_F_GSO_SHIFT) +#define NETIF_F_FSO (SKB_GSO_FCOE << NETIF_F_GSO_SHIFT) /* List of features with software fallbacks. */ #define NETIF_F_GSO_SOFTWARE (NETIF_F_TSO | NETIF_F_TSO_ECN | NETIF_F_TSO6) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9dcf956ad18..02adea2099a 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -188,6 +188,8 @@ enum { SKB_GSO_TCP_ECN = 1 << 3, SKB_GSO_TCPV6 = 1 << 4, + + SKB_GSO_FCOE = 1 << 5, }; #if BITS_PER_LONG > 32 -- cgit v1.2.3 From 4d288d5767f853bfca25adc7b6030dc95518cb2e Mon Sep 17 00:00:00 2001 From: Yi Zou Date: Fri, 27 Feb 2009 14:06:59 -0800 Subject: [SCSI] net: add FCoE offload support through net_device This adds support to provide Fiber Channel over Ethernet (FCoE) offload through net_device's net_device_ops struct. The offload through net_device for FCoE is enabled in kernel as built-in or module driver. Signed-off-by: Yi Zou Acked-by: David Miller Signed-off-by: James Bottomley --- include/linux/netdevice.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5c405571cb6..7ed49f5335b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -582,6 +582,14 @@ struct net_device_ops { #define HAVE_NETDEV_POLL void (*ndo_poll_controller)(struct net_device *dev); #endif +#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE) + int (*ndo_fcoe_ddp_setup)(struct net_device *dev, + u16 xid, + struct scatterlist *sgl, + unsigned int sgc); + int (*ndo_fcoe_ddp_done)(struct net_device *dev, + u16 xid); +#endif }; /* @@ -843,6 +851,11 @@ struct net_device struct dcbnl_rtnl_ops *dcbnl_ops; #endif +#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE) + /* max exchange id for FCoE LRO by ddp */ + unsigned int fcoe_ddp_xid; +#endif + #ifdef CONFIG_COMPAT_NET_DEV_OPS struct { int (*init)(struct net_device *dev); -- cgit v1.2.3 From 4ab3b73f85ca2e99d9dbdb55ac13e57327a7e915 Mon Sep 17 00:00:00 2001 From: Douglas Gilbert Date: Mon, 9 Mar 2009 10:51:38 -0400 Subject: [SCSI] bsg: add linux/types.h include to bsg.h Since bsg.h has recently been added to the list of kernel headers that should be exported to the user space, this attachment makes bsg.h more user space "friendly". Specifically autotools dislike headers that don't compile freestanding and bsg.h's use of __u32 types (and friends) are not standard C (C90 or C99). The inclusion of linux/types.h fixes that. Signed-off-by: Douglas Gilbert Signed-off-by: James Bottomley --- include/linux/bsg.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bsg.h b/include/linux/bsg.h index cf0303a6061..6c0a00dfa90 100644 --- a/include/linux/bsg.h +++ b/include/linux/bsg.h @@ -1,6 +1,8 @@ #ifndef BSG_H #define BSG_H +#include + #define BSG_PROTOCOL_SCSI 0 #define BSG_SUB_PROTOCOL_SCSI_CMD 0 -- cgit v1.2.3 From dec3f95959bff957f5bcbf16c2a2823f7e33d1e7 Mon Sep 17 00:00:00 2001 From: Eric Moore Date: Mon, 9 Mar 2009 01:27:49 -0600 Subject: [SCSI] mpt2sas: add MPT2SAS_MINOR(221) to miscdevice.h Signed-off-by: Eric Moore Signed-off-by: James Bottomley --- include/linux/miscdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/miscdevice.h b/include/linux/miscdevice.h index a820f816a49..beb6ec99cfe 100644 --- a/include/linux/miscdevice.h +++ b/include/linux/miscdevice.h @@ -26,6 +26,7 @@ #define TUN_MINOR 200 #define MWAVE_MINOR 219 /* ACP/Mwave Modem */ #define MPT_MINOR 220 +#define MPT2SAS_MINOR 221 #define HPET_MINOR 228 #define FUSE_MINOR 229 #define KVM_MINOR 232 -- cgit v1.2.3 From a390d1f379cf821248b735f43d2e1147ebb8241d Mon Sep 17 00:00:00 2001 From: Marcin Slusarz Date: Fri, 13 Mar 2009 15:41:19 -0700 Subject: phylib: convert state_queue work to delayed_work It closes a race in phy_stop_machine when reprogramming of phy_timer (from phy_state_machine) happens between del_timer_sync and cancel_work_sync. Without this change it could lead to crash if phy_device would be freed after phy_stop_machine (timer would fire and schedule freed work). Signed-off-by: Marcin Slusarz Acked-by: Jean Delvare Signed-off-by: David S. Miller --- include/linux/phy.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index d7e54d98869..32cf14a4b03 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -315,8 +315,7 @@ struct phy_device { /* Interrupt and Polling infrastructure */ struct work_struct phy_queue; - struct work_struct state_queue; - struct timer_list phy_timer; + struct delayed_work state_queue; atomic_t irq_disable; struct mutex lock; -- cgit v1.2.3 From 9c705260feea6ae329bc6b6d5f6d2ef0227eda0a Mon Sep 17 00:00:00 2001 From: Gabriele Paoloni Date: Fri, 13 Mar 2009 16:09:12 -0700 Subject: ppp: ppp_mp_explode() redesign I found the PPP subsystem to not work properly when connecting channels with different speeds to the same bundle. Problem Description: As the "ppp_mp_explode" function fragments the sk_buff buffer evenly among the PPP channels that are connected to a certain PPP unit to make up a bundle, if we are transmitting using an upper layer protocol that requires an Ack before sending the next packet (like TCP/IP for example), we will have a bandwidth bottleneck on the slowest channel of the bundle. Let's clarify by an example. Let's consider a scenario where we have two PPP links making up a bundle: a slow link (10KB/sec) and a fast link (1000KB/sec) working at the best (full bandwidth). On the top we have a TCP/IP stack sending a 1000 Bytes sk_buff buffer down to the PPP subsystem. The "ppp_mp_explode" function will divide the buffer in two fragments of 500B each (we are neglecting all the headers, crc, flags etc?.). Before the TCP/IP stack sends out the next buffer, it will have to wait for the ACK response from the remote peer, so it will have to wait for both fragments to have been sent over the two PPP links, received by the remote peer and reconstructed. The resulting behaviour is that, rather than having a bundle working @1010KB/sec (the sum of the channels bandwidths), we'll have a bundle working @20KB/sec (the double of the slowest channels bandwidth). Problem Solution: The problem has been solved by redesigning the "ppp_mp_explode" function in such a way to make it split the sk_buff buffer according to the speeds of the underlying PPP channels (the speeds of the serial interfaces respectively attached to the PPP channels). Referring to the above example, the redesigned "ppp_mp_explode" function will now divide the 1000 Bytes buffer into two fragments whose sizes are set according to the speeds of the channels where they are going to be sent on (e.g . 10 Byets on 10KB/sec channel and 990 Bytes on 1000KB/sec channel). The reworked function grants the same performances of the original one in optimal working conditions (i.e. a bundle made up of PPP links all working at the same speed), while greatly improving performances on the bundles made up of channels working at different speeds. Signed-off-by: Gabriele Paoloni Signed-off-by: David S. Miller --- include/linux/ppp_channel.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ppp_channel.h b/include/linux/ppp_channel.h index 9d64bdf1477..0d3fa63e90e 100644 --- a/include/linux/ppp_channel.h +++ b/include/linux/ppp_channel.h @@ -40,8 +40,8 @@ struct ppp_channel { int mtu; /* max transmit packet size */ int hdrlen; /* amount of headroom channel needs */ void *ppp; /* opaque to channel */ - /* the following are not used at present */ int speed; /* transfer rate (bytes/second) */ + /* the following is not used at present */ int latency; /* overhead time in milliseconds */ }; -- cgit v1.2.3 From 895791dac6946d535991edd11341046f8e85ea77 Mon Sep 17 00:00:00 2001 From: "Pallipadi, Venkatesh" Date: Fri, 13 Mar 2009 16:35:44 -0700 Subject: VM, x86, PAT: add a new vm flag to track full pfnmap at mmap Impact: cleanup Add a new vm flag VM_PFN_AT_MMAP to identify a PFNMAP that is fully mapped with remap_pfn_range. Patch removes the overloading of VM_INSERTPAGE from the earlier patch. Signed-off-by: Venkatesh Pallipadi Signed-off-by: Suresh Siddha Acked-by: Nick Piggin LKML-Reference: <20090313233543.GA19909@linux-os.sc.intel.com> Signed-off-by: Ingo Molnar --- include/linux/mm.h | 16 +++------------- 1 file changed, 3 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 3daa05feed9..b1ea37fc7a2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -98,12 +98,13 @@ extern unsigned int kobjsize(const void *objp); #define VM_HUGETLB 0x00400000 /* Huge TLB Page VM */ #define VM_NONLINEAR 0x00800000 /* Is non-linear (remap_file_pages) */ #define VM_MAPPED_COPY 0x01000000 /* T if mapped copy of data (nommu mmap) */ -#define VM_INSERTPAGE 0x02000000 /* The vma has had "vm_insert_page()" done on it. Refer note in VM_PFNMAP_AT_MMAP below */ +#define VM_INSERTPAGE 0x02000000 /* The vma has had "vm_insert_page()" done on it */ #define VM_ALWAYSDUMP 0x04000000 /* Always include in core dumps */ #define VM_CAN_NONLINEAR 0x08000000 /* Has ->fault & does nonlinear pages */ #define VM_MIXEDMAP 0x10000000 /* Can contain "struct page" and pure PFN pages */ #define VM_SAO 0x20000000 /* Strong Access Ordering (powerpc) */ +#define VM_PFN_AT_MMAP 0x40000000 /* PFNMAP vma that is fully mapped at mmap time */ #ifndef VM_STACK_DEFAULT_FLAGS /* arch can override this */ #define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS @@ -126,17 +127,6 @@ extern unsigned int kobjsize(const void *objp); */ #define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_RESERVED | VM_PFNMAP) -/* - * pfnmap vmas that are fully mapped at mmap time (not mapped on fault). - * Used by x86 PAT to identify such PFNMAP mappings and optimize their handling. - * Note VM_INSERTPAGE flag is overloaded here. i.e, - * VM_INSERTPAGE && !VM_PFNMAP implies - * The vma has had "vm_insert_page()" done on it - * VM_INSERTPAGE && VM_PFNMAP implies - * The vma is PFNMAP with full mapping at mmap time - */ -#define VM_PFNMAP_AT_MMAP (VM_INSERTPAGE | VM_PFNMAP) - /* * mapping from the currently active vm_flags protection bits (the * low four bits) to a page protection mask.. @@ -156,7 +146,7 @@ extern pgprot_t protection_map[16]; */ static inline int is_linear_pfn_mapping(struct vm_area_struct *vma) { - return ((vma->vm_flags & VM_PFNMAP_AT_MMAP) == VM_PFNMAP_AT_MMAP); + return (vma->vm_flags & VM_PFN_AT_MMAP); } static inline int is_pfn_mapping(struct vm_area_struct *vma) -- cgit v1.2.3 From 8bdd663aba341c15cd2fa9dbd7061b8b387964dc Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 15 Mar 2009 19:59:13 -0700 Subject: net: reorder fields of struct socket On x86_64, its rather unfortunate that "wait_queue_head_t wait" field of "struct socket" spans two cache lines (assuming a 64 bytes cache line in current cpus) offsetof(struct socket, wait)=0x30 sizeof(wait_queue_head_t)=0x18 This might explain why Kenny Chang noticed that his multicast workload was performing bad with 64 bit kernels, since more cache lines ping pongs were involved. This litle patch moves "wait" field next "fasync_list" so that both fields share a single cache line, to speedup sock_def_readable() Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/net.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index 4515efae4c3..4fc2ffd527f 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -129,11 +129,15 @@ struct socket { socket_state state; short type; unsigned long flags; - const struct proto_ops *ops; + /* + * Please keep fasync_list & wait fields in the same cache line + */ struct fasync_struct *fasync_list; + wait_queue_head_t wait; + struct file *file; struct sock *sk; - wait_queue_head_t wait; + const struct proto_ops *ops; }; struct vm_area_struct; -- cgit v1.2.3 From 0c54b85f2828128274f319a1eb3ce7f604fe2a53 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Sat, 14 Mar 2009 14:23:05 +0000 Subject: tcp: simplify tcp_current_mss MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There's very little need for most of the callsites to get tp->xmit_goal_size updated. That will cost us divide as is, so slice the function in two. Also, the only users of the tp->xmit_goal_size are directly behind tcp_current_mss(), so there's no need to store that variable into tcp_sock at all! The drop of xmit_goal_size currently leaves 16-bit hole and some reorganization would again be necessary to change that (but I'm aiming to fill that hole with u16 xmit_goal_size_segs to cache the results of the remaining divide to get that tso on regression). Bring xmit_goal_size parts into tcp.c Signed-off-by: Ilpo Järvinen Cc: Evgeniy Polyakov Cc: Ingo Molnar Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 4b86ad71e05..ad2021ccc55 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -248,7 +248,6 @@ struct tcp_sock { /* inet_connection_sock has to be the first member of tcp_sock */ struct inet_connection_sock inet_conn; u16 tcp_header_len; /* Bytes of tcp header to send */ - u16 xmit_size_goal; /* Goal for segmenting output packets */ /* * Header prediction flags -- cgit v1.2.3 From 2a3a041c4e2c1685e668b280c121a5a40a029a03 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Sat, 14 Mar 2009 22:45:16 +0000 Subject: tcp: cache result of earlier divides when mss-aligning things MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The results is very unlikely change every so often so we hardly need to divide again after doing that once for a connection. Yet, if divide still becomes necessary we detect that and do the right thing and again settle for non-divide state. Takes the u16 space which was previously taken by the plain xmit_size_goal. This should take care part of the tso vs non-tso difference we found earlier. Signed-off-by: Ilpo Järvinen Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index ad2021ccc55..9d5078bd23a 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -248,6 +248,7 @@ struct tcp_sock { /* inet_connection_sock has to be the first member of tcp_sock */ struct inet_connection_sock inet_conn; u16 tcp_header_len; /* Bytes of tcp header to send */ + u16 xmit_size_goal_segs; /* Goal for segmenting output packets */ /* * Header prediction flags -- cgit v1.2.3 From 684999149002dd046269666a390458e0acb38280 Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Fri, 6 Feb 2009 13:52:43 -0700 Subject: Rename struct file->f_ep_lock This lock moves out of the CONFIG_EPOLL ifdef and becomes f_lock. For now, epoll remains the only user, but a future patch will use it to protect f_flags as well. Cc: Davide Libenzi Reviewed-by: Christoph Hellwig Signed-off-by: Jonathan Corbet --- include/linux/eventpoll.h | 1 - include/linux/fs.h | 2 +- 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/eventpoll.h b/include/linux/eventpoll.h index f1e1d3c4712..f6856a5a1d4 100644 --- a/include/linux/eventpoll.h +++ b/include/linux/eventpoll.h @@ -61,7 +61,6 @@ struct file; static inline void eventpoll_init_file(struct file *file) { INIT_LIST_HEAD(&file->f_ep_links); - spin_lock_init(&file->f_ep_lock); } diff --git a/include/linux/fs.h b/include/linux/fs.h index 92734c0012e..2011600d12c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -848,6 +848,7 @@ struct file { #define f_dentry f_path.dentry #define f_vfsmnt f_path.mnt const struct file_operations *f_op; + spinlock_t f_lock; /* f_ep_links */ atomic_long_t f_count; unsigned int f_flags; fmode_t f_mode; @@ -866,7 +867,6 @@ struct file { #ifdef CONFIG_EPOLL /* Used by fs/eventpoll.c to link all the hooks to this file */ struct list_head f_ep_links; - spinlock_t f_ep_lock; #endif /* #ifdef CONFIG_EPOLL */ struct address_space *f_mapping; #ifdef CONFIG_DEBUG_WRITECOUNT -- cgit v1.2.3 From db1dd4d376134eba0e08af523b61cc566a4ea1cd Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Fri, 6 Feb 2009 15:25:24 -0700 Subject: Use f_lock to protect f_flags Traditionally, changes to struct file->f_flags have been done under BKL protection, or with no protection at all. This patch causes all f_flags changes after file open/creation time to be done under protection of f_lock. This allows the removal of some BKL usage and fixes a number of longstanding (if microscopic) races. Reviewed-by: Christoph Hellwig Cc: Al Viro Signed-off-by: Jonathan Corbet --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 2011600d12c..7428c6d35e6 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -848,7 +848,7 @@ struct file { #define f_dentry f_path.dentry #define f_vfsmnt f_path.mnt const struct file_operations *f_op; - spinlock_t f_lock; /* f_ep_links */ + spinlock_t f_lock; /* f_ep_links, f_flags */ atomic_long_t f_count; unsigned int f_flags; fmode_t f_mode; -- cgit v1.2.3 From acc738fec03bdaa5b77340c32a82fbfedaaabef0 Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Mon, 16 Mar 2009 15:35:29 +0100 Subject: netfilter: xtables: avoid pointer to self Commit 784544739a25c30637397ace5489eeb6e15d7d49 (netfilter: iptables: lock free counters) broke a number of modules whose rule data referenced itself. A reallocation would not reestablish the correct references, so it is best to use a separate struct that does not fall under RCU. Signed-off-by: Jan Engelhardt Signed-off-by: Patrick McHardy --- include/linux/netfilter/xt_limit.h | 9 +++++---- include/linux/netfilter/xt_quota.h | 4 +++- include/linux/netfilter/xt_statistic.h | 7 ++++--- 3 files changed, 12 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/xt_limit.h b/include/linux/netfilter/xt_limit.h index b3ce65375ec..fda222c7953 100644 --- a/include/linux/netfilter/xt_limit.h +++ b/include/linux/netfilter/xt_limit.h @@ -4,6 +4,8 @@ /* timings are in milliseconds. */ #define XT_LIMIT_SCALE 10000 +struct xt_limit_priv; + /* 1/10,000 sec period => max of 10,000/sec. Min rate is then 429490 seconds, or one every 59 hours. */ struct xt_rateinfo { @@ -11,11 +13,10 @@ struct xt_rateinfo { u_int32_t burst; /* Period multiplier for upper limit. */ /* Used internally by the kernel */ - unsigned long prev; - u_int32_t credit; + unsigned long prev; /* moved to xt_limit_priv */ + u_int32_t credit; /* moved to xt_limit_priv */ u_int32_t credit_cap, cost; - /* Ugly, ugly fucker. */ - struct xt_rateinfo *master; + struct xt_limit_priv *master; }; #endif /*_XT_RATE_H*/ diff --git a/include/linux/netfilter/xt_quota.h b/include/linux/netfilter/xt_quota.h index 4c8368d781e..8dc89dfc136 100644 --- a/include/linux/netfilter/xt_quota.h +++ b/include/linux/netfilter/xt_quota.h @@ -6,13 +6,15 @@ enum xt_quota_flags { }; #define XT_QUOTA_MASK 0x1 +struct xt_quota_priv; + struct xt_quota_info { u_int32_t flags; u_int32_t pad; /* Used internally by the kernel */ aligned_u64 quota; - struct xt_quota_info *master; + struct xt_quota_priv *master; }; #endif /* _XT_QUOTA_H */ diff --git a/include/linux/netfilter/xt_statistic.h b/include/linux/netfilter/xt_statistic.h index 3d38bc97504..8f521ab49ef 100644 --- a/include/linux/netfilter/xt_statistic.h +++ b/include/linux/netfilter/xt_statistic.h @@ -13,6 +13,8 @@ enum xt_statistic_flags { }; #define XT_STATISTIC_MASK 0x1 +struct xt_statistic_priv; + struct xt_statistic_info { u_int16_t mode; u_int16_t flags; @@ -23,11 +25,10 @@ struct xt_statistic_info { struct { u_int32_t every; u_int32_t packet; - /* Used internally by the kernel */ - u_int32_t count; + u_int32_t count; /* unused */ } nth; } u; - struct xt_statistic_info *master __attribute__((aligned(8))); + struct xt_statistic_priv *master __attribute__((aligned(8))); }; #endif /* _XT_STATISTIC_H */ -- cgit v1.2.3 From 0269ea4937343536ec7e85649932bc8c9686ea78 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 16 Mar 2009 17:10:36 +0100 Subject: netfilter: xtables: add cluster match This patch adds the iptables cluster match. This match can be used to deploy gateway and back-end load-sharing clusters. The cluster can be composed of 32 nodes maximum (although I have only tested this with two nodes, so I cannot tell what is the real scalability limit of this solution in terms of cluster nodes). Assuming that all the nodes see all packets (see below for an example on how to do that if your switch does not allow this), the cluster match decides if this node has to handle a packet given: (jhash(source IP) % total_nodes) & node_mask For related connections, the master conntrack is used. The following is an example of its use to deploy a gateway cluster composed of two nodes (where this is the node 1): iptables -I PREROUTING -t mangle -i eth1 -m cluster \ --cluster-total-nodes 2 --cluster-local-node 1 \ --cluster-proc-name eth1 -j MARK --set-mark 0xffff iptables -A PREROUTING -t mangle -i eth1 \ -m mark ! --mark 0xffff -j DROP iptables -A PREROUTING -t mangle -i eth2 -m cluster \ --cluster-total-nodes 2 --cluster-local-node 1 \ --cluster-proc-name eth2 -j MARK --set-mark 0xffff iptables -A PREROUTING -t mangle -i eth2 \ -m mark ! --mark 0xffff -j DROP And the following commands to make all nodes see the same packets: ip maddr add 01:00:5e:00:01:01 dev eth1 ip maddr add 01:00:5e:00:01:02 dev eth2 arptables -I OUTPUT -o eth1 --h-length 6 \ -j mangle --mangle-mac-s 01:00:5e:00:01:01 arptables -I INPUT -i eth1 --h-length 6 \ --destination-mac 01:00:5e:00:01:01 \ -j mangle --mangle-mac-d 00:zz:yy:xx:5a:27 arptables -I OUTPUT -o eth2 --h-length 6 \ -j mangle --mangle-mac-s 01:00:5e:00:01:02 arptables -I INPUT -i eth2 --h-length 6 \ --destination-mac 01:00:5e:00:01:02 \ -j mangle --mangle-mac-d 00:zz:yy:xx:5a:27 In the case of TCP connections, pickup facility has to be disabled to avoid marking TCP ACK packets coming in the reply direction as valid. echo 0 > /proc/sys/net/netfilter/nf_conntrack_tcp_loose BTW, some final notes: * This match mangles the skbuff pkt_type in case that it detects PACKET_MULTICAST for a non-multicast address. This may be done in a PKTTYPE target for this sole purpose. * This match supersedes the CLUSTERIP target. Signed-off-by: Pablo Neira Ayuso Signed-off-by: Patrick McHardy --- include/linux/netfilter/Kbuild | 1 + include/linux/netfilter/xt_cluster.h | 15 +++++++++++++++ 2 files changed, 16 insertions(+) create mode 100644 include/linux/netfilter/xt_cluster.h (limited to 'include/linux') diff --git a/include/linux/netfilter/Kbuild b/include/linux/netfilter/Kbuild index 947b47d7f6c..af9d2fb9721 100644 --- a/include/linux/netfilter/Kbuild +++ b/include/linux/netfilter/Kbuild @@ -21,6 +21,7 @@ header-y += xt_connbytes.h header-y += xt_connlimit.h header-y += xt_connmark.h header-y += xt_conntrack.h +header-y += xt_cluster.h header-y += xt_dccp.h header-y += xt_dscp.h header-y += xt_esp.h diff --git a/include/linux/netfilter/xt_cluster.h b/include/linux/netfilter/xt_cluster.h new file mode 100644 index 00000000000..5e0a0d07b52 --- /dev/null +++ b/include/linux/netfilter/xt_cluster.h @@ -0,0 +1,15 @@ +#ifndef _XT_CLUSTER_MATCH_H +#define _XT_CLUSTER_MATCH_H + +enum xt_cluster_flags { + XT_CLUSTER_F_INV = (1 << 0) +}; + +struct xt_cluster_match_info { + u_int32_t total_nodes; + u_int32_t node_mask; + u_int32_t hash_seed; + u_int32_t flags; +}; + +#endif /* _XT_CLUSTER_MATCH_H */ -- cgit v1.2.3 From d1c76af9e2434fac3add561e26c61b06503de986 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Mon, 16 Mar 2009 10:50:02 -0700 Subject: GRO: Move netpoll checks to correct location As my netpoll fix for net doesn't really work for net-next, we need this update to move the checks into the right place. As it stands we may pass freed skbs to netpoll_receive_skb. This patch also introduces a netpoll_rx_on function to avoid GRO completely if we're invoked through netpoll. This might seem paranoid but as netpoll may have an external receive hook it's better to be safe than sorry. I don't think we need this for 2.6.29 though since there's nothing immediately broken by it. This patch also moves the GRO_* return values to netdevice.h since VLAN needs them too (I tried to avoid this originally but alas this seems to be the easiest way out). This fixes a bug in VLAN where it continued to use the old return value 2 instead of the correct GRO_DROP. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/netdevice.h | 8 ++++++++ include/linux/netpoll.h | 11 +++++++++++ 2 files changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 493b065f76d..be3ebd7e8ce 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -330,6 +330,14 @@ enum NAPI_STATE_NPSVC, /* Netpoll - don't dequeue from poll_list */ }; +enum { + GRO_MERGED, + GRO_MERGED_FREE, + GRO_HELD, + GRO_NORMAL, + GRO_DROP, +}; + extern void __napi_schedule(struct napi_struct *n); static inline int napi_disable_pending(struct napi_struct *n) diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index e38d3c9dccd..de99025f2c5 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -63,6 +63,13 @@ static inline int netpoll_rx(struct sk_buff *skb) return ret; } +static inline int netpoll_rx_on(struct sk_buff *skb) +{ + struct netpoll_info *npinfo = skb->dev->npinfo; + + return npinfo && (npinfo->rx_np || npinfo->rx_flags); +} + static inline int netpoll_receive_skb(struct sk_buff *skb) { if (!list_empty(&skb->dev->napi_list)) @@ -99,6 +106,10 @@ static inline int netpoll_rx(struct sk_buff *skb) { return 0; } +static inline int netpoll_rx_on(struct sk_buff *skb) +{ + return 0; +} static inline int netpoll_receive_skb(struct sk_buff *skb) { return 0; -- cgit v1.2.3 From 7db90f4a25bd4184f3d36dfa4f512f53b0448da7 Mon Sep 17 00:00:00 2001 From: "Luis R. Rodriguez" Date: Mon, 9 Mar 2009 22:07:41 -0400 Subject: cfg80211: move enum reg_set_by to nl80211.h We do this so we can later inform userspace who set the regulatory domain and provide details of the request. Signed-off-by: Luis R. Rodriguez Signed-off-by: John W. Linville --- include/linux/nl80211.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index f6e56370ea6..c0fd432b57d 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -672,6 +672,25 @@ enum nl80211_bitrate_attr { NL80211_BITRATE_ATTR_MAX = __NL80211_BITRATE_ATTR_AFTER_LAST - 1 }; +/** + * enum nl80211_initiator - Indicates the initiator of a reg domain request + * @NL80211_REGDOM_SET_BY_CORE: Core queried CRDA for a dynamic world + * regulatory domain. + * @NL80211_REGDOM_SET_BY_USER: User asked the wireless core to set the + * regulatory domain. + * @NL80211_REGDOM_SET_BY_DRIVER: a wireless drivers has hinted to the + * wireless core it thinks its knows the regulatory domain we should be in. + * @NL80211_REGDOM_SET_BY_COUNTRY_IE: the wireless core has received an + * 802.11 country information element with regulatory information it + * thinks we should consider. + */ +enum nl80211_reg_initiator { + NL80211_REGDOM_SET_BY_CORE, + NL80211_REGDOM_SET_BY_USER, + NL80211_REGDOM_SET_BY_DRIVER, + NL80211_REGDOM_SET_BY_COUNTRY_IE, +}; + /** * enum nl80211_reg_rule_attr - regulatory rule attributes * @NL80211_ATTR_REG_RULE_FLAGS: a set of flags which specify additional -- cgit v1.2.3 From 73d54c9e74c4d8ee8a41bc516f481f0f754eca32 Mon Sep 17 00:00:00 2001 From: "Luis R. Rodriguez" Date: Mon, 9 Mar 2009 22:07:42 -0400 Subject: cfg80211: add regulatory netlink multicast group This allows us to send to userspace "regulatory" events. For now we just send an event when we change regulatory domains. We also notify userspace when devices are using their own custom world roaming regulatory domains. Signed-off-by: Luis R. Rodriguez Signed-off-by: John W. Linville --- include/linux/nl80211.h | 48 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 48 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index c0fd432b57d..f33aa08dd9b 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -150,6 +150,17 @@ * @NL80211_CMD_SCAN_ABORTED: scan was aborted, for unspecified reasons, * partial scan results may be available * + * @NL80211_CMD_REG_CHANGE: indicates to userspace the regulatory domain + * has been changed and provides details of the request information + * that caused the change such as who initiated the regulatory request + * (%NL80211_ATTR_REG_INITIATOR), the wiphy_idx + * (%NL80211_ATTR_REG_ALPHA2) on which the request was made from if + * the initiator was %NL80211_REGDOM_SET_BY_COUNTRY_IE or + * %NL80211_REGDOM_SET_BY_DRIVER, the type of regulatory domain + * set (%NL80211_ATTR_REG_TYPE), if the type of regulatory domain is + * %NL80211_REG_TYPE_COUNTRY the alpha2 to which we have moved on + * to (%NL80211_ATTR_REG_ALPHA2). + * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use */ @@ -204,6 +215,8 @@ enum nl80211_commands { NL80211_CMD_NEW_SCAN_RESULTS, NL80211_CMD_SCAN_ABORTED, + NL80211_CMD_REG_CHANGE, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ @@ -218,6 +231,8 @@ enum nl80211_commands { #define NL80211_CMD_SET_BSS NL80211_CMD_SET_BSS #define NL80211_CMD_SET_MGMT_EXTRA_IE NL80211_CMD_SET_MGMT_EXTRA_IE +#define NL80211_CMD_REG_CHANGE NL80211_CMD_REG_CHANGE + /** * enum nl80211_attrs - nl80211 netlink attributes * @@ -329,6 +344,11 @@ enum nl80211_commands { * messages carried the same generation number) * @NL80211_ATTR_BSS: scan result BSS * + * @NL80211_ATTR_REG_INITIATOR: indicates who requested the regulatory domain + * currently in effect. This could be any of the %NL80211_REGDOM_SET_BY_* + * @NL80211_ATTR_REG_TYPE: indicates the type of the regulatory domain currently + * set. This can be one of the nl80211_reg_type (%NL80211_REGDOM_TYPE_*) + * * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use */ @@ -403,6 +423,9 @@ enum nl80211_attrs { NL80211_ATTR_SCAN_GENERATION, NL80211_ATTR_BSS, + NL80211_ATTR_REG_INITIATOR, + NL80211_ATTR_REG_TYPE, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -420,6 +443,8 @@ enum nl80211_attrs { #define NL80211_ATTR_WIPHY_CHANNEL_TYPE NL80211_ATTR_WIPHY_CHANNEL_TYPE #define NL80211_ATTR_MGMT_SUBTYPE NL80211_ATTR_MGMT_SUBTYPE #define NL80211_ATTR_IE NL80211_ATTR_IE +#define NL80211_ATTR_REG_INITIATOR NL80211_ATTR_REG_INITIATOR +#define NL80211_ATTR_REG_TYPE NL80211_ATTR_REG_TYPE #define NL80211_MAX_SUPP_RATES 32 #define NL80211_MAX_SUPP_REG_RULES 32 @@ -691,6 +716,29 @@ enum nl80211_reg_initiator { NL80211_REGDOM_SET_BY_COUNTRY_IE, }; +/** + * enum nl80211_reg_type - specifies the type of regulatory domain + * @NL80211_REGDOM_TYPE_COUNTRY: the regulatory domain set is one that pertains + * to a specific country. When this is set you can count on the + * ISO / IEC 3166 alpha2 country code being valid. + * @NL80211_REGDOM_TYPE_WORLD: the regulatory set domain is the world regulatory + * domain. + * @NL80211_REGDOM_TYPE_CUSTOM_WORLD: the regulatory domain set is a custom + * driver specific world regulatory domain. These do not apply system-wide + * and are only applicable to the individual devices which have requested + * them to be applied. + * @NL80211_REGDOM_TYPE_INTERSECTION: the regulatory domain set is the product + * of an intersection between two regulatory domains -- the previously + * set regulatory domain on the system and the last accepted regulatory + * domain request to be processed. + */ +enum nl80211_reg_type { + NL80211_REGDOM_TYPE_COUNTRY, + NL80211_REGDOM_TYPE_WORLD, + NL80211_REGDOM_TYPE_CUSTOM_WORLD, + NL80211_REGDOM_TYPE_INTERSECTION, +}; + /** * enum nl80211_reg_rule_attr - regulatory rule attributes * @NL80211_ATTR_REG_RULE_FLAGS: a set of flags which specify additional -- cgit v1.2.3 From ac26c18bd35d982d1ba06020a992b1085fefc3e2 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Thu, 12 Feb 2009 16:19:13 +0100 Subject: dma-debug: add function to dump dma mappings This adds a function to dump the DMA mappings that the debugging code is aware of -- either for a single device, or for _all_ devices. This can be useful for debugging -- sticking a call to it in the DMA page fault handler, for example, to see if the faulting address _should_ be mapped or not, and hence work out whether it's IOMMU bugs we're seeing, or driver bugs. Signed-off-by: David Woodhouse --- include/linux/dma-debug.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma-debug.h b/include/linux/dma-debug.h index 4985c6c5237..46a11c10da0 100644 --- a/include/linux/dma-debug.h +++ b/include/linux/dma-debug.h @@ -76,6 +76,8 @@ extern void debug_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nelems, int direction); +extern void debug_dma_dump_mappings(struct device *dev); + #else /* CONFIG_DMA_API_DEBUG */ static inline void dma_debug_init(u32 num_entries) @@ -156,6 +158,10 @@ static inline void debug_dma_sync_sg_for_device(struct device *dev, { } +static inline void debug_dma_dump_mappings(struct device *dev) +{ +} + #endif /* CONFIG_DMA_API_DEBUG */ #endif /* __DMA_DEBUG_H */ -- cgit v1.2.3 From 41531c8f5f05aba5ec645d9770557eedbf75b422 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 16 Mar 2009 17:32:14 +0100 Subject: dma-debug: add a check dma memory leaks Impact: allow architectures to monitor busses for dma mem leakage This patch adds checking code to detect if a device has pending DMA operations when it is about to be unbound from its device driver. Signed-off-by: Joerg Roedel --- include/linux/dma-debug.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma-debug.h b/include/linux/dma-debug.h index 46a11c10da0..e851d23e91e 100644 --- a/include/linux/dma-debug.h +++ b/include/linux/dma-debug.h @@ -24,9 +24,12 @@ struct device; struct scatterlist; +struct bus_type; #ifdef CONFIG_DMA_API_DEBUG +extern void dma_debug_add_bus(struct bus_type *bus); + extern void dma_debug_init(u32 num_entries); extern void debug_dma_map_page(struct device *dev, struct page *page, @@ -80,6 +83,10 @@ extern void debug_dma_dump_mappings(struct device *dev); #else /* CONFIG_DMA_API_DEBUG */ +void dma_debug_add_bus(struct bus_type *bus) +{ +} + static inline void dma_debug_init(u32 num_entries) { } -- cgit v1.2.3 From 9d783ba042771284fb4ee5013c3d94220755ae7f Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Mon, 16 Mar 2009 17:04:55 -0700 Subject: x86, x2apic: enable fault handling for intr-remapping Impact: interface augmentation (not yet used) Enable fault handling flow for intr-remapping aswell. Fault handling code now shared by both dma-remapping and intr-remapping. Signed-off-by: Suresh Siddha Signed-off-by: H. Peter Anvin --- include/linux/dmar.h | 5 ++--- include/linux/intel-iommu.h | 4 ++-- 2 files changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmar.h b/include/linux/dmar.h index f28440784cf..c7768330c11 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -49,6 +49,7 @@ extern int dmar_dev_scope_init(void); /* Intel IOMMU detection */ extern void detect_intel_iommu(void); +extern int enable_drhd_fault_handling(void); extern int parse_ioapics_under_ir(void); @@ -116,9 +117,6 @@ extern struct intel_iommu *map_ioapic_to_ir(int apic); #define intr_remapping_enabled (0) #endif -#ifdef CONFIG_DMAR -extern const char *dmar_get_fault_reason(u8 fault_reason); - /* Can't use the common MSI interrupt functions * since DMAR is not a pci device */ @@ -129,6 +127,7 @@ extern void dmar_msi_write(int irq, struct msi_msg *msg); extern int dmar_set_interrupt(struct intel_iommu *iommu); extern int arch_setup_dmar_msi(unsigned int irq); +#ifdef CONFIG_DMAR extern int iommu_detected, no_iommu; extern struct list_head dmar_rmrr_units; struct dmar_rmrr_unit { diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index d2e3cbfba14..a9563840644 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -292,6 +292,8 @@ struct intel_iommu { spinlock_t register_lock; /* protect register handling */ int seq_id; /* sequence id of the iommu */ int agaw; /* agaw of this iommu */ + unsigned int irq; + unsigned char name[13]; /* Device Name */ #ifdef CONFIG_DMAR unsigned long *domain_ids; /* bitmap of domains */ @@ -299,8 +301,6 @@ struct intel_iommu { spinlock_t lock; /* protect context, domain ids */ struct root_entry *root_entry; /* virtual address */ - unsigned int irq; - unsigned char name[7]; /* Device Name */ struct iommu_flush flush; #endif struct q_inval *qi; /* Queued invalidation info */ -- cgit v1.2.3 From eba67e5da6e971993b2899d2cdf459ce77d3dbc5 Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Mon, 16 Mar 2009 17:04:56 -0700 Subject: x86, dmar: routines for disabling queued invalidation and intr remapping Impact: new interfaces (not yet used) Routines for disabling queued invalidation and interrupt remapping. Signed-off-by: Suresh Siddha Signed-off-by: H. Peter Anvin --- include/linux/intel-iommu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index a9563840644..78c1262e870 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -321,6 +321,7 @@ extern struct dmar_drhd_unit * dmar_find_matched_drhd_unit(struct pci_dev *dev); extern int alloc_iommu(struct dmar_drhd_unit *drhd); extern void free_iommu(struct intel_iommu *iommu); extern int dmar_enable_qi(struct intel_iommu *iommu); +extern void dmar_disable_qi(struct intel_iommu *iommu); extern void qi_global_iec(struct intel_iommu *iommu); extern int qi_flush_context(struct intel_iommu *iommu, u16 did, u16 sid, -- cgit v1.2.3 From 1531a6a6b81a4e6f9eec9a5608758a6ea14b96e0 Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Mon, 16 Mar 2009 17:04:57 -0700 Subject: x86, dmar: start with sane state while enabling dma and interrupt-remapping Impact: cleanup/sanitization Start from a sane state while enabling dma and interrupt-remapping, by clearing the previous recorded faults and disabling previously enabled queued invalidation and interrupt-remapping. Signed-off-by: Suresh Siddha Signed-off-by: H. Peter Anvin --- include/linux/dmar.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmar.h b/include/linux/dmar.h index c7768330c11..8a035aec14a 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -24,6 +24,7 @@ #include #include #include +#include #if defined(CONFIG_DMAR) || defined(CONFIG_INTR_REMAP) struct intel_iommu; @@ -125,6 +126,7 @@ extern void dmar_msi_mask(unsigned int irq); extern void dmar_msi_read(int irq, struct msi_msg *msg); extern void dmar_msi_write(int irq, struct msi_msg *msg); extern int dmar_set_interrupt(struct intel_iommu *iommu); +extern irqreturn_t dmar_fault(int irq, void *dev_id); extern int arch_setup_dmar_msi(unsigned int irq); #ifdef CONFIG_DMAR -- cgit v1.2.3 From 29b61be65a33c95564fa82e7e8d60d97adb68ea8 Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Mon, 16 Mar 2009 17:05:02 -0700 Subject: x86, x2apic: cleanup ifdef CONFIG_INTR_REMAP in io_apic code Impact: cleanup Clean up #ifdefs and replace them with helper functions. Signed-off-by: Suresh Siddha Signed-off-by: H. Peter Anvin --- include/linux/dmar.h | 45 ++++++++++++++++++++++++++++++++++++++------- 1 file changed, 38 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmar.h b/include/linux/dmar.h index 8a035aec14a..2f342746895 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -26,9 +26,8 @@ #include #include -#if defined(CONFIG_DMAR) || defined(CONFIG_INTR_REMAP) struct intel_iommu; - +#if defined(CONFIG_DMAR) || defined(CONFIG_INTR_REMAP) struct dmar_drhd_unit { struct list_head list; /* list of drhd units */ struct acpi_dmar_header *hdr; /* ACPI header */ @@ -52,7 +51,6 @@ extern int dmar_dev_scope_init(void); extern void detect_intel_iommu(void); extern int enable_drhd_fault_handling(void); - extern int parse_ioapics_under_ir(void); extern int alloc_iommu(struct dmar_drhd_unit *); #else @@ -65,12 +63,12 @@ static inline int dmar_table_init(void) { return -ENODEV; } +static inline int enable_drhd_fault_handling(void) +{ + return -1; +} #endif /* !CONFIG_DMAR && !CONFIG_INTR_REMAP */ -#ifdef CONFIG_INTR_REMAP -extern int intr_remapping_enabled; -extern int enable_intr_remapping(int); - struct irte { union { struct { @@ -99,6 +97,10 @@ struct irte { __u64 high; }; }; +#ifdef CONFIG_INTR_REMAP +extern int intr_remapping_enabled; +extern int enable_intr_remapping(int); + extern int get_irte(int irq, struct irte *entry); extern int modify_irte(int irq, struct irte *irte_modified); extern int alloc_irte(struct intel_iommu *iommu, int irq, u16 count); @@ -113,6 +115,35 @@ extern int irq_remapped(int irq); extern struct intel_iommu *map_dev_to_ir(struct pci_dev *dev); extern struct intel_iommu *map_ioapic_to_ir(int apic); #else +static inline int alloc_irte(struct intel_iommu *iommu, int irq, u16 count) +{ + return -1; +} +static inline int modify_irte(int irq, struct irte *irte_modified) +{ + return -1; +} +static inline int free_irte(int irq) +{ + return -1; +} +static inline int map_irq_to_irte_handle(int irq, u16 *sub_handle) +{ + return -1; +} +static inline int set_irte_irq(int irq, struct intel_iommu *iommu, u16 index, + u16 sub_handle) +{ + return -1; +} +static inline struct intel_iommu *map_dev_to_ir(struct pci_dev *dev) +{ + return NULL; +} +static inline struct intel_iommu *map_ioapic_to_ir(int apic) +{ + return NULL; +} #define irq_remapped(irq) (0) #define enable_intr_remapping(mode) (-1) #define intr_remapping_enabled (0) -- cgit v1.2.3 From 84be58d4601c86306cd939ebf58a9b90989883a4 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 18 Mar 2009 11:50:29 +0100 Subject: dma-debug: fix dma_debug_add_bus() definition for !CONFIG_DMA_API_DEBUG Impact: build fix Fix: arch/x86/kvm/x86.o: In function `dma_debug_add_bus': (.text+0x0): multiple definition of `dma_debug_add_bus' dma_debug_add_bus() should be a static inline function. Cc: Joerg Roedel LKML-Reference: <20090317120112.GP6159@amd.com> Signed-off-by: Ingo Molnar --- include/linux/dma-debug.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dma-debug.h b/include/linux/dma-debug.h index e851d23e91e..28d53cb7b5a 100644 --- a/include/linux/dma-debug.h +++ b/include/linux/dma-debug.h @@ -83,7 +83,7 @@ extern void debug_dma_dump_mappings(struct device *dev); #else /* CONFIG_DMA_API_DEBUG */ -void dma_debug_add_bus(struct bus_type *bus) +static inline void dma_debug_add_bus(struct bus_type *bus) { } -- cgit v1.2.3 From a4773c08f2872626cb923433284488fbe8acb0ae Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Mon, 2 Feb 2009 17:23:10 -0500 Subject: nfsd4: use helper for copying filehandles for replay Signed-off-by: J. Bruce Fields --- include/linux/nfsd/nfsfh.h | 7 +++++++ include/linux/nfsd/state.h | 3 +-- 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfsd/nfsfh.h b/include/linux/nfsd/nfsfh.h index fa317f6c154..afa19016c4a 100644 --- a/include/linux/nfsd/nfsfh.h +++ b/include/linux/nfsd/nfsfh.h @@ -269,6 +269,13 @@ fh_copy(struct svc_fh *dst, struct svc_fh *src) return dst; } +static inline void +fh_copy_shallow(struct knfsd_fh *dst, struct knfsd_fh *src) +{ + dst->fh_size = src->fh_size; + memcpy(&dst->fh_base, &src->fh_base, src->fh_size); +} + static __inline__ struct svc_fh * fh_init(struct svc_fh *fhp, int maxsize) { diff --git a/include/linux/nfsd/state.h b/include/linux/nfsd/state.h index 128298c0362..b65b2a6274b 100644 --- a/include/linux/nfsd/state.h +++ b/include/linux/nfsd/state.h @@ -168,8 +168,7 @@ struct nfs4_replay { unsigned int rp_buflen; char *rp_buf; unsigned intrp_allocated; - int rp_openfh_len; - char rp_openfh[NFS4_FHSIZE]; + struct knfsd_fh rp_openfh; char rp_ibuf[NFSD4_REPLAY_ISIZE]; }; -- cgit v1.2.3 From 6c02eaa1d1e53b9b2cc27d0c6fff3e57da4b611f Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Mon, 2 Feb 2009 17:30:51 -0500 Subject: nfsd4: use helper for copying delegation filehandle Signed-off-by: J. Bruce Fields --- include/linux/nfsd/state.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfsd/state.h b/include/linux/nfsd/state.h index b65b2a6274b..1130d534bb6 100644 --- a/include/linux/nfsd/state.h +++ b/include/linux/nfsd/state.h @@ -66,8 +66,7 @@ struct nfs4_cb_recall { u32 cbr_ident; int cbr_trunc; stateid_t cbr_stateid; - u32 cbr_fhlen; - char cbr_fhval[NFS4_FHSIZE]; + struct knfsd_fh cbr_fh; struct nfs4_delegation *cbr_dp; }; @@ -86,8 +85,7 @@ struct nfs4_delegation { }; #define dl_stateid dl_recall.cbr_stateid -#define dl_fhlen dl_recall.cbr_fhlen -#define dl_fhval dl_recall.cbr_fhval +#define dl_fh dl_recall.cbr_fh /* client delegation callback info */ struct nfs4_callback { -- cgit v1.2.3 From 77f18f5e4ebdea35ec3d92343b0ed7546dc87637 Mon Sep 17 00:00:00 2001 From: Harvey Harrison Date: Wed, 11 Feb 2009 17:16:58 -0800 Subject: nfs: replace uses of __constant_{endian} The base versions handle constant folding now, none of these headers are exported to userspace, so the __ prefixed versions are not necessary. Signed-off-by: Harvey Harrison Reviewed-by: NeilBrown Signed-off-by: J. Bruce Fields --- include/linux/lockd/xdr.h | 12 ++--- include/linux/lockd/xdr4.h | 10 ++-- include/linux/nfsd/nfsd.h | 132 ++++++++++++++++++++++----------------------- include/linux/sunrpc/xdr.h | 42 +++++++-------- 4 files changed, 98 insertions(+), 98 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockd/xdr.h b/include/linux/lockd/xdr.h index 7dc5b6cb44c..d39ed1cc5fb 100644 --- a/include/linux/lockd/xdr.h +++ b/include/linux/lockd/xdr.h @@ -25,13 +25,13 @@ struct svc_rqst; #define NLM_MAXCOOKIELEN 32 #define NLM_MAXSTRLEN 1024 -#define nlm_granted __constant_htonl(NLM_LCK_GRANTED) -#define nlm_lck_denied __constant_htonl(NLM_LCK_DENIED) -#define nlm_lck_denied_nolocks __constant_htonl(NLM_LCK_DENIED_NOLOCKS) -#define nlm_lck_blocked __constant_htonl(NLM_LCK_BLOCKED) -#define nlm_lck_denied_grace_period __constant_htonl(NLM_LCK_DENIED_GRACE_PERIOD) +#define nlm_granted cpu_to_be32(NLM_LCK_GRANTED) +#define nlm_lck_denied cpu_to_be32(NLM_LCK_DENIED) +#define nlm_lck_denied_nolocks cpu_to_be32(NLM_LCK_DENIED_NOLOCKS) +#define nlm_lck_blocked cpu_to_be32(NLM_LCK_BLOCKED) +#define nlm_lck_denied_grace_period cpu_to_be32(NLM_LCK_DENIED_GRACE_PERIOD) -#define nlm_drop_reply __constant_htonl(30000) +#define nlm_drop_reply cpu_to_be32(30000) /* Lock info passed via NLM */ struct nlm_lock { diff --git a/include/linux/lockd/xdr4.h b/include/linux/lockd/xdr4.h index 12bfe09de2b..7353821341e 100644 --- a/include/linux/lockd/xdr4.h +++ b/include/linux/lockd/xdr4.h @@ -15,11 +15,11 @@ #include /* error codes new to NLMv4 */ -#define nlm4_deadlock __constant_htonl(NLM_DEADLCK) -#define nlm4_rofs __constant_htonl(NLM_ROFS) -#define nlm4_stale_fh __constant_htonl(NLM_STALE_FH) -#define nlm4_fbig __constant_htonl(NLM_FBIG) -#define nlm4_failed __constant_htonl(NLM_FAILED) +#define nlm4_deadlock cpu_to_be32(NLM_DEADLCK) +#define nlm4_rofs cpu_to_be32(NLM_ROFS) +#define nlm4_stale_fh cpu_to_be32(NLM_STALE_FH) +#define nlm4_fbig cpu_to_be32(NLM_FBIG) +#define nlm4_failed cpu_to_be32(NLM_FAILED) diff --git a/include/linux/nfsd/nfsd.h b/include/linux/nfsd/nfsd.h index e19f45991b2..16f7b403d9c 100644 --- a/include/linux/nfsd/nfsd.h +++ b/include/linux/nfsd/nfsd.h @@ -186,78 +186,78 @@ void nfsd_lockd_shutdown(void); /* * These macros provide pre-xdr'ed values for faster operation. */ -#define nfs_ok __constant_htonl(NFS_OK) -#define nfserr_perm __constant_htonl(NFSERR_PERM) -#define nfserr_noent __constant_htonl(NFSERR_NOENT) -#define nfserr_io __constant_htonl(NFSERR_IO) -#define nfserr_nxio __constant_htonl(NFSERR_NXIO) -#define nfserr_eagain __constant_htonl(NFSERR_EAGAIN) -#define nfserr_acces __constant_htonl(NFSERR_ACCES) -#define nfserr_exist __constant_htonl(NFSERR_EXIST) -#define nfserr_xdev __constant_htonl(NFSERR_XDEV) -#define nfserr_nodev __constant_htonl(NFSERR_NODEV) -#define nfserr_notdir __constant_htonl(NFSERR_NOTDIR) -#define nfserr_isdir __constant_htonl(NFSERR_ISDIR) -#define nfserr_inval __constant_htonl(NFSERR_INVAL) -#define nfserr_fbig __constant_htonl(NFSERR_FBIG) -#define nfserr_nospc __constant_htonl(NFSERR_NOSPC) -#define nfserr_rofs __constant_htonl(NFSERR_ROFS) -#define nfserr_mlink __constant_htonl(NFSERR_MLINK) -#define nfserr_opnotsupp __constant_htonl(NFSERR_OPNOTSUPP) -#define nfserr_nametoolong __constant_htonl(NFSERR_NAMETOOLONG) -#define nfserr_notempty __constant_htonl(NFSERR_NOTEMPTY) -#define nfserr_dquot __constant_htonl(NFSERR_DQUOT) -#define nfserr_stale __constant_htonl(NFSERR_STALE) -#define nfserr_remote __constant_htonl(NFSERR_REMOTE) -#define nfserr_wflush __constant_htonl(NFSERR_WFLUSH) -#define nfserr_badhandle __constant_htonl(NFSERR_BADHANDLE) -#define nfserr_notsync __constant_htonl(NFSERR_NOT_SYNC) -#define nfserr_badcookie __constant_htonl(NFSERR_BAD_COOKIE) -#define nfserr_notsupp __constant_htonl(NFSERR_NOTSUPP) -#define nfserr_toosmall __constant_htonl(NFSERR_TOOSMALL) -#define nfserr_serverfault __constant_htonl(NFSERR_SERVERFAULT) -#define nfserr_badtype __constant_htonl(NFSERR_BADTYPE) -#define nfserr_jukebox __constant_htonl(NFSERR_JUKEBOX) -#define nfserr_denied __constant_htonl(NFSERR_DENIED) -#define nfserr_deadlock __constant_htonl(NFSERR_DEADLOCK) -#define nfserr_expired __constant_htonl(NFSERR_EXPIRED) -#define nfserr_bad_cookie __constant_htonl(NFSERR_BAD_COOKIE) -#define nfserr_same __constant_htonl(NFSERR_SAME) -#define nfserr_clid_inuse __constant_htonl(NFSERR_CLID_INUSE) -#define nfserr_stale_clientid __constant_htonl(NFSERR_STALE_CLIENTID) -#define nfserr_resource __constant_htonl(NFSERR_RESOURCE) -#define nfserr_moved __constant_htonl(NFSERR_MOVED) -#define nfserr_nofilehandle __constant_htonl(NFSERR_NOFILEHANDLE) -#define nfserr_minor_vers_mismatch __constant_htonl(NFSERR_MINOR_VERS_MISMATCH) -#define nfserr_share_denied __constant_htonl(NFSERR_SHARE_DENIED) -#define nfserr_stale_stateid __constant_htonl(NFSERR_STALE_STATEID) -#define nfserr_old_stateid __constant_htonl(NFSERR_OLD_STATEID) -#define nfserr_bad_stateid __constant_htonl(NFSERR_BAD_STATEID) -#define nfserr_bad_seqid __constant_htonl(NFSERR_BAD_SEQID) -#define nfserr_symlink __constant_htonl(NFSERR_SYMLINK) -#define nfserr_not_same __constant_htonl(NFSERR_NOT_SAME) -#define nfserr_restorefh __constant_htonl(NFSERR_RESTOREFH) -#define nfserr_attrnotsupp __constant_htonl(NFSERR_ATTRNOTSUPP) -#define nfserr_bad_xdr __constant_htonl(NFSERR_BAD_XDR) -#define nfserr_openmode __constant_htonl(NFSERR_OPENMODE) -#define nfserr_locks_held __constant_htonl(NFSERR_LOCKS_HELD) -#define nfserr_op_illegal __constant_htonl(NFSERR_OP_ILLEGAL) -#define nfserr_grace __constant_htonl(NFSERR_GRACE) -#define nfserr_no_grace __constant_htonl(NFSERR_NO_GRACE) -#define nfserr_reclaim_bad __constant_htonl(NFSERR_RECLAIM_BAD) -#define nfserr_badname __constant_htonl(NFSERR_BADNAME) -#define nfserr_cb_path_down __constant_htonl(NFSERR_CB_PATH_DOWN) -#define nfserr_locked __constant_htonl(NFSERR_LOCKED) -#define nfserr_wrongsec __constant_htonl(NFSERR_WRONGSEC) -#define nfserr_replay_me __constant_htonl(NFSERR_REPLAY_ME) +#define nfs_ok cpu_to_be32(NFS_OK) +#define nfserr_perm cpu_to_be32(NFSERR_PERM) +#define nfserr_noent cpu_to_be32(NFSERR_NOENT) +#define nfserr_io cpu_to_be32(NFSERR_IO) +#define nfserr_nxio cpu_to_be32(NFSERR_NXIO) +#define nfserr_eagain cpu_to_be32(NFSERR_EAGAIN) +#define nfserr_acces cpu_to_be32(NFSERR_ACCES) +#define nfserr_exist cpu_to_be32(NFSERR_EXIST) +#define nfserr_xdev cpu_to_be32(NFSERR_XDEV) +#define nfserr_nodev cpu_to_be32(NFSERR_NODEV) +#define nfserr_notdir cpu_to_be32(NFSERR_NOTDIR) +#define nfserr_isdir cpu_to_be32(NFSERR_ISDIR) +#define nfserr_inval cpu_to_be32(NFSERR_INVAL) +#define nfserr_fbig cpu_to_be32(NFSERR_FBIG) +#define nfserr_nospc cpu_to_be32(NFSERR_NOSPC) +#define nfserr_rofs cpu_to_be32(NFSERR_ROFS) +#define nfserr_mlink cpu_to_be32(NFSERR_MLINK) +#define nfserr_opnotsupp cpu_to_be32(NFSERR_OPNOTSUPP) +#define nfserr_nametoolong cpu_to_be32(NFSERR_NAMETOOLONG) +#define nfserr_notempty cpu_to_be32(NFSERR_NOTEMPTY) +#define nfserr_dquot cpu_to_be32(NFSERR_DQUOT) +#define nfserr_stale cpu_to_be32(NFSERR_STALE) +#define nfserr_remote cpu_to_be32(NFSERR_REMOTE) +#define nfserr_wflush cpu_to_be32(NFSERR_WFLUSH) +#define nfserr_badhandle cpu_to_be32(NFSERR_BADHANDLE) +#define nfserr_notsync cpu_to_be32(NFSERR_NOT_SYNC) +#define nfserr_badcookie cpu_to_be32(NFSERR_BAD_COOKIE) +#define nfserr_notsupp cpu_to_be32(NFSERR_NOTSUPP) +#define nfserr_toosmall cpu_to_be32(NFSERR_TOOSMALL) +#define nfserr_serverfault cpu_to_be32(NFSERR_SERVERFAULT) +#define nfserr_badtype cpu_to_be32(NFSERR_BADTYPE) +#define nfserr_jukebox cpu_to_be32(NFSERR_JUKEBOX) +#define nfserr_denied cpu_to_be32(NFSERR_DENIED) +#define nfserr_deadlock cpu_to_be32(NFSERR_DEADLOCK) +#define nfserr_expired cpu_to_be32(NFSERR_EXPIRED) +#define nfserr_bad_cookie cpu_to_be32(NFSERR_BAD_COOKIE) +#define nfserr_same cpu_to_be32(NFSERR_SAME) +#define nfserr_clid_inuse cpu_to_be32(NFSERR_CLID_INUSE) +#define nfserr_stale_clientid cpu_to_be32(NFSERR_STALE_CLIENTID) +#define nfserr_resource cpu_to_be32(NFSERR_RESOURCE) +#define nfserr_moved cpu_to_be32(NFSERR_MOVED) +#define nfserr_nofilehandle cpu_to_be32(NFSERR_NOFILEHANDLE) +#define nfserr_minor_vers_mismatch cpu_to_be32(NFSERR_MINOR_VERS_MISMATCH) +#define nfserr_share_denied cpu_to_be32(NFSERR_SHARE_DENIED) +#define nfserr_stale_stateid cpu_to_be32(NFSERR_STALE_STATEID) +#define nfserr_old_stateid cpu_to_be32(NFSERR_OLD_STATEID) +#define nfserr_bad_stateid cpu_to_be32(NFSERR_BAD_STATEID) +#define nfserr_bad_seqid cpu_to_be32(NFSERR_BAD_SEQID) +#define nfserr_symlink cpu_to_be32(NFSERR_SYMLINK) +#define nfserr_not_same cpu_to_be32(NFSERR_NOT_SAME) +#define nfserr_restorefh cpu_to_be32(NFSERR_RESTOREFH) +#define nfserr_attrnotsupp cpu_to_be32(NFSERR_ATTRNOTSUPP) +#define nfserr_bad_xdr cpu_to_be32(NFSERR_BAD_XDR) +#define nfserr_openmode cpu_to_be32(NFSERR_OPENMODE) +#define nfserr_locks_held cpu_to_be32(NFSERR_LOCKS_HELD) +#define nfserr_op_illegal cpu_to_be32(NFSERR_OP_ILLEGAL) +#define nfserr_grace cpu_to_be32(NFSERR_GRACE) +#define nfserr_no_grace cpu_to_be32(NFSERR_NO_GRACE) +#define nfserr_reclaim_bad cpu_to_be32(NFSERR_RECLAIM_BAD) +#define nfserr_badname cpu_to_be32(NFSERR_BADNAME) +#define nfserr_cb_path_down cpu_to_be32(NFSERR_CB_PATH_DOWN) +#define nfserr_locked cpu_to_be32(NFSERR_LOCKED) +#define nfserr_wrongsec cpu_to_be32(NFSERR_WRONGSEC) +#define nfserr_replay_me cpu_to_be32(NFSERR_REPLAY_ME) /* error codes for internal use */ /* if a request fails due to kmalloc failure, it gets dropped. * Client should resend eventually */ -#define nfserr_dropit __constant_htonl(30000) +#define nfserr_dropit cpu_to_be32(30000) /* end-of-file indicator in readdir */ -#define nfserr_eof __constant_htonl(30001) +#define nfserr_eof cpu_to_be32(30001) /* Check for dir entries '.' and '..' */ #define isdotent(n, l) (l < 3 && n[0] == '.' && (l == 1 || n[1] == '.')) diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 49e1eb45446..d8910b68e1b 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -69,27 +69,27 @@ struct xdr_buf { * pre-xdr'ed macros. */ -#define xdr_zero __constant_htonl(0) -#define xdr_one __constant_htonl(1) -#define xdr_two __constant_htonl(2) - -#define rpc_success __constant_htonl(RPC_SUCCESS) -#define rpc_prog_unavail __constant_htonl(RPC_PROG_UNAVAIL) -#define rpc_prog_mismatch __constant_htonl(RPC_PROG_MISMATCH) -#define rpc_proc_unavail __constant_htonl(RPC_PROC_UNAVAIL) -#define rpc_garbage_args __constant_htonl(RPC_GARBAGE_ARGS) -#define rpc_system_err __constant_htonl(RPC_SYSTEM_ERR) -#define rpc_drop_reply __constant_htonl(RPC_DROP_REPLY) - -#define rpc_auth_ok __constant_htonl(RPC_AUTH_OK) -#define rpc_autherr_badcred __constant_htonl(RPC_AUTH_BADCRED) -#define rpc_autherr_rejectedcred __constant_htonl(RPC_AUTH_REJECTEDCRED) -#define rpc_autherr_badverf __constant_htonl(RPC_AUTH_BADVERF) -#define rpc_autherr_rejectedverf __constant_htonl(RPC_AUTH_REJECTEDVERF) -#define rpc_autherr_tooweak __constant_htonl(RPC_AUTH_TOOWEAK) -#define rpcsec_gsserr_credproblem __constant_htonl(RPCSEC_GSS_CREDPROBLEM) -#define rpcsec_gsserr_ctxproblem __constant_htonl(RPCSEC_GSS_CTXPROBLEM) -#define rpc_autherr_oldseqnum __constant_htonl(101) +#define xdr_zero cpu_to_be32(0) +#define xdr_one cpu_to_be32(1) +#define xdr_two cpu_to_be32(2) + +#define rpc_success cpu_to_be32(RPC_SUCCESS) +#define rpc_prog_unavail cpu_to_be32(RPC_PROG_UNAVAIL) +#define rpc_prog_mismatch cpu_to_be32(RPC_PROG_MISMATCH) +#define rpc_proc_unavail cpu_to_be32(RPC_PROC_UNAVAIL) +#define rpc_garbage_args cpu_to_be32(RPC_GARBAGE_ARGS) +#define rpc_system_err cpu_to_be32(RPC_SYSTEM_ERR) +#define rpc_drop_reply cpu_to_be32(RPC_DROP_REPLY) + +#define rpc_auth_ok cpu_to_be32(RPC_AUTH_OK) +#define rpc_autherr_badcred cpu_to_be32(RPC_AUTH_BADCRED) +#define rpc_autherr_rejectedcred cpu_to_be32(RPC_AUTH_REJECTEDCRED) +#define rpc_autherr_badverf cpu_to_be32(RPC_AUTH_BADVERF) +#define rpc_autherr_rejectedverf cpu_to_be32(RPC_AUTH_REJECTEDVERF) +#define rpc_autherr_tooweak cpu_to_be32(RPC_AUTH_TOOWEAK) +#define rpcsec_gsserr_credproblem cpu_to_be32(RPCSEC_GSS_CREDPROBLEM) +#define rpcsec_gsserr_ctxproblem cpu_to_be32(RPCSEC_GSS_CTXPROBLEM) +#define rpc_autherr_oldseqnum cpu_to_be32(101) /* * Miscellaneous XDR helper functions -- cgit v1.2.3 From 203a8c8e66278a5936a230edaac29017e50c88fb Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Sat, 21 Feb 2009 13:29:14 -0800 Subject: nfsd4: separate delegreturn case from preprocess_stateid_op Delegreturn is enough a special case for preprocess_stateid_op to warrant just open-coding it in delegreturn. There should be no change in behavior here; we're just reshuffling code. Thanks to Yang Hongyang for catching a critical typo. Reviewed-by: Yang Hongyang Signed-off-by: J. Bruce Fields --- include/linux/nfsd/state.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfsd/state.h b/include/linux/nfsd/state.h index 1130d534bb6..c9311a1e2e1 100644 --- a/include/linux/nfsd/state.h +++ b/include/linux/nfsd/state.h @@ -263,7 +263,6 @@ struct nfs4_stateid { #define RD_STATE 0x00000010 #define WR_STATE 0x00000020 #define CLOSE_STATE 0x00000040 -#define DELEG_RET 0x00000080 #define seqid_mutating_err(err) \ (((err) != nfserr_stale_clientid) && \ -- cgit v1.2.3 From 6150ef0dc7f734366d297e2eb5697ae458a1ea19 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Sat, 21 Feb 2009 13:36:16 -0800 Subject: nfsd4: remove unused CHECK_FH flag All users now pass this, so it's meaningless. Signed-off-by: J. Bruce Fields --- include/linux/nfsd/state.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfsd/state.h b/include/linux/nfsd/state.h index c9311a1e2e1..503b6bb53a5 100644 --- a/include/linux/nfsd/state.h +++ b/include/linux/nfsd/state.h @@ -256,7 +256,6 @@ struct nfs4_stateid { }; /* flags for preprocess_seqid_op() */ -#define CHECK_FH 0x00000001 #define CONFIRM 0x00000002 #define OPEN_STATE 0x00000004 #define LOCK_STATE 0x00000008 -- cgit v1.2.3 From 8b671b80707e4fc76adfe4387df07b3be1007c1e Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Sun, 22 Feb 2009 14:51:34 -0800 Subject: nfsd4: remove use of mutex for file_hashtable As part of reducing the scope of the client_mutex, and in order to remove the need for mutexes from the callback code (so that callbacks can be done as asynchronous rpc calls), move manipulations of the file_hashtable under the recall_lock. Update the relevant comments while we're here. Signed-off-by: J. Bruce Fields Cc: Alexandros Batsakis Reviewed-by: Benny Halevy --- include/linux/nfsd/state.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfsd/state.h b/include/linux/nfsd/state.h index 503b6bb53a5..a6e4a00fa39 100644 --- a/include/linux/nfsd/state.h +++ b/include/linux/nfsd/state.h @@ -214,7 +214,7 @@ struct nfs4_stateowner { * share_acces, share_deny on the file. */ struct nfs4_file { - struct kref fi_ref; + atomic_t fi_ref; struct list_head fi_hash; /* hash by "struct inode *" */ struct list_head fi_stateids; struct list_head fi_delegations; -- cgit v1.2.3 From 31dec2538e45e9fff2007ea1f4c6bae9f78db724 Mon Sep 17 00:00:00 2001 From: David Shaw Date: Thu, 5 Mar 2009 20:16:14 -0500 Subject: Short write in nfsd becomes a full write to the client If a filesystem being written to via NFS returns a short write count (as opposed to an error) to nfsd, nfsd treats that as a success for the entire write, rather than the short count that actually succeeded. For example, given a 8192 byte write, if the underlying filesystem only writes 4096 bytes, nfsd will ack back to the nfs client that all 8192 bytes were written. The nfs client does have retry logic for short writes, but this is never called as the client is told the complete write succeeded. There are probably other ways it could happen, but in my case it happened with a fuse (filesystem in userspace) filesystem which can rather easily have a partial write. Here is a patch to properly return the short write count to the client. Signed-off-by: David Shaw Signed-off-by: J. Bruce Fields --- include/linux/nfsd/nfsd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfsd/nfsd.h b/include/linux/nfsd/nfsd.h index 16f7b403d9c..54beda12d26 100644 --- a/include/linux/nfsd/nfsd.h +++ b/include/linux/nfsd/nfsd.h @@ -105,7 +105,7 @@ void nfsd_close(struct file *); __be32 nfsd_read(struct svc_rqst *, struct svc_fh *, struct file *, loff_t, struct kvec *, int, unsigned long *); __be32 nfsd_write(struct svc_rqst *, struct svc_fh *,struct file *, - loff_t, struct kvec *,int, unsigned long, int *); + loff_t, struct kvec *,int, unsigned long *, int *); __be32 nfsd_readlink(struct svc_rqst *, struct svc_fh *, char *, int *); __be32 nfsd_symlink(struct svc_rqst *, struct svc_fh *, -- cgit v1.2.3 From 59a252ff8c0f2fa32c896f69d56ae33e641ce7ad Mon Sep 17 00:00:00 2001 From: Greg Banks Date: Tue, 13 Jan 2009 21:26:35 +1100 Subject: knfsd: avoid overloading the CPU scheduler with enormous load averages Avoid overloading the CPU scheduler with enormous load averages when handling high call-rate NFS loads. When the knfsd bottom half is made aware of an incoming call by the socket layer, it tries to choose an nfsd thread and wake it up. As long as there are idle threads, one will be woken up. If there are lot of nfsd threads (a sensible configuration when the server is disk-bound or is running an HSM), there will be many more nfsd threads than CPUs to run them. Under a high call-rate low service-time workload, the result is that almost every nfsd is runnable, but only a handful are actually able to run. This situation causes two significant problems: 1. The CPU scheduler takes over 10% of each CPU, which is robbing the nfsd threads of valuable CPU time. 2. At a high enough load, the nfsd threads starve userspace threads of CPU time, to the point where daemons like portmap and rpc.mountd do not schedule for tens of seconds at a time. Clients attempting to mount an NFS filesystem timeout at the very first step (opening a TCP connection to portmap) because portmap cannot wake up from select() and call accept() in time. Disclaimer: these effects were observed on a SLES9 kernel, modern kernels' schedulers may behave more gracefully. The solution is simple: keep in each svc_pool a counter of the number of threads which have been woken but have not yet run, and do not wake any more if that count reaches an arbitrary small threshold. Testing was on a 4 CPU 4 NIC Altix using 4 IRIX clients, each with 16 synthetic client threads simulating an rsync (i.e. recursive directory listing) workload reading from an i386 RH9 install image (161480 regular files in 10841 directories) on the server. That tree is small enough to fill in the server's RAM so no disk traffic was involved. This setup gives a sustained call rate in excess of 60000 calls/sec before being CPU-bound on the server. The server was running 128 nfsds. Profiling showed schedule() taking 6.7% of every CPU, and __wake_up() taking 5.2%. This patch drops those contributions to 3.0% and 2.2%. Load average was over 120 before the patch, and 20.9 after. This patch is a forward-ported version of knfsd-avoid-nfsd-overload which has been shipping in the SGI "Enhanced NFS" product since 2006. It has been posted before: http://article.gmane.org/gmane.linux.nfs/10374 Signed-off-by: Greg Banks Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 3435d24bfe5..39ec186a492 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -41,6 +41,7 @@ struct svc_pool { struct list_head sp_sockets; /* pending sockets */ unsigned int sp_nrthreads; /* # of threads in pool */ struct list_head sp_all_threads; /* all server threads */ + int sp_nwaking; /* number of threads woken but not yet active */ } ____cacheline_aligned_in_smp; /* @@ -264,6 +265,7 @@ struct svc_rqst { * cache pages */ wait_queue_head_t rq_wait; /* synchronization */ struct task_struct *rq_task; /* service thread */ + int rq_waking; /* 1 if thread is being woken */ }; /* -- cgit v1.2.3 From 03cf6c9f49a8fea953d38648d016e3f46e814991 Mon Sep 17 00:00:00 2001 From: Greg Banks Date: Tue, 13 Jan 2009 21:26:36 +1100 Subject: knfsd: add file to export stats about nfsd pools Add /proc/fs/nfsd/pool_stats to export to userspace various statistics about the operation of rpc server thread pools. This patch is based on a forward-ported version of knfsd-add-pool-thread-stats which has been shipping in the SGI "Enhanced NFS" product since 2006 and which was previously posted: http://article.gmane.org/gmane.linux.nfs/10375 It has also been updated thus: * moved EXPORT_SYMBOL() to near the function it exports * made the new struct struct seq_operations const * used SEQ_START_TOKEN instead of ((void *)1) * merged fix from SGI PV 990526 "sunrpc: use dprintk instead of printk in svc_pool_stats_*()" by Harshula Jayasuriya. * merged fix from SGI PV 964001 "Crash reading pool_stats before nfsds are started". Signed-off-by: Greg Banks Signed-off-by: Harshula Jayasuriya Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 39ec186a492..9f9f699dd46 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -24,6 +24,15 @@ */ typedef int (*svc_thread_fn)(void *); +/* statistics for svc_pool structures */ +struct svc_pool_stats { + unsigned long packets; + unsigned long sockets_queued; + unsigned long threads_woken; + unsigned long overloads_avoided; + unsigned long threads_timedout; +}; + /* * * RPC service thread pool. @@ -42,6 +51,7 @@ struct svc_pool { unsigned int sp_nrthreads; /* # of threads in pool */ struct list_head sp_all_threads; /* all server threads */ int sp_nwaking; /* number of threads woken but not yet active */ + struct svc_pool_stats sp_stats; /* statistics on pool operation */ } ____cacheline_aligned_in_smp; /* @@ -396,6 +406,7 @@ struct svc_serv * svc_create_pooled(struct svc_program *, unsigned int, sa_family_t, void (*shutdown)(struct svc_serv *), svc_thread_fn, struct module *); int svc_set_num_threads(struct svc_serv *, struct svc_pool *, int); +int svc_pool_stats_open(struct svc_serv *serv, struct file *file); void svc_destroy(struct svc_serv *); int svc_process(struct svc_rqst *); int svc_register(const struct svc_serv *, const unsigned short, -- cgit v1.2.3 From 2795e53b4ed5d1f49d2283f416c922f55ec7d461 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 12 Mar 2009 12:07:14 -0400 Subject: SUNRPC: Clean up static inline functions in svc_xprt.h Clean up: Enable the use of const arguments in higher level svc_ APIs by adding const to the arguments of the helper functions in svc_xprt.h Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc_xprt.h | 46 +++++++++++++++++++++++------------------ 1 file changed, 26 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index 0127daca435..959b931b605 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -88,29 +88,32 @@ static inline void svc_xprt_get(struct svc_xprt *xprt) kref_get(&xprt->xpt_ref); } static inline void svc_xprt_set_local(struct svc_xprt *xprt, - struct sockaddr *sa, int salen) + const struct sockaddr *sa, + const size_t salen) { memcpy(&xprt->xpt_local, sa, salen); xprt->xpt_locallen = salen; } static inline void svc_xprt_set_remote(struct svc_xprt *xprt, - struct sockaddr *sa, int salen) + const struct sockaddr *sa, + const size_t salen) { memcpy(&xprt->xpt_remote, sa, salen); xprt->xpt_remotelen = salen; } -static inline unsigned short svc_addr_port(struct sockaddr *sa) +static inline unsigned short svc_addr_port(const struct sockaddr *sa) { - unsigned short ret = 0; + const struct sockaddr_in *sin = (const struct sockaddr_in *)sa; + const struct sockaddr_in6 *sin6 = (const struct sockaddr_in6 *)sa; + switch (sa->sa_family) { case AF_INET: - ret = ntohs(((struct sockaddr_in *)sa)->sin_port); - break; + return ntohs(sin->sin_port); case AF_INET6: - ret = ntohs(((struct sockaddr_in6 *)sa)->sin6_port); - break; + return ntohs(sin6->sin6_port); } - return ret; + + return 0; } static inline size_t svc_addr_len(struct sockaddr *sa) @@ -124,36 +127,39 @@ static inline size_t svc_addr_len(struct sockaddr *sa) return -EAFNOSUPPORT; } -static inline unsigned short svc_xprt_local_port(struct svc_xprt *xprt) +static inline unsigned short svc_xprt_local_port(const struct svc_xprt *xprt) { - return svc_addr_port((struct sockaddr *)&xprt->xpt_local); + return svc_addr_port((const struct sockaddr *)&xprt->xpt_local); } -static inline unsigned short svc_xprt_remote_port(struct svc_xprt *xprt) +static inline unsigned short svc_xprt_remote_port(const struct svc_xprt *xprt) { - return svc_addr_port((struct sockaddr *)&xprt->xpt_remote); + return svc_addr_port((const struct sockaddr *)&xprt->xpt_remote); } -static inline char *__svc_print_addr(struct sockaddr *addr, - char *buf, size_t len) +static inline char *__svc_print_addr(const struct sockaddr *addr, + char *buf, const size_t len) { + const struct sockaddr_in *sin = (const struct sockaddr_in *)addr; + const struct sockaddr_in6 *sin6 = (const struct sockaddr_in6 *)addr; + switch (addr->sa_family) { case AF_INET: - snprintf(buf, len, "%pI4, port=%u", - &((struct sockaddr_in *)addr)->sin_addr, - ntohs(((struct sockaddr_in *) addr)->sin_port)); + snprintf(buf, len, "%pI4, port=%u", &sin->sin_addr, + ntohs(sin->sin_port)); break; case AF_INET6: snprintf(buf, len, "%pI6, port=%u", - &((struct sockaddr_in6 *)addr)->sin6_addr, - ntohs(((struct sockaddr_in6 *) addr)->sin6_port)); + &sin6->sin6_addr, + ntohs(sin6->sin6_port)); break; default: snprintf(buf, len, "unknown address type: %d", addr->sa_family); break; } + return buf; } #endif /* SUNRPC_SVC_XPRT_H */ -- cgit v1.2.3 From 27bf91d6a0d5a9c7224e8687754249bba67dd4cf Mon Sep 17 00:00:00 2001 From: Yevgeny Petrilin Date: Wed, 18 Mar 2009 19:45:11 -0700 Subject: mlx4_core: Add link type autosensing When a port's link is down (except to driver restart) and the port is configured for auto sensing, we try to sense port link type (Ethernet or InfiniBand) in order to determine how to initialize the port. If the port type needs to be changed, all mlx4 for the device interfaces are unregistered and then registered again with the new port types. Sensing is done with intervals of 3 seconds. Signed-off-by: Yevgeny Petrilin Signed-off-by: Roland Dreier --- include/linux/mlx4/cmd.h | 1 + include/linux/mlx4/device.h | 6 ++++-- 2 files changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h index cf9c679ab38..0f82293a82e 100644 --- a/include/linux/mlx4/cmd.h +++ b/include/linux/mlx4/cmd.h @@ -55,6 +55,7 @@ enum { MLX4_CMD_CLOSE_PORT = 0xa, MLX4_CMD_QUERY_HCA = 0xb, MLX4_CMD_QUERY_PORT = 0x43, + MLX4_CMD_SENSE_PORT = 0x4d, MLX4_CMD_SET_PORT = 0xc, MLX4_CMD_ACCESS_DDR = 0x2e, MLX4_CMD_MAP_ICM = 0xffa, diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 8f659cc2996..3aff8a6a389 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -155,8 +155,9 @@ enum mlx4_qp_region { }; enum mlx4_port_type { - MLX4_PORT_TYPE_IB = 1 << 0, - MLX4_PORT_TYPE_ETH = 1 << 1, + MLX4_PORT_TYPE_IB = 1, + MLX4_PORT_TYPE_ETH = 2, + MLX4_PORT_TYPE_AUTO = 3 }; enum mlx4_special_vlan_idx { @@ -237,6 +238,7 @@ struct mlx4_caps { enum mlx4_port_type port_type[MLX4_MAX_PORTS + 1]; u8 supported_type[MLX4_MAX_PORTS + 1]; u32 port_mask; + enum mlx4_port_type possible_type[MLX4_MAX_PORTS + 1]; }; struct mlx4_buf_list { -- cgit v1.2.3 From 7d1e8255cf959fba7ee2317550dfde39f0b936ae Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 11 Mar 2009 14:38:03 -0400 Subject: SUNRPC: Add the equivalent of the linger and linger2 timeouts to RPC sockets This fixes a regression against FreeBSD servers as reported by Tomas Kasparek. Apparently when using RPC over a TCP socket, the FreeBSD servers don't ever react to the client closing the socket, and so commit e06799f958bf7f9f8fae15f0c6f519953fb0257c (SUNRPC: Use shutdown() instead of close() when disconnecting a TCP socket) causes the setup to hang forever whenever the client attempts to close and then reconnect. We break the deadlock by adding a 'linger2' style timeout to the socket, after which, the client will abort the connection using a TCP 'RST'. The default timeout is set to 15 seconds. A subsequent patch will put it under user control by means of a systctl. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 2b0d960603b..1758d9f5b5c 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -260,6 +260,7 @@ void xprt_conditional_disconnect(struct rpc_xprt *xprt, unsigned int cookie); #define XPRT_BOUND (4) #define XPRT_BINDING (5) #define XPRT_CLOSING (6) +#define XPRT_CONNECTION_ABORT (7) static inline void xprt_set_connected(struct rpc_xprt *xprt) { -- cgit v1.2.3 From 7fe5c398fc2186ed586db11106a6692d871d0d58 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 19 Mar 2009 15:35:50 -0400 Subject: NFS: Optimise NFS close() Close-to-open cache consistency rules really only require us to flush out writes on calls to close(), and require us to revalidate attributes on the very last close of the file. Currently we appear to be doing a lot of extra attribute revalidation and cache flushes. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 0691b9c188d..9708e78a4d4 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -868,6 +868,7 @@ struct nfs_rpc_ops { int (*lock)(struct file *, int, struct file_lock *); int (*lock_check_bounds)(const struct file_lock *); void (*clear_acl_cache)(struct inode *); + void (*close_context)(struct nfs_open_context *ctx, int); }; /* -- cgit v1.2.3 From 1bf83e558cb29d163f4bc6decbc3800ecf4db195 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 13 Jan 2009 14:38:34 +0100 Subject: PCI: PCIe portdrv: Use driver data to simplify code PCI Express port driver extension, as defined by struct pcie_port_device_ext in portdrv.h, is allocated and initialized, but never used (it also is never freed). Extend it to hold the PCI Express port type as well as the port interrupt mode, change its name and use it to simplify the code in portdrv_core.c . Additionally, remove the redundant interrupt_mode member of struct pcie_device defined in include/linux/pcieport_if.h . Signed-off-by: Rafael J. Wysocki Signed-off-by: Jesse Barnes --- include/linux/pcieport_if.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pcieport_if.h b/include/linux/pcieport_if.h index 6cd91e3f982..194409af103 100644 --- a/include/linux/pcieport_if.h +++ b/include/linux/pcieport_if.h @@ -36,7 +36,6 @@ struct pcie_port_service_id { struct pcie_device { int irq; /* Service IRQ/MSI/MSI-X Vector */ - int interrupt_mode; /* [0:INTx | 1:MSI | 2:MSI-X] */ struct pcie_port_service_id id; /* Service ID */ struct pci_dev *port; /* Root/Upstream/Downstream Port */ void *priv_data; /* Service Private Data */ -- cgit v1.2.3 From 90e9cd50f7feeddc911325c8a8c1b7e1fccc6599 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 13 Jan 2009 14:39:39 +0100 Subject: PCI: PCIe portdrv: Aviod using service devices with wrong interrupts The PCI Express port driver should not attempt to register service devices that require the ability to generate interrupts if generating interrupts is not possible. Namely, if the port has no interrupt pin configured and we cannot set up MSI or MSI-X for it, there is no way it can generate interrupts and in such a case the port services that rely on interrupts (PME, PCIe HP, AER) should not be enabled for it. Signed-off-by: Rafael J. Wysocki Signed-off-by: Jesse Barnes --- include/linux/pcieport_if.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pcieport_if.h b/include/linux/pcieport_if.h index 194409af103..8e1ae1fd92f 100644 --- a/include/linux/pcieport_if.h +++ b/include/linux/pcieport_if.h @@ -22,6 +22,7 @@ #define PCIE_PORT_SERVICE_VC 8 /* Virtual Channel */ /* Root/Upstream/Downstream Port's Interrupt Mode */ +#define PCIE_PORT_NO_IRQ (-1) #define PCIE_PORT_INTx_MODE 0 #define PCIE_PORT_MSI_MODE 1 #define PCIE_PORT_MSIX_MODE 2 -- cgit v1.2.3 From 0516c8bcd25293f438573101c439ce25a18916ad Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 13 Jan 2009 14:44:19 +0100 Subject: PCI: PCIe portdrv: Simplily probe callback of service drivers The second argument of the ->probe() callback in struct pcie_port_service_driver is unnecessary and never used. Remove it. Signed-off-by: Rafael J. Wysocki Signed-off-by: Jesse Barnes --- include/linux/pcieport_if.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pcieport_if.h b/include/linux/pcieport_if.h index 8e1ae1fd92f..59e90b8a783 100644 --- a/include/linux/pcieport_if.h +++ b/include/linux/pcieport_if.h @@ -56,8 +56,7 @@ static inline void* get_service_data(struct pcie_device *dev) struct pcie_port_service_driver { const char *name; - int (*probe) (struct pcie_device *dev, - const struct pcie_port_service_id *id); + int (*probe) (struct pcie_device *dev); void (*remove) (struct pcie_device *dev); int (*suspend) (struct pcie_device *dev, pm_message_t state); int (*resume) (struct pcie_device *dev); -- cgit v1.2.3 From 22106368c999246c414610dcaacd485e741605b1 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 13 Jan 2009 14:46:46 +0100 Subject: PCI: PCIe portdrv: Remove struct pcie_port_service_id The PCI Express port driver uses 'struct pcie_port_service_id' for matching port service devices and drivers, but this structure contains fields that duplicate information from the port device itself (vendor, device, subvendor, subdevice) and fields that are not used by any existing port service driver (class, class_mask, drvier_data). Also, both existing port service drivers (AER and PCIe HP) don't even use the vendor and device fields for device matching. Therefore 'struct pcie_port_service_id' can be removed altogether and the only useful members of it (port_type, service) can be introduced directly into the port service device and port service driver structures. That simplifies the code quite a bit and reduces its size. Signed-off-by: Rafael J. Wysocki Signed-off-by: Jesse Barnes --- include/linux/pcieport_if.h | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pcieport_if.h b/include/linux/pcieport_if.h index 59e90b8a783..a3832079508 100644 --- a/include/linux/pcieport_if.h +++ b/include/linux/pcieport_if.h @@ -27,18 +27,15 @@ #define PCIE_PORT_MSI_MODE 1 #define PCIE_PORT_MSIX_MODE 2 -struct pcie_port_service_id { - __u32 vendor, device; /* Vendor and device ID or PCI_ANY_ID*/ - __u32 subvendor, subdevice; /* Subsystem ID's or PCI_ANY_ID */ - __u32 class, class_mask; /* (class,subclass,prog-if) triplet */ - __u32 port_type, service_type; /* Port Entity */ - kernel_ulong_t driver_data; +struct pcie_port_data { + int port_type; /* Type of the port */ + int port_irq_mode; /* [0:INTx | 1:MSI | 2:MSI-X] */ }; struct pcie_device { int irq; /* Service IRQ/MSI/MSI-X Vector */ - struct pcie_port_service_id id; /* Service ID */ - struct pci_dev *port; /* Root/Upstream/Downstream Port */ + struct pci_dev *port; /* Root/Upstream/Downstream Port */ + u32 service; /* Port service this device represents */ void *priv_data; /* Service Private Data */ struct device device; /* Generic Device Interface */ }; @@ -67,7 +64,9 @@ struct pcie_port_service_driver { /* Link Reset Capability - AER service driver specific */ pci_ers_result_t (*reset_link) (struct pci_dev *dev); - const struct pcie_port_service_id *id_table; + int port_type; /* Type of the port this driver can handle */ + u32 service; /* Port service this device represents */ + struct device_driver driver; }; #define to_service_driver(d) \ -- cgit v1.2.3 From a52e2e3513d4beafe8fe8699f1519b021c2d05ba Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sat, 24 Jan 2009 00:21:14 +0100 Subject: PCI/MSI: Introduce pci_msix_table_size() Introduce new function pci_msix_table_size() returning the size of the MSI-X table of given PCI device or 0 if the device doesn't support MSI-X. Signed-off-by: Rafael J. Wysocki Reviewed-by: Hidetoshi Seto Signed-off-by: Jesse Barnes --- include/linux/pci.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 7bd624bfdcf..b5d6d0e0f1c 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -799,6 +799,10 @@ static inline void pci_msi_shutdown(struct pci_dev *dev) static inline void pci_disable_msi(struct pci_dev *dev) { } +static inline int pci_msix_table_size(struct pci_dev *dev) +{ + return 0; +} static inline int pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries, int nvec) { @@ -823,6 +827,7 @@ static inline int pci_msi_enabled(void) extern int pci_enable_msi(struct pci_dev *dev); extern void pci_msi_shutdown(struct pci_dev *dev); extern void pci_disable_msi(struct pci_dev *dev); +extern int pci_msix_table_size(struct pci_dev *dev); extern int pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries, int nvec); extern void pci_msix_shutdown(struct pci_dev *dev); -- cgit v1.2.3 From b43d451385ef833e0696032aac2629da04d46c59 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sat, 24 Jan 2009 00:23:22 +0100 Subject: PCI/PCIe portdrv: Fix allocation of interrupts If MSI-X interrupt mode is used by the PCI Express port driver, too many vectors are allocated and it is not ensured that the right vectors will be used for the right services. Namely, the PCI Express specification states that both PCI Express native PME and PCI Express hotplug will always use the same MSI or MSI-X message for signalling interrupts, which implies that the same vector will be used by both of them. Also, the VC service does not use interrupts at all. Moreover, is not clear which of the vectors allocated by pci_enable_msix() in the current code will be used for PME and hotplug and which of them will be used for AER if all of these services are configured. For these reasons, rework the allocation of interrupts for PCI Express ports so that if MSI-X are enabled, the right vectors will be used for the right purposes. Signed-off-by: Rafael J. Wysocki Reviewed-by: Hidetoshi Seto Signed-off-by: Jesse Barnes --- include/linux/pcieport_if.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pcieport_if.h b/include/linux/pcieport_if.h index a3832079508..5d2afcfa6bc 100644 --- a/include/linux/pcieport_if.h +++ b/include/linux/pcieport_if.h @@ -16,10 +16,14 @@ #define PCIE_ANY_PORT 7 /* Service Type */ -#define PCIE_PORT_SERVICE_PME 1 /* Power Management Event */ -#define PCIE_PORT_SERVICE_AER 2 /* Advanced Error Reporting */ -#define PCIE_PORT_SERVICE_HP 4 /* Native Hotplug */ -#define PCIE_PORT_SERVICE_VC 8 /* Virtual Channel */ +#define PCIE_PORT_SERVICE_PME_SHIFT 0 /* Power Management Event */ +#define PCIE_PORT_SERVICE_PME (1 << PCIE_PORT_SERVICE_PME_SHIFT) +#define PCIE_PORT_SERVICE_AER_SHIFT 1 /* Advanced Error Reporting */ +#define PCIE_PORT_SERVICE_AER (1 << PCIE_PORT_SERVICE_AER_SHIFT) +#define PCIE_PORT_SERVICE_HP_SHIFT 2 /* Native Hotplug */ +#define PCIE_PORT_SERVICE_HP (1 << PCIE_PORT_SERVICE_HP_SHIFT) +#define PCIE_PORT_SERVICE_VC_SHIFT 3 /* Virtual Channel */ +#define PCIE_PORT_SERVICE_VC (1 << PCIE_PORT_SERVICE_VC_SHIFT) /* Root/Upstream/Downstream Port's Interrupt Mode */ #define PCIE_PORT_NO_IRQ (-1) -- cgit v1.2.3 From 63f10f0f6df4e4e860b790d64bebfde85b540b0a Mon Sep 17 00:00:00 2001 From: Kenji Kaneshige Date: Mon, 9 Feb 2009 15:59:29 +0900 Subject: PCI/ACPI: move _OSC code to pci_root.c Move PCI _OSC management code from drivers/pci/pci-acpi.c to drivers/acpi/pci_root.c. The benefits are - We no longer need struct osc_data and its management code (contents are moved to struct acpi_pci_root). This simplify the code, and we no longer care about kmalloc() failure. - We can make pci_acpi_osc_support() be a static function, which is called only from drivers/acpi/pci_root.c. Signed-off-by: Kenji Kaneshige Reviewed-by: Andrew Patterson Tested-by: Andrew Patterson Acked-by: Alex Chiang Signed-off-by: Jesse Barnes --- include/linux/pci-acpi.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci-acpi.h b/include/linux/pci-acpi.h index 042c166f65d..65cb103b21d 100644 --- a/include/linux/pci-acpi.h +++ b/include/linux/pci-acpi.h @@ -50,7 +50,6 @@ #ifdef CONFIG_ACPI extern acpi_status pci_osc_control_set(acpi_handle handle, u32 flags); -int pci_acpi_osc_support(acpi_handle handle, u32 flags); static inline acpi_handle acpi_find_root_bridge_handle(struct pci_dev *pdev) { /* Find root host bridge */ -- cgit v1.2.3 From 9f5404d8ea90bfa4d58a3936e5a3d0d28cecf60f Mon Sep 17 00:00:00 2001 From: Kenji Kaneshige Date: Mon, 9 Feb 2009 16:00:04 +0900 Subject: PCI/ACPI: rename pci_osc_control_set() - Rename pci_osc_control_set() to acpi_pci_osc_control_set() according to the other API names in drivers/acpi/pci_root.c. - Move _OSC related definitions to include/linux/acpi.h because _OSC related API is implemented in drivers/acpi/pci_root.c now. Signed-off-by: Kenji Kaneshige Reviewed-by: Andrew Patterson Tested-by: Andrew Patterson Signed-off-by: Jesse Barnes --- include/linux/acpi.h | 34 ++++++++++++++++++++++++++++++++++ include/linux/pci-acpi.h | 45 --------------------------------------------- 2 files changed, 34 insertions(+), 45 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 6fce2fc2d12..2a3b189e3e2 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -256,6 +256,40 @@ void __init acpi_no_s4_hw_signature(void); void __init acpi_old_suspend_ordering(void); void __init acpi_s4_no_nvs(void); #endif /* CONFIG_PM_SLEEP */ + +#define OSC_QUERY_TYPE 0 +#define OSC_SUPPORT_TYPE 1 +#define OSC_CONTROL_TYPE 2 +#define OSC_SUPPORT_MASKS 0x1f + +/* _OSC DW0 Definition */ +#define OSC_QUERY_ENABLE 1 +#define OSC_REQUEST_ERROR 2 +#define OSC_INVALID_UUID_ERROR 4 +#define OSC_INVALID_REVISION_ERROR 8 +#define OSC_CAPABILITIES_MASK_ERROR 16 + +/* _OSC DW1 Definition (OS Support Fields) */ +#define OSC_EXT_PCI_CONFIG_SUPPORT 1 +#define OSC_ACTIVE_STATE_PWR_SUPPORT 2 +#define OSC_CLOCK_PWR_CAPABILITY_SUPPORT 4 +#define OSC_PCI_SEGMENT_GROUPS_SUPPORT 8 +#define OSC_MSI_SUPPORT 16 + +/* _OSC DW1 Definition (OS Control Fields) */ +#define OSC_PCI_EXPRESS_NATIVE_HP_CONTROL 1 +#define OSC_SHPC_NATIVE_HP_CONTROL 2 +#define OSC_PCI_EXPRESS_PME_CONTROL 4 +#define OSC_PCI_EXPRESS_AER_CONTROL 8 +#define OSC_PCI_EXPRESS_CAP_STRUCTURE_CONTROL 16 + +#define OSC_CONTROL_MASKS (OSC_PCI_EXPRESS_NATIVE_HP_CONTROL | \ + OSC_SHPC_NATIVE_HP_CONTROL | \ + OSC_PCI_EXPRESS_PME_CONTROL | \ + OSC_PCI_EXPRESS_AER_CONTROL | \ + OSC_PCI_EXPRESS_CAP_STRUCTURE_CONTROL) + +extern acpi_status acpi_pci_osc_control_set(acpi_handle handle, u32 flags); #else /* CONFIG_ACPI */ static inline int early_acpi_boot_init(void) diff --git a/include/linux/pci-acpi.h b/include/linux/pci-acpi.h index 65cb103b21d..20480b9f10c 100644 --- a/include/linux/pci-acpi.h +++ b/include/linux/pci-acpi.h @@ -10,46 +10,7 @@ #include -#define OSC_QUERY_TYPE 0 -#define OSC_SUPPORT_TYPE 1 -#define OSC_CONTROL_TYPE 2 -#define OSC_SUPPORT_MASKS 0x1f - -/* - * _OSC DW0 Definition - */ -#define OSC_QUERY_ENABLE 1 -#define OSC_REQUEST_ERROR 2 -#define OSC_INVALID_UUID_ERROR 4 -#define OSC_INVALID_REVISION_ERROR 8 -#define OSC_CAPABILITIES_MASK_ERROR 16 - -/* - * _OSC DW1 Definition (OS Support Fields) - */ -#define OSC_EXT_PCI_CONFIG_SUPPORT 1 -#define OSC_ACTIVE_STATE_PWR_SUPPORT 2 -#define OSC_CLOCK_PWR_CAPABILITY_SUPPORT 4 -#define OSC_PCI_SEGMENT_GROUPS_SUPPORT 8 -#define OSC_MSI_SUPPORT 16 - -/* - * _OSC DW1 Definition (OS Control Fields) - */ -#define OSC_PCI_EXPRESS_NATIVE_HP_CONTROL 1 -#define OSC_SHPC_NATIVE_HP_CONTROL 2 -#define OSC_PCI_EXPRESS_PME_CONTROL 4 -#define OSC_PCI_EXPRESS_AER_CONTROL 8 -#define OSC_PCI_EXPRESS_CAP_STRUCTURE_CONTROL 16 - -#define OSC_CONTROL_MASKS (OSC_PCI_EXPRESS_NATIVE_HP_CONTROL | \ - OSC_SHPC_NATIVE_HP_CONTROL | \ - OSC_PCI_EXPRESS_PME_CONTROL | \ - OSC_PCI_EXPRESS_AER_CONTROL | \ - OSC_PCI_EXPRESS_CAP_STRUCTURE_CONTROL) - #ifdef CONFIG_ACPI -extern acpi_status pci_osc_control_set(acpi_handle handle, u32 flags); static inline acpi_handle acpi_find_root_bridge_handle(struct pci_dev *pdev) { /* Find root host bridge */ @@ -69,12 +30,6 @@ static inline acpi_handle acpi_pci_get_bridge_handle(struct pci_bus *pbus) return acpi_get_pci_rootbridge_handle(seg, busnr); } #else -#if !defined(AE_ERROR) -typedef u32 acpi_status; -#define AE_ERROR (acpi_status) (0x0001) -#endif -static inline acpi_status pci_osc_control_set(acpi_handle handle, u32 flags) -{return AE_ERROR;} static inline acpi_handle acpi_find_root_bridge_handle(struct pci_dev *pdev) { return NULL; } #endif -- cgit v1.2.3 From c48f1670f42b71f39f4a3bfba01ffb691cc9206c Mon Sep 17 00:00:00 2001 From: "akpm@linux-foundation.org" Date: Tue, 3 Feb 2009 15:45:26 -0800 Subject: PCI: constify pci_bus_add_devices() drivers/pci/hotplug/fakephp.c:283: warning: passing argument 1 of 'pci_bus_add_devices' discards qualifiers from pointer target type Signed-off-by: Andrew Morton Signed-off-by: Jesse Barnes --- include/linux/pci.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index b5d6d0e0f1c..a1af2fe0063 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -528,7 +528,7 @@ void pcibios_update_irq(struct pci_dev *, int irq); /* Generic PCI functions used internally */ extern struct pci_bus *pci_find_bus(int domain, int busnr); -void pci_bus_add_devices(struct pci_bus *bus); +void pci_bus_add_devices(const struct pci_bus *bus); struct pci_bus *pci_scan_bus_parented(struct device *parent, int bus, struct pci_ops *ops, void *sysdata); static inline struct pci_bus * __devinit pci_scan_bus(int bus, struct pci_ops *ops, -- cgit v1.2.3 From ea7415512a07add2b09c070c9a5d1950833cf9b3 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Wed, 18 Feb 2009 10:44:29 -0800 Subject: PCI: constify pci_bus_assign_resources() drivers/pci/hotplug/fakephp.c: In function 'pci_rescan_bus': drivers/pci/hotplug/fakephp.c:271: warning: passing argument 1 of 'pci_bus_assign_resources' discards qualifiers from pointer target type Signed-off-by: Andrew Morton Signed-off-by: Jesse Barnes --- include/linux/pci.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index a1af2fe0063..7baf2a5db12 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -708,7 +708,7 @@ ssize_t pci_write_vpd(struct pci_dev *dev, loff_t pos, size_t count, const void int pci_vpd_truncate(struct pci_dev *dev, size_t size); /* Helper functions for low-level code (drivers/pci/setup-[bus,res].c) */ -void pci_bus_assign_resources(struct pci_bus *bus); +void pci_bus_assign_resources(const struct pci_bus *bus); void pci_bus_size_bridges(struct pci_bus *bus); int pci_claim_resource(struct pci_dev *, int); void pci_assign_unassigned_resources(void); -- cgit v1.2.3 From 2e1ab634bf013792d8803ec57c7a428a76f50028 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Thu, 19 Mar 2009 23:49:41 -0700 Subject: rtnetlink: add new value for DHCP added routes To improve manageability, it would be good to be able to disambiguate routes added by administrator from those added by DHCP client. The only necessary kernel change is to add value to rtnetlink include file so iproute2 utility can use it. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 35a07c830f7..ba3254ecf7f 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -217,6 +217,7 @@ enum #define RTPROT_DNROUTED 13 /* DECnet routing daemon */ #define RTPROT_XORP 14 /* XORP */ #define RTPROT_NTK 15 /* Netsukuku */ +#define RTPROT_DHCP 16 /* DHCP client */ /* rtm_scope -- cgit v1.2.3 From 5e140dfc1fe87eae27846f193086724806b33c7d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 20 Mar 2009 01:33:32 -0700 Subject: net: reorder struct Qdisc for better SMP performance dev_queue_xmit() needs to dirty fields "state", "q", "bstats" and "qstats" On x86_64 arch, they currently span three cache lines, involving more cache line ping pongs than necessary, making longer holding of queue spinlock. We can reduce this to one cache line, by grouping all read-mostly fields at the beginning of structure. (Or should I say, all highly modified fields at the end :) ) Before patch : offsetof(struct Qdisc, state)=0x38 offsetof(struct Qdisc, q)=0x48 offsetof(struct Qdisc, bstats)=0x80 offsetof(struct Qdisc, qstats)=0x90 sizeof(struct Qdisc)=0xc8 After patch : offsetof(struct Qdisc, state)=0x80 offsetof(struct Qdisc, q)=0x88 offsetof(struct Qdisc, bstats)=0xa0 offsetof(struct Qdisc, qstats)=0xac sizeof(struct Qdisc)=0xc0 Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/gen_stats.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gen_stats.h b/include/linux/gen_stats.h index 13f4e74609a..0ffa41df0ee 100644 --- a/include/linux/gen_stats.h +++ b/include/linux/gen_stats.h @@ -22,7 +22,7 @@ struct gnet_stats_basic { __u64 bytes; __u32 packets; -}; +} __attribute__ ((packed)); /** * struct gnet_stats_rate_est - rate estimator -- cgit v1.2.3 From a4b6d516a6079c6ba8dc97d185371439035a35d0 Mon Sep 17 00:00:00 2001 From: David Brownell Date: Wed, 4 Mar 2009 12:01:41 -0800 Subject: [MTD] partitioning utility predicates Move mtd_has_partitions() and mtd_has_cmdlinepart() inlines from a DaVinci-specific driver to the header. Use those to eliminate #ifdefs in two drivers which had their own definitions of mtd_has_partitions(). Quite a lot of other MTD drivers could benefit from using use one or both of these to remove #ifdeffery. Maybe some Janitors would like to help. Signed-off-by: David Brownell Signed-off-by: Andrew Morton Signed-off-by: David Woodhouse --- include/linux/mtd/partitions.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/partitions.h b/include/linux/mtd/partitions.h index a45dd831b3f..7535a74083b 100644 --- a/include/linux/mtd/partitions.h +++ b/include/linux/mtd/partitions.h @@ -76,4 +76,16 @@ int __devinit of_mtd_parse_partitions(struct device *dev, struct device_node *node, struct mtd_partition **pparts); +#ifdef CONFIG_MTD_PARTITIONS +static inline int mtd_has_partitions(void) { return 1; } +#else +static inline int mtd_has_partitions(void) { return 0; } +#endif + +#ifdef CONFIG_MTD_CMDLINE_PARTS +static inline int mtd_has_cmdlinepart(void) { return 1; } +#else +static inline int mtd_has_cmdlinepart(void) { return 0; } +#endif + #endif -- cgit v1.2.3 From 3a3c244c9a355105bc193fde873c73727bf87192 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sun, 15 Feb 2009 22:32:48 +0100 Subject: PCI: PCIe portdrv: Implement pm object Implement pm object for the PCI Express port driver in order to use the new power management framework and reduce the code size. Signed-off-by: Rafael J. Wysocki Signed-off-by: Jesse Barnes --- include/linux/pcieport_if.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pcieport_if.h b/include/linux/pcieport_if.h index 5d2afcfa6bc..b4c79545330 100644 --- a/include/linux/pcieport_if.h +++ b/include/linux/pcieport_if.h @@ -59,7 +59,7 @@ struct pcie_port_service_driver { const char *name; int (*probe) (struct pcie_device *dev); void (*remove) (struct pcie_device *dev); - int (*suspend) (struct pcie_device *dev, pm_message_t state); + int (*suspend) (struct pcie_device *dev); int (*resume) (struct pcie_device *dev); /* Service Error Recovery Handler */ -- cgit v1.2.3 From 0747aaf42d78d26684c6f6b34a4103ff81f571f8 Mon Sep 17 00:00:00 2001 From: Kenji Kaneshige Date: Tue, 17 Feb 2009 14:11:56 +0900 Subject: PCI/ACPI: fix wrong assumption in acpi_pci_get_bridge_handle Current acpi_pci_get_bridge_handle() has an assumption that pci_bus->self is NULL on the root pci bus. But it might not true on some platforms. Because of this wrong assumption, current acpi_pci_get_bridge_handle() might return improper ACPI handle. We must check pci_bus->parent instead. This bug is the root cause of the following kernel panic reported by James Bottomley. This problem was introduced by the commit e8c331e963c58b83db24b7d0e39e8c07f687dbc6. The immediate cause was acpi_pci_get_bridge_handle() returned NULL unexpectedly and it was passed as the second argument of acpi_walk_namespace(). pci_hotplug: PCI Hot Plug PCI Core version: 0.5 acpiphp: ACPI Hot Plug PCI Controller Driver version: 0.5 BUG: unable to handle kernel NULL pointer dereference at 0000000000000010 IP: [] acpi_ns_get_next_node+0xb/0x3c PGD 0 Oops: 0000 [#1] SMP last sysfs file: CPU 0 Modules linked in: Pid: 1, comm: swapper Not tainted 2.6.28 #1 RIP: 0010:[] [] acpi_ns_get_next_node+0xb/0x3c RSP: 0018:ffff88007f87fd30 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 RBP: 0000000000000000 R08: ffffffff8037d260 R09: ffff88007f87fdfc R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000001 R13: 0000000000000000 R14: 0000000000000001 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffffffff80742040(0000) knlGS:0000000000000000 CS: 0010 DS: 0018 ES: 0018 CR0: 000000008005003b CR2: 0000000000000010 CR3: 0000000000201000 CR4: 00000000000006a0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process swapper (pid: 1, threadinfo ffff88007f87e000, task ffff88007f875040) Stack: 0000000000000000 ffffffff803964f5 ffff88007f81b728 0000000000001001 ffff88007f87fdfc ffffffff8037d260 0000000600000001 0000000000000000 ffffffff8037d260 0000000000000000 0000000000000001 ffff88007f87fdfc Call Trace: [] acpi_ns_walk_namespace+0x55/0x138 [] is_pci_dock_device+0x0/0x20 [] is_pci_dock_device+0x0/0x20 [] acpi_walk_namespace+0x5f/0x83 [] detect_ejectable_slots+0x53/0x70 [] add_bridge+0xe8/0x200 [] acpi_walk_namespace+0x6b/0x83 [] acpi_pci_register_driver+0x48/0x61 [] acpiphp_init+0x0/0x58 [] acpiphp_glue_init+0x4c/0x5a [] acpiphp_init+0x37/0x58 [] _stext+0x3b/0x180 [] create_proc_entry+0x58/0xa0 [] register_irq_proc+0xc1/0xe0 [] kernel_init+0x152/0x1ac [] finish_task_switch+0x0/0x110 [] child_rip+0xa/0x20 [] restore_args+0x0/0x30 [] kernel_init+0x0/0x1ac [] child_rip+0x0/0x20 Code: 89 c2 48 8b 00 48 85 c0 75 f5 48 8b 45 00 48 89 02 44 88 65 09 48 89 5d 00 31 c0 5b 5d 41 5c c3 53 48 85 d2 89 fb 48 89 d7 75 06 <48> 8b 56 10 eb 08 e8 73 f1 ff ff 48 89 c2 85 db 74 1a eb 13 0f RIP [] acpi_ns_get_next_node+0xb/0x3c RSP CR2: 0000000000000010 ---[ end trace a7919e7f17c0a725 ]--- Signed-off-by: Kenji Kaneshige Signed-off-by: Jesse Barnes --- include/linux/pci-acpi.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci-acpi.h b/include/linux/pci-acpi.h index 20480b9f10c..3cee2367459 100644 --- a/include/linux/pci-acpi.h +++ b/include/linux/pci-acpi.h @@ -23,11 +23,10 @@ static inline acpi_handle acpi_find_root_bridge_handle(struct pci_dev *pdev) static inline acpi_handle acpi_pci_get_bridge_handle(struct pci_bus *pbus) { - int seg = pci_domain_nr(pbus), busnr = pbus->number; - struct pci_dev *bridge = pbus->self; - if (bridge) - return DEVICE_ACPI_HANDLE(&(bridge->dev)); - return acpi_get_pci_rootbridge_handle(seg, busnr); + if (pbus->parent) + return DEVICE_ACPI_HANDLE(&(pbus->self->dev)); + return acpi_get_pci_rootbridge_handle(pci_domain_nr(pbus), + pbus->number); } #else static inline acpi_handle acpi_find_root_bridge_handle(struct pci_dev *pdev) -- cgit v1.2.3 From d18690af626b83fef1d1953b9f70e09497060586 Mon Sep 17 00:00:00 2001 From: Kenji Kaneshige Date: Tue, 17 Feb 2009 14:12:36 +0900 Subject: PCI/ACPI: fix wrong assumption in acpi_find_root_bridge_handle Current acpi_find_root_bridge_handle() has a assumption that pci_bus->self is NULL on the root pci bus. But it might not be true on some platforms. Because of this wrong assumption, current acpi_find_root_bridge_handle() might cause endless loop. We must check pci_bus->parent instead. Signed-off-by: Kenji Kaneshige Signed-off-by: Jesse Barnes --- include/linux/pci-acpi.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci-acpi.h b/include/linux/pci-acpi.h index 3cee2367459..092e82e0048 100644 --- a/include/linux/pci-acpi.h +++ b/include/linux/pci-acpi.h @@ -13,12 +13,12 @@ #ifdef CONFIG_ACPI static inline acpi_handle acpi_find_root_bridge_handle(struct pci_dev *pdev) { - /* Find root host bridge */ - while (pdev->bus->self) - pdev = pdev->bus->self; - - return acpi_get_pci_rootbridge_handle(pci_domain_nr(pdev->bus), - pdev->bus->number); + struct pci_bus *pbus = pdev->bus; + /* Find a PCI root bus */ + while (pbus->parent) + pbus = pbus->parent; + return acpi_get_pci_rootbridge_handle(pci_domain_nr(pbus), + pbus->number); } static inline acpi_handle acpi_pci_get_bridge_handle(struct pci_bus *pbus) -- cgit v1.2.3 From 998dd7c719f62dcfa91d7bf7f4eb9c160e03d817 Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Wed, 25 Feb 2009 13:15:52 +0800 Subject: PCI: fix incorrect mask of PM No_Soft_Reset bit Reviewed-by: Matthew Wilcox Signed-off-by: Yu Zhao Signed-off-by: Jesse Barnes --- include/linux/pci_regs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci_regs.h b/include/linux/pci_regs.h index 027815b4635..b647a4df59f 100644 --- a/include/linux/pci_regs.h +++ b/include/linux/pci_regs.h @@ -235,7 +235,7 @@ #define PCI_PM_CAP_PME_SHIFT 11 /* Start of the PME Mask in PMC */ #define PCI_PM_CTRL 4 /* PM control and status register */ #define PCI_PM_CTRL_STATE_MASK 0x0003 /* Current power state (D0 to D3) */ -#define PCI_PM_CTRL_NO_SOFT_RESET 0x0004 /* No reset for D3hot->D0 */ +#define PCI_PM_CTRL_NO_SOFT_RESET 0x0008 /* No reset for D3hot->D0 */ #define PCI_PM_CTRL_PME_ENABLE 0x0100 /* PME pin enable */ #define PCI_PM_CTRL_DATA_SEL_MASK 0x1e00 /* Data select (??) */ #define PCI_PM_CTRL_DATA_SCALE_MASK 0x6000 /* Data scale (??) */ -- cgit v1.2.3 From 24d27553390c69d11cdbd930d635193956fc295f Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 17 Mar 2009 08:54:06 -0400 Subject: PCI MSI: Replace 'type' with 'is_msix' By changing from a 5-bit field to a 1-bit field, we free up some bits that can be used by a later patch. Also rearrange the fields for better packing on 64-bit platforms (reducing the size of msi_desc from 72 bytes to 64 bytes). Signed-off-by: Matthew Wilcox Signed-off-by: Jesse Barnes --- include/linux/msi.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/msi.h b/include/linux/msi.h index d2b8a1e8ca1..9c5ce214fbf 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -20,13 +20,13 @@ extern void write_msi_msg(unsigned int irq, struct msi_msg *msg); struct msi_desc { struct { - __u8 type : 5; /* {0: unused, 5h:MSI, 11h:MSI-X} */ + __u8 is_msix : 1; __u8 maskbit : 1; /* mask-pending bit supported ? */ __u8 masked : 1; __u8 is_64 : 1; /* Address size: 0=32bit 1=64bit */ __u8 pos; /* Location of the msi capability */ - __u32 maskbits_mask; /* mask bits mask */ __u16 entry_nr; /* specific enabled entry */ + __u32 maskbits_mask; /* mask bits mask */ unsigned default_irq; /* default pre-assigned irq */ }msi_attrib; -- cgit v1.2.3 From 264d9caaa1c574c0274b019a810abfe957391005 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 17 Mar 2009 08:54:08 -0400 Subject: PCI MSI: Use mask_pos instead of mask_base when appropriate MSI interrupts have a mask_pos where MSI-X have a mask_base. Use a transparent union to get rid of some ugly casts. Signed-off-by: Matthew Wilcox Signed-off-by: Jesse Barnes --- include/linux/msi.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/msi.h b/include/linux/msi.h index 9c5ce214fbf..5025ca4d91e 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -33,7 +33,10 @@ struct msi_desc { unsigned int irq; struct list_head list; - void __iomem *mask_base; + union { + void __iomem *mask_base; + u8 mask_pos; + }; struct pci_dev *dev; /* Last set MSI message */ -- cgit v1.2.3 From f2440d9acbe866b917b16cc0f927366341ce9215 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 17 Mar 2009 08:54:09 -0400 Subject: PCI MSI: Refactor interrupt masking code Since most of the callers already know whether they have an MSI or an MSI-X capability, split msi_set_mask_bits() into msi_mask_irq() and msix_mask_irq(). The only callers which don't (mask_msi_irq() and unmask_msi_irq()) can share code in msi_set_mask_bit(). This then becomes the only caller of msix_flush_writes(), so we can inline it. The flushing read can be to any address that belongs to the device, so we can eliminate the calculation too. We can also get rid of maskbits_mask from struct msi_desc and simply recalculate it on the rare occasion that we need it. The single-bit 'masked' element is replaced by a copy of the 32-bit 'masked' register, so this patch does not affect the size of msi_desc. Signed-off-by: Matthew Wilcox Signed-off-by: Jesse Barnes --- include/linux/msi.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/msi.h b/include/linux/msi.h index 5025ca4d91e..37c1bbe546e 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -22,14 +22,13 @@ struct msi_desc { struct { __u8 is_msix : 1; __u8 maskbit : 1; /* mask-pending bit supported ? */ - __u8 masked : 1; __u8 is_64 : 1; /* Address size: 0=32bit 1=64bit */ __u8 pos; /* Location of the msi capability */ __u16 entry_nr; /* specific enabled entry */ - __u32 maskbits_mask; /* mask bits mask */ unsigned default_irq; /* default pre-assigned irq */ - }msi_attrib; + } msi_attrib; + u32 masked; /* mask bits */ unsigned int irq; struct list_head list; -- cgit v1.2.3 From 1c8d7b0a562da06d3ebe83f01b1ed553205d1ae4 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 17 Mar 2009 08:54:10 -0400 Subject: PCI MSI: Add support for multiple MSI Add the new API pci_enable_msi_block() to allow drivers to request multiple MSI and reimplement pci_enable_msi in terms of pci_enable_msi_block. Ensure that the architecture back ends don't have to know about multiple MSI. Signed-off-by: Matthew Wilcox Signed-off-by: Jesse Barnes --- include/linux/msi.h | 1 + include/linux/pci.h | 6 ++++-- 2 files changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/msi.h b/include/linux/msi.h index 37c1bbe546e..6991ab5b24d 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -21,6 +21,7 @@ extern void write_msi_msg(unsigned int irq, struct msi_msg *msg); struct msi_desc { struct { __u8 is_msix : 1; + __u8 multiple: 3; /* log2 number of messages */ __u8 maskbit : 1; /* mask-pending bit supported ? */ __u8 is_64 : 1; /* Address size: 0=32bit 1=64bit */ __u8 pos; /* Location of the msi capability */ diff --git a/include/linux/pci.h b/include/linux/pci.h index 7baf2a5db12..1f6c5ddaae3 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -789,7 +789,7 @@ struct msix_entry { #ifndef CONFIG_PCI_MSI -static inline int pci_enable_msi(struct pci_dev *dev) +static inline int pci_enable_msi_block(struct pci_dev *dev, unsigned int nvec) { return -1; } @@ -824,7 +824,7 @@ static inline int pci_msi_enabled(void) return 0; } #else -extern int pci_enable_msi(struct pci_dev *dev); +extern int pci_enable_msi_block(struct pci_dev *dev, unsigned int nvec); extern void pci_msi_shutdown(struct pci_dev *dev); extern void pci_disable_msi(struct pci_dev *dev); extern int pci_msix_table_size(struct pci_dev *dev); @@ -846,6 +846,8 @@ static inline int pcie_aspm_enabled(void) extern int pcie_aspm_enabled(void); #endif +#define pci_enable_msi(pdev) pci_enable_msi_block(pdev, 1) + #ifdef CONFIG_HT_IRQ /* The functions a driver should call */ int ht_create_irq(struct pci_dev *dev, int idx); -- cgit v1.2.3 From 8293b0f629095efbe7c7e3f9b437f8c040c19eb5 Mon Sep 17 00:00:00 2001 From: David O'Shea Date: Mon, 2 Mar 2009 09:51:13 +0100 Subject: PCI: Compaq Evo D510 SMBus quirk using USB instead of VGA On the Compaq Evo D510 SFF/CMT, a PCI quirk activated the SMBus device based on detection of the on-board VGA controller, but the on-board VGA is disabled if an AGP card is inserted, so look for one of the USB controllers instead. Signed-off-by: David O'Shea Signed-off-by: Jean Delvare Signed-off-by: Jesse Barnes --- include/linux/pci_ids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index aca8c458aa8..3ddf8beabdf 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2373,6 +2373,7 @@ #define PCI_DEVICE_ID_INTEL_82801CA_12 0x248c #define PCI_DEVICE_ID_INTEL_82801DB_0 0x24c0 #define PCI_DEVICE_ID_INTEL_82801DB_1 0x24c1 +#define PCI_DEVICE_ID_INTEL_82801DB_2 0x24c2 #define PCI_DEVICE_ID_INTEL_82801DB_3 0x24c3 #define PCI_DEVICE_ID_INTEL_82801DB_5 0x24c5 #define PCI_DEVICE_ID_INTEL_82801DB_6 0x24c6 -- cgit v1.2.3 From d1b054da8f599905f3c18a218961dcf17f9d5f13 Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Fri, 20 Mar 2009 11:25:11 +0800 Subject: PCI: initialize and release SR-IOV capability If a device has the SR-IOV capability, initialize it (set the ARI Capable Hierarchy in the lowest numbered PF if necessary; calculate the System Page Size for the VF MMIO, probe the VF Offset, Stride and BARs). A lock for the VF bus allocation is also initialized if a PF is the lowest numbered PF. Reviewed-by: Matthew Wilcox Signed-off-by: Yu Zhao Signed-off-by: Jesse Barnes --- include/linux/pci.h | 11 +++++++++++ include/linux/pci_regs.h | 33 +++++++++++++++++++++++++++++++++ 2 files changed, 44 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 1f6c5ddaae3..8ce2f2d9ab6 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -93,6 +93,12 @@ enum { /* #6: expansion ROM resource */ PCI_ROM_RESOURCE, + /* device specific resources */ +#ifdef CONFIG_PCI_IOV + PCI_IOV_RESOURCES, + PCI_IOV_RESOURCE_END = PCI_IOV_RESOURCES + PCI_SRIOV_NUM_BARS - 1, +#endif + /* resources assigned to buses behind the bridge */ #define PCI_BRIDGE_RESOURCE_NUM 4 @@ -180,6 +186,7 @@ struct pci_cap_saved_state { struct pcie_link_state; struct pci_vpd; +struct pci_sriov; /* * The pci_dev structure is used to describe PCI devices. @@ -257,6 +264,7 @@ struct pci_dev { unsigned int is_managed:1; unsigned int is_pcie:1; unsigned int state_saved:1; + unsigned int is_physfn:1; pci_dev_flags_t dev_flags; atomic_t enable_cnt; /* pci_enable_device has been called */ @@ -270,6 +278,9 @@ struct pci_dev { struct list_head msi_list; #endif struct pci_vpd *vpd; +#ifdef CONFIG_PCI_IOV + struct pci_sriov *sriov; /* SR-IOV capability related */ +#endif }; extern struct pci_dev *alloc_pci_dev(void); diff --git a/include/linux/pci_regs.h b/include/linux/pci_regs.h index b647a4df59f..d4e663877f4 100644 --- a/include/linux/pci_regs.h +++ b/include/linux/pci_regs.h @@ -375,6 +375,7 @@ #define PCI_EXP_TYPE_UPSTREAM 0x5 /* Upstream Port */ #define PCI_EXP_TYPE_DOWNSTREAM 0x6 /* Downstream Port */ #define PCI_EXP_TYPE_PCI_BRIDGE 0x7 /* PCI/PCI-X Bridge */ +#define PCI_EXP_TYPE_RC_END 0x9 /* Root Complex Integrated Endpoint */ #define PCI_EXP_FLAGS_SLOT 0x0100 /* Slot implemented */ #define PCI_EXP_FLAGS_IRQ 0x3e00 /* Interrupt message number */ #define PCI_EXP_DEVCAP 4 /* Device capabilities */ @@ -498,6 +499,7 @@ #define PCI_EXT_CAP_ID_DSN 3 #define PCI_EXT_CAP_ID_PWR 4 #define PCI_EXT_CAP_ID_ARI 14 +#define PCI_EXT_CAP_ID_SRIOV 16 /* Advanced Error Reporting */ #define PCI_ERR_UNCOR_STATUS 4 /* Uncorrectable Error Status */ @@ -615,4 +617,35 @@ #define PCI_ARI_CTRL_ACS 0x0002 /* ACS Function Groups Enable */ #define PCI_ARI_CTRL_FG(x) (((x) >> 4) & 7) /* Function Group */ +/* Single Root I/O Virtualization */ +#define PCI_SRIOV_CAP 0x04 /* SR-IOV Capabilities */ +#define PCI_SRIOV_CAP_VFM 0x01 /* VF Migration Capable */ +#define PCI_SRIOV_CAP_INTR(x) ((x) >> 21) /* Interrupt Message Number */ +#define PCI_SRIOV_CTRL 0x08 /* SR-IOV Control */ +#define PCI_SRIOV_CTRL_VFE 0x01 /* VF Enable */ +#define PCI_SRIOV_CTRL_VFM 0x02 /* VF Migration Enable */ +#define PCI_SRIOV_CTRL_INTR 0x04 /* VF Migration Interrupt Enable */ +#define PCI_SRIOV_CTRL_MSE 0x08 /* VF Memory Space Enable */ +#define PCI_SRIOV_CTRL_ARI 0x10 /* ARI Capable Hierarchy */ +#define PCI_SRIOV_STATUS 0x0a /* SR-IOV Status */ +#define PCI_SRIOV_STATUS_VFM 0x01 /* VF Migration Status */ +#define PCI_SRIOV_INITIAL_VF 0x0c /* Initial VFs */ +#define PCI_SRIOV_TOTAL_VF 0x0e /* Total VFs */ +#define PCI_SRIOV_NUM_VF 0x10 /* Number of VFs */ +#define PCI_SRIOV_FUNC_LINK 0x12 /* Function Dependency Link */ +#define PCI_SRIOV_VF_OFFSET 0x14 /* First VF Offset */ +#define PCI_SRIOV_VF_STRIDE 0x16 /* Following VF Stride */ +#define PCI_SRIOV_VF_DID 0x1a /* VF Device ID */ +#define PCI_SRIOV_SUP_PGSIZE 0x1c /* Supported Page Sizes */ +#define PCI_SRIOV_SYS_PGSIZE 0x20 /* System Page Size */ +#define PCI_SRIOV_BAR 0x24 /* VF BAR0 */ +#define PCI_SRIOV_NUM_BARS 6 /* Number of VF BARs */ +#define PCI_SRIOV_VFM 0x3c /* VF Migration State Array Offset*/ +#define PCI_SRIOV_VFM_BIR(x) ((x) & 7) /* State BIR */ +#define PCI_SRIOV_VFM_OFFSET(x) ((x) & ~7) /* State Offset */ +#define PCI_SRIOV_VFM_UA 0x0 /* Inactive.Unavailable */ +#define PCI_SRIOV_VFM_MI 0x1 /* Dormant.MigrateIn */ +#define PCI_SRIOV_VFM_MO 0x2 /* Active.MigrateOut */ +#define PCI_SRIOV_VFM_AV 0x3 /* Active.Available */ + #endif /* LINUX_PCI_REGS_H */ -- cgit v1.2.3 From dd7cc44d0bcec5e9c42fe52e88dc254ae62eac8d Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Fri, 20 Mar 2009 11:25:15 +0800 Subject: PCI: add SR-IOV API for Physical Function driver Add or remove the Virtual Function when the SR-IOV is enabled or disabled by the device driver. This can happen anytime rather than only at the device probe stage. Reviewed-by: Matthew Wilcox Signed-off-by: Yu Zhao Signed-off-by: Jesse Barnes --- include/linux/pci.h | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 8ce2f2d9ab6..c2e491e0406 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -265,6 +265,7 @@ struct pci_dev { unsigned int is_pcie:1; unsigned int state_saved:1; unsigned int is_physfn:1; + unsigned int is_virtfn:1; pci_dev_flags_t dev_flags; atomic_t enable_cnt; /* pci_enable_device has been called */ @@ -279,7 +280,10 @@ struct pci_dev { #endif struct pci_vpd *vpd; #ifdef CONFIG_PCI_IOV - struct pci_sriov *sriov; /* SR-IOV capability related */ + union { + struct pci_sriov *sriov; /* SR-IOV capability related */ + struct pci_dev *physfn; /* the PF this VF is associated with */ + }; #endif }; @@ -1212,5 +1216,18 @@ int pci_ext_cfg_avail(struct pci_dev *dev); void __iomem *pci_ioremap_bar(struct pci_dev *pdev, int bar); +#ifdef CONFIG_PCI_IOV +extern int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn); +extern void pci_disable_sriov(struct pci_dev *dev); +#else +static inline int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn) +{ + return -ENODEV; +} +static inline void pci_disable_sriov(struct pci_dev *dev) +{ +} +#endif + #endif /* __KERNEL__ */ #endif /* LINUX_PCI_H */ -- cgit v1.2.3 From 74bb1bcc7dbbc9ddef773bf3395d7ff92aaaad2e Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Fri, 20 Mar 2009 11:25:16 +0800 Subject: PCI: handle SR-IOV Virtual Function Migration Add or remove a Virtual Function after receiving a Migrate In or Out Request. Reviewed-by: Matthew Wilcox Signed-off-by: Yu Zhao Signed-off-by: Jesse Barnes --- include/linux/pci.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index c2e491e0406..1216843412d 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -52,6 +52,7 @@ #include #include #include +#include /* Include the ID list */ #include @@ -1219,6 +1220,7 @@ void __iomem *pci_ioremap_bar(struct pci_dev *pdev, int bar); #ifdef CONFIG_PCI_IOV extern int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn); extern void pci_disable_sriov(struct pci_dev *dev); +extern irqreturn_t pci_sriov_migration(struct pci_dev *dev); #else static inline int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn) { @@ -1227,6 +1229,10 @@ static inline int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn) static inline void pci_disable_sriov(struct pci_dev *dev) { } +static inline irqreturn_t pci_sriov_migration(struct pci_dev *dev) +{ + return IRQ_NONE; +} #endif #endif /* __KERNEL__ */ -- cgit v1.2.3 From 79af72d716cf1bb13b175429cf181a6c4d063ee8 Mon Sep 17 00:00:00 2001 From: Kenji Kaneshige Date: Fri, 20 Mar 2009 14:55:55 -0600 Subject: PCI: pci_is_root_bus helper Introduce pci_is_root_bus helper function. This will help make code more consistent, as well as prevent incorrect assumptions (such as pci_bus->self == NULL on a root bus, which is not always true). Signed-off-by: Kenji Kaneshige Signed-off-by: Alex Chiang Signed-off-by: Jesse Barnes --- include/linux/pci.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 1216843412d..50d94388e87 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -357,6 +357,15 @@ struct pci_bus { #define pci_bus_b(n) list_entry(n, struct pci_bus, node) #define to_pci_bus(n) container_of(n, struct pci_bus, dev) +/* + * Returns true if the pci bus is root (behind host-pci bridge), + * false otherwise + */ +static inline bool pci_is_root_bus(struct pci_bus *pbus) +{ + return !(pbus->parent); +} + #ifdef CONFIG_PCI_MSI static inline bool pci_dev_msi_enabled(struct pci_dev *pci_dev) { -- cgit v1.2.3 From 3ed4fd96b3188406ac5357d9290bcffa08c65cf6 Mon Sep 17 00:00:00 2001 From: Alex Chiang Date: Fri, 20 Mar 2009 14:56:25 -0600 Subject: PCI: Introduce pci_rescan_bus() This API is used by the PCI core to rescan a bus and rediscover newly added devices. Over time, it is expected that the various PCI hotplug drivers will migrate to this interface and away from the old pci_do_scan_bus() interface. Signed-off-by: Alex Chiang Signed-off-by: Jesse Barnes --- include/linux/pci.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 50d94388e87..6fb335b0d74 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -726,6 +726,9 @@ int pci_back_from_sleep(struct pci_dev *dev); /* Functions for PCI Hotplug drivers to use */ int pci_bus_find_capability(struct pci_bus *bus, unsigned int devfn, int cap); +#ifdef CONFIG_HOTPLUG +unsigned int pci_rescan_bus(struct pci_bus *bus); +#endif /* Vital product data routines */ ssize_t pci_read_vpd(struct pci_dev *dev, loff_t pos, size_t count, void *buf); -- cgit v1.2.3 From e2fc4d19292ef2eb208f76976ddc3320cc5839b6 Mon Sep 17 00:00:00 2001 From: Maciej Sosnowski Date: Sat, 21 Mar 2009 13:31:23 -0700 Subject: dca: add missing copyright/license headers In two dca files copyright and license headers are missing. This patch adds them there. Signed-off-by: Maciej Sosnowski Signed-off-by: David S. Miller --- include/linux/dca.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dca.h b/include/linux/dca.h index b00a753eda5..9c20c7e87d0 100644 --- a/include/linux/dca.h +++ b/include/linux/dca.h @@ -1,3 +1,23 @@ +/* + * Copyright(c) 2007 - 2009 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program; if not, write to the Free Software Foundation, Inc., 59 + * Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * The full GNU General Public License is included in this distribution in the + * file called COPYING. + */ #ifndef DCA_H #define DCA_H /* DCA Provider API */ -- cgit v1.2.3 From 9247744e5eaa29aecee5342a0c8694187a6aadcd Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Sat, 21 Mar 2009 13:39:26 -0700 Subject: skb: expose and constify hash primitives Some minor changes to queue hashing: 1. Use const on accessor functions 2. Export skb_tx_hash for use in drivers (see ixgbe) Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/skbuff.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 1fbab2ae613..bb1981fd60f 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1969,7 +1969,7 @@ static inline void skb_set_queue_mapping(struct sk_buff *skb, u16 queue_mapping) skb->queue_mapping = queue_mapping; } -static inline u16 skb_get_queue_mapping(struct sk_buff *skb) +static inline u16 skb_get_queue_mapping(const struct sk_buff *skb) { return skb->queue_mapping; } @@ -1984,16 +1984,19 @@ static inline void skb_record_rx_queue(struct sk_buff *skb, u16 rx_queue) skb->queue_mapping = rx_queue + 1; } -static inline u16 skb_get_rx_queue(struct sk_buff *skb) +static inline u16 skb_get_rx_queue(const struct sk_buff *skb) { return skb->queue_mapping - 1; } -static inline bool skb_rx_queue_recorded(struct sk_buff *skb) +static inline bool skb_rx_queue_recorded(const struct sk_buff *skb) { return (skb->queue_mapping != 0); } +extern u16 skb_tx_hash(const struct net_device *dev, + const struct sk_buff *skb); + #ifdef CONFIG_XFRM static inline struct sec_path *skb_sec_path(struct sk_buff *skb) { -- cgit v1.2.3 From 777baa4711c6b8373f4e03a3a558d44a6b046d7a Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Fri, 20 Mar 2009 19:35:54 +0000 Subject: usbnet: support net_device_ops Use net_device_ops for usbnet device, and export for use by other derived drivers. Signed-off-by: Stephen Hemminger Acked-by: David Brownell Signed-off-by: David S. Miller --- include/linux/usb/usbnet.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index 7d382224307..36fabb95c7d 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -176,6 +176,11 @@ struct skb_data { /* skb->cb is one of these */ size_t length; }; +extern int usbnet_open (struct net_device *net); +extern int usbnet_stop (struct net_device *net); +extern int usbnet_start_xmit (struct sk_buff *skb, struct net_device *net); +extern void usbnet_tx_timeout (struct net_device *net); +extern int usbnet_change_mtu (struct net_device *net, int new_mtu); extern int usbnet_get_endpoints(struct usbnet *, struct usb_interface *); extern void usbnet_defer_kevent (struct usbnet *, int); -- cgit v1.2.3 From 2d622719f1572ef31e0616444a515eba3094d050 Mon Sep 17 00:00:00 2001 From: Tom Zanussi Date: Sun, 22 Mar 2009 03:30:49 -0500 Subject: tracing: add ring_buffer_event_discard() to ring buffer This patch overloads RINGBUF_TYPE_PADDING to provide a way to discard events from the ring buffer, for the event-filtering mechanism introduced in a subsequent patch. I did the initial version but thanks to Steven Rostedt for adding the parts that actually made it work. ;-) Signed-off-by: Tom Zanussi Acked-by: Frederic Weisbecker Signed-off-by: Ingo Molnar --- include/linux/ring_buffer.h | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 9e6052bd1a1..e1b7b217388 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -18,10 +18,13 @@ struct ring_buffer_event { /** * enum ring_buffer_type - internal ring buffer types * - * @RINGBUF_TYPE_PADDING: Left over page padding - * array is ignored - * size is variable depending on how much + * @RINGBUF_TYPE_PADDING: Left over page padding or discarded event + * If time_delta is 0: + * array is ignored + * size is variable depending on how much * padding is needed + * If time_delta is non zero: + * everything else same as RINGBUF_TYPE_DATA * * @RINGBUF_TYPE_TIME_EXTEND: Extend the time delta * array[0] = time delta (28 .. 59) @@ -65,6 +68,8 @@ ring_buffer_event_time_delta(struct ring_buffer_event *event) return event->time_delta; } +void ring_buffer_event_discard(struct ring_buffer_event *event); + /* * size is in bytes for each per CPU buffer. */ -- cgit v1.2.3 From dd5b6ce6fd465eab90357711c8e8124dc3a31ff0 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 23 Mar 2009 13:21:06 +0100 Subject: nefilter: nfnetlink: add nfnetlink_set_err and use it in ctnetlink This patch adds nfnetlink_set_err() to propagate the error to netlink broadcast listener in case of memory allocation errors in the message building. Signed-off-by: Pablo Neira Ayuso Signed-off-by: Patrick McHardy --- include/linux/netfilter/nfnetlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 7d8e0455cca..135e5cfe68a 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -76,6 +76,7 @@ extern int nfnetlink_subsys_unregister(const struct nfnetlink_subsystem *n); extern int nfnetlink_has_listeners(unsigned int group); extern int nfnetlink_send(struct sk_buff *skb, u32 pid, unsigned group, int echo); +extern void nfnetlink_set_err(u32 pid, u32 group, int error); extern int nfnetlink_unicast(struct sk_buff *skb, u_int32_t pid, int flags); extern void nfnl_lock(void); -- cgit v1.2.3 From 402d326519c1a4859c527702383f4e60f606ef52 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 12 Feb 2009 10:40:00 +0000 Subject: NOMMU: Present backing device capabilities for MTD chardevs Present backing device capabilities for MTD character device files to allow NOMMU mmap to do direct mapping where possible. Signed-off-by: David Howells Tested-by: Bernd Schmidt Signed-off-by: David Woodhouse --- include/linux/mtd/mtd.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index 3aa5d77c2cd..0c079fd307a 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -162,6 +162,20 @@ struct mtd_info { /* We probably shouldn't allow XIP if the unpoint isn't a NULL */ void (*unpoint) (struct mtd_info *mtd, loff_t from, size_t len); + /* Allow NOMMU mmap() to directly map the device (if not NULL) + * - return the address to which the offset maps + * - return -ENOSYS to indicate refusal to do the mapping + */ + unsigned long (*get_unmapped_area) (struct mtd_info *mtd, + unsigned long len, + unsigned long offset, + unsigned long flags); + + /* Backing device capabilities for this device + * - provides mmap capabilities + */ + struct backing_dev_info *backing_dev_info; + int (*read) (struct mtd_info *mtd, loff_t from, size_t len, size_t *retlen, u_char *buf); int (*write) (struct mtd_info *mtd, loff_t to, size_t len, size_t *retlen, const u_char *buf); -- cgit v1.2.3 From d0bfb940ecabf0b44fb1fd80d8d60594e569e5ec Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Mon, 15 Dec 2008 13:52:10 +0100 Subject: KVM: New guest debug interface This rips out the support for KVM_DEBUG_GUEST and introduces a new IOCTL instead: KVM_SET_GUEST_DEBUG. The IOCTL payload consists of a generic part, controlling the "main switch" and the single-step feature. The arch specific part adds an x86 interface for intercepting both types of debug exceptions separately and re-injecting them when the host was not interested. Moveover, the foundation for guest debugging via debug registers is layed. To signal breakpoint events properly back to userland, an arch-specific data block is now returned along KVM_EXIT_DEBUG. For x86, the arch block contains the PC, the debug exception, and relevant debug registers to tell debug events properly apart. The availability of this new interface is signaled by KVM_CAP_SET_GUEST_DEBUG. Empty stubs for not yet supported archs are provided. Note that both SVM and VTX are supported, but only the latter was tested yet. Based on the experience with all those VTX corner case, I would be fairly surprised if SVM will work out of the box. Signed-off-by: Jan Kiszka Signed-off-by: Avi Kivity --- include/linux/kvm.h | 51 +++++++++++++++++++++++++++++++++--------------- include/linux/kvm_host.h | 6 +++--- 2 files changed, 38 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 0424326f167..429a2ce202f 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -126,6 +126,7 @@ struct kvm_run { __u64 data_offset; /* relative to kvm_run start */ } io; struct { + struct kvm_debug_exit_arch arch; } debug; /* KVM_EXIT_MMIO */ struct { @@ -217,21 +218,6 @@ struct kvm_interrupt { __u32 irq; }; -struct kvm_breakpoint { - __u32 enabled; - __u32 padding; - __u64 address; -}; - -/* for KVM_DEBUG_GUEST */ -struct kvm_debug_guest { - /* int */ - __u32 enabled; - __u32 pad; - struct kvm_breakpoint breakpoints[4]; - __u32 singlestep; -}; - /* for KVM_GET_DIRTY_LOG */ struct kvm_dirty_log { __u32 slot; @@ -292,6 +278,17 @@ struct kvm_s390_interrupt { __u64 parm64; }; +/* for KVM_SET_GUEST_DEBUG */ + +#define KVM_GUESTDBG_ENABLE 0x00000001 +#define KVM_GUESTDBG_SINGLESTEP 0x00000002 + +struct kvm_guest_debug { + __u32 control; + __u32 pad; + struct kvm_guest_debug_arch arch; +}; + #define KVM_TRC_SHIFT 16 /* * kvm trace categories @@ -396,6 +393,7 @@ struct kvm_trace_rec { #ifdef __KVM_HAVE_USER_NMI #define KVM_CAP_USER_NMI 22 #endif +#define KVM_CAP_SET_GUEST_DEBUG 23 /* * ioctls for VM fds @@ -440,7 +438,8 @@ struct kvm_trace_rec { #define KVM_SET_SREGS _IOW(KVMIO, 0x84, struct kvm_sregs) #define KVM_TRANSLATE _IOWR(KVMIO, 0x85, struct kvm_translation) #define KVM_INTERRUPT _IOW(KVMIO, 0x86, struct kvm_interrupt) -#define KVM_DEBUG_GUEST _IOW(KVMIO, 0x87, struct kvm_debug_guest) +/* KVM_DEBUG_GUEST is no longer supported, use KVM_SET_GUEST_DEBUG instead */ +#define KVM_DEBUG_GUEST __KVM_DEPRECATED_DEBUG_GUEST #define KVM_GET_MSRS _IOWR(KVMIO, 0x88, struct kvm_msrs) #define KVM_SET_MSRS _IOW(KVMIO, 0x89, struct kvm_msrs) #define KVM_SET_CPUID _IOW(KVMIO, 0x8a, struct kvm_cpuid) @@ -469,6 +468,26 @@ struct kvm_trace_rec { #define KVM_SET_MP_STATE _IOW(KVMIO, 0x99, struct kvm_mp_state) /* Available with KVM_CAP_NMI */ #define KVM_NMI _IO(KVMIO, 0x9a) +/* Available with KVM_CAP_SET_GUEST_DEBUG */ +#define KVM_SET_GUEST_DEBUG _IOW(KVMIO, 0x9b, struct kvm_guest_debug) + +/* + * Deprecated interfaces + */ +struct kvm_breakpoint { + __u32 enabled; + __u32 padding; + __u64 address; +}; + +struct kvm_debug_guest { + __u32 enabled; + __u32 pad; + struct kvm_breakpoint breakpoints[4]; + __u32 singlestep; +}; + +#define __KVM_DEPRECATED_DEBUG_GUEST _IOW(KVMIO, 0x87, struct kvm_debug_guest) #define KVM_TRC_INJ_VIRQ (KVM_TRC_HANDLER + 0x02) #define KVM_TRC_REDELIVER_EVT (KVM_TRC_HANDLER + 0x03) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index bf6f703642f..e92212f970d 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -73,7 +73,7 @@ struct kvm_vcpu { struct kvm_run *run; int guest_mode; unsigned long requests; - struct kvm_guest_debug guest_debug; + unsigned long guest_debug; int fpu_active; int guest_fpu_loaded; wait_queue_head_t wq; @@ -255,8 +255,8 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state); int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state); -int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu, - struct kvm_debug_guest *dbg); +int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, + struct kvm_guest_debug *dbg); int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run); int kvm_arch_init(void *opaque); -- cgit v1.2.3 From e9a999fe1feaddb71bffbacbbd68e0da8ca8b50b Mon Sep 17 00:00:00 2001 From: Jes Sorensen Date: Thu, 18 Dec 2008 12:17:51 +0100 Subject: KVM: ia64: stack get/restore patch Implement KVM_IA64_VCPU_[GS]ET_STACK ioctl calls. This is required for live migrations. Patch is based on previous implementation that was part of old GET/SET_REGS ioctl calls. Signed-off-by: Jes Sorensen Signed-off-by: Avi Kivity --- include/linux/kvm.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 429a2ce202f..28582fcd3f7 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -489,6 +489,9 @@ struct kvm_debug_guest { #define __KVM_DEPRECATED_DEBUG_GUEST _IOW(KVMIO, 0x87, struct kvm_debug_guest) +#define KVM_IA64_VCPU_GET_STACK _IOR(KVMIO, 0x9a, void *) +#define KVM_IA64_VCPU_SET_STACK _IOW(KVMIO, 0x9b, void *) + #define KVM_TRC_INJ_VIRQ (KVM_TRC_HANDLER + 0x02) #define KVM_TRC_REDELIVER_EVT (KVM_TRC_HANDLER + 0x03) #define KVM_TRC_PEND_INTR (KVM_TRC_HANDLER + 0x04) -- cgit v1.2.3 From 971cc3dcbc0e020b82f568e61a47b72be03307dd Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Fri, 19 Dec 2008 18:13:54 +0100 Subject: KVM: Advertise guest debug capability per-arch Limit KVM_CAP_SET_GUEST_DEBUG only to those archs (currently x86) that support it. This simplifies user space stub implementations. Signed-off-by: Jan Kiszka Signed-off-by: Avi Kivity --- include/linux/kvm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 28582fcd3f7..11e3e6197c8 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -393,7 +393,9 @@ struct kvm_trace_rec { #ifdef __KVM_HAVE_USER_NMI #define KVM_CAP_USER_NMI 22 #endif +#if defined(CONFIG_X86) #define KVM_CAP_SET_GUEST_DEBUG 23 +#endif /* * ioctls for VM fds -- cgit v1.2.3 From 0f346074403bc109f9569f14b45cb09e83729032 Mon Sep 17 00:00:00 2001 From: Izik Eidus Date: Mon, 29 Dec 2008 01:42:20 +0200 Subject: KVM: remove the vmap usage vmap() on guest pages hides those pages from the Linux mm for an extended (userspace determined) amount of time. Get rid of it. Signed-off-by: Izik Eidus Signed-off-by: Avi Kivity --- include/linux/kvm_types.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index 9b6f395c962..5f4a18cae26 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -43,8 +43,7 @@ typedef hfn_t pfn_t; struct kvm_pio_request { unsigned long count; int cur_count; - struct page *guest_pages[2]; - unsigned guest_page_offset; + gva_t guest_gva; int in; int port; int size; -- cgit v1.2.3 From 52d939a0bf44081bc9f69b4fbdc9e7f416df27c7 Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Tue, 30 Dec 2008 15:55:06 -0200 Subject: KVM: PIT: provide an option to disable interrupt reinjection Certain clocks (such as TSC) in older 2.6 guests overaccount for lost ticks, causing severe time drift. Interrupt reinjection magnifies the problem. Provide an option to disable it. [avi: allow room for expansion in case we want to disable reinjection of other timers] Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- include/linux/kvm.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 11e3e6197c8..ae7a12c7742 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -396,6 +396,9 @@ struct kvm_trace_rec { #if defined(CONFIG_X86) #define KVM_CAP_SET_GUEST_DEBUG 23 #endif +#if defined(CONFIG_X86) +#define KVM_CAP_REINJECT_CONTROL 24 +#endif /* * ioctls for VM fds @@ -429,6 +432,7 @@ struct kvm_trace_rec { struct kvm_assigned_pci_dev) #define KVM_ASSIGN_IRQ _IOR(KVMIO, 0x70, \ struct kvm_assigned_irq) +#define KVM_REINJECT_CONTROL _IO(KVMIO, 0x71) /* * ioctls for vcpu fds -- cgit v1.2.3 From 1c08364c3565242f1e1bd585bc2ce458967941af Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Sun, 4 Jan 2009 12:39:07 +0200 Subject: KVM: Move struct kvm_pio_request into x86 kvm_host.h This is an x86 specific stucture and has no business living in common code. Signed-off-by: Avi Kivity --- include/linux/kvm_types.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index 5f4a18cae26..2b8318c83e5 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -40,16 +40,4 @@ typedef unsigned long hfn_t; typedef hfn_t pfn_t; -struct kvm_pio_request { - unsigned long count; - int cur_count; - gva_t guest_gva; - int in; - int port; - int size; - int string; - int down; - int rep; -}; - #endif /* __KVM_TYPES_H__ */ -- cgit v1.2.3 From 67346440e83d2a2f2e9801f370b6240317c7d9bd Mon Sep 17 00:00:00 2001 From: Sheng Yang Date: Tue, 6 Jan 2009 10:03:01 +0800 Subject: KVM: Remove duplicated prototype of kvm_arch_destroy_vm Signed-off-by: Sheng Yang Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index e92212f970d..3cf0ede3fd7 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -237,7 +237,6 @@ int kvm_vm_ioctl_set_memory_region(struct kvm *kvm, int user_alloc); long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); -void kvm_arch_destroy_vm(struct kvm *kvm); int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu); int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu); -- cgit v1.2.3 From 17071fe74fe0fbfdb03cd9b82f2490447cf1f986 Mon Sep 17 00:00:00 2001 From: Sheng Yang Date: Tue, 6 Jan 2009 16:25:11 +0800 Subject: KVM: Add support to disable MSI for assigned device MSI is always enabled by default for msi2intx=1. But if msi2intx=0, we have to disable MSI if guest require to do so. The patch also discard unnecessary msi2intx judgment if guest want to update MSI state. Notice KVM_DEV_IRQ_ASSIGN_MSI_ACTION is a mask which should cover all MSI related operations, though we only got one for now. Signed-off-by: Sheng Yang Signed-off-by: Avi Kivity --- include/linux/kvm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index ae7a12c7742..73f34806686 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -550,6 +550,7 @@ struct kvm_assigned_irq { #define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0) +#define KVM_DEV_IRQ_ASSIGN_MSI_ACTION KVM_DEV_IRQ_ASSIGN_ENABLE_MSI #define KVM_DEV_IRQ_ASSIGN_ENABLE_MSI (1 << 0) #endif -- cgit v1.2.3 From 75858a84a6207f5e60196f6bbd18fde4250e5759 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Sun, 4 Jan 2009 17:10:50 +0200 Subject: KVM: Interrupt mask notifiers for ioapic Allow clients to request notifications when the guest masks or unmasks a particular irq line. This complements irq ack notifications, as the guest will not ack an irq line that is masked. Currently implemented for the ioapic only. Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 3cf0ede3fd7..99963f36a6d 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -127,6 +127,10 @@ struct kvm { struct kvm_coalesced_mmio_ring *coalesced_mmio_ring; #endif +#ifdef CONFIG_HAVE_KVM_IRQCHIP + struct hlist_head mask_notifier_list; +#endif + #ifdef KVM_ARCH_WANT_MMU_NOTIFIER struct mmu_notifier mmu_notifier; unsigned long mmu_notifier_seq; @@ -320,6 +324,19 @@ struct kvm_assigned_dev_kernel { struct pci_dev *dev; struct kvm *kvm; }; + +struct kvm_irq_mask_notifier { + void (*func)(struct kvm_irq_mask_notifier *kimn, bool masked); + int irq; + struct hlist_node link; +}; + +void kvm_register_irq_mask_notifier(struct kvm *kvm, int irq, + struct kvm_irq_mask_notifier *kimn); +void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq, + struct kvm_irq_mask_notifier *kimn); +void kvm_fire_mask_notifiers(struct kvm *kvm, int irq, bool mask); + void kvm_set_irq(struct kvm *kvm, int irq_source_id, int irq, int level); void kvm_notify_acked_irq(struct kvm *kvm, unsigned gsi); void kvm_register_irq_ack_notifier(struct kvm *kvm, -- cgit v1.2.3 From 399ec807ddc38ecccf8c06dbde04531cbdc63e11 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Wed, 19 Nov 2008 13:58:46 +0200 Subject: KVM: Userspace controlled irq routing Currently KVM has a static routing from GSI numbers to interrupts (namely, 0-15 are mapped 1:1 to both PIC and IOAPIC, and 16:23 are mapped 1:1 to the IOAPIC). This is insufficient for several reasons: - HPET requires non 1:1 mapping for the timer interrupt - MSIs need a new method to assign interrupt numbers and dispatch them - ACPI APIC mode needs to be able to reassign the PCI LINK interrupts to the ioapics This patch implements an interrupt routing table (as a linked list, but this can be easily changed) and a userspace interface to replace the table. The routing table is initialized according to the current hardwired mapping. Signed-off-by: Avi Kivity --- include/linux/kvm.h | 33 +++++++++++++++++++++++++++++++++ include/linux/kvm_host.h | 31 +++++++++++++++++++++++++++++++ 2 files changed, 64 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 73f34806686..7a5d73a8d4f 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -398,6 +398,38 @@ struct kvm_trace_rec { #endif #if defined(CONFIG_X86) #define KVM_CAP_REINJECT_CONTROL 24 +#endif +#if defined(CONFIG_X86)||defined(CONFIG_IA64) +#define KVM_CAP_IRQ_ROUTING 25 +#endif + +#ifdef KVM_CAP_IRQ_ROUTING + +struct kvm_irq_routing_irqchip { + __u32 irqchip; + __u32 pin; +}; + +/* gsi routing entry types */ +#define KVM_IRQ_ROUTING_IRQCHIP 1 + +struct kvm_irq_routing_entry { + __u32 gsi; + __u32 type; + __u32 flags; + __u32 pad; + union { + struct kvm_irq_routing_irqchip irqchip; + __u32 pad[8]; + } u; +}; + +struct kvm_irq_routing { + __u32 nr; + __u32 flags; + struct kvm_irq_routing_entry entries[0]; +}; + #endif /* @@ -430,6 +462,7 @@ struct kvm_trace_rec { _IOW(KVMIO, 0x68, struct kvm_coalesced_mmio_zone) #define KVM_ASSIGN_PCI_DEVICE _IOR(KVMIO, 0x69, \ struct kvm_assigned_pci_dev) +#define KVM_SET_GSI_ROUTING _IOW(KVMIO, 0x6a, struct kvm_irq_routing) #define KVM_ASSIGN_IRQ _IOR(KVMIO, 0x70, \ struct kvm_assigned_irq) #define KVM_REINJECT_CONTROL _IO(KVMIO, 0x71) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 99963f36a6d..ce285e01bd5 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -107,6 +107,19 @@ struct kvm_memory_slot { int user_alloc; }; +struct kvm_kernel_irq_routing_entry { + u32 gsi; + void (*set)(struct kvm_kernel_irq_routing_entry *e, + struct kvm *kvm, int level); + union { + struct { + unsigned irqchip; + unsigned pin; + } irqchip; + }; + struct list_head link; +}; + struct kvm { struct mutex lock; /* protects the vcpus array and APIC accesses */ spinlock_t mmu_lock; @@ -128,6 +141,7 @@ struct kvm { #endif #ifdef CONFIG_HAVE_KVM_IRQCHIP + struct list_head irq_routing; /* of kvm_kernel_irq_routing_entry */ struct hlist_head mask_notifier_list; #endif @@ -480,4 +494,21 @@ static inline int mmu_notifier_retry(struct kvm_vcpu *vcpu, unsigned long mmu_se } #endif +#ifdef CONFIG_HAVE_KVM_IRQCHIP + +#define KVM_MAX_IRQ_ROUTES 1024 + +int kvm_setup_default_irq_routing(struct kvm *kvm); +int kvm_set_irq_routing(struct kvm *kvm, + const struct kvm_irq_routing_entry *entries, + unsigned nr, + unsigned flags); +void kvm_free_irq_routing(struct kvm *kvm); + +#else + +static inline void kvm_free_irq_routing(struct kvm *kvm) {} + +#endif + #endif -- cgit v1.2.3 From 91b2ae773d3b168b763237fac33f75b13d891f20 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Mon, 19 Jan 2009 14:57:52 +0200 Subject: KVM: Avoid using CONFIG_ in userspace visible headers Kconfig symbols are not available in userspace, and are not stripped by headers-install. Avoid their use by adding #defines in to suit each architecture. Signed-off-by: Avi Kivity --- include/linux/kvm.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 7a5d73a8d4f..869462ca762 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -393,13 +393,13 @@ struct kvm_trace_rec { #ifdef __KVM_HAVE_USER_NMI #define KVM_CAP_USER_NMI 22 #endif -#if defined(CONFIG_X86) +#ifdef __KVM_HAVE_GUEST_DEBUG #define KVM_CAP_SET_GUEST_DEBUG 23 #endif -#if defined(CONFIG_X86) +#ifdef __KVM_HAVE_PIT #define KVM_CAP_REINJECT_CONTROL 24 #endif -#if defined(CONFIG_X86)||defined(CONFIG_IA64) +#ifdef __KVM_HAVE_IOAPIC #define KVM_CAP_IRQ_ROUTING 25 #endif -- cgit v1.2.3 From 44882eed2ebe7f75f8cdae5671ab1d6e0fa40dbc Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Tue, 27 Jan 2009 15:12:38 -0200 Subject: KVM: make irq ack notifications aware of routing table IRQ ack notifications assume an identity mapping between pin->gsi, which might not be the case with, for example, HPET. Translate before acking. Signed-off-by: Marcelo Tosatti Acked-by: Gleb Natapov --- include/linux/kvm_host.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index ce285e01bd5..c03a0a9a858 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -352,7 +352,7 @@ void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq, void kvm_fire_mask_notifiers(struct kvm *kvm, int irq, bool mask); void kvm_set_irq(struct kvm *kvm, int irq_source_id, int irq, int level); -void kvm_notify_acked_irq(struct kvm *kvm, unsigned gsi); +void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin); void kvm_register_irq_ack_notifier(struct kvm *kvm, struct kvm_irq_ack_notifier *kian); void kvm_unregister_irq_ack_notifier(struct kvm_irq_ack_notifier *kian); -- cgit v1.2.3 From 79950e1073150909619b7c0f9a39a2fea83a42d8 Mon Sep 17 00:00:00 2001 From: Sheng Yang Date: Tue, 10 Feb 2009 13:57:06 +0800 Subject: KVM: Use irq routing API for MSI Merge MSI userspace interface with IRQ routing table. Notice the API have been changed, and using IRQ routing table would be the only interface kvm-userspace supported. Signed-off-by: Sheng Yang Signed-off-by: Avi Kivity --- include/linux/kvm.h | 9 +++++++++ include/linux/kvm_host.h | 2 +- 2 files changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 869462ca762..2163b3dd36e 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -410,8 +410,16 @@ struct kvm_irq_routing_irqchip { __u32 pin; }; +struct kvm_irq_routing_msi { + __u32 address_lo; + __u32 address_hi; + __u32 data; + __u32 pad; +}; + /* gsi routing entry types */ #define KVM_IRQ_ROUTING_IRQCHIP 1 +#define KVM_IRQ_ROUTING_MSI 2 struct kvm_irq_routing_entry { __u32 gsi; @@ -420,6 +428,7 @@ struct kvm_irq_routing_entry { __u32 pad; union { struct kvm_irq_routing_irqchip irqchip; + struct kvm_irq_routing_msi msi; __u32 pad[8]; } u; }; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index c03a0a9a858..339eda3ca6e 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -116,6 +116,7 @@ struct kvm_kernel_irq_routing_entry { unsigned irqchip; unsigned pin; } irqchip; + struct msi_msg msi; }; struct list_head link; }; @@ -327,7 +328,6 @@ struct kvm_assigned_dev_kernel { int host_irq; bool host_irq_disabled; int guest_irq; - struct msi_msg guest_msi; #define KVM_ASSIGNED_DEV_GUEST_INTX (1 << 0) #define KVM_ASSIGNED_DEV_GUEST_MSI (1 << 1) #define KVM_ASSIGNED_DEV_HOST_INTX (1 << 8) -- cgit v1.2.3 From c807660407a695f390034e402edfe544a1d2e40c Mon Sep 17 00:00:00 2001 From: Gerd Hoffmann Date: Wed, 4 Feb 2009 17:52:04 +0100 Subject: KVM: Fix kvmclock on !constant_tsc boxes kvmclock currently falls apart on machines without constant tsc. This patch fixes it. Changes: * keep tsc frequency in a per-cpu variable. * handle kvmclock update using a new request flag, thus checking whenever we need an update each time we enter guest context. * use a cpufreq notifier to track frequency changes and force kvmclock updates. * send ipis to kick cpu out of guest context if needed to make sure the guest doesn't see stale values. Signed-off-by: Gerd Hoffmann Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 339eda3ca6e..18b4df8264c 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -37,6 +37,7 @@ #define KVM_REQ_PENDING_TIMER 5 #define KVM_REQ_UNHALT 6 #define KVM_REQ_MMU_SYNC 7 +#define KVM_REQ_KVMCLOCK_UPDATE 8 #define KVM_USERSPACE_IRQ_SOURCE_ID 0 -- cgit v1.2.3 From 4925663a079c77d95d8685228ad6675fc5639c8e Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Wed, 4 Feb 2009 17:28:14 +0200 Subject: KVM: Report IRQ injection status to userspace. IRQ injection status is either -1 (if there was no CPU found that should except the interrupt because IRQ was masked or ioapic was misconfigured or ...) or >= 0 in that case the number indicates to how many CPUs interrupt was injected. If the value is 0 it means that the interrupt was coalesced and probably should be reinjected. Signed-off-by: Gleb Natapov Signed-off-by: Avi Kivity --- include/linux/kvm.h | 7 ++++++- include/linux/kvm_host.h | 4 ++-- 2 files changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 2163b3dd36e..dd48225d182 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -48,7 +48,10 @@ struct kvm_irq_level { * For IA-64 (APIC model) IOAPIC0: irq 0-23; IOAPIC1: irq 24-47.. * For X86 (standard AT mode) PIC0/1: irq 0-15. IOAPIC0: 0-23.. */ - __u32 irq; + union { + __u32 irq; + __s32 status; + }; __u32 level; }; @@ -402,6 +405,7 @@ struct kvm_trace_rec { #ifdef __KVM_HAVE_IOAPIC #define KVM_CAP_IRQ_ROUTING 25 #endif +#define KVM_CAP_IRQ_INJECT_STATUS 26 #ifdef KVM_CAP_IRQ_ROUTING @@ -465,6 +469,7 @@ struct kvm_irq_routing { #define KVM_CREATE_PIT _IO(KVMIO, 0x64) #define KVM_GET_PIT _IOWR(KVMIO, 0x65, struct kvm_pit_state) #define KVM_SET_PIT _IOR(KVMIO, 0x66, struct kvm_pit_state) +#define KVM_IRQ_LINE_STATUS _IOWR(KVMIO, 0x67, struct kvm_irq_level) #define KVM_REGISTER_COALESCED_MMIO \ _IOW(KVMIO, 0x67, struct kvm_coalesced_mmio_zone) #define KVM_UNREGISTER_COALESCED_MMIO \ diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 18b4df8264c..894a56e365e 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -110,7 +110,7 @@ struct kvm_memory_slot { struct kvm_kernel_irq_routing_entry { u32 gsi; - void (*set)(struct kvm_kernel_irq_routing_entry *e, + int (*set)(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int level); union { struct { @@ -352,7 +352,7 @@ void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq, struct kvm_irq_mask_notifier *kimn); void kvm_fire_mask_notifiers(struct kvm *kvm, int irq, bool mask); -void kvm_set_irq(struct kvm *kvm, int irq_source_id, int irq, int level); +int kvm_set_irq(struct kvm *kvm, int irq_source_id, int irq, int level); void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin); void kvm_register_irq_ack_notifier(struct kvm *kvm, struct kvm_irq_ack_notifier *kian); -- cgit v1.2.3 From 2df8a40bccf5999261d0d3a82eac5a77678e61bd Mon Sep 17 00:00:00 2001 From: Weidong Han Date: Fri, 13 Feb 2009 10:50:56 +0800 Subject: KVM: define KVM_CAP_DEVICE_DEASSIGNMENT define KVM_CAP_DEVICE_DEASSIGNMENT and KVM_DEASSIGN_PCI_DEVICE for device deassignment. the ioctl has been already implemented in the commit: 0a920356748df4fb06e86c21c23d2ed6d31d37ad Acked-by: Mark McLoughlin Signed-off-by: Weidong Han Signed-off-by: Avi Kivity --- include/linux/kvm.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index dd48225d182..0d94b274c3a 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -406,6 +406,9 @@ struct kvm_trace_rec { #define KVM_CAP_IRQ_ROUTING 25 #endif #define KVM_CAP_IRQ_INJECT_STATUS 26 +#ifdef __KVM_HAVE_DEVICE_ASSIGNMENT +#define KVM_CAP_DEVICE_DEASSIGNMENT 27 +#endif #ifdef KVM_CAP_IRQ_ROUTING @@ -480,6 +483,8 @@ struct kvm_irq_routing { #define KVM_ASSIGN_IRQ _IOR(KVMIO, 0x70, \ struct kvm_assigned_irq) #define KVM_REINJECT_CONTROL _IO(KVMIO, 0x71) +#define KVM_DEASSIGN_PCI_DEVICE _IOR(KVMIO, 0x72, \ + struct kvm_assigned_pci_dev) /* * ioctls for vcpu fds -- cgit v1.2.3 From bc7a8660df62da3fb5cad025322eda75fbee8731 Mon Sep 17 00:00:00 2001 From: Sheng Yang Date: Tue, 17 Mar 2009 19:27:19 +0800 Subject: KVM: Correct deassign device ioctl to IOW It's IOR by mistake, so fix it before release. Signed-off-by: Sheng Yang Signed-off-by: Avi Kivity --- include/linux/kvm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 0d94b274c3a..311a073afe8 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -483,7 +483,7 @@ struct kvm_irq_routing { #define KVM_ASSIGN_IRQ _IOR(KVMIO, 0x70, \ struct kvm_assigned_irq) #define KVM_REINJECT_CONTROL _IO(KVMIO, 0x71) -#define KVM_DEASSIGN_PCI_DEVICE _IOR(KVMIO, 0x72, \ +#define KVM_DEASSIGN_PCI_DEVICE _IOW(KVMIO, 0x72, \ struct kvm_assigned_pci_dev) /* -- cgit v1.2.3 From 58c610bd1a3f50820e45a7c09ec0e44d2cda15dd Mon Sep 17 00:00:00 2001 From: Sheng Yang Date: Wed, 18 Mar 2009 15:33:05 +0800 Subject: intel-iommu: Snooping control support Snooping control enabled IOMMU to guarantee DMA cache coherency and thus reduce software effort (VMM) in maintaining effective memory type. Signed-off-by: Sheng Yang Signed-off-by: David Woodhouse --- include/linux/intel-iommu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index d2e3cbfba14..3ad89400493 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -123,7 +123,7 @@ static inline void dmar_writeq(void __iomem *addr, u64 val) #define ecap_eim_support(e) ((e >> 4) & 0x1) #define ecap_ir_support(e) ((e >> 3) & 0x1) #define ecap_max_handle_mask(e) ((e >> 20) & 0xf) - +#define ecap_sc_support(e) ((e >> 7) & 0x1) /* Snooping Control */ /* IOTLB_REG */ #define DMA_TLB_FLUSH_GRANU_OFFSET 60 -- cgit v1.2.3 From dbb9fd8630e95b6155aff658a2b5f80e95ca2bc6 Mon Sep 17 00:00:00 2001 From: Sheng Yang Date: Wed, 18 Mar 2009 15:33:06 +0800 Subject: iommu: Add domain_has_cap iommu_ops This iommu_op can tell if domain have a specific capability, like snooping control for Intel IOMMU, which can be used by other components of kernel to adjust the behaviour. Signed-off-by: Sheng Yang Signed-off-by: David Woodhouse --- include/linux/iommu.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 8a7bfb1b6ca..0cf3a4e43f2 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -28,6 +28,8 @@ struct iommu_domain { void *priv; }; +#define IOMMU_CAP_CACHE_COHERENCY 0x1 + struct iommu_ops { int (*domain_init)(struct iommu_domain *domain); void (*domain_destroy)(struct iommu_domain *domain); @@ -39,6 +41,8 @@ struct iommu_ops { size_t size); phys_addr_t (*iova_to_phys)(struct iommu_domain *domain, unsigned long iova); + int (*domain_has_cap)(struct iommu_domain *domain, + unsigned long cap); }; #ifdef CONFIG_IOMMU_API @@ -57,6 +61,8 @@ extern void iommu_unmap_range(struct iommu_domain *domain, unsigned long iova, size_t size); extern phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, unsigned long iova); +extern int iommu_domain_has_cap(struct iommu_domain *domain, + unsigned long cap); #else /* CONFIG_IOMMU_API */ @@ -107,6 +113,12 @@ static inline phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, return 0; } +static inline int domain_has_cap(struct iommu_domain *domain, + unsigned long cap) +{ + return 0; +} + #endif /* CONFIG_IOMMU_API */ #endif /* __LINUX_IOMMU_H */ -- cgit v1.2.3 From 9cf0669746be19a4906a6c48920060bcf54c708b Mon Sep 17 00:00:00 2001 From: Sheng Yang Date: Wed, 18 Mar 2009 15:33:07 +0800 Subject: intel-iommu: VT-d page table to support snooping control bit The user can request to enable snooping control through VT-d page table. Signed-off-by: Sheng Yang Signed-off-by: David Woodhouse --- include/linux/dma_remapping.h | 1 + include/linux/iommu.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma_remapping.h b/include/linux/dma_remapping.h index af1dab41674..1a455f1f86d 100644 --- a/include/linux/dma_remapping.h +++ b/include/linux/dma_remapping.h @@ -11,6 +11,7 @@ #define DMA_PTE_READ (1) #define DMA_PTE_WRITE (2) +#define DMA_PTE_SNP (1 << 11) struct intel_iommu; struct dmar_domain; diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 0cf3a4e43f2..3af4ffd591b 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -21,6 +21,7 @@ #define IOMMU_READ (1) #define IOMMU_WRITE (2) +#define IOMMU_CACHE (4) /* DMA cache coherency */ struct device; -- cgit v1.2.3 From f057f6cdf64175db1151b1f5d110e29904f119a1 Mon Sep 17 00:00:00 2001 From: Steven Whitehouse Date: Mon, 12 Jan 2009 10:43:39 +0000 Subject: GFS2: Merge lock_dlm module into GFS2 This is the big patch that I've been working on for some time now. There are many reasons for wanting to make this change such as: o Reducing overhead by eliminating duplicated fields between structures o Simplifcation of the code (reduces the code size by a fair bit) o The locking interface is now the DLM interface itself as proposed some time ago. o Fewer lookups of glocks when processing replies from the DLM o Fewer memory allocations/deallocations for each glock o Scope to do further optimisations in the future (but this patch is more than big enough for now!) Please note that (a) this patch relates to the lock_dlm module and not the DLM itself, that is still a separate module; and (b) that we retain the ability to build GFS2 as a standalone single node filesystem with out requiring the DLM. This patch needs a lot of testing, hence my keeping it I restarted my -git tree after the last merge window. That way, this has the maximum exposure before its merged. This is (modulo a few minor bug fixes) the same patch that I've been posting on and off the the last three months and its passed a number of different tests so far. Signed-off-by: Steven Whitehouse --- include/linux/lm_interface.h | 277 ------------------------------------------- 1 file changed, 277 deletions(-) delete mode 100644 include/linux/lm_interface.h (limited to 'include/linux') diff --git a/include/linux/lm_interface.h b/include/linux/lm_interface.h deleted file mode 100644 index 2ed8fa1b762..00000000000 --- a/include/linux/lm_interface.h +++ /dev/null @@ -1,277 +0,0 @@ -/* - * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. - */ - -#ifndef __LM_INTERFACE_DOT_H__ -#define __LM_INTERFACE_DOT_H__ - - -typedef void (*lm_callback_t) (void *ptr, unsigned int type, void *data); - -/* - * lm_mount() flags - * - * LM_MFLAG_SPECTATOR - * GFS is asking to join the filesystem's lockspace, but it doesn't want to - * modify the filesystem. The lock module shouldn't assign a journal to the FS - * mount. It shouldn't send recovery callbacks to the FS mount. If the node - * dies or withdraws, all locks can be wiped immediately. - * - * LM_MFLAG_CONV_NODROP - * Do not allow the dlm to internally resolve conversion deadlocks by demoting - * the lock to unlocked and then reacquiring it in the requested mode. Instead, - * it should cancel the request and return LM_OUT_CONV_DEADLK. - */ - -#define LM_MFLAG_SPECTATOR 0x00000001 -#define LM_MFLAG_CONV_NODROP 0x00000002 - -/* - * lm_lockstruct flags - * - * LM_LSFLAG_LOCAL - * The lock_nolock module returns LM_LSFLAG_LOCAL to GFS, indicating that GFS - * can make single-node optimizations. - */ - -#define LM_LSFLAG_LOCAL 0x00000001 - -/* - * lm_lockname types - */ - -#define LM_TYPE_RESERVED 0x00 -#define LM_TYPE_NONDISK 0x01 -#define LM_TYPE_INODE 0x02 -#define LM_TYPE_RGRP 0x03 -#define LM_TYPE_META 0x04 -#define LM_TYPE_IOPEN 0x05 -#define LM_TYPE_FLOCK 0x06 -#define LM_TYPE_PLOCK 0x07 -#define LM_TYPE_QUOTA 0x08 -#define LM_TYPE_JOURNAL 0x09 - -/* - * lm_lock() states - * - * SHARED is compatible with SHARED, not with DEFERRED or EX. - * DEFERRED is compatible with DEFERRED, not with SHARED or EX. - */ - -#define LM_ST_UNLOCKED 0 -#define LM_ST_EXCLUSIVE 1 -#define LM_ST_DEFERRED 2 -#define LM_ST_SHARED 3 - -/* - * lm_lock() flags - * - * LM_FLAG_TRY - * Don't wait to acquire the lock if it can't be granted immediately. - * - * LM_FLAG_TRY_1CB - * Send one blocking callback if TRY is set and the lock is not granted. - * - * LM_FLAG_NOEXP - * GFS sets this flag on lock requests it makes while doing journal recovery. - * These special requests should not be blocked due to the recovery like - * ordinary locks would be. - * - * LM_FLAG_ANY - * A SHARED request may also be granted in DEFERRED, or a DEFERRED request may - * also be granted in SHARED. The preferred state is whichever is compatible - * with other granted locks, or the specified state if no other locks exist. - * - * LM_FLAG_PRIORITY - * Override fairness considerations. Suppose a lock is held in a shared state - * and there is a pending request for the deferred state. A shared lock - * request with the priority flag would be allowed to bypass the deferred - * request and directly join the other shared lock. A shared lock request - * without the priority flag might be forced to wait until the deferred - * requested had acquired and released the lock. - */ - -#define LM_FLAG_TRY 0x00000001 -#define LM_FLAG_TRY_1CB 0x00000002 -#define LM_FLAG_NOEXP 0x00000004 -#define LM_FLAG_ANY 0x00000008 -#define LM_FLAG_PRIORITY 0x00000010 - -/* - * lm_lock() and lm_async_cb return flags - * - * LM_OUT_ST_MASK - * Masks the lower two bits of lock state in the returned value. - * - * LM_OUT_CACHEABLE - * The lock hasn't been released so GFS can continue to cache data for it. - * - * LM_OUT_CANCELED - * The lock request was canceled. - * - * LM_OUT_ASYNC - * The result of the request will be returned in an LM_CB_ASYNC callback. - * - * LM_OUT_CONV_DEADLK - * The lock request was canceled do to a conversion deadlock. - */ - -#define LM_OUT_ST_MASK 0x00000003 -#define LM_OUT_CANCELED 0x00000008 -#define LM_OUT_ASYNC 0x00000080 -#define LM_OUT_ERROR 0x00000100 - -/* - * lm_callback_t types - * - * LM_CB_NEED_E LM_CB_NEED_D LM_CB_NEED_S - * Blocking callback, a remote node is requesting the given lock in - * EXCLUSIVE, DEFERRED, or SHARED. - * - * LM_CB_NEED_RECOVERY - * The given journal needs to be recovered. - * - * LM_CB_ASYNC - * The given lock has been granted. - */ - -#define LM_CB_NEED_E 257 -#define LM_CB_NEED_D 258 -#define LM_CB_NEED_S 259 -#define LM_CB_NEED_RECOVERY 260 -#define LM_CB_ASYNC 262 - -/* - * lm_recovery_done() messages - */ - -#define LM_RD_GAVEUP 308 -#define LM_RD_SUCCESS 309 - - -struct lm_lockname { - u64 ln_number; - unsigned int ln_type; -}; - -#define lm_name_equal(name1, name2) \ - (((name1)->ln_number == (name2)->ln_number) && \ - ((name1)->ln_type == (name2)->ln_type)) \ - -struct lm_async_cb { - struct lm_lockname lc_name; - int lc_ret; -}; - -struct lm_lockstruct; - -struct lm_lockops { - const char *lm_proto_name; - - /* - * Mount/Unmount - */ - - int (*lm_mount) (char *table_name, char *host_data, - lm_callback_t cb, void *cb_data, - unsigned int min_lvb_size, int flags, - struct lm_lockstruct *lockstruct, - struct kobject *fskobj); - - void (*lm_others_may_mount) (void *lockspace); - - void (*lm_unmount) (void *lockspace); - - void (*lm_withdraw) (void *lockspace); - - /* - * Lock oriented operations - */ - - int (*lm_get_lock) (void *lockspace, struct lm_lockname *name, void **lockp); - - void (*lm_put_lock) (void *lock); - - unsigned int (*lm_lock) (void *lock, unsigned int cur_state, - unsigned int req_state, unsigned int flags); - - unsigned int (*lm_unlock) (void *lock, unsigned int cur_state); - - void (*lm_cancel) (void *lock); - - int (*lm_hold_lvb) (void *lock, char **lvbp); - void (*lm_unhold_lvb) (void *lock, char *lvb); - - /* - * Posix Lock oriented operations - */ - - int (*lm_plock_get) (void *lockspace, struct lm_lockname *name, - struct file *file, struct file_lock *fl); - - int (*lm_plock) (void *lockspace, struct lm_lockname *name, - struct file *file, int cmd, struct file_lock *fl); - - int (*lm_punlock) (void *lockspace, struct lm_lockname *name, - struct file *file, struct file_lock *fl); - - /* - * Client oriented operations - */ - - void (*lm_recovery_done) (void *lockspace, unsigned int jid, - unsigned int message); - - struct module *lm_owner; -}; - -/* - * lm_mount() return values - * - * ls_jid - the journal ID this node should use - * ls_first - this node is the first to mount the file system - * ls_lvb_size - size in bytes of lock value blocks - * ls_lockspace - lock module's context for this file system - * ls_ops - lock module's functions - * ls_flags - lock module features - */ - -struct lm_lockstruct { - unsigned int ls_jid; - unsigned int ls_first; - unsigned int ls_lvb_size; - void *ls_lockspace; - const struct lm_lockops *ls_ops; - int ls_flags; -}; - -/* - * Lock module bottom interface. A lock module makes itself available to GFS - * with these functions. - */ - -int gfs2_register_lockproto(const struct lm_lockops *proto); -void gfs2_unregister_lockproto(const struct lm_lockops *proto); - -/* - * Lock module top interface. GFS calls these functions when mounting or - * unmounting a file system. - */ - -int gfs2_mount_lockproto(char *proto_name, char *table_name, char *host_data, - lm_callback_t cb, void *cb_data, - unsigned int min_lvb_size, int flags, - struct lm_lockstruct *lockstruct, - struct kobject *fskobj); - -void gfs2_unmount_lockproto(struct lm_lockstruct *lockstruct); - -void gfs2_withdraw_lockproto(struct lm_lockstruct *lockstruct); - -#endif /* __LM_INTERFACE_DOT_H__ */ - -- cgit v1.2.3 From 32ca163c9cdb33151d79e95a7cf244f62b5d4418 Mon Sep 17 00:00:00 2001 From: Petros Koutoupis Date: Tue, 10 Mar 2009 08:25:54 +0100 Subject: block: genhd.h comment needs updating The include/linux/genhd.h file, on line 338-352 declares some function prototypes in which the comment on line 338 states that the definition of these prototypes are to be found at drivers/block/genhd.c. The problem is that genhd.c has been relocated to block/genhd.c. See attached patch to correct this minor cosmetic typo. Signed-off-by: Petros Koutoupis Signed-off-by: Jens Axboe --- include/linux/genhd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 16948eaecae..56946b21ab7 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -336,7 +336,7 @@ static inline void part_dec_in_flight(struct hd_struct *part) /* drivers/block/ll_rw_blk.c */ extern void part_round_stats(int cpu, struct hd_struct *part); -/* drivers/block/genhd.c */ +/* block/genhd.c */ extern int get_blkdev_list(char *, int); extern void add_disk(struct gendisk *disk); extern void del_gendisk(struct gendisk *gp); -- cgit v1.2.3 From 6d2a78e783416ba99e36beb1d4395b785b34e867 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Tue, 10 Mar 2009 08:27:39 +0100 Subject: block: add private bio_set for bio integrity allocations The integrity bio allocation needs its own bio_set to avoid violating the mempool allocation rules and risking deadlocks. Signed-off-by: Martin K. Petersen Signed-off-by: Jens Axboe --- include/linux/bio.h | 18 ++++-------------- 1 file changed, 4 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index d8bd43bfdcf..b05b1d4d17d 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -426,9 +426,6 @@ struct bio_set { unsigned int front_pad; mempool_t *bio_pool; -#if defined(CONFIG_BLK_DEV_INTEGRITY) - mempool_t *bio_integrity_pool; -#endif mempool_t *bvec_pool; }; @@ -519,9 +516,8 @@ static inline int bio_has_data(struct bio *bio) #define bio_integrity(bio) (bio->bi_integrity != NULL) -extern struct bio_integrity_payload *bio_integrity_alloc_bioset(struct bio *, gfp_t, unsigned int, struct bio_set *); extern struct bio_integrity_payload *bio_integrity_alloc(struct bio *, gfp_t, unsigned int); -extern void bio_integrity_free(struct bio *, struct bio_set *); +extern void bio_integrity_free(struct bio *); extern int bio_integrity_add_page(struct bio *, struct page *, unsigned int, unsigned int); extern int bio_integrity_enabled(struct bio *bio); extern int bio_integrity_set_tag(struct bio *, void *, unsigned int); @@ -531,27 +527,21 @@ extern void bio_integrity_endio(struct bio *, int); extern void bio_integrity_advance(struct bio *, unsigned int); extern void bio_integrity_trim(struct bio *, unsigned int, unsigned int); extern void bio_integrity_split(struct bio *, struct bio_pair *, int); -extern int bio_integrity_clone(struct bio *, struct bio *, gfp_t, struct bio_set *); -extern int bioset_integrity_create(struct bio_set *, int); -extern void bioset_integrity_free(struct bio_set *); -extern void bio_integrity_init_slab(void); +extern int bio_integrity_clone(struct bio *, struct bio *, gfp_t); #else /* CONFIG_BLK_DEV_INTEGRITY */ #define bio_integrity(a) (0) -#define bioset_integrity_create(a, b) (0) #define bio_integrity_prep(a) (0) #define bio_integrity_enabled(a) (0) -#define bio_integrity_clone(a, b, c,d ) (0) -#define bioset_integrity_free(a) do { } while (0) -#define bio_integrity_free(a, b) do { } while (0) +#define bio_integrity_clone(a, b, c) (0) +#define bio_integrity_free(a) do { } while (0) #define bio_integrity_endio(a, b) do { } while (0) #define bio_integrity_advance(a, b) do { } while (0) #define bio_integrity_trim(a, b, c) do { } while (0) #define bio_integrity_split(a, b, c) do { } while (0) #define bio_integrity_set_tag(a, b, c) do { } while (0) #define bio_integrity_get_tag(a, b, c) do { } while (0) -#define bio_integrity_init_slab(a) do { } while (0) #endif /* CONFIG_BLK_DEV_INTEGRITY */ -- cgit v1.2.3 From d399228646e26db315d6233bed65ec9d08c57f57 Mon Sep 17 00:00:00 2001 From: Petros Koutoupis Date: Wed, 11 Mar 2009 10:49:35 +0100 Subject: block: genhd.h cleanup patch In include/linux/genhd.h: Line 335 has a comment that needs to be updated from: /* drivers/block/ll_rw_blk.c */ to /* block/blk-core.c */. Also as of kernel 2.6.16, the function definition for get_blkdev_list was removed from block/genhd.c but the function declaration is still present on line 339. This patch addresses both those fixes, by updating the comment and removing the declaration. Signed-off-by: Petros Koutoupis Signed-off-by: Jens Axboe --- include/linux/genhd.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 56946b21ab7..634c53028fb 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -333,11 +333,10 @@ static inline void part_dec_in_flight(struct hd_struct *part) part_to_disk(part)->part0.in_flight--; } -/* drivers/block/ll_rw_blk.c */ +/* block/blk-core.c */ extern void part_round_stats(int cpu, struct hd_struct *part); /* block/genhd.c */ -extern int get_blkdev_list(char *, int); extern void add_disk(struct gendisk *disk); extern void del_gendisk(struct gendisk *gp); extern void unlink_gendisk(struct gendisk *gp); -- cgit v1.2.3 From 05378940caf979a8655c18b18a17213dcfa52412 Mon Sep 17 00:00:00 2001 From: Boaz Harrosh Date: Tue, 24 Mar 2009 12:23:40 +0100 Subject: bsg: add support for tail queuing Currently inherited from sg.c bsg will submit asynchronous request at the head-of-the-queue, (using "at_head" set in the call to blk_execute_rq_nowait()). This is bad in situation where the queues are full, requests will execute out of order, and can cause starvation of the first submitted requests. The sg_io_v4->flags member is used and a bit is allocated to denote the Q_AT_TAIL. Zero is to queue at_head as before, to be compatible with old code at the write/read path. SG_IO code path behavior was changed so to be the same as write/read behavior. SG_IO was very rarely used and breaking compatibility with it is OK at this stage. sg_io_hdr at sg.h also has a flags member and uses 3 bits from the first nibble and one bit from the last nibble. Even though none of these bits are supported by bsg, The second nibble is allocated for use by bsg. Just in case. Signed-off-by: Boaz Harrosh CC: Douglas Gilbert Signed-off-by: Jens Axboe --- include/linux/bsg.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bsg.h b/include/linux/bsg.h index cf0303a6061..3f0c64ace42 100644 --- a/include/linux/bsg.h +++ b/include/linux/bsg.h @@ -7,6 +7,14 @@ #define BSG_SUB_PROTOCOL_SCSI_TMF 1 #define BSG_SUB_PROTOCOL_SCSI_TRANSPORT 2 +/* + * For flags member below + * sg.h sg_io_hdr also has bits defined for it's flags member. However + * none of these bits are implemented/used by bsg. The bits below are + * allocated to not conflict with sg.h ones anyway. + */ +#define BSG_FLAG_Q_AT_TAIL 0x10 /* default, == 0 at this bit, is Q_AT_HEAD */ + struct sg_io_v4 { __s32 guard; /* [i] 'Q' to differentiate from v3 */ __u32 protocol; /* [i] 0 -> SCSI , .... */ -- cgit v1.2.3 From bf8e3355ec8f4e472f9841e94203cd759b45226e Mon Sep 17 00:00:00 2001 From: Stefan Richter Date: Fri, 5 Dec 2008 22:43:41 +0100 Subject: firewire: cdev: documentation fixlet Reported-by: Jay Fenlason Signed-off-by: Stefan Richter --- include/linux/firewire-cdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/firewire-cdev.h b/include/linux/firewire-cdev.h index 4d078e99c01..899ef279f5b 100644 --- a/include/linux/firewire-cdev.h +++ b/include/linux/firewire-cdev.h @@ -229,7 +229,7 @@ struct fw_cdev_get_info { * Send a request to the device. This ioctl implements all outgoing requests. * Both quadlet and block request specify the payload as a pointer to the data * in the @data field. Once the transaction completes, the kernel writes an - * &fw_cdev_event_request event back. The @closure field is passed back to + * &fw_cdev_event_response event back. The @closure field is passed back to * user space in the response event. */ struct fw_cdev_send_request { -- cgit v1.2.3 From 632321ecd99bf85c982a75f8329b4ecbb95b3a8f Mon Sep 17 00:00:00 2001 From: Stefan Richter Date: Fri, 2 Jan 2009 12:47:13 +0100 Subject: firewire: cdev: fix documentation of FW_CDEV_IOC_GET_INFO The FW_CDEV_IOC_GET_INFO ioctl looks at client->device->config_rom, not at the local node's config ROM. We could fix the implementation or the documentation. I believe the way how it is currently implemented is more useful than the way how it is currently documented. In fact, libdc1394 uses the ABI already as implemented, not as documented. Hence let's change the documentation. Signed-off-by: Stefan Richter --- include/linux/firewire-cdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/firewire-cdev.h b/include/linux/firewire-cdev.h index 899ef279f5b..86c8ff5326f 100644 --- a/include/linux/firewire-cdev.h +++ b/include/linux/firewire-cdev.h @@ -201,7 +201,7 @@ union fw_cdev_event { * case, @rom_length is updated with the actual length of the * configuration ROM. * @rom: If non-zero, address of a buffer to be filled by a copy of the - * local node's configuration ROM + * device's configuration ROM * @bus_reset: If non-zero, address of a buffer to be filled by a * &struct fw_cdev_event_bus_reset with the current state * of the bus. This does not cause a bus reset to happen. -- cgit v1.2.3 From b1bda4cdc2037447bd66753bf5ccab66d91b0b59 Mon Sep 17 00:00:00 2001 From: "Jay Fenlason, Stefan Richter" Date: Sun, 4 Jan 2009 16:23:29 +0100 Subject: firewire: cdev: add ioctls for isochronous resource management Based on Date: Tue, 18 Nov 2008 11:41:27 -0500 From: Jay Fenlason Subject: [Patch V4] Add ISO resource management support with several changes to the ABI and implementation. Only the part of the ABI which enables auto-reallocation and auto-deallocation is included here. This implements ioctls for kernel-assisted allocation of isochronous channels and isochronous bandwidth. The benefits are: - The client does not have to have write access to the /dev/fw* device corresponding to the IRM. - The client does not have to perform reallocation after bus resets. - Channel and bandwidth are deallocated by the kernel if the file is closed before the client deallocated the resources. Thus resources are released even if the client crashes. It is anticipated that future in-kernel code (firewire-core IRM code; the firewire port of firedtv), will use the fw-iso.c portions of this code too. Signed-off-by: Stefan Richter Tested-by: David Moore --- include/linux/firewire-cdev.h | 100 ++++++++++++++++++++++++++++++++++++------ 1 file changed, 87 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/firewire-cdev.h b/include/linux/firewire-cdev.h index 86c8ff5326f..25b96dd0574 100644 --- a/include/linux/firewire-cdev.h +++ b/include/linux/firewire-cdev.h @@ -25,10 +25,12 @@ #include #include -#define FW_CDEV_EVENT_BUS_RESET 0x00 -#define FW_CDEV_EVENT_RESPONSE 0x01 -#define FW_CDEV_EVENT_REQUEST 0x02 -#define FW_CDEV_EVENT_ISO_INTERRUPT 0x03 +#define FW_CDEV_EVENT_BUS_RESET 0x00 +#define FW_CDEV_EVENT_RESPONSE 0x01 +#define FW_CDEV_EVENT_REQUEST 0x02 +#define FW_CDEV_EVENT_ISO_INTERRUPT 0x03 +#define FW_CDEV_EVENT_ISO_RESOURCE_ALLOCATED 0x04 +#define FW_CDEV_EVENT_ISO_RESOURCE_DEALLOCATED 0x05 /** * struct fw_cdev_event_common - Common part of all fw_cdev_event_ types @@ -146,6 +148,37 @@ struct fw_cdev_event_iso_interrupt { __u32 header[0]; }; +/** + * struct fw_cdev_event_iso_resource - Iso resources were allocated or freed + * @closure: See &fw_cdev_event_common; + * set by %FW_CDEV_IOC_ALLOCATE_ISO_RESOURCE ioctl + * @type: %FW_CDEV_EVENT_ISO_RESOURCE_ALLOCATED or + * %FW_CDEV_EVENT_ISO_RESOURCE_DEALLOCATED + * @handle: Reference by which an allocated resource can be deallocated + * @channel: Isochronous channel which was (de)allocated, if any + * @bandwidth: Bandwidth allocation units which were (de)allocated, if any + * @channels_available: Last known availability of channels + * @bandwidth_available: Last known availability of bandwidth + * + * An %FW_CDEV_EVENT_ISO_RESOURCE_ALLOCATED event is sent after an isochronous + * resource was allocated at the IRM. The client has to check @channel and + * @bandwidth for whether the allocation actually succeeded. + * + * @channel is <0 if no channel was allocated. + * @bandwidth is 0 if no bandwidth was allocated. + * + * An %FW_CDEV_EVENT_ISO_RESOURCE_DEALLOCATED event is sent after an isochronous + * resource was deallocated at the IRM. It is also sent when automatic + * reallocation after a bus reset failed. + */ +struct fw_cdev_event_iso_resource { + __u64 closure; + __u32 type; + __u32 handle; + __s32 channel; + __s32 bandwidth; +}; + /** * union fw_cdev_event - Convenience union of fw_cdev_event_ types * @common: Valid for all types @@ -153,6 +186,9 @@ struct fw_cdev_event_iso_interrupt { * @response: Valid if @common.type == %FW_CDEV_EVENT_RESPONSE * @request: Valid if @common.type == %FW_CDEV_EVENT_REQUEST * @iso_interrupt: Valid if @common.type == %FW_CDEV_EVENT_ISO_INTERRUPT + * @iso_resource: Valid if @common.type == + * %FW_CDEV_EVENT_ISO_RESOURCE_ALLOCATED or + * %FW_CDEV_EVENT_ISO_RESOURCE_DEALLOCATED * * Convenience union for userspace use. Events could be read(2) into an * appropriately aligned char buffer and then cast to this union for further @@ -163,13 +199,15 @@ struct fw_cdev_event_iso_interrupt { * not fit will be discarded so that the next read(2) will return a new event. */ union fw_cdev_event { - struct fw_cdev_event_common common; - struct fw_cdev_event_bus_reset bus_reset; - struct fw_cdev_event_response response; - struct fw_cdev_event_request request; - struct fw_cdev_event_iso_interrupt iso_interrupt; + struct fw_cdev_event_common common; + struct fw_cdev_event_bus_reset bus_reset; + struct fw_cdev_event_response response; + struct fw_cdev_event_request request; + struct fw_cdev_event_iso_interrupt iso_interrupt; + struct fw_cdev_event_iso_resource iso_resource; }; +/* available since kernel version 2.6.22 */ #define FW_CDEV_IOC_GET_INFO _IOWR('#', 0x00, struct fw_cdev_get_info) #define FW_CDEV_IOC_SEND_REQUEST _IOW('#', 0x01, struct fw_cdev_send_request) #define FW_CDEV_IOC_ALLOCATE _IOWR('#', 0x02, struct fw_cdev_allocate) @@ -178,13 +216,18 @@ union fw_cdev_event { #define FW_CDEV_IOC_INITIATE_BUS_RESET _IOW('#', 0x05, struct fw_cdev_initiate_bus_reset) #define FW_CDEV_IOC_ADD_DESCRIPTOR _IOWR('#', 0x06, struct fw_cdev_add_descriptor) #define FW_CDEV_IOC_REMOVE_DESCRIPTOR _IOW('#', 0x07, struct fw_cdev_remove_descriptor) - #define FW_CDEV_IOC_CREATE_ISO_CONTEXT _IOWR('#', 0x08, struct fw_cdev_create_iso_context) #define FW_CDEV_IOC_QUEUE_ISO _IOWR('#', 0x09, struct fw_cdev_queue_iso) #define FW_CDEV_IOC_START_ISO _IOW('#', 0x0a, struct fw_cdev_start_iso) #define FW_CDEV_IOC_STOP_ISO _IOW('#', 0x0b, struct fw_cdev_stop_iso) + +/* available since kernel version 2.6.24 */ #define FW_CDEV_IOC_GET_CYCLE_TIMER _IOR('#', 0x0c, struct fw_cdev_get_cycle_timer) +/* available since kernel version 2.6.30 */ +#define FW_CDEV_IOC_ALLOCATE_ISO_RESOURCE _IOWR('#', 0x0d, struct fw_cdev_allocate_iso_resource) +#define FW_CDEV_IOC_DEALLOCATE_ISO_RESOURCE _IOW('#', 0x0e, struct fw_cdev_deallocate) + /* FW_CDEV_VERSION History * * 1 Feb 18, 2007: Initial version. @@ -284,9 +327,9 @@ struct fw_cdev_allocate { }; /** - * struct fw_cdev_deallocate - Free an address range allocation - * @handle: Handle to the address range, as returned by the kernel when the - * range was allocated + * struct fw_cdev_deallocate - Free a CSR address range or isochronous resource + * @handle: Handle to the address range or iso resource, as returned by the + * kernel when the range or resource was allocated */ struct fw_cdev_deallocate { __u32 handle; @@ -479,4 +522,35 @@ struct fw_cdev_get_cycle_timer { __u32 cycle_timer; }; +/** + * struct fw_cdev_allocate_iso_resource - Allocate a channel or bandwidth + * @closure: Passed back to userspace in correponding iso resource events + * @channels: Isochronous channels of which one is to be allocated + * @bandwidth: Isochronous bandwidth units to be allocated + * @handle: Handle to the allocation, written by the kernel + * + * The %FW_CDEV_IOC_ALLOCATE_ISO_RESOURCE ioctl initiates allocation of an + * isochronous channel and/or of isochronous bandwidth at the isochronous + * resource manager (IRM). Only one of the channels specified in @channels is + * allocated. An %FW_CDEV_EVENT_ISO_RESOURCE_ALLOCATED is sent after + * communication with the IRM, indicating success or failure in the event data. + * The kernel will automatically reallocate the resources after bus resets. + * Should a reallocation fail, an %FW_CDEV_EVENT_ISO_RESOURCE_DEALLOCATED event + * will be sent. The kernel will also automatically deallocate the resources + * when the file descriptor is closed. + * + * @channels is a host-endian bitfield with the most significant bit + * representing channel 0 and the least significant bit representing channel 63: + * 1ULL << (63 - c) + * + * @bandwidth is expressed in bandwidth allocation units, i.e. the time to send + * one quadlet of data (payload or header data) at speed S1600. + */ +struct fw_cdev_allocate_iso_resource { + __u64 closure; + __u64 channels; + __u32 bandwidth; + __u32 handle; +}; + #endif /* _LINUX_FIREWIRE_CDEV_H */ -- cgit v1.2.3 From 1ec3c0269d7196118cc7c403654ca5f19ef4d584 Mon Sep 17 00:00:00 2001 From: Stefan Richter Date: Sun, 4 Jan 2009 16:23:29 +0100 Subject: firewire: cdev: add ioctls for manual iso resource management This adds ioctls for allocation and deallocation of a channel or/and bandwidth without auto-reallocation and without auto-deallocation. The benefit of these ioctls is that libraw1394-style isochronous resource management can be implemented without write access to the IRM's character device file. Signed-off-by: Stefan Richter --- include/linux/firewire-cdev.h | 42 ++++++++++++++++++++++++++++++++---------- 1 file changed, 32 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/firewire-cdev.h b/include/linux/firewire-cdev.h index 25b96dd0574..08ca838a727 100644 --- a/include/linux/firewire-cdev.h +++ b/include/linux/firewire-cdev.h @@ -151,7 +151,7 @@ struct fw_cdev_event_iso_interrupt { /** * struct fw_cdev_event_iso_resource - Iso resources were allocated or freed * @closure: See &fw_cdev_event_common; - * set by %FW_CDEV_IOC_ALLOCATE_ISO_RESOURCE ioctl + * set by %FW_CDEV_IOC_(DE)ALLOCATE_ISO_RESOURCE(_ONCE) ioctl * @type: %FW_CDEV_EVENT_ISO_RESOURCE_ALLOCATED or * %FW_CDEV_EVENT_ISO_RESOURCE_DEALLOCATED * @handle: Reference by which an allocated resource can be deallocated @@ -164,12 +164,12 @@ struct fw_cdev_event_iso_interrupt { * resource was allocated at the IRM. The client has to check @channel and * @bandwidth for whether the allocation actually succeeded. * - * @channel is <0 if no channel was allocated. - * @bandwidth is 0 if no bandwidth was allocated. - * * An %FW_CDEV_EVENT_ISO_RESOURCE_DEALLOCATED event is sent after an isochronous * resource was deallocated at the IRM. It is also sent when automatic * reallocation after a bus reset failed. + * + * @channel is <0 if no channel was (de)allocated or if reallocation failed. + * @bandwidth is 0 if no bandwidth was (de)allocated or if reallocation failed. */ struct fw_cdev_event_iso_resource { __u64 closure; @@ -225,8 +225,10 @@ union fw_cdev_event { #define FW_CDEV_IOC_GET_CYCLE_TIMER _IOR('#', 0x0c, struct fw_cdev_get_cycle_timer) /* available since kernel version 2.6.30 */ -#define FW_CDEV_IOC_ALLOCATE_ISO_RESOURCE _IOWR('#', 0x0d, struct fw_cdev_allocate_iso_resource) -#define FW_CDEV_IOC_DEALLOCATE_ISO_RESOURCE _IOW('#', 0x0e, struct fw_cdev_deallocate) +#define FW_CDEV_IOC_ALLOCATE_ISO_RESOURCE _IOWR('#', 0x0d, struct fw_cdev_allocate_iso_resource) +#define FW_CDEV_IOC_DEALLOCATE_ISO_RESOURCE _IOW('#', 0x0e, struct fw_cdev_deallocate) +#define FW_CDEV_IOC_ALLOCATE_ISO_RESOURCE_ONCE _IOW('#', 0x0f, struct fw_cdev_allocate_iso_resource) +#define FW_CDEV_IOC_DEALLOCATE_ISO_RESOURCE_ONCE _IOW('#', 0x10, struct fw_cdev_allocate_iso_resource) /* FW_CDEV_VERSION History * @@ -523,11 +525,12 @@ struct fw_cdev_get_cycle_timer { }; /** - * struct fw_cdev_allocate_iso_resource - Allocate a channel or bandwidth + * struct fw_cdev_allocate_iso_resource - (De)allocate a channel or bandwidth * @closure: Passed back to userspace in correponding iso resource events - * @channels: Isochronous channels of which one is to be allocated - * @bandwidth: Isochronous bandwidth units to be allocated - * @handle: Handle to the allocation, written by the kernel + * @channels: Isochronous channels of which one is to be (de)allocated + * @bandwidth: Isochronous bandwidth units to be (de)allocated + * @handle: Handle to the allocation, written by the kernel (only valid in + * case of %FW_CDEV_IOC_ALLOCATE_ISO_RESOURCE ioctls) * * The %FW_CDEV_IOC_ALLOCATE_ISO_RESOURCE ioctl initiates allocation of an * isochronous channel and/or of isochronous bandwidth at the isochronous @@ -539,6 +542,25 @@ struct fw_cdev_get_cycle_timer { * will be sent. The kernel will also automatically deallocate the resources * when the file descriptor is closed. * + * The %FW_CDEV_IOC_DEALLOCATE_ISO_RESOURCE ioctl can be used to initiate + * deallocation of resources which were allocated as described above. + * An %FW_CDEV_EVENT_ISO_RESOURCE_DEALLOCATED event concludes this operation. + * + * The %FW_CDEV_IOC_ALLOCATE_ISO_RESOURCE_ONCE ioctl is a variant of allocation + * without automatic re- or deallocation. + * An %FW_CDEV_EVENT_ISO_RESOURCE_ALLOCATED event concludes this operation, + * indicating success or failure in its data. + * + * The %FW_CDEV_IOC_DEALLOCATE_ISO_RESOURCE_ONCE ioctl works like + * %FW_CDEV_IOC_ALLOCATE_ISO_RESOURCE_ONCE except that resources are freed + * instead of allocated. At most one channel may be specified in this ioctl. + * An %FW_CDEV_EVENT_ISO_RESOURCE_DEALLOCATED event concludes this operation. + * + * To summarize, %FW_CDEV_IOC_DEALLOCATE_ISO_RESOURCE allocates iso resources + * for the lifetime of the fd or handle. + * In contrast, %FW_CDEV_IOC_ALLOCATE_ISO_RESOURCE_ONCE allocates iso resources + * for the duration of a bus generation. + * * @channels is a host-endian bitfield with the most significant bit * representing channel 0 and the least significant bit representing channel 63: * 1ULL << (63 - c) -- cgit v1.2.3 From 33580a3ef5ba3bc0ee1b520df82a24bb37ce28f0 Mon Sep 17 00:00:00 2001 From: Stefan Richter Date: Sun, 4 Jan 2009 16:23:29 +0100 Subject: firewire: cdev: add ioctl to query maximum transmission speed While the speed of asynchronous transactions is automatically chosen by the kernel, the speed of isochronous streams has to be chosen by the initiating client. In case of 1394a bus topologies, the maximum possible speed could be figured out with some effort by evaluation of the remote node's link speed field in the config ROM, the local node's link speed field, and the PHY speeds and topologic information in the local node's or IRM's topology map CSR. However, this does not work in case of 1394b buses. Hence add an ioctl to export the maximum speed which the kernel already determined. Signed-off-by: Stefan Richter --- include/linux/firewire-cdev.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/firewire-cdev.h b/include/linux/firewire-cdev.h index 08ca838a727..f819c102695 100644 --- a/include/linux/firewire-cdev.h +++ b/include/linux/firewire-cdev.h @@ -229,6 +229,7 @@ union fw_cdev_event { #define FW_CDEV_IOC_DEALLOCATE_ISO_RESOURCE _IOW('#', 0x0e, struct fw_cdev_deallocate) #define FW_CDEV_IOC_ALLOCATE_ISO_RESOURCE_ONCE _IOW('#', 0x0f, struct fw_cdev_allocate_iso_resource) #define FW_CDEV_IOC_DEALLOCATE_ISO_RESOURCE_ONCE _IOW('#', 0x10, struct fw_cdev_allocate_iso_resource) +#define FW_CDEV_IOC_GET_SPEED _IOR('#', 0x11, struct fw_cdev_get_speed) /* FW_CDEV_VERSION History * @@ -575,4 +576,13 @@ struct fw_cdev_allocate_iso_resource { __u32 handle; }; +/** + * struct fw_cdev_get_speed - Query maximum speed to or from this device + * @max_speed: Speed code; minimum of the device's link speed, the local node's + * link speed, and all PHY port speeds between the two links + */ +struct fw_cdev_get_speed { + __u32 max_speed; +}; + #endif /* _LINUX_FIREWIRE_CDEV_H */ -- cgit v1.2.3 From acfe8333572cad5dc70fce18ac966be0446548d7 Mon Sep 17 00:00:00 2001 From: "Jay Fenlason, Stefan Richter" Date: Sun, 4 Jan 2009 16:23:29 +0100 Subject: firewire: cdev: add ioctl for broadcast write requests Write transactions to the broadcast node ID are a convenient way to trigger functions of multiple nodes at once. IIDC is a protocol which can make use of this if multiple cameras with same command_regs_base are connected at the same bus. Based on Date: Wed, 10 Sep 2008 11:32:16 -0400 From: Jay Fenlason Subject: [patch] SEND_BROADCAST_REQUEST Changes: ioctl_send_request() and ioctl_send_broadcast_request() now share code. Broadcast speed corrected to S100. Check for proper tcode. Signed-off-by: Stefan Richter --- include/linux/firewire-cdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/firewire-cdev.h b/include/linux/firewire-cdev.h index f819c102695..340a78502bc 100644 --- a/include/linux/firewire-cdev.h +++ b/include/linux/firewire-cdev.h @@ -230,6 +230,7 @@ union fw_cdev_event { #define FW_CDEV_IOC_ALLOCATE_ISO_RESOURCE_ONCE _IOW('#', 0x0f, struct fw_cdev_allocate_iso_resource) #define FW_CDEV_IOC_DEALLOCATE_ISO_RESOURCE_ONCE _IOW('#', 0x10, struct fw_cdev_allocate_iso_resource) #define FW_CDEV_IOC_GET_SPEED _IOR('#', 0x11, struct fw_cdev_get_speed) +#define FW_CDEV_IOC_SEND_BROADCAST_REQUEST _IOW('#', 0x12, struct fw_cdev_send_request) /* FW_CDEV_VERSION History * -- cgit v1.2.3 From 77258da403be4cfce84b6abcdb515ad0bd1f92f1 Mon Sep 17 00:00:00 2001 From: Stefan Richter Date: Wed, 7 Jan 2009 20:14:53 +0100 Subject: firewire: cdev: increment fw_cdev_version, update documentation Necessary due to Date: Tue, 22 Jul 2008 23:23:40 -0700 From: David Moore Subject: firewire: Include iso timestamp in headers when header_size > 4 Side note: The lack of upwards compatibility sounds worse than it is. All existing client implementations, libraw1394 and libdc1394, set header_size = 4. And since the ABI v1 behaviour does not offer any advantages over the new behaviour, we deliberately do not provide the old behaviour anymore. Also add documentation about the format of fw_cdev_get_cycle_timer which may be used in conjunction with the timestamp of iso packets but has a different format. Signed-off-by: Stefan Richter --- include/linux/firewire-cdev.h | 35 ++++++++++++++++++++++++++++++----- 1 file changed, 30 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/firewire-cdev.h b/include/linux/firewire-cdev.h index 340a78502bc..6ed9127680f 100644 --- a/include/linux/firewire-cdev.h +++ b/include/linux/firewire-cdev.h @@ -138,7 +138,24 @@ struct fw_cdev_event_request { * This event is sent when the controller has completed an &fw_cdev_iso_packet * with the %FW_CDEV_ISO_INTERRUPT bit set. In the receive case, the headers * stripped of all packets up until and including the interrupt packet are - * returned in the @header field. + * returned in the @header field. The amount of header data per packet is as + * specified at iso context creation by &fw_cdev_create_iso_context.header_size. + * + * In version 1 of this ABI, header data consisted of the 1394 isochronous + * packet header, followed by quadlets from the packet payload if + * &fw_cdev_create_iso_context.header_size > 4. + * + * In version 2 of this ABI, header data consist of the 1394 isochronous + * packet header, followed by a timestamp quadlet if + * &fw_cdev_create_iso_context.header_size > 4, followed by quadlets from the + * packet payload if &fw_cdev_create_iso_context.header_size > 8. + * + * Behaviour of ver. 1 of this ABI is no longer available since ABI ver. 2. + * + * Format of 1394 iso packet header: 16 bits len, 2 bits tag, 6 bits channel, + * 4 bits tcode, 4 bits sy, in big endian byte order. Format of timestamp: + * 16 bits invalid, 3 bits cycleSeconds, 13 bits cycleCount, in big endian byte + * order. */ struct fw_cdev_event_iso_interrupt { __u64 closure; @@ -232,11 +249,13 @@ union fw_cdev_event { #define FW_CDEV_IOC_GET_SPEED _IOR('#', 0x11, struct fw_cdev_get_speed) #define FW_CDEV_IOC_SEND_BROADCAST_REQUEST _IOW('#', 0x12, struct fw_cdev_send_request) -/* FW_CDEV_VERSION History - * - * 1 Feb 18, 2007: Initial version. +/* + * FW_CDEV_VERSION History + * 1 (2.6.22) - initial version + * 2 (2.6.30) - changed &fw_cdev_event_iso_interrupt.header if + * &fw_cdev_create_iso_context.header_size is 8 or more */ -#define FW_CDEV_VERSION 1 +#define FW_CDEV_VERSION 2 /** * struct fw_cdev_get_info - General purpose information ioctl @@ -417,6 +436,9 @@ struct fw_cdev_remove_descriptor { * * If a context was successfully created, the kernel writes back a handle to the * context, which must be passed in for subsequent operations on that context. + * + * Note that the effect of a @header_size > 4 depends on + * &fw_cdev_get_info.version, as documented at &fw_cdev_event_iso_interrupt. */ struct fw_cdev_create_iso_context { __u32 type; @@ -520,6 +542,9 @@ struct fw_cdev_stop_iso { * The %FW_CDEV_IOC_GET_CYCLE_TIMER ioctl reads the isochronous cycle timer * and also the system clock. This allows to express the receive time of an * isochronous packet as a system time with microsecond accuracy. + * + * @cycle_timer consists of 7 bits cycleSeconds, 13 bits cycleCount, and + * 12 bits cycleOffset, in host byte order. */ struct fw_cdev_get_cycle_timer { __u64 local_time; -- cgit v1.2.3 From 5d9cb7d276a9c465fef5a771792eac2cf1929f2b Mon Sep 17 00:00:00 2001 From: Stefan Richter Date: Thu, 8 Jan 2009 23:07:40 +0100 Subject: firewire: cdev: add ioctls for iso resource management, amendment Some fixes: - Remove stale documentation. - Fix a != vs. == thinko that got in the way of channel management. - Try bandwidth deallocation even if channel deallocation failed. A simplification: - fw_cdev_allocate_iso_resource.channels is now ordered like libdc1394's dc1394_iso_allocate_channel() channels_allowed argument. By the way, I looked closer at cards from NEC, TI, and VIA, and noticed that they all don't implement IEEE 1394a behaviour which is meant to deviate from IEEE 1212's notion of lock compare-swap. This means that we have to do two lock transactions instead of one in many cases where one transaction would already succeed on a fully 1394a compliant IRM. Signed-off-by: Stefan Richter --- include/linux/firewire-cdev.h | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/firewire-cdev.h b/include/linux/firewire-cdev.h index 6ed9127680f..2e35379bf96 100644 --- a/include/linux/firewire-cdev.h +++ b/include/linux/firewire-cdev.h @@ -174,8 +174,6 @@ struct fw_cdev_event_iso_interrupt { * @handle: Reference by which an allocated resource can be deallocated * @channel: Isochronous channel which was (de)allocated, if any * @bandwidth: Bandwidth allocation units which were (de)allocated, if any - * @channels_available: Last known availability of channels - * @bandwidth_available: Last known availability of bandwidth * * An %FW_CDEV_EVENT_ISO_RESOURCE_ALLOCATED event is sent after an isochronous * resource was allocated at the IRM. The client has to check @channel and @@ -580,7 +578,7 @@ struct fw_cdev_get_cycle_timer { * * The %FW_CDEV_IOC_DEALLOCATE_ISO_RESOURCE_ONCE ioctl works like * %FW_CDEV_IOC_ALLOCATE_ISO_RESOURCE_ONCE except that resources are freed - * instead of allocated. At most one channel may be specified in this ioctl. + * instead of allocated. * An %FW_CDEV_EVENT_ISO_RESOURCE_DEALLOCATED event concludes this operation. * * To summarize, %FW_CDEV_IOC_DEALLOCATE_ISO_RESOURCE allocates iso resources @@ -588,9 +586,9 @@ struct fw_cdev_get_cycle_timer { * In contrast, %FW_CDEV_IOC_ALLOCATE_ISO_RESOURCE_ONCE allocates iso resources * for the duration of a bus generation. * - * @channels is a host-endian bitfield with the most significant bit - * representing channel 0 and the least significant bit representing channel 63: - * 1ULL << (63 - c) + * @channels is a host-endian bitfield with the least significant bit + * representing channel 0 and the most significant bit representing channel 63: + * 1ULL << c for each channel c that is a candidate for (de)allocation. * * @bandwidth is expressed in bandwidth allocation units, i.e. the time to send * one quadlet of data (payload or header data) at speed S1600. -- cgit v1.2.3 From f8c2287c65f8f72000102fc058232669e4540bc4 Mon Sep 17 00:00:00 2001 From: Jay Fenlason Date: Thu, 5 Mar 2009 19:08:40 +0100 Subject: firewire: implement asynchronous stream transmission Allow userspace and other firewire drivers (fw-ipv4 I'm looking at you!) to send Asynchronous Transmit Streams as described in 7.8.3 of release 1.1 of the 1394 Open Host Controller Interface Specification. Signed-off-by: Jay Fenlason Signed-off-by: Stefan Richter (tweaks) --- include/linux/firewire-cdev.h | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'include/linux') diff --git a/include/linux/firewire-cdev.h b/include/linux/firewire-cdev.h index 2e35379bf96..4dfc84d0ac7 100644 --- a/include/linux/firewire-cdev.h +++ b/include/linux/firewire-cdev.h @@ -246,6 +246,7 @@ union fw_cdev_event { #define FW_CDEV_IOC_DEALLOCATE_ISO_RESOURCE_ONCE _IOW('#', 0x10, struct fw_cdev_allocate_iso_resource) #define FW_CDEV_IOC_GET_SPEED _IOR('#', 0x11, struct fw_cdev_get_speed) #define FW_CDEV_IOC_SEND_BROADCAST_REQUEST _IOW('#', 0x12, struct fw_cdev_send_request) +#define FW_CDEV_IOC_SEND_STREAM_PACKET _IOW('#', 0x13, struct fw_cdev_send_stream_packet) /* * FW_CDEV_VERSION History @@ -609,4 +610,30 @@ struct fw_cdev_get_speed { __u32 max_speed; }; +/** + * struct fw_cdev_send_stream_packet - send an asynchronous stream packet + * @generation: Bus generation where the packet is valid + * @speed: Speed code to send the packet at + * @channel: Channel to send the packet on + * @sy: Four-bit sy code for the packet + * @tag: Two-bit tag field to use for the packet + * @size: Size of the packet's data payload + * @data: Userspace pointer to the payload + * + * The %FW_CDEV_IOC_SEND_STREAM_PACKET ioctl sends an asynchronous stream packet + * to every device (that is listening to the specified channel) on the + * firewire bus. It is the applications's job to ensure + * that the intended device(s) will be able to receive the packet at the chosen + * transmit speed. + */ +struct fw_cdev_send_stream_packet { + __u32 generation; + __u32 speed; + __u32 channel; + __u32 sy; + __u32 tag; + __u32 size; + __u64 data; +}; + #endif /* _LINUX_FIREWIRE_CDEV_H */ -- cgit v1.2.3 From c8a25900f35e575938c791507894c036c0f2ca7d Mon Sep 17 00:00:00 2001 From: Stefan Richter Date: Tue, 10 Mar 2009 20:59:16 +0100 Subject: firewire: cdev: amendment to "add ioctl to query maximum transmission speed" The as yet unreleased FW_CDEV_IOC_GET_SPEED ioctl puts only a single integer into the parameter buffer. We can use ioctl()'s return value instead. (Also: Some whitespace change in firewire-cdev.h.) Signed-off-by: Stefan Richter --- include/linux/firewire-cdev.h | 37 ++++++++++++++----------------------- 1 file changed, 14 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/firewire-cdev.h b/include/linux/firewire-cdev.h index 4dfc84d0ac7..de4035792f7 100644 --- a/include/linux/firewire-cdev.h +++ b/include/linux/firewire-cdev.h @@ -223,28 +223,28 @@ union fw_cdev_event { }; /* available since kernel version 2.6.22 */ -#define FW_CDEV_IOC_GET_INFO _IOWR('#', 0x00, struct fw_cdev_get_info) -#define FW_CDEV_IOC_SEND_REQUEST _IOW('#', 0x01, struct fw_cdev_send_request) -#define FW_CDEV_IOC_ALLOCATE _IOWR('#', 0x02, struct fw_cdev_allocate) -#define FW_CDEV_IOC_DEALLOCATE _IOW('#', 0x03, struct fw_cdev_deallocate) -#define FW_CDEV_IOC_SEND_RESPONSE _IOW('#', 0x04, struct fw_cdev_send_response) -#define FW_CDEV_IOC_INITIATE_BUS_RESET _IOW('#', 0x05, struct fw_cdev_initiate_bus_reset) -#define FW_CDEV_IOC_ADD_DESCRIPTOR _IOWR('#', 0x06, struct fw_cdev_add_descriptor) -#define FW_CDEV_IOC_REMOVE_DESCRIPTOR _IOW('#', 0x07, struct fw_cdev_remove_descriptor) -#define FW_CDEV_IOC_CREATE_ISO_CONTEXT _IOWR('#', 0x08, struct fw_cdev_create_iso_context) -#define FW_CDEV_IOC_QUEUE_ISO _IOWR('#', 0x09, struct fw_cdev_queue_iso) -#define FW_CDEV_IOC_START_ISO _IOW('#', 0x0a, struct fw_cdev_start_iso) -#define FW_CDEV_IOC_STOP_ISO _IOW('#', 0x0b, struct fw_cdev_stop_iso) +#define FW_CDEV_IOC_GET_INFO _IOWR('#', 0x00, struct fw_cdev_get_info) +#define FW_CDEV_IOC_SEND_REQUEST _IOW('#', 0x01, struct fw_cdev_send_request) +#define FW_CDEV_IOC_ALLOCATE _IOWR('#', 0x02, struct fw_cdev_allocate) +#define FW_CDEV_IOC_DEALLOCATE _IOW('#', 0x03, struct fw_cdev_deallocate) +#define FW_CDEV_IOC_SEND_RESPONSE _IOW('#', 0x04, struct fw_cdev_send_response) +#define FW_CDEV_IOC_INITIATE_BUS_RESET _IOW('#', 0x05, struct fw_cdev_initiate_bus_reset) +#define FW_CDEV_IOC_ADD_DESCRIPTOR _IOWR('#', 0x06, struct fw_cdev_add_descriptor) +#define FW_CDEV_IOC_REMOVE_DESCRIPTOR _IOW('#', 0x07, struct fw_cdev_remove_descriptor) +#define FW_CDEV_IOC_CREATE_ISO_CONTEXT _IOWR('#', 0x08, struct fw_cdev_create_iso_context) +#define FW_CDEV_IOC_QUEUE_ISO _IOWR('#', 0x09, struct fw_cdev_queue_iso) +#define FW_CDEV_IOC_START_ISO _IOW('#', 0x0a, struct fw_cdev_start_iso) +#define FW_CDEV_IOC_STOP_ISO _IOW('#', 0x0b, struct fw_cdev_stop_iso) /* available since kernel version 2.6.24 */ -#define FW_CDEV_IOC_GET_CYCLE_TIMER _IOR('#', 0x0c, struct fw_cdev_get_cycle_timer) +#define FW_CDEV_IOC_GET_CYCLE_TIMER _IOR('#', 0x0c, struct fw_cdev_get_cycle_timer) /* available since kernel version 2.6.30 */ #define FW_CDEV_IOC_ALLOCATE_ISO_RESOURCE _IOWR('#', 0x0d, struct fw_cdev_allocate_iso_resource) #define FW_CDEV_IOC_DEALLOCATE_ISO_RESOURCE _IOW('#', 0x0e, struct fw_cdev_deallocate) #define FW_CDEV_IOC_ALLOCATE_ISO_RESOURCE_ONCE _IOW('#', 0x0f, struct fw_cdev_allocate_iso_resource) #define FW_CDEV_IOC_DEALLOCATE_ISO_RESOURCE_ONCE _IOW('#', 0x10, struct fw_cdev_allocate_iso_resource) -#define FW_CDEV_IOC_GET_SPEED _IOR('#', 0x11, struct fw_cdev_get_speed) +#define FW_CDEV_IOC_GET_SPEED _IO('#', 0x11) /* returns speed code */ #define FW_CDEV_IOC_SEND_BROADCAST_REQUEST _IOW('#', 0x12, struct fw_cdev_send_request) #define FW_CDEV_IOC_SEND_STREAM_PACKET _IOW('#', 0x13, struct fw_cdev_send_stream_packet) @@ -601,15 +601,6 @@ struct fw_cdev_allocate_iso_resource { __u32 handle; }; -/** - * struct fw_cdev_get_speed - Query maximum speed to or from this device - * @max_speed: Speed code; minimum of the device's link speed, the local node's - * link speed, and all PHY port speeds between the two links - */ -struct fw_cdev_get_speed { - __u32 max_speed; -}; - /** * struct fw_cdev_send_stream_packet - send an asynchronous stream packet * @generation: Bus generation where the packet is valid -- cgit v1.2.3 From de487da8ca5839d057e1f4b57ee3f387e180b800 Mon Sep 17 00:00:00 2001 From: Stefan Richter Date: Tue, 10 Mar 2009 21:00:23 +0100 Subject: firewire: cdev: secure add_descriptor ioctl The access permissions and ownership or ACL of /dev/fw* character device files will typically be set based on the device type of the respective nodes, as obtained by firewire-core from descriptors in the device's configuration ROM. An example policy is to deny write permission by default but grant write permission to files of AV/C video and audio devices and IIDC video devices. The FW_CDEV_IOC_ADD_DESCRIPTOR ioctl could be used to partly subvert such a policy: Find a device file with relaxed permissions, use the ioctl to add a descriptor with AV/C marker to the local node's ROM, thus gain access to the local node's character device file. (This is only possible if there are udev scripts installed which actively relax permissions for known device types and if there is a device of such a type connected.) Accessibility of the local node's device file is relevant to host security if the host contains two or more IEEE 1394 link layer controllers which are plugged into a single bus. Therefore change the ABI to deny FW_CDEV_IOC_ADD_DESCRIPTOR if the file belongs to a remote node. (This change has no impact on known implementers of the ABI: None of them uses the ioctl yet.) Also clarify the documentation: The ioctl affects all local nodes, not just one local node. Cc: stable@kernel.org Signed-off-by: Stefan Richter --- include/linux/firewire-cdev.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/firewire-cdev.h b/include/linux/firewire-cdev.h index de4035792f7..25bc82726ef 100644 --- a/include/linux/firewire-cdev.h +++ b/include/linux/firewire-cdev.h @@ -394,6 +394,9 @@ struct fw_cdev_initiate_bus_reset { * If successful, the kernel adds the descriptor and writes back a handle to the * kernel-side object to be used for later removal of the descriptor block and * immediate key. + * + * This ioctl affects the configuration ROMs of all local nodes. + * The ioctl only succeeds on device files which represent a local node. */ struct fw_cdev_add_descriptor { __u32 immediate; @@ -409,7 +412,7 @@ struct fw_cdev_add_descriptor { * descriptor was added * * Remove a descriptor block and accompanying immediate key from the local - * node's configuration ROM. + * nodes' configuration ROMs. */ struct fw_cdev_remove_descriptor { __u32 handle; -- cgit v1.2.3 From 18e9b10fcdc090d3a38606958167d5923c7099b7 Mon Sep 17 00:00:00 2001 From: Stefan Richter Date: Tue, 10 Mar 2009 21:02:21 +0100 Subject: firewire: cdev: add closure to async stream ioctl This changes the as yet unreleased FW_CDEV_IOC_SEND_STREAM_PACKET ioctl to generate an fw_cdev_event_response event just like the other two ioctls for asynchronous request transmission do. This way, clients get feedback on successful or unsuccessful transmission. This also adds input validation for length, tag, channel, sy, speed. Signed-off-by: Stefan Richter --- include/linux/firewire-cdev.h | 31 ++++++++++++++++--------------- 1 file changed, 16 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/firewire-cdev.h b/include/linux/firewire-cdev.h index 25bc82726ef..c6b3ca3af6d 100644 --- a/include/linux/firewire-cdev.h +++ b/include/linux/firewire-cdev.h @@ -606,28 +606,29 @@ struct fw_cdev_allocate_iso_resource { /** * struct fw_cdev_send_stream_packet - send an asynchronous stream packet - * @generation: Bus generation where the packet is valid - * @speed: Speed code to send the packet at - * @channel: Channel to send the packet on - * @sy: Four-bit sy code for the packet - * @tag: Two-bit tag field to use for the packet - * @size: Size of the packet's data payload - * @data: Userspace pointer to the payload + * @length: Length of outgoing payload, in bytes + * @tag: Data format tag + * @channel: Isochronous channel to transmit to + * @sy: Synchronization code + * @closure: Passed back to userspace in the response event + * @data: Userspace pointer to payload + * @generation: The bus generation where packet is valid + * @speed: Speed to transmit at * * The %FW_CDEV_IOC_SEND_STREAM_PACKET ioctl sends an asynchronous stream packet - * to every device (that is listening to the specified channel) on the - * firewire bus. It is the applications's job to ensure - * that the intended device(s) will be able to receive the packet at the chosen - * transmit speed. + * to every device which is listening to the specified channel. The kernel + * writes an &fw_cdev_event_response event which indicates success or failure of + * the transmission. */ struct fw_cdev_send_stream_packet { - __u32 generation; - __u32 speed; + __u32 length; + __u32 tag; __u32 channel; __u32 sy; - __u32 tag; - __u32 size; + __u64 closure; __u64 data; + __u32 generation; + __u32 speed; }; #endif /* _LINUX_FIREWIRE_CDEV_H */ -- cgit v1.2.3 From 7a254df007b3db88bd430474030fec92e7bab22a Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 24 Mar 2009 23:22:39 +0100 Subject: ide: move ide_pktcmd_tf_load() to ide-atapi.c Then make it static and remove 'dma' argument. Acked-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 25087aead65..e7b787de528 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1202,8 +1202,6 @@ void ide_read_bcount_and_ireason(ide_drive_t *, u16 *, u8 *); extern int drive_is_ready(ide_drive_t *); -void ide_pktcmd_tf_load(ide_drive_t *, u32, u16, u8); - int ide_check_atapi_device(ide_drive_t *, const char *); void ide_init_pc(struct ide_atapi_pc *); -- cgit v1.2.3 From 7ed5b157d9dff55bf477b4c8b4708d5d45476677 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 24 Mar 2009 23:22:41 +0100 Subject: ide: add ide_for_each_present_dev() iterator * Add ide_for_each_present_dev() iterator and convert IDE code to use it. * Do some drive-by CodingStyle fixups in ide-acpi.c while at it. There should be no functional changes caused by this patch. Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index e7b787de528..7ed395b4b89 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1609,6 +1609,10 @@ static inline ide_drive_t *ide_get_pair_dev(ide_drive_t *drive) #define ide_port_for_each_dev(i, dev, port) \ for ((i) = 0; ((dev) = (port)->devices[i]) || (i) < MAX_DRIVES; (i)++) +#define ide_port_for_each_present_dev(i, dev, port) \ + for ((i) = 0; ((dev) = (port)->devices[i]) || (i) < MAX_DRIVES; (i)++) \ + if ((dev)->dev_flags & IDE_DFLAG_PRESENT) + #define ide_host_for_each_port(i, port, host) \ for ((i) = 0; ((port) = (host)->ports[i]) || (i) < MAX_HOST_PORTS; (i)++) -- cgit v1.2.3 From 8b803bd184e3f6892284d4b50801b9ec85cd9b96 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 24 Mar 2009 23:22:41 +0100 Subject: ide: sanitize ACPI initialization * ide_acpi_init() -> ide_acpi_init_port() * ide_acpi_blacklist() -> ide_acpi_init() * Call ide_acpi_init() only once (do it during IDE core initialization) and cleanup the function accordingly. Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 7ed395b4b89..6bb104f4e34 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1484,17 +1484,19 @@ static inline void ide_release_dma_engine(ide_hwif_t *hwif) { ; } #endif /* CONFIG_BLK_DEV_IDEDMA */ #ifdef CONFIG_BLK_DEV_IDEACPI +int ide_acpi_init(void); extern int ide_acpi_exec_tfs(ide_drive_t *drive); extern void ide_acpi_get_timing(ide_hwif_t *hwif); extern void ide_acpi_push_timing(ide_hwif_t *hwif); -extern void ide_acpi_init(ide_hwif_t *hwif); +void ide_acpi_init_port(ide_hwif_t *); void ide_acpi_port_init_devices(ide_hwif_t *); extern void ide_acpi_set_state(ide_hwif_t *hwif, int on); #else +static inline int ide_acpi_init(void) { return 0; } static inline int ide_acpi_exec_tfs(ide_drive_t *drive) { return 0; } static inline void ide_acpi_get_timing(ide_hwif_t *hwif) { ; } static inline void ide_acpi_push_timing(ide_hwif_t *hwif) { ; } -static inline void ide_acpi_init(ide_hwif_t *hwif) { ; } +static inline void ide_acpi_init_port(ide_hwif_t *hwif) { ; } static inline void ide_acpi_port_init_devices(ide_hwif_t *hwif) { ; } static inline void ide_acpi_set_state(ide_hwif_t *hwif, int on) {} #endif -- cgit v1.2.3 From b6a45a0b1e9a358b81201659cf87b023e3ec73e0 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 24 Mar 2009 23:22:43 +0100 Subject: ide: move drive_is_ready() to ide-io.c Move drive_is_ready() to ide-io.c, then make it static. Also make some minor CodingStyle fixups while at it. Acked-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 6bb104f4e34..2e95adeedff 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1200,8 +1200,6 @@ void SELECT_MASK(ide_drive_t *, int); u8 ide_read_error(ide_drive_t *); void ide_read_bcount_and_ireason(ide_drive_t *, u16 *, u8 *); -extern int drive_is_ready(ide_drive_t *); - int ide_check_atapi_device(ide_drive_t *, const char *); void ide_init_pc(struct ide_atapi_pc *); -- cgit v1.2.3 From 65ca5377322c7543163066f373ae9e6b0ad8de8a Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 24 Mar 2009 23:22:43 +0100 Subject: ide: move ide_dma_timeout_retry() to ide-dma.c Move ide_dma_timeout_retry() to ide-dma.c and add static inline version for CONFIG_BLK_DEV_IDEDMA=n. Acked-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 2e95adeedff..d0065a90452 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1467,6 +1467,7 @@ static inline int config_drive_for_dma(ide_drive_t *drive) { return 0; } void ide_dma_lost_irq(ide_drive_t *); void ide_dma_timeout(ide_drive_t *); +ide_startstop_t ide_dma_timeout_retry(ide_drive_t *, int); #else static inline int ide_id_dma_bug(ide_drive_t *drive) { return 0; } @@ -1478,6 +1479,7 @@ static inline void ide_dma_on(ide_drive_t *drive) { ; } static inline void ide_dma_verbose(ide_drive_t *drive) { ; } static inline int ide_set_dma(ide_drive_t *drive) { return 1; } static inline void ide_check_dma_crc(ide_drive_t *drive) { ; } +static inline ide_startstop_t ide_dma_timeout_retry(ide_drive_t *drive, int error) { return ide_stopped; } static inline void ide_release_dma_engine(ide_hwif_t *hwif) { ; } #endif /* CONFIG_BLK_DEV_IDEDMA */ -- cgit v1.2.3 From 1866082339597930c5b77aad8de34ab4fbb5724f Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 24 Mar 2009 23:22:44 +0100 Subject: ide: remove ide_do_drive_cmd() * Use elv_add_request() instead of __elv_add_request() in ide_do_drive_cmd(). * ide_do_drive_cmd() is used only in ide-{atapi,cd}.c so inline it there. There should be no functional changes caused by this patch. Acked-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index d0065a90452..8fadffe53cd 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1174,8 +1174,6 @@ extern ide_startstop_t ide_do_reset (ide_drive_t *); extern int ide_devset_execute(ide_drive_t *drive, const struct ide_devset *setting, int arg); -extern void ide_do_drive_cmd(ide_drive_t *, struct request *); - extern void ide_end_drive_cmd(ide_drive_t *, u8, u8); void ide_tf_dump(const char *, struct ide_taskfile *); -- cgit v1.2.3 From c4e66c36cce3f23d68013c4112013123ffe80bdb Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 24 Mar 2009 23:22:44 +0100 Subject: ide: move ide_do_park_unpark() to ide-park.c Acked-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 8fadffe53cd..110d2635989 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1169,6 +1169,8 @@ int ide_busy_sleep(ide_hwif_t *, unsigned long, int); int ide_wait_stat(ide_startstop_t *, ide_drive_t *, u8, u8, unsigned long); +ide_startstop_t ide_do_park_unpark(ide_drive_t *, struct request *); + extern ide_startstop_t ide_do_reset (ide_drive_t *); extern int ide_devset_execute(ide_drive_t *drive, -- cgit v1.2.3 From 11938c929022bb92b1a42f5e1289524a1e465dc0 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 24 Mar 2009 23:22:44 +0100 Subject: ide: move device settings code to ide-devsets.c Remove stale comment from ide.c while at it. Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 110d2635989..eca5082c343 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1170,6 +1170,7 @@ int ide_busy_sleep(ide_hwif_t *, unsigned long, int); int ide_wait_stat(ide_startstop_t *, ide_drive_t *, u8, u8, unsigned long); ide_startstop_t ide_do_park_unpark(ide_drive_t *, struct request *); +ide_startstop_t ide_do_devset(ide_drive_t *, struct request *); extern ide_startstop_t ide_do_reset (ide_drive_t *); -- cgit v1.2.3 From 7eeaaaa52285d5e6cb79f515e99c591dcb9d04fe Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 24 Mar 2009 23:22:46 +0100 Subject: ide: move xfer mode tuning code to ide-xfer-mode.c * Move xfer mode tuning code to ide-xfer-mode.c. * Add CONFIG_IDE_XFER_MODE config option to be selected by host drivers that support xfer mode tuning. * Add CONFIG_IDE_XFER_MODE=n static inline versions of ide_set_pio() and ide_set_xfer_rate(). * Make IDE_TIMINGS and BLK_DEV_IDEDMA config options select IDE_XFER_MODE, also add explicit selects for few host drivers that need it. * Build/link ide-xfer-mode.o and ide-pio-blacklist.o (it is needed only by ide-xfer-mode.o) only if CONFIG_IDE_XFER_MODE=y. Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index eca5082c343..323c3710fbf 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1531,9 +1531,7 @@ static inline void ide_set_hwifdata (ide_hwif_t * hwif, void *data) hwif->hwif_data = data; } -const char *ide_xfer_verbose(u8 mode); extern void ide_toggle_bounce(ide_drive_t *drive, int on); -extern int ide_set_xfer_rate(ide_drive_t *drive, u8 rate); u64 ide_get_lba_addr(struct ide_taskfile *, int); u8 ide_dump_status(ide_drive_t *, const char *, u8); @@ -1572,14 +1570,18 @@ void ide_timing_merge(struct ide_timing *, struct ide_timing *, struct ide_timing *, unsigned int); int ide_timing_compute(ide_drive_t *, u8, struct ide_timing *, int, int); +#ifdef CONFIG_IDE_XFER_MODE int ide_scan_pio_blacklist(char *); - +const char *ide_xfer_verbose(u8); u8 ide_get_best_pio_mode(ide_drive_t *, u8, u8); - int ide_set_pio_mode(ide_drive_t *, u8); int ide_set_dma_mode(ide_drive_t *, u8); - void ide_set_pio(ide_drive_t *, u8); +int ide_set_xfer_rate(ide_drive_t *, u8); +#else +static inline void ide_set_pio(ide_drive_t *drive, u8 pio) { ; } +static inline int ide_set_xfer_rate(ide_drive_t *drive, u8 rate) { return -1; } +#endif static inline void ide_set_max_pio(ide_drive_t *drive) { -- cgit v1.2.3 From 327fa1c29466b8fe471a91fc11e9c6171163c81a Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 24 Mar 2009 23:22:47 +0100 Subject: ide: move error handling code to ide-eh.c (v2) Do some CodingStyle fixups in while at it. v2: Add missing include (reported by Stephen Rothwell). Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 323c3710fbf..0c87ed52a87 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1146,11 +1146,14 @@ int generic_ide_ioctl(ide_drive_t *, struct block_device *, unsigned, unsigned l extern int ide_vlb_clk; extern int ide_pci_clk; -extern int ide_end_request (ide_drive_t *drive, int uptodate, int nrsecs); -int ide_end_dequeued_request(ide_drive_t *drive, struct request *rq, - int uptodate, int nr_sectors); - -extern void ide_set_handler (ide_drive_t *drive, ide_handler_t *handler, unsigned int timeout, ide_expiry_t *expiry); +int ide_end_request(ide_drive_t *, int, int); +int ide_end_dequeued_request(ide_drive_t *, struct request *, int, int); +void ide_kill_rq(ide_drive_t *, struct request *); + +void __ide_set_handler(ide_drive_t *, ide_handler_t *, unsigned int, + ide_expiry_t *); +void ide_set_handler(ide_drive_t *, ide_handler_t *, unsigned int, + ide_expiry_t *); void ide_execute_command(ide_drive_t *, u8, ide_handler_t *, unsigned int, ide_expiry_t *); -- cgit v1.2.3 From 2467922a560bb7e6eb4635435760ad0a2197ffcc Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 24 Mar 2009 23:22:52 +0100 Subject: ide: remove no longer needed IDE_HFLAG[_FORCE]_LEGACY_IRQS There should be no functional changes caused by this patch. Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 0c87ed52a87..bfd07b866b6 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1349,10 +1349,6 @@ enum { IDE_HFLAG_ERROR_STOPS_FIFO = (1 << 19), /* serialize ports */ IDE_HFLAG_SERIALIZE = (1 << 20), - /* use legacy IRQs */ - IDE_HFLAG_LEGACY_IRQS = (1 << 21), - /* force use of legacy IRQs */ - IDE_HFLAG_FORCE_LEGACY_IRQS = (1 << 22), /* host is TRM290 */ IDE_HFLAG_TRM290 = (1 << 23), /* use 32-bit I/O ops */ -- cgit v1.2.3 From 8b07ed26f8eb73d4f55a9d852712cd588c45ff51 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 24 Mar 2009 23:22:52 +0100 Subject: ide: remove no longer needed IRQ fallback code from hwif_init() Then remove no longer used __ide_default_irq(). Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 15 --------------- 1 file changed, 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index bfd07b866b6..31e492c7bde 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -193,21 +193,6 @@ static inline void ide_std_init_ports(hw_regs_t *hw, hw->io_ports.ctl_addr = ctl_addr; } -/* for IDE PCI controllers in legacy mode, temporary */ -static inline int __ide_default_irq(unsigned long base) -{ - switch (base) { -#ifdef CONFIG_IA64 - case 0x1f0: return isa_irq_to_vector(14); - case 0x170: return isa_irq_to_vector(15); -#else - case 0x1f0: return 14; - case 0x170: return 15; -#endif - } - return 0; -} - #if defined(CONFIG_ARM) || defined(CONFIG_FRV) || defined(CONFIG_M68K) || \ defined(CONFIG_MIPS) || defined(CONFIG_MN10300) || defined(CONFIG_PARISC) \ || defined(CONFIG_PPC) || defined(CONFIG_SPARC) || defined(CONFIG_SPARC64) -- cgit v1.2.3 From 2ed0ef543ae3f3ea4f8bd0433fb1fed22625a309 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 24 Mar 2009 23:22:53 +0100 Subject: ide: fix ->init_chipset method to return 'int' value * Return 0 instead of dev->irq in ->init_chipset implementations. * Fix ->init_chipset method to return 'int' value instead of 'unsigned int' one. This fixes ->init_chipset handling for host drivers (cs5530, hpt366 and pdc202xx_new) for which it is possible for this method to fail. Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 31e492c7bde..117dd171e70 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -851,7 +851,7 @@ struct ide_host { ide_hwif_t *ports[MAX_HOST_PORTS + 1]; unsigned int n_ports; struct device *dev[2]; - unsigned int (*init_chipset)(struct pci_dev *); + int (*init_chipset)(struct pci_dev *); irq_handler_t irq_handler; unsigned long host_flags; void *host_priv; @@ -1361,7 +1361,7 @@ enum { struct ide_port_info { char *name; - unsigned int (*init_chipset)(struct pci_dev *); + int (*init_chipset)(struct pci_dev *); void (*init_iops)(ide_hwif_t *); void (*init_hwif)(ide_hwif_t *); int (*init_dma)(ide_hwif_t *, -- cgit v1.2.3 From 86ccf37c6acd74cf7e4b7751ee045de19943c5a0 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 24 Mar 2009 23:22:53 +0100 Subject: ide: remove pciirq argument from ide_pci_setup_ports() * Set ->irq explicitly in cs5520.c. * Remove irq argument from ide_hw_configure(). * Remove pciirq argument from ide_pci_setup_ports(). There should be no functional changes caused by this patch. Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 117dd171e70..24e265af4f1 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1265,7 +1265,7 @@ static inline int ide_pci_is_in_compatibility_mode(struct pci_dev *dev) return 0; } -void ide_pci_setup_ports(struct pci_dev *, const struct ide_port_info *, int, +void ide_pci_setup_ports(struct pci_dev *, const struct ide_port_info *, hw_regs_t *, hw_regs_t **); void ide_setup_pci_noise(struct pci_dev *, const struct ide_port_info *); -- cgit v1.2.3 From 662641d98b4396b48f513726d141c5f646c08259 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 24 Mar 2009 23:22:54 +0100 Subject: frv: remove * Remove superfluous includes. * Remove . Cc: David Howells Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 24e265af4f1..047b74621dd 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -193,8 +193,8 @@ static inline void ide_std_init_ports(hw_regs_t *hw, hw->io_ports.ctl_addr = ctl_addr; } -#if defined(CONFIG_ARM) || defined(CONFIG_FRV) || defined(CONFIG_M68K) || \ - defined(CONFIG_MIPS) || defined(CONFIG_MN10300) || defined(CONFIG_PARISC) \ +#if defined(CONFIG_ARM) || defined(CONFIG_M68K) || defined(CONFIG_MIPS) || \ + defined(CONFIG_MN10300) || defined(CONFIG_PARISC) \ || defined(CONFIG_PPC) || defined(CONFIG_SPARC) || defined(CONFIG_SPARC64) #include #else -- cgit v1.2.3 From d45b70ab9bbf1a46ae52972d532f9e267b8d39d9 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 24 Mar 2009 23:22:54 +0100 Subject: mn10300: remove * Remove superfluous include. * Remove no longer used SUPPORT_SLOW_DATA_PORTS define. * Move defining SUPPORT_VLB_SYNC to . * Use __ide_mm_*() macros from (MN10300 uses only memory-mapped I/O). * Remove . While at it: * Remove superfluous SPARC64 #ifdef from . Cc: David Howells Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 047b74621dd..bbce9b2bdfc 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -26,7 +26,7 @@ #include #include -#if defined(CONFIG_CRIS) || defined(CONFIG_FRV) +#if defined(CONFIG_CRIS) || defined(CONFIG_FRV) || defined(CONFIG_MN10300) # define SUPPORT_VLB_SYNC 0 #else # define SUPPORT_VLB_SYNC 1 @@ -194,8 +194,7 @@ static inline void ide_std_init_ports(hw_regs_t *hw, } #if defined(CONFIG_ARM) || defined(CONFIG_M68K) || defined(CONFIG_MIPS) || \ - defined(CONFIG_MN10300) || defined(CONFIG_PARISC) \ - || defined(CONFIG_PPC) || defined(CONFIG_SPARC) || defined(CONFIG_SPARC64) + defined(CONFIG_PARISC) || defined(CONFIG_PPC) || defined(CONFIG_SPARC) #include #else #include -- cgit v1.2.3 From 552d3a99bdce8a0d7f9abe3766fb3655ef5757dc Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 24 Mar 2009 23:22:58 +0100 Subject: ide: remove broken EXABYTENEST support do_identify() marks EXABYTENEST device as non-present and frees drive->id so enable_nest() has absolutely no chance of working. The code was like this since at least 2.6.12-rc2 and nobody has noticed so just remove broken EXABYTENEST support. Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ata.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ata.h b/include/linux/ata.h index 9a061accd8b..68132c4a0e9 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -244,8 +244,6 @@ enum { ATA_CMD_MEDIA_UNLOCK = 0xDF, /* marked obsolete in the ATA/ATAPI-7 spec */ ATA_CMD_RESTORE = 0x10, - /* EXABYTE specific */ - ATA_EXABYTE_ENABLE_NEST = 0xF0, /* READ_LOG_EXT pages */ ATA_LOG_SATA_NCQ = 0x10, -- cgit v1.2.3 From 2ebe1d9efed5f232afc8d00901d0959c9814bce3 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 24 Mar 2009 23:22:59 +0100 Subject: ide: use try_to_identify() in ide_driveid_update() * Pass pointer to buffer for IDENTIFY data to do_identify() and try_to_identify(). * Un-static try_to_identify() and use it in ide_driveid_update(). * Rename try_to_identify() to ide_dev_read_id(). There should be no functional changes caused by this patch. Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index bbce9b2bdfc..854eba8b2ba 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1235,6 +1235,8 @@ int ide_no_data_taskfile(ide_drive_t *, ide_task_t *); int ide_taskfile_ioctl(ide_drive_t *, unsigned int, unsigned long); +int ide_dev_read_id(ide_drive_t *, u8, u16 *); + extern int ide_driveid_update(ide_drive_t *); extern int ide_config_drive_speed(ide_drive_t *, u8); extern u8 eighty_ninty_three (ide_drive_t *); -- cgit v1.2.3 From 1662e3a7f076e51e3073faf9ce77157b529c475b Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Wed, 18 Mar 2009 14:28:53 -0400 Subject: USB: add quirk to avoid config and interface strings Apparently the Configuration and Interface strings aren't used as often as the Vendor, Product, and Serial strings. In at least one device (a Saitek Cyborg Gold 3D joystick), attempts to read the Configuration string cause the device to stop responding to Control requests. This patch (as1226) adds a quirks flag, telling the kernel not to read a device's Configuration or Interface strings, together with a new quirk for the offending joystick. Reported-by: Melchior FRANZ Tested-by: Melchior FRANZ Signed-off-by: Alan Stern Cc: stable [2.6.28 and 2.6.29, nothing earlier] Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/quirks.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h index 7f6c603db65..2526f3bbd27 100644 --- a/include/linux/usb/quirks.h +++ b/include/linux/usb/quirks.h @@ -16,4 +16,7 @@ /* device can't handle Set-Interface requests */ #define USB_QUIRK_NO_SET_INTF 0x00000004 +/* device can't handle its Configuration or Interface strings */ +#define USB_QUIRK_CONFIG_INTF_STRINGS 0x00000008 + #endif /* __LINUX_USB_QUIRKS_H */ -- cgit v1.2.3 From c2344f13b59e007d782a3e591ebc551bc583a8b7 Mon Sep 17 00:00:00 2001 From: Robert Jarzmik Date: Sat, 24 Jan 2009 23:54:31 -0800 Subject: USB: gpio_vbus: add delayed vbus_session calls Call usb_gadget_vbus_connect() and ...disconnect() from a workqueue rather than from an irq handler, allowing msleep() calls in vbus_session. Update kerneldoc to match. [ dbrownell@users.sourceforge.net: more kerneldoc updates ] Signed-off-by: Robert Jarzmik Signed-off-by: David Brownell Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/gadget.h | 6 ++++-- include/linux/usb/otg.h | 4 ++++ 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 0460a746480..bbf45d500b6 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -598,6 +598,7 @@ static inline int usb_gadget_clear_selfpowered(struct usb_gadget *gadget) /** * usb_gadget_vbus_connect - Notify controller that VBUS is powered * @gadget:The device which now has VBUS power. + * Context: can sleep * * This call is used by a driver for an external transceiver (or GPIO) * that detects a VBUS power session starting. Common responses include @@ -636,6 +637,7 @@ static inline int usb_gadget_vbus_draw(struct usb_gadget *gadget, unsigned mA) /** * usb_gadget_vbus_disconnect - notify controller about VBUS session end * @gadget:the device whose VBUS supply is being described + * Context: can sleep * * This call is used by a driver for an external transceiver (or GPIO) * that detects a VBUS power session ending. Common responses include @@ -792,19 +794,20 @@ struct usb_gadget_driver { /** * usb_gadget_register_driver - register a gadget driver * @driver:the driver being registered + * Context: can sleep * * Call this in your gadget driver's module initialization function, * to tell the underlying usb controller driver about your driver. * The driver's bind() function will be called to bind it to a * gadget before this registration call returns. It's expected that * the bind() functions will be in init sections. - * This function must be called in a context that can sleep. */ int usb_gadget_register_driver(struct usb_gadget_driver *driver); /** * usb_gadget_unregister_driver - unregister a gadget driver * @driver:the driver being unregistered + * Context: can sleep * * Call this in your gadget driver's module cleanup function, * to tell the underlying usb controller that your driver is @@ -813,7 +816,6 @@ int usb_gadget_register_driver(struct usb_gadget_driver *driver); * to unbind() and clean up any device state, before this procedure * finally returns. It's expected that the unbind() functions * will in in exit sections, so may not be linked in some kernels. - * This function must be called in a context that can sleep. */ int usb_gadget_unregister_driver(struct usb_gadget_driver *driver); diff --git a/include/linux/usb/otg.h b/include/linux/usb/otg.h index 94df4fe6c6c..60a52576fd5 100644 --- a/include/linux/usb/otg.h +++ b/include/linux/usb/otg.h @@ -86,6 +86,7 @@ extern int otg_set_transceiver(struct otg_transceiver *); extern struct otg_transceiver *otg_get_transceiver(void); extern void otg_put_transceiver(struct otg_transceiver *); +/* Context: can sleep */ static inline int otg_start_hnp(struct otg_transceiver *otg) { @@ -102,6 +103,8 @@ otg_set_host(struct otg_transceiver *otg, struct usb_bus *host) /* for usb peripheral controller drivers */ + +/* Context: can sleep */ static inline int otg_set_peripheral(struct otg_transceiver *otg, struct usb_gadget *periph) { @@ -114,6 +117,7 @@ otg_set_power(struct otg_transceiver *otg, unsigned mA) return otg->set_power(otg, mA); } +/* Context: can sleep */ static inline int otg_set_suspend(struct otg_transceiver *otg, int suspend) { -- cgit v1.2.3 From 4d6914b72966862f37de634299a80ca2a4b1829f Mon Sep 17 00:00:00 2001 From: Julia Lawall Date: Mon, 29 Dec 2008 22:48:19 +0100 Subject: USB: Move definitions from usb.h to usb/ch9.h The functions: usb_endpoint_dir_in(epd) usb_endpoint_dir_out(epd) usb_endpoint_is_bulk_in(epd) usb_endpoint_is_bulk_out(epd) usb_endpoint_is_int_in(epd) usb_endpoint_is_int_out(epd) usb_endpoint_is_isoc_in(epd) usb_endpoint_is_isoc_out(epd) usb_endpoint_num(epd) usb_endpoint_type(epd) usb_endpoint_xfer_bulk(epd) usb_endpoint_xfer_control(epd) usb_endpoint_xfer_int(epd) usb_endpoint_xfer_isoc(epd) are moved from include/linux/usb.h to include/linux/usb/ch9.h. include/linux/usb/ch9.h makes more sense for these functions because they only depend on constants that are defined in this file. Signed-off-by: Julia Lawall Acked-by: David Brownell Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 180 ------------------------------------------------ include/linux/usb/ch9.h | 179 +++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 179 insertions(+), 180 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index 88079fd6023..0c05ff62119 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -643,186 +643,6 @@ static inline int usb_make_path(struct usb_device *dev, char *buf, size_t size) /*-------------------------------------------------------------------------*/ -/** - * usb_endpoint_num - get the endpoint's number - * @epd: endpoint to be checked - * - * Returns @epd's number: 0 to 15. - */ -static inline int usb_endpoint_num(const struct usb_endpoint_descriptor *epd) -{ - return epd->bEndpointAddress & USB_ENDPOINT_NUMBER_MASK; -} - -/** - * usb_endpoint_type - get the endpoint's transfer type - * @epd: endpoint to be checked - * - * Returns one of USB_ENDPOINT_XFER_{CONTROL, ISOC, BULK, INT} according - * to @epd's transfer type. - */ -static inline int usb_endpoint_type(const struct usb_endpoint_descriptor *epd) -{ - return epd->bmAttributes & USB_ENDPOINT_XFERTYPE_MASK; -} - -/** - * usb_endpoint_dir_in - check if the endpoint has IN direction - * @epd: endpoint to be checked - * - * Returns true if the endpoint is of type IN, otherwise it returns false. - */ -static inline int usb_endpoint_dir_in(const struct usb_endpoint_descriptor *epd) -{ - return ((epd->bEndpointAddress & USB_ENDPOINT_DIR_MASK) == USB_DIR_IN); -} - -/** - * usb_endpoint_dir_out - check if the endpoint has OUT direction - * @epd: endpoint to be checked - * - * Returns true if the endpoint is of type OUT, otherwise it returns false. - */ -static inline int usb_endpoint_dir_out( - const struct usb_endpoint_descriptor *epd) -{ - return ((epd->bEndpointAddress & USB_ENDPOINT_DIR_MASK) == USB_DIR_OUT); -} - -/** - * usb_endpoint_xfer_bulk - check if the endpoint has bulk transfer type - * @epd: endpoint to be checked - * - * Returns true if the endpoint is of type bulk, otherwise it returns false. - */ -static inline int usb_endpoint_xfer_bulk( - const struct usb_endpoint_descriptor *epd) -{ - return ((epd->bmAttributes & USB_ENDPOINT_XFERTYPE_MASK) == - USB_ENDPOINT_XFER_BULK); -} - -/** - * usb_endpoint_xfer_control - check if the endpoint has control transfer type - * @epd: endpoint to be checked - * - * Returns true if the endpoint is of type control, otherwise it returns false. - */ -static inline int usb_endpoint_xfer_control( - const struct usb_endpoint_descriptor *epd) -{ - return ((epd->bmAttributes & USB_ENDPOINT_XFERTYPE_MASK) == - USB_ENDPOINT_XFER_CONTROL); -} - -/** - * usb_endpoint_xfer_int - check if the endpoint has interrupt transfer type - * @epd: endpoint to be checked - * - * Returns true if the endpoint is of type interrupt, otherwise it returns - * false. - */ -static inline int usb_endpoint_xfer_int( - const struct usb_endpoint_descriptor *epd) -{ - return ((epd->bmAttributes & USB_ENDPOINT_XFERTYPE_MASK) == - USB_ENDPOINT_XFER_INT); -} - -/** - * usb_endpoint_xfer_isoc - check if the endpoint has isochronous transfer type - * @epd: endpoint to be checked - * - * Returns true if the endpoint is of type isochronous, otherwise it returns - * false. - */ -static inline int usb_endpoint_xfer_isoc( - const struct usb_endpoint_descriptor *epd) -{ - return ((epd->bmAttributes & USB_ENDPOINT_XFERTYPE_MASK) == - USB_ENDPOINT_XFER_ISOC); -} - -/** - * usb_endpoint_is_bulk_in - check if the endpoint is bulk IN - * @epd: endpoint to be checked - * - * Returns true if the endpoint has bulk transfer type and IN direction, - * otherwise it returns false. - */ -static inline int usb_endpoint_is_bulk_in( - const struct usb_endpoint_descriptor *epd) -{ - return (usb_endpoint_xfer_bulk(epd) && usb_endpoint_dir_in(epd)); -} - -/** - * usb_endpoint_is_bulk_out - check if the endpoint is bulk OUT - * @epd: endpoint to be checked - * - * Returns true if the endpoint has bulk transfer type and OUT direction, - * otherwise it returns false. - */ -static inline int usb_endpoint_is_bulk_out( - const struct usb_endpoint_descriptor *epd) -{ - return (usb_endpoint_xfer_bulk(epd) && usb_endpoint_dir_out(epd)); -} - -/** - * usb_endpoint_is_int_in - check if the endpoint is interrupt IN - * @epd: endpoint to be checked - * - * Returns true if the endpoint has interrupt transfer type and IN direction, - * otherwise it returns false. - */ -static inline int usb_endpoint_is_int_in( - const struct usb_endpoint_descriptor *epd) -{ - return (usb_endpoint_xfer_int(epd) && usb_endpoint_dir_in(epd)); -} - -/** - * usb_endpoint_is_int_out - check if the endpoint is interrupt OUT - * @epd: endpoint to be checked - * - * Returns true if the endpoint has interrupt transfer type and OUT direction, - * otherwise it returns false. - */ -static inline int usb_endpoint_is_int_out( - const struct usb_endpoint_descriptor *epd) -{ - return (usb_endpoint_xfer_int(epd) && usb_endpoint_dir_out(epd)); -} - -/** - * usb_endpoint_is_isoc_in - check if the endpoint is isochronous IN - * @epd: endpoint to be checked - * - * Returns true if the endpoint has isochronous transfer type and IN direction, - * otherwise it returns false. - */ -static inline int usb_endpoint_is_isoc_in( - const struct usb_endpoint_descriptor *epd) -{ - return (usb_endpoint_xfer_isoc(epd) && usb_endpoint_dir_in(epd)); -} - -/** - * usb_endpoint_is_isoc_out - check if the endpoint is isochronous OUT - * @epd: endpoint to be checked - * - * Returns true if the endpoint has isochronous transfer type and OUT direction, - * otherwise it returns false. - */ -static inline int usb_endpoint_is_isoc_out( - const struct usb_endpoint_descriptor *epd) -{ - return (usb_endpoint_xfer_isoc(epd) && usb_endpoint_dir_out(epd)); -} - -/*-------------------------------------------------------------------------*/ - #define USB_DEVICE_ID_MATCH_DEVICE \ (USB_DEVICE_ID_MATCH_VENDOR | USB_DEVICE_ID_MATCH_PRODUCT) #define USB_DEVICE_ID_MATCH_DEV_RANGE \ diff --git a/include/linux/usb/ch9.h b/include/linux/usb/ch9.h index 9b42baed390..fa777db7f7e 100644 --- a/include/linux/usb/ch9.h +++ b/include/linux/usb/ch9.h @@ -353,6 +353,185 @@ struct usb_endpoint_descriptor { #define USB_ENDPOINT_XFER_INT 3 #define USB_ENDPOINT_MAX_ADJUSTABLE 0x80 +/*-------------------------------------------------------------------------*/ + +/** + * usb_endpoint_num - get the endpoint's number + * @epd: endpoint to be checked + * + * Returns @epd's number: 0 to 15. + */ +static inline int usb_endpoint_num(const struct usb_endpoint_descriptor *epd) +{ + return epd->bEndpointAddress & USB_ENDPOINT_NUMBER_MASK; +} + +/** + * usb_endpoint_type - get the endpoint's transfer type + * @epd: endpoint to be checked + * + * Returns one of USB_ENDPOINT_XFER_{CONTROL, ISOC, BULK, INT} according + * to @epd's transfer type. + */ +static inline int usb_endpoint_type(const struct usb_endpoint_descriptor *epd) +{ + return epd->bmAttributes & USB_ENDPOINT_XFERTYPE_MASK; +} + +/** + * usb_endpoint_dir_in - check if the endpoint has IN direction + * @epd: endpoint to be checked + * + * Returns true if the endpoint is of type IN, otherwise it returns false. + */ +static inline int usb_endpoint_dir_in(const struct usb_endpoint_descriptor *epd) +{ + return ((epd->bEndpointAddress & USB_ENDPOINT_DIR_MASK) == USB_DIR_IN); +} + +/** + * usb_endpoint_dir_out - check if the endpoint has OUT direction + * @epd: endpoint to be checked + * + * Returns true if the endpoint is of type OUT, otherwise it returns false. + */ +static inline int usb_endpoint_dir_out( + const struct usb_endpoint_descriptor *epd) +{ + return ((epd->bEndpointAddress & USB_ENDPOINT_DIR_MASK) == USB_DIR_OUT); +} + +/** + * usb_endpoint_xfer_bulk - check if the endpoint has bulk transfer type + * @epd: endpoint to be checked + * + * Returns true if the endpoint is of type bulk, otherwise it returns false. + */ +static inline int usb_endpoint_xfer_bulk( + const struct usb_endpoint_descriptor *epd) +{ + return ((epd->bmAttributes & USB_ENDPOINT_XFERTYPE_MASK) == + USB_ENDPOINT_XFER_BULK); +} + +/** + * usb_endpoint_xfer_control - check if the endpoint has control transfer type + * @epd: endpoint to be checked + * + * Returns true if the endpoint is of type control, otherwise it returns false. + */ +static inline int usb_endpoint_xfer_control( + const struct usb_endpoint_descriptor *epd) +{ + return ((epd->bmAttributes & USB_ENDPOINT_XFERTYPE_MASK) == + USB_ENDPOINT_XFER_CONTROL); +} + +/** + * usb_endpoint_xfer_int - check if the endpoint has interrupt transfer type + * @epd: endpoint to be checked + * + * Returns true if the endpoint is of type interrupt, otherwise it returns + * false. + */ +static inline int usb_endpoint_xfer_int( + const struct usb_endpoint_descriptor *epd) +{ + return ((epd->bmAttributes & USB_ENDPOINT_XFERTYPE_MASK) == + USB_ENDPOINT_XFER_INT); +} + +/** + * usb_endpoint_xfer_isoc - check if the endpoint has isochronous transfer type + * @epd: endpoint to be checked + * + * Returns true if the endpoint is of type isochronous, otherwise it returns + * false. + */ +static inline int usb_endpoint_xfer_isoc( + const struct usb_endpoint_descriptor *epd) +{ + return ((epd->bmAttributes & USB_ENDPOINT_XFERTYPE_MASK) == + USB_ENDPOINT_XFER_ISOC); +} + +/** + * usb_endpoint_is_bulk_in - check if the endpoint is bulk IN + * @epd: endpoint to be checked + * + * Returns true if the endpoint has bulk transfer type and IN direction, + * otherwise it returns false. + */ +static inline int usb_endpoint_is_bulk_in( + const struct usb_endpoint_descriptor *epd) +{ + return (usb_endpoint_xfer_bulk(epd) && usb_endpoint_dir_in(epd)); +} + +/** + * usb_endpoint_is_bulk_out - check if the endpoint is bulk OUT + * @epd: endpoint to be checked + * + * Returns true if the endpoint has bulk transfer type and OUT direction, + * otherwise it returns false. + */ +static inline int usb_endpoint_is_bulk_out( + const struct usb_endpoint_descriptor *epd) +{ + return (usb_endpoint_xfer_bulk(epd) && usb_endpoint_dir_out(epd)); +} + +/** + * usb_endpoint_is_int_in - check if the endpoint is interrupt IN + * @epd: endpoint to be checked + * + * Returns true if the endpoint has interrupt transfer type and IN direction, + * otherwise it returns false. + */ +static inline int usb_endpoint_is_int_in( + const struct usb_endpoint_descriptor *epd) +{ + return (usb_endpoint_xfer_int(epd) && usb_endpoint_dir_in(epd)); +} + +/** + * usb_endpoint_is_int_out - check if the endpoint is interrupt OUT + * @epd: endpoint to be checked + * + * Returns true if the endpoint has interrupt transfer type and OUT direction, + * otherwise it returns false. + */ +static inline int usb_endpoint_is_int_out( + const struct usb_endpoint_descriptor *epd) +{ + return (usb_endpoint_xfer_int(epd) && usb_endpoint_dir_out(epd)); +} + +/** + * usb_endpoint_is_isoc_in - check if the endpoint is isochronous IN + * @epd: endpoint to be checked + * + * Returns true if the endpoint has isochronous transfer type and IN direction, + * otherwise it returns false. + */ +static inline int usb_endpoint_is_isoc_in( + const struct usb_endpoint_descriptor *epd) +{ + return (usb_endpoint_xfer_isoc(epd) && usb_endpoint_dir_in(epd)); +} + +/** + * usb_endpoint_is_isoc_out - check if the endpoint is isochronous OUT + * @epd: endpoint to be checked + * + * Returns true if the endpoint has isochronous transfer type and OUT direction, + * otherwise it returns false. + */ +static inline int usb_endpoint_is_isoc_out( + const struct usb_endpoint_descriptor *epd) +{ + return (usb_endpoint_xfer_isoc(epd) && usb_endpoint_dir_out(epd)); +} /*-------------------------------------------------------------------------*/ -- cgit v1.2.3 From f8bece8d91f9ed9cff3c98920802f1b3046b7560 Mon Sep 17 00:00:00 2001 From: Oliver Neukum Date: Thu, 5 Feb 2009 16:54:25 +0100 Subject: USB: serial: introduce a flag into the usb serial layer to tell drivers that their URBs are killed due to suspension This patch introduces a flag into the usb serial layer to tell drivers that their URBs are killed due to suspension. That is necessary to let drivers know whether they should report an error back. Signed-off-by: Oliver Neukum Hi Greg, this is for 2.6.30. Patches to use this in drivers are under development. Regards Oliver --- include/linux/usb/serial.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h index 0b8617a9176..b9584254259 100644 --- a/include/linux/usb/serial.h +++ b/include/linux/usb/serial.h @@ -130,7 +130,8 @@ struct usb_serial { struct usb_device *dev; struct usb_serial_driver *type; struct usb_interface *interface; - unsigned char disconnected; + unsigned char disconnected:1; + unsigned char suspending:1; unsigned char minor; unsigned char num_ports; unsigned char num_port_pointers; -- cgit v1.2.3 From f6d92a05c86754d62eabc84856d2035d0de3ddc3 Mon Sep 17 00:00:00 2001 From: Ajay Kumar Gupta Date: Fri, 6 Feb 2009 17:32:35 +0530 Subject: USB: otg: adding nop usb transceiver NOP transceiver is used by all the usb transceiver which are mostly autonomous and doesn't require any programming or which are built into the usb ip itself.NOP transceiver only allocates the memory for struct xceiv and calls otg_set_transceiver() so function call to otg_get_transceiver() will return a valid transceiver. NOP transceiver device should be registered by calling usb_nop_xceiv_register() from platform files. Signed-off-by: Ajay Kumar Gupta Cc: Felipe Balbi Cc: David Brownell Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/otg.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/otg.h b/include/linux/usb/otg.h index 60a52576fd5..1aaa826396a 100644 --- a/include/linux/usb/otg.h +++ b/include/linux/usb/otg.h @@ -80,6 +80,10 @@ struct otg_transceiver { /* for board-specific init logic */ extern int otg_set_transceiver(struct otg_transceiver *); +#ifdef CONFIG_NOP_USB_XCEIV +extern void usb_nop_xceiv_register(void); +extern void usb_nop_xceiv_unregister(void); +#endif /* for usb host and peripheral controller drivers */ -- cgit v1.2.3 From e6e244b6cb1f70e7109381626293cd40a8334ed3 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Thu, 12 Feb 2009 14:47:44 -0500 Subject: usb-storage: prepare for subdriver separation This patch (as1206) is the first step in converting usb-storage's subdrivers into separate modules. It makes the following large-scale changes: Remove a bunch of unnecessary #ifdef's from usb_usual.h. Not truly necessary, but it does clean things up. Move the USB device-ID table (which is duplicated between libusual and usb-storage) into its own source file, usual-tables.c, and arrange for this to be linked with either libusual or usb-storage according to whether USB_LIBUSUAL is configured. Add to usual-tables.c a new usb_usual_ignore_device() function to detect whether a particular device needs to be managed by a subdriver and not by the standard handlers in usb-storage. Export a whole bunch of functions in usb-storage, renaming some of them because their names don't already begin with "usb_stor_". These functions will be needed by the new subdriver modules. Split usb-storage's probe routine into two functions. The subdrivers will call the probe1 routine, then fill in their transport and protocol settings, and then call the probe2 routine. Take the default cases and error checking out of get_transport() and get_protocol(), which run during probe1, and instead put a check for invalid transport or protocol values into the probe2 function. Add a new probe routine to be used for standard devices, i.e., those that don't need a subdriver. This new routine checks whether the device should be ignored (because it should be handled by ub or by a subdriver), and if not, calls the probe1 and probe2 functions. Signed-off-by: Alan Stern CC: Matthew Dharm Signed-off-by: Greg Kroah-Hartman --- include/linux/usb_usual.h | 21 ++++----------------- 1 file changed, 4 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb_usual.h b/include/linux/usb_usual.h index 1eea1ab68dc..3d15fb9bc11 100644 --- a/include/linux/usb_usual.h +++ b/include/linux/usb_usual.h @@ -96,39 +96,26 @@ enum { US_DO_ALL_FLAGS }; #define US_PR_CBI 0x00 /* Control/Bulk/Interrupt */ #define US_PR_CB 0x01 /* Control/Bulk w/o interrupt */ #define US_PR_BULK 0x50 /* bulk only */ -#ifdef CONFIG_USB_STORAGE_USBAT + #define US_PR_USBAT 0x80 /* SCM-ATAPI bridge */ -#endif -#ifdef CONFIG_USB_STORAGE_SDDR09 #define US_PR_EUSB_SDDR09 0x81 /* SCM-SCSI bridge for SDDR-09 */ -#endif -#ifdef CONFIG_USB_STORAGE_SDDR55 #define US_PR_SDDR55 0x82 /* SDDR-55 (made up) */ -#endif #define US_PR_DPCM_USB 0xf0 /* Combination CB/SDDR09 */ -#ifdef CONFIG_USB_STORAGE_FREECOM #define US_PR_FREECOM 0xf1 /* Freecom */ -#endif -#ifdef CONFIG_USB_STORAGE_DATAFAB #define US_PR_DATAFAB 0xf2 /* Datafab chipsets */ -#endif -#ifdef CONFIG_USB_STORAGE_JUMPSHOT #define US_PR_JUMPSHOT 0xf3 /* Lexar Jumpshot */ -#endif -#ifdef CONFIG_USB_STORAGE_ALAUDA #define US_PR_ALAUDA 0xf4 /* Alauda chipsets */ -#endif -#ifdef CONFIG_USB_STORAGE_KARMA #define US_PR_KARMA 0xf5 /* Rio Karma */ -#endif #define US_PR_DEVICE 0xff /* Use device's value */ /* */ +extern int usb_usual_ignore_device(struct usb_interface *intf); +extern struct usb_device_id usb_storage_usb_ids[]; + #ifdef CONFIG_USB_LIBUSUAL -extern struct usb_device_id storage_usb_ids[]; extern void usb_usual_set_present(int type); extern void usb_usual_clear_present(int type); extern int usb_usual_check_type(const struct usb_device_id *, int type); -- cgit v1.2.3 From 6da9c99059bf24fb1faae6b9613bae64ea50c05e Mon Sep 17 00:00:00 2001 From: David Vrabel Date: Wed, 18 Feb 2009 14:43:47 +0000 Subject: USB: allow libusb to talk to unauthenticated WUSB devices To permit a userspace application to associate with WUSB devices using numeric association, control transfers to unauthenticated WUSB devices must be allowed. This requires that wusbcore correctly sets the device state to UNAUTHENTICATED, DEFAULT and ADDRESS and that control transfers can be performed to UNAUTHENTICATED devices. Signed-off-by: David Vrabel Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/ch9.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/ch9.h b/include/linux/usb/ch9.h index fa777db7f7e..d9d54803dbc 100644 --- a/include/linux/usb/ch9.h +++ b/include/linux/usb/ch9.h @@ -763,8 +763,8 @@ enum usb_device_state { /* chapter 9 and authentication (wireless) device states */ USB_STATE_ATTACHED, USB_STATE_POWERED, /* wired */ - USB_STATE_UNAUTHENTICATED, /* auth */ USB_STATE_RECONNECTING, /* auth */ + USB_STATE_UNAUTHENTICATED, /* auth */ USB_STATE_DEFAULT, /* limited function */ USB_STATE_ADDRESS, USB_STATE_CONFIGURED, /* most functions */ -- cgit v1.2.3 From 16e2e5f634f86ccda18366967c4e592eb61bc9cc Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 3 Mar 2009 16:44:13 -0800 Subject: USB: make transfer_buffer_lengths in struct urb field u32 Roel Kluin pointed out that transfer_buffer_lengths in struct urb was declared as an 'int'. This patch changes this field to be 'u32' to prevent any potential negative conversion and comparison errors. This triggered a few compiler warning messages when these fields were being used with the min macro, so they have also been fixed up in this patch. Cc: Roel Kluin Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index 0c05ff62119..db8808e05a2 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -1177,7 +1177,7 @@ struct urb { unsigned int transfer_flags; /* (in) URB_SHORT_NOT_OK | ...*/ void *transfer_buffer; /* (in) associated data buffer */ dma_addr_t transfer_dma; /* (in) dma addr for transfer_buffer */ - int transfer_buffer_length; /* (in) data buffer length */ + u32 transfer_buffer_length; /* (in) data buffer length */ int actual_length; /* (return) actual transfer length */ unsigned char *setup_packet; /* (in) setup packet (control only) */ dma_addr_t setup_dma; /* (in) dma addr for setup_packet */ -- cgit v1.2.3 From 8c209e6782ca0e3046803fc04a5ac01c8c10437a Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 6 Mar 2009 21:31:03 -0800 Subject: USB: make actual_length in struct urb field u32 actual_length should also be a u32 and not a signed value. This patch changes this field to be 'u32' to prevent any potential negative conversion and comparison errors. This triggered a few compiler warning messages when these fields were being used with the min macro, so they have also been fixed up in this patch. Cc: Roel Kluin Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index db8808e05a2..c6b2ab41b90 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -1178,7 +1178,7 @@ struct urb { void *transfer_buffer; /* (in) associated data buffer */ dma_addr_t transfer_dma; /* (in) dma addr for transfer_buffer */ u32 transfer_buffer_length; /* (in) data buffer length */ - int actual_length; /* (return) actual transfer length */ + u32 actual_length; /* (return) actual transfer length */ unsigned char *setup_packet; /* (in) setup packet (control only) */ dma_addr_t setup_dma; /* (in) dma addr for setup_packet */ int start_frame; /* (modify) start frame (ISO) */ -- cgit v1.2.3 From 64a3a25f440c65510cb0d15080dcd2f0032d6051 Mon Sep 17 00:00:00 2001 From: "D.J. Capelis" Date: Wed, 4 Mar 2009 10:27:52 -0800 Subject: USB: pedantic: spelling correction in comment for ch9.h Just noticed this during a grep, figured I might as well send it in. From: D.J. Capelis Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/ch9.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/ch9.h b/include/linux/usb/ch9.h index d9d54803dbc..b145119a90d 100644 --- a/include/linux/usb/ch9.h +++ b/include/linux/usb/ch9.h @@ -102,7 +102,7 @@ #define USB_REQ_LOOPBACK_DATA_READ 0x16 #define USB_REQ_SET_INTERFACE_DS 0x17 -/* The Link Power Mangement (LPM) ECN defines USB_REQ_TEST_AND_SET command, +/* The Link Power Management (LPM) ECN defines USB_REQ_TEST_AND_SET command, * used by hubs to put ports into a new L1 suspend state, except that it * forgot to define its number ... */ -- cgit v1.2.3 From 8942939a6c83f34615de5ae041cc9ca846923f94 Mon Sep 17 00:00:00 2001 From: David Brownell Date: Thu, 19 Mar 2009 14:14:17 -0700 Subject: USB: gadget: composite device-level suspend/resume hooks Address one open question in the composite gadget framework: Yes, we should have device-level suspend/resume callbacks in addition to the function-level ones. We have at least one scenario (with gadget zero in OTG test mode) that's awkward to handle without it. Signed-off-by: David Brownell Cc: Felipe Balbi Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/composite.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index 935c380ffe4..acd7b0f06c8 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -244,6 +244,10 @@ int usb_add_config(struct usb_composite_dev *, * value; it should return zero on successful initialization. * @unbind: Reverses @bind(); called as a side effect of unregistering * this driver. + * @suspend: Notifies when the host stops sending USB traffic, + * after function notifications + * @resume: Notifies configuration when the host restarts USB traffic, + * before function notifications * * Devices default to reporting self powered operation. Devices which rely * on bus powered operation should report this in their @bind() method. @@ -268,6 +272,10 @@ struct usb_composite_driver { int (*bind)(struct usb_composite_dev *); int (*unbind)(struct usb_composite_dev *); + + /* global suspend hooks */ + void (*suspend)(struct usb_composite_dev *); + void (*resume)(struct usb_composite_dev *); }; extern int usb_composite_register(struct usb_composite_driver *); -- cgit v1.2.3 From 38938bfe3489394e2eed5e40c9bb8f66a2ce1405 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 24 Mar 2009 16:37:55 -0700 Subject: netlink: add NETLINK_NO_ENOBUFS socket flag This patch adds the NETLINK_NO_ENOBUFS socket flag. This flag can be used by unicast and broadcast listeners to avoid receiving ENOBUFS errors. Generally speaking, ENOBUFS errors are useful to notify two things to the listener: a) You may increase the receiver buffer size via setsockopt(). b) You have lost messages, you may be out of sync. In some cases, ignoring ENOBUFS errors can be useful. For example: a) nfnetlink_queue: this subsystem does not have any sort of resync method and you can decide to ignore ENOBUFS once you have set a given buffer size. b) ctnetlink: you can use this together with the socket flag NETLINK_BROADCAST_SEND_ERROR to stop getting ENOBUFS errors as you do not need to resync (packets whose event are not delivered are drop to provide reliable logging and state-synchronization). Moreover, the use of NETLINK_NO_ENOBUFS also reduces a "go up, go down" effect in terms of performance which is due to the netlink congestion control when the listener cannot back off. The effect is the following: 1) throughput rate goes up and netlink messages are inserted in the receiver buffer. 2) Then, netlink buffer fills and overruns (set on nlk->state bit 0). 3) While the listener empties the receiver buffer, netlink keeps dropping messages. Thus, throughput goes dramatically down. 4) Then, once the listener has emptied the buffer (nlk->state bit 0 is set off), goto step 1. This effect is easy to trigger with netlink broadcast under heavy load, and it is more noticeable when using a big receiver buffer. You can find some results in [1] that show this problem. [1] http://1984.lsi.us.es/linux/netlink/ This patch also includes the use of sk_drop to account the number of netlink messages drop due to overrun. This value is shown in /proc/net/netlink. Signed-off-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- include/linux/netlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 1e6bf995435..5ba398e9030 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -104,6 +104,7 @@ struct nlmsgerr #define NETLINK_DROP_MEMBERSHIP 2 #define NETLINK_PKTINFO 3 #define NETLINK_BROADCAST_ERROR 4 +#define NETLINK_NO_ENOBUFS 5 struct nl_pktinfo { -- cgit v1.2.3 From 2c0f3e96f3fc7bbd1cb3caa601f19cf030c2b958 Mon Sep 17 00:00:00 2001 From: Kay Sievers Date: Tue, 24 Mar 2009 16:38:23 -0700 Subject: wimax: struct device - replace bus_id with dev_name(), dev_set_name() Cc: inaky.perez-gonzalez@intel.com Cc: linux-wimax@intel.com Acked-by: Greg Kroah-Hartman Signed-off-by: Kay Sievers --- include/linux/wimax/debug.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/wimax/debug.h b/include/linux/wimax/debug.h index ba0c49399a8..c703e034042 100644 --- a/include/linux/wimax/debug.h +++ b/include/linux/wimax/debug.h @@ -178,7 +178,7 @@ void __d_head(char *head, size_t head_size, WARN_ON(1); } else snprintf(head, head_size, "%s %s: ", - dev_driver_string(dev), dev->bus_id); + dev_driver_string(dev), dev_name(dev)); } -- cgit v1.2.3 From 1fa5ae857bb14f6046205171d98506d8112dd74e Mon Sep 17 00:00:00 2001 From: Kay Sievers Date: Sun, 25 Jan 2009 15:17:37 +0100 Subject: driver core: get rid of struct device's bus_id string array Now that all users of bus_id is gone, we can remove it from struct device. Signed-off-by: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 4 +--- include/linux/kobject.h | 2 ++ 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 47f343c7bdd..d5706c448bc 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -374,7 +374,6 @@ struct device { struct device *parent; struct kobject kobj; - char bus_id[BUS_ID_SIZE]; /* position on parent bus */ unsigned uevent_suppress:1; const char *init_name; /* initial name of the device */ struct device_type *type; @@ -427,8 +426,7 @@ struct device { static inline const char *dev_name(const struct device *dev) { - /* will be changed into kobject_name(&dev->kobj) in the near future */ - return dev->bus_id; + return kobject_name(&dev->kobj); } extern int dev_set_name(struct device *dev, const char *name, ...) diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 5437ac0276e..c9c214d7bba 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -72,6 +72,8 @@ struct kobject { extern int kobject_set_name(struct kobject *kobj, const char *name, ...) __attribute__((format(printf, 2, 3))); +extern int kobject_set_name_vargs(struct kobject *kobj, const char *fmt, + va_list vargs); static inline const char *kobject_name(const struct kobject *kobj) { -- cgit v1.2.3 From 57fee4a58fe802272742caae248872c392a60670 Mon Sep 17 00:00:00 2001 From: Eric Miao Date: Wed, 4 Feb 2009 11:52:40 +0800 Subject: platform: introduce module id table for platform devices Now platform_device is being widely used on SoC processors where the peripherals are attached to the system bus, which is simple enough. However, silicon IPs for these SoCs are usually shared heavily across a family of processors, even products from different companies. This makes the original simple driver name based matching insufficient, or simply not straight-forward. Introduce a module id table for platform devices, and makes it clear that a platform driver is able to support some shared IP and handle slight differences across different platforms (by 'driver_data'). Module alias is handled automatically when a MODULE_DEVICE_TABLE() is defined. To not disturb the current platform drivers too much, the matched id entry is recorded and can be retrieved by platform_get_device_id(). Signed-off-by: Eric Miao Cc: Kay Sievers Cc: Ben Dooks Signed-off-by: Greg Kroah-Hartman --- include/linux/mod_devicetable.h | 9 +++++++++ include/linux/platform_device.h | 6 ++++++ 2 files changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index fde86671f48..1bf5900ffe4 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -454,4 +454,13 @@ struct dmi_system_id { #define DMI_MATCH(a, b) { a, b } +#define PLATFORM_NAME_SIZE 20 +#define PLATFORM_MODULE_PREFIX "platform:" + +struct platform_device_id { + char name[PLATFORM_NAME_SIZE]; + kernel_ulong_t driver_data + __attribute__((aligned(sizeof(kernel_ulong_t)))); +}; + #endif /* LINUX_MOD_DEVICETABLE_H */ diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index 9a342699c60..76aef7be32a 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -12,6 +12,7 @@ #define _PLATFORM_DEVICE_H_ #include +#include struct platform_device { const char * name; @@ -19,8 +20,12 @@ struct platform_device { struct device dev; u32 num_resources; struct resource * resource; + + struct platform_device_id *id_entry; }; +#define platform_get_device_id(pdev) ((pdev)->id_entry) + #define to_platform_device(x) container_of((x), struct platform_device, dev) extern int platform_device_register(struct platform_device *); @@ -56,6 +61,7 @@ struct platform_driver { int (*resume_early)(struct platform_device *); int (*resume)(struct platform_device *); struct device_driver driver; + struct platform_device_id *id_table; }; extern int platform_driver_register(struct platform_driver *); -- cgit v1.2.3 From 8205779114e8f612549d191f8e151526a74ab9f2 Mon Sep 17 00:00:00 2001 From: "Hans J. Koch" Date: Wed, 7 Jan 2009 00:15:39 +0100 Subject: UIO: Add name attributes for mappings and port regions If a UIO device has several memory mappings, it can be difficult for userspace to find the right one. The situation becomes even worse if the UIO driver can handle different versions of a card that have different numbers of mappings. Benedikt Spranger has such cards and pointed this out to me. Thanks, Bene! To address this problem, this patch adds "name" sysfs attributes for each mapping. Userspace can use these to clearly identify each mapping. The name string is optional. If a driver doesn't set it, an empty string will be returned, so this patch won't break existing drivers. The same problem exists for port region information, so a "name" attribute is added there, too. Signed-off-by: Hans J. Koch Signed-off-by: Greg Kroah-Hartman --- include/linux/uio_driver.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/uio_driver.h b/include/linux/uio_driver.h index a0bb6bd2e5c..5dcc9ff72f6 100644 --- a/include/linux/uio_driver.h +++ b/include/linux/uio_driver.h @@ -22,6 +22,7 @@ struct uio_map; /** * struct uio_mem - description of a UIO memory region + * @name: name of the memory region for identification * @addr: address of the device's memory * @size: size of IO * @memtype: type of memory addr points to @@ -29,6 +30,7 @@ struct uio_map; * @map: for use by the UIO core only. */ struct uio_mem { + const char *name; unsigned long addr; unsigned long size; int memtype; @@ -42,12 +44,14 @@ struct uio_portio; /** * struct uio_port - description of a UIO port region + * @name: name of the port region for identification * @start: start of port region * @size: size of port region * @porttype: type of port (see UIO_PORT_* below) * @portio: for use by the UIO core only. */ struct uio_port { + const char *name; unsigned long start; unsigned long size; int porttype; -- cgit v1.2.3 From b23530ebc339c4092ae2c9f37341a5398fea8b89 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Sat, 21 Feb 2009 16:45:07 +0800 Subject: driver core: remove polling for driver_probe_done(v5) This patch removes 100ms polling for driver_probe_done in wait_for_device_probe(), and uses wait_event() instead. Removing polling in fs initialization may lead to a faster boot. This patch also changes the return type of wait_for_device_done() from int to void. This patch is against Arjan's patch in linux-next tree. Signed-off-by: Ming Lei Acked-by: Cornelia Huck Reviewed-by: Arjan van de Ven Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index d5706c448bc..c56b154a0bf 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -147,7 +147,7 @@ extern void put_driver(struct device_driver *drv); extern struct device_driver *driver_find(const char *name, struct bus_type *bus); extern int driver_probe_done(void); -extern int wait_for_device_probe(void); +extern void wait_for_device_probe(void); /* sysfs interface for exporting driver attributes */ -- cgit v1.2.3 From fb069a5d132fb926ed17af3211a114ac7cf27d7a Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 16 Dec 2008 12:23:36 -0800 Subject: driver core: create a private portion of struct device This is to be used to move things out of struct device that no code outside of the driver core should ever touch. Cc: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index c56b154a0bf..4cf063fea2a 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -28,6 +28,7 @@ #define BUS_ID_SIZE 20 struct device; +struct device_private; struct device_driver; struct driver_private; struct class; @@ -373,6 +374,8 @@ struct device { struct klist_node knode_bus; struct device *parent; + struct device_private *p; + struct kobject kobj; unsigned uevent_suppress:1; const char *init_name; /* initial name of the device */ -- cgit v1.2.3 From f791b8c836307b58cbf62133a6a772ed1a92fb33 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 16 Dec 2008 12:24:56 -0800 Subject: driver core: move klist_children into private structure Nothing outside of the driver core should ever touch klist_children, or knode_parent, so move them out of the public eye. Cc: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 4cf063fea2a..808d808ec69 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -368,8 +368,6 @@ struct device_dma_parameters { }; struct device { - struct klist klist_children; - struct klist_node knode_parent; /* node in sibling list */ struct klist_node knode_driver; struct klist_node knode_bus; struct device *parent; -- cgit v1.2.3 From 8940b4f312dced51b45004819b776ec3aa7fcd5d Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 16 Dec 2008 12:25:49 -0800 Subject: driver core: move knode_driver into private structure Nothing outside of the driver core should ever touch knode_driver, so move it out of the public eye. Cc: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 808d808ec69..83e241f407b 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -368,7 +368,6 @@ struct device_dma_parameters { }; struct device { - struct klist_node knode_driver; struct klist_node knode_bus; struct device *parent; -- cgit v1.2.3 From ae1b41715ee2aae356fbcca032838b71d70b855f Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 16 Dec 2008 12:26:21 -0800 Subject: driver core: move knode_bus into private structure Nothing outside of the driver core should ever touch knode_bus, so move it out of the public eye. Cc: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 83e241f407b..5a64775e68e 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -368,7 +368,6 @@ struct device_dma_parameters { }; struct device { - struct klist_node knode_bus; struct device *parent; struct device_private *p; -- cgit v1.2.3 From 006f4571a15fae3a0575f2a0f9e9b63b3d1012f8 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Sun, 8 Mar 2009 23:13:32 +0800 Subject: driver core: move platform_data into platform_device This patch moves platform_data from struct device into struct platform_device, based on the two ideas: 1. Now all platform_driver is registered by platform_driver_register, which makes probe()/release()/... of platform_driver passed parameter of platform_device *, so platform driver can get platform_data from platform_device; 2. Other kind of devices do not need to use platform_data, we can decrease size of device if moving it to platform_device. Taking into consideration of thousands of files to be fixed and they can't be finished in one night(maybe it will take a long time), so we keep platform_data in device to allow two kind of cases coexist until all platform devices pass its platfrom data from platform_device->platform_data. All patches to do this kind of conversion are welcome. Signed-off-by: Ming Lei Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 9 +++++++-- include/linux/platform_device.h | 1 + 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 5a64775e68e..4bea53fe8f4 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -385,8 +385,13 @@ struct device { struct device_driver *driver; /* which driver has allocated this device */ void *driver_data; /* data private to the driver */ - void *platform_data; /* Platform specific data, device - core doesn't touch it */ + + void *platform_data; /* We will remove platform_data + field if all platform devices + pass its platform specific data + from platform_device->platform_data, + other kind of devices should not + use platform_data. */ struct dev_pm_info power; #ifdef CONFIG_NUMA diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index 76aef7be32a..76e470a299b 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -20,6 +20,7 @@ struct platform_device { struct device dev; u32 num_resources; struct resource * resource; + void *platform_data; struct platform_device_id *id_entry; }; -- cgit v1.2.3 From 4995f8ef9d3aac72745e12419d7fbaa8d01b1d81 Mon Sep 17 00:00:00 2001 From: Kay Sievers Date: Mon, 9 Mar 2009 14:18:52 +0100 Subject: vcs: hook sysfs devices into object lifetime instead of "binding" During bootup performance tracing I noticed many occurrences of vca* device creation and removal, leading to the usual userspace uevent processing, which are, in this case, rather pointless. A simple test showing the kernel timing (not including all the work userspace has to do), gives us these numbers: $ time for i in `seq 1000`; do echo a > /dev/tty2; done real 0m1.142s user 0m0.015s sys 0m0.540s If we move the hook for the vcs* driver core devices from the tty "binding" to the vc allocation/deallocation, which is what the vcs* devices represent, we get the following numbers: $ time for i in `seq 1000`; do echo a > /dev/tty2; done real 0m0.152s user 0m0.030s sys 0m0.072s Cc: Alan Cox Signed-off-by: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/console.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/console.h b/include/linux/console.h index a67a90cf826..dcca5339ceb 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -137,8 +137,8 @@ extern void resume_console(void); int mda_console_init(void); void prom_con_init(void); -void vcs_make_sysfs(struct tty_struct *tty); -void vcs_remove_sysfs(struct tty_struct *tty); +void vcs_make_sysfs(int index); +void vcs_remove_sysfs(int index); /* Some debug stub to catch some of the obvious races in the VT code */ #if 1 -- cgit v1.2.3 From f67f129e519fa87f8ebd236b6336fe43f31ee141 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Sun, 1 Mar 2009 21:10:49 +0800 Subject: Driver core: implement uevent suppress in kobject This patch implements uevent suppress in kobject and removes it from struct device, based on the following ideas: 1,Uevent sending should be one attribute of kobject, so suppressing it in kobject layer is more natural than in device layer. By this way, we can do it for other objects embedded with kobject. 2,It may save several bytes for each instance of struct device.(On my omap3(32bit ARM) based box, can save 8bytes per device object) This patch also introduces dev_set|get_uevent_suppress() helpers to set and query uevent_suppress attribute in case to help kobject as private part of struct device in future. [This version is against the latest driver-core patch set of Greg,please ignore the last version.] Signed-off-by: Ming Lei Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 11 ++++++++++- include/linux/kobject.h | 1 + 2 files changed, 11 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 4bea53fe8f4..914c1016dd8 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -373,7 +373,6 @@ struct device { struct device_private *p; struct kobject kobj; - unsigned uevent_suppress:1; const char *init_name; /* initial name of the device */ struct device_type *type; @@ -465,6 +464,16 @@ static inline void dev_set_drvdata(struct device *dev, void *data) dev->driver_data = data; } +static inline unsigned int dev_get_uevent_suppress(const struct device *dev) +{ + return dev->kobj.uevent_suppress; +} + +static inline void dev_set_uevent_suppress(struct device *dev, int val) +{ + dev->kobj.uevent_suppress = val; +} + static inline int device_is_registered(struct device *dev) { return dev->kobj.state_in_sysfs; diff --git a/include/linux/kobject.h b/include/linux/kobject.h index c9c214d7bba..58ae8e00fcd 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -68,6 +68,7 @@ struct kobject { unsigned int state_in_sysfs:1; unsigned int state_add_uevent_sent:1; unsigned int state_remove_uevent_sent:1; + unsigned int uevent_suppress:1; }; extern int kobject_set_name(struct kobject *kobj, const char *name, ...) -- cgit v1.2.3 From ffa6a7054d172a2f57248dff2de600ca795c5656 Mon Sep 17 00:00:00 2001 From: Cornelia Huck Date: Wed, 4 Mar 2009 12:44:00 +0100 Subject: Driver core: Fix device_move() vs. dpm list ordering, v2 dpm_list currently relies on the fact that child devices will be registered after their parents to get a correct suspend order. Using device_move() however destroys this assumption, as an already registered device may be moved under a newly registered one. This patch adds a new argument to device_move(), allowing callers to specify how dpm_list should be adapted. Signed-off-by: Cornelia Huck Acked-by: Alan Stern Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 3 ++- include/linux/pm.h | 11 +++++++++++ 2 files changed, 13 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 914c1016dd8..f98d0cfb4f8 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -494,7 +494,8 @@ extern int device_for_each_child(struct device *dev, void *data, extern struct device *device_find_child(struct device *dev, void *data, int (*match)(struct device *dev, void *data)); extern int device_rename(struct device *dev, char *new_name); -extern int device_move(struct device *dev, struct device *new_parent); +extern int device_move(struct device *dev, struct device *new_parent, + enum dpm_order dpm_order); /* * Root device objects for grouping under /sys/devices diff --git a/include/linux/pm.h b/include/linux/pm.h index 24ba5f67b3a..1d4e2d28982 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -400,6 +400,9 @@ extern void __suspend_report_result(const char *function, void *fn, int ret); #else /* !CONFIG_PM_SLEEP */ +#define device_pm_lock() do {} while (0) +#define device_pm_unlock() do {} while (0) + static inline int device_suspend(pm_message_t state) { return 0; @@ -409,6 +412,14 @@ static inline int device_suspend(pm_message_t state) #endif /* !CONFIG_PM_SLEEP */ +/* How to reorder dpm_list after device_move() */ +enum dpm_order { + DPM_ORDER_NONE, + DPM_ORDER_DEV_AFTER_PARENT, + DPM_ORDER_PARENT_BEFORE_DEV, + DPM_ORDER_DEV_LAST, +}; + /* * Global Power Management flags * Used to keep APM and ACPI from both being active -- cgit v1.2.3 From e9d376f0fa66bd630fe27403669c6ae6c22a868f Mon Sep 17 00:00:00 2001 From: Jason Baron Date: Thu, 5 Feb 2009 11:51:38 -0500 Subject: dynamic debug: combine dprintk and dynamic printk This patch combines Greg Bank's dprintk() work with the existing dynamic printk patchset, we are now calling it 'dynamic debug'. The new feature of this patchset is a richer /debugfs control file interface, (an example output from my system is at the bottom), which allows fined grained control over the the debug output. The output can be controlled by function, file, module, format string, and line number. for example, enabled all debug messages in module 'nf_conntrack': echo -n 'module nf_conntrack +p' > /mnt/debugfs/dynamic_debug/control to disable them: echo -n 'module nf_conntrack -p' > /mnt/debugfs/dynamic_debug/control A further explanation can be found in the documentation patch. Signed-off-by: Greg Banks Signed-off-by: Jason Baron Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 2 +- include/linux/dynamic_debug.h | 88 +++++++++++++++++++++++++++++++++++++++ include/linux/dynamic_printk.h | 93 ------------------------------------------ include/linux/kernel.h | 4 +- 4 files changed, 91 insertions(+), 96 deletions(-) create mode 100644 include/linux/dynamic_debug.h delete mode 100644 include/linux/dynamic_printk.h (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index f98d0cfb4f8..2918c0e8fdf 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -582,7 +582,7 @@ extern const char *dev_driver_string(const struct device *dev); #if defined(DEBUG) #define dev_dbg(dev, format, arg...) \ dev_printk(KERN_DEBUG , dev , format , ## arg) -#elif defined(CONFIG_DYNAMIC_PRINTK_DEBUG) +#elif defined(CONFIG_DYNAMIC_DEBUG) #define dev_dbg(dev, format, ...) do { \ dynamic_dev_dbg(dev, format, ##__VA_ARGS__); \ } while (0) diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h new file mode 100644 index 00000000000..07781aaa116 --- /dev/null +++ b/include/linux/dynamic_debug.h @@ -0,0 +1,88 @@ +#ifndef _DYNAMIC_DEBUG_H +#define _DYNAMIC_DEBUG_H + +/* dynamic_printk_enabled, and dynamic_printk_enabled2 are bitmasks in which + * bit n is set to 1 if any modname hashes into the bucket n, 0 otherwise. They + * use independent hash functions, to reduce the chance of false positives. + */ +extern long long dynamic_debug_enabled; +extern long long dynamic_debug_enabled2; + +/* + * An instance of this structure is created in a special + * ELF section at every dynamic debug callsite. At runtime, + * the special section is treated as an array of these. + */ +struct _ddebug { + /* + * These fields are used to drive the user interface + * for selecting and displaying debug callsites. + */ + const char *modname; + const char *function; + const char *filename; + const char *format; + char primary_hash; + char secondary_hash; + unsigned int lineno:24; + /* + * The flags field controls the behaviour at the callsite. + * The bits here are changed dynamically when the user + * writes commands to /dynamic_debug/ddebug + */ +#define _DPRINTK_FLAGS_PRINT (1<<0) /* printk() a message using the format */ +#define _DPRINTK_FLAGS_DEFAULT 0 + unsigned int flags:8; +} __attribute__((aligned(8))); + + +int ddebug_add_module(struct _ddebug *tab, unsigned int n, + const char *modname); + +#if defined(CONFIG_DYNAMIC_DEBUG) +extern int ddebug_remove_module(char *mod_name); + +#define __dynamic_dbg_enabled(dd) ({ \ + int __ret = 0; \ + if (unlikely((dynamic_debug_enabled & (1LL << DEBUG_HASH)) && \ + (dynamic_debug_enabled2 & (1LL << DEBUG_HASH2)))) \ + if (unlikely(dd.flags)) \ + __ret = 1; \ + __ret; }) + +#define dynamic_pr_debug(fmt, ...) do { \ + static struct _ddebug descriptor \ + __used \ + __attribute__((section("__verbose"), aligned(8))) = \ + { KBUILD_MODNAME, __func__, __FILE__, fmt, DEBUG_HASH, \ + DEBUG_HASH2, __LINE__, _DPRINTK_FLAGS_DEFAULT }; \ + if (__dynamic_dbg_enabled(descriptor)) \ + printk(KERN_DEBUG KBUILD_MODNAME ":" fmt, \ + ##__VA_ARGS__); \ + } while (0) + + +#define dynamic_dev_dbg(dev, fmt, ...) do { \ + static struct _ddebug descriptor \ + __used \ + __attribute__((section("__verbose"), aligned(8))) = \ + { KBUILD_MODNAME, __func__, __FILE__, fmt, DEBUG_HASH, \ + DEBUG_HASH2, __LINE__, _DPRINTK_FLAGS_DEFAULT }; \ + if (__dynamic_dbg_enabled(descriptor)) \ + dev_printk(KERN_DEBUG, dev, \ + KBUILD_MODNAME ": " fmt, \ + ##__VA_ARGS__); \ + } while (0) + +#else + +static inline int ddebug_remove_module(char *mod) +{ + return 0; +} + +#define dynamic_pr_debug(fmt, ...) do { } while (0) +#define dynamic_dev_dbg(dev, format, ...) do { } while (0) +#endif + +#endif diff --git a/include/linux/dynamic_printk.h b/include/linux/dynamic_printk.h deleted file mode 100644 index 2d528d00907..00000000000 --- a/include/linux/dynamic_printk.h +++ /dev/null @@ -1,93 +0,0 @@ -#ifndef _DYNAMIC_PRINTK_H -#define _DYNAMIC_PRINTK_H - -#define DYNAMIC_DEBUG_HASH_BITS 6 -#define DEBUG_HASH_TABLE_SIZE (1 << DYNAMIC_DEBUG_HASH_BITS) - -#define TYPE_BOOLEAN 1 - -#define DYNAMIC_ENABLED_ALL 0 -#define DYNAMIC_ENABLED_NONE 1 -#define DYNAMIC_ENABLED_SOME 2 - -extern int dynamic_enabled; - -/* dynamic_printk_enabled, and dynamic_printk_enabled2 are bitmasks in which - * bit n is set to 1 if any modname hashes into the bucket n, 0 otherwise. They - * use independent hash functions, to reduce the chance of false positives. - */ -extern long long dynamic_printk_enabled; -extern long long dynamic_printk_enabled2; - -struct mod_debug { - char *modname; - char *logical_modname; - char *flag_names; - int type; - int hash; - int hash2; -} __attribute__((aligned(8))); - -int register_dynamic_debug_module(char *mod_name, int type, char *share_name, - char *flags, int hash, int hash2); - -#if defined(CONFIG_DYNAMIC_PRINTK_DEBUG) -extern int unregister_dynamic_debug_module(char *mod_name); -extern int __dynamic_dbg_enabled_helper(char *modname, int type, - int value, int hash); - -#define __dynamic_dbg_enabled(module, type, value, level, hash) ({ \ - int __ret = 0; \ - if (unlikely((dynamic_printk_enabled & (1LL << DEBUG_HASH)) && \ - (dynamic_printk_enabled2 & (1LL << DEBUG_HASH2)))) \ - __ret = __dynamic_dbg_enabled_helper(module, type, \ - value, hash);\ - __ret; }) - -#define dynamic_pr_debug(fmt, ...) do { \ - static char mod_name[] \ - __attribute__((section("__verbose_strings"))) \ - = KBUILD_MODNAME; \ - static struct mod_debug descriptor \ - __used \ - __attribute__((section("__verbose"), aligned(8))) = \ - { mod_name, mod_name, NULL, TYPE_BOOLEAN, DEBUG_HASH, DEBUG_HASH2 };\ - if (__dynamic_dbg_enabled(KBUILD_MODNAME, TYPE_BOOLEAN, \ - 0, 0, DEBUG_HASH)) \ - printk(KERN_DEBUG KBUILD_MODNAME ":" fmt, \ - ##__VA_ARGS__); \ - } while (0) - -#define dynamic_dev_dbg(dev, format, ...) do { \ - static char mod_name[] \ - __attribute__((section("__verbose_strings"))) \ - = KBUILD_MODNAME; \ - static struct mod_debug descriptor \ - __used \ - __attribute__((section("__verbose"), aligned(8))) = \ - { mod_name, mod_name, NULL, TYPE_BOOLEAN, DEBUG_HASH, DEBUG_HASH2 };\ - if (__dynamic_dbg_enabled(KBUILD_MODNAME, TYPE_BOOLEAN, \ - 0, 0, DEBUG_HASH)) \ - dev_printk(KERN_DEBUG, dev, \ - KBUILD_MODNAME ": " format, \ - ##__VA_ARGS__); \ - } while (0) - -#else - -static inline int unregister_dynamic_debug_module(const char *mod_name) -{ - return 0; -} -static inline int __dynamic_dbg_enabled_helper(char *modname, int type, - int value, int hash) -{ - return 0; -} - -#define __dynamic_dbg_enabled(module, type, value, level, hash) ({ 0; }) -#define dynamic_pr_debug(fmt, ...) do { } while (0) -#define dynamic_dev_dbg(dev, format, ...) do { } while (0) -#endif - -#endif diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 7fa371898e3..b5496ecbec7 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -16,7 +16,7 @@ #include #include #include -#include +#include #include #include @@ -358,7 +358,7 @@ static inline char *pack_hex_byte(char *buf, u8 byte) #if defined(DEBUG) #define pr_debug(fmt, ...) \ printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) -#elif defined(CONFIG_DYNAMIC_PRINTK_DEBUG) +#elif defined(CONFIG_DYNAMIC_DEBUG) #define pr_debug(fmt, ...) do { \ dynamic_pr_debug(pr_fmt(fmt), ##__VA_ARGS__); \ } while (0) -- cgit v1.2.3 From e6e66b02e11563abdb7f69dcb7a2efbd8d577e77 Mon Sep 17 00:00:00 2001 From: Greg Banks Date: Wed, 11 Mar 2009 21:07:28 +1100 Subject: Dynamic debug: fix pr_fmt() build error When CONFIG_DYNAMIC_DEBUG is enabled, allow callers of pr_debug() to provide their own definition of pr_fmt() even if that definition uses tricks like #define pr_fmt(fmt) "%s:" fmt, __func__ Signed-off-by: Greg Banks Cc: Jason Baron Acked-by: Geert Uytterhoeven Signed-off-by: Greg Kroah-Hartman --- include/linux/dynamic_debug.h | 4 ++-- include/linux/kernel.h | 3 ++- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h index 07781aaa116..baabf33be24 100644 --- a/include/linux/dynamic_debug.h +++ b/include/linux/dynamic_debug.h @@ -57,7 +57,7 @@ extern int ddebug_remove_module(char *mod_name); { KBUILD_MODNAME, __func__, __FILE__, fmt, DEBUG_HASH, \ DEBUG_HASH2, __LINE__, _DPRINTK_FLAGS_DEFAULT }; \ if (__dynamic_dbg_enabled(descriptor)) \ - printk(KERN_DEBUG KBUILD_MODNAME ":" fmt, \ + printk(KERN_DEBUG KBUILD_MODNAME ":" pr_fmt(fmt), \ ##__VA_ARGS__); \ } while (0) @@ -70,7 +70,7 @@ extern int ddebug_remove_module(char *mod_name); DEBUG_HASH2, __LINE__, _DPRINTK_FLAGS_DEFAULT }; \ if (__dynamic_dbg_enabled(descriptor)) \ dev_printk(KERN_DEBUG, dev, \ - KBUILD_MODNAME ": " fmt, \ + KBUILD_MODNAME ": " pr_fmt(fmt),\ ##__VA_ARGS__); \ } while (0) diff --git a/include/linux/kernel.h b/include/linux/kernel.h index b5496ecbec7..914918abfdd 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -359,8 +359,9 @@ static inline char *pack_hex_byte(char *buf, u8 byte) #define pr_debug(fmt, ...) \ printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #elif defined(CONFIG_DYNAMIC_DEBUG) +/* dynamic_pr_debug() uses pr_fmt() internally so we don't need it here */ #define pr_debug(fmt, ...) do { \ - dynamic_pr_debug(pr_fmt(fmt), ##__VA_ARGS__); \ + dynamic_pr_debug(fmt, ##__VA_ARGS__); \ } while (0) #else #define pr_debug(fmt, ...) \ -- cgit v1.2.3 From 1a660164c291f41b2aa853a7269b310933574ef9 Mon Sep 17 00:00:00 2001 From: Mark Lord Date: Wed, 25 Feb 2009 15:18:32 -0500 Subject: [libata] Export ata_pio_queue_task() so that it can be used from sata_mv. Signed-off-by: Mark Lord Signed-off-by: Jeff Garzik --- include/linux/libata.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index dc18b87ed72..19af7d22a7f 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1008,6 +1008,9 @@ extern int ata_cable_sata(struct ata_port *ap); extern int ata_cable_ignore(struct ata_port *ap); extern int ata_cable_unknown(struct ata_port *ap); +extern void ata_pio_queue_task(struct ata_port *ap, void *data, + unsigned long delay); + /* Timing helpers */ extern unsigned int ata_pio_need_iordy(const struct ata_device *); extern const struct ata_timing *ata_timing_find_mode(u8 xfer_mode); -- cgit v1.2.3 From 22ddbd1e036ce035c1cccb2496aefafac79aba2c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Erik=20Inge=20Bols=C3=B8?= Date: Sat, 14 Mar 2009 21:37:48 +0100 Subject: include/linux/ata.h: add some more transfer masks MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Erik Inge Bolsø Signed-off-by: Jeff Garzik --- include/linux/ata.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ata.h b/include/linux/ata.h index 9a061accd8b..3901b0022cd 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -108,6 +108,8 @@ enum { ATA_PIO5 = ATA_PIO4 | (1 << 5), ATA_PIO6 = ATA_PIO5 | (1 << 6), + ATA_PIO4_ONLY = (1 << 4), + ATA_SWDMA0 = (1 << 0), ATA_SWDMA1 = ATA_SWDMA0 | (1 << 1), ATA_SWDMA2 = ATA_SWDMA1 | (1 << 2), @@ -117,6 +119,8 @@ enum { ATA_MWDMA0 = (1 << 0), ATA_MWDMA1 = ATA_MWDMA0 | (1 << 1), ATA_MWDMA2 = ATA_MWDMA1 | (1 << 2), + ATA_MWDMA3 = ATA_MWDMA2 | (1 << 3), + ATA_MWDMA4 = ATA_MWDMA3 | (1 << 4), ATA_MWDMA12_ONLY = (1 << 1) | (1 << 2), ATA_MWDMA2_ONLY = (1 << 2), @@ -131,6 +135,8 @@ enum { ATA_UDMA7 = ATA_UDMA6 | (1 << 7), /* ATA_UDMA7 is just for completeness... doesn't exist (yet?). */ + ATA_UDMA24_ONLY = (1 << 2) | (1 << 4), + ATA_UDMA_MASK_40C = ATA_UDMA2, /* udma0-2 */ /* DMA-related */ -- cgit v1.2.3 From 3d47aa8e7e7b2aa09256590388aa8dddc79280f9 Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Tue, 24 Mar 2009 10:23:19 +0000 Subject: [libata] Drain data on errors If the device is signalling that there is data to drain after an error we should read the bytes out and throw them away. Without this some devices and controllers get wedged and don't recover. Based on earlier work by Mark Lord Signed-off-by: Alan Cox Signed-off-by: Jeff Garzik --- include/linux/libata.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 19af7d22a7f..3a07a32dfc2 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -836,6 +836,8 @@ struct ata_port_operations { void (*bmdma_start)(struct ata_queued_cmd *qc); void (*bmdma_stop)(struct ata_queued_cmd *qc); u8 (*bmdma_status)(struct ata_port *ap); + + void (*drain_fifo)(struct ata_queued_cmd *qc); #endif /* CONFIG_ATA_SFF */ ssize_t (*em_show)(struct ata_port *ap, char *buf); @@ -1587,6 +1589,7 @@ extern int ata_sff_softreset(struct ata_link *link, unsigned int *classes, extern int sata_sff_hardreset(struct ata_link *link, unsigned int *class, unsigned long deadline); extern void ata_sff_postreset(struct ata_link *link, unsigned int *classes); +extern void ata_sff_drain_fifo(struct ata_queued_cmd *qc); extern void ata_sff_error_handler(struct ata_port *ap); extern void ata_sff_post_internal_cmd(struct ata_queued_cmd *qc); extern int ata_sff_port_start(struct ata_port *ap); -- cgit v1.2.3 From c96f1732e25362d10ee7bcac1df8412a2e6b7d23 Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Tue, 24 Mar 2009 10:23:46 +0000 Subject: [libata] Improve timeout handling On a timeout call a device specific handler early in the recovery so that we can complete and process successful commands which timed out due to IRQ loss or the like rather more elegantly. [Revised to exclude the timeout handling on a few devices that inherit from SFF but are not SFF enough to use the default timeout handler] Signed-off-by: Alan Cox Signed-off-by: Jeff Garzik --- include/linux/libata.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 3a07a32dfc2..76262d83656 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -795,6 +795,7 @@ struct ata_port_operations { ata_reset_fn_t pmp_hardreset; ata_postreset_fn_t pmp_postreset; void (*error_handler)(struct ata_port *ap); + void (*lost_interrupt)(struct ata_port *ap); void (*post_internal_cmd)(struct ata_queued_cmd *qc); /* @@ -1577,6 +1578,7 @@ extern bool ata_sff_qc_fill_rtf(struct ata_queued_cmd *qc); extern unsigned int ata_sff_host_intr(struct ata_port *ap, struct ata_queued_cmd *qc); extern irqreturn_t ata_sff_interrupt(int irq, void *dev_instance); +extern void ata_sff_lost_interrupt(struct ata_port *ap); extern void ata_sff_freeze(struct ata_port *ap); extern void ata_sff_thaw(struct ata_port *ap); extern int ata_sff_prereset(struct ata_link *link, unsigned long deadline); -- cgit v1.2.3 From 54aee6a5f560d0e1bf3f39987c6ebe06daeb0ce1 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 25 Mar 2009 09:13:24 -0700 Subject: dmaengine: kill some unused headers The dmaengine redux left some unneeded headers in include/linux/dmaengine.h, clean them up. Signed-off-by: Dan Williams --- include/linux/dmaengine.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 1956c8d46d3..96e676e5bf9 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -23,9 +23,6 @@ #include #include -#include -#include -#include #include /** -- cgit v1.2.3 From 06164f3194e01ea4c76941ac60f541d656c8975f Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 25 Mar 2009 09:13:25 -0700 Subject: async_tx: provide __async_inline for HAS_DMA=n archs To allow an async_tx routine to be compiled away on HAS_DMA=n arch it needs to be declared __always_inline otherwise the compiler may emit code and cause a link error. Signed-off-by: Dan Williams --- include/linux/async_tx.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/async_tx.h b/include/linux/async_tx.h index 45f6297821b..5fc2ef8d97f 100644 --- a/include/linux/async_tx.h +++ b/include/linux/async_tx.h @@ -21,6 +21,15 @@ #include #include +/* on architectures without dma-mapping capabilities we need to ensure + * that the asynchronous path compiles away + */ +#ifdef CONFIG_HAS_DMA +#define __async_inline +#else +#define __async_inline __always_inline +#endif + /** * dma_chan_ref - object used to manage dma channels received from the * dmaengine core. -- cgit v1.2.3 From 729b5d1b8ec72c28e99840b3f300ba67726e3ab9 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 25 Mar 2009 09:13:25 -0700 Subject: dmaengine: allow dma support for async_tx to be toggled Provide a config option for blocking the allocation of dma channels to the async_tx api. Signed-off-by: Dan Williams --- include/linux/dmaengine.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 96e676e5bf9..2afc2c95e42 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -288,6 +288,24 @@ static inline void net_dmaengine_put(void) } #endif +#ifdef CONFIG_ASYNC_TX_DMA +#define async_dmaengine_get() dmaengine_get() +#define async_dmaengine_put() dmaengine_put() +#define async_dma_find_channel(type) dma_find_channel(type) +#else +static inline void async_dmaengine_get(void) +{ +} +static inline void async_dmaengine_put(void) +{ +} +static inline struct dma_chan * +async_dma_find_channel(enum dma_transaction_type type) +{ + return NULL; +} +#endif + dma_cookie_t dma_async_memcpy_buf_to_buf(struct dma_chan *chan, void *dest, void *src, size_t len); dma_cookie_t dma_async_memcpy_buf_to_pg(struct dma_chan *chan, -- cgit v1.2.3 From b8dfe498775de912116f275680ddb57c8799d9ef Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 25 Mar 2009 17:31:52 +0100 Subject: netfilter: factorize ifname_compare() We use same not trivial helper function in four places. We can factorize it. Signed-off-by: Eric Dumazet Signed-off-by: Patrick McHardy --- include/linux/netfilter/x_tables.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index e8e08d03675..72918b7cbe8 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -435,6 +435,29 @@ extern void xt_free_table_info(struct xt_table_info *info); extern void xt_table_entry_swap_rcu(struct xt_table_info *old, struct xt_table_info *new); +/* + * This helper is performance critical and must be inlined + */ +static inline unsigned long ifname_compare_aligned(const char *_a, + const char *_b, + const char *_mask) +{ + const unsigned long *a = (const unsigned long *)_a; + const unsigned long *b = (const unsigned long *)_b; + const unsigned long *mask = (const unsigned long *)_mask; + unsigned long ret; + + ret = (a[0] ^ b[0]) & mask[0]; + if (IFNAMSIZ > sizeof(unsigned long)) + ret |= (a[1] ^ b[1]) & mask[1]; + if (IFNAMSIZ > 2 * sizeof(unsigned long)) + ret |= (a[2] ^ b[2]) & mask[2]; + if (IFNAMSIZ > 3 * sizeof(unsigned long)) + ret |= (a[3] ^ b[3]) & mask[3]; + BUILD_BUG_ON(IFNAMSIZ > 4 * sizeof(unsigned long)); + return ret; +} + #ifdef CONFIG_COMPAT #include -- cgit v1.2.3 From 0361a28d3f9a4315a100c7b37ba0b55cfe15fe07 Mon Sep 17 00:00:00 2001 From: Oliver Neukum Date: Wed, 17 Dec 2008 15:38:03 +0100 Subject: HID: autosuspend support for USB HID This uses the USB busy mechanism for aggessive autosuspend of USB HID devices. It autosuspends all opened devices supporting remote wakeup after a timeout unless - output is being done to the device - a key is being held down (remote wakeup isn't triggered upon key release) - LED(s) are lit - hiddev is opened As in the current driver closed devices will be autosuspended even if they don't support remote wakeup. The patch is quite large because output to devices is done in hard interrupt context meaning a lot a queuing and locking had to be touched. The LED stuff has been solved by means of a simple counter. Additions to the generic HID code could be avoided. In addition it now covers hidraw. It contains an embryonic version of an API to let the generic HID code tell the lower levels which capabilities with respect to power management are needed. Signed-off-by: Oliver Neukum Signed-off-by: Jiri Kosina --- include/linux/hid.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index fa8ee9cef7b..6ac7795a8ac 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -603,12 +603,17 @@ struct hid_ll_driver { int (*open)(struct hid_device *hdev); void (*close)(struct hid_device *hdev); + int (*power)(struct hid_device *hdev, int level); + int (*hidinput_input_event) (struct input_dev *idev, unsigned int type, unsigned int code, int value); int (*parse)(struct hid_device *hdev); }; +#define PM_HINT_FULLON 1<<5 +#define PM_HINT_NORMAL 1<<1 + /* Applications from HID Usage Tables 4/8/99 Version 1.1 */ /* We ignore a few input applications that are not widely used */ #define IS_INPUT_APPLICATION(a) (((a >= 0x00010000) && (a <= 0x00010008)) || (a == 0x00010080) || (a == 0x000c0001) || (a == 0x000d0002)) @@ -641,6 +646,7 @@ int hidinput_find_field(struct hid_device *hid, unsigned int type, unsigned int void hid_output_report(struct hid_report *report, __u8 *data); struct hid_device *hid_allocate_device(void); int hid_parse_report(struct hid_device *hid, __u8 *start, unsigned size); +int hid_check_keys_pressed(struct hid_device *hid); int hid_connect(struct hid_device *hid, unsigned int connect_mask); /** -- cgit v1.2.3 From f18df228997fb716990590d248663981a15f17d4 Mon Sep 17 00:00:00 2001 From: Mingming Cao Date: Tue, 13 Jan 2009 16:43:09 +0100 Subject: quota: Add quota reservation support Delayed allocation defers the block allocation at the dirty pages flush-out time, doing quota charge/check at that time is too late. But we can't charge the quota blocks until blocks are really allocated, otherwise users could get overcharged after reboot from system crash. This patch adds quota reservation for delayed allocation. Quota blocks are reserved in memory, inode and quota won't gets dirtied until later block allocation time. Signed-off-by: Mingming Cao Signed-off-by: Jan Kara --- include/linux/quota.h | 3 +++ include/linux/quotaops.h | 21 +++++++++++++++++++++ 2 files changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/quota.h b/include/linux/quota.h index d72d5d84fde..54b837fa64f 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -198,6 +198,7 @@ struct mem_dqblk { qsize_t dqb_bhardlimit; /* absolute limit on disk blks alloc */ qsize_t dqb_bsoftlimit; /* preferred limit on disk blks */ qsize_t dqb_curspace; /* current used space */ + qsize_t dqb_rsvspace; /* current reserved space for delalloc*/ qsize_t dqb_ihardlimit; /* absolute limit on allocated inodes */ qsize_t dqb_isoftlimit; /* preferred inode limit */ qsize_t dqb_curinodes; /* current # allocated inodes */ @@ -308,6 +309,8 @@ struct dquot_operations { int (*release_dquot) (struct dquot *); /* Quota is going to be deleted from disk */ int (*mark_dirty) (struct dquot *); /* Dquot is marked dirty */ int (*write_info) (struct super_block *, int); /* Write of quota "superblock" */ + /* reserve quota for delayed block allocation */ + int (*reserve_space) (struct inode *, qsize_t, int); }; /* Operations handling requests from userspace */ diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index 0b35b3a1be0..3e3a0d2874d 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -183,6 +183,16 @@ static inline int vfs_dq_alloc_space(struct inode *inode, qsize_t nr) return ret; } +static inline int vfs_dq_reserve_space(struct inode *inode, qsize_t nr) +{ + if (sb_any_quota_active(inode->i_sb)) { + /* Used space is updated in alloc_space() */ + if (inode->i_sb->dq_op->reserve_space(inode, nr, 0) == NO_QUOTA) + return 1; + } + return 0; +} + static inline int vfs_dq_alloc_inode(struct inode *inode) { if (sb_any_quota_active(inode->i_sb)) { @@ -339,6 +349,11 @@ static inline int vfs_dq_alloc_space(struct inode *inode, qsize_t nr) return 0; } +static inline int vfs_dq_reserve_space(struct inode *inode, qsize_t nr) +{ + return 0; +} + static inline void vfs_dq_free_space_nodirty(struct inode *inode, qsize_t nr) { inode_sub_bytes(inode, nr); @@ -376,6 +391,12 @@ static inline int vfs_dq_alloc_block(struct inode *inode, qsize_t nr) nr << inode->i_sb->s_blocksize_bits); } +static inline int vfs_dq_reserve_block(struct inode *inode, qsize_t nr) +{ + return vfs_dq_reserve_space(inode, + nr << inode->i_blkbits); +} + static inline void vfs_dq_free_block_nodirty(struct inode *inode, qsize_t nr) { vfs_dq_free_space_nodirty(inode, nr << inode->i_sb->s_blocksize_bits); -- cgit v1.2.3 From 740d9dcd949a986c88886a591054a0cdb89ef669 Mon Sep 17 00:00:00 2001 From: Mingming Cao Date: Tue, 13 Jan 2009 16:43:14 +0100 Subject: quota: Add quota reservation claim and released operations Reserved quota will be claimed at the block allocation time. Over-booked quota could be returned back with the release callback function. Signed-off-by: Mingming Cao Signed-off-by: Jan Kara --- include/linux/quota.h | 6 ++++++ include/linux/quotaops.h | 53 ++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 59 insertions(+) (limited to 'include/linux') diff --git a/include/linux/quota.h b/include/linux/quota.h index 54b837fa64f..a510d91561f 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -311,6 +311,12 @@ struct dquot_operations { int (*write_info) (struct super_block *, int); /* Write of quota "superblock" */ /* reserve quota for delayed block allocation */ int (*reserve_space) (struct inode *, qsize_t, int); + /* claim reserved quota for delayed alloc */ + int (*claim_space) (struct inode *, qsize_t); + /* release rsved quota for delayed alloc */ + void (*release_rsv) (struct inode *, qsize_t); + /* get reserved quota for delayed alloc */ + qsize_t (*get_reserved_space) (struct inode *); }; /* Operations handling requests from userspace */ diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index 3e3a0d2874d..7369d04e0a8 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -35,6 +35,11 @@ void dquot_destroy(struct dquot *dquot); int dquot_alloc_space(struct inode *inode, qsize_t number, int prealloc); int dquot_alloc_inode(const struct inode *inode, qsize_t number); +int dquot_reserve_space(struct inode *inode, qsize_t number, int prealloc); +int dquot_claim_space(struct inode *inode, qsize_t number); +void dquot_release_reserved_space(struct inode *inode, qsize_t number); +qsize_t dquot_get_reserved_space(struct inode *inode); + int dquot_free_space(struct inode *inode, qsize_t number); int dquot_free_inode(const struct inode *inode, qsize_t number); @@ -203,6 +208,31 @@ static inline int vfs_dq_alloc_inode(struct inode *inode) return 0; } +/* + * Convert in-memory reserved quotas to real consumed quotas + */ +static inline int vfs_dq_claim_space(struct inode *inode, qsize_t nr) +{ + if (sb_any_quota_active(inode->i_sb)) { + if (inode->i_sb->dq_op->claim_space(inode, nr) == NO_QUOTA) + return 1; + } else + inode_add_bytes(inode, nr); + + mark_inode_dirty(inode); + return 0; +} + +/* + * Release reserved (in-memory) quotas + */ +static inline +void vfs_dq_release_reservation_space(struct inode *inode, qsize_t nr) +{ + if (sb_any_quota_active(inode->i_sb)) + inode->i_sb->dq_op->release_rsv(inode, nr); +} + static inline void vfs_dq_free_space_nodirty(struct inode *inode, qsize_t nr) { if (sb_any_quota_active(inode->i_sb)) @@ -354,6 +384,17 @@ static inline int vfs_dq_reserve_space(struct inode *inode, qsize_t nr) return 0; } +static inline int vfs_dq_claim_space(struct inode *inode, qsize_t nr) +{ + return vfs_dq_alloc_space(inode, nr); +} + +static inline +int vfs_dq_release_reservation_space(struct inode *inode, qsize_t nr) +{ + return 0; +} + static inline void vfs_dq_free_space_nodirty(struct inode *inode, qsize_t nr) { inode_sub_bytes(inode, nr); @@ -397,6 +438,18 @@ static inline int vfs_dq_reserve_block(struct inode *inode, qsize_t nr) nr << inode->i_blkbits); } +static inline int vfs_dq_claim_block(struct inode *inode, qsize_t nr) +{ + return vfs_dq_claim_space(inode, + nr << inode->i_blkbits); +} + +static inline +void vfs_dq_release_reservation_block(struct inode *inode, qsize_t nr) +{ + vfs_dq_release_reservation_space(inode, nr << inode->i_blkbits); +} + static inline void vfs_dq_free_block_nodirty(struct inode *inode, qsize_t nr) { vfs_dq_free_space_nodirty(inode, nr << inode->i_sb->s_blocksize_bits); -- cgit v1.2.3 From 9900ba3487f9ba392db30e12d210f768a90abb13 Mon Sep 17 00:00:00 2001 From: Mingming Cao Date: Wed, 14 Jan 2009 16:18:57 +0100 Subject: quota: Use inode->i_blkbits to get block bits Andrew has suggested to use inode->i_blkbits to get the block bits info, rather than use super block's blockbits. That should be faster and emit less code. Signed-off-by: Mingming Cao Signed-off-by: Jan Kara --- include/linux/quotaops.h | 22 ++++++++-------------- 1 file changed, 8 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index 7369d04e0a8..69b502e5eba 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -410,38 +410,32 @@ static inline void vfs_dq_free_space(struct inode *inode, qsize_t nr) static inline int vfs_dq_prealloc_block_nodirty(struct inode *inode, qsize_t nr) { - return vfs_dq_prealloc_space_nodirty(inode, - nr << inode->i_sb->s_blocksize_bits); + return vfs_dq_prealloc_space_nodirty(inode, nr << inode->i_blkbits); } static inline int vfs_dq_prealloc_block(struct inode *inode, qsize_t nr) { - return vfs_dq_prealloc_space(inode, - nr << inode->i_sb->s_blocksize_bits); + return vfs_dq_prealloc_space(inode, nr << inode->i_blkbits); } static inline int vfs_dq_alloc_block_nodirty(struct inode *inode, qsize_t nr) { - return vfs_dq_alloc_space_nodirty(inode, - nr << inode->i_sb->s_blocksize_bits); + return vfs_dq_alloc_space_nodirty(inode, nr << inode->i_blkbits); } static inline int vfs_dq_alloc_block(struct inode *inode, qsize_t nr) { - return vfs_dq_alloc_space(inode, - nr << inode->i_sb->s_blocksize_bits); + return vfs_dq_alloc_space(inode, nr << inode->i_blkbits); } static inline int vfs_dq_reserve_block(struct inode *inode, qsize_t nr) { - return vfs_dq_reserve_space(inode, - nr << inode->i_blkbits); + return vfs_dq_reserve_space(inode, nr << inode->i_blkbits); } static inline int vfs_dq_claim_block(struct inode *inode, qsize_t nr) { - return vfs_dq_claim_space(inode, - nr << inode->i_blkbits); + return vfs_dq_claim_space(inode, nr << inode->i_blkbits); } static inline @@ -452,12 +446,12 @@ void vfs_dq_release_reservation_block(struct inode *inode, qsize_t nr) static inline void vfs_dq_free_block_nodirty(struct inode *inode, qsize_t nr) { - vfs_dq_free_space_nodirty(inode, nr << inode->i_sb->s_blocksize_bits); + vfs_dq_free_space_nodirty(inode, nr << inode->i_blkbits); } static inline void vfs_dq_free_block(struct inode *inode, qsize_t nr) { - vfs_dq_free_space(inode, nr << inode->i_sb->s_blocksize_bits); + vfs_dq_free_space(inode, nr << inode->i_blkbits); } /* -- cgit v1.2.3 From dd6f3c6d5a26a282521f15a183fdc2d6f35cfa0f Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 26 Jan 2009 16:01:43 +0100 Subject: quota: Remove NODQUOT macro Remove this macro which is just a definition of NULL. Fix a few coding style issues along the way. Signed-off-by: Jan Kara --- include/linux/quota.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/quota.h b/include/linux/quota.h index a510d91561f..78c48895b12 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -277,8 +277,6 @@ struct dquot { struct mem_dqblk dq_dqb; /* Diskquota usage */ }; -#define NODQUOT (struct dquot *)NULL - #define QUOTA_OK 0 #define NO_QUOTA 1 -- cgit v1.2.3 From bf84c82d000b9820b01f516d13d328f354f8a8ee Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 26 Jan 2009 17:37:01 +0100 Subject: quota: Remove uppercase aliases for quota functions. Since all users have been converted, remove uppercase names of quota functions. Signed-off-by: Jan Kara --- include/linux/quotaops.h | 31 ------------------------------- 1 file changed, 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index 69b502e5eba..36353d95c8d 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -454,35 +454,4 @@ static inline void vfs_dq_free_block(struct inode *inode, qsize_t nr) vfs_dq_free_space(inode, nr << inode->i_blkbits); } -/* - * Define uppercase equivalents for compatibility with old function names - * Can go away when we think all users have been converted (15/04/2008) - */ -#define DQUOT_INIT(inode) vfs_dq_init(inode) -#define DQUOT_DROP(inode) vfs_dq_drop(inode) -#define DQUOT_PREALLOC_SPACE_NODIRTY(inode, nr) \ - vfs_dq_prealloc_space_nodirty(inode, nr) -#define DQUOT_PREALLOC_SPACE(inode, nr) vfs_dq_prealloc_space(inode, nr) -#define DQUOT_ALLOC_SPACE_NODIRTY(inode, nr) \ - vfs_dq_alloc_space_nodirty(inode, nr) -#define DQUOT_ALLOC_SPACE(inode, nr) vfs_dq_alloc_space(inode, nr) -#define DQUOT_PREALLOC_BLOCK_NODIRTY(inode, nr) \ - vfs_dq_prealloc_block_nodirty(inode, nr) -#define DQUOT_PREALLOC_BLOCK(inode, nr) vfs_dq_prealloc_block(inode, nr) -#define DQUOT_ALLOC_BLOCK_NODIRTY(inode, nr) \ - vfs_dq_alloc_block_nodirty(inode, nr) -#define DQUOT_ALLOC_BLOCK(inode, nr) vfs_dq_alloc_block(inode, nr) -#define DQUOT_ALLOC_INODE(inode) vfs_dq_alloc_inode(inode) -#define DQUOT_FREE_SPACE_NODIRTY(inode, nr) \ - vfs_dq_free_space_nodirty(inode, nr) -#define DQUOT_FREE_SPACE(inode, nr) vfs_dq_free_space(inode, nr) -#define DQUOT_FREE_BLOCK_NODIRTY(inode, nr) \ - vfs_dq_free_block_nodirty(inode, nr) -#define DQUOT_FREE_BLOCK(inode, nr) vfs_dq_free_block(inode, nr) -#define DQUOT_FREE_INODE(inode) vfs_dq_free_inode(inode) -#define DQUOT_TRANSFER(inode, iattr) vfs_dq_transfer(inode, iattr) -#define DQUOT_SYNC(sb) vfs_dq_sync(sb) -#define DQUOT_OFF(sb, remount) vfs_dq_off(sb, remount) -#define DQUOT_ON_REMOUNT(sb) vfs_dq_quota_on_remount(sb) - #endif /* _LINUX_QUOTAOPS_ */ -- cgit v1.2.3 From 7058548cd50e5bda8db086bb2e5c1d82f746d047 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Wed, 25 Mar 2009 23:35:46 -0400 Subject: ext4: Use WRITE_SYNC for commits which are caused by fsync() If a commit is triggered by fsync(), set a flag indicating the journal blocks associated with the transaction should be flushed out using WRITE_SYNC. Signed-off-by: "Theodore Ts'o" --- include/linux/jbd2.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 4d248b3f132..8815a3456b3 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -648,6 +648,12 @@ struct transaction_s */ int t_handle_count; + /* + * This transaction is being forced and some process is + * waiting for it to finish. + */ + int t_synchronous_commit:1; + /* * For use by the filesystem to store fs-specific data * structures associated with the transaction -- cgit v1.2.3 From 0f571515c332e00b3515dbe0859ceaa30ab66e00 Mon Sep 17 00:00:00 2001 From: Atsushi Nemoto Date: Fri, 6 Mar 2009 20:07:14 +0900 Subject: dmaengine: Add privatecnt to revert DMA_PRIVATE property Currently dma_request_channel() set DMA_PRIVATE capability but never clear it. So if a public channel was once grabbed by dma_request_channel(), the device stay PRIVATE forever. Add privatecnt member to dma_device to correctly revert it. [lg@denx.de: fix bad usage of 'chan' in dma_async_device_register] Signed-off-by: Atsushi Nemoto Acked-by: Maciej Sosnowski Signed-off-by: Dan Williams --- include/linux/dmaengine.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 2afc2c95e42..2e2aa3df170 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -202,6 +202,7 @@ struct dma_async_tx_descriptor { /** * struct dma_device - info on the entity supplying DMA services * @chancnt: how many DMA channels are supported + * @privatecnt: how many DMA channels are requested by dma_request_channel * @channels: the list of struct dma_chan * @global_node: list_head for global dma_device_list * @cap_mask: one or more dma_capability flags @@ -224,6 +225,7 @@ struct dma_async_tx_descriptor { struct dma_device { unsigned int chancnt; + unsigned int privatecnt; struct list_head channels; struct list_head global_node; dma_cap_mask_t cap_mask; @@ -352,6 +354,13 @@ __dma_cap_set(enum dma_transaction_type tx_type, dma_cap_mask_t *dstp) set_bit(tx_type, dstp->bits); } +#define dma_cap_clear(tx, mask) __dma_cap_clear((tx), &(mask)) +static inline void +__dma_cap_clear(enum dma_transaction_type tx_type, dma_cap_mask_t *dstp) +{ + clear_bit(tx_type, dstp->bits); +} + #define dma_cap_zero(mask) __dma_cap_zero(&(mask)) static inline void __dma_cap_zero(dma_cap_mask_t *dstp) { -- cgit v1.2.3 From 9d50638bae05ab7f62d700c9e4a83a1845cf9ef4 Mon Sep 17 00:00:00 2001 From: Jaswinder Singh Rajput Date: Sun, 8 Feb 2009 11:00:25 +0530 Subject: unconditionally include asm/types.h from linux/types.h Reported-by: Sam Ravnborg Signed-off-by: Jaswinder Singh Rajput Signed-off-by: Ingo Molnar --- include/linux/types.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/types.h b/include/linux/types.h index c30973ace89..fca82ed55f4 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -1,6 +1,8 @@ #ifndef _LINUX_TYPES_H #define _LINUX_TYPES_H +#include + #ifndef __ASSEMBLY__ #ifdef __KERNEL__ @@ -10,7 +12,6 @@ #endif #include -#include #ifndef __KERNEL_STRICT_NAMES -- cgit v1.2.3 From 85efde6f4e0de9577256c5f0030088d3fd4347c1 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 26 Feb 2009 00:51:39 +0100 Subject: make exported headers use strict posix types A number of standard posix types are used in exported headers, which is not allowed if __STRICT_KERNEL_NAMES is defined. In order to get rid of the non-__STRICT_KERNEL_NAMES part and to make sane headers the default, we have to change them all to safe types. There are also still some leftovers in reiserfs_fs.h, elfcore.h and coda.h, but these files have not compiled in user space for a long time. This leaves out the various integer types ({u_,u,}int{8,16,32,64}_t), which we take care of separately. Signed-off-by: Arnd Bergmann Acked-by: Mauro Carvalho Chehab Cc: David Airlie Cc: Arnaldo Carvalho de Melo Cc: YOSHIFUJI Hideaki Cc: netdev@vger.kernel.org Cc: linux-ppp@vger.kernel.org Cc: Jaroslav Kysela Cc: Takashi Iwai Cc: David Woodhouse Signed-off-by: H. Peter Anvin Signed-off-by: Ingo Molnar --- include/linux/agpgart.h | 14 +++++++------- include/linux/cn_proc.h | 20 ++++++++++---------- include/linux/cyclades.h | 6 +++--- include/linux/dvb/video.h | 2 +- include/linux/if_pppol2tp.h | 2 +- include/linux/mroute6.h | 2 +- include/linux/netfilter_ipv4/ipt_owner.h | 8 ++++---- include/linux/netfilter_ipv6/ip6t_owner.h | 8 ++++---- include/linux/ppp_defs.h | 4 ++-- include/linux/suspend_ioctls.h | 11 ++++++----- include/linux/time.h | 8 ++++---- include/linux/times.h | 8 ++++---- include/linux/utime.h | 4 ++-- include/linux/xfrm.h | 2 +- 14 files changed, 50 insertions(+), 49 deletions(-) (limited to 'include/linux') diff --git a/include/linux/agpgart.h b/include/linux/agpgart.h index 110c600c885..f6778eceb8f 100644 --- a/include/linux/agpgart.h +++ b/include/linux/agpgart.h @@ -77,20 +77,20 @@ typedef struct _agp_setup { * The "prot" down below needs still a "sleep" flag somehow ... */ typedef struct _agp_segment { - off_t pg_start; /* starting page to populate */ - size_t pg_count; /* number of pages */ - int prot; /* prot flags for mmap */ + __kernel_off_t pg_start; /* starting page to populate */ + __kernel_size_t pg_count; /* number of pages */ + int prot; /* prot flags for mmap */ } agp_segment; typedef struct _agp_region { - pid_t pid; /* pid of process */ - size_t seg_count; /* number of segments */ + __kernel_pid_t pid; /* pid of process */ + __kernel_size_t seg_count; /* number of segments */ struct _agp_segment *seg_list; } agp_region; typedef struct _agp_allocate { int key; /* tag of allocation */ - size_t pg_count; /* number of pages */ + __kernel_size_t pg_count;/* number of pages */ __u32 type; /* 0 == normal, other devspec */ __u32 physical; /* device specific (some devices * need a phys address of the @@ -100,7 +100,7 @@ typedef struct _agp_allocate { typedef struct _agp_bind { int key; /* tag of allocation */ - off_t pg_start; /* starting page to populate */ + __kernel_off_t pg_start;/* starting page to populate */ } agp_bind; typedef struct _agp_unbind { diff --git a/include/linux/cn_proc.h b/include/linux/cn_proc.h index 1c86d65bc4b..b8125b2eb66 100644 --- a/include/linux/cn_proc.h +++ b/include/linux/cn_proc.h @@ -65,20 +65,20 @@ struct proc_event { } ack; struct fork_proc_event { - pid_t parent_pid; - pid_t parent_tgid; - pid_t child_pid; - pid_t child_tgid; + __kernel_pid_t parent_pid; + __kernel_pid_t parent_tgid; + __kernel_pid_t child_pid; + __kernel_pid_t child_tgid; } fork; struct exec_proc_event { - pid_t process_pid; - pid_t process_tgid; + __kernel_pid_t process_pid; + __kernel_pid_t process_tgid; } exec; struct id_proc_event { - pid_t process_pid; - pid_t process_tgid; + __kernel_pid_t process_pid; + __kernel_pid_t process_tgid; union { __u32 ruid; /* task uid */ __u32 rgid; /* task gid */ @@ -90,8 +90,8 @@ struct proc_event { } id; struct exit_proc_event { - pid_t process_pid; - pid_t process_tgid; + __kernel_pid_t process_pid; + __kernel_pid_t process_tgid; __u32 exit_code, exit_signal; } exit; } event_data; diff --git a/include/linux/cyclades.h b/include/linux/cyclades.h index d06fbf28634..788850ba4e7 100644 --- a/include/linux/cyclades.h +++ b/include/linux/cyclades.h @@ -82,9 +82,9 @@ struct cyclades_monitor { * open) */ struct cyclades_idle_stats { - time_t in_use; /* Time device has been in use (secs) */ - time_t recv_idle; /* Time since last char received (secs) */ - time_t xmit_idle; /* Time since last char transmitted (secs) */ + __kernel_time_t in_use; /* Time device has been in use (secs) */ + __kernel_time_t recv_idle; /* Time since last char received (secs) */ + __kernel_time_t xmit_idle; /* Time since last char transmitted (secs) */ unsigned long recv_bytes; /* Bytes received */ unsigned long xmit_bytes; /* Bytes transmitted */ unsigned long overruns; /* Input overruns */ diff --git a/include/linux/dvb/video.h b/include/linux/dvb/video.h index bd49c3ebf91..ee5d2df2d78 100644 --- a/include/linux/dvb/video.h +++ b/include/linux/dvb/video.h @@ -137,7 +137,7 @@ struct video_event { #define VIDEO_EVENT_FRAME_RATE_CHANGED 2 #define VIDEO_EVENT_DECODER_STOPPED 3 #define VIDEO_EVENT_VSYNC 4 - time_t timestamp; + __kernel_time_t timestamp; union { video_size_t size; unsigned int frame_rate; /* in frames per 1000sec */ diff --git a/include/linux/if_pppol2tp.h b/include/linux/if_pppol2tp.h index c7a66882b6d..3a14b088c8e 100644 --- a/include/linux/if_pppol2tp.h +++ b/include/linux/if_pppol2tp.h @@ -26,7 +26,7 @@ */ struct pppol2tp_addr { - pid_t pid; /* pid that owns the fd. + __kernel_pid_t pid; /* pid that owns the fd. * 0 => current */ int fd; /* FD of UDP socket to use */ diff --git a/include/linux/mroute6.h b/include/linux/mroute6.h index 5375faca1f7..43dc97e3218 100644 --- a/include/linux/mroute6.h +++ b/include/linux/mroute6.h @@ -65,7 +65,7 @@ struct mif6ctl { mifi_t mif6c_mifi; /* Index of MIF */ unsigned char mif6c_flags; /* MIFF_ flags */ unsigned char vifc_threshold; /* ttl limit */ - u_short mif6c_pifi; /* the index of the physical IF */ + __u16 mif6c_pifi; /* the index of the physical IF */ unsigned int vifc_rate_limit; /* Rate limiter values (NI) */ }; diff --git a/include/linux/netfilter_ipv4/ipt_owner.h b/include/linux/netfilter_ipv4/ipt_owner.h index 92f4bdac54e..a78445be999 100644 --- a/include/linux/netfilter_ipv4/ipt_owner.h +++ b/include/linux/netfilter_ipv4/ipt_owner.h @@ -9,10 +9,10 @@ #define IPT_OWNER_COMM 0x10 struct ipt_owner_info { - uid_t uid; - gid_t gid; - pid_t pid; - pid_t sid; + __kernel_uid32_t uid; + __kernel_gid32_t gid; + __kernel_pid_t pid; + __kernel_pid_t sid; char comm[16]; u_int8_t match, invert; /* flags */ }; diff --git a/include/linux/netfilter_ipv6/ip6t_owner.h b/include/linux/netfilter_ipv6/ip6t_owner.h index 19937da3d10..ec5cc7a38c4 100644 --- a/include/linux/netfilter_ipv6/ip6t_owner.h +++ b/include/linux/netfilter_ipv6/ip6t_owner.h @@ -8,10 +8,10 @@ #define IP6T_OWNER_SID 0x08 struct ip6t_owner_info { - uid_t uid; - gid_t gid; - pid_t pid; - pid_t sid; + __kernel_uid32_t uid; + __kernel_gid32_t gid; + __kernel_pid_t pid; + __kernel_pid_t sid; u_int8_t match, invert; /* flags */ }; diff --git a/include/linux/ppp_defs.h b/include/linux/ppp_defs.h index 1c866bda201..0f93ed6b4a8 100644 --- a/include/linux/ppp_defs.h +++ b/include/linux/ppp_defs.h @@ -177,8 +177,8 @@ struct ppp_comp_stats { * the last NP packet was sent or received. */ struct ppp_idle { - time_t xmit_idle; /* time since last NP packet sent */ - time_t recv_idle; /* time since last NP packet received */ + __kernel_time_t xmit_idle; /* time since last NP packet sent */ + __kernel_time_t recv_idle; /* time since last NP packet received */ }; #endif /* _PPP_DEFS_H_ */ diff --git a/include/linux/suspend_ioctls.h b/include/linux/suspend_ioctls.h index 2c6faec96bd..0b30382984f 100644 --- a/include/linux/suspend_ioctls.h +++ b/include/linux/suspend_ioctls.h @@ -1,14 +1,15 @@ #ifndef _LINUX_SUSPEND_IOCTLS_H #define _LINUX_SUSPEND_IOCTLS_H +#include /* * This structure is used to pass the values needed for the identification * of the resume swap area from a user space to the kernel via the * SNAPSHOT_SET_SWAP_AREA ioctl */ struct resume_swap_area { - loff_t offset; - u_int32_t dev; + __kernel_loff_t offset; + __u32 dev; } __attribute__((packed)); #define SNAPSHOT_IOC_MAGIC '3' @@ -20,13 +21,13 @@ struct resume_swap_area { #define SNAPSHOT_S2RAM _IO(SNAPSHOT_IOC_MAGIC, 11) #define SNAPSHOT_SET_SWAP_AREA _IOW(SNAPSHOT_IOC_MAGIC, 13, \ struct resume_swap_area) -#define SNAPSHOT_GET_IMAGE_SIZE _IOR(SNAPSHOT_IOC_MAGIC, 14, loff_t) +#define SNAPSHOT_GET_IMAGE_SIZE _IOR(SNAPSHOT_IOC_MAGIC, 14, __kernel_loff_t) #define SNAPSHOT_PLATFORM_SUPPORT _IO(SNAPSHOT_IOC_MAGIC, 15) #define SNAPSHOT_POWER_OFF _IO(SNAPSHOT_IOC_MAGIC, 16) #define SNAPSHOT_CREATE_IMAGE _IOW(SNAPSHOT_IOC_MAGIC, 17, int) #define SNAPSHOT_PREF_IMAGE_SIZE _IO(SNAPSHOT_IOC_MAGIC, 18) -#define SNAPSHOT_AVAIL_SWAP_SIZE _IOR(SNAPSHOT_IOC_MAGIC, 19, loff_t) -#define SNAPSHOT_ALLOC_SWAP_PAGE _IOR(SNAPSHOT_IOC_MAGIC, 20, loff_t) +#define SNAPSHOT_AVAIL_SWAP_SIZE _IOR(SNAPSHOT_IOC_MAGIC, 19, __kernel_loff_t) +#define SNAPSHOT_ALLOC_SWAP_PAGE _IOR(SNAPSHOT_IOC_MAGIC, 20, __kernel_loff_t) #define SNAPSHOT_IOC_MAXNR 20 #endif /* _LINUX_SUSPEND_IOCTLS_H */ diff --git a/include/linux/time.h b/include/linux/time.h index fbbd2a1c92b..242f62499bb 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -12,14 +12,14 @@ #ifndef _STRUCT_TIMESPEC #define _STRUCT_TIMESPEC struct timespec { - time_t tv_sec; /* seconds */ - long tv_nsec; /* nanoseconds */ + __kernel_time_t tv_sec; /* seconds */ + long tv_nsec; /* nanoseconds */ }; #endif struct timeval { - time_t tv_sec; /* seconds */ - suseconds_t tv_usec; /* microseconds */ + __kernel_time_t tv_sec; /* seconds */ + __kernel_suseconds_t tv_usec; /* microseconds */ }; struct timezone { diff --git a/include/linux/times.h b/include/linux/times.h index e2d3020742a..87b62615ced 100644 --- a/include/linux/times.h +++ b/include/linux/times.h @@ -4,10 +4,10 @@ #include struct tms { - clock_t tms_utime; - clock_t tms_stime; - clock_t tms_cutime; - clock_t tms_cstime; + __kernel_clock_t tms_utime; + __kernel_clock_t tms_stime; + __kernel_clock_t tms_cutime; + __kernel_clock_t tms_cstime; }; #endif diff --git a/include/linux/utime.h b/include/linux/utime.h index 640be6a1959..5cdf673afbd 100644 --- a/include/linux/utime.h +++ b/include/linux/utime.h @@ -4,8 +4,8 @@ #include struct utimbuf { - time_t actime; - time_t modtime; + __kernel_time_t actime; + __kernel_time_t modtime; }; #endif diff --git a/include/linux/xfrm.h b/include/linux/xfrm.h index 52f3abd453a..2d4ec15abac 100644 --- a/include/linux/xfrm.h +++ b/include/linux/xfrm.h @@ -58,7 +58,7 @@ struct xfrm_selector __u8 prefixlen_s; __u8 proto; int ifindex; - uid_t user; + __kernel_uid32_t user; }; #define XFRM_INF (~(__u64)0) -- cgit v1.2.3 From 9adfbfb611307060db54691bc7e6d53fdc12312b Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 26 Feb 2009 00:51:40 +0100 Subject: make most exported headers use strict integer types This takes care of all files that have only a small number of non-strict integer type uses. Signed-off-by: Arnd Bergmann Cc: Mauro Carvalho Chehab Cc: David Airlie Cc: Arnaldo Carvalho de Melo Cc: YOSHIFUJI Hideaki Cc: netdev@vger.kernel.org Cc: linux-ppp@vger.kernel.org Cc: Jaroslav Kysela Cc: Takashi Iwai Cc: David Woodhouse Signed-off-by: H. Peter Anvin Signed-off-by: Ingo Molnar --- include/linux/atmlec.h | 5 +- include/linux/atmmpc.h | 45 ++++---- include/linux/cm4000_cs.h | 10 +- include/linux/dlm_netlink.h | 18 +-- include/linux/dm-ioctl.h | 42 +++---- include/linux/dvb/audio.h | 2 +- include/linux/dvb/video.h | 22 ++-- include/linux/if_arcnet.h | 27 ++--- include/linux/ip_vs.h | 26 ++--- include/linux/ivtvfb.h | 2 +- include/linux/matroxfb.h | 2 +- include/linux/pfkeyv2.h | 242 ++++++++++++++++++++-------------------- include/linux/selinux_netlink.h | 6 +- 13 files changed, 229 insertions(+), 220 deletions(-) (limited to 'include/linux') diff --git a/include/linux/atmlec.h b/include/linux/atmlec.h index 6f5a1bab8f5..39c917fd1b9 100644 --- a/include/linux/atmlec.h +++ b/include/linux/atmlec.h @@ -11,6 +11,7 @@ #include #include #include +#include /* ATM lec daemon control socket */ #define ATMLEC_CTRL _IO('a', ATMIOC_LANE) @@ -78,8 +79,8 @@ struct atmlec_msg { } normal; struct atmlec_config_msg config; struct { - uint16_t lec_id; /* requestor lec_id */ - uint32_t tran_id; /* transaction id */ + __u16 lec_id; /* requestor lec_id */ + __u32 tran_id; /* transaction id */ unsigned char mac_addr[ETH_ALEN]; /* dst mac addr */ unsigned char atm_addr[ATM_ESA_LEN]; /* reqestor ATM addr */ } proxy; /* diff --git a/include/linux/atmmpc.h b/include/linux/atmmpc.h index ea1650425a1..2aba5787fa6 100644 --- a/include/linux/atmmpc.h +++ b/include/linux/atmmpc.h @@ -4,6 +4,7 @@ #include #include #include +#include #define ATMMPC_CTRL _IO('a', ATMIOC_MPOA) #define ATMMPC_DATA _IO('a', ATMIOC_MPOA+1) @@ -18,39 +19,39 @@ struct atmmpc_ioc { }; typedef struct in_ctrl_info { - uint8_t Last_NHRP_CIE_code; - uint8_t Last_Q2931_cause_value; - uint8_t eg_MPC_ATM_addr[ATM_ESA_LEN]; + __u8 Last_NHRP_CIE_code; + __u8 Last_Q2931_cause_value; + __u8 eg_MPC_ATM_addr[ATM_ESA_LEN]; __be32 tag; __be32 in_dst_ip; /* IP address this ingress MPC sends packets to */ - uint16_t holding_time; - uint32_t request_id; + __u16 holding_time; + __u32 request_id; } in_ctrl_info; typedef struct eg_ctrl_info { - uint8_t DLL_header[256]; - uint8_t DH_length; + __u8 DLL_header[256]; + __u8 DH_length; __be32 cache_id; __be32 tag; __be32 mps_ip; __be32 eg_dst_ip; /* IP address to which ingress MPC sends packets */ - uint8_t in_MPC_data_ATM_addr[ATM_ESA_LEN]; - uint16_t holding_time; + __u8 in_MPC_data_ATM_addr[ATM_ESA_LEN]; + __u16 holding_time; } eg_ctrl_info; struct mpc_parameters { - uint16_t mpc_p1; /* Shortcut-Setup Frame Count */ - uint16_t mpc_p2; /* Shortcut-Setup Frame Time */ - uint8_t mpc_p3[8]; /* Flow-detection Protocols */ - uint16_t mpc_p4; /* MPC Initial Retry Time */ - uint16_t mpc_p5; /* MPC Retry Time Maximum */ - uint16_t mpc_p6; /* Hold Down Time */ + __u16 mpc_p1; /* Shortcut-Setup Frame Count */ + __u16 mpc_p2; /* Shortcut-Setup Frame Time */ + __u8 mpc_p3[8]; /* Flow-detection Protocols */ + __u16 mpc_p4; /* MPC Initial Retry Time */ + __u16 mpc_p5; /* MPC Retry Time Maximum */ + __u16 mpc_p6; /* Hold Down Time */ } ; struct k_message { - uint16_t type; + __u16 type; __be32 ip_mask; - uint8_t MPS_ctrl[ATM_ESA_LEN]; + __u8 MPS_ctrl[ATM_ESA_LEN]; union { in_ctrl_info in_info; eg_ctrl_info eg_info; @@ -61,11 +62,11 @@ struct k_message { struct llc_snap_hdr { /* RFC 1483 LLC/SNAP encapsulation for routed IP PDUs */ - uint8_t dsap; /* Destination Service Access Point (0xAA) */ - uint8_t ssap; /* Source Service Access Point (0xAA) */ - uint8_t ui; /* Unnumbered Information (0x03) */ - uint8_t org[3]; /* Organizational identification (0x000000) */ - uint8_t type[2]; /* Ether type (for IP) (0x0800) */ + __u8 dsap; /* Destination Service Access Point (0xAA) */ + __u8 ssap; /* Source Service Access Point (0xAA) */ + __u8 ui; /* Unnumbered Information (0x03) */ + __u8 org[3]; /* Organizational identification (0x000000) */ + __u8 type[2]; /* Ether type (for IP) (0x0800) */ }; /* TLVs this MPC recognizes */ diff --git a/include/linux/cm4000_cs.h b/include/linux/cm4000_cs.h index 605ebe24bb2..72bfefdbd76 100644 --- a/include/linux/cm4000_cs.h +++ b/include/linux/cm4000_cs.h @@ -1,6 +1,8 @@ #ifndef _CM4000_H_ #define _CM4000_H_ +#include + #define MAX_ATR 33 #define CM4000_MAX_DEV 4 @@ -10,9 +12,9 @@ * not to break compilation of userspace apps. -HW */ typedef struct atreq { - int32_t atr_len; + __s32 atr_len; unsigned char atr[64]; - int32_t power_act; + __s32 power_act; unsigned char bIFSD; unsigned char bIFSC; } atreq_t; @@ -22,13 +24,13 @@ typedef struct atreq { * member sizes. This leads to CONFIG_COMPAT breakage, since 32bit userspace * will lay out the structure members differently than the 64bit kernel. * - * I've changed "ptsreq.protocol" from "unsigned long" to "u_int32_t". + * I've changed "ptsreq.protocol" from "unsigned long" to "__u32". * On 32bit this will make no difference. With 64bit kernels, it will make * 32bit apps work, too. */ typedef struct ptsreq { - u_int32_t protocol; /*T=0: 2^0, T=1: 2^1*/ + __u32 protocol; /*T=0: 2^0, T=1: 2^1*/ unsigned char flags; unsigned char pts1; unsigned char pts2; diff --git a/include/linux/dlm_netlink.h b/include/linux/dlm_netlink.h index 19276332707..647c8ef2722 100644 --- a/include/linux/dlm_netlink.h +++ b/include/linux/dlm_netlink.h @@ -9,6 +9,8 @@ #ifndef _DLM_NETLINK_H #define _DLM_NETLINK_H +#include + enum { DLM_STATUS_WAITING = 1, DLM_STATUS_GRANTED = 2, @@ -18,16 +20,16 @@ enum { #define DLM_LOCK_DATA_VERSION 1 struct dlm_lock_data { - uint16_t version; - uint32_t lockspace_id; + __u16 version; + __u32 lockspace_id; int nodeid; int ownpid; - uint32_t id; - uint32_t remid; - uint64_t xid; - int8_t status; - int8_t grmode; - int8_t rqmode; + __u32 id; + __u32 remid; + __u64 xid; + __s8 status; + __s8 grmode; + __s8 rqmode; unsigned long timestamp; int resource_namelen; char resource_name[DLM_RESNAME_MAXLEN]; diff --git a/include/linux/dm-ioctl.h b/include/linux/dm-ioctl.h index 28c2940eb30..48e44ee2b46 100644 --- a/include/linux/dm-ioctl.h +++ b/include/linux/dm-ioctl.h @@ -113,20 +113,20 @@ struct dm_ioctl { * return -ENOTTY) fill out this field, even if the * command failed. */ - uint32_t version[3]; /* in/out */ - uint32_t data_size; /* total size of data passed in + __u32 version[3]; /* in/out */ + __u32 data_size; /* total size of data passed in * including this struct */ - uint32_t data_start; /* offset to start of data + __u32 data_start; /* offset to start of data * relative to start of this struct */ - uint32_t target_count; /* in/out */ - int32_t open_count; /* out */ - uint32_t flags; /* in/out */ - uint32_t event_nr; /* in/out */ - uint32_t padding; + __u32 target_count; /* in/out */ + __s32 open_count; /* out */ + __u32 flags; /* in/out */ + __u32 event_nr; /* in/out */ + __u32 padding; - uint64_t dev; /* in/out */ + __u64 dev; /* in/out */ char name[DM_NAME_LEN]; /* device name */ char uuid[DM_UUID_LEN]; /* unique identifier for @@ -139,9 +139,9 @@ struct dm_ioctl { * dm_ioctl. */ struct dm_target_spec { - uint64_t sector_start; - uint64_t length; - int32_t status; /* used when reading from kernel only */ + __u64 sector_start; + __u64 length; + __s32 status; /* used when reading from kernel only */ /* * Location of the next dm_target_spec. @@ -153,7 +153,7 @@ struct dm_target_spec { * (that follows the dm_ioctl struct) to the start of the "next" * dm_target_spec. */ - uint32_t next; + __u32 next; char target_type[DM_MAX_TYPE_NAME]; @@ -168,17 +168,17 @@ struct dm_target_spec { * Used to retrieve the target dependencies. */ struct dm_target_deps { - uint32_t count; /* Array size */ - uint32_t padding; /* unused */ - uint64_t dev[0]; /* out */ + __u32 count; /* Array size */ + __u32 padding; /* unused */ + __u64 dev[0]; /* out */ }; /* * Used to get a list of all dm devices. */ struct dm_name_list { - uint64_t dev; - uint32_t next; /* offset to the next record from + __u64 dev; + __u32 next; /* offset to the next record from the _start_ of this */ char name[0]; }; @@ -187,8 +187,8 @@ struct dm_name_list { * Used to retrieve the target versions */ struct dm_target_versions { - uint32_t next; - uint32_t version[3]; + __u32 next; + __u32 version[3]; char name[0]; }; @@ -197,7 +197,7 @@ struct dm_target_versions { * Used to pass message to a target */ struct dm_target_msg { - uint64_t sector; /* Device sector */ + __u64 sector; /* Device sector */ char message[0]; }; diff --git a/include/linux/dvb/audio.h b/include/linux/dvb/audio.h index bb0df2aaebf..fec66bd24f2 100644 --- a/include/linux/dvb/audio.h +++ b/include/linux/dvb/audio.h @@ -76,7 +76,7 @@ struct audio_karaoke{ /* if Vocal1 or Vocal2 are non-zero, they get mixed */ } audio_karaoke_t; /* into left and right */ -typedef uint16_t audio_attributes_t; +typedef __u16 audio_attributes_t; /* bits: descr. */ /* 15-13 audio coding mode (0=ac3, 2=mpeg1, 3=mpeg2ext, 4=LPCM, 6=DTS, */ /* 12 multichannel extension */ diff --git a/include/linux/dvb/video.h b/include/linux/dvb/video.h index ee5d2df2d78..1d750c0fd86 100644 --- a/include/linux/dvb/video.h +++ b/include/linux/dvb/video.h @@ -132,7 +132,7 @@ struct video_command { #define VIDEO_VSYNC_FIELD_PROGRESSIVE (3) struct video_event { - int32_t type; + __s32 type; #define VIDEO_EVENT_SIZE_CHANGED 1 #define VIDEO_EVENT_FRAME_RATE_CHANGED 2 #define VIDEO_EVENT_DECODER_STOPPED 3 @@ -157,25 +157,25 @@ struct video_status { struct video_still_picture { char __user *iFrame; /* pointer to a single iframe in memory */ - int32_t size; + __s32 size; }; typedef struct video_highlight { int active; /* 1=show highlight, 0=hide highlight */ - uint8_t contrast1; /* 7- 4 Pattern pixel contrast */ + __u8 contrast1; /* 7- 4 Pattern pixel contrast */ /* 3- 0 Background pixel contrast */ - uint8_t contrast2; /* 7- 4 Emphasis pixel-2 contrast */ + __u8 contrast2; /* 7- 4 Emphasis pixel-2 contrast */ /* 3- 0 Emphasis pixel-1 contrast */ - uint8_t color1; /* 7- 4 Pattern pixel color */ + __u8 color1; /* 7- 4 Pattern pixel color */ /* 3- 0 Background pixel color */ - uint8_t color2; /* 7- 4 Emphasis pixel-2 color */ + __u8 color2; /* 7- 4 Emphasis pixel-2 color */ /* 3- 0 Emphasis pixel-1 color */ - uint32_t ypos; /* 23-22 auto action mode */ + __u32 ypos; /* 23-22 auto action mode */ /* 21-12 start y */ /* 9- 0 end y */ - uint32_t xpos; /* 23-22 button color number */ + __u32 xpos; /* 23-22 button color number */ /* 21-12 start x */ /* 9- 0 end x */ } video_highlight_t; @@ -189,17 +189,17 @@ typedef struct video_spu { typedef struct video_spu_palette { /* SPU Palette information */ int length; - uint8_t __user *palette; + __u8 __user *palette; } video_spu_palette_t; typedef struct video_navi_pack { int length; /* 0 ... 1024 */ - uint8_t data[1024]; + __u8 data[1024]; } video_navi_pack_t; -typedef uint16_t video_attributes_t; +typedef __u16 video_attributes_t; /* bits: descr. */ /* 15-14 Video compression mode (0=MPEG-1, 1=MPEG-2) */ /* 13-12 TV system (0=525/60, 1=625/50) */ diff --git a/include/linux/if_arcnet.h b/include/linux/if_arcnet.h index 27ea2ac445a..0835debab11 100644 --- a/include/linux/if_arcnet.h +++ b/include/linux/if_arcnet.h @@ -16,6 +16,7 @@ #ifndef _LINUX_IF_ARCNET_H #define _LINUX_IF_ARCNET_H +#include #include @@ -57,10 +58,10 @@ */ struct arc_rfc1201 { - uint8_t proto; /* protocol ID field - varies */ - uint8_t split_flag; /* for use with split packets */ + __u8 proto; /* protocol ID field - varies */ + __u8 split_flag; /* for use with split packets */ __be16 sequence; /* sequence number */ - uint8_t payload[0]; /* space remaining in packet (504 bytes)*/ + __u8 payload[0]; /* space remaining in packet (504 bytes)*/ }; #define RFC1201_HDR_SIZE 4 @@ -70,8 +71,8 @@ struct arc_rfc1201 */ struct arc_rfc1051 { - uint8_t proto; /* ARC_P_RFC1051_ARP/RFC1051_IP */ - uint8_t payload[0]; /* 507 bytes */ + __u8 proto; /* ARC_P_RFC1051_ARP/RFC1051_IP */ + __u8 payload[0]; /* 507 bytes */ }; #define RFC1051_HDR_SIZE 1 @@ -82,20 +83,20 @@ struct arc_rfc1051 */ struct arc_eth_encap { - uint8_t proto; /* Always ARC_P_ETHER */ + __u8 proto; /* Always ARC_P_ETHER */ struct ethhdr eth; /* standard ethernet header (yuck!) */ - uint8_t payload[0]; /* 493 bytes */ + __u8 payload[0]; /* 493 bytes */ }; #define ETH_ENCAP_HDR_SIZE 14 struct arc_cap { - uint8_t proto; - uint8_t cookie[sizeof(int)]; /* Actually NOT sent over the network */ + __u8 proto; + __u8 cookie[sizeof(int)]; /* Actually NOT sent over the network */ union { - uint8_t ack; - uint8_t raw[0]; /* 507 bytes */ + __u8 ack; + __u8 raw[0]; /* 507 bytes */ } mes; }; @@ -109,7 +110,7 @@ struct arc_cap */ struct arc_hardware { - uint8_t source, /* source ARCnet - filled in automagically */ + __u8 source, /* source ARCnet - filled in automagically */ dest, /* destination ARCnet - 0 for broadcast */ offset[2]; /* offset bytes (some weird semantics) */ }; @@ -130,7 +131,7 @@ struct archdr struct arc_rfc1051 rfc1051; struct arc_eth_encap eth_encap; struct arc_cap cap; - uint8_t raw[0]; /* 508 bytes */ + __u8 raw[0]; /* 508 bytes */ } soft; }; diff --git a/include/linux/ip_vs.h b/include/linux/ip_vs.h index 0f434a28fb5..148265e63e8 100644 --- a/include/linux/ip_vs.h +++ b/include/linux/ip_vs.h @@ -96,10 +96,10 @@ */ struct ip_vs_service_user { /* virtual service addresses */ - u_int16_t protocol; + __u16 protocol; __be32 addr; /* virtual ip address */ __be16 port; - u_int32_t fwmark; /* firwall mark of service */ + __u32 fwmark; /* firwall mark of service */ /* virtual service options */ char sched_name[IP_VS_SCHEDNAME_MAXLEN]; @@ -119,8 +119,8 @@ struct ip_vs_dest_user { int weight; /* destination weight */ /* thresholds for active connections */ - u_int32_t u_threshold; /* upper threshold */ - u_int32_t l_threshold; /* lower threshold */ + __u32 u_threshold; /* upper threshold */ + __u32 l_threshold; /* lower threshold */ }; @@ -159,10 +159,10 @@ struct ip_vs_getinfo { /* The argument to IP_VS_SO_GET_SERVICE */ struct ip_vs_service_entry { /* which service: user fills in these */ - u_int16_t protocol; + __u16 protocol; __be32 addr; /* virtual address */ __be16 port; - u_int32_t fwmark; /* firwall mark of service */ + __u32 fwmark; /* firwall mark of service */ /* service options */ char sched_name[IP_VS_SCHEDNAME_MAXLEN]; @@ -184,12 +184,12 @@ struct ip_vs_dest_entry { unsigned conn_flags; /* connection flags */ int weight; /* destination weight */ - u_int32_t u_threshold; /* upper threshold */ - u_int32_t l_threshold; /* lower threshold */ + __u32 u_threshold; /* upper threshold */ + __u32 l_threshold; /* lower threshold */ - u_int32_t activeconns; /* active connections */ - u_int32_t inactconns; /* inactive connections */ - u_int32_t persistconns; /* persistent connections */ + __u32 activeconns; /* active connections */ + __u32 inactconns; /* inactive connections */ + __u32 persistconns; /* persistent connections */ /* statistics */ struct ip_vs_stats_user stats; @@ -199,10 +199,10 @@ struct ip_vs_dest_entry { /* The argument to IP_VS_SO_GET_DESTS */ struct ip_vs_get_dests { /* which service: user fills in these */ - u_int16_t protocol; + __u16 protocol; __be32 addr; /* virtual address */ __be16 port; - u_int32_t fwmark; /* firwall mark of service */ + __u32 fwmark; /* firwall mark of service */ /* number of real servers */ unsigned int num_dests; diff --git a/include/linux/ivtvfb.h b/include/linux/ivtvfb.h index e20af47b59a..9d88b29ddf5 100644 --- a/include/linux/ivtvfb.h +++ b/include/linux/ivtvfb.h @@ -33,6 +33,6 @@ struct ivtvfb_dma_frame { }; #define IVTVFB_IOC_DMA_FRAME _IOW('V', BASE_VIDIOC_PRIVATE+0, struct ivtvfb_dma_frame) -#define FBIO_WAITFORVSYNC _IOW('F', 0x20, u_int32_t) +#define FBIO_WAITFORVSYNC _IOW('F', 0x20, __u32) #endif diff --git a/include/linux/matroxfb.h b/include/linux/matroxfb.h index 404f678e734..2203121a43e 100644 --- a/include/linux/matroxfb.h +++ b/include/linux/matroxfb.h @@ -37,7 +37,7 @@ enum matroxfb_ctrl_id { MATROXFB_CID_LAST }; -#define FBIO_WAITFORVSYNC _IOW('F', 0x20, u_int32_t) +#define FBIO_WAITFORVSYNC _IOW('F', 0x20, __u32) #endif diff --git a/include/linux/pfkeyv2.h b/include/linux/pfkeyv2.h index 01b262959f2..228b0b6306b 100644 --- a/include/linux/pfkeyv2.h +++ b/include/linux/pfkeyv2.h @@ -12,187 +12,187 @@ #define PFKEYV2_REVISION 199806L struct sadb_msg { - uint8_t sadb_msg_version; - uint8_t sadb_msg_type; - uint8_t sadb_msg_errno; - uint8_t sadb_msg_satype; - uint16_t sadb_msg_len; - uint16_t sadb_msg_reserved; - uint32_t sadb_msg_seq; - uint32_t sadb_msg_pid; + __u8 sadb_msg_version; + __u8 sadb_msg_type; + __u8 sadb_msg_errno; + __u8 sadb_msg_satype; + __u16 sadb_msg_len; + __u16 sadb_msg_reserved; + __u32 sadb_msg_seq; + __u32 sadb_msg_pid; } __attribute__((packed)); /* sizeof(struct sadb_msg) == 16 */ struct sadb_ext { - uint16_t sadb_ext_len; - uint16_t sadb_ext_type; + __u16 sadb_ext_len; + __u16 sadb_ext_type; } __attribute__((packed)); /* sizeof(struct sadb_ext) == 4 */ struct sadb_sa { - uint16_t sadb_sa_len; - uint16_t sadb_sa_exttype; + __u16 sadb_sa_len; + __u16 sadb_sa_exttype; __be32 sadb_sa_spi; - uint8_t sadb_sa_replay; - uint8_t sadb_sa_state; - uint8_t sadb_sa_auth; - uint8_t sadb_sa_encrypt; - uint32_t sadb_sa_flags; + __u8 sadb_sa_replay; + __u8 sadb_sa_state; + __u8 sadb_sa_auth; + __u8 sadb_sa_encrypt; + __u32 sadb_sa_flags; } __attribute__((packed)); /* sizeof(struct sadb_sa) == 16 */ struct sadb_lifetime { - uint16_t sadb_lifetime_len; - uint16_t sadb_lifetime_exttype; - uint32_t sadb_lifetime_allocations; - uint64_t sadb_lifetime_bytes; - uint64_t sadb_lifetime_addtime; - uint64_t sadb_lifetime_usetime; + __u16 sadb_lifetime_len; + __u16 sadb_lifetime_exttype; + __u32 sadb_lifetime_allocations; + __u64 sadb_lifetime_bytes; + __u64 sadb_lifetime_addtime; + __u64 sadb_lifetime_usetime; } __attribute__((packed)); /* sizeof(struct sadb_lifetime) == 32 */ struct sadb_address { - uint16_t sadb_address_len; - uint16_t sadb_address_exttype; - uint8_t sadb_address_proto; - uint8_t sadb_address_prefixlen; - uint16_t sadb_address_reserved; + __u16 sadb_address_len; + __u16 sadb_address_exttype; + __u8 sadb_address_proto; + __u8 sadb_address_prefixlen; + __u16 sadb_address_reserved; } __attribute__((packed)); /* sizeof(struct sadb_address) == 8 */ struct sadb_key { - uint16_t sadb_key_len; - uint16_t sadb_key_exttype; - uint16_t sadb_key_bits; - uint16_t sadb_key_reserved; + __u16 sadb_key_len; + __u16 sadb_key_exttype; + __u16 sadb_key_bits; + __u16 sadb_key_reserved; } __attribute__((packed)); /* sizeof(struct sadb_key) == 8 */ struct sadb_ident { - uint16_t sadb_ident_len; - uint16_t sadb_ident_exttype; - uint16_t sadb_ident_type; - uint16_t sadb_ident_reserved; - uint64_t sadb_ident_id; + __u16 sadb_ident_len; + __u16 sadb_ident_exttype; + __u16 sadb_ident_type; + __u16 sadb_ident_reserved; + __u64 sadb_ident_id; } __attribute__((packed)); /* sizeof(struct sadb_ident) == 16 */ struct sadb_sens { - uint16_t sadb_sens_len; - uint16_t sadb_sens_exttype; - uint32_t sadb_sens_dpd; - uint8_t sadb_sens_sens_level; - uint8_t sadb_sens_sens_len; - uint8_t sadb_sens_integ_level; - uint8_t sadb_sens_integ_len; - uint32_t sadb_sens_reserved; + __u16 sadb_sens_len; + __u16 sadb_sens_exttype; + __u32 sadb_sens_dpd; + __u8 sadb_sens_sens_level; + __u8 sadb_sens_sens_len; + __u8 sadb_sens_integ_level; + __u8 sadb_sens_integ_len; + __u32 sadb_sens_reserved; } __attribute__((packed)); /* sizeof(struct sadb_sens) == 16 */ /* followed by: - uint64_t sadb_sens_bitmap[sens_len]; - uint64_t sadb_integ_bitmap[integ_len]; */ + __u64 sadb_sens_bitmap[sens_len]; + __u64 sadb_integ_bitmap[integ_len]; */ struct sadb_prop { - uint16_t sadb_prop_len; - uint16_t sadb_prop_exttype; - uint8_t sadb_prop_replay; - uint8_t sadb_prop_reserved[3]; + __u16 sadb_prop_len; + __u16 sadb_prop_exttype; + __u8 sadb_prop_replay; + __u8 sadb_prop_reserved[3]; } __attribute__((packed)); /* sizeof(struct sadb_prop) == 8 */ /* followed by: struct sadb_comb sadb_combs[(sadb_prop_len + - sizeof(uint64_t) - sizeof(struct sadb_prop)) / + sizeof(__u64) - sizeof(struct sadb_prop)) / sizeof(struct sadb_comb)]; */ struct sadb_comb { - uint8_t sadb_comb_auth; - uint8_t sadb_comb_encrypt; - uint16_t sadb_comb_flags; - uint16_t sadb_comb_auth_minbits; - uint16_t sadb_comb_auth_maxbits; - uint16_t sadb_comb_encrypt_minbits; - uint16_t sadb_comb_encrypt_maxbits; - uint32_t sadb_comb_reserved; - uint32_t sadb_comb_soft_allocations; - uint32_t sadb_comb_hard_allocations; - uint64_t sadb_comb_soft_bytes; - uint64_t sadb_comb_hard_bytes; - uint64_t sadb_comb_soft_addtime; - uint64_t sadb_comb_hard_addtime; - uint64_t sadb_comb_soft_usetime; - uint64_t sadb_comb_hard_usetime; + __u8 sadb_comb_auth; + __u8 sadb_comb_encrypt; + __u16 sadb_comb_flags; + __u16 sadb_comb_auth_minbits; + __u16 sadb_comb_auth_maxbits; + __u16 sadb_comb_encrypt_minbits; + __u16 sadb_comb_encrypt_maxbits; + __u32 sadb_comb_reserved; + __u32 sadb_comb_soft_allocations; + __u32 sadb_comb_hard_allocations; + __u64 sadb_comb_soft_bytes; + __u64 sadb_comb_hard_bytes; + __u64 sadb_comb_soft_addtime; + __u64 sadb_comb_hard_addtime; + __u64 sadb_comb_soft_usetime; + __u64 sadb_comb_hard_usetime; } __attribute__((packed)); /* sizeof(struct sadb_comb) == 72 */ struct sadb_supported { - uint16_t sadb_supported_len; - uint16_t sadb_supported_exttype; - uint32_t sadb_supported_reserved; + __u16 sadb_supported_len; + __u16 sadb_supported_exttype; + __u32 sadb_supported_reserved; } __attribute__((packed)); /* sizeof(struct sadb_supported) == 8 */ /* followed by: struct sadb_alg sadb_algs[(sadb_supported_len + - sizeof(uint64_t) - sizeof(struct sadb_supported)) / + sizeof(__u64) - sizeof(struct sadb_supported)) / sizeof(struct sadb_alg)]; */ struct sadb_alg { - uint8_t sadb_alg_id; - uint8_t sadb_alg_ivlen; - uint16_t sadb_alg_minbits; - uint16_t sadb_alg_maxbits; - uint16_t sadb_alg_reserved; + __u8 sadb_alg_id; + __u8 sadb_alg_ivlen; + __u16 sadb_alg_minbits; + __u16 sadb_alg_maxbits; + __u16 sadb_alg_reserved; } __attribute__((packed)); /* sizeof(struct sadb_alg) == 8 */ struct sadb_spirange { - uint16_t sadb_spirange_len; - uint16_t sadb_spirange_exttype; - uint32_t sadb_spirange_min; - uint32_t sadb_spirange_max; - uint32_t sadb_spirange_reserved; + __u16 sadb_spirange_len; + __u16 sadb_spirange_exttype; + __u32 sadb_spirange_min; + __u32 sadb_spirange_max; + __u32 sadb_spirange_reserved; } __attribute__((packed)); /* sizeof(struct sadb_spirange) == 16 */ struct sadb_x_kmprivate { - uint16_t sadb_x_kmprivate_len; - uint16_t sadb_x_kmprivate_exttype; - uint32_t sadb_x_kmprivate_reserved; + __u16 sadb_x_kmprivate_len; + __u16 sadb_x_kmprivate_exttype; + __u32 sadb_x_kmprivate_reserved; } __attribute__((packed)); /* sizeof(struct sadb_x_kmprivate) == 8 */ struct sadb_x_sa2 { - uint16_t sadb_x_sa2_len; - uint16_t sadb_x_sa2_exttype; - uint8_t sadb_x_sa2_mode; - uint8_t sadb_x_sa2_reserved1; - uint16_t sadb_x_sa2_reserved2; - uint32_t sadb_x_sa2_sequence; - uint32_t sadb_x_sa2_reqid; + __u16 sadb_x_sa2_len; + __u16 sadb_x_sa2_exttype; + __u8 sadb_x_sa2_mode; + __u8 sadb_x_sa2_reserved1; + __u16 sadb_x_sa2_reserved2; + __u32 sadb_x_sa2_sequence; + __u32 sadb_x_sa2_reqid; } __attribute__((packed)); /* sizeof(struct sadb_x_sa2) == 16 */ struct sadb_x_policy { - uint16_t sadb_x_policy_len; - uint16_t sadb_x_policy_exttype; - uint16_t sadb_x_policy_type; - uint8_t sadb_x_policy_dir; - uint8_t sadb_x_policy_reserved; - uint32_t sadb_x_policy_id; - uint32_t sadb_x_policy_priority; + __u16 sadb_x_policy_len; + __u16 sadb_x_policy_exttype; + __u16 sadb_x_policy_type; + __u8 sadb_x_policy_dir; + __u8 sadb_x_policy_reserved; + __u32 sadb_x_policy_id; + __u32 sadb_x_policy_priority; } __attribute__((packed)); /* sizeof(struct sadb_x_policy) == 16 */ struct sadb_x_ipsecrequest { - uint16_t sadb_x_ipsecrequest_len; - uint16_t sadb_x_ipsecrequest_proto; - uint8_t sadb_x_ipsecrequest_mode; - uint8_t sadb_x_ipsecrequest_level; - uint16_t sadb_x_ipsecrequest_reserved1; - uint32_t sadb_x_ipsecrequest_reqid; - uint32_t sadb_x_ipsecrequest_reserved2; + __u16 sadb_x_ipsecrequest_len; + __u16 sadb_x_ipsecrequest_proto; + __u8 sadb_x_ipsecrequest_mode; + __u8 sadb_x_ipsecrequest_level; + __u16 sadb_x_ipsecrequest_reserved1; + __u32 sadb_x_ipsecrequest_reqid; + __u32 sadb_x_ipsecrequest_reserved2; } __attribute__((packed)); /* sizeof(struct sadb_x_ipsecrequest) == 16 */ @@ -200,38 +200,38 @@ struct sadb_x_ipsecrequest { * type of NAT-T is supported, draft-ietf-ipsec-udp-encaps-06 */ struct sadb_x_nat_t_type { - uint16_t sadb_x_nat_t_type_len; - uint16_t sadb_x_nat_t_type_exttype; - uint8_t sadb_x_nat_t_type_type; - uint8_t sadb_x_nat_t_type_reserved[3]; + __u16 sadb_x_nat_t_type_len; + __u16 sadb_x_nat_t_type_exttype; + __u8 sadb_x_nat_t_type_type; + __u8 sadb_x_nat_t_type_reserved[3]; } __attribute__((packed)); /* sizeof(struct sadb_x_nat_t_type) == 8 */ /* Pass a NAT Traversal port (Source or Dest port) */ struct sadb_x_nat_t_port { - uint16_t sadb_x_nat_t_port_len; - uint16_t sadb_x_nat_t_port_exttype; + __u16 sadb_x_nat_t_port_len; + __u16 sadb_x_nat_t_port_exttype; __be16 sadb_x_nat_t_port_port; - uint16_t sadb_x_nat_t_port_reserved; + __u16 sadb_x_nat_t_port_reserved; } __attribute__((packed)); /* sizeof(struct sadb_x_nat_t_port) == 8 */ /* Generic LSM security context */ struct sadb_x_sec_ctx { - uint16_t sadb_x_sec_len; - uint16_t sadb_x_sec_exttype; - uint8_t sadb_x_ctx_alg; /* LSMs: e.g., selinux == 1 */ - uint8_t sadb_x_ctx_doi; - uint16_t sadb_x_ctx_len; + __u16 sadb_x_sec_len; + __u16 sadb_x_sec_exttype; + __u8 sadb_x_ctx_alg; /* LSMs: e.g., selinux == 1 */ + __u8 sadb_x_ctx_doi; + __u16 sadb_x_ctx_len; } __attribute__((packed)); /* sizeof(struct sadb_sec_ctx) = 8 */ /* Used by MIGRATE to pass addresses IKE will use to perform * negotiation with the peer */ struct sadb_x_kmaddress { - uint16_t sadb_x_kmaddress_len; - uint16_t sadb_x_kmaddress_exttype; - uint32_t sadb_x_kmaddress_reserved; + __u16 sadb_x_kmaddress_len; + __u16 sadb_x_kmaddress_exttype; + __u32 sadb_x_kmaddress_reserved; } __attribute__((packed)); /* sizeof(struct sadb_x_kmaddress) == 8 */ diff --git a/include/linux/selinux_netlink.h b/include/linux/selinux_netlink.h index bbf489decd8..d239797785c 100644 --- a/include/linux/selinux_netlink.h +++ b/include/linux/selinux_netlink.h @@ -12,6 +12,8 @@ #ifndef _LINUX_SELINUX_NETLINK_H #define _LINUX_SELINUX_NETLINK_H +#include + /* Message types. */ #define SELNL_MSG_BASE 0x10 enum { @@ -38,11 +40,11 @@ enum selinux_nlgroups { /* Message structures */ struct selnl_msg_setenforce { - int32_t val; + __s32 val; }; struct selnl_msg_policyload { - u_int32_t seqno; + __u32 seqno; }; #endif /* _LINUX_SELINUX_NETLINK_H */ -- cgit v1.2.3 From ccef7ab534347e2e1e1ef398d2ec987d37e519f3 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 26 Feb 2009 00:51:41 +0100 Subject: make MTD headers use strict integer types The MTD headers traditionally use stdint types rather than the kernel integer types. This converts them to do the same as all the others. Cc: David Woodhouse Signed-off-by: Arnd Bergmann Signed-off-by: H. Peter Anvin Signed-off-by: Ingo Molnar --- include/linux/jffs2.h | 27 ++++++++++++++------------- 1 file changed, 14 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jffs2.h b/include/linux/jffs2.h index da720bc3eb1..2b32d638147 100644 --- a/include/linux/jffs2.h +++ b/include/linux/jffs2.h @@ -12,6 +12,7 @@ #ifndef __LINUX_JFFS2_H__ #define __LINUX_JFFS2_H__ +#include #include /* You must include something which defines the C99 uintXX_t types. @@ -91,15 +92,15 @@ byteswapping */ typedef struct { - uint32_t v32; + __u32 v32; } __attribute__((packed)) jint32_t; typedef struct { - uint32_t m; + __u32 m; } __attribute__((packed)) jmode_t; typedef struct { - uint16_t v16; + __u16 v16; } __attribute__((packed)) jint16_t; struct jffs2_unknown_node @@ -121,12 +122,12 @@ struct jffs2_raw_dirent jint32_t version; jint32_t ino; /* == zero for unlink */ jint32_t mctime; - uint8_t nsize; - uint8_t type; - uint8_t unused[2]; + __u8 nsize; + __u8 type; + __u8 unused[2]; jint32_t node_crc; jint32_t name_crc; - uint8_t name[0]; + __u8 name[0]; }; /* The JFFS2 raw inode structure: Used for storage on physical media. */ @@ -153,12 +154,12 @@ struct jffs2_raw_inode jint32_t offset; /* Where to begin to write. */ jint32_t csize; /* (Compressed) data size */ jint32_t dsize; /* Size of the node's data. (after decompression) */ - uint8_t compr; /* Compression algorithm used */ - uint8_t usercompr; /* Compression algorithm requested by the user */ + __u8 compr; /* Compression algorithm used */ + __u8 usercompr; /* Compression algorithm requested by the user */ jint16_t flags; /* See JFFS2_INO_FLAG_* */ jint32_t data_crc; /* CRC for the (compressed) data. */ jint32_t node_crc; /* CRC for the raw inode (excluding data) */ - uint8_t data[0]; + __u8 data[0]; }; struct jffs2_raw_xattr { @@ -168,12 +169,12 @@ struct jffs2_raw_xattr { jint32_t hdr_crc; jint32_t xid; /* XATTR identifier number */ jint32_t version; - uint8_t xprefix; - uint8_t name_len; + __u8 xprefix; + __u8 name_len; jint16_t value_len; jint32_t data_crc; jint32_t node_crc; - uint8_t data[0]; + __u8 data[0]; } __attribute__((packed)); struct jffs2_raw_xref -- cgit v1.2.3 From 60c195c729532815c5209c81442fa0eb26ace706 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 26 Feb 2009 00:51:43 +0100 Subject: make netfilter use strict integer types Netfilter traditionally uses BSD integer types in its interface headers. This changes it to use the Linux strict integer types, like everyone else. Cc: netfilter-devel@vger.kernel.org Signed-off-by: Arnd Bergmann Acked-by: David S. Miller Signed-off-by: H. Peter Anvin Signed-off-by: Ingo Molnar --- include/linux/netfilter/nf_conntrack_tcp.h | 6 +++-- include/linux/netfilter/nfnetlink.h | 4 ++-- include/linux/netfilter/nfnetlink_compat.h | 7 ++++-- include/linux/netfilter/nfnetlink_log.h | 32 +++++++++++++------------- include/linux/netfilter/nfnetlink_queue.h | 24 ++++++++++---------- include/linux/netfilter/x_tables.h | 30 +++++++++++++------------ include/linux/netfilter/xt_CLASSIFY.h | 4 +++- include/linux/netfilter/xt_CONNMARK.h | 8 ++++--- include/linux/netfilter/xt_CONNSECMARK.h | 4 +++- include/linux/netfilter/xt_DSCP.h | 7 +++--- include/linux/netfilter/xt_MARK.h | 6 +++-- include/linux/netfilter/xt_NFLOG.h | 12 +++++----- include/linux/netfilter/xt_NFQUEUE.h | 4 +++- include/linux/netfilter/xt_RATEEST.h | 6 +++-- include/linux/netfilter/xt_SECMARK.h | 6 +++-- include/linux/netfilter/xt_TCPMSS.h | 4 +++- include/linux/netfilter/xt_connbytes.h | 6 +++-- include/linux/netfilter/xt_connmark.h | 8 ++++--- include/linux/netfilter/xt_conntrack.h | 12 +++++----- include/linux/netfilter/xt_dccp.h | 14 +++++++----- include/linux/netfilter/xt_dscp.h | 12 +++++----- include/linux/netfilter/xt_esp.h | 6 +++-- include/linux/netfilter/xt_hashlimit.h | 32 +++++++++++++------------- include/linux/netfilter/xt_iprange.h | 4 +++- include/linux/netfilter/xt_length.h | 6 +++-- include/linux/netfilter/xt_limit.h | 10 +++++---- include/linux/netfilter/xt_mark.h | 8 ++++--- include/linux/netfilter/xt_multiport.h | 18 ++++++++------- include/linux/netfilter/xt_owner.h | 8 ++++--- include/linux/netfilter/xt_physdev.h | 6 +++-- include/linux/netfilter/xt_policy.h | 14 +++++++----- include/linux/netfilter/xt_rateest.h | 14 +++++++----- include/linux/netfilter/xt_realm.h | 8 ++++--- include/linux/netfilter/xt_recent.h | 12 +++++----- include/linux/netfilter/xt_sctp.h | 36 ++++++++++++++++-------------- include/linux/netfilter/xt_statistic.h | 14 +++++++----- include/linux/netfilter/xt_string.h | 12 +++++----- include/linux/netfilter/xt_tcpmss.h | 6 +++-- include/linux/netfilter/xt_tcpudp.h | 20 +++++++++-------- 39 files changed, 260 insertions(+), 190 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nf_conntrack_tcp.h b/include/linux/netfilter/nf_conntrack_tcp.h index a049df4f223..3066789b972 100644 --- a/include/linux/netfilter/nf_conntrack_tcp.h +++ b/include/linux/netfilter/nf_conntrack_tcp.h @@ -2,6 +2,8 @@ #define _NF_CONNTRACK_TCP_H /* TCP tracking. */ +#include + /* This is exposed to userspace (ctnetlink) */ enum tcp_conntrack { TCP_CONNTRACK_NONE, @@ -34,8 +36,8 @@ enum tcp_conntrack { #define IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED 0x10 struct nf_ct_tcp_flags { - u_int8_t flags; - u_int8_t mask; + __u8 flags; + __u8 mask; }; #ifdef __KERNEL__ diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 7d8e0455cca..e53546cfa35 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -25,8 +25,8 @@ enum nfnetlink_groups { /* General form of address family dependent message. */ struct nfgenmsg { - u_int8_t nfgen_family; /* AF_xxx */ - u_int8_t version; /* nfnetlink version */ + __u8 nfgen_family; /* AF_xxx */ + __u8 version; /* nfnetlink version */ __be16 res_id; /* resource id */ }; diff --git a/include/linux/netfilter/nfnetlink_compat.h b/include/linux/netfilter/nfnetlink_compat.h index e1451760c9c..eda55cabcee 100644 --- a/include/linux/netfilter/nfnetlink_compat.h +++ b/include/linux/netfilter/nfnetlink_compat.h @@ -1,5 +1,8 @@ #ifndef _NFNETLINK_COMPAT_H #define _NFNETLINK_COMPAT_H + +#include + #ifndef __KERNEL__ /* Old nfnetlink macros for userspace */ @@ -20,8 +23,8 @@ struct nfattr { - u_int16_t nfa_len; - u_int16_t nfa_type; /* we use 15 bits for the type, and the highest + __u16 nfa_len; + __u16 nfa_type; /* we use 15 bits for the type, and the highest * bit to indicate whether the payload is nested */ }; diff --git a/include/linux/netfilter/nfnetlink_log.h b/include/linux/netfilter/nfnetlink_log.h index f661731f3cb..d3bab7a2c9b 100644 --- a/include/linux/netfilter/nfnetlink_log.h +++ b/include/linux/netfilter/nfnetlink_log.h @@ -17,14 +17,14 @@ enum nfulnl_msg_types { struct nfulnl_msg_packet_hdr { __be16 hw_protocol; /* hw protocol (network order) */ - u_int8_t hook; /* netfilter hook */ - u_int8_t _pad; + __u8 hook; /* netfilter hook */ + __u8 _pad; }; struct nfulnl_msg_packet_hw { __be16 hw_addrlen; - u_int16_t _pad; - u_int8_t hw_addr[8]; + __u16 _pad; + __u8 hw_addr[8]; }; struct nfulnl_msg_packet_timestamp { @@ -35,12 +35,12 @@ struct nfulnl_msg_packet_timestamp { enum nfulnl_attr_type { NFULA_UNSPEC, NFULA_PACKET_HDR, - NFULA_MARK, /* u_int32_t nfmark */ + NFULA_MARK, /* __u32 nfmark */ NFULA_TIMESTAMP, /* nfulnl_msg_packet_timestamp */ - NFULA_IFINDEX_INDEV, /* u_int32_t ifindex */ - NFULA_IFINDEX_OUTDEV, /* u_int32_t ifindex */ - NFULA_IFINDEX_PHYSINDEV, /* u_int32_t ifindex */ - NFULA_IFINDEX_PHYSOUTDEV, /* u_int32_t ifindex */ + NFULA_IFINDEX_INDEV, /* __u32 ifindex */ + NFULA_IFINDEX_OUTDEV, /* __u32 ifindex */ + NFULA_IFINDEX_PHYSINDEV, /* __u32 ifindex */ + NFULA_IFINDEX_PHYSOUTDEV, /* __u32 ifindex */ NFULA_HWADDR, /* nfulnl_msg_packet_hw */ NFULA_PAYLOAD, /* opaque data payload */ NFULA_PREFIX, /* string prefix */ @@ -65,23 +65,23 @@ enum nfulnl_msg_config_cmds { }; struct nfulnl_msg_config_cmd { - u_int8_t command; /* nfulnl_msg_config_cmds */ + __u8 command; /* nfulnl_msg_config_cmds */ } __attribute__ ((packed)); struct nfulnl_msg_config_mode { __be32 copy_range; - u_int8_t copy_mode; - u_int8_t _pad; + __u8 copy_mode; + __u8 _pad; } __attribute__ ((packed)); enum nfulnl_attr_config { NFULA_CFG_UNSPEC, NFULA_CFG_CMD, /* nfulnl_msg_config_cmd */ NFULA_CFG_MODE, /* nfulnl_msg_config_mode */ - NFULA_CFG_NLBUFSIZ, /* u_int32_t buffer size */ - NFULA_CFG_TIMEOUT, /* u_int32_t in 1/100 s */ - NFULA_CFG_QTHRESH, /* u_int32_t */ - NFULA_CFG_FLAGS, /* u_int16_t */ + NFULA_CFG_NLBUFSIZ, /* __u32 buffer size */ + NFULA_CFG_TIMEOUT, /* __u32 in 1/100 s */ + NFULA_CFG_QTHRESH, /* __u32 */ + NFULA_CFG_FLAGS, /* __u16 */ __NFULA_CFG_MAX }; #define NFULA_CFG_MAX (__NFULA_CFG_MAX -1) diff --git a/include/linux/netfilter/nfnetlink_queue.h b/include/linux/netfilter/nfnetlink_queue.h index 83e789633e3..2455fe5f4e0 100644 --- a/include/linux/netfilter/nfnetlink_queue.h +++ b/include/linux/netfilter/nfnetlink_queue.h @@ -15,13 +15,13 @@ enum nfqnl_msg_types { struct nfqnl_msg_packet_hdr { __be32 packet_id; /* unique ID of packet in queue */ __be16 hw_protocol; /* hw protocol (network order) */ - u_int8_t hook; /* netfilter hook */ + __u8 hook; /* netfilter hook */ } __attribute__ ((packed)); struct nfqnl_msg_packet_hw { __be16 hw_addrlen; - u_int16_t _pad; - u_int8_t hw_addr[8]; + __u16 _pad; + __u8 hw_addr[8]; }; struct nfqnl_msg_packet_timestamp { @@ -33,12 +33,12 @@ enum nfqnl_attr_type { NFQA_UNSPEC, NFQA_PACKET_HDR, NFQA_VERDICT_HDR, /* nfqnl_msg_verdict_hrd */ - NFQA_MARK, /* u_int32_t nfmark */ + NFQA_MARK, /* __u32 nfmark */ NFQA_TIMESTAMP, /* nfqnl_msg_packet_timestamp */ - NFQA_IFINDEX_INDEV, /* u_int32_t ifindex */ - NFQA_IFINDEX_OUTDEV, /* u_int32_t ifindex */ - NFQA_IFINDEX_PHYSINDEV, /* u_int32_t ifindex */ - NFQA_IFINDEX_PHYSOUTDEV, /* u_int32_t ifindex */ + NFQA_IFINDEX_INDEV, /* __u32 ifindex */ + NFQA_IFINDEX_OUTDEV, /* __u32 ifindex */ + NFQA_IFINDEX_PHYSINDEV, /* __u32 ifindex */ + NFQA_IFINDEX_PHYSOUTDEV, /* __u32 ifindex */ NFQA_HWADDR, /* nfqnl_msg_packet_hw */ NFQA_PAYLOAD, /* opaque data payload */ @@ -61,8 +61,8 @@ enum nfqnl_msg_config_cmds { }; struct nfqnl_msg_config_cmd { - u_int8_t command; /* nfqnl_msg_config_cmds */ - u_int8_t _pad; + __u8 command; /* nfqnl_msg_config_cmds */ + __u8 _pad; __be16 pf; /* AF_xxx for PF_[UN]BIND */ }; @@ -74,7 +74,7 @@ enum nfqnl_config_mode { struct nfqnl_msg_config_params { __be32 copy_range; - u_int8_t copy_mode; /* enum nfqnl_config_mode */ + __u8 copy_mode; /* enum nfqnl_config_mode */ } __attribute__ ((packed)); @@ -82,7 +82,7 @@ enum nfqnl_attr_config { NFQA_CFG_UNSPEC, NFQA_CFG_CMD, /* nfqnl_msg_config_cmd */ NFQA_CFG_PARAMS, /* nfqnl_msg_config_params */ - NFQA_CFG_QUEUE_MAXLEN, /* u_int32_t */ + NFQA_CFG_QUEUE_MAXLEN, /* __u32 */ __NFQA_CFG_MAX }; #define NFQA_CFG_MAX (__NFQA_CFG_MAX-1) diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index c7ee8744d26..33fd9c949d8 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -1,6 +1,8 @@ #ifndef _X_TABLES_H #define _X_TABLES_H +#include + #define XT_FUNCTION_MAXNAMELEN 30 #define XT_TABLE_MAXNAMELEN 32 @@ -8,22 +10,22 @@ struct xt_entry_match { union { struct { - u_int16_t match_size; + __u16 match_size; /* Used by userspace */ char name[XT_FUNCTION_MAXNAMELEN-1]; - u_int8_t revision; + __u8 revision; } user; struct { - u_int16_t match_size; + __u16 match_size; /* Used inside the kernel */ struct xt_match *match; } kernel; /* Total length */ - u_int16_t match_size; + __u16 match_size; } u; unsigned char data[0]; @@ -33,22 +35,22 @@ struct xt_entry_target { union { struct { - u_int16_t target_size; + __u16 target_size; /* Used by userspace */ char name[XT_FUNCTION_MAXNAMELEN-1]; - u_int8_t revision; + __u8 revision; } user; struct { - u_int16_t target_size; + __u16 target_size; /* Used inside the kernel */ struct xt_target *target; } kernel; /* Total length */ - u_int16_t target_size; + __u16 target_size; } u; unsigned char data[0]; @@ -74,7 +76,7 @@ struct xt_get_revision { char name[XT_FUNCTION_MAXNAMELEN-1]; - u_int8_t revision; + __u8 revision; }; /* CONTINUE verdict for targets */ @@ -90,10 +92,10 @@ struct xt_get_revision */ struct _xt_align { - u_int8_t u8; - u_int16_t u16; - u_int32_t u32; - u_int64_t u64; + __u8 u8; + __u16 u16; + __u32 u32; + __u64 u64; }; #define XT_ALIGN(s) (((s) + (__alignof__(struct _xt_align)-1)) \ @@ -109,7 +111,7 @@ struct _xt_align struct xt_counters { - u_int64_t pcnt, bcnt; /* Packet and byte counters */ + __u64 pcnt, bcnt; /* Packet and byte counters */ }; /* The argument to IPT_SO_ADD_COUNTERS. */ diff --git a/include/linux/netfilter/xt_CLASSIFY.h b/include/linux/netfilter/xt_CLASSIFY.h index 58111355255..a813bf14dd6 100644 --- a/include/linux/netfilter/xt_CLASSIFY.h +++ b/include/linux/netfilter/xt_CLASSIFY.h @@ -1,8 +1,10 @@ #ifndef _XT_CLASSIFY_H #define _XT_CLASSIFY_H +#include + struct xt_classify_target_info { - u_int32_t priority; + __u32 priority; }; #endif /*_XT_CLASSIFY_H */ diff --git a/include/linux/netfilter/xt_CONNMARK.h b/include/linux/netfilter/xt_CONNMARK.h index 4e58ba43c28..7635c8ffdad 100644 --- a/include/linux/netfilter/xt_CONNMARK.h +++ b/include/linux/netfilter/xt_CONNMARK.h @@ -1,6 +1,8 @@ #ifndef _XT_CONNMARK_H_target #define _XT_CONNMARK_H_target +#include + /* Copyright (C) 2002,2004 MARA Systems AB * by Henrik Nordstrom * @@ -19,12 +21,12 @@ enum { struct xt_connmark_target_info { unsigned long mark; unsigned long mask; - u_int8_t mode; + __u8 mode; }; struct xt_connmark_tginfo1 { - u_int32_t ctmark, ctmask, nfmask; - u_int8_t mode; + __u32 ctmark, ctmask, nfmask; + __u8 mode; }; #endif /*_XT_CONNMARK_H_target*/ diff --git a/include/linux/netfilter/xt_CONNSECMARK.h b/include/linux/netfilter/xt_CONNSECMARK.h index c6bd75469ba..b973ff80fa1 100644 --- a/include/linux/netfilter/xt_CONNSECMARK.h +++ b/include/linux/netfilter/xt_CONNSECMARK.h @@ -1,13 +1,15 @@ #ifndef _XT_CONNSECMARK_H_target #define _XT_CONNSECMARK_H_target +#include + enum { CONNSECMARK_SAVE = 1, CONNSECMARK_RESTORE, }; struct xt_connsecmark_target_info { - u_int8_t mode; + __u8 mode; }; #endif /*_XT_CONNSECMARK_H_target */ diff --git a/include/linux/netfilter/xt_DSCP.h b/include/linux/netfilter/xt_DSCP.h index 14da1968e2c..648e0b3bed2 100644 --- a/include/linux/netfilter/xt_DSCP.h +++ b/include/linux/netfilter/xt_DSCP.h @@ -11,15 +11,16 @@ #ifndef _XT_DSCP_TARGET_H #define _XT_DSCP_TARGET_H #include +#include /* target info */ struct xt_DSCP_info { - u_int8_t dscp; + __u8 dscp; }; struct xt_tos_target_info { - u_int8_t tos_value; - u_int8_t tos_mask; + __u8 tos_value; + __u8 tos_mask; }; #endif /* _XT_DSCP_TARGET_H */ diff --git a/include/linux/netfilter/xt_MARK.h b/include/linux/netfilter/xt_MARK.h index 778b278fd9f..028304bcc0b 100644 --- a/include/linux/netfilter/xt_MARK.h +++ b/include/linux/netfilter/xt_MARK.h @@ -1,6 +1,8 @@ #ifndef _XT_MARK_H_target #define _XT_MARK_H_target +#include + /* Version 0 */ struct xt_mark_target_info { unsigned long mark; @@ -15,11 +17,11 @@ enum { struct xt_mark_target_info_v1 { unsigned long mark; - u_int8_t mode; + __u8 mode; }; struct xt_mark_tginfo2 { - u_int32_t mark, mask; + __u32 mark, mask; }; #endif /*_XT_MARK_H_target */ diff --git a/include/linux/netfilter/xt_NFLOG.h b/include/linux/netfilter/xt_NFLOG.h index cdcd0ed58f7..eaac7b5226e 100644 --- a/include/linux/netfilter/xt_NFLOG.h +++ b/include/linux/netfilter/xt_NFLOG.h @@ -1,17 +1,19 @@ #ifndef _XT_NFLOG_TARGET #define _XT_NFLOG_TARGET +#include + #define XT_NFLOG_DEFAULT_GROUP 0x1 #define XT_NFLOG_DEFAULT_THRESHOLD 1 #define XT_NFLOG_MASK 0x0 struct xt_nflog_info { - u_int32_t len; - u_int16_t group; - u_int16_t threshold; - u_int16_t flags; - u_int16_t pad; + __u32 len; + __u16 group; + __u16 threshold; + __u16 flags; + __u16 pad; char prefix[64]; }; diff --git a/include/linux/netfilter/xt_NFQUEUE.h b/include/linux/netfilter/xt_NFQUEUE.h index 9a9af79f74d..982a89f7827 100644 --- a/include/linux/netfilter/xt_NFQUEUE.h +++ b/include/linux/netfilter/xt_NFQUEUE.h @@ -8,9 +8,11 @@ #ifndef _XT_NFQ_TARGET_H #define _XT_NFQ_TARGET_H +#include + /* target info */ struct xt_NFQ_info { - u_int16_t queuenum; + __u16 queuenum; }; #endif /* _XT_NFQ_TARGET_H */ diff --git a/include/linux/netfilter/xt_RATEEST.h b/include/linux/netfilter/xt_RATEEST.h index f79e3133cbe..6605e20ad8c 100644 --- a/include/linux/netfilter/xt_RATEEST.h +++ b/include/linux/netfilter/xt_RATEEST.h @@ -1,10 +1,12 @@ #ifndef _XT_RATEEST_TARGET_H #define _XT_RATEEST_TARGET_H +#include + struct xt_rateest_target_info { char name[IFNAMSIZ]; - int8_t interval; - u_int8_t ewma_log; + __s8 interval; + __u8 ewma_log; /* Used internally by the kernel */ struct xt_rateest *est __attribute__((aligned(8))); diff --git a/include/linux/netfilter/xt_SECMARK.h b/include/linux/netfilter/xt_SECMARK.h index c53fbffa997..6fcd3448b18 100644 --- a/include/linux/netfilter/xt_SECMARK.h +++ b/include/linux/netfilter/xt_SECMARK.h @@ -1,6 +1,8 @@ #ifndef _XT_SECMARK_H_target #define _XT_SECMARK_H_target +#include + /* * This is intended for use by various security subsystems (but not * at the same time). @@ -12,12 +14,12 @@ #define SECMARK_SELCTX_MAX 256 struct xt_secmark_target_selinux_info { - u_int32_t selsid; + __u32 selsid; char selctx[SECMARK_SELCTX_MAX]; }; struct xt_secmark_target_info { - u_int8_t mode; + __u8 mode; union { struct xt_secmark_target_selinux_info sel; } u; diff --git a/include/linux/netfilter/xt_TCPMSS.h b/include/linux/netfilter/xt_TCPMSS.h index 53a292cd47f..9a6960afc13 100644 --- a/include/linux/netfilter/xt_TCPMSS.h +++ b/include/linux/netfilter/xt_TCPMSS.h @@ -1,8 +1,10 @@ #ifndef _XT_TCPMSS_H #define _XT_TCPMSS_H +#include + struct xt_tcpmss_info { - u_int16_t mss; + __u16 mss; }; #define XT_TCPMSS_CLAMP_PMTU 0xffff diff --git a/include/linux/netfilter/xt_connbytes.h b/include/linux/netfilter/xt_connbytes.h index c022c989754..52bd6153b99 100644 --- a/include/linux/netfilter/xt_connbytes.h +++ b/include/linux/netfilter/xt_connbytes.h @@ -1,6 +1,8 @@ #ifndef _XT_CONNBYTES_H #define _XT_CONNBYTES_H +#include + enum xt_connbytes_what { XT_CONNBYTES_PKTS, XT_CONNBYTES_BYTES, @@ -19,7 +21,7 @@ struct xt_connbytes_info aligned_u64 from; /* count to be matched */ aligned_u64 to; /* count to be matched */ } count; - u_int8_t what; /* ipt_connbytes_what */ - u_int8_t direction; /* ipt_connbytes_direction */ + __u8 what; /* ipt_connbytes_what */ + __u8 direction; /* ipt_connbytes_direction */ }; #endif diff --git a/include/linux/netfilter/xt_connmark.h b/include/linux/netfilter/xt_connmark.h index 359ef86918d..571e266d004 100644 --- a/include/linux/netfilter/xt_connmark.h +++ b/include/linux/netfilter/xt_connmark.h @@ -1,6 +1,8 @@ #ifndef _XT_CONNMARK_H #define _XT_CONNMARK_H +#include + /* Copyright (C) 2002,2004 MARA Systems AB * by Henrik Nordstrom * @@ -12,12 +14,12 @@ struct xt_connmark_info { unsigned long mark, mask; - u_int8_t invert; + __u8 invert; }; struct xt_connmark_mtinfo1 { - u_int32_t mark, mask; - u_int8_t invert; + __u32 mark, mask; + __u8 invert; }; #endif /*_XT_CONNMARK_H*/ diff --git a/include/linux/netfilter/xt_conntrack.h b/include/linux/netfilter/xt_conntrack.h index 8f534527539..3430c775194 100644 --- a/include/linux/netfilter/xt_conntrack.h +++ b/include/linux/netfilter/xt_conntrack.h @@ -63,9 +63,9 @@ struct xt_conntrack_info unsigned long expires_min, expires_max; /* Flags word */ - u_int8_t flags; + __u8 flags; /* Inverse flags */ - u_int8_t invflags; + __u8 invflags; }; struct xt_conntrack_mtinfo1 { @@ -73,12 +73,12 @@ struct xt_conntrack_mtinfo1 { union nf_inet_addr origdst_addr, origdst_mask; union nf_inet_addr replsrc_addr, replsrc_mask; union nf_inet_addr repldst_addr, repldst_mask; - u_int32_t expires_min, expires_max; - u_int16_t l4proto; + __u32 expires_min, expires_max; + __u16 l4proto; __be16 origsrc_port, origdst_port; __be16 replsrc_port, repldst_port; - u_int16_t match_flags, invert_flags; - u_int8_t state_mask, status_mask; + __u16 match_flags, invert_flags; + __u8 state_mask, status_mask; }; #endif /*_XT_CONNTRACK_H*/ diff --git a/include/linux/netfilter/xt_dccp.h b/include/linux/netfilter/xt_dccp.h index e0221b9d32c..a579e1b6f04 100644 --- a/include/linux/netfilter/xt_dccp.h +++ b/include/linux/netfilter/xt_dccp.h @@ -1,6 +1,8 @@ #ifndef _XT_DCCP_H_ #define _XT_DCCP_H_ +#include + #define XT_DCCP_SRC_PORTS 0x01 #define XT_DCCP_DEST_PORTS 0x02 #define XT_DCCP_TYPE 0x04 @@ -9,14 +11,14 @@ #define XT_DCCP_VALID_FLAGS 0x0f struct xt_dccp_info { - u_int16_t dpts[2]; /* Min, Max */ - u_int16_t spts[2]; /* Min, Max */ + __u16 dpts[2]; /* Min, Max */ + __u16 spts[2]; /* Min, Max */ - u_int16_t flags; - u_int16_t invflags; + __u16 flags; + __u16 invflags; - u_int16_t typemask; - u_int8_t option; + __u16 typemask; + __u8 option; }; #endif /* _XT_DCCP_H_ */ diff --git a/include/linux/netfilter/xt_dscp.h b/include/linux/netfilter/xt_dscp.h index f49bc1a648d..15f8932ad5c 100644 --- a/include/linux/netfilter/xt_dscp.h +++ b/include/linux/netfilter/xt_dscp.h @@ -10,20 +10,22 @@ #ifndef _XT_DSCP_H #define _XT_DSCP_H +#include + #define XT_DSCP_MASK 0xfc /* 11111100 */ #define XT_DSCP_SHIFT 2 #define XT_DSCP_MAX 0x3f /* 00111111 */ /* match info */ struct xt_dscp_info { - u_int8_t dscp; - u_int8_t invert; + __u8 dscp; + __u8 invert; }; struct xt_tos_match_info { - u_int8_t tos_mask; - u_int8_t tos_value; - u_int8_t invert; + __u8 tos_mask; + __u8 tos_value; + __u8 invert; }; #endif /* _XT_DSCP_H */ diff --git a/include/linux/netfilter/xt_esp.h b/include/linux/netfilter/xt_esp.h index 9380fb1c27d..ef6fa4747d0 100644 --- a/include/linux/netfilter/xt_esp.h +++ b/include/linux/netfilter/xt_esp.h @@ -1,10 +1,12 @@ #ifndef _XT_ESP_H #define _XT_ESP_H +#include + struct xt_esp { - u_int32_t spis[2]; /* Security Parameter Index */ - u_int8_t invflags; /* Inverse flags */ + __u32 spis[2]; /* Security Parameter Index */ + __u8 invflags; /* Inverse flags */ }; /* Values for "invflags" field in struct xt_esp. */ diff --git a/include/linux/netfilter/xt_hashlimit.h b/include/linux/netfilter/xt_hashlimit.h index 51b18d83b47..b1925b5925e 100644 --- a/include/linux/netfilter/xt_hashlimit.h +++ b/include/linux/netfilter/xt_hashlimit.h @@ -1,6 +1,8 @@ #ifndef _XT_HASHLIMIT_H #define _XT_HASHLIMIT_H +#include + /* timings are in milliseconds. */ #define XT_HASHLIMIT_SCALE 10000 /* 1/10,000 sec period => max of 10,000/sec. Min rate is then 429490 @@ -18,15 +20,15 @@ enum { }; struct hashlimit_cfg { - u_int32_t mode; /* bitmask of XT_HASHLIMIT_HASH_* */ - u_int32_t avg; /* Average secs between packets * scale */ - u_int32_t burst; /* Period multiplier for upper limit. */ + __u32 mode; /* bitmask of XT_HASHLIMIT_HASH_* */ + __u32 avg; /* Average secs between packets * scale */ + __u32 burst; /* Period multiplier for upper limit. */ /* user specified */ - u_int32_t size; /* how many buckets */ - u_int32_t max; /* max number of entries */ - u_int32_t gc_interval; /* gc interval */ - u_int32_t expire; /* when do entries expire? */ + __u32 size; /* how many buckets */ + __u32 max; /* max number of entries */ + __u32 gc_interval; /* gc interval */ + __u32 expire; /* when do entries expire? */ }; struct xt_hashlimit_info { @@ -42,17 +44,17 @@ struct xt_hashlimit_info { }; struct hashlimit_cfg1 { - u_int32_t mode; /* bitmask of XT_HASHLIMIT_HASH_* */ - u_int32_t avg; /* Average secs between packets * scale */ - u_int32_t burst; /* Period multiplier for upper limit. */ + __u32 mode; /* bitmask of XT_HASHLIMIT_HASH_* */ + __u32 avg; /* Average secs between packets * scale */ + __u32 burst; /* Period multiplier for upper limit. */ /* user specified */ - u_int32_t size; /* how many buckets */ - u_int32_t max; /* max number of entries */ - u_int32_t gc_interval; /* gc interval */ - u_int32_t expire; /* when do entries expire? */ + __u32 size; /* how many buckets */ + __u32 max; /* max number of entries */ + __u32 gc_interval; /* gc interval */ + __u32 expire; /* when do entries expire? */ - u_int8_t srcmask, dstmask; + __u8 srcmask, dstmask; }; struct xt_hashlimit_mtinfo1 { diff --git a/include/linux/netfilter/xt_iprange.h b/include/linux/netfilter/xt_iprange.h index a4299c7d368..c1f21a779a4 100644 --- a/include/linux/netfilter/xt_iprange.h +++ b/include/linux/netfilter/xt_iprange.h @@ -1,6 +1,8 @@ #ifndef _LINUX_NETFILTER_XT_IPRANGE_H #define _LINUX_NETFILTER_XT_IPRANGE_H 1 +#include + enum { IPRANGE_SRC = 1 << 0, /* match source IP address */ IPRANGE_DST = 1 << 1, /* match destination IP address */ @@ -11,7 +13,7 @@ enum { struct xt_iprange_mtinfo { union nf_inet_addr src_min, src_max; union nf_inet_addr dst_min, dst_max; - u_int8_t flags; + __u8 flags; }; #endif /* _LINUX_NETFILTER_XT_IPRANGE_H */ diff --git a/include/linux/netfilter/xt_length.h b/include/linux/netfilter/xt_length.h index 7c2b439f73f..b82ed7c4b1e 100644 --- a/include/linux/netfilter/xt_length.h +++ b/include/linux/netfilter/xt_length.h @@ -1,9 +1,11 @@ #ifndef _XT_LENGTH_H #define _XT_LENGTH_H +#include + struct xt_length_info { - u_int16_t min, max; - u_int8_t invert; + __u16 min, max; + __u8 invert; }; #endif /*_XT_LENGTH_H*/ diff --git a/include/linux/netfilter/xt_limit.h b/include/linux/netfilter/xt_limit.h index b3ce65375ec..190e98b1f7c 100644 --- a/include/linux/netfilter/xt_limit.h +++ b/include/linux/netfilter/xt_limit.h @@ -1,19 +1,21 @@ #ifndef _XT_RATE_H #define _XT_RATE_H +#include + /* timings are in milliseconds. */ #define XT_LIMIT_SCALE 10000 /* 1/10,000 sec period => max of 10,000/sec. Min rate is then 429490 seconds, or one every 59 hours. */ struct xt_rateinfo { - u_int32_t avg; /* Average secs between packets * scale */ - u_int32_t burst; /* Period multiplier for upper limit. */ + __u32 avg; /* Average secs between packets * scale */ + __u32 burst; /* Period multiplier for upper limit. */ /* Used internally by the kernel */ unsigned long prev; - u_int32_t credit; - u_int32_t credit_cap, cost; + __u32 credit; + __u32 credit_cap, cost; /* Ugly, ugly fucker. */ struct xt_rateinfo *master; diff --git a/include/linux/netfilter/xt_mark.h b/include/linux/netfilter/xt_mark.h index fae74bc3f34..6fa460a3cc2 100644 --- a/include/linux/netfilter/xt_mark.h +++ b/include/linux/netfilter/xt_mark.h @@ -1,14 +1,16 @@ #ifndef _XT_MARK_H #define _XT_MARK_H +#include + struct xt_mark_info { unsigned long mark, mask; - u_int8_t invert; + __u8 invert; }; struct xt_mark_mtinfo1 { - u_int32_t mark, mask; - u_int8_t invert; + __u32 mark, mask; + __u8 invert; }; #endif /*_XT_MARK_H*/ diff --git a/include/linux/netfilter/xt_multiport.h b/include/linux/netfilter/xt_multiport.h index d49ee418371..185db499fcb 100644 --- a/include/linux/netfilter/xt_multiport.h +++ b/include/linux/netfilter/xt_multiport.h @@ -1,6 +1,8 @@ #ifndef _XT_MULTIPORT_H #define _XT_MULTIPORT_H +#include + enum xt_multiport_flags { XT_MULTIPORT_SOURCE, @@ -13,18 +15,18 @@ enum xt_multiport_flags /* Must fit inside union xt_matchinfo: 16 bytes */ struct xt_multiport { - u_int8_t flags; /* Type of comparison */ - u_int8_t count; /* Number of ports */ - u_int16_t ports[XT_MULTI_PORTS]; /* Ports */ + __u8 flags; /* Type of comparison */ + __u8 count; /* Number of ports */ + __u16 ports[XT_MULTI_PORTS]; /* Ports */ }; struct xt_multiport_v1 { - u_int8_t flags; /* Type of comparison */ - u_int8_t count; /* Number of ports */ - u_int16_t ports[XT_MULTI_PORTS]; /* Ports */ - u_int8_t pflags[XT_MULTI_PORTS]; /* Port flags */ - u_int8_t invert; /* Invert flag */ + __u8 flags; /* Type of comparison */ + __u8 count; /* Number of ports */ + __u16 ports[XT_MULTI_PORTS]; /* Ports */ + __u8 pflags[XT_MULTI_PORTS]; /* Port flags */ + __u8 invert; /* Invert flag */ }; #endif /*_XT_MULTIPORT_H*/ diff --git a/include/linux/netfilter/xt_owner.h b/include/linux/netfilter/xt_owner.h index c84e52cfe41..2081761714b 100644 --- a/include/linux/netfilter/xt_owner.h +++ b/include/linux/netfilter/xt_owner.h @@ -1,6 +1,8 @@ #ifndef _XT_OWNER_MATCH_H #define _XT_OWNER_MATCH_H +#include + enum { XT_OWNER_UID = 1 << 0, XT_OWNER_GID = 1 << 1, @@ -8,9 +10,9 @@ enum { }; struct xt_owner_match_info { - u_int32_t uid_min, uid_max; - u_int32_t gid_min, gid_max; - u_int8_t match, invert; + __u32 uid_min, uid_max; + __u32 gid_min, gid_max; + __u8 match, invert; }; #endif /* _XT_OWNER_MATCH_H */ diff --git a/include/linux/netfilter/xt_physdev.h b/include/linux/netfilter/xt_physdev.h index 25a7a1815b5..8555e399886 100644 --- a/include/linux/netfilter/xt_physdev.h +++ b/include/linux/netfilter/xt_physdev.h @@ -1,6 +1,8 @@ #ifndef _XT_PHYSDEV_H #define _XT_PHYSDEV_H +#include + #ifdef __KERNEL__ #include #endif @@ -17,8 +19,8 @@ struct xt_physdev_info { char in_mask[IFNAMSIZ]; char physoutdev[IFNAMSIZ]; char out_mask[IFNAMSIZ]; - u_int8_t invert; - u_int8_t bitmask; + __u8 invert; + __u8 bitmask; }; #endif /*_XT_PHYSDEV_H*/ diff --git a/include/linux/netfilter/xt_policy.h b/include/linux/netfilter/xt_policy.h index 053d8cc6546..7bb64e7c853 100644 --- a/include/linux/netfilter/xt_policy.h +++ b/include/linux/netfilter/xt_policy.h @@ -1,6 +1,8 @@ #ifndef _XT_POLICY_H #define _XT_POLICY_H +#include + #define XT_POLICY_MAX_ELEM 4 enum xt_policy_flags @@ -19,7 +21,7 @@ enum xt_policy_modes struct xt_policy_spec { - u_int8_t saddr:1, + __u8 saddr:1, daddr:1, proto:1, mode:1, @@ -55,9 +57,9 @@ struct xt_policy_elem #endif }; __be32 spi; - u_int32_t reqid; - u_int8_t proto; - u_int8_t mode; + __u32 reqid; + __u8 proto; + __u8 mode; struct xt_policy_spec match; struct xt_policy_spec invert; @@ -66,8 +68,8 @@ struct xt_policy_elem struct xt_policy_info { struct xt_policy_elem pol[XT_POLICY_MAX_ELEM]; - u_int16_t flags; - u_int16_t len; + __u16 flags; + __u16 len; }; #endif /* _XT_POLICY_H */ diff --git a/include/linux/netfilter/xt_rateest.h b/include/linux/netfilter/xt_rateest.h index 2010cb74250..d40a6196842 100644 --- a/include/linux/netfilter/xt_rateest.h +++ b/include/linux/netfilter/xt_rateest.h @@ -1,6 +1,8 @@ #ifndef _XT_RATEEST_MATCH_H #define _XT_RATEEST_MATCH_H +#include + enum xt_rateest_match_flags { XT_RATEEST_MATCH_INVERT = 1<<0, XT_RATEEST_MATCH_ABS = 1<<1, @@ -20,12 +22,12 @@ enum xt_rateest_match_mode { struct xt_rateest_match_info { char name1[IFNAMSIZ]; char name2[IFNAMSIZ]; - u_int16_t flags; - u_int16_t mode; - u_int32_t bps1; - u_int32_t pps1; - u_int32_t bps2; - u_int32_t pps2; + __u16 flags; + __u16 mode; + __u32 bps1; + __u32 pps1; + __u32 bps2; + __u32 pps2; /* Used internally by the kernel */ struct xt_rateest *est1 __attribute__((aligned(8))); diff --git a/include/linux/netfilter/xt_realm.h b/include/linux/netfilter/xt_realm.h index 220e8724571..d4a82ee56a0 100644 --- a/include/linux/netfilter/xt_realm.h +++ b/include/linux/netfilter/xt_realm.h @@ -1,10 +1,12 @@ #ifndef _XT_REALM_H #define _XT_REALM_H +#include + struct xt_realm_info { - u_int32_t id; - u_int32_t mask; - u_int8_t invert; + __u32 id; + __u32 mask; + __u8 invert; }; #endif /* _XT_REALM_H */ diff --git a/include/linux/netfilter/xt_recent.h b/include/linux/netfilter/xt_recent.h index 5cfeb81c679..d2c27660992 100644 --- a/include/linux/netfilter/xt_recent.h +++ b/include/linux/netfilter/xt_recent.h @@ -1,6 +1,8 @@ #ifndef _LINUX_NETFILTER_XT_RECENT_H #define _LINUX_NETFILTER_XT_RECENT_H 1 +#include + enum { XT_RECENT_CHECK = 1 << 0, XT_RECENT_SET = 1 << 1, @@ -15,12 +17,12 @@ enum { }; struct xt_recent_mtinfo { - u_int32_t seconds; - u_int32_t hit_count; - u_int8_t check_set; - u_int8_t invert; + __u32 seconds; + __u32 hit_count; + __u8 check_set; + __u8 invert; char name[XT_RECENT_NAME_LEN]; - u_int8_t side; + __u8 side; }; #endif /* _LINUX_NETFILTER_XT_RECENT_H */ diff --git a/include/linux/netfilter/xt_sctp.h b/include/linux/netfilter/xt_sctp.h index 32000ba6ece..29287be696a 100644 --- a/include/linux/netfilter/xt_sctp.h +++ b/include/linux/netfilter/xt_sctp.h @@ -1,6 +1,8 @@ #ifndef _XT_SCTP_H_ #define _XT_SCTP_H_ +#include + #define XT_SCTP_SRC_PORTS 0x01 #define XT_SCTP_DEST_PORTS 0x02 #define XT_SCTP_CHUNK_TYPES 0x04 @@ -8,49 +10,49 @@ #define XT_SCTP_VALID_FLAGS 0x07 struct xt_sctp_flag_info { - u_int8_t chunktype; - u_int8_t flag; - u_int8_t flag_mask; + __u8 chunktype; + __u8 flag; + __u8 flag_mask; }; #define XT_NUM_SCTP_FLAGS 4 struct xt_sctp_info { - u_int16_t dpts[2]; /* Min, Max */ - u_int16_t spts[2]; /* Min, Max */ + __u16 dpts[2]; /* Min, Max */ + __u16 spts[2]; /* Min, Max */ - u_int32_t chunkmap[256 / sizeof (u_int32_t)]; /* Bit mask of chunks to be matched according to RFC 2960 */ + __u32 chunkmap[256 / sizeof (__u32)]; /* Bit mask of chunks to be matched according to RFC 2960 */ #define SCTP_CHUNK_MATCH_ANY 0x01 /* Match if any of the chunk types are present */ #define SCTP_CHUNK_MATCH_ALL 0x02 /* Match if all of the chunk types are present */ #define SCTP_CHUNK_MATCH_ONLY 0x04 /* Match if these are the only chunk types present */ - u_int32_t chunk_match_type; + __u32 chunk_match_type; struct xt_sctp_flag_info flag_info[XT_NUM_SCTP_FLAGS]; int flag_count; - u_int32_t flags; - u_int32_t invflags; + __u32 flags; + __u32 invflags; }; #define bytes(type) (sizeof(type) * 8) #define SCTP_CHUNKMAP_SET(chunkmap, type) \ do { \ - (chunkmap)[type / bytes(u_int32_t)] |= \ - 1 << (type % bytes(u_int32_t)); \ + (chunkmap)[type / bytes(__u32)] |= \ + 1 << (type % bytes(__u32)); \ } while (0) #define SCTP_CHUNKMAP_CLEAR(chunkmap, type) \ do { \ - (chunkmap)[type / bytes(u_int32_t)] &= \ - ~(1 << (type % bytes(u_int32_t))); \ + (chunkmap)[type / bytes(__u32)] &= \ + ~(1 << (type % bytes(__u32))); \ } while (0) #define SCTP_CHUNKMAP_IS_SET(chunkmap, type) \ ({ \ - ((chunkmap)[type / bytes (u_int32_t)] & \ - (1 << (type % bytes (u_int32_t)))) ? 1: 0; \ + ((chunkmap)[type / bytes (__u32)] & \ + (1 << (type % bytes (__u32)))) ? 1: 0; \ }) #define SCTP_CHUNKMAP_RESET(chunkmap) \ @@ -65,7 +67,7 @@ struct xt_sctp_info { #define SCTP_CHUNKMAP_IS_CLEAR(chunkmap) \ __sctp_chunkmap_is_clear((chunkmap), ARRAY_SIZE(chunkmap)) static inline bool -__sctp_chunkmap_is_clear(const u_int32_t *chunkmap, unsigned int n) +__sctp_chunkmap_is_clear(const __u32 *chunkmap, unsigned int n) { unsigned int i; for (i = 0; i < n; ++i) @@ -77,7 +79,7 @@ __sctp_chunkmap_is_clear(const u_int32_t *chunkmap, unsigned int n) #define SCTP_CHUNKMAP_IS_ALL_SET(chunkmap) \ __sctp_chunkmap_is_all_set((chunkmap), ARRAY_SIZE(chunkmap)) static inline bool -__sctp_chunkmap_is_all_set(const u_int32_t *chunkmap, unsigned int n) +__sctp_chunkmap_is_all_set(const __u32 *chunkmap, unsigned int n) { unsigned int i; for (i = 0; i < n; ++i) diff --git a/include/linux/netfilter/xt_statistic.h b/include/linux/netfilter/xt_statistic.h index 3d38bc97504..095f3c66f45 100644 --- a/include/linux/netfilter/xt_statistic.h +++ b/include/linux/netfilter/xt_statistic.h @@ -1,6 +1,8 @@ #ifndef _XT_STATISTIC_H #define _XT_STATISTIC_H +#include + enum xt_statistic_mode { XT_STATISTIC_MODE_RANDOM, XT_STATISTIC_MODE_NTH, @@ -14,17 +16,17 @@ enum xt_statistic_flags { #define XT_STATISTIC_MASK 0x1 struct xt_statistic_info { - u_int16_t mode; - u_int16_t flags; + __u16 mode; + __u16 flags; union { struct { - u_int32_t probability; + __u32 probability; } random; struct { - u_int32_t every; - u_int32_t packet; + __u32 every; + __u32 packet; /* Used internally by the kernel */ - u_int32_t count; + __u32 count; } nth; } u; struct xt_statistic_info *master __attribute__((aligned(8))); diff --git a/include/linux/netfilter/xt_string.h b/include/linux/netfilter/xt_string.h index 8a6ba7bbef9..ecbb95fc89e 100644 --- a/include/linux/netfilter/xt_string.h +++ b/include/linux/netfilter/xt_string.h @@ -1,6 +1,8 @@ #ifndef _XT_STRING_H #define _XT_STRING_H +#include + #define XT_STRING_MAX_PATTERN_SIZE 128 #define XT_STRING_MAX_ALGO_NAME_SIZE 16 @@ -11,18 +13,18 @@ enum { struct xt_string_info { - u_int16_t from_offset; - u_int16_t to_offset; + __u16 from_offset; + __u16 to_offset; char algo[XT_STRING_MAX_ALGO_NAME_SIZE]; char pattern[XT_STRING_MAX_PATTERN_SIZE]; - u_int8_t patlen; + __u8 patlen; union { struct { - u_int8_t invert; + __u8 invert; } v0; struct { - u_int8_t flags; + __u8 flags; } v1; } u; diff --git a/include/linux/netfilter/xt_tcpmss.h b/include/linux/netfilter/xt_tcpmss.h index e03274c4c79..fbac56b9e66 100644 --- a/include/linux/netfilter/xt_tcpmss.h +++ b/include/linux/netfilter/xt_tcpmss.h @@ -1,9 +1,11 @@ #ifndef _XT_TCPMSS_MATCH_H #define _XT_TCPMSS_MATCH_H +#include + struct xt_tcpmss_match_info { - u_int16_t mss_min, mss_max; - u_int8_t invert; + __u16 mss_min, mss_max; + __u8 invert; }; #endif /*_XT_TCPMSS_MATCH_H*/ diff --git a/include/linux/netfilter/xt_tcpudp.h b/include/linux/netfilter/xt_tcpudp.h index 78bc65f11ad..a490a0bc1d2 100644 --- a/include/linux/netfilter/xt_tcpudp.h +++ b/include/linux/netfilter/xt_tcpudp.h @@ -1,15 +1,17 @@ #ifndef _XT_TCPUDP_H #define _XT_TCPUDP_H +#include + /* TCP matching stuff */ struct xt_tcp { - u_int16_t spts[2]; /* Source port range. */ - u_int16_t dpts[2]; /* Destination port range. */ - u_int8_t option; /* TCP Option iff non-zero*/ - u_int8_t flg_mask; /* TCP flags mask byte */ - u_int8_t flg_cmp; /* TCP flags compare byte */ - u_int8_t invflags; /* Inverse flags */ + __u16 spts[2]; /* Source port range. */ + __u16 dpts[2]; /* Destination port range. */ + __u8 option; /* TCP Option iff non-zero*/ + __u8 flg_mask; /* TCP flags mask byte */ + __u8 flg_cmp; /* TCP flags compare byte */ + __u8 invflags; /* Inverse flags */ }; /* Values for "inv" field in struct ipt_tcp. */ @@ -22,9 +24,9 @@ struct xt_tcp /* UDP matching stuff */ struct xt_udp { - u_int16_t spts[2]; /* Source port range. */ - u_int16_t dpts[2]; /* Destination port range. */ - u_int8_t invflags; /* Inverse flags */ + __u16 spts[2]; /* Source port range. */ + __u16 dpts[2]; /* Destination port range. */ + __u8 invflags; /* Inverse flags */ }; /* Values for "invflags" field in struct ipt_udp. */ -- cgit v1.2.3 From 3a471cbc081b6bf2b58a48db13d734ecd3b0d437 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 26 Feb 2009 00:51:45 +0100 Subject: remove __KERNEL_STRICT_NAMES With the last used of non-strict names gone from the exported header files, we can remove the old libc5 compatibility cruft from our headers and only export strict types. Signed-off-by: Arnd Bergmann Signed-off-by: H. Peter Anvin Signed-off-by: Ingo Molnar --- include/linux/types.h | 13 ++----------- 1 file changed, 2 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/types.h b/include/linux/types.h index fca82ed55f4..5abe354020f 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -13,7 +13,7 @@ #include -#ifndef __KERNEL_STRICT_NAMES +#ifdef __KERNEL__ typedef __u32 __kernel_dev_t; @@ -31,7 +31,6 @@ typedef __kernel_timer_t timer_t; typedef __kernel_clockid_t clockid_t; typedef __kernel_mqd_t mqd_t; -#ifdef __KERNEL__ typedef _Bool bool; typedef __kernel_uid32_t uid_t; @@ -47,14 +46,6 @@ typedef __kernel_old_uid_t old_uid_t; typedef __kernel_old_gid_t old_gid_t; #endif /* CONFIG_UID16 */ -/* libc5 includes this file to define uid_t, thus uid_t can never change - * when it is included by non-kernel code - */ -#else -typedef __kernel_uid_t uid_t; -typedef __kernel_gid_t gid_t; -#endif /* __KERNEL__ */ - #if defined(__GNUC__) typedef __kernel_loff_t loff_t; #endif @@ -156,7 +147,7 @@ typedef unsigned long blkcnt_t; #define pgoff_t unsigned long #endif -#endif /* __KERNEL_STRICT_NAMES */ +#endif /* __KERNEL__ */ /* * Below are truly Linux-specific types that should never collide with -- cgit v1.2.3 From 8cd2c29dd5f04d91dac6ea7f8b9df4ff1b4380ee Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Wed, 25 Feb 2009 15:22:19 -0800 Subject: compiler-gcc4: conditionalize #error on __KERNEL__ Impact: Fix for exported headers We only want to error out on specific gcc versions if we are actually building the kernel, so conditionalize the #if...#error on __KERNEL__. Based on a patchset by Arnd Bergmann . Cc: Arnd Bergmann Signed-off-by: H. Peter Anvin Signed-off-by: Ingo Molnar --- include/linux/compiler-gcc4.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc4.h b/include/linux/compiler-gcc4.h index 09992718f9e..450fa597c94 100644 --- a/include/linux/compiler-gcc4.h +++ b/include/linux/compiler-gcc4.h @@ -3,8 +3,10 @@ #endif /* GCC 4.1.[01] miscompiles __weak */ -#if __GNUC_MINOR__ == 1 && __GNUC_PATCHLEVEL__ <= 1 -# error Your version of gcc miscompiles the __weak directive +#ifdef __KERNEL__ +# if __GNUC_MINOR__ == 1 && __GNUC_PATCHLEVEL__ <= 1 +# error Your version of gcc miscompiles the __weak directive +# endif #endif #define __used __attribute__((__used__)) -- cgit v1.2.3 From d0adde574b8487ef30f69e2d08bba769e4be513f Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Thu, 26 Mar 2009 17:49:56 +0000 Subject: Add a strictatime mount option Add support for explicitly requesting full atime updates. This makes it possible for kernels to default to relatime but still allow userspace to override it. Signed-off-by: Matthew Garrett Signed-off-by: Linus Torvalds --- include/linux/fs.h | 1 + include/linux/mount.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 92734c0012e..5bc81c4a98c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -141,6 +141,7 @@ struct inodes_stat_t { #define MS_RELATIME (1<<21) /* Update atime relative to mtime/ctime. */ #define MS_KERNMOUNT (1<<22) /* this is a kern_mount call */ #define MS_I_VERSION (1<<23) /* Update inode I_version field */ +#define MS_STRICTATIME (1<<24) /* Always perform atime updates */ #define MS_ACTIVE (1<<30) #define MS_NOUSER (1<<31) diff --git a/include/linux/mount.h b/include/linux/mount.h index cab2a85e2ee..51f55f903af 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -27,6 +27,7 @@ struct mnt_namespace; #define MNT_NODIRATIME 0x10 #define MNT_RELATIME 0x20 #define MNT_READONLY 0x40 /* does the user want this to be r/o? */ +#define MNT_STRICTATIME 0x80 #define MNT_SHRINKABLE 0x100 #define MNT_IMBALANCED_WRITE_COUNT 0x200 /* just for debugging */ -- cgit v1.2.3 From 898585172fa729513d8636257b44bd1cfd279096 Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Mon, 16 Feb 2009 02:55:47 +0800 Subject: PCI: save and restore PCIe 2.0 registers PCIe 2.0 defines several new registers (Device Control 2, Link Control 2, and Slot Control 2). Save and retore them in pci_save_pcie_state() and pci_restore_pcie_state(). Signed-off-by: Yu Zhao Signed-off-by: Jesse Barnes --- include/linux/pci_regs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_regs.h b/include/linux/pci_regs.h index d4e663877f4..e4d08c1b2e0 100644 --- a/include/linux/pci_regs.h +++ b/include/linux/pci_regs.h @@ -488,6 +488,8 @@ #define PCI_EXP_DEVCAP2_ARI 0x20 /* Alternative Routing-ID */ #define PCI_EXP_DEVCTL2 40 /* Device Control 2 */ #define PCI_EXP_DEVCTL2_ARI 0x20 /* Alternative Routing-ID */ +#define PCI_EXP_LNKCTL2 48 /* Link Control 2 */ +#define PCI_EXP_SLTCTL2 56 /* Slot Control 2 */ /* Extended Capabilities (PCI-X 2.0 and Express) */ #define PCI_EXT_CAP_ID(header) (header & 0x0000ffff) -- cgit v1.2.3 From 3341323bb4c198f704cffbfdda37bcec1226ef7d Mon Sep 17 00:00:00 2001 From: Alexander Clouter Date: Fri, 27 Mar 2009 12:59:54 +0800 Subject: hwrng: timeriomem - Use phys address rather than virt There is no ioremap'ing or anything in timeriomem-rng.c as I foolishly used already remapped virtual addresses instead of passing the physical address to be polled. This patch fixes this flaw and lets developers do the Right Thing(tm). Signed-off-by: Alexander Clouter Signed-off-by: Herbert Xu --- include/linux/timeriomem-rng.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/timeriomem-rng.h b/include/linux/timeriomem-rng.h index dd253177f65..3e08a1c8683 100644 --- a/include/linux/timeriomem-rng.h +++ b/include/linux/timeriomem-rng.h @@ -14,7 +14,7 @@ struct timeriomem_rng_data { struct completion completion; unsigned int present:1; - u32 __iomem *address; + void __iomem *address; /* measures in usecs */ unsigned int period; -- cgit v1.2.3 From ac99533fb716171db12798039671f19631cf3586 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Thu, 26 Mar 2009 15:11:25 +0000 Subject: wan: convert sdla driver to net_device_ops Also use internal net_device_stats Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/if_frad.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/if_frad.h b/include/linux/if_frad.h index 60e16a551dd..673f2209453 100644 --- a/include/linux/if_frad.h +++ b/include/linux/if_frad.h @@ -153,7 +153,6 @@ struct frhdr struct dlci_local { - struct net_device_stats stats; struct net_device *master; struct net_device *slave; struct dlci_conf config; -- cgit v1.2.3 From 088b1b88609ce89b6ab19d114cdbec94a44aa22c Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Fri, 2 Jan 2009 13:34:47 +0100 Subject: ide: improve debugging scheme and more specifically, push __func__ into debug macro thus making ide_debug_log() calls shorter and more readable. Signed-off-by: Borislav Petkov --- include/linux/ide.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 854eba8b2ba..9a386501b9c 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1045,10 +1045,11 @@ enum { }; /* DRV_NAME has to be defined in the driver before using the macro below */ -#define __ide_debug_log(lvl, fmt, args...) \ -{ \ - if (unlikely(drive->debug_mask & lvl)) \ - printk(KERN_INFO DRV_NAME ": " fmt, ## args); \ +#define __ide_debug_log(lvl, fmt, args...) \ +{ \ + if (unlikely(drive->debug_mask & lvl)) \ + printk(KERN_INFO DRV_NAME ": %s: " fmt "\n", \ + __func__, ## args); \ } /* -- cgit v1.2.3 From d15a613ba01ff2b209ecad7a38ccbb23b3b06c92 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 27 Mar 2009 12:46:21 +0100 Subject: ide: remove IDE_ARCH_INTR (v2) This micro-optimization is not worth it. Just always check for existence of ->ack_intr method in ide_intr() and ide_timer_expiry(). v2: Fix brown-paper-bag bug spotted by David D. Kilzer. Cc: Geert Uytterhoeven Cc: Michael Schmitz Cc: "David D. Kilzer" Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 9a386501b9c..cda80b5779a 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -202,11 +202,6 @@ static inline void ide_std_init_ports(hw_regs_t *hw, #define MAX_HWIFS 10 -/* Currently only m68k, apus and m8xx need it */ -#ifndef IDE_ARCH_ACK_INTR -# define ide_ack_intr(hwif) (1) -#endif - /* Currently only Atari needs it */ #ifndef IDE_ARCH_LOCK # define ide_release_lock() do {} while (0) -- cgit v1.2.3 From e354c1d8033d97a97a38a1b2cffa1bc285b92ad4 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 27 Mar 2009 12:46:22 +0100 Subject: ide: remove IDE_ARCH_LOCK (v2) * Add ->{get,release}_lock methods to struct ide_port_info and struct ide_host. * Convert core IDE code, m68k IDE code and falconide support to use ->{get,release}_lock methods instead of ide_{get,release}_lock(). * Remove IDE_ARCH_LOCK. v2: * Build fix from Geert updating ide_{get,release}_lock() callers in falconide.c. Cc: Geert Uytterhoeven Cc: Michael Schmitz Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index cda80b5779a..b7d95f09cc2 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -202,12 +202,6 @@ static inline void ide_std_init_ports(hw_regs_t *hw, #define MAX_HWIFS 10 -/* Currently only Atari needs it */ -#ifndef IDE_ARCH_LOCK -# define ide_release_lock() do {} while (0) -# define ide_get_lock(hdlr, data) do {} while (0) -#endif /* IDE_ARCH_LOCK */ - /* * Now for the data we need to maintain per-drive: ide_drive_t */ @@ -845,8 +839,14 @@ struct ide_host { ide_hwif_t *ports[MAX_HOST_PORTS + 1]; unsigned int n_ports; struct device *dev[2]; + int (*init_chipset)(struct pci_dev *); + + void (*get_lock)(irq_handler_t, void *); + void (*release_lock)(void); + irq_handler_t irq_handler; + unsigned long host_flags; void *host_priv; ide_hwif_t *cur_port; /* for hosts requiring serialization */ @@ -1358,7 +1358,12 @@ enum { struct ide_port_info { char *name; + int (*init_chipset)(struct pci_dev *); + + void (*get_lock)(irq_handler_t, void *); + void (*release_lock)(void); + void (*init_iops)(ide_hwif_t *); void (*init_hwif)(ide_hwif_t *); int (*init_dma)(ide_hwif_t *, -- cgit v1.2.3 From 15a453a955f89f6545118770c669b52e925368bd Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 27 Mar 2009 12:46:26 +0100 Subject: ide: include only when needed Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index b7d95f09cc2..47878719c56 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -193,13 +193,6 @@ static inline void ide_std_init_ports(hw_regs_t *hw, hw->io_ports.ctl_addr = ctl_addr; } -#if defined(CONFIG_ARM) || defined(CONFIG_M68K) || defined(CONFIG_MIPS) || \ - defined(CONFIG_PARISC) || defined(CONFIG_PPC) || defined(CONFIG_SPARC) -#include -#else -#include -#endif - #define MAX_HWIFS 10 /* -- cgit v1.2.3 From 69197ad70ef6b854988299c1377864f9755cd03d Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 27 Mar 2009 12:46:26 +0100 Subject: ide: fix memleak on failure in probe_for_drive() Always free drive->id in probe_for_drive() if device is not present. While at it: - remove dead IDE_DFLAG_DEAD flag - remove superfluous IDE_DFLAG_PRESENT check Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 47878719c56..ab8ee4f32f5 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -494,8 +494,6 @@ enum { IDE_DFLAG_NICE1 = (1 << 5), /* device is physically present */ IDE_DFLAG_PRESENT = (1 << 6), - /* device ejected hint */ - IDE_DFLAG_DEAD = (1 << 7), /* id read from device (synthetic if not set) */ IDE_DFLAG_ID_READ = (1 << 8), IDE_DFLAG_NOPROBE = (1 << 9), -- cgit v1.2.3 From 255115fb35f80735c21a1cbe9809e9795a3af26e Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 27 Mar 2009 12:46:27 +0100 Subject: ide: allow host drivers to specify IRQ flags * Add ->irq_flags field to struct ide_port_info and struct ide_host. * Update host drivers and IDE PCI code to use ->irq_flags field. * Convert init_irq() and ide_intr() to use host->irq_flags. This fixes handling of shared IRQs for non-PCI hosts and removes ugly ifdeffery from core IDE code. Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index ab8ee4f32f5..901d323c7bb 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -839,6 +839,9 @@ struct ide_host { irq_handler_t irq_handler; unsigned long host_flags; + + int irq_flags; + void *host_priv; ide_hwif_t *cur_port; /* for hosts requiring serialization */ @@ -1371,6 +1374,9 @@ struct ide_port_info { u16 max_sectors; /* if < than the default one */ u32 host_flags; + + int irq_flags; + u8 pio_mask; u8 swdma_mask; u8 mwdma_mask; -- cgit v1.2.3 From 2787cb8ae5c68a6945eb82ccf96b5f2c4f238323 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 27 Mar 2009 12:46:28 +0100 Subject: ide: add IDE_HFLAG_DTC2278 host flag Add IDE_HFLAG_DTC2278 host flag and use it instead of ide_dtc2278 chipset type in ide_init_port(). There should be no functional changes caused by this patch. Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 901d323c7bb..732a05f3de0 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1325,6 +1325,8 @@ enum { IDE_HFLAG_ERROR_STOPS_FIFO = (1 << 19), /* serialize ports */ IDE_HFLAG_SERIALIZE = (1 << 20), + /* host is DTC2278 */ + IDE_HFLAG_DTC2278 = (1 << 21), /* host is TRM290 */ IDE_HFLAG_TRM290 = (1 << 23), /* use 32-bit I/O ops */ -- cgit v1.2.3 From c094ea0774d6881598da430ea0916a597162f8df Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 27 Mar 2009 12:46:28 +0100 Subject: ide: add IDE_HFLAG_4DRIVES host flag Add IDE_HFLAG_4DRIVES host flag and use it instead of ide_4drives chipset type in ide_init_port(). There should be no functional changes caused by this patch. Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 732a05f3de0..3d4ba8e95d4 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1327,6 +1327,8 @@ enum { IDE_HFLAG_SERIALIZE = (1 << 20), /* host is DTC2278 */ IDE_HFLAG_DTC2278 = (1 << 21), + /* 4 devices on a single set of I/O ports */ + IDE_HFLAG_4DRIVES = (1 << 22), /* host is TRM290 */ IDE_HFLAG_TRM290 = (1 << 23), /* use 32-bit I/O ops */ -- cgit v1.2.3 From 19710d25d50ae0be05eebe4231ed8918b1092d82 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 27 Mar 2009 12:46:28 +0100 Subject: ide: add "flagged" taskfile flags to struct ide_taskfile (v2) * Add ->ftf_flags field to struct ide_taskfile and convert flags for TASKFILE ioctl to use it. * Rename "flagged" taskfile flags: - IDE_TFLAG_FLAGGED -> IDE_FTFLAG_FLAGGED - IDE_TFLAG_FLAGGED_SET_IN_FLAGS -> IDE_FTFLAG_SET_IN_FLAGS - IDE_TFLAG_{OUT,IN}_DATA -> IDE_FTFLAG_{OUT,IN}_DATA v2: * Remember to fully update ide-h8300.c, scc_pata.c and tx493{8,9}ide.c (thanks to Stephen Rothwell for noticing). There should be no functional changes caused by this patch. Cc: Stephen Rothwell Acked-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 66 ++++++++++++++++++++++++++++------------------------- 1 file changed, 35 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 3d4ba8e95d4..675d4363ece 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -234,56 +234,52 @@ typedef enum { enum { IDE_TFLAG_LBA48 = (1 << 0), - IDE_TFLAG_FLAGGED = (1 << 2), - IDE_TFLAG_OUT_DATA = (1 << 3), - IDE_TFLAG_OUT_HOB_FEATURE = (1 << 4), - IDE_TFLAG_OUT_HOB_NSECT = (1 << 5), - IDE_TFLAG_OUT_HOB_LBAL = (1 << 6), - IDE_TFLAG_OUT_HOB_LBAM = (1 << 7), - IDE_TFLAG_OUT_HOB_LBAH = (1 << 8), + IDE_TFLAG_OUT_HOB_FEATURE = (1 << 1), + IDE_TFLAG_OUT_HOB_NSECT = (1 << 2), + IDE_TFLAG_OUT_HOB_LBAL = (1 << 3), + IDE_TFLAG_OUT_HOB_LBAM = (1 << 4), + IDE_TFLAG_OUT_HOB_LBAH = (1 << 5), IDE_TFLAG_OUT_HOB = IDE_TFLAG_OUT_HOB_FEATURE | IDE_TFLAG_OUT_HOB_NSECT | IDE_TFLAG_OUT_HOB_LBAL | IDE_TFLAG_OUT_HOB_LBAM | IDE_TFLAG_OUT_HOB_LBAH, - IDE_TFLAG_OUT_FEATURE = (1 << 9), - IDE_TFLAG_OUT_NSECT = (1 << 10), - IDE_TFLAG_OUT_LBAL = (1 << 11), - IDE_TFLAG_OUT_LBAM = (1 << 12), - IDE_TFLAG_OUT_LBAH = (1 << 13), + IDE_TFLAG_OUT_FEATURE = (1 << 6), + IDE_TFLAG_OUT_NSECT = (1 << 7), + IDE_TFLAG_OUT_LBAL = (1 << 8), + IDE_TFLAG_OUT_LBAM = (1 << 9), + IDE_TFLAG_OUT_LBAH = (1 << 10), IDE_TFLAG_OUT_TF = IDE_TFLAG_OUT_FEATURE | IDE_TFLAG_OUT_NSECT | IDE_TFLAG_OUT_LBAL | IDE_TFLAG_OUT_LBAM | IDE_TFLAG_OUT_LBAH, - IDE_TFLAG_OUT_DEVICE = (1 << 14), - IDE_TFLAG_WRITE = (1 << 15), - IDE_TFLAG_FLAGGED_SET_IN_FLAGS = (1 << 16), - IDE_TFLAG_IN_DATA = (1 << 17), - IDE_TFLAG_CUSTOM_HANDLER = (1 << 18), - IDE_TFLAG_DMA_PIO_FALLBACK = (1 << 19), - IDE_TFLAG_IN_HOB_FEATURE = (1 << 20), - IDE_TFLAG_IN_HOB_NSECT = (1 << 21), - IDE_TFLAG_IN_HOB_LBAL = (1 << 22), - IDE_TFLAG_IN_HOB_LBAM = (1 << 23), - IDE_TFLAG_IN_HOB_LBAH = (1 << 24), + IDE_TFLAG_OUT_DEVICE = (1 << 11), + IDE_TFLAG_WRITE = (1 << 12), + IDE_TFLAG_CUSTOM_HANDLER = (1 << 13), + IDE_TFLAG_DMA_PIO_FALLBACK = (1 << 14), + IDE_TFLAG_IN_HOB_FEATURE = (1 << 15), + IDE_TFLAG_IN_HOB_NSECT = (1 << 16), + IDE_TFLAG_IN_HOB_LBAL = (1 << 17), + IDE_TFLAG_IN_HOB_LBAM = (1 << 18), + IDE_TFLAG_IN_HOB_LBAH = (1 << 19), IDE_TFLAG_IN_HOB_LBA = IDE_TFLAG_IN_HOB_LBAL | IDE_TFLAG_IN_HOB_LBAM | IDE_TFLAG_IN_HOB_LBAH, IDE_TFLAG_IN_HOB = IDE_TFLAG_IN_HOB_FEATURE | IDE_TFLAG_IN_HOB_NSECT | IDE_TFLAG_IN_HOB_LBA, - IDE_TFLAG_IN_FEATURE = (1 << 1), - IDE_TFLAG_IN_NSECT = (1 << 25), - IDE_TFLAG_IN_LBAL = (1 << 26), - IDE_TFLAG_IN_LBAM = (1 << 27), - IDE_TFLAG_IN_LBAH = (1 << 28), + IDE_TFLAG_IN_FEATURE = (1 << 20), + IDE_TFLAG_IN_NSECT = (1 << 21), + IDE_TFLAG_IN_LBAL = (1 << 22), + IDE_TFLAG_IN_LBAM = (1 << 23), + IDE_TFLAG_IN_LBAH = (1 << 24), IDE_TFLAG_IN_LBA = IDE_TFLAG_IN_LBAL | IDE_TFLAG_IN_LBAM | IDE_TFLAG_IN_LBAH, IDE_TFLAG_IN_TF = IDE_TFLAG_IN_NSECT | IDE_TFLAG_IN_LBA, - IDE_TFLAG_IN_DEVICE = (1 << 29), + IDE_TFLAG_IN_DEVICE = (1 << 25), IDE_TFLAG_HOB = IDE_TFLAG_OUT_HOB | IDE_TFLAG_IN_HOB, IDE_TFLAG_TF = IDE_TFLAG_OUT_TF | @@ -291,9 +287,16 @@ enum { IDE_TFLAG_DEVICE = IDE_TFLAG_OUT_DEVICE | IDE_TFLAG_IN_DEVICE, /* force 16-bit I/O operations */ - IDE_TFLAG_IO_16BIT = (1 << 30), + IDE_TFLAG_IO_16BIT = (1 << 26), /* ide_task_t was allocated using kmalloc() */ - IDE_TFLAG_DYN = (1 << 31), + IDE_TFLAG_DYN = (1 << 27), +}; + +enum { + IDE_FTFLAG_FLAGGED = (1 << 0), + IDE_FTFLAG_SET_IN_FLAGS = (1 << 1), + IDE_FTFLAG_OUT_DATA = (1 << 2), + IDE_FTFLAG_IN_DATA = (1 << 3), }; struct ide_taskfile { @@ -330,6 +333,7 @@ typedef struct ide_task_s { struct ide_taskfile tf; u8 tf_array[14]; }; + u8 ftf_flags; /* for TASKFILE ioctl */ u32 tf_flags; int data_phase; struct request *rq; /* copy of request */ -- cgit v1.2.3 From 3616b6536a74ff1c56029c17cbb3575c69c0a574 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 27 Mar 2009 12:46:29 +0100 Subject: ide: complete power step in ide_complete_pm_request() * Complete power step in ide_complete_pm_request(). * Rename ide_complete_pm_request() to ide_complete_pm_rq(). There should be no functional changes caused by this patch. Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 675d4363ece..c5ac19e43fc 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1081,7 +1081,7 @@ int generic_ide_resume(struct device *); void ide_complete_power_step(ide_drive_t *, struct request *); ide_startstop_t ide_start_power_step(ide_drive_t *, struct request *); -void ide_complete_pm_request(ide_drive_t *, struct request *); +void ide_complete_pm_rq(ide_drive_t *, struct request *); void ide_check_pm_state(ide_drive_t *, struct request *); /* -- cgit v1.2.3 From a09485df9cda49fbde2766c86eb18a9cae585162 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 27 Mar 2009 12:46:31 +0100 Subject: ide: move request type specific code from ide_end_drive_cmd() to callers (v3) * Move request type specific code from ide_end_drive_cmd() to callers. * Remove stale ide_end_drive_cmd() documentation and drop no longer used 'stat' argument. Then rename the function to ide_complete_rq(). v2: * Fix handling of blk_pm_request() requests in task_no_data_intr(). v3: * Some ide_no_data_taskfile() users (HPA code and HDIO_DRIVE_* ioctls handlers) access original command later so we need to update it in ide_complete_task(). There should be no functional changes caused by this patch. Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index c5ac19e43fc..83bed2f4378 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1158,7 +1158,8 @@ extern ide_startstop_t ide_do_reset (ide_drive_t *); extern int ide_devset_execute(ide_drive_t *drive, const struct ide_devset *setting, int arg); -extern void ide_end_drive_cmd(ide_drive_t *, u8, u8); +void ide_complete_task(ide_drive_t *, ide_task_t *, u8, u8); +void ide_complete_rq(ide_drive_t *, u8); void ide_tf_dump(const char *, struct ide_taskfile *); -- cgit v1.2.3 From e3d9a73a83d98fc466dabdcfe4f4e7e4419e3f8e Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 27 Mar 2009 12:46:32 +0100 Subject: ide: remove ->data_phase field from ide_hwif_t * Always use hwif->task->data_phase and remove ->data_phase field from ide_hwif_t. * Remove superfluous REQ_TYPE_ATA_TASKFILE check from ide_pio_datablock() while at it. There should be no functional changes caused by this patch. Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 83bed2f4378..146b07a9b64 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -768,9 +768,6 @@ typedef struct hwif_s { int orig_sg_nents; int sg_dma_direction; /* dma transfer direction */ - /* data phase of the active command (currently only valid for PIO/DMA) */ - int data_phase; - struct ide_task_s task; /* current command */ unsigned int nsect; -- cgit v1.2.3 From c7016e95a556098db6dc4d9096a6189be9e18266 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 27 Mar 2009 12:46:33 +0100 Subject: ide: remove no longer needed PC_FLAG_TIMEDOUT packet command flag There should be no functional changes caused by this patch. Acked-by: Borislav Petkov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 146b07a9b64..8b0ea43884c 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -350,8 +350,6 @@ enum { PC_FLAG_DMA_IN_PROGRESS = (1 << 4), PC_FLAG_DMA_ERROR = (1 << 5), PC_FLAG_WRITING = (1 << 6), - /* command timed out */ - PC_FLAG_TIMEDOUT = (1 << 7), }; /* -- cgit v1.2.3 From 5e2040fd0a97888952b37243b5868872bbe0f6ac Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 27 Mar 2009 12:46:34 +0100 Subject: ide: move ->failed_pc to ide_drive_t Move ->failed_pc from struct ide_{disk,tape}_obj to ide_drive_t. There should be no functional changes caused by this patch. Acked-by: Borislav Petkov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 8b0ea43884c..4a904681f3e 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -609,6 +609,9 @@ struct ide_drive_s { /* current packet command */ struct ide_atapi_pc *pc; + /* last failed packet command */ + struct ide_atapi_pc *failed_pc; + /* callback for packet commands */ void (*pc_callback)(struct ide_drive_s *, int); -- cgit v1.2.3 From c152cc1a90f9680cefa74d9ff9ce36038081ba72 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 27 Mar 2009 12:46:34 +0100 Subject: ide: use ->end_request only for private device driver requests * Move IDE{FLOPPY,TAPE}_ERROR_* defines to and rename them to IDE_DRV_ERROR_*. * Handle ->end_request special cases for floppy/tape media in ide_kill_rq(). * Call ->end_request only for private device driver requests. There should be no functional changes caused by this patch. Acked-by: Borislav Petkov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 4a904681f3e..aece06a4930 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -40,6 +40,13 @@ #define ERROR_RESET 3 /* Reset controller every 4th retry */ #define ERROR_RECAL 1 /* Recalibrate every 2nd retry */ +/* Error codes returned in rq->errors to the higher part of the driver. */ +enum { + IDE_DRV_ERROR_GENERAL = 101, + IDE_DRV_ERROR_FILEMARK = 102, + IDE_DRV_ERROR_EOD = 103, +}; + /* * Definitions for accessing IDE controller registers */ -- cgit v1.2.3 From 3ee38302ffc63da93eb0313053a990bb3466e275 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 27 Mar 2009 12:46:36 +0100 Subject: ide: remove ->end_request method * Handle completion of private driver requests explicitly for ide_floppy and ide_tape media in ide_kill_rq(). * Remove no longer needed ->end_request method. There should be no functional changes caused by this patch. Acked-by: Borislav Petkov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index aece06a4930..c2cdf775018 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -427,7 +427,6 @@ struct ide_disk_ops { int); ide_startstop_t (*do_request)(struct ide_drive_s *, struct request *, sector_t); - int (*end_request)(struct ide_drive_s *, int, int); int (*ioctl)(struct ide_drive_s *, struct block_device *, fmode_t, unsigned int, unsigned long); }; @@ -1098,7 +1097,6 @@ void ide_check_pm_state(ide_drive_t *, struct request *); struct ide_driver { const char *version; ide_startstop_t (*do_request)(ide_drive_t *, struct request *, sector_t); - int (*end_request)(ide_drive_t *, int, int); struct device_driver gen_driver; int (*probe)(ide_drive_t *); void (*remove)(ide_drive_t *); -- cgit v1.2.3 From 03a2faaea8f44edfe583ddf1240948019becfbe4 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 27 Mar 2009 12:46:36 +0100 Subject: ide: return request status from ->pc_callback method Make ->pc_callback method return request status and then move the request completion from ->pc_callback to ide_pc_intr(). There should be no functional changes caused by this patch. Acked-by: Borislav Petkov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index c2cdf775018..9127d87cfa9 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -619,7 +619,7 @@ struct ide_drive_s { struct ide_atapi_pc *failed_pc; /* callback for packet commands */ - void (*pc_callback)(struct ide_drive_s *, int); + int (*pc_callback)(struct ide_drive_s *, int); void (*pc_update_buffers)(struct ide_drive_s *, struct ide_atapi_pc *); int (*pc_io_buffers)(struct ide_drive_s *, struct ide_atapi_pc *, -- cgit v1.2.3 From e6830a86c260d73c6f370aa7ed17ee6c71e5ee05 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 27 Mar 2009 12:46:37 +0100 Subject: ide: call ide_build_sglist() prior to ->dma_setup (v2) * Re-map sg table if needed in ide_build_sglist(). * Move ide_build_sglist() call from ->dma_setup to its users. * Un-export ide_build_sglist(). v2: * Build fix for CONFIG_BLK_DEV_IDEDMA=n (noticed by Randy Dunlap). There should be no functional changes caused by this patch. Cc: Randy Dunlap Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 9127d87cfa9..2ee236d1f3a 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1477,6 +1477,8 @@ static inline int ide_set_dma(ide_drive_t *drive) { return 1; } static inline void ide_check_dma_crc(ide_drive_t *drive) { ; } static inline ide_startstop_t ide_dma_timeout_retry(ide_drive_t *drive, int error) { return ide_stopped; } static inline void ide_release_dma_engine(ide_hwif_t *hwif) { ; } +static inline int ide_build_sglist(ide_drive_t *drive, + struct request *rq) { return 0; } #endif /* CONFIG_BLK_DEV_IDEDMA */ #ifdef CONFIG_BLK_DEV_IDEACPI -- cgit v1.2.3 From 22aa4b32a19b1f231d4ce7e9af6354b577a22a35 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 27 Mar 2009 12:46:37 +0100 Subject: ide: remove ide_task_t typedef While at it: - rename struct ide_task_s to struct ide_cmd - remove stale comments from idedisk_{read_native,set}_max_address() - drop unused 'cmd' argument from ide_{cmd,task}_ioctl() - drop unused 'task' argument from tx4939ide_tf_load_fixup() - rename ide_complete_task() to ide_complete_cmd() - use consistent naming for struct ide_cmd variables There should be no functional changes caused by this patch. Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 2ee236d1f3a..f0e3618c725 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -295,7 +295,7 @@ enum { IDE_TFLAG_IN_DEVICE, /* force 16-bit I/O operations */ IDE_TFLAG_IO_16BIT = (1 << 26), - /* ide_task_t was allocated using kmalloc() */ + /* struct ide_cmd was allocated using kmalloc() */ IDE_TFLAG_DYN = (1 << 27), }; @@ -335,7 +335,7 @@ struct ide_taskfile { }; }; -typedef struct ide_task_s { +struct ide_cmd { union { struct ide_taskfile tf; u8 tf_array[14]; @@ -345,7 +345,7 @@ typedef struct ide_task_s { int data_phase; struct request *rq; /* copy of request */ void *special; /* valid_t generally */ -} ide_task_t; +}; /* ATAPI packet command flags */ enum { @@ -652,8 +652,8 @@ struct ide_tp_ops { void (*set_irq)(struct hwif_s *, int); - void (*tf_load)(ide_drive_t *, struct ide_task_s *); - void (*tf_read)(ide_drive_t *, struct ide_task_s *); + void (*tf_load)(ide_drive_t *, struct ide_cmd *); + void (*tf_read)(ide_drive_t *, struct ide_cmd *); void (*input_data)(ide_drive_t *, struct request *, void *, unsigned int); @@ -775,7 +775,7 @@ typedef struct hwif_s { int orig_sg_nents; int sg_dma_direction; /* dma transfer direction */ - struct ide_task_s task; /* current command */ + struct ide_cmd cmd; /* current command */ unsigned int nsect; unsigned int nleft; @@ -1161,7 +1161,7 @@ extern ide_startstop_t ide_do_reset (ide_drive_t *); extern int ide_devset_execute(ide_drive_t *drive, const struct ide_devset *setting, int arg); -void ide_complete_task(ide_drive_t *, ide_task_t *, u8, u8); +void ide_complete_cmd(ide_drive_t *, struct ide_cmd *, u8, u8); void ide_complete_rq(ide_drive_t *, u8); void ide_tf_dump(const char *, struct ide_taskfile *); @@ -1172,8 +1172,8 @@ u8 ide_read_altstatus(ide_hwif_t *); void ide_set_irq(ide_hwif_t *, int); -void ide_tf_load(ide_drive_t *, ide_task_t *); -void ide_tf_read(ide_drive_t *, ide_task_t *); +void ide_tf_load(ide_drive_t *, struct ide_cmd *); +void ide_tf_read(ide_drive_t *, struct ide_cmd *); void ide_input_data(ide_drive_t *, struct request *, void *, unsigned int); void ide_output_data(ide_drive_t *, struct request *, void *, unsigned int); @@ -1224,14 +1224,14 @@ int ide_cd_get_xferlen(struct request *); ide_startstop_t ide_issue_pc(ide_drive_t *); -ide_startstop_t do_rw_taskfile(ide_drive_t *, ide_task_t *); +ide_startstop_t do_rw_taskfile(ide_drive_t *, struct ide_cmd *); void task_end_request(ide_drive_t *, struct request *, u8); -int ide_raw_taskfile(ide_drive_t *, ide_task_t *, u8 *, u16); -int ide_no_data_taskfile(ide_drive_t *, ide_task_t *); +int ide_raw_taskfile(ide_drive_t *, struct ide_cmd *, u8 *, u16); +int ide_no_data_taskfile(ide_drive_t *, struct ide_cmd *); -int ide_taskfile_ioctl(ide_drive_t *, unsigned int, unsigned long); +int ide_taskfile_ioctl(ide_drive_t *, unsigned long); int ide_dev_read_id(ide_drive_t *, u8, u16 *); -- cgit v1.2.3 From adb1af9803d167091c2cb4de14014185054bfe2c Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 27 Mar 2009 12:46:38 +0100 Subject: ide: pass command instead of request to ide_pio_datablock() * Add IDE_TFLAG_FS taskfile flag and set it for REQ_TYPE_FS requests. * Convert ->{in,out}put_data methods to take command instead of request as an argument. Then convert pre_task_out_intr(), task_end_request(), task_error(), task_in_unexpected(), ide_pio_sector(), ide_pio_multi() and ide_pio_datablock() in similar way. * Rename task_end_request() to ide_finish_cmd(). There should be no functional changes caused by this patch. Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index f0e3618c725..1785582e1f8 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -297,6 +297,7 @@ enum { IDE_TFLAG_IO_16BIT = (1 << 26), /* struct ide_cmd was allocated using kmalloc() */ IDE_TFLAG_DYN = (1 << 27), + IDE_TFLAG_FS = (1 << 28), }; enum { @@ -655,10 +656,10 @@ struct ide_tp_ops { void (*tf_load)(ide_drive_t *, struct ide_cmd *); void (*tf_read)(ide_drive_t *, struct ide_cmd *); - void (*input_data)(ide_drive_t *, struct request *, void *, - unsigned int); - void (*output_data)(ide_drive_t *, struct request *, void *, - unsigned int); + void (*input_data)(ide_drive_t *, struct ide_cmd *, + void *, unsigned int); + void (*output_data)(ide_drive_t *, struct ide_cmd *, + void *, unsigned int); }; extern const struct ide_tp_ops default_tp_ops; @@ -866,7 +867,7 @@ typedef ide_startstop_t (ide_handler_t)(ide_drive_t *); typedef int (ide_expiry_t)(ide_drive_t *); /* used by ide-cd, ide-floppy, etc. */ -typedef void (xfer_func_t)(ide_drive_t *, struct request *rq, void *, unsigned); +typedef void (xfer_func_t)(ide_drive_t *, struct ide_cmd *, void *, unsigned); extern struct mutex ide_setting_mtx; @@ -1175,8 +1176,8 @@ void ide_set_irq(ide_hwif_t *, int); void ide_tf_load(ide_drive_t *, struct ide_cmd *); void ide_tf_read(ide_drive_t *, struct ide_cmd *); -void ide_input_data(ide_drive_t *, struct request *, void *, unsigned int); -void ide_output_data(ide_drive_t *, struct request *, void *, unsigned int); +void ide_input_data(ide_drive_t *, struct ide_cmd *, void *, unsigned int); +void ide_output_data(ide_drive_t *, struct ide_cmd *, void *, unsigned int); int ide_io_buffers(ide_drive_t *, struct ide_atapi_pc *, unsigned int, int); @@ -1226,7 +1227,7 @@ ide_startstop_t ide_issue_pc(ide_drive_t *); ide_startstop_t do_rw_taskfile(ide_drive_t *, struct ide_cmd *); -void task_end_request(ide_drive_t *, struct request *, u8); +void ide_finish_cmd(ide_drive_t *, struct ide_cmd *, u8); int ide_raw_taskfile(ide_drive_t *, struct ide_cmd *, u8 *, u16); int ide_no_data_taskfile(ide_drive_t *, struct ide_cmd *); -- cgit v1.2.3 From b6308ee0c55acd2e943d849773c9f0a49c516317 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 27 Mar 2009 12:46:38 +0100 Subject: ide: move command related fields from ide_hwif_t to struct ide_cmd * Move command related fields from ide_hwif_t to struct ide_cmd. * Make ide_init_sg_cmd() take command and sectors number as arguments. There should be no functional changes caused by this patch. Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 1785582e1f8..02128e9241d 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -344,6 +344,16 @@ struct ide_cmd { u8 ftf_flags; /* for TASKFILE ioctl */ u32 tf_flags; int data_phase; + + int sg_nents; /* number of sg entries */ + int orig_sg_nents; + int sg_dma_direction; /* DMA transfer direction */ + + unsigned int nsect; + unsigned int nleft; + struct scatterlist *cursg; + unsigned int cursg_ofs; + struct request *rq; /* copy of request */ void *special; /* valid_t generally */ }; @@ -772,17 +782,9 @@ typedef struct hwif_s { /* Scatter-gather list used to build the above */ struct scatterlist *sg_table; int sg_max_nents; /* Maximum number of entries in it */ - int sg_nents; /* Current number of entries in it */ - int orig_sg_nents; - int sg_dma_direction; /* dma transfer direction */ struct ide_cmd cmd; /* current command */ - unsigned int nsect; - unsigned int nleft; - struct scatterlist *cursg; - unsigned int cursg_ofs; - int rqsize; /* max sectors per request */ int irq; /* our irq number */ @@ -1410,7 +1412,7 @@ int ide_pci_resume(struct pci_dev *); #endif void ide_map_sg(ide_drive_t *, struct request *); -void ide_init_sg_cmd(ide_drive_t *, struct request *); +void ide_init_sg_cmd(struct ide_cmd *, int); #define BAD_DMA_DRIVE 0 #define GOOD_DMA_DRIVE 1 -- cgit v1.2.3 From 0dfb991c6943c810175376b58d1c29cfe532541b Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 27 Mar 2009 12:46:39 +0100 Subject: ide: use ata_tf_protocols enums * Add IDE_TFLAG_MULTI_PIO taskfile flag and set it for commands using multi-PIO protocol. * Use ata_tf_protocols enums instead of TASKFILE_* defines to denote command's protocol and then rename ->data_phase field to ->protocol. * Remove no longer needed includes. There should be no functional changes caused by this patch. Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 02128e9241d..f9decc9852e 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -298,6 +298,7 @@ enum { /* struct ide_cmd was allocated using kmalloc() */ IDE_TFLAG_DYN = (1 << 27), IDE_TFLAG_FS = (1 << 28), + IDE_TFLAG_MULTI_PIO = (1 << 29), }; enum { @@ -343,7 +344,7 @@ struct ide_cmd { }; u8 ftf_flags; /* for TASKFILE ioctl */ u32 tf_flags; - int data_phase; + int protocol; int sg_nents; /* number of sg entries */ int orig_sg_nents; -- cgit v1.2.3 From 1caf236dafb7291f9fdfe54b12dd945aec0dca03 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 27 Mar 2009 12:46:42 +0100 Subject: ide: add ide_end_rq() (v2) * Move request dequeuing from __ide_end_request() to ide_end_request(). * Rename __ide_end_request() to ide_end_rq() and export it. * Fix ide_end_rq() to pass original blk_end_request() return value. * ide_end_dequeued_request() is used only in cdrom_end_request() so inline it there and then remove the function. v2: * Remove needless BUG_ON() while at it (start_request()'s one is enough). There should be no functional changes caused by this patch. Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index f9decc9852e..f910f4ccfaa 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1131,8 +1131,8 @@ int generic_ide_ioctl(ide_drive_t *, struct block_device *, unsigned, unsigned l extern int ide_vlb_clk; extern int ide_pci_clk; +int ide_end_rq(ide_drive_t *, struct request *, int, unsigned int); int ide_end_request(ide_drive_t *, int, int); -int ide_end_dequeued_request(ide_drive_t *, struct request *, int, int); void ide_kill_rq(ide_drive_t *, struct request *); void __ide_set_handler(ide_drive_t *, ide_handler_t *, unsigned int, -- cgit v1.2.3 From 6902a5331256e1b9f4cef95a1e3622252113b260 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 27 Mar 2009 12:46:43 +0100 Subject: ide: pass error value to ide_complete_rq() Set rq->errors at ide_complete_rq() call sites and then pass error value to ide_complete_rq(). [ Some rq->errors assignments look really wrong but this patch leaves them alone to not introduce too many changes at once. ] There should be no functional changes caused by this patch. Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index f910f4ccfaa..32369d5797d 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1166,7 +1166,7 @@ extern int ide_devset_execute(ide_drive_t *drive, const struct ide_devset *setting, int arg); void ide_complete_cmd(ide_drive_t *, struct ide_cmd *, u8, u8); -void ide_complete_rq(ide_drive_t *, u8); +void ide_complete_rq(ide_drive_t *, int); void ide_tf_dump(const char *, struct ide_taskfile *); -- cgit v1.2.3 From a9587fd8c48415cc93fef7f4ba7748a5d3477e7b Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 27 Mar 2009 12:46:44 +0100 Subject: ide: remove BUG() from ide_complete_rq() It is no longer needed so remove it, also while at it dequeue the request only on blk_end_request() success and make ide_complete_rq() return an error value. Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 32369d5797d..bb62bfaf02e 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1166,7 +1166,7 @@ extern int ide_devset_execute(ide_drive_t *drive, const struct ide_devset *setting, int arg); void ide_complete_cmd(ide_drive_t *, struct ide_cmd *, u8, u8); -void ide_complete_rq(ide_drive_t *, int); +int ide_complete_rq(ide_drive_t *, int); void ide_tf_dump(const char *, struct ide_taskfile *); -- cgit v1.2.3 From f974b196f58fe042c7b2b4c0ee15d5a6112dbf40 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 27 Mar 2009 12:46:44 +0100 Subject: ide: pass number of bytes to complete to ide_complete_rq() There should be no functional changes caused by this patch. Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index bb62bfaf02e..cbfb64fdeda 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1166,7 +1166,7 @@ extern int ide_devset_execute(ide_drive_t *drive, const struct ide_devset *setting, int arg); void ide_complete_cmd(ide_drive_t *, struct ide_cmd *, u8, u8); -int ide_complete_rq(ide_drive_t *, int); +int ide_complete_rq(ide_drive_t *, int, unsigned int); void ide_tf_dump(const char *, struct ide_taskfile *); -- cgit v1.2.3 From 130e886708d6e11f3d54e5d27c266578de56f343 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 27 Mar 2009 12:46:45 +0100 Subject: ide: remove ide_end_request() * Add ide_rq_bytes() helper. * Add blk_noretry_request() quirk to ide_complete_rq() (currently only fs requests can be marked as "noretry" so there is no change in behavior). * Switch current ide_end_request() users to use ide_complete_rq(). [ No need to check for rq->nr_sectors == 0 in {ide_dma,task_pio}_intr(), nsectors == 0 in cdrom_end_request() and err == 0 in ide_do_devset(). ] * Remove no longer needed ide_end_request(). There should be no functional changes caused by this patch. Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index cbfb64fdeda..b6142171baf 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1131,8 +1131,8 @@ int generic_ide_ioctl(ide_drive_t *, struct block_device *, unsigned, unsigned l extern int ide_vlb_clk; extern int ide_pci_clk; +unsigned int ide_rq_bytes(struct request *); int ide_end_rq(ide_drive_t *, struct request *, int, unsigned int); -int ide_end_request(ide_drive_t *, int, int); void ide_kill_rq(ide_drive_t *, struct request *); void __ide_set_handler(ide_drive_t *, ide_handler_t *, unsigned int, -- cgit v1.2.3 From 2298169418f43ba5e0919762a4bab95a1227872a Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 27 Mar 2009 12:46:46 +0100 Subject: ide: pass command to ide_map_sg() * Set IDE_TFLAG_WRITE flag and ->rq also for ATA_CMD_PACKET commands. * Pass command to ->dma_setup method and update all its implementations accordingly. * Pass command instead of request to ide_build_sglist(), *_build_dmatable() and ide_map_sg(). While at it: * Fix scc_dma_setup() documentation + use ATA_DMA_WR define. * Rename sgiioc4_build_dma_table() to sgiioc4_build_dmatable(), change return value type to 'int' and drop unused 'ddir' argument. * Do some minor cleanups in [tx4939]ide_dma_setup(). There should be no functional changes caused by this patch. Acked-by: Borislav Petkov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index b6142171baf..b30e79c6ff5 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -714,7 +714,7 @@ struct ide_port_ops { struct ide_dma_ops { void (*dma_host_set)(struct ide_drive_s *, int); - int (*dma_setup)(struct ide_drive_s *); + int (*dma_setup)(struct ide_drive_s *, struct ide_cmd *); void (*dma_exec_cmd)(struct ide_drive_s *, u8); void (*dma_start)(struct ide_drive_s *); int (*dma_end)(struct ide_drive_s *); @@ -1412,7 +1412,7 @@ int ide_pci_resume(struct pci_dev *); #define ide_pci_resume NULL #endif -void ide_map_sg(ide_drive_t *, struct request *); +void ide_map_sg(ide_drive_t *, struct ide_cmd *); void ide_init_sg_cmd(struct ide_cmd *, int); #define BAD_DMA_DRIVE 0 @@ -1447,14 +1447,14 @@ ide_startstop_t ide_dma_intr(ide_drive_t *); int ide_allocate_dma_engine(ide_hwif_t *); void ide_release_dma_engine(ide_hwif_t *); -int ide_build_sglist(ide_drive_t *, struct request *); +int ide_build_sglist(ide_drive_t *, struct ide_cmd *); void ide_destroy_dmatable(ide_drive_t *); #ifdef CONFIG_BLK_DEV_IDEDMA_SFF int config_drive_for_dma(ide_drive_t *); -extern int ide_build_dmatable(ide_drive_t *, struct request *); +int ide_build_dmatable(ide_drive_t *, struct ide_cmd *); void ide_dma_host_set(ide_drive_t *, int); -extern int ide_dma_setup(ide_drive_t *); +int ide_dma_setup(ide_drive_t *, struct ide_cmd *); void ide_dma_exec_cmd(ide_drive_t *, u8); extern void ide_dma_start(ide_drive_t *); int ide_dma_end(ide_drive_t *); @@ -1482,7 +1482,7 @@ static inline void ide_check_dma_crc(ide_drive_t *drive) { ; } static inline ide_startstop_t ide_dma_timeout_retry(ide_drive_t *drive, int error) { return ide_stopped; } static inline void ide_release_dma_engine(ide_hwif_t *hwif) { ; } static inline int ide_build_sglist(ide_drive_t *drive, - struct request *rq) { return 0; } + struct ide_cmd *cmd) { return 0; } #endif /* CONFIG_BLK_DEV_IDEDMA */ #ifdef CONFIG_BLK_DEV_IDEACPI -- cgit v1.2.3 From b788ee9c6561fd9219a503216284d61036a0dc0b Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 27 Mar 2009 12:46:46 +0100 Subject: ide: use do_rw_taskfile() for ATA_CMD_PACKET commands * Pass command to ide_issue_pc() and update ->do_request methods in ide-{cd,floppy,tape}.c accordingly. * Convert ide_pktcmd_tf_load() to ide_init_packet_cmd() which just initializes command structure and use do_rw_taskfile() to load ATA_CMD_PACKET commands. While at it: * Rename ide{floppy,tape}_issue_pc() to ide_{floppy,tape}_issue_pc(). There should be no functional changes caused by this patch. Acked-by: Borislav Petkov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index b30e79c6ff5..e339d664655 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1226,7 +1226,7 @@ int ide_cd_expiry(ide_drive_t *); int ide_cd_get_xferlen(struct request *); -ide_startstop_t ide_issue_pc(ide_drive_t *); +ide_startstop_t ide_issue_pc(ide_drive_t *, struct ide_cmd *); ide_startstop_t do_rw_taskfile(ide_drive_t *, struct ide_cmd *); -- cgit v1.2.3 From 60c0cd02b254805691cdc61101ada6af7bd56fde Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 27 Mar 2009 12:46:46 +0100 Subject: ide: set hwif->expiry prior to calling [__]ide_set_handler() * Set hwif->expiry prior to calling [__]ide_set_handler() and drop 'expiry' argument. * Set hwif->expiry to NULL in ide_{timer_expiry,intr}() and remove 'hwif->expiry = NULL' assignments. There should be no functional changes caused by this patch. Acked-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index e339d664655..476f59885fd 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1135,10 +1135,8 @@ unsigned int ide_rq_bytes(struct request *); int ide_end_rq(ide_drive_t *, struct request *, int, unsigned int); void ide_kill_rq(ide_drive_t *, struct request *); -void __ide_set_handler(ide_drive_t *, ide_handler_t *, unsigned int, - ide_expiry_t *); -void ide_set_handler(ide_drive_t *, ide_handler_t *, unsigned int, - ide_expiry_t *); +void __ide_set_handler(ide_drive_t *, ide_handler_t *, unsigned int); +void ide_set_handler(ide_drive_t *, ide_handler_t *, unsigned int); void ide_execute_command(ide_drive_t *, u8, ide_handler_t *, unsigned int, ide_expiry_t *); -- cgit v1.2.3 From 22117d6eaac50d366d9013c88318a869ea4d8739 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 27 Mar 2009 12:46:47 +0100 Subject: ide: add ->dma_timer_expiry method and remove ->dma_exec_cmd one (v2) * Rename dma_timer_expiry() to ide_dma_sff_timer_expiry() and export it. * Add ->dma_timer_expiry method and use it to set hwif->expiry for ATA_PROT_DMA protocol in do_rw_taskfile(). * Initialize ->dma_timer_expiry to ide_dma_sff_timer_expiry() for SFF hosts. * Move setting hwif->expiry from ide_execute_command() to its users and drop 'expiry' argument. * Use ide_execute_command() instead of ->dma_exec_cmd in do_rw_taskfile(). * Remove ->dma_exec_cmd method and its implementations. * Unexport ide_execute_command() and ide_dma_intr(). v2: * Fix CONFIG_BLK_DEV_IDEDMA=n build (noticed by Randy Dunlap). * Fix *dma_expiry naming (suggested by Sergei Shtylyov). There should be no functional changes caused by this patch. Cc: Randy Dunlap Cc: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 476f59885fd..9476939101b 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -715,11 +715,11 @@ struct ide_port_ops { struct ide_dma_ops { void (*dma_host_set)(struct ide_drive_s *, int); int (*dma_setup)(struct ide_drive_s *, struct ide_cmd *); - void (*dma_exec_cmd)(struct ide_drive_s *, u8); void (*dma_start)(struct ide_drive_s *); int (*dma_end)(struct ide_drive_s *); int (*dma_test_irq)(struct ide_drive_s *); void (*dma_lost_irq)(struct ide_drive_s *); + int (*dma_timer_expiry)(struct ide_drive_s *); void (*dma_timeout)(struct ide_drive_s *); /* * The following method is optional and only required to be @@ -1138,8 +1138,7 @@ void ide_kill_rq(ide_drive_t *, struct request *); void __ide_set_handler(ide_drive_t *, ide_handler_t *, unsigned int); void ide_set_handler(ide_drive_t *, ide_handler_t *, unsigned int); -void ide_execute_command(ide_drive_t *, u8, ide_handler_t *, unsigned int, - ide_expiry_t *); +void ide_execute_command(ide_drive_t *, u8, ide_handler_t *, unsigned int); void ide_execute_pkt_cmd(ide_drive_t *); @@ -1453,10 +1452,10 @@ int config_drive_for_dma(ide_drive_t *); int ide_build_dmatable(ide_drive_t *, struct ide_cmd *); void ide_dma_host_set(ide_drive_t *, int); int ide_dma_setup(ide_drive_t *, struct ide_cmd *); -void ide_dma_exec_cmd(ide_drive_t *, u8); extern void ide_dma_start(ide_drive_t *); int ide_dma_end(ide_drive_t *); int ide_dma_test_irq(ide_drive_t *); +int ide_dma_sff_timer_expiry(ide_drive_t *); u8 ide_dma_sff_read_status(ide_hwif_t *); extern const struct ide_dma_ops sff_dma_ops; #else @@ -1477,6 +1476,7 @@ static inline void ide_dma_on(ide_drive_t *drive) { ; } static inline void ide_dma_verbose(ide_drive_t *drive) { ; } static inline int ide_set_dma(ide_drive_t *drive) { return 1; } static inline void ide_check_dma_crc(ide_drive_t *drive) { ; } +static inline ide_startstop_t ide_dma_intr(ide_drive_t *drive) { return ide_stopped; } static inline ide_startstop_t ide_dma_timeout_retry(ide_drive_t *drive, int error) { return ide_stopped; } static inline void ide_release_dma_engine(ide_hwif_t *hwif) { ; } static inline int ide_build_sglist(ide_drive_t *drive, -- cgit v1.2.3 From 35b5d0be3d8de9a5ac51471c12029fb115200cdc Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 27 Mar 2009 12:46:47 +0100 Subject: ide: remove ide_execute_pkt_cmd() (v2) * Pass command structure to ide_execute_command() and skip __ide_set_handler() for ATAPI protocols on non-DRQ devices. * Convert ide_issue_pc() to always use ide_execute_command() and remove no longer needed ide_execute_pkt_cmd(). v2: * Fix for non-DRQ devices (based on report from Borislav). There should be no functional changes caused by this patch. Acked-by: Borislav Petkov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 9476939101b..2d0c7afd5e5 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1138,9 +1138,8 @@ void ide_kill_rq(ide_drive_t *, struct request *); void __ide_set_handler(ide_drive_t *, ide_handler_t *, unsigned int); void ide_set_handler(ide_drive_t *, ide_handler_t *, unsigned int); -void ide_execute_command(ide_drive_t *, u8, ide_handler_t *, unsigned int); - -void ide_execute_pkt_cmd(ide_drive_t *); +void ide_execute_command(ide_drive_t *, struct ide_cmd *, ide_handler_t *, + unsigned int); void ide_pad_transfer(ide_drive_t *, int, int); -- cgit v1.2.3 From bf717c0a2e18dbe82eeb28e57b0abede3cdf45d6 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 27 Mar 2009 12:46:47 +0100 Subject: ide: keep track of number of bytes instead of sectors in struct ide_cmd * Pass number of bytes instead of sectors to ide_init_sg_cmd(). * Pass number of bytes to process to ide_pio_sector() and rename it to ide_pio_bytes(). * Rename ->nsect field to ->nbytes in struct ide_cmd and use ->nbytes, ->nleft and ->cursg_ofs to keep track of number of bytes instead of sectors. There should be no functional changes caused by this patch. Acked-by: Borislav Petkov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 2d0c7afd5e5..d5d832271f4 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -350,7 +350,7 @@ struct ide_cmd { int orig_sg_nents; int sg_dma_direction; /* DMA transfer direction */ - unsigned int nsect; + unsigned int nbytes; unsigned int nleft; struct scatterlist *cursg; unsigned int cursg_ofs; @@ -1409,7 +1409,7 @@ int ide_pci_resume(struct pci_dev *); #endif void ide_map_sg(ide_drive_t *, struct ide_cmd *); -void ide_init_sg_cmd(struct ide_cmd *, int); +void ide_init_sg_cmd(struct ide_cmd *, unsigned int); #define BAD_DMA_DRIVE 0 #define GOOD_DMA_DRIVE 1 -- cgit v1.2.3 From 05fd8e73e1357feaea9c48938d937eae76b4aef4 Mon Sep 17 00:00:00 2001 From: Sascha Hauer Date: Sat, 7 Mar 2009 12:55:49 +0100 Subject: clkdev: add possibility to get a clock based on the device name This adds clk_get_sys to get a clock without the associated struct device. Signed-off-by: Sascha Hauer --- include/linux/clk.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk.h b/include/linux/clk.h index 778777316ea..1db9bbf444a 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -125,4 +125,21 @@ int clk_set_parent(struct clk *clk, struct clk *parent); */ struct clk *clk_get_parent(struct clk *clk); +/** + * clk_get_sys - get a clock based upon the device name + * @dev_id: device name + * @con_id: connection ID + * + * Returns a struct clk corresponding to the clock producer, or + * valid IS_ERR() condition containing errno. The implementation + * uses @dev_id and @con_id to determine the clock consumer, and + * thereby the clock producer. In contrast to clk_get() this function + * takes the device name instead of the device itself for identification. + * + * Drivers must assume that the clock source is not enabled. + * + * clk_get_sys should not be called from within interrupt context. + */ +struct clk *clk_get_sys(const char *dev_id, const char *con_id); + #endif -- cgit v1.2.3 From 9b57896e62bfa752ee7435e6cfe57fb210c0db8c Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Thu, 26 Mar 2009 21:58:14 +0900 Subject: sony-laptop: Add support for extra keyboard events The current sony-laptop code assumes that the keyboard event method is always located at slot 2 in the platform code. Remove this assumption and add support for some additional hotkeys. Signed-off-by: Matthew Garrett Signed-off-by: Mattia Dongili Signed-off-by: Len Brown --- include/linux/sonypi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sonypi.h b/include/linux/sonypi.h index f41ffd7c2dd..8458dbe9586 100644 --- a/include/linux/sonypi.h +++ b/include/linux/sonypi.h @@ -103,6 +103,7 @@ #define SONYPI_EVENT_WIRELESS_OFF 61 #define SONYPI_EVENT_ZOOM_IN_PRESSED 62 #define SONYPI_EVENT_ZOOM_OUT_PRESSED 63 +#define SONYPI_EVENT_CD_EJECT_PRESSED 64 /* get/set brightness */ #define SONYPI_IOCGBRT _IOR('v', 0, __u8) -- cgit v1.2.3 From 45c7942ba8f6b7d5d1147c10f84f0cbf5fa3a2b8 Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Thu, 26 Mar 2009 21:58:16 +0900 Subject: sony-laptop: Add support for extended hotkeys Recent Sony SR-series machines have an additional set of buttons accessed via the 0x127 method rather than the 0x100 method. Add support for these. Signed-off-by: Matthew Garrett Signed-off-by: Mattia Dongili Signed-off-by: Len Brown --- include/linux/sonypi.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sonypi.h b/include/linux/sonypi.h index 8458dbe9586..bb835019ac7 100644 --- a/include/linux/sonypi.h +++ b/include/linux/sonypi.h @@ -104,6 +104,10 @@ #define SONYPI_EVENT_ZOOM_IN_PRESSED 62 #define SONYPI_EVENT_ZOOM_OUT_PRESSED 63 #define SONYPI_EVENT_CD_EJECT_PRESSED 64 +#define SONYPI_EVENT_MODEKEY_PRESSED 65 +#define SONYPI_EVENT_PKEY_P4 66 +#define SONYPI_EVENT_PKEY_P5 67 +#define SONYPI_EVENT_SETTINGKEY_PRESSED 68 /* get/set brightness */ #define SONYPI_IOCGBRT _IOR('v', 0, __u8) -- cgit v1.2.3 From 1cae71032183776e833036fe828315dcd3444df1 Mon Sep 17 00:00:00 2001 From: Harald Jenny Date: Thu, 26 Mar 2009 21:58:18 +0900 Subject: sony-laptop: VGN-A317M hotkey support This laptop has 5 SPIC managed buttons above the keyboard: sound + and - as well as brightness, zoom and S1. Possibly the entire VGN-A serie behaves the same. Signed-off-by: Harald Jenny Signed-off-by: Mattia Dongili Signed-off-by: Len Brown --- include/linux/sonypi.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sonypi.h b/include/linux/sonypi.h index bb835019ac7..34c4475ac4a 100644 --- a/include/linux/sonypi.h +++ b/include/linux/sonypi.h @@ -108,6 +108,9 @@ #define SONYPI_EVENT_PKEY_P4 66 #define SONYPI_EVENT_PKEY_P5 67 #define SONYPI_EVENT_SETTINGKEY_PRESSED 68 +#define SONYPI_EVENT_VOLUME_INC_PRESSED 69 +#define SONYPI_EVENT_VOLUME_DEC_PRESSED 70 +#define SONYPI_EVENT_BRIGHTNESS_PRESSED 71 /* get/set brightness */ #define SONYPI_IOCGBRT _IOR('v', 0, __u8) -- cgit v1.2.3 From 2b1c6bd77d4e6a727ffac8630cd154b2144b751a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 28 Nov 2008 10:09:09 +0100 Subject: generic compat_sys_ustat Due to a different size of ino_t ustat needs a compat handler, but currently only x86 and mips provide one. Add a generic compat_sys_ustat and switch all architectures over to it. Instead of doing various user copy hacks compat_sys_ustat just reimplements sys_ustat as it's trivial. This was suggested by Arnd Bergmann. Found by Eric Sandeen when running xfstests/017 on ppc64, which causes stack smashing warnings on RHEL/Fedora due to the too large amount of data writen by the syscall. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/compat.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 3fd2194ff57..b880864672d 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -125,6 +125,13 @@ struct compat_dirent { char d_name[256]; }; +struct compat_ustat { + compat_daddr_t f_tfree; + compat_ino_t f_tinode; + char f_fname[6]; + char f_fpack[6]; +}; + typedef union compat_sigval { compat_int_t sival_int; compat_uptr_t sival_ptr; @@ -178,6 +185,7 @@ long compat_sys_semtimedop(int semid, struct sembuf __user *tsems, unsigned nsems, const struct compat_timespec __user *timeout); asmlinkage long compat_sys_keyctl(u32 option, u32 arg2, u32 arg3, u32 arg4, u32 arg5); +asmlinkage long compat_sys_ustat(unsigned dev, struct compat_ustat __user *u32); asmlinkage ssize_t compat_sys_readv(unsigned long fd, const struct compat_iovec __user *vec, unsigned long vlen); -- cgit v1.2.3 From 10f303ae1e5e77a9f7cb053e6329906afb132c67 Mon Sep 17 00:00:00 2001 From: Cheng Renquan Date: Wed, 14 Jan 2009 17:01:33 +0800 Subject: do_pipe cleanup: drop its last user in arch/alpha/ The last user of do_pipe is in arch/alpha/, after replacing it with do_pipe_flags, the do_pipe can be totally dropped. Signed-off-by: Cheng Renquan Acked-by: Richard Henderson Signed-off-by: Al Viro --- include/linux/fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 92734c0012e..51de83bd8a8 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1881,7 +1881,6 @@ static inline void allow_write_access(struct file *file) if (file) atomic_inc(&file->f_path.dentry->d_inode->i_writecount); } -extern int do_pipe(int *); extern int do_pipe_flags(int *, int); extern struct file *create_read_pipe(struct file *f, int flags); extern struct file *create_write_pipe(int flags); -- cgit v1.2.3 From c2aca5e529a2499d454c41e01f59f1d5fe4a1364 Mon Sep 17 00:00:00 2001 From: Steven Whitehouse Date: Tue, 20 Jan 2009 10:29:45 +0000 Subject: vfs: Update fs.h to use inline functions when no file locking set This avoids various issues which might give rise to compiler warnings about missing functions and/or unused variable with the previous macros. This also fixes a bug where one of the macros was returning 0, but it should have been void. Reported-by: Randy Dunlap Signed-off-by: Steven Whitehouse Tested-by: Randy Dunlap Signed-off-by: Al Viro --- include/linux/fs.h | 165 ++++++++++++++++++++++++++++++++++++++++++++--------- 1 file changed, 139 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 51de83bd8a8..d84020b7e67 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1063,34 +1063,147 @@ extern int lease_modify(struct file_lock **, int); extern int lock_may_read(struct inode *, loff_t start, unsigned long count); extern int lock_may_write(struct inode *, loff_t start, unsigned long count); #else /* !CONFIG_FILE_LOCKING */ -#define fcntl_getlk(a, b) ({ -EINVAL; }) -#define fcntl_setlk(a, b, c, d) ({ -EACCES; }) +static inline int fcntl_getlk(struct file *file, struct flock __user *user) +{ + return -EINVAL; +} + +static inline int fcntl_setlk(unsigned int fd, struct file *file, + unsigned int cmd, struct flock __user *user) +{ + return -EACCES; +} + #if BITS_PER_LONG == 32 -#define fcntl_getlk64(a, b) ({ -EINVAL; }) -#define fcntl_setlk64(a, b, c, d) ({ -EACCES; }) +static inline int fcntl_getlk64(struct file *file, struct flock64 __user *user) +{ + return -EINVAL; +} + +static inline int fcntl_setlk64(unsigned int fd, struct file *file, + unsigned int cmd, struct flock64 __user *user) +{ + return -EACCES; +} #endif -#define fcntl_setlease(a, b, c) ({ 0; }) -#define fcntl_getlease(a) ({ 0; }) -#define locks_init_lock(a) ({ }) -#define __locks_copy_lock(a, b) ({ }) -#define locks_copy_lock(a, b) ({ }) -#define locks_remove_posix(a, b) ({ }) -#define locks_remove_flock(a) ({ }) -#define posix_test_lock(a, b) ({ 0; }) -#define posix_lock_file(a, b, c) ({ -ENOLCK; }) -#define posix_lock_file_wait(a, b) ({ -ENOLCK; }) -#define posix_unblock_lock(a, b) (-ENOENT) -#define vfs_test_lock(a, b) ({ 0; }) -#define vfs_lock_file(a, b, c, d) (-ENOLCK) -#define vfs_cancel_lock(a, b) ({ 0; }) -#define flock_lock_file_wait(a, b) ({ -ENOLCK; }) -#define __break_lease(a, b) ({ 0; }) -#define lease_get_mtime(a, b) ({ }) -#define generic_setlease(a, b, c) ({ -EINVAL; }) -#define vfs_setlease(a, b, c) ({ -EINVAL; }) -#define lease_modify(a, b) ({ -EINVAL; }) -#define lock_may_read(a, b, c) ({ 1; }) -#define lock_may_write(a, b, c) ({ 1; }) +static inline int fcntl_setlease(unsigned int fd, struct file *filp, long arg) +{ + return 0; +} + +static inline int fcntl_getlease(struct file *filp) +{ + return 0; +} + +static inline void locks_init_lock(struct file_lock *fl) +{ + return; +} + +static inline void __locks_copy_lock(struct file_lock *new, struct file_lock *fl) +{ + return; +} + +static inline void locks_copy_lock(struct file_lock *new, struct file_lock *fl) +{ + return; +} + +static inline void locks_remove_posix(struct file *filp, fl_owner_t owner) +{ + return; +} + +static inline void locks_remove_flock(struct file *filp) +{ + return; +} + +static inline void posix_test_lock(struct file *filp, struct file_lock *fl) +{ + return; +} + +static inline int posix_lock_file(struct file *filp, struct file_lock *fl, + struct file_lock *conflock) +{ + return -ENOLCK; +} + +static inline int posix_lock_file_wait(struct file *filp, struct file_lock *fl) +{ + return -ENOLCK; +} + +static inline int posix_unblock_lock(struct file *filp, + struct file_lock *waiter) +{ + return -ENOENT; +} + +static inline int vfs_test_lock(struct file *filp, struct file_lock *fl) +{ + return 0; +} + +static inline int vfs_lock_file(struct file *filp, unsigned int cmd, + struct file_lock *fl, struct file_lock *conf) +{ + return -ENOLCK; +} + +static inline int vfs_cancel_lock(struct file *filp, struct file_lock *fl) +{ + return 0; +} + +static inline int flock_lock_file_wait(struct file *filp, + struct file_lock *request) +{ + return -ENOLCK; +} + +static inline int __break_lease(struct inode *inode, unsigned int mode) +{ + return 0; +} + +static inline void lease_get_mtime(struct inode *inode, struct timespec *time) +{ + return; +} + +static inline int generic_setlease(struct file *filp, long arg, + struct file_lock **flp) +{ + return -EINVAL; +} + +static inline int vfs_setlease(struct file *filp, long arg, + struct file_lock **lease) +{ + return -EINVAL; +} + +static inline int lease_modify(struct file_lock **before, int arg) +{ + return -EINVAL; +} + +static inline int lock_may_read(struct inode *inode, loff_t start, + unsigned long len) +{ + return 1; +} + +static inline int lock_may_write(struct inode *inode, loff_t start, + unsigned long len) +{ + return 1; +} + #endif /* !CONFIG_FILE_LOCKING */ -- cgit v1.2.3 From af5df56688acfb75c1b15b4e000ec5e82a9cdc29 Mon Sep 17 00:00:00 2001 From: Steven Whitehouse Date: Tue, 20 Jan 2009 10:29:46 +0000 Subject: vfs: Further changes from macro to inline function in fs.h There is a second set of macros for when CONFIG_FILE_LOCKING is not set. This patch updates those to become inline functions as well. Signed-off-by: Steven Whitehouse Signed-off-by: Al Viro --- include/linux/fs.h | 45 ++++++++++++++++++++++++++++++++++++++------- 1 file changed, 38 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index d84020b7e67..5f74d616cd7 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1800,13 +1800,44 @@ static inline int break_lease(struct inode *inode, unsigned int mode) return 0; } #else /* !CONFIG_FILE_LOCKING */ -#define locks_mandatory_locked(a) ({ 0; }) -#define locks_mandatory_area(a, b, c, d, e) ({ 0; }) -#define __mandatory_lock(a) ({ 0; }) -#define mandatory_lock(a) ({ 0; }) -#define locks_verify_locked(a) ({ 0; }) -#define locks_verify_truncate(a, b, c) ({ 0; }) -#define break_lease(a, b) ({ 0; }) +static inline int locks_mandatory_locked(struct inode *inode) +{ + return 0; +} + +static inline int locks_mandatory_area(int rw, struct inode *inode, + struct file *filp, loff_t offset, + size_t count) +{ + return 0; +} + +static inline int __mandatory_lock(struct inode *inode) +{ + return 0; +} + +static inline int mandatory_lock(struct inode *inode) +{ + return 0; +} + +static inline int locks_verify_locked(struct inode *inode) +{ + return 0; +} + +static inline int locks_verify_truncate(struct inode *inode, struct file *filp, + size_t size) +{ + return 0; +} + +static inline int break_lease(struct inode *inode, unsigned int mode) +{ + return 0; +} + #endif /* CONFIG_FILE_LOCKING */ /* fs/open.c */ -- cgit v1.2.3 From e56980d451904b623573ef4966cbab768e433c79 Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Wed, 11 Feb 2009 13:14:54 -0800 Subject: fs: make struct dentry->d_op const This change will allow for tagging many dentry_operations const in the source tree. Signed-off-by: Jan Engelhardt Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Al Viro --- include/linux/dcache.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index c66d22487bf..15156364d19 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -112,7 +112,7 @@ struct dentry { struct list_head d_subdirs; /* our children */ struct list_head d_alias; /* inode alias list */ unsigned long d_time; /* used by d_revalidate */ - struct dentry_operations *d_op; + const struct dentry_operations *d_op; struct super_block *d_sb; /* The root of the dentry tree */ void *d_fsdata; /* fs-specific data */ -- cgit v1.2.3 From f786aa90e026f2174bb0c26d49f338c5c46ede55 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 20 Feb 2009 05:51:22 +0000 Subject: constify dentry_operations: NFS Signed-off-by: Al Viro --- include/linux/nfs_fs.h | 2 +- include/linux/nfs_xdr.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index db867b04ac3..8cc8807f77d 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -415,7 +415,7 @@ extern const struct inode_operations nfs_dir_inode_operations; extern const struct inode_operations nfs3_dir_inode_operations; #endif /* CONFIG_NFS_V3 */ extern const struct file_operations nfs_dir_operations; -extern struct dentry_operations nfs_dentry_operations; +extern const struct dentry_operations nfs_dentry_operations; extern void nfs_force_lookup_revalidate(struct inode *dir); extern int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fh, struct nfs_fattr *fattr); diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 2e5f00066af..43a713fce11 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -785,7 +785,7 @@ struct nfs_access_entry; */ struct nfs_rpc_ops { u32 version; /* Protocol version */ - struct dentry_operations *dentry_ops; + const struct dentry_operations *dentry_ops; const struct inode_operations *dir_inode_ops; const struct inode_operations *file_inode_ops; -- cgit v1.2.3 From e16404ed0f3f330dc3e99b95cef69bb60bcd27f7 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 20 Feb 2009 05:55:13 +0000 Subject: constify dentry_operations: misc filesystems Signed-off-by: Al Viro --- include/linux/ncp_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ncp_fs.h b/include/linux/ncp_fs.h index f69e66d151c..30b06c89394 100644 --- a/include/linux/ncp_fs.h +++ b/include/linux/ncp_fs.h @@ -204,7 +204,7 @@ void ncp_update_inode2(struct inode *, struct ncp_entry_info *); /* linux/fs/ncpfs/dir.c */ extern const struct inode_operations ncp_dir_inode_operations; extern const struct file_operations ncp_dir_operations; -extern struct dentry_operations ncp_root_dentry_operations; +extern const struct dentry_operations ncp_root_dentry_operations; int ncp_conn_logged_in(struct super_block *); int ncp_date_dos2unix(__le16 time, __le16 date); void ncp_date_unix2dos(int unix_date, __le16 * time, __le16 * date); -- cgit v1.2.3 From 585d3bc06f4ca57f975a5a1f698f65a45ea66225 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Wed, 25 Feb 2009 10:44:19 +0100 Subject: fs: move bdev code out of buffer.c Move some block device related code out from buffer.c and put it in block_dev.c. I'm trying to move non-buffer_head code out of buffer.c Signed-off-by: Al Viro --- include/linux/buffer_head.h | 7 ------- include/linux/fs.h | 7 +++++++ 2 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index bd7ac793be1..f19fd9045ea 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -165,15 +165,8 @@ int sync_mapping_buffers(struct address_space *mapping); void unmap_underlying_metadata(struct block_device *bdev, sector_t block); void mark_buffer_async_write(struct buffer_head *bh); -void invalidate_bdev(struct block_device *); -int sync_blockdev(struct block_device *bdev); void __wait_on_buffer(struct buffer_head *); wait_queue_head_t *bh_waitq_head(struct buffer_head *bh); -int fsync_bdev(struct block_device *); -struct super_block *freeze_bdev(struct block_device *); -int thaw_bdev(struct block_device *, struct super_block *); -int fsync_super(struct super_block *); -int fsync_no_super(struct block_device *); struct buffer_head *__find_get_block(struct block_device *bdev, sector_t block, unsigned size); struct buffer_head *__getblk(struct block_device *bdev, sector_t block, diff --git a/include/linux/fs.h b/include/linux/fs.h index 5f74d616cd7..c2c4454a268 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1874,6 +1874,13 @@ extern void bd_set_size(struct block_device *, loff_t size); extern void bd_forget(struct inode *inode); extern void bdput(struct block_device *); extern struct block_device *open_by_devnum(dev_t, fmode_t); +extern void invalidate_bdev(struct block_device *); +extern int sync_blockdev(struct block_device *bdev); +extern struct super_block *freeze_bdev(struct block_device *); +extern int thaw_bdev(struct block_device *bdev, struct super_block *sb); +extern int fsync_bdev(struct block_device *); +extern int fsync_super(struct super_block *); +extern int fsync_no_super(struct block_device *); #else static inline void bd_forget(struct inode *inode) {} #endif -- cgit v1.2.3 From a3ec947c85ec339884b30ef6a08133e9311fdae1 Mon Sep 17 00:00:00 2001 From: Sukadev Bhattiprolu Date: Wed, 4 Mar 2009 12:06:34 -0800 Subject: vfs: simple_set_mnt() should return void simple_set_mnt() is defined as returning 'int' but always returns 0. Callers assume simple_set_mnt() never fails and don't properly cleanup if it were to _ever_ fail. For instance, get_sb_single() and get_sb_nodev() should: up_write(sb->s_unmount); deactivate_super(sb); if simple_set_mnt() fails. Since simple_set_mnt() never fails, would be cleaner if it did not return anything. [akpm@linux-foundation.org: fix build] Signed-off-by: Sukadev Bhattiprolu Acked-by: Serge Hallyn Cc: Al Viro Cc: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Al Viro --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index c2c4454a268..a7d73914a9f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1719,7 +1719,7 @@ struct super_block *sget(struct file_system_type *type, extern int get_sb_pseudo(struct file_system_type *, char *, const struct super_operations *ops, unsigned long, struct vfsmount *mnt); -extern int simple_set_mnt(struct vfsmount *mnt, struct super_block *sb); +extern void simple_set_mnt(struct vfsmount *mnt, struct super_block *sb); int __put_super_and_need_restart(struct super_block *sb); /* Alas, no aliases. Too much hassle with bringing module.h everywhere */ -- cgit v1.2.3 From 03a971a2899886006f19f3495973bbd646d8bdae Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Wed, 3 Dec 2008 18:00:38 +0000 Subject: thermal: support forcing support for passive cooling Due to poor thermal design or Linux driving hardware outside its thermal envelope, some systems will reach critical temperature and shut down under high load. This patch adds support for forcing a polling-based passive trip point if the firmware doesn't provide one. The assumption is made that the processor is the most practical means to reduce the dynamic heat generation, so hitting the passive thermal limit will cause the CPU to be throttled until the temperature stabalises around the defined value. UI is provided via a "passive" sysfs entry in the thermal zone directory. It accepts a decimal value in millidegrees celsius, or "0" to disable the functionality. Default behaviour is for this functionality to be disabled. Signed-off-by: Matthew Garrett Signed-off-by: Len Brown --- include/linux/thermal.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index a81c61521ba..1de8b9eb841 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -113,6 +113,7 @@ struct thermal_zone_device { int polling_delay; int last_temperature; bool passive; + unsigned int forced_passive; struct thermal_zone_device_ops *ops; struct list_head cooling_devices; struct idr idr; -- cgit v1.2.3 From cc0be3227df9146968311308a9d19db1469ce1db Mon Sep 17 00:00:00 2001 From: Dmitri Vorobiev Date: Fri, 27 Mar 2009 15:55:36 -0700 Subject: net: Add missing include into include/linux/netdevice.h The inline function skb_gro_mac_header defined in include/linux/netdevice.h makes use of page_address(). Depending on configuration options, the latter is either defined as a macro or is declared as a function in another header file, namely include/linux/mm.h. However, include/linux/netdevice.h does not include include/linux/mm.h. On MIPS, this has produced the following build error: CC kernel/sysctl_check.o In file included from include/linux/icmpv6.h:173, from include/linux/ipv6.h:208, from include/net/ip_vs.h:26, from kernel/sysctl_check.c:6: include/linux/netdevice.h: In function 'skb_gro_mac_header': include/linux/netdevice.h:1132: error: implicit declaration of function 'page_address' include/linux/netdevice.h:1133: warning: pointer/integer type mismatch in conditional expression make[1]: *** [kernel/sysctl_check.o] Error 1 make: *** [kernel] Error 2 The patch adds the missing include and fixes the build error. Signed-off-by: Dmitri Vorobiev Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index be3ebd7e8ce..1b55952a17f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -32,6 +32,7 @@ #ifdef __KERNEL__ #include #include +#include #include #include #include -- cgit v1.2.3 From 42d671c78f6486c932b68a50f88768c7b4e57ebf Mon Sep 17 00:00:00 2001 From: Greg Banks Date: Fri, 27 Mar 2009 02:32:47 +1100 Subject: Fix a build warning about leaking CONFIG_NFSD to userspace. Fix a build warning about leaking CONFIG_NFSD to userspace. The nfsd_stats data structure does not need to be available to userspace; no kernel interface uses it. So move it inside #ifdef __KERNEL__ and the warning goes away. Signed-off-by: Greg Banks Signed-off-by: J. Bruce Fields --- include/linux/nfsd/stats.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfsd/stats.h b/include/linux/nfsd/stats.h index 7678cfbe996..2693ef647df 100644 --- a/include/linux/nfsd/stats.h +++ b/include/linux/nfsd/stats.h @@ -11,6 +11,11 @@ #include +/* thread usage wraps very million seconds (approx one fortnight) */ +#define NFSD_USAGE_WRAP (HZ*1000000) + +#ifdef __KERNEL__ + struct nfsd_stats { unsigned int rchits; /* repcache hits */ unsigned int rcmisses; /* repcache hits */ @@ -35,10 +40,6 @@ struct nfsd_stats { }; -/* thread usage wraps very million seconds (approx one fortnight) */ -#define NFSD_USAGE_WRAP (HZ*1000000) - -#ifdef __KERNEL__ extern struct nfsd_stats nfsdstats; extern struct svc_stat nfsd_svcstats; -- cgit v1.2.3 From 8fdc621dc743b87879ccf0177969864b09388d9a Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Sat, 14 Mar 2009 09:34:01 +0100 Subject: nl80211: export supported commands This makes nl80211 export the supported commands (command groups) per wiphy so userspace has an idea what it can do -- this will be required reading for userspace when we introduce auth/assoc /or/ connect for older hardware that cannot separate auth and assoc. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/nl80211.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index f33aa08dd9b..3700d927e24 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -349,6 +349,10 @@ enum nl80211_commands { * @NL80211_ATTR_REG_TYPE: indicates the type of the regulatory domain currently * set. This can be one of the nl80211_reg_type (%NL80211_REGDOM_TYPE_*) * + * @NL80211_ATTR_SUPPORTED_COMMANDS: wiphy attribute that specifies + * an array of command numbers (i.e. a mapping index to command number) + * that the driver for the given wiphy supports. + * * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use */ @@ -426,6 +430,8 @@ enum nl80211_attrs { NL80211_ATTR_REG_INITIATOR, NL80211_ATTR_REG_TYPE, + NL80211_ATTR_SUPPORTED_COMMANDS, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, -- cgit v1.2.3 From 3f46b29cd8caa35fcbc46e254a5abeee4e0e9e2f Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Sat, 14 Mar 2009 19:10:51 +0100 Subject: ieee80211: document DS bit usage I keep needing this because I'm too stupid to remember it. Everybody else can probably remember, but who knows :) Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/ieee80211.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index b1bb817d142..382387e75b8 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -18,6 +18,22 @@ #include #include +/* + * DS bit usage + * + * TA = transmitter address + * RA = receiver address + * DA = destination address + * SA = source address + * + * ToDS FromDS A1(RA) A2(TA) A3 A4 Use + * ----------------------------------------------------------------- + * 0 0 DA SA BSSID - IBSS/DLS + * 0 1 DA BSSID SA - AP -> STA + * 1 0 BSSID SA DA - AP <- STA + * 1 1 RA TA DA SA unspecified (WDS) + */ + #define FCS_LEN 4 #define IEEE80211_FCTL_VERS 0x0003 -- cgit v1.2.3 From 6039f6d23fe792d615da5449e9fa1c6b43caacf6 Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Thu, 19 Mar 2009 13:39:21 +0200 Subject: nl80211: Event notifications for MLME events Add new nl80211 event notifications (and a new multicast group, "mlme") for informing user space about received and processed Authentication, (Re)Association Response, Deauthentication, and Disassociation frames in station and IBSS modes (i.e., MLME SAP interface primitives MLME-AUTHENTICATE.confirm, MLME-ASSOCIATE.confirm, MLME-REASSOCIATE.confirm, MLME-DEAUTHENTICATE.indicate, and MLME-DISASSOCIATE.indication). The event data is encapsulated as the 802.11 management frame since we already have the frame in that format and it includes all the needed information. This is the initial step in providing MLME SAP interface for authentication and association with nl80211. In other words, kernel code will act as the MLME and a user space application can control it as the SME. Signed-off-by: Jouni Malinen Signed-off-by: John W. Linville --- include/linux/nl80211.h | 36 +++++++++++++++++++++++++++++++++++- 1 file changed, 35 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 3700d927e24..5ce68ae8314 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -161,6 +161,25 @@ * %NL80211_REG_TYPE_COUNTRY the alpha2 to which we have moved on * to (%NL80211_ATTR_REG_ALPHA2). * + * @NL80211_CMD_AUTHENTICATE: authentication notification (on the "mlme" + * multicast group). This event reports reception of an Authentication + * frame in station and IBSS modes when the local MLME processed the + * frame, i.e., it was for the local STA and was received in correct + * state. This is similar to MLME-AUTHENTICATE.confirm primitive in the + * MLME SAP interface (kernel providing MLME, userspace SME). The + * included NL80211_ATTR_FRAME attribute contains the management frame + * (including both the header and frame body, but not FCS). + * @NL80211_CMD_ASSOCIATE: association notification; like + * NL80211_CMD_AUTHENTICATE but for Association Response and Reassociation + * Response frames (similar to MLME-ASSOCIATE.confirm or + * MLME-REASSOCIATE.confirm primitives). + * @NL80211_CMD_DEAUTHENTICATE: deauthentication notification; like + * NL80211_CMD_AUTHENTICATE but for Deauthentication frames (similar to + * MLME-DEAUTHENTICATE.indication primitive). + * @NL80211_CMD_DISASSOCIATE: disassociation notification; like + * NL80211_CMD_AUTHENTICATE but for Disassociation frames (similar to + * MLME-DISASSOCIATE.indication primitive). + * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use */ @@ -217,6 +236,11 @@ enum nl80211_commands { NL80211_CMD_REG_CHANGE, + NL80211_CMD_AUTHENTICATE, + NL80211_CMD_ASSOCIATE, + NL80211_CMD_DEAUTHENTICATE, + NL80211_CMD_DISASSOCIATE, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ @@ -230,8 +254,11 @@ enum nl80211_commands { */ #define NL80211_CMD_SET_BSS NL80211_CMD_SET_BSS #define NL80211_CMD_SET_MGMT_EXTRA_IE NL80211_CMD_SET_MGMT_EXTRA_IE - #define NL80211_CMD_REG_CHANGE NL80211_CMD_REG_CHANGE +#define NL80211_CMD_AUTHENTICATE NL80211_CMD_AUTHENTICATE +#define NL80211_CMD_ASSOCIATE NL80211_CMD_ASSOCIATE +#define NL80211_CMD_DEAUTHENTICATE NL80211_CMD_DEAUTHENTICATE +#define NL80211_CMD_DISASSOCIATE NL80211_CMD_DISASSOCIATE /** * enum nl80211_attrs - nl80211 netlink attributes @@ -353,6 +380,10 @@ enum nl80211_commands { * an array of command numbers (i.e. a mapping index to command number) * that the driver for the given wiphy supports. * + * @NL80211_ATTR_FRAME: frame data (binary attribute), including frame header + * and body, but not FCS; used, e.g., with NL80211_CMD_AUTHENTICATE and + * NL80211_CMD_ASSOCIATE events + * * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use */ @@ -432,6 +463,8 @@ enum nl80211_attrs { NL80211_ATTR_SUPPORTED_COMMANDS, + NL80211_ATTR_FRAME, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -451,6 +484,7 @@ enum nl80211_attrs { #define NL80211_ATTR_IE NL80211_ATTR_IE #define NL80211_ATTR_REG_INITIATOR NL80211_ATTR_REG_INITIATOR #define NL80211_ATTR_REG_TYPE NL80211_ATTR_REG_TYPE +#define NL80211_ATTR_FRAME NL80211_ATTR_FRAME #define NL80211_MAX_SUPP_RATES 32 #define NL80211_MAX_SUPP_REG_RULES 32 -- cgit v1.2.3 From 636a5d3625993c5ca59abc81794b9ded93cdb740 Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Thu, 19 Mar 2009 13:39:22 +0200 Subject: nl80211: Add MLME primitives to support external SME This patch adds new nl80211 commands to allow user space to request authentication and association (and also deauthentication and disassociation). The commands are structured to allow separate authentication and association steps, i.e., the interface between kernel and user space is similar to the MLME SAP interface in IEEE 802.11 standard and an user space application takes the role of the SME. The patch introduces MLME-AUTHENTICATE.request, MLME-{,RE}ASSOCIATE.request, MLME-DEAUTHENTICATE.request, and MLME-DISASSOCIATE.request primitives. The authentication and association commands request the actual operations in two steps (assuming the driver supports this; if not, separate authentication step is skipped; this could end up being a separate "connect" command). The initial implementation for mac80211 uses the current net/mac80211/mlme.c for actual sending and processing of management frames and the new nl80211 commands will just stop the current state machine from moving automatically from authentication to association. Future cleanup may move more of the MLME operations into cfg80211. The goal of this design is to provide more control of authentication and association process to user space without having to move the full MLME implementation. This should be enough to allow IEEE 802.11r FT protocol and 802.11s SAE authentication to be implemented. Obviously, this will also bring the extra benefit of not having to use WEXT for association requests with mac80211. An example implementation of a user space SME using the new nl80211 commands is available for wpa_supplicant. This patch is enough to get IEEE 802.11r FT protocol working with over-the-air mechanism (over-the-DS will need additional MLME primitives for handling the FT Action frames). Signed-off-by: Jouni Malinen Signed-off-by: John W. Linville --- include/linux/ieee80211.h | 1 + include/linux/nl80211.h | 58 +++++++++++++++++++++++++++++++++++++++-------- 2 files changed, 49 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 382387e75b8..4b501b48ce8 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -867,6 +867,7 @@ struct ieee80211_ht_info { /* Authentication algorithms */ #define WLAN_AUTH_OPEN 0 #define WLAN_AUTH_SHARED_KEY 1 +#define WLAN_AUTH_FT 2 #define WLAN_AUTH_LEAP 128 #define WLAN_AUTH_CHALLENGE_LEN 128 diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 5ce68ae8314..9685eaab40a 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -161,24 +161,37 @@ * %NL80211_REG_TYPE_COUNTRY the alpha2 to which we have moved on * to (%NL80211_ATTR_REG_ALPHA2). * - * @NL80211_CMD_AUTHENTICATE: authentication notification (on the "mlme" - * multicast group). This event reports reception of an Authentication + * @NL80211_CMD_AUTHENTICATE: authentication request and notification. + * This command is used both as a command (request to authenticate) and + * as an event on the "mlme" multicast group indicating completion of the + * authentication process. + * When used as a command, %NL80211_ATTR_IFINDEX is used to identify the + * interface. %NL80211_ATTR_MAC is used to specify PeerSTAAddress (and + * BSSID in case of station mode). %NL80211_ATTR_SSID is used to specify + * the SSID (mainly for association, but is included in authentication + * request, too, to help BSS selection. %NL80211_ATTR_WIPHY_FREQ is used + * to specify the frequence of the channel in MHz. %NL80211_ATTR_AUTH_TYPE + * is used to specify the authentication type. %NL80211_ATTR_IE is used to + * define IEs (VendorSpecificInfo, but also including RSN IE and FT IEs) + * to be added to the frame. + * When used as an event, this reports reception of an Authentication * frame in station and IBSS modes when the local MLME processed the * frame, i.e., it was for the local STA and was received in correct * state. This is similar to MLME-AUTHENTICATE.confirm primitive in the * MLME SAP interface (kernel providing MLME, userspace SME). The * included NL80211_ATTR_FRAME attribute contains the management frame * (including both the header and frame body, but not FCS). - * @NL80211_CMD_ASSOCIATE: association notification; like - * NL80211_CMD_AUTHENTICATE but for Association Response and Reassociation - * Response frames (similar to MLME-ASSOCIATE.confirm or - * MLME-REASSOCIATE.confirm primitives). - * @NL80211_CMD_DEAUTHENTICATE: deauthentication notification; like + * @NL80211_CMD_ASSOCIATE: association request and notification; like + * NL80211_CMD_AUTHENTICATE but for Association and Reassociation + * (similar to MLME-ASSOCIATE.request, MLME-REASSOCIATE.request, + * MLME-ASSOCIATE.confirm or MLME-REASSOCIATE.confirm primitives). + * @NL80211_CMD_DEAUTHENTICATE: deauthentication request and notification; like * NL80211_CMD_AUTHENTICATE but for Deauthentication frames (similar to - * MLME-DEAUTHENTICATE.indication primitive). - * @NL80211_CMD_DISASSOCIATE: disassociation notification; like + * MLME-DEAUTHENTICATION.request and MLME-DEAUTHENTICATE.indication + * primitives). + * @NL80211_CMD_DISASSOCIATE: disassociation request and notification; like * NL80211_CMD_AUTHENTICATE but for Disassociation frames (similar to - * MLME-DISASSOCIATE.indication primitive). + * MLME-DISASSOCIATE.request and MLME-DISASSOCIATE.indication primitives). * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use @@ -383,6 +396,11 @@ enum nl80211_commands { * @NL80211_ATTR_FRAME: frame data (binary attribute), including frame header * and body, but not FCS; used, e.g., with NL80211_CMD_AUTHENTICATE and * NL80211_CMD_ASSOCIATE events + * @NL80211_ATTR_SSID: SSID (binary attribute, 0..32 octets) + * @NL80211_ATTR_AUTH_TYPE: AuthenticationType, see &enum nl80211_auth_type, + * represented as a u32 + * @NL80211_ATTR_REASON_CODE: ReasonCode for %NL80211_CMD_DEAUTHENTICATE and + * %NL80211_CMD_DISASSOCIATE, u16 * * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -464,6 +482,9 @@ enum nl80211_attrs { NL80211_ATTR_SUPPORTED_COMMANDS, NL80211_ATTR_FRAME, + NL80211_ATTR_SSID, + NL80211_ATTR_AUTH_TYPE, + NL80211_ATTR_REASON_CODE, /* add attributes here, update the policy in nl80211.c */ @@ -485,6 +506,9 @@ enum nl80211_attrs { #define NL80211_ATTR_REG_INITIATOR NL80211_ATTR_REG_INITIATOR #define NL80211_ATTR_REG_TYPE NL80211_ATTR_REG_TYPE #define NL80211_ATTR_FRAME NL80211_ATTR_FRAME +#define NL80211_ATTR_SSID NL80211_ATTR_SSID +#define NL80211_ATTR_AUTH_TYPE NL80211_ATTR_AUTH_TYPE +#define NL80211_ATTR_REASON_CODE NL80211_ATTR_REASON_CODE #define NL80211_MAX_SUPP_RATES 32 #define NL80211_MAX_SUPP_REG_RULES 32 @@ -1018,4 +1042,18 @@ enum nl80211_bss { NL80211_BSS_MAX = __NL80211_BSS_AFTER_LAST - 1 }; +/** + * enum nl80211_auth_type - AuthenticationType + * + * @NL80211_AUTHTYPE_OPEN_SYSTEM: Open System authentication + * @NL80211_AUTHTYPE_SHARED_KEY: Shared Key authentication (WEP only) + * @NL80211_AUTHTYPE_FT: Fast BSS Transition (IEEE 802.11r) + * @NL80211_AUTHTYPE_NETWORK_EAP: Network EAP (some Cisco APs and mainly LEAP) + */ +enum nl80211_auth_type { + NL80211_AUTHTYPE_OPEN_SYSTEM, + NL80211_AUTHTYPE_SHARED_KEY, + NL80211_AUTHTYPE_FT, + NL80211_AUTHTYPE_NETWORK_EAP, +}; #endif /* __LINUX_NL80211_H */ -- cgit v1.2.3 From 65fc73ac4a310945dfeceac961726c2765ad2ec0 Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Fri, 20 Mar 2009 21:21:16 +0200 Subject: nl80211: Remove NL80211_CMD_SET_MGMT_EXTRA_IE The functionality that NL80211_CMD_SET_MGMT_EXTRA_IE provided can now be achieved with cleaner design by adding IE(s) into NL80211_CMD_TRIGGER_SCAN, NL80211_CMD_AUTHENTICATE, NL80211_CMD_ASSOCIATE, NL80211_CMD_DEAUTHENTICATE, and NL80211_CMD_DISASSOCIATE. Since this is a very recently added command and there are no known (or known planned) applications using NL80211_CMD_SET_MGMT_EXTRA_IE and taken into account how much extra complexity it adds to the IE processing we have now (and need to add in the future to fix IE order in couple of frames), it looks like the best option is to just remove the implementation of this command for now. The enum values themselves are left to avoid changing the nl80211 command or attribute numbers. Signed-off-by: Jouni Malinen Signed-off-by: John W. Linville --- include/linux/nl80211.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 9685eaab40a..cbe8ce3bf48 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -142,6 +142,12 @@ * %NL80211_ATTR_IE. If the command succeeds, the requested data will be * added to all specified management frames generated by * kernel/firmware/driver. + * Note: This command has been removed and it is only reserved at this + * point to avoid re-using existing command number. The functionality this + * command was planned for has been provided with cleaner design with the + * option to specify additional IEs in NL80211_CMD_TRIGGER_SCAN, + * NL80211_CMD_AUTHENTICATE, NL80211_CMD_ASSOCIATE, + * NL80211_CMD_DEAUTHENTICATE, and NL80211_CMD_DISASSOCIATE. * * @NL80211_CMD_GET_SCAN: get scan results * @NL80211_CMD_TRIGGER_SCAN: trigger a new scan with the given parameters @@ -238,7 +244,7 @@ enum nl80211_commands { NL80211_CMD_GET_MESH_PARAMS, NL80211_CMD_SET_MESH_PARAMS, - NL80211_CMD_SET_MGMT_EXTRA_IE, + NL80211_CMD_SET_MGMT_EXTRA_IE /* reserved; not used */, NL80211_CMD_GET_REG, -- cgit v1.2.3 From af83debf5bb44257082d4489ac86123a0cadf6d3 Mon Sep 17 00:00:00 2001 From: Tulio Magno Quites Machado Filho Date: Sun, 22 Mar 2009 01:41:13 +0100 Subject: ath5k: Support LED's on Acer Extensa 5620z Add vendor ID for Quanta Microsystems and update the led table with the reported device. Reported-by: Scott Barnes Signed-off-by: Tulio Magno Quites Machado Filho Signed-off-by: John W. Linville --- include/linux/pci_ids.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 097f410edef..05dfa7c4fb6 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2271,6 +2271,8 @@ #define PCI_DEVICE_ID_KORENIX_JETCARDF0 0x1600 #define PCI_DEVICE_ID_KORENIX_JETCARDF1 0x16ff +#define PCI_VENDOR_ID_QMI 0x1a32 + #define PCI_VENDOR_ID_TEKRAM 0x1de1 #define PCI_DEVICE_ID_TEKRAM_DC290 0xdc29 -- cgit v1.2.3 From 512a004382f2c60d5c4f855476ba965adc00250c Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 27 Mar 2009 22:14:27 -0400 Subject: ext3: Use WRITE_SYNC for commits which are caused by fsync() If a commit is triggered by fsync(), set a flag indicating the journal blocks associated with the transaction should be flushed out using WRITE_SYNC. Signed-off-by: "Theodore Ts'o" Acked-by: Jan Kara --- include/linux/jbd.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/jbd.h b/include/linux/jbd.h index 64246dce566..2c6943152c2 100644 --- a/include/linux/jbd.h +++ b/include/linux/jbd.h @@ -552,6 +552,11 @@ struct transaction_s */ int t_handle_count; + /* + * This transaction is being forced and some process is + * waiting for it to finish. + */ + int t_synchronous_commit:1; }; /** -- cgit v1.2.3 From 7faa144a518c456e2057918f030f50100144ccc6 Mon Sep 17 00:00:00 2001 From: Alexey Starikovskiy Date: Fri, 27 Mar 2009 22:23:52 -0400 Subject: ACPI: battery: add power_{now,avg} properties to power_class ACPI has smart batteries, which work in units of energy and measure rate of (dis)charge as power, thus it is not appropriate to export it as a current_now. Current_now will still be exported to allow for userland applications to match. Signed-off-by: Alexey Starikovskiy Signed-off-by: Len Brown --- include/linux/power_supply.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index 8ff25e0e7f7..594c494ac3f 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -73,6 +73,8 @@ enum power_supply_property { POWER_SUPPLY_PROP_VOLTAGE_AVG, POWER_SUPPLY_PROP_CURRENT_NOW, POWER_SUPPLY_PROP_CURRENT_AVG, + POWER_SUPPLY_PROP_POWER_NOW, + POWER_SUPPLY_PROP_POWER_AVG, POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN, POWER_SUPPLY_PROP_CHARGE_EMPTY_DESIGN, POWER_SUPPLY_PROP_CHARGE_FULL, -- cgit v1.2.3 From 8651d5c0b1f874c5b8307ae2b858bc40f9f02482 Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Fri, 27 Mar 2009 17:10:48 -0400 Subject: lsm: Remove the socket_post_accept() hook The socket_post_accept() hook is not currently used by any in-tree modules and its existence continues to cause problems by confusing people about what can be safely accomplished using this hook. If a legitimate need for this hook arises in the future it can always be reintroduced. Signed-off-by: Paul Moore Signed-off-by: James Morris --- include/linux/security.h | 13 ------------- 1 file changed, 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index 1f2ab6353c0..54ed15799a8 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -880,11 +880,6 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) * @sock contains the listening socket structure. * @newsock contains the newly created server socket for connection. * Return 0 if permission is granted. - * @socket_post_accept: - * This hook allows a security module to copy security - * information into the newly created socket's inode. - * @sock contains the listening socket structure. - * @newsock contains the newly created server socket for connection. * @socket_sendmsg: * Check permission before transmitting a message to another socket. * @sock contains the socket structure. @@ -1554,8 +1549,6 @@ struct security_operations { struct sockaddr *address, int addrlen); int (*socket_listen) (struct socket *sock, int backlog); int (*socket_accept) (struct socket *sock, struct socket *newsock); - void (*socket_post_accept) (struct socket *sock, - struct socket *newsock); int (*socket_sendmsg) (struct socket *sock, struct msghdr *msg, int size); int (*socket_recvmsg) (struct socket *sock, @@ -2537,7 +2530,6 @@ int security_socket_bind(struct socket *sock, struct sockaddr *address, int addr int security_socket_connect(struct socket *sock, struct sockaddr *address, int addrlen); int security_socket_listen(struct socket *sock, int backlog); int security_socket_accept(struct socket *sock, struct socket *newsock); -void security_socket_post_accept(struct socket *sock, struct socket *newsock); int security_socket_sendmsg(struct socket *sock, struct msghdr *msg, int size); int security_socket_recvmsg(struct socket *sock, struct msghdr *msg, int size, int flags); @@ -2616,11 +2608,6 @@ static inline int security_socket_accept(struct socket *sock, return 0; } -static inline void security_socket_post_accept(struct socket *sock, - struct socket *newsock) -{ -} - static inline int security_socket_sendmsg(struct socket *sock, struct msghdr *msg, int size) { -- cgit v1.2.3 From efb3288b423d7e3533a68dccecaa05a56a281a4e Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 18 Mar 2009 20:45:43 -0400 Subject: SUNRPC: Clean up static inline functions in svc_xprt.h Clean up: Enable the use of const arguments in higher level svc_ APIs by adding const to the arguments of the helper functions in svc_xprt.h Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/svc_xprt.h | 46 +++++++++++++++++++++++------------------ 1 file changed, 26 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index 0127daca435..959b931b605 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -88,29 +88,32 @@ static inline void svc_xprt_get(struct svc_xprt *xprt) kref_get(&xprt->xpt_ref); } static inline void svc_xprt_set_local(struct svc_xprt *xprt, - struct sockaddr *sa, int salen) + const struct sockaddr *sa, + const size_t salen) { memcpy(&xprt->xpt_local, sa, salen); xprt->xpt_locallen = salen; } static inline void svc_xprt_set_remote(struct svc_xprt *xprt, - struct sockaddr *sa, int salen) + const struct sockaddr *sa, + const size_t salen) { memcpy(&xprt->xpt_remote, sa, salen); xprt->xpt_remotelen = salen; } -static inline unsigned short svc_addr_port(struct sockaddr *sa) +static inline unsigned short svc_addr_port(const struct sockaddr *sa) { - unsigned short ret = 0; + const struct sockaddr_in *sin = (const struct sockaddr_in *)sa; + const struct sockaddr_in6 *sin6 = (const struct sockaddr_in6 *)sa; + switch (sa->sa_family) { case AF_INET: - ret = ntohs(((struct sockaddr_in *)sa)->sin_port); - break; + return ntohs(sin->sin_port); case AF_INET6: - ret = ntohs(((struct sockaddr_in6 *)sa)->sin6_port); - break; + return ntohs(sin6->sin6_port); } - return ret; + + return 0; } static inline size_t svc_addr_len(struct sockaddr *sa) @@ -124,36 +127,39 @@ static inline size_t svc_addr_len(struct sockaddr *sa) return -EAFNOSUPPORT; } -static inline unsigned short svc_xprt_local_port(struct svc_xprt *xprt) +static inline unsigned short svc_xprt_local_port(const struct svc_xprt *xprt) { - return svc_addr_port((struct sockaddr *)&xprt->xpt_local); + return svc_addr_port((const struct sockaddr *)&xprt->xpt_local); } -static inline unsigned short svc_xprt_remote_port(struct svc_xprt *xprt) +static inline unsigned short svc_xprt_remote_port(const struct svc_xprt *xprt) { - return svc_addr_port((struct sockaddr *)&xprt->xpt_remote); + return svc_addr_port((const struct sockaddr *)&xprt->xpt_remote); } -static inline char *__svc_print_addr(struct sockaddr *addr, - char *buf, size_t len) +static inline char *__svc_print_addr(const struct sockaddr *addr, + char *buf, const size_t len) { + const struct sockaddr_in *sin = (const struct sockaddr_in *)addr; + const struct sockaddr_in6 *sin6 = (const struct sockaddr_in6 *)addr; + switch (addr->sa_family) { case AF_INET: - snprintf(buf, len, "%pI4, port=%u", - &((struct sockaddr_in *)addr)->sin_addr, - ntohs(((struct sockaddr_in *) addr)->sin_port)); + snprintf(buf, len, "%pI4, port=%u", &sin->sin_addr, + ntohs(sin->sin_port)); break; case AF_INET6: snprintf(buf, len, "%pI6, port=%u", - &((struct sockaddr_in6 *)addr)->sin6_addr, - ntohs(((struct sockaddr_in6 *) addr)->sin6_port)); + &sin6->sin6_addr, + ntohs(sin6->sin6_port)); break; default: snprintf(buf, len, "unknown address type: %d", addr->sa_family); break; } + return buf; } #endif /* SUNRPC_SVC_XPRT_H */ -- cgit v1.2.3 From 156e62094a74cf43f02f56ef96b6cda567501357 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 18 Mar 2009 20:45:58 -0400 Subject: SUNRPC: Clean up svc_find_xprt() calling sequence Clean up: add documentating comment and use appropriate data types for svc_find_xprt()'s arguments. This also eliminates a mixed sign comparison: @port was an int, while the return value of svc_xprt_local_port() is an unsigned short. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/svc_xprt.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index 959b931b605..55b68582c5d 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -80,7 +80,8 @@ void svc_close_xprt(struct svc_xprt *xprt); void svc_delete_xprt(struct svc_xprt *xprt); int svc_port_is_privileged(struct sockaddr *sin); int svc_print_xprts(char *buf, int maxlen); -struct svc_xprt *svc_find_xprt(struct svc_serv *, char *, int, int); +struct svc_xprt *svc_find_xprt(struct svc_serv *serv, const char *xcl_name, + const sa_family_t af, const unsigned short port); int svc_xprt_names(struct svc_serv *serv, char *buf, int buflen); static inline void svc_xprt_get(struct svc_xprt *xprt) -- cgit v1.2.3 From 4b62e58cccff9c5e7ffc7023f7ec24c75fbd549b Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 18 Mar 2009 20:46:06 -0400 Subject: SUNRPC: Pass a family argument to svc_register() The sv_family field is going away. Instead of using sv_family, have the svc_register() function take a protocol family argument. Since this argument represents a protocol family, and not an address family, this argument takes an int, as this is what is passed to sock_create_kern(). Also make sure svc_register's helpers are checking for PF_FOO instead of AF_FOO. The value of [AP]F_FOO are equivalent; this is simply a symbolic change to reflect the semantics of the value stored in that variable. sock_create_kern() should return EPFNOSUPPORT if the passed-in protocol family isn't supported, but it uses EAFNOSUPPORT for this case. We will stick with that tradition here, as svc_register() is called by the RPC server in the same path as sock_create_kern(). Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/svc.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 3435d24bfe5..1f18fc728cb 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -396,8 +396,8 @@ struct svc_serv * svc_create_pooled(struct svc_program *, unsigned int, int svc_set_num_threads(struct svc_serv *, struct svc_pool *, int); void svc_destroy(struct svc_serv *); int svc_process(struct svc_rqst *); -int svc_register(const struct svc_serv *, const unsigned short, - const unsigned short); +int svc_register(const struct svc_serv *, const int, + const unsigned short, const unsigned short); void svc_wake_up(struct svc_serv *); void svc_reserve(struct svc_rqst *rqstp, int space); -- cgit v1.2.3 From 9652ada3fb5914a67d8422114e8a76388330fa79 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 18 Mar 2009 20:46:21 -0400 Subject: SUNRPC: Change svc_create_xprt() to take a @family argument The sv_family field is going away. Pass a protocol family argument to svc_create_xprt() instead of extracting the family from the passed-in svc_serv struct. Again, as this is a listener socket and not an address, we make this new argument an "int" protocol family, instead of an "sa_family_t." Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/svc_xprt.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index 55b68582c5d..0d9cb6ef28b 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -71,7 +71,8 @@ int svc_reg_xprt_class(struct svc_xprt_class *); void svc_unreg_xprt_class(struct svc_xprt_class *); void svc_xprt_init(struct svc_xprt_class *, struct svc_xprt *, struct svc_serv *); -int svc_create_xprt(struct svc_serv *, char *, unsigned short, int); +int svc_create_xprt(struct svc_serv *, const char *, const int, + const unsigned short, int); void svc_xprt_enqueue(struct svc_xprt *xprt); void svc_xprt_received(struct svc_xprt *); void svc_xprt_put(struct svc_xprt *xprt); -- cgit v1.2.3 From 49a9072f29a1039f142ec98b44a72d7173651c02 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 18 Mar 2009 20:46:29 -0400 Subject: SUNRPC: Remove @family argument from svc_create() and svc_create_pooled() Since an RPC service listener's protocol family is specified now via svc_create_xprt(), it no longer needs to be passed to svc_create() or svc_create_pooled(). Remove that argument from the synopsis of those functions, and remove the sv_family field from the svc_serv struct. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/svc.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 1f18fc728cb..d3a4c023193 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -69,7 +69,6 @@ struct svc_serv { struct list_head sv_tempsocks; /* all temporary sockets */ int sv_tmpcnt; /* count of temporary sockets */ struct timer_list sv_temptimer; /* timer for aging temporary sockets */ - sa_family_t sv_family; /* listener's address family */ char * sv_name; /* service name */ @@ -385,13 +384,13 @@ struct svc_procedure { /* * Function prototypes. */ -struct svc_serv *svc_create(struct svc_program *, unsigned int, sa_family_t, +struct svc_serv *svc_create(struct svc_program *, unsigned int, void (*shutdown)(struct svc_serv *)); struct svc_rqst *svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool); void svc_exit_thread(struct svc_rqst *); struct svc_serv * svc_create_pooled(struct svc_program *, unsigned int, - sa_family_t, void (*shutdown)(struct svc_serv *), + void (*shutdown)(struct svc_serv *), svc_thread_fn, struct module *); int svc_set_num_threads(struct svc_serv *, struct svc_pool *, int); void svc_destroy(struct svc_serv *); -- cgit v1.2.3 From d2dd14ac1847082d4bb955619e86ed315c0ecd20 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Sat, 28 Mar 2009 21:34:41 +0100 Subject: i2c-nforce2: Add support for MCP67, MCP73, MCP78S and MCP79 The MCP78S and MCP79 appear to be compatible with the previous nForce chips as far as the SMBus controller is concerned. The MCP67 and MCP73 were not tested yet but I'd be very surprised if they weren't compatible too. Signed-off-by: Jean Delvare Cc: Oleg Ryjkov Cc: Malcolm Lalkaka Cc: Zbigniew Luszpinski --- include/linux/pci_ids.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 05dfa7c4fb6..5109fecde28 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1237,6 +1237,7 @@ #define PCI_DEVICE_ID_NVIDIA_NVENET_21 0x0451 #define PCI_DEVICE_ID_NVIDIA_NVENET_22 0x0452 #define PCI_DEVICE_ID_NVIDIA_NVENET_23 0x0453 +#define PCI_DEVICE_ID_NVIDIA_NFORCE_MCP67_SMBUS 0x0542 #define PCI_DEVICE_ID_NVIDIA_NVENET_24 0x054C #define PCI_DEVICE_ID_NVIDIA_NVENET_25 0x054D #define PCI_DEVICE_ID_NVIDIA_NVENET_26 0x054E @@ -1247,11 +1248,14 @@ #define PCI_DEVICE_ID_NVIDIA_NVENET_31 0x07DF #define PCI_DEVICE_ID_NVIDIA_NFORCE_MCP67_IDE 0x0560 #define PCI_DEVICE_ID_NVIDIA_NFORCE_MCP73_IDE 0x056C +#define PCI_DEVICE_ID_NVIDIA_NFORCE_MCP78S_SMBUS 0x0752 #define PCI_DEVICE_ID_NVIDIA_NFORCE_MCP77_IDE 0x0759 #define PCI_DEVICE_ID_NVIDIA_NVENET_32 0x0760 #define PCI_DEVICE_ID_NVIDIA_NVENET_33 0x0761 #define PCI_DEVICE_ID_NVIDIA_NVENET_34 0x0762 #define PCI_DEVICE_ID_NVIDIA_NVENET_35 0x0763 +#define PCI_DEVICE_ID_NVIDIA_NFORCE_MCP73_SMBUS 0x07D8 +#define PCI_DEVICE_ID_NVIDIA_NFORCE_MCP79_SMBUS 0x0AA2 #define PCI_DEVICE_ID_NVIDIA_NVENET_36 0x0AB0 #define PCI_DEVICE_ID_NVIDIA_NVENET_37 0x0AB1 #define PCI_DEVICE_ID_NVIDIA_NVENET_38 0x0AB2 -- cgit v1.2.3 From eff9ec95efaaf6b12d230f0ea7d3c295d3bc9d57 Mon Sep 17 00:00:00 2001 From: Marco Aurelio da Costa Date: Sat, 28 Mar 2009 21:34:44 +0100 Subject: i2c-algo-pca: Add PCA9665 support Add support for the PCA9665 I2C controller. Signed-off-by: Wolfram Sang Signed-off-by: Jean Delvare --- include/linux/i2c-algo-pca.h | 33 +++++++++++++++++++++++++++++++-- 1 file changed, 31 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c-algo-pca.h b/include/linux/i2c-algo-pca.h index adcb3dc7ac2..1364d62e2fb 100644 --- a/include/linux/i2c-algo-pca.h +++ b/include/linux/i2c-algo-pca.h @@ -1,7 +1,14 @@ #ifndef _LINUX_I2C_ALGO_PCA_H #define _LINUX_I2C_ALGO_PCA_H -/* Clock speeds for the bus */ +/* Chips known to the pca algo */ +#define I2C_PCA_CHIP_9564 0x00 +#define I2C_PCA_CHIP_9665 0x01 + +/* Internal period for PCA9665 oscilator */ +#define I2C_PCA_OSC_PER 3 /* e10-8s */ + +/* Clock speeds for the bus for PCA9564*/ #define I2C_PCA_CON_330kHz 0x00 #define I2C_PCA_CON_288kHz 0x01 #define I2C_PCA_CON_217kHz 0x02 @@ -18,6 +25,26 @@ #define I2C_PCA_ADR 0x02 /* OWN ADR Read/Write */ #define I2C_PCA_CON 0x03 /* CONTROL Read/Write */ +/* PCA9665 registers */ +#define I2C_PCA_INDPTR 0x00 /* INDIRECT Pointer Write Only */ +#define I2C_PCA_IND 0x02 /* INDIRECT Read/Write */ + +/* PCA9665 indirect registers */ +#define I2C_PCA_ICOUNT 0x00 /* Byte Count for buffered mode */ +#define I2C_PCA_IADR 0x01 /* OWN ADR */ +#define I2C_PCA_ISCLL 0x02 /* SCL LOW period */ +#define I2C_PCA_ISCLH 0x03 /* SCL HIGH period */ +#define I2C_PCA_ITO 0x04 /* TIMEOUT */ +#define I2C_PCA_IPRESET 0x05 /* Parallel bus reset */ +#define I2C_PCA_IMODE 0x06 /* I2C Bus mode */ + +/* PCA9665 I2C bus mode */ +#define I2C_PCA_MODE_STD 0x00 /* Standard mode */ +#define I2C_PCA_MODE_FAST 0x01 /* Fast mode */ +#define I2C_PCA_MODE_FASTP 0x02 /* Fast Plus mode */ +#define I2C_PCA_MODE_TURBO 0x03 /* Turbo mode */ + + #define I2C_PCA_CON_AA 0x80 /* Assert Acknowledge */ #define I2C_PCA_CON_ENSIO 0x40 /* Enable */ #define I2C_PCA_CON_STA 0x20 /* Start */ @@ -31,7 +58,9 @@ struct i2c_algo_pca_data { int (*read_byte) (void *data, int reg); int (*wait_for_completion) (void *data); void (*reset_chip) (void *data); - /* i2c_clock values are defined in linux/i2c-algo-pca.h */ + /* For PCA9564, use one of the predefined frequencies: + * 330000, 288000, 217000, 146000, 88000, 59000, 44000, 36000 + * For PCA9665, use the frequency you want here. */ unsigned int i2c_clock; }; -- cgit v1.2.3 From 8e99ada8deaa9033600cd2c7d0a9366b0e99ab68 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Sat, 28 Mar 2009 21:34:45 +0100 Subject: i2c-algo-pca: Rework waiting for a free bus Waiting for a free bus now accepts the timeout value in jiffies and does proper checking using time_before. Signed-off-by: Wolfram Sang Signed-off-by: Jean Delvare --- include/linux/i2c-pca-platform.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/i2c-pca-platform.h b/include/linux/i2c-pca-platform.h index 3d191873f2d..aba33759dec 100644 --- a/include/linux/i2c-pca-platform.h +++ b/include/linux/i2c-pca-platform.h @@ -6,7 +6,7 @@ struct i2c_pca9564_pf_platform_data { * not supplied (negative value), but it * cannot exit some error conditions then */ int i2c_clock_speed; /* values are defined in linux/i2c-algo-pca.h */ - int timeout; /* timeout = this value * 10us */ + int timeout; /* timeout in jiffies */ }; #endif /* I2C_PCA9564_PLATFORM_H */ -- cgit v1.2.3 From 506a8b6c27cb08998dc13069fbdf6eb7ec748b99 Mon Sep 17 00:00:00 2001 From: Flavio Leitner Date: Sat, 28 Mar 2009 21:34:46 +0100 Subject: i2c-piix4: Add support for the Broadcom HT1100 chipset Add support for the Broadcom HT1100 LD chipset (SMBus function.) Signed-off-by: Flavio Leitner Signed-off-by: Jean Delvare --- include/linux/pci_ids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 5109fecde28..2c9e8080da5 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1479,6 +1479,7 @@ #define PCI_DEVICE_ID_SERVERWORKS_HT1000IDE 0x0214 #define PCI_DEVICE_ID_SERVERWORKS_CSB6IDE2 0x0217 #define PCI_DEVICE_ID_SERVERWORKS_CSB6LPC 0x0227 +#define PCI_DEVICE_ID_SERVERWORKS_HT1100LD 0x0408 #define PCI_VENDOR_ID_SBE 0x1176 #define PCI_DEVICE_ID_SBE_WANXL100 0x0301 -- cgit v1.2.3 From 795e2fe0a3b69dbc040d7efcf517e0cbad6901d0 Mon Sep 17 00:00:00 2001 From: David Howells Date: Sat, 28 Mar 2009 23:23:01 +0000 Subject: Annotate struct fs_struct's usage count restriction Annotate struct fs_struct's usage count to indicate the restrictions upon it. It may not be incremented, except by clone(CLONE_FS), as this affects the check in check_unsafe_exec() in fs/exec.c. Signed-off-by: David Howells Signed-off-by: Hugh Dickins Cc: stable@kernel.org Signed-off-by: Linus Torvalds --- include/linux/fs_struct.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs_struct.h b/include/linux/fs_struct.h index a97c053d3a9..18b467dbe27 100644 --- a/include/linux/fs_struct.h +++ b/include/linux/fs_struct.h @@ -4,7 +4,10 @@ #include struct fs_struct { - atomic_t count; + atomic_t count; /* This usage count is used by check_unsafe_exec() for + * security checking purposes - therefore it may not be + * incremented, except by clone(CLONE_FS). + */ rwlock_t lock; int umask; struct path root, pwd; -- cgit v1.2.3 From 4b21cd4eedff2123712c2132c8c6264d40332465 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 28 Mar 2009 23:38:40 -0700 Subject: skbuff.h: fix missing kernel-doc Add missing struct field to fix kernel-doc warning: Warning(include/linux/skbuff.h:182): No description found for parameter 'flags' Signed-off-by: Randy Dunlap Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index bb1981fd60f..eb2e837afaf 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -168,6 +168,7 @@ struct skb_shared_hwtstamps { * @software: generate software time stamp * @in_progress: device driver is going to provide * hardware time stamp + * @flags: all shared_tx flags * * These flags are attached to packets as part of the * &skb_shared_info. Use skb_tx() to get a pointer. -- cgit v1.2.3 From e7557af56a576762a655f1aaaded253ad14c5958 Mon Sep 17 00:00:00 2001 From: Harvey Harrison Date: Sat, 28 Mar 2009 15:38:31 +0000 Subject: netpoll: store local and remote ip in net-endian Allows for the removal of byteswapping in some places and the removal of HIPQUAD (replaced by %pI4). Signed-off-by: Harvey Harrison Signed-off-by: David S. Miller --- include/linux/netpoll.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index de99025f2c5..2524267210d 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -18,7 +18,7 @@ struct netpoll { const char *name; void (*rx_hook)(struct netpoll *, int, char *, int); - u32 local_ip, remote_ip; + __be32 local_ip, remote_ip; u16 local_port, remote_port; u8 remote_mac[ETH_ALEN]; }; -- cgit v1.2.3 From 2c60b6885afc56a17b9d55b04c4328123063fc9d Mon Sep 17 00:00:00 2001 From: Harvey Harrison Date: Sat, 28 Mar 2009 15:38:31 +0000 Subject: kernel: remove HIPQUAD() All users have been removed. Signed-off-by: Harvey Harrison Signed-off-by: David S. Miller --- include/linux/kernel.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 914918abfdd..f81d80f47dc 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -379,18 +379,6 @@ static inline char *pack_hex_byte(char *buf, u8 byte) ((unsigned char *)&addr)[3] #define NIPQUAD_FMT "%u.%u.%u.%u" -#if defined(__LITTLE_ENDIAN) -#define HIPQUAD(addr) \ - ((unsigned char *)&addr)[3], \ - ((unsigned char *)&addr)[2], \ - ((unsigned char *)&addr)[1], \ - ((unsigned char *)&addr)[0] -#elif defined(__BIG_ENDIAN) -#define HIPQUAD NIPQUAD -#else -#error "Please fix asm/byteorder.h" -#endif /* __LITTLE_ENDIAN */ - /* * min()/max()/clamp() macros that also do * strict type-checking.. See the -- cgit v1.2.3 From 503e57630309643562c12f09d4c8a96eb629ee33 Mon Sep 17 00:00:00 2001 From: Ralf Baechle Date: Sun, 29 Mar 2009 12:59:50 +0200 Subject: Fix build error in MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit relies on and having been included previous. If not, the errors like below will result. CC arch/mips/mti-malta/malta-int.o In file included from arch/mips/mti-malta/malta-int.c:25: include/linux/irq.h: In function ‘init_alloc_desc_masks’: include/linux/irq.h:444: error: implicit declaration of function ‘cpu_to_node’ include/linux/irq.h:446: error: ‘GFP_ATOMIC’ undeclared (first use in this function) include/linux/irq.h:446: error: (Each undeclared identifier is reported only once include/linux/irq.h:446: error: for each function it appears in.) make[3]: *** [arch/mips/mti-malta/malta-int.o] Error 1 make[2]: *** [arch/mips/mti-malta] Error 2 make[1]: *** [sub-make] Error 2 Fixed by including the two missing headers. Signed-off-by: Ralf Baechle Signed-off-by: Linus Torvalds --- include/linux/irq.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index 873e4ac11b8..9c62fbe2ef3 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -17,9 +17,11 @@ #include #include #include +#include #include #include #include +#include #include #include -- cgit v1.2.3 From e354d571bb481f1d71f2c3004b9ff570b32e83bd Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Sat, 28 Mar 2009 11:30:52 +0300 Subject: nfsd: embed nfsd4_current_state in nfsd4_compoundres Remove the allocation of struct nfsd4_compound_state. Signed-off-by: Andy Adamson Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- include/linux/nfsd/xdr4.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfsd/xdr4.h b/include/linux/nfsd/xdr4.h index 27bd3e38ec5..fd15ddc3359 100644 --- a/include/linux/nfsd/xdr4.h +++ b/include/linux/nfsd/xdr4.h @@ -45,9 +45,9 @@ #define XDR_LEN(n) (((n) + 3) & ~3) struct nfsd4_compound_state { - struct svc_fh current_fh; - struct svc_fh save_fh; - struct nfs4_stateowner *replay_owner; + struct svc_fh current_fh; + struct svc_fh save_fh; + struct nfs4_stateowner *replay_owner; }; struct nfsd4_change_info { @@ -416,7 +416,8 @@ struct nfsd4_compoundres { u32 taglen; char * tag; u32 opcnt; - __be32 * tagp; /* where to encode tag and opcount */ + __be32 * tagp; /* tag, opcount encode location */ + struct nfsd4_compound_state cstate; }; #define NFS4_SVC_XDRSIZE sizeof(struct nfsd4_compoundargs) -- cgit v1.2.3 From af76aba00fdcfb21535c9f9872245d14097a4561 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Mon, 30 Mar 2009 22:05:11 -0600 Subject: cpumask: fix seq_bitmap_*() functions. 1) seq_bitmap_list() should take a const. 2) All the seq_bitmap should use cpumask_bits(). Signed-off-by: Rusty Russell --- include/linux/seq_file.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index f616f31576d..004f3b3342c 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -55,7 +55,7 @@ int seq_bitmap(struct seq_file *m, const unsigned long *bits, unsigned int nr_bits); static inline int seq_cpumask(struct seq_file *m, const struct cpumask *mask) { - return seq_bitmap(m, mask->bits, nr_cpu_ids); + return seq_bitmap(m, cpumask_bits(mask), nr_cpu_ids); } static inline int seq_nodemask(struct seq_file *m, nodemask_t *mask) @@ -63,12 +63,13 @@ static inline int seq_nodemask(struct seq_file *m, nodemask_t *mask) return seq_bitmap(m, mask->bits, MAX_NUMNODES); } -int seq_bitmap_list(struct seq_file *m, unsigned long *bits, +int seq_bitmap_list(struct seq_file *m, const unsigned long *bits, unsigned int nr_bits); -static inline int seq_cpumask_list(struct seq_file *m, cpumask_t *mask) +static inline int seq_cpumask_list(struct seq_file *m, + const struct cpumask *mask) { - return seq_bitmap_list(m, mask->bits, NR_CPUS); + return seq_bitmap_list(m, cpumask_bits(mask), nr_cpu_ids); } static inline int seq_nodemask_list(struct seq_file *m, nodemask_t *mask) -- cgit v1.2.3 From aa85ea5b89c36c51200d795dd788139bd9b8cf50 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Mon, 30 Mar 2009 22:05:15 -0600 Subject: cpumask: use new cpumask_ functions in core code. Impact: cleanup Time to clean up remaining laggards using the old cpu_ functions. Signed-off-by: Rusty Russell Cc: Greg Kroah-Hartman Cc: Ingo Molnar Cc: Trond.Myklebust@netapp.com --- include/linux/cpuset.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 90c6074a36c..2e0d79678de 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -90,12 +90,12 @@ static inline void cpuset_init_smp(void) {} static inline void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask) { - *mask = cpu_possible_map; + cpumask_copy(mask, cpu_possible_mask); } static inline void cpuset_cpus_allowed_locked(struct task_struct *p, struct cpumask *mask) { - *mask = cpu_possible_map; + cpumask_copy(mask, cpu_possible_mask); } static inline nodemask_t cpuset_mems_allowed(struct task_struct *p) -- cgit v1.2.3 From 6f4303fb2ec68055e793b84887a7ae0f9ea7cc2d Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Thu, 29 Jan 2009 00:15:51 +0100 Subject: HID: bring back possibility to specify vid/pid ignore on module load When hid quirks were converted to specialized driver, the HID_QUIRK_IGNORE has been moved completely, as the hid_ignore_list[] has been moved into the generic code. However userspace already got used to the possibility that modprobing usbhid with 'quirks=vid:pid:0x4' makes the device ignored by usbhid driver. So keep this quirk flag in place for backwards compatibility. Signed-off-by: Jiri Kosina --- include/linux/hid.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index fa8ee9cef7b..a46cda48869 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -270,6 +270,7 @@ struct hid_item { #define HID_QUIRK_INVERT 0x00000001 #define HID_QUIRK_NOTOUCH 0x00000002 +#define HID_QUIRK_IGNORE 0x00000004 #define HID_QUIRK_NOGET 0x00000008 #define HID_QUIRK_BADPAD 0x00000020 #define HID_QUIRK_MULTI_INPUT 0x00000040 -- cgit v1.2.3 From afa5eb7c68689ced4284f01c96feed44a2d0a127 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Wed, 18 Mar 2009 09:13:37 +0100 Subject: HID: remove compat stuff This removal was scheduled and there is no problem with later distros to adapt for the new bus, thanks to aliases. module-init-tools map files are deprecated nowadays, so that the patch which introduced hid ones into the m-i-t won't be accepted and hence there is no reason for leaving compat stuff in. Signed-off-by: Jiri Slaby Cc: Jiri Kosina Signed-off-by: Jiri Kosina --- include/linux/hid.h | 16 ---------------- 1 file changed, 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index a46cda48869..a46cbea71d6 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -792,21 +792,5 @@ dbg_hid(const char *fmt, ...) __FILE__ , ## arg) #endif /* HID_FF */ -#ifdef __KERNEL__ -#ifdef CONFIG_HID_COMPAT -#define HID_COMPAT_LOAD_DRIVER(name) \ -/* prototype to avoid sparse warning */ \ -extern void hid_compat_##name(void); \ -void hid_compat_##name(void) { } \ -EXPORT_SYMBOL(hid_compat_##name) -#else -#define HID_COMPAT_LOAD_DRIVER(name) -#endif /* HID_COMPAT */ -#define HID_COMPAT_CALL_DRIVER(name) do { \ - extern void hid_compat_##name(void); \ - hid_compat_##name(); \ -} while (0) -#endif /* __KERNEL__ */ - #endif -- cgit v1.2.3 From 877d03105d04b2c13e241130277fa69c8d2564f0 Mon Sep 17 00:00:00 2001 From: Nick Andrew Date: Mon, 26 Jan 2009 11:06:57 +0100 Subject: trivial: Fix misspelling of firmware Fix misspelling of firmware. Signed-off-by: Nick Andrew Signed-off-by: Jiri Kosina --- include/linux/libata.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 76262d83656..b450a262885 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -379,7 +379,7 @@ enum { ATA_HORKAGE_BRIDGE_OK = (1 << 10), /* no bridge limits */ ATA_HORKAGE_ATAPI_MOD16_DMA = (1 << 11), /* use ATAPI DMA for commands not multiple of 16 bytes */ - ATA_HORKAGE_FIRMWARE_WARN = (1 << 12), /* firwmare update warning */ + ATA_HORKAGE_FIRMWARE_WARN = (1 << 12), /* firmware update warning */ ATA_HORKAGE_1_5_GBPS = (1 << 13), /* force 1.5 Gbps */ /* DMA mask for user DMA control: User visible values; DO NOT -- cgit v1.2.3 From 5243ef8b54a927cae23216253e4e3f03af6f1446 Mon Sep 17 00:00:00 2001 From: Mark Vels Date: Sun, 18 Jan 2009 18:42:45 +0100 Subject: trivial: PWM: fix of #endif comment Signed-off-by: Mark Vels Signed-off-by: Jiri Kosina --- include/linux/pwm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pwm.h b/include/linux/pwm.h index 3945f803d51..7c775751392 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -28,4 +28,4 @@ int pwm_enable(struct pwm_device *pwm); */ void pwm_disable(struct pwm_device *pwm); -#endif /* __ASM_ARCH_PWM_H */ +#endif /* __LINUX_PWM_H */ -- cgit v1.2.3 From 21acb9caa2e30b100e9a1943d995bb99d40f4035 Mon Sep 17 00:00:00 2001 From: Thadeu Lima de Souza Cascardo Date: Wed, 4 Feb 2009 10:12:08 +0100 Subject: trivial: fix where cgroup documentation is not correctly referred to cgroup documentation was moved to Documentation/cgroups/. There are some places that still refer to Documentation/controllers/, Documentation/cgroups.txt and Documentation/cpusets.txt. Fix those. Signed-off-by: Thadeu Lima de Souza Cascardo Reviewed-by: Li Zefan Acked-by: Paul Menage Signed-off-by: Jiri Kosina --- include/linux/cgroup.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 499900d0cee..b837631fe49 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -342,7 +342,10 @@ int cgroup_task_count(const struct cgroup *cgrp); /* Return true if the cgroup is a descendant of the current cgroup */ int cgroup_is_descendant(const struct cgroup *cgrp); -/* Control Group subsystem type. See Documentation/cgroups.txt for details */ +/* + * Control Group subsystem type. + * See Documentation/cgroups/cgroups.txt for details + */ struct cgroup_subsys { struct cgroup_subsys_state *(*create)(struct cgroup_subsys *ss, -- cgit v1.2.3 From 39db4b8dd16b6d3b56fd3155f309e0eec8481c9a Mon Sep 17 00:00:00 2001 From: Tobias Klauser Date: Mon, 9 Feb 2009 23:07:35 +0100 Subject: trivial: wusb: Storage class should be before const qualifier The C99 specification states in section 6.11.5: The placement of a storage-class specifier other than at the beginning of the declaration specifiers in a declaration is an obsolescent feature. Acked-by: David Vrabel Signed-off-by: Tobias Klauser Signed-off-by: Jiri Kosina --- include/linux/usb/wusb.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/wusb.h b/include/linux/usb/wusb.h index 5f401b644ed..429c631d2aa 100644 --- a/include/linux/usb/wusb.h +++ b/include/linux/usb/wusb.h @@ -80,8 +80,7 @@ struct wusb_ckhdid { u8 data[16]; } __attribute__((packed)); -const static -struct wusb_ckhdid wusb_ckhdid_zero = { .data = { 0 } }; +static const struct wusb_ckhdid wusb_ckhdid_zero = { .data = { 0 } }; #define WUSB_CKHDID_STRSIZE (3 * sizeof(struct wusb_ckhdid) + 1) -- cgit v1.2.3 From 0cbfdc8648115b2e8451ae9122311d01d2722005 Mon Sep 17 00:00:00 2001 From: Kazuo Moriwaka Date: Tue, 3 Mar 2009 13:01:23 +0100 Subject: trivial: jbd header comment typo fix for JBD_PARANOID_IOFAIL jbd header comment typo fix. Signed-off-by: Kazuo Moriwaka Signed-off-by: Jiri Kosina --- include/linux/jbd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/jbd.h b/include/linux/jbd.h index 64246dce566..e8ca681d8ac 100644 --- a/include/linux/jbd.h +++ b/include/linux/jbd.h @@ -35,7 +35,7 @@ #define journal_oom_retry 1 /* - * Define JBD_PARANIOD_IOFAIL to cause a kernel BUG() if ext3 finds + * Define JBD_PARANOID_IOFAIL to cause a kernel BUG() if ext3 finds * certain classes of error which can occur due to failed IOs. Under * normal use we want ext3 to continue after such errors, because * hardware _can_ fail, but for debugging purposes when running tests on -- cgit v1.2.3 From 4a6a4499693a419a20559c41e33a7bd70bf20a6f Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Fri, 27 Mar 2009 12:24:31 -0600 Subject: Fix a lockdep warning in fasync_helper() Lockdep gripes if file->f_lock is taken in a no-IRQ situation, since that is not always the case. We don't really want to disable IRQs for every acquisition of f_lock; instead, just move it outside of fasync_lock. Reported-by: Bartlomiej Zolnierkiewicz Reported-by: Larry Finger Reported-by: Wu Fengguang Signed-off-by: Jonathan Corbet --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 7428c6d35e6..2f13c1d7781 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -848,7 +848,7 @@ struct file { #define f_dentry f_path.dentry #define f_vfsmnt f_path.mnt const struct file_operations *f_op; - spinlock_t f_lock; /* f_ep_links, f_flags */ + spinlock_t f_lock; /* f_ep_links, f_flags, no IRQ */ atomic_long_t f_count; unsigned int f_flags; fmode_t f_mode; -- cgit v1.2.3 From 553d0d839b93550780d1b46e6bcd01a3c5c5883e Mon Sep 17 00:00:00 2001 From: Kyle Guinn Date: Fri, 16 Jan 2009 05:28:38 -0300 Subject: V4L/DVB (10365): Add Mars-Semi MR97310A format The MR97310A is a dual-mode webcam controller that provides compressed BGGR Bayer frames. The decompression algorithm for still images is the same as for video, and is currently implemented in libgphoto2. Signed-off-by: Kyle Guinn Signed-off-by: Jean-Francois Moine Signed-off-by: Mauro Carvalho Chehab --- include/linux/videodev2.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h index 5571dbe1c0a..74aea975b30 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -344,6 +344,7 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_SPCA508 v4l2_fourcc('S', '5', '0', '8') /* YUVY per line */ #define V4L2_PIX_FMT_SPCA561 v4l2_fourcc('S', '5', '6', '1') /* compressed GBRG bayer */ #define V4L2_PIX_FMT_PAC207 v4l2_fourcc('P', '2', '0', '7') /* compressed BGGR bayer */ +#define V4L2_PIX_FMT_MR97310A v4l2_fourcc('M', '3', '1', '0') /* compressed BGGR bayer */ #define V4L2_PIX_FMT_PJPG v4l2_fourcc('P', 'J', 'P', 'G') /* Pixart 73xx JPEG */ #define V4L2_PIX_FMT_YVYU v4l2_fourcc('Y', 'V', 'Y', 'U') /* 16 YVU 4:2:2 */ -- cgit v1.2.3 From 2c32cc0c1f54d62c7e9ab81d1c1a3aa5b9efd73d Mon Sep 17 00:00:00 2001 From: Sergio Aguirre Date: Tue, 20 Jan 2009 18:34:43 -0300 Subject: V4L/DVB (10575): V4L2: Add COLORFX user control This is a common feature on many cameras. the options are: Default colors, B & W, Sepia Signed-off-by: Sergio Aguirre Signed-off-by: Mauro Carvalho Chehab --- include/linux/videodev2.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h index 74aea975b30..c64e76a087b 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -880,8 +880,15 @@ enum v4l2_power_line_frequency { #define V4L2_CID_BACKLIGHT_COMPENSATION (V4L2_CID_BASE+28) #define V4L2_CID_CHROMA_AGC (V4L2_CID_BASE+29) #define V4L2_CID_COLOR_KILLER (V4L2_CID_BASE+30) +#define V4L2_CID_COLORFX (V4L2_CID_BASE+31) +enum v4l2_colorfx { + V4L2_COLORFX_NONE = 0, + V4L2_COLORFX_BW = 1, + V4L2_COLORFX_SEPIA = 2, +}; + /* last CID + 1 */ -#define V4L2_CID_LASTP1 (V4L2_CID_BASE+31) +#define V4L2_CID_LASTP1 (V4L2_CID_BASE+32) /* MPEG-class control IDs defined by V4L2 */ #define V4L2_CID_MPEG_BASE (V4L2_CTRL_CLASS_MPEG | 0x900) -- cgit v1.2.3 From 1a367f3bc3a750b839c5711ecd0c9941e2c5aafa Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Fri, 20 Feb 2009 05:55:39 -0300 Subject: V4L/DVB (10686): v4l2: add V4L2_CTRL_FLAG_WRITE_ONLY flag. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/linux/videodev2.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h index c64e76a087b..11b8b3ec77b 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -830,6 +830,7 @@ struct v4l2_querymenu { #define V4L2_CTRL_FLAG_UPDATE 0x0008 #define V4L2_CTRL_FLAG_INACTIVE 0x0010 #define V4L2_CTRL_FLAG_SLIDER 0x0020 +#define V4L2_CTRL_FLAG_WRITE_ONLY 0x0040 /* Query flag, to be ORed with the control ID */ #define V4L2_CTRL_FLAG_NEXT_CTRL 0x80000000 -- cgit v1.2.3 From cc1139c7cdc1455fdf460c33fe63a36524753834 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 26 Feb 2009 23:08:22 -0300 Subject: V4L/DVB(10738a): remove include/linux/video_encoder.h include/linux/video_encoder.h is not used anymore by a v4l driver. Let's remove it and its occurences. Signed-off-by: Mauro Carvalho Chehab --- include/linux/Kbuild | 1 - include/linux/video_encoder.h | 23 ----------------------- 2 files changed, 24 deletions(-) delete mode 100644 include/linux/video_encoder.h (limited to 'include/linux') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index e9581fd9fb6..da7ff0ba386 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -159,7 +159,6 @@ header-y += un.h header-y += utime.h header-y += veth.h header-y += video_decoder.h -header-y += video_encoder.h header-y += videotext.h header-y += x25.h diff --git a/include/linux/video_encoder.h b/include/linux/video_encoder.h deleted file mode 100644 index b7b6423bbb8..00000000000 --- a/include/linux/video_encoder.h +++ /dev/null @@ -1,23 +0,0 @@ -#ifndef _LINUX_VIDEO_ENCODER_H -#define _LINUX_VIDEO_ENCODER_H - -#include - -struct video_encoder_capability { /* this name is too long */ - __u32 flags; -#define VIDEO_ENCODER_PAL 1 /* can encode PAL signal */ -#define VIDEO_ENCODER_NTSC 2 /* can encode NTSC */ -#define VIDEO_ENCODER_SECAM 4 /* can encode SECAM */ -#define VIDEO_ENCODER_CCIR 16 /* CCIR-601 pixel rate (720 pixels per line) instead of square pixel rate */ - int inputs; /* number of inputs */ - int outputs; /* number of outputs */ -}; - -#define ENCODER_GET_CAPABILITIES _IOR('e', 1, struct video_encoder_capability) -#define ENCODER_SET_NORM _IOW('e', 2, int) -#define ENCODER_SET_INPUT _IOW('e', 3, int) /* 0 <= input < #inputs */ -#define ENCODER_SET_OUTPUT _IOW('e', 4, int) /* 0 <= output < #outputs */ -#define ENCODER_ENABLE_OUTPUT _IOW('e', 5, int) /* boolean output enable control */ - - -#endif -- cgit v1.2.3 From 42d12f5aa105af08bc0ed0580e32156a1a325c6b Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 10 Mar 2009 05:02:28 -0300 Subject: V4L/DVB (10870a): remove all references for video_decoder.h changeset 04934e44e3784a1b969582e2d59afcec278470c6 removed the last implementation that were still using the V4L1 obsoleted header. Now, video_decoder.h is not used anymore by any driver. Let's remove it and all references for it in Kernel. Signed-off-by: Mauro Carvalho Chehab --- include/linux/Kbuild | 1 - include/linux/video_decoder.h | 48 ------------------------------------------- 2 files changed, 49 deletions(-) delete mode 100644 include/linux/video_decoder.h (limited to 'include/linux') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index da7ff0ba386..a67b6227d27 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -158,7 +158,6 @@ header-y += ultrasound.h header-y += un.h header-y += utime.h header-y += veth.h -header-y += video_decoder.h header-y += videotext.h header-y += x25.h diff --git a/include/linux/video_decoder.h b/include/linux/video_decoder.h deleted file mode 100644 index e26c0c86a6e..00000000000 --- a/include/linux/video_decoder.h +++ /dev/null @@ -1,48 +0,0 @@ -#ifndef _LINUX_VIDEO_DECODER_H -#define _LINUX_VIDEO_DECODER_H - -#include - -#define HAVE_VIDEO_DECODER 1 - -struct video_decoder_capability { /* this name is too long */ - __u32 flags; -#define VIDEO_DECODER_PAL 1 /* can decode PAL signal */ -#define VIDEO_DECODER_NTSC 2 /* can decode NTSC */ -#define VIDEO_DECODER_SECAM 4 /* can decode SECAM */ -#define VIDEO_DECODER_AUTO 8 /* can autosense norm */ -#define VIDEO_DECODER_CCIR 16 /* CCIR-601 pixel rate (720 pixels per line) instead of square pixel rate */ - int inputs; /* number of inputs */ - int outputs; /* number of outputs */ -}; - -/* -DECODER_GET_STATUS returns the following flags. The only one you need is -DECODER_STATUS_GOOD, the others are just nice things to know. -*/ -#define DECODER_STATUS_GOOD 1 /* receiving acceptable input */ -#define DECODER_STATUS_COLOR 2 /* receiving color information */ -#define DECODER_STATUS_PAL 4 /* auto detected */ -#define DECODER_STATUS_NTSC 8 /* auto detected */ -#define DECODER_STATUS_SECAM 16 /* auto detected */ - -struct video_decoder_init { - unsigned char len; - const unsigned char *data; -}; - -#define DECODER_GET_CAPABILITIES _IOR('d', 1, struct video_decoder_capability) -#define DECODER_GET_STATUS _IOR('d', 2, int) -#define DECODER_SET_NORM _IOW('d', 3, int) -#define DECODER_SET_INPUT _IOW('d', 4, int) /* 0 <= input < #inputs */ -#define DECODER_SET_OUTPUT _IOW('d', 5, int) /* 0 <= output < #outputs */ -#define DECODER_ENABLE_OUTPUT _IOW('d', 6, int) /* boolean output enable control */ -#define DECODER_SET_PICTURE _IOW('d', 7, struct video_picture) -#define DECODER_SET_GPIO _IOW('d', 8, int) /* switch general purpose pin */ -#define DECODER_INIT _IOW('d', 9, struct video_decoder_init) /* init internal registers at once */ -#define DECODER_SET_VBI_BYPASS _IOW('d', 10, int) /* switch vbi bypass */ - -#define DECODER_DUMP _IO('d', 192) /* debug hook */ - - -#endif -- cgit v1.2.3 From 7e0a16f6118a297dd467c1e5a0908429fcdf56af Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 10 Mar 2009 05:31:34 -0300 Subject: V4L/DVB (10907): avoid loading the entire videodev.h header on V4L2 drivers Signed-off-by: Mauro Carvalho Chehab --- include/linux/videodev.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/videodev.h b/include/linux/videodev.h index 837f392fbe9..b19eab14097 100644 --- a/include/linux/videodev.h +++ b/include/linux/videodev.h @@ -16,6 +16,23 @@ #include #include +#if defined(__MIN_V4L1) && defined (__KERNEL__) + +/* + * Used by those V4L2 core functions that need a minimum V4L1 support, + * in order to allow V4L1 Compatibilty code compilation. + */ + +struct video_mbuf +{ + int size; /* Total memory to map */ + int frames; /* Frames */ + int offsets[VIDEO_MAX_FRAME]; +}; + +#define VIDIOCGMBUF _IOR('v',20, struct video_mbuf) /* Memory map buffer info */ + +#else #if defined(CONFIG_VIDEO_V4L1_COMPAT) || !defined (__KERNEL__) #define VID_TYPE_CAPTURE 1 /* Can capture */ @@ -312,6 +329,7 @@ struct video_code #define VID_PLAY_END_MARK 14 #endif /* CONFIG_VIDEO_V4L1_COMPAT */ +#endif /* __MIN_V4L1 */ #endif /* __LINUX_VIDEODEV_H */ -- cgit v1.2.3 From fbc9fa4e8781170e2fbca2859feda114d4758132 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Fri, 6 Mar 2009 09:55:42 -0300 Subject: V4L/DVB (10910): videodev2.h: remove deprecated VIDIOC_G_CHIP_IDENT_OLD As announced VIDIOC_G_CHIP_IDENT_OLD is now removed for 2.6.30. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/linux/videodev2.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h index 11b8b3ec77b..78ba0755ffb 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -1412,14 +1412,6 @@ struct v4l2_dbg_chip_ident { __u32 revision; /* chip revision, chip specific */ } __attribute__ ((packed)); -/* VIDIOC_G_CHIP_IDENT_OLD: Deprecated, do not use */ -struct v4l2_chip_ident_old { - __u32 match_type; /* Match type */ - __u32 match_chip; /* Match this chip, meaning determined by match_type */ - __u32 ident; /* chip identifier as specified in */ - __u32 revision; /* chip revision, chip specific */ -}; - /* * I O C T L C O D E S F O R V I D E O D E V I C E S * @@ -1497,8 +1489,6 @@ struct v4l2_chip_ident_old { /* Experimental, meant for debugging, testing and internal use. Never use this ioctl in applications! */ #define VIDIOC_DBG_G_CHIP_IDENT _IOWR('V', 81, struct v4l2_dbg_chip_ident) -/* This is deprecated and will go away in 2.6.30 */ -#define VIDIOC_G_CHIP_IDENT_OLD _IOWR('V', 81, struct v4l2_chip_ident_old) #endif #define VIDIOC_S_HW_FREQ_SEEK _IOW('V', 82, struct v4l2_hw_freq_seek) -- cgit v1.2.3 From 6273fda6e32e2cd9a478545d0cbc15ac497b1f4b Mon Sep 17 00:00:00 2001 From: Andy Walls Date: Sat, 14 Mar 2009 17:06:07 -0300 Subject: V4L/DVB (11042): v4l2-api: Add definitions for V4L2_MPEG_STREAM_VBI_FMT_IVTV payloads This addition to the v4l2-api add definitions for the constants and data structures used for sliced VBI data insertion into MPEG streams triggered by V4L2_MPEG_STREAM_VBI_FMT_IVTV. This simply declares what the ivtv and cx18 drivers and MythTV have already been doing and provides a proper data structure definition to user space. Signed-off-by: Andy Walls Signed-off-by: Mauro Carvalho Chehab --- include/linux/ivtv.h | 10 +++++----- include/linux/videodev2.h | 47 +++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 52 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ivtv.h b/include/linux/ivtv.h index f2720280b9e..062d20f7432 100644 --- a/include/linux/ivtv.h +++ b/include/linux/ivtv.h @@ -60,10 +60,10 @@ struct ivtv_dma_frame { #define IVTV_IOC_DMA_FRAME _IOW ('V', BASE_VIDIOC_PRIVATE+0, struct ivtv_dma_frame) -/* These are the VBI types as they appear in the embedded VBI private packets. */ -#define IVTV_SLICED_TYPE_TELETEXT_B (1) -#define IVTV_SLICED_TYPE_CAPTION_525 (4) -#define IVTV_SLICED_TYPE_WSS_625 (5) -#define IVTV_SLICED_TYPE_VPS (7) +/* Deprecated defines: applications should use the defines from videodev2.h */ +#define IVTV_SLICED_TYPE_TELETEXT_B V4L2_MPEG_VBI_IVTV_TELETEXT_B +#define IVTV_SLICED_TYPE_CAPTION_525 V4L2_MPEG_VBI_IVTV_CAPTION_525 +#define IVTV_SLICED_TYPE_WSS_625 V4L2_MPEG_VBI_IVTV_WSS_625 +#define IVTV_SLICED_TYPE_VPS V4L2_MPEG_VBI_IVTV_VPS #endif /* _LINUX_IVTV_H */ diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h index 78ba0755ffb..61f1a4921af 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -1347,6 +1347,53 @@ struct v4l2_sliced_vbi_data { __u8 data[48]; }; +/* + * Sliced VBI data inserted into MPEG Streams + */ + +/* + * V4L2_MPEG_STREAM_VBI_FMT_IVTV: + * + * Structure of payload contained in an MPEG 2 Private Stream 1 PES Packet in an + * MPEG-2 Program Pack that contains V4L2_MPEG_STREAM_VBI_FMT_IVTV Sliced VBI + * data + * + * Note, the MPEG-2 Program Pack and Private Stream 1 PES packet header + * definitions are not included here. See the MPEG-2 specifications for details + * on these headers. + */ + +/* Line type IDs */ +#define V4L2_MPEG_VBI_IVTV_TELETEXT_B (1) +#define V4L2_MPEG_VBI_IVTV_CAPTION_525 (4) +#define V4L2_MPEG_VBI_IVTV_WSS_625 (5) +#define V4L2_MPEG_VBI_IVTV_VPS (7) + +struct v4l2_mpeg_vbi_itv0_line { + __u8 id; /* One of V4L2_MPEG_VBI_IVTV_* above */ + __u8 data[42]; /* Sliced VBI data for the line */ +} __attribute__ ((packed)); + +struct v4l2_mpeg_vbi_itv0 { + __le32 linemask[2]; /* Bitmasks of VBI service lines present */ + struct v4l2_mpeg_vbi_itv0_line line[35]; +} __attribute__ ((packed)); + +struct v4l2_mpeg_vbi_ITV0 { + struct v4l2_mpeg_vbi_itv0_line line[36]; +} __attribute__ ((packed)); + +#define V4L2_MPEG_VBI_IVTV_MAGIC0 "itv0" +#define V4L2_MPEG_VBI_IVTV_MAGIC1 "ITV0" + +struct v4l2_mpeg_vbi_fmt_ivtv { + __u8 magic[4]; + union { + struct v4l2_mpeg_vbi_itv0 itv0; + struct v4l2_mpeg_vbi_ITV0 ITV0; + }; +} __attribute__ ((packed)); + /* * A G G R E G A T E S T R U C T U R E S */ -- cgit v1.2.3 From 968cf78285ef03672ae514e9ad7a60919eb97551 Mon Sep 17 00:00:00 2001 From: Devin Heitmueller Date: Wed, 11 Mar 2009 03:00:38 -0300 Subject: V4L/DVB (11065): au8522: add support for analog side of demodulator Add support for the analog functionality in the au8522 analog/digital demodulator Thanks to Michael Krufky and Steven Toth for providing sample hardware, engineering level support, and testing. Signed-off-by: Devin Heitmueller Signed-off-by: Michael Krufky [mchehab: renamed drivers/media/video/au8522_decoder.c as drivers/media/dvb/frontends/au8522_decoder.c to avoid breaking bisect] Signed-off-by: Mauro Carvalho Chehab --- include/linux/i2c-id.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/i2c-id.h b/include/linux/i2c-id.h index 1ffc23bc5d1..17d9af070f0 100644 --- a/include/linux/i2c-id.h +++ b/include/linux/i2c-id.h @@ -71,6 +71,7 @@ #define I2C_DRIVERID_VP27SMPX 93 /* Panasonic VP27s tuner internal MPX */ #define I2C_DRIVERID_M52790 95 /* Mitsubishi M52790SP/FP AV switch */ #define I2C_DRIVERID_CS5345 96 /* cs5345 audio processor */ +#define I2C_DRIVERID_AU8522 97 /* Auvitek au8522 */ #define I2C_DRIVERID_OV7670 1048 /* Omnivision 7670 camera */ -- cgit v1.2.3 From 9aba42efe85bc7a55e3fed0747ce14abc9ee96e7 Mon Sep 17 00:00:00 2001 From: Janne Grunau Date: Wed, 18 Mar 2009 18:10:04 -0300 Subject: V4L/DVB (11096): V4L2 Driver for the Hauppauge HD PVR usb capture device The device encodes component video up to 1080i to a MPEG-TS stream with H.264 video and stereo AAC audio. Newer firmwares accept also AC3 (up to 5.1) audio over optical SPDIF without reencoding. Firmware upgrade is unimplemeted but rather unimportant since the firmware sits on a flash chip. The I2C adapter to drive the integrated infrared receiver/sender is currently disabled due to a conflict with cx18-based devices. Tested-by: Jarod Wilson Signed-off-by: Janne Grunau Signed-off-by: Mauro Carvalho Chehab --- include/linux/i2c-id.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/i2c-id.h b/include/linux/i2c-id.h index 17d9af070f0..f27604af837 100644 --- a/include/linux/i2c-id.h +++ b/include/linux/i2c-id.h @@ -88,6 +88,7 @@ #define I2C_HW_B_CX2341X 0x010020 /* Conexant CX2341X MPEG encoder cards */ #define I2C_HW_B_CX23885 0x010022 /* conexant 23885 based tv cards (bus1) */ #define I2C_HW_B_AU0828 0x010023 /* auvitek au0828 usb bridge */ +#define I2C_HW_B_HDPVR 0x010025 /* Hauppauge HD PVR */ /* --- SGI adapters */ #define I2C_HW_SGI_VINO 0x160000 -- cgit v1.2.3 From 14a19c0a2254ba58ed7559e072456ab94c9a2d3c Mon Sep 17 00:00:00 2001 From: Theodore Kilgore Date: Wed, 25 Mar 2009 07:13:13 -0300 Subject: V4L/DVB (11213): gspca - sq905c: New subdriver. The code in the new sq905c.c is based upon the structure of the code in gspca/sq905.c, and upon the code in libgphoto2/camlibs/digigr8, which supports the same set of cameras in stillcam mode. I am a co-author of gspca/sq905.c and I am the sole author of libgphoto2/camlibs/digigr8, which is licensed under the LGPL. I hereby give myself permission to use my own code from libgphoto2 in gspca/sq905c.c. Signed-off-by: Theodore Kilgore Signed-off-by: Jean-Francois Moine Signed-off-by: Mauro Carvalho Chehab --- include/linux/videodev2.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h index 61f1a4921af..139d234923c 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -345,6 +345,7 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_SPCA561 v4l2_fourcc('S', '5', '6', '1') /* compressed GBRG bayer */ #define V4L2_PIX_FMT_PAC207 v4l2_fourcc('P', '2', '0', '7') /* compressed BGGR bayer */ #define V4L2_PIX_FMT_MR97310A v4l2_fourcc('M', '3', '1', '0') /* compressed BGGR bayer */ +#define V4L2_PIX_FMT_SQ905C v4l2_fourcc('9', '0', '5', 'C') /* compressed RGGB bayer */ #define V4L2_PIX_FMT_PJPG v4l2_fourcc('P', 'J', 'P', 'G') /* Pixart 73xx JPEG */ #define V4L2_PIX_FMT_YVYU v4l2_fourcc('Y', 'V', 'Y', 'U') /* 16 YVU 4:2:2 */ -- cgit v1.2.3 From 702d21c6f6c790b12c4820cd2f29bc8472aed633 Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Mon, 30 Mar 2009 14:02:16 -0400 Subject: reiserfs: add support for mount count incrementing The following patch adds the fields for tracking mount counts and last fsck timestamps to the superblock. It also increments the mount count on every read-write mount. Reiserfsprogs 3.6.21 added support for these fields. Signed-off-by: Jeff Mahoney Signed-off-by: Linus Torvalds --- include/linux/reiserfs_fs.h | 6 +++++- include/linux/reiserfs_fs_sb.h | 3 +++ 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index bc5114d35e9..ab748a03fe9 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -171,7 +171,11 @@ struct reiserfs_super_block { __le32 s_flags; /* Right now used only by inode-attributes, if enabled */ unsigned char s_uuid[16]; /* filesystem unique identifier */ unsigned char s_label[16]; /* filesystem volume label */ - char s_unused[88]; /* zero filled by mkreiserfs and + __le16 s_mnt_count; /* Count of mounts since last fsck */ + __le16 s_max_mnt_count; /* Maximum mounts before check */ + __le32 s_lastcheck; /* Timestamp of last fsck */ + __le32 s_check_interval; /* Interval between checks */ + char s_unused[76]; /* zero filled by mkreiserfs and * reiserfs_convert_objectid_map_v1() * so any additions must be updated * there as well. */ diff --git a/include/linux/reiserfs_fs_sb.h b/include/linux/reiserfs_fs_sb.h index bda6b562a1e..ccd38f35153 100644 --- a/include/linux/reiserfs_fs_sb.h +++ b/include/linux/reiserfs_fs_sb.h @@ -73,6 +73,9 @@ typedef enum { #define sb_version(sbp) (le16_to_cpu((sbp)->s_v1.s_version)) #define set_sb_version(sbp,v) ((sbp)->s_v1.s_version = cpu_to_le16(v)) +#define sb_mnt_count(sbp) (le16_to_cpu((sbp)->s_mnt_count)) +#define set_sb_mnt_count(sbp, v) ((sbp)->s_mnt_count = cpu_to_le16(v)) + #define sb_reserved_for_journal(sbp) \ (le16_to_cpu((sbp)->s_v1.s_reserved_for_journal)) #define set_sb_reserved_for_journal(sbp,v) \ -- cgit v1.2.3 From 600ed41675d8c384519d8f0b3c76afed39ef2f4b Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Mon, 30 Mar 2009 14:02:17 -0400 Subject: reiserfs: audit transaction ids to always be unsigned ints This patch fixes up the reiserfs code such that transaction ids are always unsigned ints. In places they can currently be signed ints or unsigned longs. The former just causes an annoying clm-2200 warning and may join a transaction when it should wait. The latter is just for correctness since the disk format uses a 32-bit transaction id. There aren't any runtime problems that result from it not wrapping at the correct location since the value is truncated correctly even on big endian systems. The 0 value might make it to disk, but the mount-time checks will bump it to 10 itself. Signed-off-by: Jeff Mahoney Signed-off-by: Linus Torvalds --- include/linux/reiserfs_fs.h | 2 +- include/linux/reiserfs_fs_i.h | 2 +- include/linux/reiserfs_fs_sb.h | 8 ++++---- 3 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index ab748a03fe9..bd52b949f8c 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -1676,7 +1676,7 @@ struct reiserfs_transaction_handle { int t_refcount; int t_blocks_logged; /* number of blocks this writer has logged */ int t_blocks_allocated; /* number of blocks this writer allocated */ - unsigned long t_trans_id; /* sanity check, equals the current trans id */ + unsigned int t_trans_id; /* sanity check, equals the current trans id */ void *t_handle_save; /* save existing current->journal_info */ unsigned displace_new_blocks:1; /* if new block allocation occurres, that block should be displaced from others */ diff --git a/include/linux/reiserfs_fs_i.h b/include/linux/reiserfs_fs_i.h index ce3663fb010..201dd910b04 100644 --- a/include/linux/reiserfs_fs_i.h +++ b/include/linux/reiserfs_fs_i.h @@ -51,7 +51,7 @@ struct reiserfs_inode_info { /* we use these for fsync or O_SYNC to decide which transaction ** needs to be committed in order for this inode to be properly ** flushed */ - unsigned long i_trans_id; + unsigned int i_trans_id; struct reiserfs_journal_list *i_jl; struct mutex i_mmap; #ifdef CONFIG_REISERFS_FS_POSIX_ACL diff --git a/include/linux/reiserfs_fs_sb.h b/include/linux/reiserfs_fs_sb.h index ccd38f35153..12fc2a0d13b 100644 --- a/include/linux/reiserfs_fs_sb.h +++ b/include/linux/reiserfs_fs_sb.h @@ -156,7 +156,7 @@ struct reiserfs_journal_list { atomic_t j_commit_left; atomic_t j_older_commits_done; /* all commits older than this on disk */ struct mutex j_commit_mutex; - unsigned long j_trans_id; + unsigned int j_trans_id; time_t j_timestamp; struct reiserfs_list_bitmap *j_list_bitmap; struct buffer_head *j_commit_bh; /* commit buffer head */ @@ -185,7 +185,7 @@ struct reiserfs_journal { int j_1st_reserved_block; /* first block on s_dev of reserved area journal */ unsigned long j_state; - unsigned long j_trans_id; + unsigned int j_trans_id; unsigned long j_mount_id; unsigned long j_start; /* start of current waiting commit (index into j_ap_blocks) */ unsigned long j_len; /* length of current waiting commit */ @@ -226,10 +226,10 @@ struct reiserfs_journal { int j_num_work_lists; /* number that need attention from kreiserfsd */ /* debugging to make sure things are flushed in order */ - int j_last_flush_id; + unsigned int j_last_flush_id; /* debugging to make sure things are committed in order */ - int j_last_commit_id; + unsigned int j_last_commit_id; struct list_head j_bitmap_nodes; struct list_head j_dirty_buffers; -- cgit v1.2.3 From eba00305591714f1d85ccad1afbf58259c2197b4 Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Mon, 30 Mar 2009 14:02:18 -0400 Subject: reiserfs: use buffer_info for leaf_paste_entries This patch makes leaf_paste_entries more consistent with respect to the other leaf operations. Using buffer_info instead of buffer_head directly allows us to get a superblock pointer for use in error handling. Signed-off-by: Jeff Mahoney Signed-off-by: Linus Torvalds --- include/linux/reiserfs_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index bd52b949f8c..65bb5e3e3ab 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -2026,7 +2026,7 @@ void leaf_paste_in_buffer(struct buffer_info *bi, int pasted_item_num, int zeros_number); void leaf_cut_from_buffer(struct buffer_info *bi, int cut_item_num, int pos_in_item, int cut_size); -void leaf_paste_entries(struct buffer_head *bh, int item_num, int before, +void leaf_paste_entries(struct buffer_info *bi, int item_num, int before, int new_entry_count, struct reiserfs_de_head *new_dehs, const char *records, int paste_size); /* ibalance.c */ -- cgit v1.2.3 From 45b03d5e8e674eb6555b767e1c8eb40b671ff892 Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Mon, 30 Mar 2009 14:02:21 -0400 Subject: reiserfs: rework reiserfs_warning ReiserFS warnings can be somewhat inconsistent. In some cases: * a unique identifier may be associated with it * the function name may be included * the device may be printed separately This patch aims to make warnings more consistent. reiserfs_warning() prints the device name, so printing it a second time is not required. The function name for a warning is always helpful in debugging, so it is now automatically inserted into the output. Hans has stated that every warning should have a unique identifier. Some cases lack them, others really shouldn't have them. reiserfs_warning() now expects an id associated with each message. In the rare case where one isn't needed, "" will suffice. Signed-off-by: Jeff Mahoney Signed-off-by: Linus Torvalds --- include/linux/reiserfs_fs.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index 65bb5e3e3ab..056e2a3b04e 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -79,7 +79,10 @@ struct fid; */ #define REISERFS_DEBUG_CODE 5 /* extra messages to help find/debug errors */ -void reiserfs_warning(struct super_block *s, const char *fmt, ...); +void __reiserfs_warning(struct super_block *s, const char *id, + const char *func, const char *fmt, ...); +#define reiserfs_warning(s, id, fmt, args...) \ + __reiserfs_warning(s, id, __func__, fmt, ##args) /* assertions handling */ /** always check a condition and panic if it's false. */ @@ -558,7 +561,7 @@ static inline int uniqueness2type(__u32 uniqueness) case V1_DIRENTRY_UNIQUENESS: return TYPE_DIRENTRY; default: - reiserfs_warning(NULL, "vs-500: unknown uniqueness %d", + reiserfs_warning(NULL, "vs-500", "unknown uniqueness %d", uniqueness); case V1_ANY_UNIQUENESS: return TYPE_ANY; @@ -578,7 +581,7 @@ static inline __u32 type2uniqueness(int type) case TYPE_DIRENTRY: return V1_DIRENTRY_UNIQUENESS; default: - reiserfs_warning(NULL, "vs-501: unknown type %d", type); + reiserfs_warning(NULL, "vs-501", "unknown type %d", type); case TYPE_ANY: return V1_ANY_UNIQUENESS; } -- cgit v1.2.3 From fd7cb031efb1dd71cb731668e2f597d9e61acdcb Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Mon, 30 Mar 2009 14:02:23 -0400 Subject: reiserfs: eliminate reiserfs_warning from uniqueness functions uniqueness2type and type2uniquness issue a warning when the value is unknown. When called from reiserfs_warning, this causes a re-entrancy problem and deadlocks on the error buffer lock. Signed-off-by: Jeff Mahoney Signed-off-by: Linus Torvalds --- include/linux/reiserfs_fs.h | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index 056e2a3b04e..cf5407ee0f3 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -560,10 +560,8 @@ static inline int uniqueness2type(__u32 uniqueness) return TYPE_DIRECT; case V1_DIRENTRY_UNIQUENESS: return TYPE_DIRENTRY; - default: - reiserfs_warning(NULL, "vs-500", "unknown uniqueness %d", - uniqueness); case V1_ANY_UNIQUENESS: + default: return TYPE_ANY; } } @@ -580,9 +578,8 @@ static inline __u32 type2uniqueness(int type) return V1_DIRECT_UNIQUENESS; case TYPE_DIRENTRY: return V1_DIRENTRY_UNIQUENESS; - default: - reiserfs_warning(NULL, "vs-501", "unknown type %d", type); case TYPE_ANY: + default: return V1_ANY_UNIQUENESS; } } -- cgit v1.2.3 From c3a9c2109f84882b9b3178f6b1838d550d3df0ec Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Mon, 30 Mar 2009 14:02:25 -0400 Subject: reiserfs: rework reiserfs_panic ReiserFS panics can be somewhat inconsistent. In some cases: * a unique identifier may be associated with it * the function name may be included * the device may be printed separately This patch aims to make warnings more consistent. reiserfs_warning() prints the device name, so printing it a second time is not required. The function name for a warning is always helpful in debugging, so it is now automatically inserted into the output. Hans has stated that every warning should have a unique identifier. Some cases lack them, others really shouldn't have them. reiserfs_warning() now expects an id associated with each message. In the rare case where one isn't needed, "" will suffice. Signed-off-by: Jeff Mahoney Signed-off-by: Linus Torvalds --- include/linux/reiserfs_fs.h | 28 ++++++++++++++++++++++------ 1 file changed, 22 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index cf5407ee0f3..04bfd61eeaa 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -86,11 +86,14 @@ void __reiserfs_warning(struct super_block *s, const char *id, /* assertions handling */ /** always check a condition and panic if it's false. */ -#define __RASSERT( cond, scond, format, args... ) \ -if( !( cond ) ) \ - reiserfs_panic( NULL, "reiserfs[%i]: assertion " scond " failed at " \ - __FILE__ ":%i:%s: " format "\n", \ - in_interrupt() ? -1 : task_pid_nr(current), __LINE__ , __func__ , ##args ) +#define __RASSERT(cond, scond, format, args...) \ +do { \ + if (!(cond)) \ + reiserfs_panic(NULL, "assertion failure", "(" #cond ") at " \ + __FILE__ ":%i:%s: " format "\n", \ + in_interrupt() ? -1 : task_pid_nr(current), \ + __LINE__, __func__ , ##args); \ +} while (0) #define RASSERT(cond, format, args...) __RASSERT(cond, #cond, format, ##args) @@ -1448,6 +1451,16 @@ struct buffer_info { int bi_position; }; +static inline struct super_block *sb_from_tb(struct tree_balance *tb) +{ + return tb ? tb->tb_sb : NULL; +} + +static inline struct super_block *sb_from_bi(struct buffer_info *bi) +{ + return bi ? sb_from_tb(bi->tb) : NULL; +} + /* there are 4 types of items: stat data, directory item, indirect, direct. +-------------------+------------+--------------+------------+ | | k_offset | k_uniqueness | mergeable? | @@ -1988,8 +2001,11 @@ int fix_nodes(int n_op_mode, struct tree_balance *p_s_tb, void unfix_nodes(struct tree_balance *); /* prints.c */ -void reiserfs_panic(struct super_block *s, const char *fmt, ...) +void __reiserfs_panic(struct super_block *s, const char *id, + const char *function, const char *fmt, ...) __attribute__ ((noreturn)); +#define reiserfs_panic(s, id, fmt, args...) \ + __reiserfs_panic(s, id, __func__, fmt, ##args) void reiserfs_info(struct super_block *s, const char *fmt, ...); void reiserfs_debug(struct super_block *s, int level, const char *fmt, ...); void print_indirect_item(struct buffer_head *bh, int item_num); -- cgit v1.2.3 From 32e8b1062915d00d07d3b88a95174648e369b6a3 Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Mon, 30 Mar 2009 14:02:26 -0400 Subject: reiserfs: rearrange journal abort This patch kills off reiserfs_journal_abort as it is never called, and combines __reiserfs_journal_abort_{soft,hard} into one function called reiserfs_abort_journal, which performs the same work. It is silent as opposed to the old version, since the message was always issued after a regular 'abort' message. Signed-off-by: Jeff Mahoney Signed-off-by: Linus Torvalds --- include/linux/reiserfs_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index 04bfd61eeaa..d097966bbd9 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -1771,7 +1771,7 @@ int journal_begin(struct reiserfs_transaction_handle *, struct super_block *p_s_sb, unsigned long); int journal_join_abort(struct reiserfs_transaction_handle *, struct super_block *p_s_sb, unsigned long); -void reiserfs_journal_abort(struct super_block *sb, int errno); +void reiserfs_abort_journal(struct super_block *sb, int errno); void reiserfs_abort(struct super_block *sb, int errno, const char *fmt, ...); int reiserfs_allocate_list_bitmaps(struct super_block *s, struct reiserfs_list_bitmap *, unsigned int); -- cgit v1.2.3 From 1e5e59d431038c53954fe8f0b38bee0f0ad30349 Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Mon, 30 Mar 2009 14:02:27 -0400 Subject: reiserfs: introduce reiserfs_error() Although reiserfs can currently handle severe errors such as journal failure, it cannot handle less severe errors like metadata i/o failure. The following patch adds a reiserfs_error() function akin to the one in ext3. Subsequent patches will use this new error handler to handle errors more gracefully in general. Signed-off-by: Jeff Mahoney Signed-off-by: Linus Torvalds --- include/linux/reiserfs_fs.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index d097966bbd9..6c4af98b676 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -2006,6 +2006,10 @@ void __reiserfs_panic(struct super_block *s, const char *id, __attribute__ ((noreturn)); #define reiserfs_panic(s, id, fmt, args...) \ __reiserfs_panic(s, id, __func__, fmt, ##args) +void __reiserfs_error(struct super_block *s, const char *id, + const char *function, const char *fmt, ...); +#define reiserfs_error(s, id, fmt, args...) \ + __reiserfs_error(s, id, __func__, fmt, ##args) void reiserfs_info(struct super_block *s, const char *fmt, ...); void reiserfs_debug(struct super_block *s, int level, const char *fmt, ...); void print_indirect_item(struct buffer_head *bh, int item_num); -- cgit v1.2.3 From 6dfede696391133eadd7ce90b61c9573ee6e5a90 Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Mon, 30 Mar 2009 14:02:32 -0400 Subject: reiserfs: remove IS_PRIVATE helpers There are a number of helper functions for marking a reiserfs inode private that were leftover from reiserfs did its own thing wrt to private inodes. S_PRIVATE has been in the kernel for some time, so this patch removes the helpers and uses IS_PRIVATE instead. Signed-off-by: Jeff Mahoney Signed-off-by: Linus Torvalds --- include/linux/reiserfs_xattr.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/reiserfs_xattr.h b/include/linux/reiserfs_xattr.h index af135ae895d..58f32ba7f5a 100644 --- a/include/linux/reiserfs_xattr.h +++ b/include/linux/reiserfs_xattr.h @@ -44,7 +44,6 @@ struct reiserfs_xattr_handler { }; #ifdef CONFIG_REISERFS_FS_XATTR -#define is_reiserfs_priv_object(inode) IS_PRIVATE(inode) #define has_xattr_dir(inode) (REISERFS_I(inode)->i_flags & i_has_xattr_dir) ssize_t reiserfs_getxattr(struct dentry *dentry, const char *name, void *buffer, size_t size); @@ -104,11 +103,6 @@ static inline void reiserfs_read_unlock_xattr_i(struct inode *inode) up_read(&REISERFS_I(inode)->xattr_sem); } -static inline void reiserfs_mark_inode_private(struct inode *inode) -{ - inode->i_flags |= S_PRIVATE; -} - static inline void reiserfs_init_xattr_rwsem(struct inode *inode) { init_rwsem(&REISERFS_I(inode)->xattr_sem); @@ -116,8 +110,6 @@ static inline void reiserfs_init_xattr_rwsem(struct inode *inode) #else -#define is_reiserfs_priv_object(inode) 0 -#define reiserfs_mark_inode_private(inode) do {;} while(0) #define reiserfs_getxattr NULL #define reiserfs_setxattr NULL #define reiserfs_listxattr NULL -- cgit v1.2.3 From a72bdb1cd244725ff47b3a29662e2cb820d8c60f Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Mon, 30 Mar 2009 14:02:33 -0400 Subject: reiserfs: Clean up xattrs when REISERFS_FS_XATTR is unset The current reiserfs xattr implementation will not clean up old xattr files if files are deleted when REISERFS_FS_XATTR is unset. This results in inaccessible lost files, wasting space. This patch compiles in basic xattr knowledge, such as how to delete them and change ownership for quota tracking. If the file system has never used xattrs, then the operation is quite fast: it returns immediately when it sees there is no .reiserfs_priv directory. Signed-off-by: Jeff Mahoney Signed-off-by: Linus Torvalds --- include/linux/reiserfs_fs_sb.h | 2 +- include/linux/reiserfs_xattr.h | 29 ++++++----------------------- 2 files changed, 7 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/reiserfs_fs_sb.h b/include/linux/reiserfs_fs_sb.h index 12fc2a0d13b..cbb8868e844 100644 --- a/include/linux/reiserfs_fs_sb.h +++ b/include/linux/reiserfs_fs_sb.h @@ -402,8 +402,8 @@ struct reiserfs_sb_info { int reserved_blocks; /* amount of blocks reserved for further allocations */ spinlock_t bitmap_lock; /* this lock on now only used to protect reserved_blocks variable */ struct dentry *priv_root; /* root of /.reiserfs_priv */ -#ifdef CONFIG_REISERFS_FS_XATTR struct dentry *xattr_root; /* root of /.reiserfs_priv/.xa */ +#ifdef CONFIG_REISERFS_FS_XATTR struct rw_semaphore xattr_dir_sem; #endif int j_errno; diff --git a/include/linux/reiserfs_xattr.h b/include/linux/reiserfs_xattr.h index 58f32ba7f5a..13cdd5e1cb6 100644 --- a/include/linux/reiserfs_xattr.h +++ b/include/linux/reiserfs_xattr.h @@ -43,6 +43,12 @@ struct reiserfs_xattr_handler { struct list_head handlers; }; +int reiserfs_xattr_register_handlers(void) __init; +void reiserfs_xattr_unregister_handlers(void); +int reiserfs_xattr_init(struct super_block *sb, int mount_flags); +int reiserfs_delete_xattrs(struct inode *inode); +int reiserfs_chown_xattrs(struct inode *inode, struct iattr *attrs); + #ifdef CONFIG_REISERFS_FS_XATTR #define has_xattr_dir(inode) (REISERFS_I(inode)->i_flags & i_has_xattr_dir) ssize_t reiserfs_getxattr(struct dentry *dentry, const char *name, @@ -51,9 +57,6 @@ int reiserfs_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags); ssize_t reiserfs_listxattr(struct dentry *dentry, char *buffer, size_t size); int reiserfs_removexattr(struct dentry *dentry, const char *name); -int reiserfs_delete_xattrs(struct inode *inode); -int reiserfs_chown_xattrs(struct inode *inode, struct iattr *attrs); -int reiserfs_xattr_init(struct super_block *sb, int mount_flags); int reiserfs_permission(struct inode *inode, int mask); int reiserfs_xattr_del(struct inode *, const char *); @@ -64,9 +67,6 @@ extern struct reiserfs_xattr_handler user_handler; extern struct reiserfs_xattr_handler trusted_handler; extern struct reiserfs_xattr_handler security_handler; -int reiserfs_xattr_register_handlers(void) __init; -void reiserfs_xattr_unregister_handlers(void); - static inline void reiserfs_write_lock_xattrs(struct super_block *sb) { down_write(&REISERFS_XATTR_DIR_SEM(sb)); @@ -121,23 +121,6 @@ static inline void reiserfs_init_xattr_rwsem(struct inode *inode) #define reiserfs_permission NULL -#define reiserfs_xattr_register_handlers() 0 -#define reiserfs_xattr_unregister_handlers() - -static inline int reiserfs_delete_xattrs(struct inode *inode) -{ - return 0; -}; -static inline int reiserfs_chown_xattrs(struct inode *inode, - struct iattr *attrs) -{ - return 0; -}; -static inline int reiserfs_xattr_init(struct super_block *sb, int mount_flags) -{ - sb->s_flags = (sb->s_flags & ~MS_POSIXACL); /* to be sure */ - return 0; -}; static inline void reiserfs_init_xattr_rwsem(struct inode *inode) { } -- cgit v1.2.3 From d984561b326cd0fe0d1183d11b9b4fa1d011d21d Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Mon, 30 Mar 2009 14:02:35 -0400 Subject: reiserfs: eliminate per-super xattr lock With the switch to using inode->i_mutex locking during lookups/creation in the xattr root, the per-super xattr lock is no longer needed. This patch removes it. Signed-off-by: Jeff Mahoney Signed-off-by: Linus Torvalds --- include/linux/reiserfs_fs.h | 3 --- include/linux/reiserfs_fs_sb.h | 3 --- include/linux/reiserfs_xattr.h | 28 +++++----------------------- 3 files changed, 5 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index 6c4af98b676..e00d240314c 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -2224,7 +2224,4 @@ int reiserfs_unpack(struct inode *inode, struct file *filp); #define reiserfs_write_lock( sb ) lock_kernel() #define reiserfs_write_unlock( sb ) unlock_kernel() -/* xattr stuff */ -#define REISERFS_XATTR_DIR_SEM(s) (REISERFS_SB(s)->xattr_dir_sem) - #endif /* _LINUX_REISER_FS_H */ diff --git a/include/linux/reiserfs_fs_sb.h b/include/linux/reiserfs_fs_sb.h index cbb8868e844..c8aee41ccc2 100644 --- a/include/linux/reiserfs_fs_sb.h +++ b/include/linux/reiserfs_fs_sb.h @@ -403,9 +403,6 @@ struct reiserfs_sb_info { spinlock_t bitmap_lock; /* this lock on now only used to protect reserved_blocks variable */ struct dentry *priv_root; /* root of /.reiserfs_priv */ struct dentry *xattr_root; /* root of /.reiserfs_priv/.xa */ -#ifdef CONFIG_REISERFS_FS_XATTR - struct rw_semaphore xattr_dir_sem; -#endif int j_errno; #ifdef CONFIG_QUOTA char *s_qf_names[MAXQUOTAS]; diff --git a/include/linux/reiserfs_xattr.h b/include/linux/reiserfs_xattr.h index 13cdd5e1cb6..65c16fa5124 100644 --- a/include/linux/reiserfs_xattr.h +++ b/include/linux/reiserfs_xattr.h @@ -67,45 +67,27 @@ extern struct reiserfs_xattr_handler user_handler; extern struct reiserfs_xattr_handler trusted_handler; extern struct reiserfs_xattr_handler security_handler; -static inline void reiserfs_write_lock_xattrs(struct super_block *sb) -{ - down_write(&REISERFS_XATTR_DIR_SEM(sb)); -} -static inline void reiserfs_write_unlock_xattrs(struct super_block *sb) -{ - up_write(&REISERFS_XATTR_DIR_SEM(sb)); -} -static inline void reiserfs_read_lock_xattrs(struct super_block *sb) -{ - down_read(&REISERFS_XATTR_DIR_SEM(sb)); -} - -static inline void reiserfs_read_unlock_xattrs(struct super_block *sb) -{ - up_read(&REISERFS_XATTR_DIR_SEM(sb)); -} - static inline void reiserfs_write_lock_xattr_i(struct inode *inode) { - down_write(&REISERFS_I(inode)->xattr_sem); + down_write(&REISERFS_I(inode)->i_xattr_sem); } static inline void reiserfs_write_unlock_xattr_i(struct inode *inode) { - up_write(&REISERFS_I(inode)->xattr_sem); + up_write(&REISERFS_I(inode)->i_xattr_sem); } static inline void reiserfs_read_lock_xattr_i(struct inode *inode) { - down_read(&REISERFS_I(inode)->xattr_sem); + down_read(&REISERFS_I(inode)->i_xattr_sem); } static inline void reiserfs_read_unlock_xattr_i(struct inode *inode) { - up_read(&REISERFS_I(inode)->xattr_sem); + up_read(&REISERFS_I(inode)->i_xattr_sem); } static inline void reiserfs_init_xattr_rwsem(struct inode *inode) { - init_rwsem(&REISERFS_I(inode)->xattr_sem); + init_rwsem(&REISERFS_I(inode)->i_xattr_sem); } #else -- cgit v1.2.3 From 8b6dd72a441a683cef7ace93de0a57ced4367f00 Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Mon, 30 Mar 2009 14:02:36 -0400 Subject: reiserfs: make per-inode xattr locking more fine grained The per-inode locking can be made more fine-grained to surround just the interaction with the filesystem itself. This really only applies to protecting reads during a write, since concurrent writes are barred with inode->i_mutex at the vfs level. Signed-off-by: Jeff Mahoney Signed-off-by: Linus Torvalds --- include/linux/reiserfs_fs_i.h | 2 +- include/linux/reiserfs_xattr.h | 22 ---------------------- 2 files changed, 1 insertion(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/reiserfs_fs_i.h b/include/linux/reiserfs_fs_i.h index 201dd910b04..76360b36ac3 100644 --- a/include/linux/reiserfs_fs_i.h +++ b/include/linux/reiserfs_fs_i.h @@ -59,7 +59,7 @@ struct reiserfs_inode_info { struct posix_acl *i_acl_default; #endif #ifdef CONFIG_REISERFS_FS_XATTR - struct rw_semaphore xattr_sem; + struct rw_semaphore i_xattr_sem; #endif struct inode vfs_inode; }; diff --git a/include/linux/reiserfs_xattr.h b/include/linux/reiserfs_xattr.h index 65c16fa5124..3bd154fd56e 100644 --- a/include/linux/reiserfs_xattr.h +++ b/include/linux/reiserfs_xattr.h @@ -67,24 +67,6 @@ extern struct reiserfs_xattr_handler user_handler; extern struct reiserfs_xattr_handler trusted_handler; extern struct reiserfs_xattr_handler security_handler; -static inline void reiserfs_write_lock_xattr_i(struct inode *inode) -{ - down_write(&REISERFS_I(inode)->i_xattr_sem); -} -static inline void reiserfs_write_unlock_xattr_i(struct inode *inode) -{ - up_write(&REISERFS_I(inode)->i_xattr_sem); -} -static inline void reiserfs_read_lock_xattr_i(struct inode *inode) -{ - down_read(&REISERFS_I(inode)->i_xattr_sem); -} - -static inline void reiserfs_read_unlock_xattr_i(struct inode *inode) -{ - up_read(&REISERFS_I(inode)->i_xattr_sem); -} - static inline void reiserfs_init_xattr_rwsem(struct inode *inode) { init_rwsem(&REISERFS_I(inode)->i_xattr_sem); @@ -96,10 +78,6 @@ static inline void reiserfs_init_xattr_rwsem(struct inode *inode) #define reiserfs_setxattr NULL #define reiserfs_listxattr NULL #define reiserfs_removexattr NULL -#define reiserfs_write_lock_xattrs(sb) do {;} while(0) -#define reiserfs_write_unlock_xattrs(sb) do {;} while(0) -#define reiserfs_read_lock_xattrs(sb) -#define reiserfs_read_unlock_xattrs(sb) #define reiserfs_permission NULL -- cgit v1.2.3 From 48b32a3553a54740d236b79a90f20147a25875e3 Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Mon, 30 Mar 2009 14:02:38 -0400 Subject: reiserfs: use generic xattr handlers Christoph Hellwig had asked me quite some time ago to port the reiserfs xattrs to the generic xattr interface. This patch replaces the reiserfs-specific xattr handling code with the generic struct xattr_handler. However, since reiserfs doesn't split the prefix and name when accessing xattrs, it can't leverage generic_{set,get,list,remove}xattr without needlessly reconstructing the name on the back end. Update 7/26/07: Added missing dput() to deletion path. Update 8/30/07: Added missing mark_inode_dirty when i_mode is used to represent an ACL and no previous ACL existed. Signed-off-by: Jeff Mahoney Signed-off-by: Linus Torvalds --- include/linux/reiserfs_acl.h | 16 ++-------------- include/linux/reiserfs_fs_sb.h | 3 +-- include/linux/reiserfs_xattr.h | 25 ++++++------------------- 3 files changed, 9 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/include/linux/reiserfs_acl.h b/include/linux/reiserfs_acl.h index fe00f781a62..d180446470f 100644 --- a/include/linux/reiserfs_acl.h +++ b/include/linux/reiserfs_acl.h @@ -52,10 +52,8 @@ int reiserfs_acl_chmod(struct inode *inode); int reiserfs_inherit_default_acl(struct inode *dir, struct dentry *dentry, struct inode *inode); int reiserfs_cache_default_acl(struct inode *dir); -extern int reiserfs_xattr_posix_acl_init(void) __init; -extern int reiserfs_xattr_posix_acl_exit(void); -extern struct reiserfs_xattr_handler posix_acl_default_handler; -extern struct reiserfs_xattr_handler posix_acl_access_handler; +extern struct xattr_handler reiserfs_posix_acl_default_handler; +extern struct xattr_handler reiserfs_posix_acl_access_handler; static inline void reiserfs_init_acl_access(struct inode *inode) { @@ -75,16 +73,6 @@ static inline struct posix_acl *reiserfs_get_acl(struct inode *inode, int type) return NULL; } -static inline int reiserfs_xattr_posix_acl_init(void) -{ - return 0; -} - -static inline int reiserfs_xattr_posix_acl_exit(void) -{ - return 0; -} - static inline int reiserfs_acl_chmod(struct inode *inode) { return 0; diff --git a/include/linux/reiserfs_fs_sb.h b/include/linux/reiserfs_fs_sb.h index c8aee41ccc2..4686b90886e 100644 --- a/include/linux/reiserfs_fs_sb.h +++ b/include/linux/reiserfs_fs_sb.h @@ -451,7 +451,6 @@ enum reiserfs_mount_options { REISERFS_NO_UNHASHED_RELOCATION, REISERFS_HASHED_RELOCATION, REISERFS_ATTRS, - REISERFS_XATTRS, REISERFS_XATTRS_USER, REISERFS_POSIXACL, REISERFS_BARRIER_NONE, @@ -489,7 +488,7 @@ enum reiserfs_mount_options { #define reiserfs_data_log(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_DATA_LOG)) #define reiserfs_data_ordered(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_DATA_ORDERED)) #define reiserfs_data_writeback(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_DATA_WRITEBACK)) -#define reiserfs_xattrs(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_XATTRS)) +#define reiserfs_xattrs(s) ((s)->s_xattr != NULL) #define reiserfs_xattrs_user(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_XATTRS_USER)) #define reiserfs_posixacl(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_POSIXACL)) #define reiserfs_xattrs_optional(s) (reiserfs_xattrs_user(s) || reiserfs_posixacl(s)) diff --git a/include/linux/reiserfs_xattr.h b/include/linux/reiserfs_xattr.h index 3bd154fd56e..958fcaca0e8 100644 --- a/include/linux/reiserfs_xattr.h +++ b/include/linux/reiserfs_xattr.h @@ -29,20 +29,6 @@ struct iattr; struct super_block; struct nameidata; -struct reiserfs_xattr_handler { - char *prefix; - int (*init) (void); - void (*exit) (void); - int (*get) (struct inode * inode, const char *name, void *buffer, - size_t size); - int (*set) (struct inode * inode, const char *name, const void *buffer, - size_t size, int flags); - int (*del) (struct inode * inode, const char *name); - int (*list) (struct inode * inode, const char *name, int namelen, - char *out); - struct list_head handlers; -}; - int reiserfs_xattr_register_handlers(void) __init; void reiserfs_xattr_unregister_handlers(void); int reiserfs_xattr_init(struct super_block *sb, int mount_flags); @@ -59,13 +45,14 @@ ssize_t reiserfs_listxattr(struct dentry *dentry, char *buffer, size_t size); int reiserfs_removexattr(struct dentry *dentry, const char *name); int reiserfs_permission(struct inode *inode, int mask); -int reiserfs_xattr_del(struct inode *, const char *); -int reiserfs_xattr_get(const struct inode *, const char *, void *, size_t); +int reiserfs_xattr_get(struct inode *, const char *, void *, size_t); +int __reiserfs_xattr_set(struct inode *, const char *, const void *, + size_t, int); int reiserfs_xattr_set(struct inode *, const char *, const void *, size_t, int); -extern struct reiserfs_xattr_handler user_handler; -extern struct reiserfs_xattr_handler trusted_handler; -extern struct reiserfs_xattr_handler security_handler; +extern struct xattr_handler reiserfs_xattr_user_handler; +extern struct xattr_handler reiserfs_xattr_trusted_handler; +extern struct xattr_handler reiserfs_xattr_security_handler; static inline void reiserfs_init_xattr_rwsem(struct inode *inode) { -- cgit v1.2.3 From 0ab2621ebd9a28bf7a524ecd50d492a10579dfcc Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Mon, 30 Mar 2009 14:02:39 -0400 Subject: reiserfs: journaled xattrs Deadlocks are possible in the xattr code between the journal lock and the xattr sems. This patch implements journalling for xattr operations. The benefit is twofold: * It gets rid of the deadlock possibility by always ensuring that xattr write operations are initiated inside a transaction. * It corrects the problem where xattr backing files aren't considered any differently than normal files, despite the fact they are metadata. I discussed the added journal load with Chris Mason, and we decided that since xattrs (versus other journal activity) is fairly rare, the introduction of larger transactions to support journaled xattrs wouldn't be too big a deal. Signed-off-by: Jeff Mahoney Signed-off-by: Linus Torvalds --- include/linux/reiserfs_acl.h | 3 ++- include/linux/reiserfs_fs.h | 4 ++++ include/linux/reiserfs_xattr.h | 40 ++++++++++++++++++++++++++++++++++++++-- 3 files changed, 44 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/reiserfs_acl.h b/include/linux/reiserfs_acl.h index d180446470f..52240e02de0 100644 --- a/include/linux/reiserfs_acl.h +++ b/include/linux/reiserfs_acl.h @@ -49,7 +49,8 @@ static inline int reiserfs_acl_count(size_t size) #ifdef CONFIG_REISERFS_FS_POSIX_ACL struct posix_acl *reiserfs_get_acl(struct inode *inode, int type); int reiserfs_acl_chmod(struct inode *inode); -int reiserfs_inherit_default_acl(struct inode *dir, struct dentry *dentry, +int reiserfs_inherit_default_acl(struct reiserfs_transaction_handle *th, + struct inode *dir, struct dentry *dentry, struct inode *inode); int reiserfs_cache_default_acl(struct inode *dir); extern struct xattr_handler reiserfs_posix_acl_default_handler; diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index e00d240314c..67ad310fa88 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -1615,6 +1615,10 @@ struct reiserfs_journal_header { #define JOURNAL_MAX_COMMIT_AGE 30 #define JOURNAL_MAX_TRANS_AGE 30 #define JOURNAL_PER_BALANCE_CNT (3 * (MAX_HEIGHT-2) + 9) +#define JOURNAL_BLOCKS_PER_OBJECT(sb) (JOURNAL_PER_BALANCE_CNT * 3 + \ + 2 * (REISERFS_QUOTA_INIT_BLOCKS(sb) + \ + REISERFS_QUOTA_TRANS_BLOCKS(sb))) + #ifdef CONFIG_QUOTA /* We need to update data and inode (atime) */ #define REISERFS_QUOTA_TRANS_BLOCKS(s) (REISERFS_SB(s)->s_mount_opt & (1<i_sb->s_blocksize); + ret >>= inode->i_sb->s_blocksize_bits; + } + return ret; +} + +/* We may have to create up to 3 objects: xattr root, xattr dir, xattr file. + * Let's try to be smart about it. + * xattr root: We cache it. If it's not cached, we may need to create it. + * xattr dir: If anything has been loaded for this inode, we can set a flag + * saying so. + * xattr file: Since we don't cache xattrs, we can't tell. We always include + * blocks for it. + * + * However, since root and dir can be created between calls - YOU MUST SAVE + * THIS VALUE. + */ +static inline size_t reiserfs_xattr_jcreate_nblocks(struct inode *inode) +{ + size_t nblocks = JOURNAL_BLOCKS_PER_OBJECT(inode->i_sb); + + if ((REISERFS_I(inode)->i_flags & i_has_xattr_dir) == 0) { + nblocks += JOURNAL_BLOCKS_PER_OBJECT(inode->i_sb); + if (REISERFS_SB(inode->i_sb)->xattr_root == NULL) + nblocks += JOURNAL_BLOCKS_PER_OBJECT(inode->i_sb); + } + + return nblocks; +} + static inline void reiserfs_init_xattr_rwsem(struct inode *inode) { init_rwsem(&REISERFS_I(inode)->i_xattr_sem); -- cgit v1.2.3 From a41f1a4715f26f7bc4d047d0bc7710145c8e69c7 Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Mon, 30 Mar 2009 14:02:40 -0400 Subject: reiserfs: use generic readdir for operations across all xattrs The current reiserfs xattr implementation open codes reiserfs_readdir and frees the path before calling the filldir function. Typically, the filldir function is something that modifies the file system, such as a chown or an inode deletion that also require reading of an inode associated with each direntry. Since the file system is modified, the path retained becomes invalid for the next run. In addition, it runs backwards in attempt to minimize activity. This is clearly suboptimal from a code cleanliness perspective as well as performance-wise. This patch implements a generic reiserfs_for_each_xattr that uses the generic readdir and a specific filldir routine that simply populates an array of dentries and then performs a specific operation on them. When all files have been operated on, it then calls the operation on the directory itself. The result is a noticable code reduction and better performance. Signed-off-by: Jeff Mahoney Signed-off-by: Linus Torvalds --- include/linux/reiserfs_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index 67ad310fa88..c0365e07fce 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -1984,6 +1984,7 @@ extern const struct inode_operations reiserfs_dir_inode_operations; extern const struct inode_operations reiserfs_symlink_inode_operations; extern const struct inode_operations reiserfs_special_inode_operations; extern const struct file_operations reiserfs_dir_operations; +int reiserfs_readdir_dentry(struct dentry *, void *, filldir_t, loff_t *); /* tail_conversion.c */ int direct2indirect(struct reiserfs_transaction_handle *, struct inode *, -- cgit v1.2.3 From 57fe60df62410f949da094d06ced1dda9575b69c Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Mon, 30 Mar 2009 14:02:41 -0400 Subject: reiserfs: add atomic addition of selinux attributes during inode creation Some time ago, some changes were made to make security inode attributes be atomically written during inode creation. ReiserFS fell behind in this area, but with the reworking of the xattr code, it's now fairly easy to add. The following patch adds the ability for security attributes to be added automatically during inode creation. Signed-off-by: Jeff Mahoney Signed-off-by: Linus Torvalds --- include/linux/reiserfs_fs.h | 4 +++- include/linux/reiserfs_xattr.h | 32 ++++++++++++++++++++++++++++++++ 2 files changed, 35 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index c0365e07fce..eb4e912e6bd 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -1915,10 +1915,12 @@ void make_le_item_head(struct item_head *ih, const struct cpu_key *key, loff_t offset, int type, int length, int entry_count); struct inode *reiserfs_iget(struct super_block *s, const struct cpu_key *key); +struct reiserfs_security_handle; int reiserfs_new_inode(struct reiserfs_transaction_handle *th, struct inode *dir, int mode, const char *symname, loff_t i_size, - struct dentry *dentry, struct inode *inode); + struct dentry *dentry, struct inode *inode, + struct reiserfs_security_handle *security); void reiserfs_update_sd_size(struct reiserfs_transaction_handle *th, struct inode *inode, loff_t size); diff --git a/include/linux/reiserfs_xattr.h b/include/linux/reiserfs_xattr.h index 20eca09729a..dcae01e63e4 100644 --- a/include/linux/reiserfs_xattr.h +++ b/include/linux/reiserfs_xattr.h @@ -15,6 +15,12 @@ struct reiserfs_xattr_header { __le32 h_hash; /* hash of the value */ }; +struct reiserfs_security_handle { + char *name; + void *value; + size_t length; +}; + #ifdef __KERNEL__ #include @@ -54,6 +60,14 @@ int reiserfs_xattr_set_handle(struct reiserfs_transaction_handle *, extern struct xattr_handler reiserfs_xattr_user_handler; extern struct xattr_handler reiserfs_xattr_trusted_handler; extern struct xattr_handler reiserfs_xattr_security_handler; +#ifdef CONFIG_REISERFS_FS_SECURITY +int reiserfs_security_init(struct inode *dir, struct inode *inode, + struct reiserfs_security_handle *sec); +int reiserfs_security_write(struct reiserfs_transaction_handle *th, + struct inode *inode, + struct reiserfs_security_handle *sec); +void reiserfs_security_free(struct reiserfs_security_handle *sec); +#endif #define xattr_size(size) ((size) + sizeof(struct reiserfs_xattr_header)) static inline loff_t reiserfs_xattr_nblocks(struct inode *inode, loff_t size) @@ -109,6 +123,24 @@ static inline void reiserfs_init_xattr_rwsem(struct inode *inode) } #endif /* CONFIG_REISERFS_FS_XATTR */ +#ifndef CONFIG_REISERFS_FS_SECURITY +static inline int reiserfs_security_init(struct inode *dir, + struct inode *inode, + struct reiserfs_security_handle *sec) +{ + return 0; +} +static inline int +reiserfs_security_write(struct reiserfs_transaction_handle *th, + struct inode *inode, + struct reiserfs_security_handle *sec) +{ + return 0; +} +static inline void reiserfs_security_free(struct reiserfs_security_handle *sec) +{} +#endif + #endif /* __KERNEL__ */ #endif /* _LINUX_REISERFS_XATTR_H */ -- cgit v1.2.3 From 0222e6571c332563a48d4cf5487b67feabe60b5e Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Mon, 30 Mar 2009 14:02:44 -0400 Subject: reiserfs: strip trailing whitespace This patch strips trailing whitespace from the reiserfs code. Signed-off-by: Jeff Mahoney Signed-off-by: Linus Torvalds --- include/linux/reiserfs_fs_sb.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/reiserfs_fs_sb.h b/include/linux/reiserfs_fs_sb.h index 4686b90886e..5621d87c447 100644 --- a/include/linux/reiserfs_fs_sb.h +++ b/include/linux/reiserfs_fs_sb.h @@ -14,7 +14,7 @@ typedef enum { } reiserfs_super_block_flags; /* struct reiserfs_super_block accessors/mutators - * since this is a disk structure, it will always be in + * since this is a disk structure, it will always be in * little endian format. */ #define sb_block_count(sbp) (le32_to_cpu((sbp)->s_v1.s_block_count)) #define set_sb_block_count(sbp,v) ((sbp)->s_v1.s_block_count = cpu_to_le32(v)) @@ -83,16 +83,16 @@ typedef enum { /* LOGGING -- */ -/* These all interelate for performance. +/* These all interelate for performance. ** -** If the journal block count is smaller than n transactions, you lose speed. +** If the journal block count is smaller than n transactions, you lose speed. ** I don't know what n is yet, I'm guessing 8-16. ** ** typical transaction size depends on the application, how often fsync is -** called, and how many metadata blocks you dirty in a 30 second period. +** called, and how many metadata blocks you dirty in a 30 second period. ** The more small files (<16k) you use, the larger your transactions will ** be. -** +** ** If your journal fills faster than dirty buffers get flushed to disk, it must flush them before allowing the journal ** to wrap, which slows things down. If you need high speed meta data updates, the journal should be big enough ** to prevent wrapping before dirty meta blocks get to disk. @@ -242,7 +242,7 @@ struct reiserfs_journal { struct reiserfs_list_bitmap j_list_bitmap[JOURNAL_NUM_BITMAPS]; /* array of bitmaps to record the deleted blocks */ struct reiserfs_journal_cnode *j_hash_table[JOURNAL_HASH_SIZE]; /* hash table for real buffer heads in current trans */ - struct reiserfs_journal_cnode *j_list_hash_table[JOURNAL_HASH_SIZE]; /* hash table for all the real buffer heads in all + struct reiserfs_journal_cnode *j_list_hash_table[JOURNAL_HASH_SIZE]; /* hash table for all the real buffer heads in all the transactions */ struct list_head j_prealloc_list; /* list of inodes which have preallocated blocks */ int j_persistent_trans; @@ -426,7 +426,7 @@ enum reiserfs_mount_options { partition will be dealt with in a manner of 3.5.x */ -/* -o hash={tea, rupasov, r5, detect} is meant for properly mounting +/* -o hash={tea, rupasov, r5, detect} is meant for properly mounting ** reiserfs disks from 3.5.19 or earlier. 99% of the time, this option ** is not required. If the normal autodection code can't determine which ** hash to use (because both hashes had the same value for a file) -- cgit v1.2.3 From a9dd364358fbdc68faee5d20c2d648c320dc3cf0 Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Mon, 30 Mar 2009 14:02:45 -0400 Subject: reiserfs: rename p_s_sb to sb This patch is a simple s/p_s_sb/sb/g to the reiserfs code. This is the first in a series of patches to rip out some of the awful variable naming in reiserfs. Signed-off-by: Jeff Mahoney Signed-off-by: Linus Torvalds --- include/linux/reiserfs_fs.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index eb4e912e6bd..9bd7800d989 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -1769,12 +1769,12 @@ int journal_end_sync(struct reiserfs_transaction_handle *, struct super_block *, int journal_mark_freed(struct reiserfs_transaction_handle *, struct super_block *, b_blocknr_t blocknr); int journal_transaction_should_end(struct reiserfs_transaction_handle *, int); -int reiserfs_in_journal(struct super_block *p_s_sb, unsigned int bmap_nr, - int bit_nr, int searchall, b_blocknr_t *next); +int reiserfs_in_journal(struct super_block *sb, unsigned int bmap_nr, + int bit_nr, int searchall, b_blocknr_t *next); int journal_begin(struct reiserfs_transaction_handle *, - struct super_block *p_s_sb, unsigned long); + struct super_block *sb, unsigned long); int journal_join_abort(struct reiserfs_transaction_handle *, - struct super_block *p_s_sb, unsigned long); + struct super_block *sb, unsigned long); void reiserfs_abort_journal(struct super_block *sb, int errno); void reiserfs_abort(struct super_block *sb, int errno, const char *fmt, ...); int reiserfs_allocate_list_bitmaps(struct super_block *s, @@ -1830,11 +1830,11 @@ static inline void copy_key(struct reiserfs_key *to, int comp_items(const struct item_head *stored_ih, const struct treepath *p_s_path); const struct reiserfs_key *get_rkey(const struct treepath *p_s_chk_path, - const struct super_block *p_s_sb); + const struct super_block *sb); int search_by_key(struct super_block *, const struct cpu_key *, struct treepath *, int); #define search_item(s,key,path) search_by_key (s, key, path, DISK_LEAF_NODE_LEVEL) -int search_for_position_by_key(struct super_block *p_s_sb, +int search_for_position_by_key(struct super_block *sb, const struct cpu_key *p_s_cpu_key, struct treepath *p_s_search_path); extern void decrement_bcount(struct buffer_head *p_s_bh); @@ -1978,7 +1978,7 @@ int reiserfs_global_version_in_proc(char *buffer, char **start, off_t offset, #define PROC_INFO_MAX( sb, field, value ) VOID_V #define PROC_INFO_INC( sb, field ) VOID_V #define PROC_INFO_ADD( sb, field, val ) VOID_V -#define PROC_INFO_BH_STAT( p_s_sb, p_s_bh, n_node_level ) VOID_V +#define PROC_INFO_BH_STAT(sb, p_s_bh, n_node_level) VOID_V #endif /* dir.c */ -- cgit v1.2.3 From ad31a4fc0386e8590c51ca4b8f1ae1d8b8b2ac5e Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Mon, 30 Mar 2009 14:02:46 -0400 Subject: reiserfs: rename p_s_bh to bh This patch is a simple s/p_s_bh/bh/g to the reiserfs code. This is the second in a series of patches to rip out some of the awful variable naming in reiserfs. Signed-off-by: Jeff Mahoney Signed-off-by: Linus Torvalds --- include/linux/reiserfs_fs.h | 35 ++++++++++++++++++----------------- 1 file changed, 18 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index 9bd7800d989..9cfa518c90b 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -751,25 +751,25 @@ struct block_head { #define DISK_LEAF_NODE_LEVEL 1 /* Leaf node level. */ /* Given the buffer head of a formatted node, resolve to the block head of that node. */ -#define B_BLK_HEAD(p_s_bh) ((struct block_head *)((p_s_bh)->b_data)) +#define B_BLK_HEAD(bh) ((struct block_head *)((bh)->b_data)) /* Number of items that are in buffer. */ -#define B_NR_ITEMS(p_s_bh) (blkh_nr_item(B_BLK_HEAD(p_s_bh))) -#define B_LEVEL(p_s_bh) (blkh_level(B_BLK_HEAD(p_s_bh))) -#define B_FREE_SPACE(p_s_bh) (blkh_free_space(B_BLK_HEAD(p_s_bh))) +#define B_NR_ITEMS(bh) (blkh_nr_item(B_BLK_HEAD(bh))) +#define B_LEVEL(bh) (blkh_level(B_BLK_HEAD(bh))) +#define B_FREE_SPACE(bh) (blkh_free_space(B_BLK_HEAD(bh))) -#define PUT_B_NR_ITEMS(p_s_bh,val) do { set_blkh_nr_item(B_BLK_HEAD(p_s_bh),val); } while (0) -#define PUT_B_LEVEL(p_s_bh,val) do { set_blkh_level(B_BLK_HEAD(p_s_bh),val); } while (0) -#define PUT_B_FREE_SPACE(p_s_bh,val) do { set_blkh_free_space(B_BLK_HEAD(p_s_bh),val); } while (0) +#define PUT_B_NR_ITEMS(bh, val) do { set_blkh_nr_item(B_BLK_HEAD(bh), val); } while (0) +#define PUT_B_LEVEL(bh, val) do { set_blkh_level(B_BLK_HEAD(bh), val); } while (0) +#define PUT_B_FREE_SPACE(bh, val) do { set_blkh_free_space(B_BLK_HEAD(bh), val); } while (0) /* Get right delimiting key. -- little endian */ -#define B_PRIGHT_DELIM_KEY(p_s_bh) (&(blk_right_delim_key(B_BLK_HEAD(p_s_bh)))) +#define B_PRIGHT_DELIM_KEY(bh) (&(blk_right_delim_key(B_BLK_HEAD(bh)))) /* Does the buffer contain a disk leaf. */ -#define B_IS_ITEMS_LEVEL(p_s_bh) (B_LEVEL(p_s_bh) == DISK_LEAF_NODE_LEVEL) +#define B_IS_ITEMS_LEVEL(bh) (B_LEVEL(bh) == DISK_LEAF_NODE_LEVEL) /* Does the buffer contain a disk internal node */ -#define B_IS_KEYS_LEVEL(p_s_bh) (B_LEVEL(p_s_bh) > DISK_LEAF_NODE_LEVEL \ - && B_LEVEL(p_s_bh) <= MAX_HEIGHT) +#define B_IS_KEYS_LEVEL(bh) (B_LEVEL(bh) > DISK_LEAF_NODE_LEVEL \ + && B_LEVEL(bh) <= MAX_HEIGHT) /***************************************************************************/ /* STAT DATA */ @@ -1119,12 +1119,13 @@ struct disk_child { #define put_dc_size(dc_p, val) do { (dc_p)->dc_size = cpu_to_le16(val); } while(0) /* Get disk child by buffer header and position in the tree node. */ -#define B_N_CHILD(p_s_bh,n_pos) ((struct disk_child *)\ -((p_s_bh)->b_data+BLKH_SIZE+B_NR_ITEMS(p_s_bh)*KEY_SIZE+DC_SIZE*(n_pos))) +#define B_N_CHILD(bh, n_pos) ((struct disk_child *)\ +((bh)->b_data + BLKH_SIZE + B_NR_ITEMS(bh) * KEY_SIZE + DC_SIZE * (n_pos))) /* Get disk child number by buffer header and position in the tree node. */ -#define B_N_CHILD_NUM(p_s_bh,n_pos) (dc_block_number(B_N_CHILD(p_s_bh,n_pos))) -#define PUT_B_N_CHILD_NUM(p_s_bh,n_pos, val) (put_dc_block_number(B_N_CHILD(p_s_bh,n_pos), val )) +#define B_N_CHILD_NUM(bh, n_pos) (dc_block_number(B_N_CHILD(bh, n_pos))) +#define PUT_B_N_CHILD_NUM(bh, n_pos, val) \ + (put_dc_block_number(B_N_CHILD(bh, n_pos), val)) /* maximal value of field child_size in structure disk_child */ /* child size is the combined size of all items and their headers */ @@ -1837,7 +1838,7 @@ int search_by_key(struct super_block *, const struct cpu_key *, int search_for_position_by_key(struct super_block *sb, const struct cpu_key *p_s_cpu_key, struct treepath *p_s_search_path); -extern void decrement_bcount(struct buffer_head *p_s_bh); +extern void decrement_bcount(struct buffer_head *bh); void decrement_counters_in_path(struct treepath *p_s_search_path); void pathrelse(struct treepath *p_s_search_path); int reiserfs_check_path(struct treepath *p); @@ -1978,7 +1979,7 @@ int reiserfs_global_version_in_proc(char *buffer, char **start, off_t offset, #define PROC_INFO_MAX( sb, field, value ) VOID_V #define PROC_INFO_INC( sb, field ) VOID_V #define PROC_INFO_ADD( sb, field, val ) VOID_V -#define PROC_INFO_BH_STAT(sb, p_s_bh, n_node_level) VOID_V +#define PROC_INFO_BH_STAT(sb, bh, n_node_level) VOID_V #endif /* dir.c */ -- cgit v1.2.3 From 995c762ea486b48c9777522071fbf132dea96807 Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Mon, 30 Mar 2009 14:02:47 -0400 Subject: reiserfs: rename p_s_inode to inode This patch is a simple s/p_s_inode/inode/g to the reiserfs code. This is the third in a series of patches to rip out some of the awful variable naming in reiserfs. Signed-off-by: Jeff Mahoney Signed-off-by: Linus Torvalds --- include/linux/reiserfs_fs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index 9cfa518c90b..3192dc79322 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -1870,9 +1870,9 @@ int reiserfs_delete_item(struct reiserfs_transaction_handle *th, void reiserfs_delete_solid_item(struct reiserfs_transaction_handle *th, struct inode *inode, struct reiserfs_key *key); int reiserfs_delete_object(struct reiserfs_transaction_handle *th, - struct inode *p_s_inode); + struct inode *inode); int reiserfs_do_truncate(struct reiserfs_transaction_handle *th, - struct inode *p_s_inode, struct page *, + struct inode *inode, struct page *, int update_timestamps); #define i_block_size(inode) ((inode)->i_sb->s_blocksize) -- cgit v1.2.3 From a063ae17925cafabe55ebe1957ca0e8c480bd132 Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Mon, 30 Mar 2009 14:02:48 -0400 Subject: reiserfs: rename p_s_tb to tb This patch is a simple s/p_s_tb/tb/g to the reiserfs code. This is the fourth in a series of patches to rip out some of the awful variable naming in reiserfs. Signed-off-by: Jeff Mahoney Signed-off-by: Linus Torvalds --- include/linux/reiserfs_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index 3192dc79322..b72dc209547 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -2004,7 +2004,7 @@ extern const struct address_space_operations reiserfs_address_space_operations; /* fix_nodes.c */ -int fix_nodes(int n_op_mode, struct tree_balance *p_s_tb, +int fix_nodes(int n_op_mode, struct tree_balance *tb, struct item_head *p_s_ins_ih, const void *); void unfix_nodes(struct tree_balance *); -- cgit v1.2.3 From d68caa9530a8ba54f97002e02bf6a0ad2462b8c0 Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Mon, 30 Mar 2009 14:02:49 -0400 Subject: reiserfs: rename p_._ variables This patch is a simple s/p_._//g to the reiserfs code. This is the fifth in a series of patches to rip out some of the awful variable naming in reiserfs. Signed-off-by: Jeff Mahoney Signed-off-by: Linus Torvalds --- include/linux/reiserfs_fs.h | 46 ++++++++++++++++++++++----------------------- 1 file changed, 23 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index b72dc209547..e711c796e9d 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -694,9 +694,9 @@ static inline void cpu_key_k_offset_dec(struct cpu_key *key) #define is_indirect_cpu_ih(ih) (is_indirect_cpu_key (&((ih)->ih_key))) #define is_statdata_cpu_ih(ih) (is_statdata_cpu_key (&((ih)->ih_key))) -#define I_K_KEY_IN_ITEM(p_s_ih, p_s_key, n_blocksize) \ - ( ! COMP_SHORT_KEYS(p_s_ih, p_s_key) && \ - I_OFF_BYTE_IN_ITEM(p_s_ih, k_offset (p_s_key), n_blocksize) ) +#define I_K_KEY_IN_ITEM(ih, key, n_blocksize) \ + (!COMP_SHORT_KEYS(ih, key) && \ + I_OFF_BYTE_IN_ITEM(ih, k_offset(key), n_blocksize)) /* maximal length of item */ #define MAX_ITEM_LEN(block_size) (block_size - BLKH_SIZE - IH_SIZE) @@ -1196,33 +1196,33 @@ struct treepath { struct treepath var = {.path_length = ILLEGAL_PATH_ELEMENT_OFFSET, .reada = 0,} /* Get path element by path and path position. */ -#define PATH_OFFSET_PELEMENT(p_s_path,n_offset) ((p_s_path)->path_elements +(n_offset)) +#define PATH_OFFSET_PELEMENT(path, n_offset) ((path)->path_elements + (n_offset)) /* Get buffer header at the path by path and path position. */ -#define PATH_OFFSET_PBUFFER(p_s_path,n_offset) (PATH_OFFSET_PELEMENT(p_s_path,n_offset)->pe_buffer) +#define PATH_OFFSET_PBUFFER(path, n_offset) (PATH_OFFSET_PELEMENT(path, n_offset)->pe_buffer) /* Get position in the element at the path by path and path position. */ -#define PATH_OFFSET_POSITION(p_s_path,n_offset) (PATH_OFFSET_PELEMENT(p_s_path,n_offset)->pe_position) +#define PATH_OFFSET_POSITION(path, n_offset) (PATH_OFFSET_PELEMENT(path, n_offset)->pe_position) -#define PATH_PLAST_BUFFER(p_s_path) (PATH_OFFSET_PBUFFER((p_s_path), (p_s_path)->path_length)) +#define PATH_PLAST_BUFFER(path) (PATH_OFFSET_PBUFFER((path), (path)->path_length)) /* you know, to the person who didn't write this the macro name does not at first suggest what it does. Maybe POSITION_FROM_PATH_END? Or maybe we should just focus on dumping paths... -Hans */ -#define PATH_LAST_POSITION(p_s_path) (PATH_OFFSET_POSITION((p_s_path), (p_s_path)->path_length)) +#define PATH_LAST_POSITION(path) (PATH_OFFSET_POSITION((path), (path)->path_length)) -#define PATH_PITEM_HEAD(p_s_path) B_N_PITEM_HEAD(PATH_PLAST_BUFFER(p_s_path),PATH_LAST_POSITION(p_s_path)) +#define PATH_PITEM_HEAD(path) B_N_PITEM_HEAD(PATH_PLAST_BUFFER(path), PATH_LAST_POSITION(path)) /* in do_balance leaf has h == 0 in contrast with path structure, where root has level == 0. That is why we need these defines */ -#define PATH_H_PBUFFER(p_s_path, h) PATH_OFFSET_PBUFFER (p_s_path, p_s_path->path_length - (h)) /* tb->S[h] */ +#define PATH_H_PBUFFER(path, h) PATH_OFFSET_PBUFFER (path, path->path_length - (h)) /* tb->S[h] */ #define PATH_H_PPARENT(path, h) PATH_H_PBUFFER (path, (h) + 1) /* tb->F[h] or tb->S[0]->b_parent */ #define PATH_H_POSITION(path, h) PATH_OFFSET_POSITION (path, path->path_length - (h)) #define PATH_H_B_ITEM_ORDER(path, h) PATH_H_POSITION(path, h + 1) /* tb->S[h]->b_item_order */ -#define PATH_H_PATH_OFFSET(p_s_path, n_h) ((p_s_path)->path_length - (n_h)) +#define PATH_H_PATH_OFFSET(path, n_h) ((path)->path_length - (n_h)) #define get_last_bh(path) PATH_PLAST_BUFFER(path) #define get_ih(path) PATH_PITEM_HEAD(path) @@ -1512,7 +1512,7 @@ extern struct item_operations *item_ops[TYPE_ANY + 1]; #define COMP_SHORT_KEYS comp_short_keys /* number of blocks pointed to by the indirect item */ -#define I_UNFM_NUM(p_s_ih) ( ih_item_len(p_s_ih) / UNFM_P_SIZE ) +#define I_UNFM_NUM(ih) (ih_item_len(ih) / UNFM_P_SIZE) /* the used space within the unformatted node corresponding to pos within the item pointed to by ih */ #define I_POS_UNFM_SIZE(ih,pos,size) (((pos) == I_UNFM_NUM(ih) - 1 ) ? (size) - ih_free_space(ih) : (size)) @@ -1793,8 +1793,8 @@ int reiserfs_convert_objectid_map_v1(struct super_block *); /* stree.c */ int B_IS_IN_TREE(const struct buffer_head *); -extern void copy_item_head(struct item_head *p_v_to, - const struct item_head *p_v_from); +extern void copy_item_head(struct item_head *to, + const struct item_head *from); // first key is in cpu form, second - le extern int comp_short_keys(const struct reiserfs_key *le_key, @@ -1829,20 +1829,20 @@ static inline void copy_key(struct reiserfs_key *to, memcpy(to, from, KEY_SIZE); } -int comp_items(const struct item_head *stored_ih, const struct treepath *p_s_path); -const struct reiserfs_key *get_rkey(const struct treepath *p_s_chk_path, +int comp_items(const struct item_head *stored_ih, const struct treepath *path); +const struct reiserfs_key *get_rkey(const struct treepath *chk_path, const struct super_block *sb); int search_by_key(struct super_block *, const struct cpu_key *, struct treepath *, int); #define search_item(s,key,path) search_by_key (s, key, path, DISK_LEAF_NODE_LEVEL) int search_for_position_by_key(struct super_block *sb, - const struct cpu_key *p_s_cpu_key, - struct treepath *p_s_search_path); + const struct cpu_key *cpu_key, + struct treepath *search_path); extern void decrement_bcount(struct buffer_head *bh); -void decrement_counters_in_path(struct treepath *p_s_search_path); -void pathrelse(struct treepath *p_s_search_path); +void decrement_counters_in_path(struct treepath *search_path); +void pathrelse(struct treepath *search_path); int reiserfs_check_path(struct treepath *p); -void pathrelse_and_restore(struct super_block *s, struct treepath *p_s_search_path); +void pathrelse_and_restore(struct super_block *s, struct treepath *search_path); int reiserfs_insert_item(struct reiserfs_transaction_handle *th, struct treepath *path, @@ -1865,7 +1865,7 @@ int reiserfs_cut_from_item(struct reiserfs_transaction_handle *th, int reiserfs_delete_item(struct reiserfs_transaction_handle *th, struct treepath *path, const struct cpu_key *key, - struct inode *inode, struct buffer_head *p_s_un_bh); + struct inode *inode, struct buffer_head *un_bh); void reiserfs_delete_solid_item(struct reiserfs_transaction_handle *th, struct inode *inode, struct reiserfs_key *key); @@ -2005,7 +2005,7 @@ extern const struct address_space_operations reiserfs_address_space_operations; /* fix_nodes.c */ int fix_nodes(int n_op_mode, struct tree_balance *tb, - struct item_head *p_s_ins_ih, const void *); + struct item_head *ins_ih, const void *); void unfix_nodes(struct tree_balance *); /* prints.c */ -- cgit v1.2.3 From e7a19c5624c66afa8118b10cd59f87ee407646bc Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Mon, 30 Mar 2009 21:46:44 +0200 Subject: dmi: Let dmi_walk() users pass private data At the moment, dmi_walk() lacks flexibility, users can't pass data to the callback function. Add a pointer for private data to make this function more flexible. Signed-off-by: Jean Delvare Cc: Hans de Goede Cc: Matthew Garrett Cc: Roland Dreier --- include/linux/dmi.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmi.h b/include/linux/dmi.h index d741b9ceb0e..bb5489c82c9 100644 --- a/include/linux/dmi.h +++ b/include/linux/dmi.h @@ -47,7 +47,8 @@ extern int dmi_get_year(int field); extern int dmi_name_in_vendors(const char *str); extern int dmi_name_in_serial(const char *str); extern int dmi_available; -extern int dmi_walk(void (*decode)(const struct dmi_header *)); +extern int dmi_walk(void (*decode)(const struct dmi_header *, void *), + void *private_data); extern bool dmi_match(enum dmi_field f, const char *str); #else @@ -61,8 +62,8 @@ static inline int dmi_get_year(int year) { return 0; } static inline int dmi_name_in_vendors(const char *s) { return 0; } static inline int dmi_name_in_serial(const char *s) { return 0; } #define dmi_available 0 -static inline int dmi_walk(void (*decode)(const struct dmi_header *)) - { return -1; } +static inline int dmi_walk(void (*decode)(const struct dmi_header *, void *), + void *private_data) { return -1; } static inline bool dmi_match(enum dmi_field f, const char *str) { return false; } static inline const struct dmi_system_id * -- cgit v1.2.3 From 0a0c5168df270a50e3518e4f12bddb31f8f5f38f Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 16 Mar 2009 22:33:49 +0100 Subject: PM: Introduce functions for suspending and resuming device interrupts Introduce helper functions allowing us to prevent device drivers from getting any interrupts (without disabling interrupts on the CPU) during suspend (or hibernation) and to make them start to receive interrupts again during the subsequent resume. These functions make it possible to keep timer interrupts enabled while the "late" suspend and "early" resume callbacks provided by device drivers are being executed. In turn, this allows device drivers' "late" suspend and "early" resume callbacks to sleep, execute ACPI callbacks etc. The functions introduced here will be used to rework the handling of interrupts during suspend (hibernation) and resume. Namely, interrupts will only be disabled on the CPU right before suspending sysdevs, while device drivers will be prevented from receiving interrupts, with the help of the new helper function, before their "late" suspend callbacks run (and analogously during resume). Signed-off-by: Rafael J. Wysocki Acked-by: Ingo Molnar --- include/linux/interrupt.h | 9 +++++++++ include/linux/irq.h | 1 + 2 files changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 0c9cb63e689..c68bffd182b 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -117,6 +117,15 @@ extern void disable_irq_nosync(unsigned int irq); extern void disable_irq(unsigned int irq); extern void enable_irq(unsigned int irq); +/* The following three functions are for the core kernel use only. */ +extern void suspend_device_irqs(void); +extern void resume_device_irqs(void); +#ifdef CONFIG_PM_SLEEP +extern int check_wakeup_irqs(void); +#else +static inline int check_wakeup_irqs(void) { return 0; } +#endif + #if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_HARDIRQS) extern cpumask_var_t irq_default_affinity; diff --git a/include/linux/irq.h b/include/linux/irq.h index 9c62fbe2ef3..974890b3c52 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -67,6 +67,7 @@ typedef void (*irq_flow_handler_t)(unsigned int irq, #define IRQ_SPURIOUS_DISABLED 0x00800000 /* IRQ was disabled by the spurious trap */ #define IRQ_MOVE_PCNTXT 0x01000000 /* IRQ migration from process context */ #define IRQ_AFFINITY_SET 0x02000000 /* IRQ affinity was set from userspace*/ +#define IRQ_SUSPENDED 0x04000000 /* IRQ has gone through suspend sequence */ #ifdef CONFIG_IRQ_PER_CPU # define CHECK_IRQ_PER_CPU(var) ((var) & IRQ_PER_CPU) -- cgit v1.2.3 From 0e5dd46b761195356065a30611f265adec286d0d Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 26 Mar 2009 22:51:40 +0100 Subject: PCI PM: Introduce __pci_[start|complete]_power_transition() (rev. 2) The radeonfb driver needs to program the device's PMCSR directly due to some quirky hardware it has to handle (see http://bugzilla.kernel.org/show_bug.cgi?id=12846 for details) and after doing that it needs to call the platform (usually ACPI) to finish the power transition of the device. Currently it uses pci_set_power_state() for this purpose, however making a specific assumption about the internal behavior of this function, which has changed recently so that this assumption is no longer satisfied. For this reason, introduce __pci_complete_power_transition() that may be called by the radeonfb driver to complete the power transition of the device. For symmetry, introduce __pci_start_power_transition(). Signed-off-by: Rafael J. Wysocki Acked-by: Jesse Barnes --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 7bd624bfdcf..df364413261 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -689,6 +689,7 @@ size_t pci_get_rom_size(struct pci_dev *pdev, void __iomem *rom, size_t size); /* Power management related routines */ int pci_save_state(struct pci_dev *dev); int pci_restore_state(struct pci_dev *dev); +int __pci_complete_power_transition(struct pci_dev *dev, pci_power_t state); int pci_set_power_state(struct pci_dev *dev, pci_power_t state); pci_power_t pci_choose_state(struct pci_dev *dev, pm_message_t state); bool pci_pme_capable(struct pci_dev *dev, pci_power_t state); -- cgit v1.2.3 From 99b76233803beab302123d243eea9e41149804f3 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Wed, 25 Mar 2009 22:48:06 +0300 Subject: proc 2/2: remove struct proc_dir_entry::owner Setting ->owner as done currently (pde->owner = THIS_MODULE) is racy as correctly noted at bug #12454. Someone can lookup entry with NULL ->owner, thus not pinning enything, and release it later resulting in module refcount underflow. We can keep ->owner and supply it at registration time like ->proc_fops and ->data. But this leaves ->owner as easy-manipulative field (just one C assignment) and somebody will forget to unpin previous/pin current module when switching ->owner. ->proc_fops is declared as "const" which should give some thoughts. ->read_proc/->write_proc were just fixed to not require ->owner for protection. rmmod'ed directories will be empty and return "." and ".." -- no harm. And directories with tricky enough readdir and lookup shouldn't be modular. We definitely don't want such modular code. Removing ->owner will also make PDE smaller. So, let's nuke it. Kudos to Jeff Layton for reminding about this, let's say, oversight. http://bugzilla.kernel.org/show_bug.cgi?id=12454 Signed-off-by: Alexey Dobriyan --- include/linux/ipmi_smi.h | 2 +- include/linux/proc_fs.h | 4 ---- 2 files changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipmi_smi.h b/include/linux/ipmi_smi.h index 62b73668b60..f7c9c75a277 100644 --- a/include/linux/ipmi_smi.h +++ b/include/linux/ipmi_smi.h @@ -230,6 +230,6 @@ static inline void ipmi_free_smi_msg(struct ipmi_smi_msg *msg) automatically be dstroyed when the interface is destroyed. */ int ipmi_smi_add_proc_entry(ipmi_smi_t smi, char *name, read_proc_t *read_proc, - void *data, struct module *owner); + void *data); #endif /* __LINUX_IPMI_SMI_H */ diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index b8bdb96eff7..fbfa3d44d33 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -41,9 +41,6 @@ enum { * while parent/subdir create the directory structure (every * /proc file has a parent, but "subdir" is NULL for all * non-directory entries). - * - * "owner" is used to protect module - * from unloading while proc_dir_entry is in use */ typedef int (read_proc_t)(char *page, char **start, off_t off, @@ -70,7 +67,6 @@ struct proc_dir_entry { * somewhere. */ const struct file_operations *proc_fops; - struct module *owner; struct proc_dir_entry *next, *parent, *subdir; void *data; read_proc_t *read_proc; -- cgit v1.2.3 From 77e465867080c2d1e0c410e96dcdcd51e8584a6f Mon Sep 17 00:00:00 2001 From: Alexander Beregalov Date: Tue, 31 Mar 2009 00:32:40 +0400 Subject: reiserfs: fix build breakage Fix this build error when REISERFS_FS_POSIX_ACL is not set: fs/reiserfs/inode.c: In function 'reiserfs_new_inode': fs/reiserfs/inode.c:1919: warning: passing argument 1 of 'reiserfs_inherit_default_acl' from incompatible pointer type fs/reiserfs/inode.c:1919: warning: passing argument 2 of 'reiserfs_inherit_default_acl' from incompatible pointer type fs/reiserfs/inode.c:1919: warning: passing argument 3 of 'reiserfs_inherit_default_acl' from incompatible pointer type fs/reiserfs/inode.c:1919: error: too many arguments to function 'reiserfs_inherit_default_acl' due to a missing transaction-handle argument in the non-acl compatibility function. Signed-off-by: Alexander Beregalov Acked-by: Jeff Mahoney Signed-off-by: Linus Torvalds --- include/linux/reiserfs_acl.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/reiserfs_acl.h b/include/linux/reiserfs_acl.h index 52240e02de0..8cc65757e47 100644 --- a/include/linux/reiserfs_acl.h +++ b/include/linux/reiserfs_acl.h @@ -80,7 +80,8 @@ static inline int reiserfs_acl_chmod(struct inode *inode) } static inline int -reiserfs_inherit_default_acl(const struct inode *dir, struct dentry *dentry, +reiserfs_inherit_default_acl(struct reiserfs_transaction_handle *th, + const struct inode *dir, struct dentry *dentry, struct inode *inode) { return 0; -- cgit v1.2.3 From e180a6b7759a99a28cbcce3547c4c80822cb6c2a Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Tue, 31 Mar 2009 13:05:29 -0600 Subject: param: fix charp parameters set via sysfs Impact: fix crash on reading from /sys/module/.../ieee80211_default_rc_algo The module_param type "charp" simply sets a char * pointer in the module to the parameter in the commandline string: this is why we keep the (mangled) module command line around. But when set via sysfs (as about 11 charp parameters can be) this memory is freed on the way out of the write(). Future reads hit random mem. So we kstrdup instead: we have to check we're not in early commandline parsing, and we have to note when we've used it so we can reliably kfree the parameter when it's next overwritten, and also on module unload. (Thanks to Randy Dunlap for CONFIG_SYSFS=n fixes) Reported-by: Sitsofe Wheeler Diagnosed-by: Frederic Weisbecker Tested-by: Frederic Weisbecker Tested-by: Christof Schmitt Signed-off-by: Rusty Russell --- include/linux/module.h | 4 ++++ include/linux/moduleparam.h | 10 ++++++++++ 2 files changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index 145a75528cc..08e5e75d612 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -248,6 +248,10 @@ struct module const unsigned long *crcs; unsigned int num_syms; + /* Kernel parameters. */ + struct kernel_param *kp; + unsigned int num_kp; + /* GPL-only exported symbols. */ unsigned int num_gpl_syms; const struct kernel_symbol *gpl_syms; diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h index e4af3399ef4..a4f0b931846 100644 --- a/include/linux/moduleparam.h +++ b/include/linux/moduleparam.h @@ -138,6 +138,16 @@ extern int parse_args(const char *name, unsigned num, int (*unknown)(char *param, char *val)); +/* Called by module remove. */ +#ifdef CONFIG_SYSFS +extern void destroy_params(const struct kernel_param *params, unsigned num); +#else +static inline void destroy_params(const struct kernel_param *params, + unsigned num) +{ +} +#endif /* !CONFIG_SYSFS */ + /* All the helper functions */ /* The macros to do compile-time type checking stolen from Jakub Jelinek, who IIRC came up with this idea for the 2.4 module init code. */ -- cgit v1.2.3 From e610499e2656e61975affd0af56b26eb73964c84 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Tue, 31 Mar 2009 13:05:31 -0600 Subject: module: __module_address Impact: New API, cleanup ksplice wants to know the bounds of a module, not just the module text. It makes sense to have __module_address. We then implement is_module_address and __module_text_address in terms of this (and change is_module_text_address() to bool while we're at it). Also, add proper kerneldoc for them all. Cc: Anders Kaseorg Cc: Jeff Arnold Cc: Tim Abbott Signed-off-by: Rusty Russell --- include/linux/module.h | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index 08e5e75d612..fd1241e1416 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -365,7 +365,9 @@ static inline int module_is_live(struct module *mod) /* Is this address in a module? (second is with no locks, for oops) */ struct module *module_text_address(unsigned long addr); struct module *__module_text_address(unsigned long addr); -int is_module_address(unsigned long addr); +struct module *__module_address(unsigned long addr); +bool is_module_address(unsigned long addr); +bool is_module_text_address(unsigned long addr); static inline int within_module_core(unsigned long addr, struct module *mod) { @@ -494,21 +496,29 @@ search_module_extables(unsigned long addr) return NULL; } -/* Is this address in a module? */ static inline struct module *module_text_address(unsigned long addr) { return NULL; } -/* Is this address in a module? (don't take a lock, we're oopsing) */ +static inline struct module *__module_address(unsigned long addr) +{ + return NULL; +} + static inline struct module *__module_text_address(unsigned long addr) { return NULL; } -static inline int is_module_address(unsigned long addr) +static inline bool is_module_address(unsigned long addr) { - return 0; + return false; +} + +static inline bool is_module_text_address(unsigned long addr) +{ + return false; } /* Get/put a kernel symbol (calls should be symmetric) */ -- cgit v1.2.3 From a6e6abd575fcbe6572ebc7a70ad616406d206fa8 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Tue, 31 Mar 2009 13:05:31 -0600 Subject: module: remove module_text_address() Impact: Replace and remove risky (non-EXPORTed) API module_text_address() returns a pointer to the module, which given locking improvements in module.c, is useless except to test for NULL: 1) If the module can't go away, use __module_text_address. 2) Otherwise, just use is_module_text_address(). Cc: linux-mtd@lists.infradead.org Signed-off-by: Rusty Russell --- include/linux/module.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index fd1241e1416..69761ce0dbf 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -362,8 +362,6 @@ static inline int module_is_live(struct module *mod) return mod->state != MODULE_STATE_GOING; } -/* Is this address in a module? (second is with no locks, for oops) */ -struct module *module_text_address(unsigned long addr); struct module *__module_text_address(unsigned long addr); struct module *__module_address(unsigned long addr); bool is_module_address(unsigned long addr); @@ -496,11 +494,6 @@ search_module_extables(unsigned long addr) return NULL; } -static inline struct module *module_text_address(unsigned long addr) -{ - return NULL; -} - static inline struct module *__module_address(unsigned long addr) { return NULL; -- cgit v1.2.3 From 75a66614db21007bcc8c37f9c5d5b922981387b9 Mon Sep 17 00:00:00 2001 From: Anders Kaseorg Date: Fri, 5 Dec 2008 19:03:58 -0500 Subject: Ksplice: Add functions for walking kallsyms symbols Impact: New API kallsyms_lookup_name only returns the first match that it finds. Ksplice needs information about all symbols with a given name in order to correctly resolve local symbols. kallsyms_on_each_symbol provides a generic mechanism for iterating over the kallsyms table. Cc: Jeff Arnold Cc: Tim Abbott Signed-off-by: Anders Kaseorg Signed-off-by: Rusty Russell --- include/linux/kallsyms.h | 15 +++++++++++++++ include/linux/module.h | 12 ++++++++++++ 2 files changed, 27 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h index f3fe34391d8..792274269f2 100644 --- a/include/linux/kallsyms.h +++ b/include/linux/kallsyms.h @@ -13,10 +13,17 @@ #define KSYM_SYMBOL_LEN (sizeof("%s+%#lx/%#lx [%s]") + (KSYM_NAME_LEN - 1) + \ 2*(BITS_PER_LONG*3/10) + (MODULE_NAME_LEN - 1) + 1) +struct module; + #ifdef CONFIG_KALLSYMS /* Lookup the address for a symbol. Returns 0 if not found. */ unsigned long kallsyms_lookup_name(const char *name); +/* Call a function on each kallsyms symbol in the core kernel */ +int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, + unsigned long), + void *data); + extern int kallsyms_lookup_size_offset(unsigned long addr, unsigned long *symbolsize, unsigned long *offset); @@ -43,6 +50,14 @@ static inline unsigned long kallsyms_lookup_name(const char *name) return 0; } +static inline int kallsyms_on_each_symbol(int (*fn)(void *, const char *, + struct module *, + unsigned long), + void *data) +{ + return 0; +} + static inline int kallsyms_lookup_size_offset(unsigned long addr, unsigned long *symbolsize, unsigned long *offset) diff --git a/include/linux/module.h b/include/linux/module.h index 69761ce0dbf..c3d3fc4ffb1 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -387,6 +387,10 @@ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, /* Look for this name: can be of form module:name. */ unsigned long module_kallsyms_lookup_name(const char *name); +int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *, + struct module *, unsigned long), + void *data); + extern void __module_put_and_exit(struct module *mod, long code) __attribute__((noreturn)); #define module_put_and_exit(code) __module_put_and_exit(THIS_MODULE, code); @@ -566,6 +570,14 @@ static inline unsigned long module_kallsyms_lookup_name(const char *name) return 0; } +static inline int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *, + struct module *, + unsigned long), + void *data) +{ + return 0; +} + static inline int register_module_notifier(struct notifier_block * nb) { /* no events will happen anyway, so this can always succeed */ -- cgit v1.2.3 From c6b37801911d7f4663c99cad8aa230bc934cea82 Mon Sep 17 00:00:00 2001 From: Tim Abbott Date: Fri, 5 Dec 2008 19:03:59 -0500 Subject: module: Export symbols needed for Ksplice Impact: Expose some module.c symbols Ksplice uses several functions from module.c in order to resolve symbols and implement dependency handling. Calling these functions requires holding module_mutex, so it is exported. (This is just the module part of a bigger add-exports patch from Tim). Cc: Anders Kaseorg Cc: Jeff Arnold Signed-off-by: Tim Abbott Signed-off-by: Rusty Russell --- include/linux/module.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index c3d3fc4ffb1..d246da0b0f8 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -354,6 +354,8 @@ struct module #define MODULE_ARCH_INIT {} #endif +extern struct mutex module_mutex; + /* FIXME: It'd be nice to isolate modules during init, too, so they aren't used before they (may) fail. But presently too much code (IDE & SCSI) require entry into the module during init.*/ @@ -379,6 +381,31 @@ static inline int within_module_init(unsigned long addr, struct module *mod) addr < (unsigned long)mod->module_init + mod->init_size; } +/* Search for module by name: must hold module_mutex. */ +struct module *find_module(const char *name); + +struct symsearch { + const struct kernel_symbol *start, *stop; + const unsigned long *crcs; + enum { + NOT_GPL_ONLY, + GPL_ONLY, + WILL_BE_GPL_ONLY, + } licence; + bool unused; +}; + +/* Search for an exported symbol by name. */ +const struct kernel_symbol *find_symbol(const char *name, + struct module **owner, + const unsigned long **crc, + bool gplok, + bool warn); + +/* Walk the exported symbol table */ +bool each_symbol(bool (*fn)(const struct symsearch *arr, struct module *owner, + unsigned int symnum, void *data), void *data); + /* Returns 0 and fills in value, defined and namebuf, or -ERANGE if symnum out of range. */ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, @@ -452,6 +479,7 @@ static inline void __module_get(struct module *module) #define symbol_put_addr(p) do { } while(0) #endif /* CONFIG_MODULE_UNLOAD */ +int use_module(struct module *a, struct module *b); /* This is a #define so the string doesn't get put in every .o file */ #define module_name(mod) \ -- cgit v1.2.3 From acae05156551fd7528fbb616271e672789388e3c Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Sun, 8 Feb 2009 10:42:01 -0800 Subject: module: create a request_module_nowait() There seems to be a common pattern in the kernel where drivers want to call request_module() from inside a module_init() function. Currently this would deadlock. As a result, several drivers go through hoops like scheduling things via kevent, or creating custom work queues (because kevent can deadlock on them). This patch changes this to use a request_module_nowait() function macro instead, which just fires the modprobe off but doesn't wait for it, and thus avoids the original deadlock entirely. On my laptop this already results in one less kernel thread running.. (Includes Jiri's patch to use enum umh_wait) Signed-off-by: Arjan van de Ven Signed-off-by: Rusty Russell (bool-ified) Cc: Jiri Slaby --- include/linux/kmod.h | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kmod.h b/include/linux/kmod.h index 92213a9194e..d5fa565086d 100644 --- a/include/linux/kmod.h +++ b/include/linux/kmod.h @@ -29,10 +29,15 @@ #ifdef CONFIG_MODULES /* modprobe exit status on success, -ve on error. Return value * usually useless though. */ -extern int request_module(const char * name, ...) __attribute__ ((format (printf, 1, 2))); -#define try_then_request_module(x, mod...) ((x) ?: (request_module(mod), (x))) +extern int __request_module(bool wait, const char *name, ...) \ + __attribute__((format(printf, 2, 3))); +#define request_module(mod...) __request_module(true, mod) +#define request_module_nowait(mod...) __request_module(false, mod) +#define try_then_request_module(x, mod...) \ + ((x) ?: (__request_module(false, mod), (x))) #else -static inline int request_module(const char * name, ...) { return -ENOSYS; } +static inline int request_module(const char *name, ...) { return -ENOSYS; } +static inline int request_module_nowait(const char *name, ...) { return -ENOSYS; } #define try_then_request_module(x, mod...) (x) #endif -- cgit v1.2.3 From 66f92cf9d415e96a5bdd6c64de8dd8418595d2fc Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Tue, 31 Mar 2009 13:05:36 -0600 Subject: strstarts: helper function for !strncmp(str, prefix, strlen(prefix)) Impact: minor new API ksplice added a "starts_with" function, which seems like a common need. When people open-code it they seem to use fixed numbers rather than strlen, so it's quite a readability win (also, strncmp() almost always wants != 0 on it). So here's strstarts(). Cc: Anders Kaseorg Cc: Jeff Arnold Cc: Tim Abbott Signed-off-by: Rusty Russell --- include/linux/string.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/string.h b/include/linux/string.h index d18fc198aa2..76ec218bb30 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -114,5 +114,14 @@ extern bool sysfs_streq(const char *s1, const char *s2); extern ssize_t memory_read_from_buffer(void *to, size_t count, loff_t *ppos, const void *from, size_t available); +/** + * strstarts - does @str start with @prefix? + * @str: string to examine + * @prefix: prefix to look for. + */ +static inline bool strstarts(const char *str, const char *prefix) +{ + return strncmp(str, prefix, strlen(prefix)) == 0; +} #endif #endif /* _LINUX_STRING_H_ */ -- cgit v1.2.3 From eea1bf384e05b5ab747f8530c4fba9e9e6907fff Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 31 Mar 2009 14:27:02 +1100 Subject: md: Fix is_mddev_idle test (again). There are two problems with is_mddev_idle. 1/ sync_io is 'atomic_t' and hence 'int'. curr_events and all the rest are 'long'. So if sync_io were to wrap on a 64bit host, the value of curr_events would go very negative suddenly, and take a very long time to return to positive. So do all calculations as 'int'. That gives us plenty of precision for what we need. 2/ To initialise rdev->last_events we simply call is_mddev_idle, on the assumption that it will make sure that last_events is in a suitable range. It used to do this, but now it does not. So now we need to be more explicit about initialisation. Signed-off-by: NeilBrown --- include/linux/raid/md_k.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h index 9743e4dbc91..4aedb9fe2bd 100644 --- a/include/linux/raid/md_k.h +++ b/include/linux/raid/md_k.h @@ -51,7 +51,7 @@ struct mdk_rdev_s sector_t size; /* Device size (in blocks) */ mddev_t *mddev; /* RAID array if running */ - long last_events; /* IO event timestamp */ + int last_events; /* IO event timestamp */ struct block_device *bdev; /* block device handle */ -- cgit v1.2.3 From ef740c372dfd80e706dbf955d4e4aedda6c0c148 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 31 Mar 2009 14:27:03 +1100 Subject: md: move headers out of include/linux/raid/ Move the headers with the local structures for the disciplines and bitmap.h into drivers/md/ so that they are more easily grepable for hacking and not far away. md.h is left where it is for now as there are some uses from the outside. Signed-off-by: Christoph Hellwig Signed-off-by: NeilBrown --- include/linux/raid/bitmap.h | 288 ----------------------------- include/linux/raid/linear.h | 31 ---- include/linux/raid/multipath.h | 42 ----- include/linux/raid/raid0.h | 30 --- include/linux/raid/raid1.h | 134 -------------- include/linux/raid/raid10.h | 123 ------------- include/linux/raid/raid5.h | 402 ----------------------------------------- 7 files changed, 1050 deletions(-) delete mode 100644 include/linux/raid/bitmap.h delete mode 100644 include/linux/raid/linear.h delete mode 100644 include/linux/raid/multipath.h delete mode 100644 include/linux/raid/raid0.h delete mode 100644 include/linux/raid/raid1.h delete mode 100644 include/linux/raid/raid10.h delete mode 100644 include/linux/raid/raid5.h (limited to 'include/linux') diff --git a/include/linux/raid/bitmap.h b/include/linux/raid/bitmap.h deleted file mode 100644 index e98900671ca..00000000000 --- a/include/linux/raid/bitmap.h +++ /dev/null @@ -1,288 +0,0 @@ -/* - * bitmap.h: Copyright (C) Peter T. Breuer (ptb@ot.uc3m.es) 2003 - * - * additions: Copyright (C) 2003-2004, Paul Clements, SteelEye Technology, Inc. - */ -#ifndef BITMAP_H -#define BITMAP_H 1 - -#define BITMAP_MAJOR_LO 3 -/* version 4 insists the bitmap is in little-endian order - * with version 3, it is host-endian which is non-portable - */ -#define BITMAP_MAJOR_HI 4 -#define BITMAP_MAJOR_HOSTENDIAN 3 - -#define BITMAP_MINOR 39 - -/* - * in-memory bitmap: - * - * Use 16 bit block counters to track pending writes to each "chunk". - * The 2 high order bits are special-purpose, the first is a flag indicating - * whether a resync is needed. The second is a flag indicating whether a - * resync is active. - * This means that the counter is actually 14 bits: - * - * +--------+--------+------------------------------------------------+ - * | resync | resync | counter | - * | needed | active | | - * | (0-1) | (0-1) | (0-16383) | - * +--------+--------+------------------------------------------------+ - * - * The "resync needed" bit is set when: - * a '1' bit is read from storage at startup. - * a write request fails on some drives - * a resync is aborted on a chunk with 'resync active' set - * It is cleared (and resync-active set) when a resync starts across all drives - * of the chunk. - * - * - * The "resync active" bit is set when: - * a resync is started on all drives, and resync_needed is set. - * resync_needed will be cleared (as long as resync_active wasn't already set). - * It is cleared when a resync completes. - * - * The counter counts pending write requests, plus the on-disk bit. - * When the counter is '1' and the resync bits are clear, the on-disk - * bit can be cleared aswell, thus setting the counter to 0. - * When we set a bit, or in the counter (to start a write), if the fields is - * 0, we first set the disk bit and set the counter to 1. - * - * If the counter is 0, the on-disk bit is clear and the stipe is clean - * Anything that dirties the stipe pushes the counter to 2 (at least) - * and sets the on-disk bit (lazily). - * If a periodic sweep find the counter at 2, it is decremented to 1. - * If the sweep find the counter at 1, the on-disk bit is cleared and the - * counter goes to zero. - * - * Also, we'll hijack the "map" pointer itself and use it as two 16 bit block - * counters as a fallback when "page" memory cannot be allocated: - * - * Normal case (page memory allocated): - * - * page pointer (32-bit) - * - * [ ] ------+ - * | - * +-------> [ ][ ]..[ ] (4096 byte page == 2048 counters) - * c1 c2 c2048 - * - * Hijacked case (page memory allocation failed): - * - * hijacked page pointer (32-bit) - * - * [ ][ ] (no page memory allocated) - * counter #1 (16-bit) counter #2 (16-bit) - * - */ - -#ifdef __KERNEL__ - -#define PAGE_BITS (PAGE_SIZE << 3) -#define PAGE_BIT_SHIFT (PAGE_SHIFT + 3) - -typedef __u16 bitmap_counter_t; -#define COUNTER_BITS 16 -#define COUNTER_BIT_SHIFT 4 -#define COUNTER_BYTE_RATIO (COUNTER_BITS / 8) -#define COUNTER_BYTE_SHIFT (COUNTER_BIT_SHIFT - 3) - -#define NEEDED_MASK ((bitmap_counter_t) (1 << (COUNTER_BITS - 1))) -#define RESYNC_MASK ((bitmap_counter_t) (1 << (COUNTER_BITS - 2))) -#define COUNTER_MAX ((bitmap_counter_t) RESYNC_MASK - 1) -#define NEEDED(x) (((bitmap_counter_t) x) & NEEDED_MASK) -#define RESYNC(x) (((bitmap_counter_t) x) & RESYNC_MASK) -#define COUNTER(x) (((bitmap_counter_t) x) & COUNTER_MAX) - -/* how many counters per page? */ -#define PAGE_COUNTER_RATIO (PAGE_BITS / COUNTER_BITS) -/* same, except a shift value for more efficient bitops */ -#define PAGE_COUNTER_SHIFT (PAGE_BIT_SHIFT - COUNTER_BIT_SHIFT) -/* same, except a mask value for more efficient bitops */ -#define PAGE_COUNTER_MASK (PAGE_COUNTER_RATIO - 1) - -#define BITMAP_BLOCK_SIZE 512 -#define BITMAP_BLOCK_SHIFT 9 - -/* how many blocks per chunk? (this is variable) */ -#define CHUNK_BLOCK_RATIO(bitmap) ((bitmap)->chunksize >> BITMAP_BLOCK_SHIFT) -#define CHUNK_BLOCK_SHIFT(bitmap) ((bitmap)->chunkshift - BITMAP_BLOCK_SHIFT) -#define CHUNK_BLOCK_MASK(bitmap) (CHUNK_BLOCK_RATIO(bitmap) - 1) - -/* when hijacked, the counters and bits represent even larger "chunks" */ -/* there will be 1024 chunks represented by each counter in the page pointers */ -#define PAGEPTR_BLOCK_RATIO(bitmap) \ - (CHUNK_BLOCK_RATIO(bitmap) << PAGE_COUNTER_SHIFT >> 1) -#define PAGEPTR_BLOCK_SHIFT(bitmap) \ - (CHUNK_BLOCK_SHIFT(bitmap) + PAGE_COUNTER_SHIFT - 1) -#define PAGEPTR_BLOCK_MASK(bitmap) (PAGEPTR_BLOCK_RATIO(bitmap) - 1) - -/* - * on-disk bitmap: - * - * Use one bit per "chunk" (block set). We do the disk I/O on the bitmap - * file a page at a time. There's a superblock at the start of the file. - */ - -/* map chunks (bits) to file pages - offset by the size of the superblock */ -#define CHUNK_BIT_OFFSET(chunk) ((chunk) + (sizeof(bitmap_super_t) << 3)) - -#endif - -/* - * bitmap structures: - */ - -#define BITMAP_MAGIC 0x6d746962 - -/* use these for bitmap->flags and bitmap->sb->state bit-fields */ -enum bitmap_state { - BITMAP_STALE = 0x002, /* the bitmap file is out of date or had -EIO */ - BITMAP_WRITE_ERROR = 0x004, /* A write error has occurred */ - BITMAP_HOSTENDIAN = 0x8000, -}; - -/* the superblock at the front of the bitmap file -- little endian */ -typedef struct bitmap_super_s { - __le32 magic; /* 0 BITMAP_MAGIC */ - __le32 version; /* 4 the bitmap major for now, could change... */ - __u8 uuid[16]; /* 8 128 bit uuid - must match md device uuid */ - __le64 events; /* 24 event counter for the bitmap (1)*/ - __le64 events_cleared;/*32 event counter when last bit cleared (2) */ - __le64 sync_size; /* 40 the size of the md device's sync range(3) */ - __le32 state; /* 48 bitmap state information */ - __le32 chunksize; /* 52 the bitmap chunk size in bytes */ - __le32 daemon_sleep; /* 56 seconds between disk flushes */ - __le32 write_behind; /* 60 number of outstanding write-behind writes */ - - __u8 pad[256 - 64]; /* set to zero */ -} bitmap_super_t; - -/* notes: - * (1) This event counter is updated before the eventcounter in the md superblock - * When a bitmap is loaded, it is only accepted if this event counter is equal - * to, or one greater than, the event counter in the superblock. - * (2) This event counter is updated when the other one is *if*and*only*if* the - * array is not degraded. As bits are not cleared when the array is degraded, - * this represents the last time that any bits were cleared. - * If a device is being added that has an event count with this value or - * higher, it is accepted as conforming to the bitmap. - * (3)This is the number of sectors represented by the bitmap, and is the range that - * resync happens across. For raid1 and raid5/6 it is the size of individual - * devices. For raid10 it is the size of the array. - */ - -#ifdef __KERNEL__ - -/* the in-memory bitmap is represented by bitmap_pages */ -struct bitmap_page { - /* - * map points to the actual memory page - */ - char *map; - /* - * in emergencies (when map cannot be alloced), hijack the map - * pointer and use it as two counters itself - */ - unsigned int hijacked:1; - /* - * count of dirty bits on the page - */ - unsigned int count:31; -}; - -/* keep track of bitmap file pages that have pending writes on them */ -struct page_list { - struct list_head list; - struct page *page; -}; - -/* the main bitmap structure - one per mddev */ -struct bitmap { - struct bitmap_page *bp; - unsigned long pages; /* total number of pages in the bitmap */ - unsigned long missing_pages; /* number of pages not yet allocated */ - - mddev_t *mddev; /* the md device that the bitmap is for */ - - int counter_bits; /* how many bits per block counter */ - - /* bitmap chunksize -- how much data does each bit represent? */ - unsigned long chunksize; - unsigned long chunkshift; /* chunksize = 2^chunkshift (for bitops) */ - unsigned long chunks; /* total number of data chunks for the array */ - - /* We hold a count on the chunk currently being synced, and drop - * it when the last block is started. If the resync is aborted - * midway, we need to be able to drop that count, so we remember - * the counted chunk.. - */ - unsigned long syncchunk; - - __u64 events_cleared; - int need_sync; - - /* bitmap spinlock */ - spinlock_t lock; - - long offset; /* offset from superblock if file is NULL */ - struct file *file; /* backing disk file */ - struct page *sb_page; /* cached copy of the bitmap file superblock */ - struct page **filemap; /* list of cache pages for the file */ - unsigned long *filemap_attr; /* attributes associated w/ filemap pages */ - unsigned long file_pages; /* number of pages in the file */ - int last_page_size; /* bytes in the last page */ - - unsigned long flags; - - int allclean; - - unsigned long max_write_behind; /* write-behind mode */ - atomic_t behind_writes; - - /* - * the bitmap daemon - periodically wakes up and sweeps the bitmap - * file, cleaning up bits and flushing out pages to disk as necessary - */ - unsigned long daemon_lastrun; /* jiffies of last run */ - unsigned long daemon_sleep; /* how many seconds between updates? */ - unsigned long last_end_sync; /* when we lasted called end_sync to - * update bitmap with resync progress */ - - atomic_t pending_writes; /* pending writes to the bitmap file */ - wait_queue_head_t write_wait; - wait_queue_head_t overflow_wait; - -}; - -/* the bitmap API */ - -/* these are used only by md/bitmap */ -int bitmap_create(mddev_t *mddev); -void bitmap_flush(mddev_t *mddev); -void bitmap_destroy(mddev_t *mddev); - -void bitmap_print_sb(struct bitmap *bitmap); -void bitmap_update_sb(struct bitmap *bitmap); - -int bitmap_setallbits(struct bitmap *bitmap); -void bitmap_write_all(struct bitmap *bitmap); - -void bitmap_dirty_bits(struct bitmap *bitmap, unsigned long s, unsigned long e); - -/* these are exported */ -int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, - unsigned long sectors, int behind); -void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, - unsigned long sectors, int success, int behind); -int bitmap_start_sync(struct bitmap *bitmap, sector_t offset, int *blocks, int degraded); -void bitmap_end_sync(struct bitmap *bitmap, sector_t offset, int *blocks, int aborted); -void bitmap_close_sync(struct bitmap *bitmap); -void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector); - -void bitmap_unplug(struct bitmap *bitmap); -void bitmap_daemon_work(struct bitmap *bitmap); -#endif - -#endif diff --git a/include/linux/raid/linear.h b/include/linux/raid/linear.h deleted file mode 100644 index f38b9c586af..00000000000 --- a/include/linux/raid/linear.h +++ /dev/null @@ -1,31 +0,0 @@ -#ifndef _LINEAR_H -#define _LINEAR_H - -#include - -struct dev_info { - mdk_rdev_t *rdev; - sector_t num_sectors; - sector_t start_sector; -}; - -typedef struct dev_info dev_info_t; - -struct linear_private_data -{ - struct linear_private_data *prev; /* earlier version */ - dev_info_t **hash_table; - sector_t spacing; - sector_t array_sectors; - int sector_shift; /* shift before dividing - * by spacing - */ - dev_info_t disks[0]; -}; - - -typedef struct linear_private_data linear_conf_t; - -#define mddev_to_conf(mddev) ((linear_conf_t *) mddev->private) - -#endif diff --git a/include/linux/raid/multipath.h b/include/linux/raid/multipath.h deleted file mode 100644 index 6f53fc177a4..00000000000 --- a/include/linux/raid/multipath.h +++ /dev/null @@ -1,42 +0,0 @@ -#ifndef _MULTIPATH_H -#define _MULTIPATH_H - -#include - -struct multipath_info { - mdk_rdev_t *rdev; -}; - -struct multipath_private_data { - mddev_t *mddev; - struct multipath_info *multipaths; - int raid_disks; - int working_disks; - spinlock_t device_lock; - struct list_head retry_list; - - mempool_t *pool; -}; - -typedef struct multipath_private_data multipath_conf_t; - -/* - * this is the only point in the RAID code where we violate - * C type safety. mddev->private is an 'opaque' pointer. - */ -#define mddev_to_conf(mddev) ((multipath_conf_t *) mddev->private) - -/* - * this is our 'private' 'collective' MULTIPATH buffer head. - * it contains information about what kind of IO operations were started - * for this MULTIPATH operation, and about their status: - */ - -struct multipath_bh { - mddev_t *mddev; - struct bio *master_bio; - struct bio bio; - int path; - struct list_head retry_list; -}; -#endif diff --git a/include/linux/raid/raid0.h b/include/linux/raid/raid0.h deleted file mode 100644 index fd42aa87c39..00000000000 --- a/include/linux/raid/raid0.h +++ /dev/null @@ -1,30 +0,0 @@ -#ifndef _RAID0_H -#define _RAID0_H - -#include - -struct strip_zone -{ - sector_t zone_start; /* Zone offset in md_dev (in sectors) */ - sector_t dev_start; /* Zone offset in real dev (in sectors) */ - sector_t sectors; /* Zone size in sectors */ - int nb_dev; /* # of devices attached to the zone */ - mdk_rdev_t **dev; /* Devices attached to the zone */ -}; - -struct raid0_private_data -{ - struct strip_zone **hash_table; /* Table of indexes into strip_zone */ - struct strip_zone *strip_zone; - mdk_rdev_t **devlist; /* lists of rdevs, pointed to by strip_zone->dev */ - int nr_strip_zones; - - sector_t spacing; - int sector_shift; /* shift this before divide by spacing */ -}; - -typedef struct raid0_private_data raid0_conf_t; - -#define mddev_to_conf(mddev) ((raid0_conf_t *) mddev->private) - -#endif diff --git a/include/linux/raid/raid1.h b/include/linux/raid/raid1.h deleted file mode 100644 index 0a9ba7c3302..00000000000 --- a/include/linux/raid/raid1.h +++ /dev/null @@ -1,134 +0,0 @@ -#ifndef _RAID1_H -#define _RAID1_H - -#include - -typedef struct mirror_info mirror_info_t; - -struct mirror_info { - mdk_rdev_t *rdev; - sector_t head_position; -}; - -/* - * memory pools need a pointer to the mddev, so they can force an unplug - * when memory is tight, and a count of the number of drives that the - * pool was allocated for, so they know how much to allocate and free. - * mddev->raid_disks cannot be used, as it can change while a pool is active - * These two datums are stored in a kmalloced struct. - */ - -struct pool_info { - mddev_t *mddev; - int raid_disks; -}; - - -typedef struct r1bio_s r1bio_t; - -struct r1_private_data_s { - mddev_t *mddev; - mirror_info_t *mirrors; - int raid_disks; - int last_used; - sector_t next_seq_sect; - spinlock_t device_lock; - - struct list_head retry_list; - /* queue pending writes and submit them on unplug */ - struct bio_list pending_bio_list; - /* queue of writes that have been unplugged */ - struct bio_list flushing_bio_list; - - /* for use when syncing mirrors: */ - - spinlock_t resync_lock; - int nr_pending; - int nr_waiting; - int nr_queued; - int barrier; - sector_t next_resync; - int fullsync; /* set to 1 if a full sync is needed, - * (fresh device added). - * Cleared when a sync completes. - */ - - wait_queue_head_t wait_barrier; - - struct pool_info *poolinfo; - - struct page *tmppage; - - mempool_t *r1bio_pool; - mempool_t *r1buf_pool; -}; - -typedef struct r1_private_data_s conf_t; - -/* - * this is the only point in the RAID code where we violate - * C type safety. mddev->private is an 'opaque' pointer. - */ -#define mddev_to_conf(mddev) ((conf_t *) mddev->private) - -/* - * this is our 'private' RAID1 bio. - * - * it contains information about what kind of IO operations were started - * for this RAID1 operation, and about their status: - */ - -struct r1bio_s { - atomic_t remaining; /* 'have we finished' count, - * used from IRQ handlers - */ - atomic_t behind_remaining; /* number of write-behind ios remaining - * in this BehindIO request - */ - sector_t sector; - int sectors; - unsigned long state; - mddev_t *mddev; - /* - * original bio going to /dev/mdx - */ - struct bio *master_bio; - /* - * if the IO is in READ direction, then this is where we read - */ - int read_disk; - - struct list_head retry_list; - struct bitmap_update *bitmap_update; - /* - * if the IO is in WRITE direction, then multiple bios are used. - * We choose the number when they are allocated. - */ - struct bio *bios[0]; - /* DO NOT PUT ANY NEW FIELDS HERE - bios array is contiguously alloced*/ -}; - -/* when we get a read error on a read-only array, we redirect to another - * device without failing the first device, or trying to over-write to - * correct the read error. To keep track of bad blocks on a per-bio - * level, we store IO_BLOCKED in the appropriate 'bios' pointer - */ -#define IO_BLOCKED ((struct bio*)1) - -/* bits for r1bio.state */ -#define R1BIO_Uptodate 0 -#define R1BIO_IsSync 1 -#define R1BIO_Degraded 2 -#define R1BIO_BehindIO 3 -#define R1BIO_Barrier 4 -#define R1BIO_BarrierRetry 5 -/* For write-behind requests, we call bi_end_io when - * the last non-write-behind device completes, providing - * any write was successful. Otherwise we call when - * any write-behind write succeeds, otherwise we call - * with failure when last write completes (and all failed). - * Record that bi_end_io was called with this flag... - */ -#define R1BIO_Returned 6 - -#endif diff --git a/include/linux/raid/raid10.h b/include/linux/raid/raid10.h deleted file mode 100644 index e9091cfeb28..00000000000 --- a/include/linux/raid/raid10.h +++ /dev/null @@ -1,123 +0,0 @@ -#ifndef _RAID10_H -#define _RAID10_H - -#include - -typedef struct mirror_info mirror_info_t; - -struct mirror_info { - mdk_rdev_t *rdev; - sector_t head_position; -}; - -typedef struct r10bio_s r10bio_t; - -struct r10_private_data_s { - mddev_t *mddev; - mirror_info_t *mirrors; - int raid_disks; - spinlock_t device_lock; - - /* geometry */ - int near_copies; /* number of copies layed out raid0 style */ - int far_copies; /* number of copies layed out - * at large strides across drives - */ - int far_offset; /* far_copies are offset by 1 stripe - * instead of many - */ - int copies; /* near_copies * far_copies. - * must be <= raid_disks - */ - sector_t stride; /* distance between far copies. - * This is size / far_copies unless - * far_offset, in which case it is - * 1 stripe. - */ - - int chunk_shift; /* shift from chunks to sectors */ - sector_t chunk_mask; - - struct list_head retry_list; - /* queue pending writes and submit them on unplug */ - struct bio_list pending_bio_list; - - - spinlock_t resync_lock; - int nr_pending; - int nr_waiting; - int nr_queued; - int barrier; - sector_t next_resync; - int fullsync; /* set to 1 if a full sync is needed, - * (fresh device added). - * Cleared when a sync completes. - */ - - wait_queue_head_t wait_barrier; - - mempool_t *r10bio_pool; - mempool_t *r10buf_pool; - struct page *tmppage; -}; - -typedef struct r10_private_data_s conf_t; - -/* - * this is the only point in the RAID code where we violate - * C type safety. mddev->private is an 'opaque' pointer. - */ -#define mddev_to_conf(mddev) ((conf_t *) mddev->private) - -/* - * this is our 'private' RAID10 bio. - * - * it contains information about what kind of IO operations were started - * for this RAID10 operation, and about their status: - */ - -struct r10bio_s { - atomic_t remaining; /* 'have we finished' count, - * used from IRQ handlers - */ - sector_t sector; /* virtual sector number */ - int sectors; - unsigned long state; - mddev_t *mddev; - /* - * original bio going to /dev/mdx - */ - struct bio *master_bio; - /* - * if the IO is in READ direction, then this is where we read - */ - int read_slot; - - struct list_head retry_list; - /* - * if the IO is in WRITE direction, then multiple bios are used, - * one for each copy. - * When resyncing we also use one for each copy. - * When reconstructing, we use 2 bios, one for read, one for write. - * We choose the number when they are allocated. - */ - struct { - struct bio *bio; - sector_t addr; - int devnum; - } devs[0]; -}; - -/* when we get a read error on a read-only array, we redirect to another - * device without failing the first device, or trying to over-write to - * correct the read error. To keep track of bad blocks on a per-bio - * level, we store IO_BLOCKED in the appropriate 'bios' pointer - */ -#define IO_BLOCKED ((struct bio*)1) - -/* bits for r10bio.state */ -#define R10BIO_Uptodate 0 -#define R10BIO_IsSync 1 -#define R10BIO_IsRecover 2 -#define R10BIO_Degraded 3 -#endif diff --git a/include/linux/raid/raid5.h b/include/linux/raid/raid5.h deleted file mode 100644 index 3b267279245..00000000000 --- a/include/linux/raid/raid5.h +++ /dev/null @@ -1,402 +0,0 @@ -#ifndef _RAID5_H -#define _RAID5_H - -#include -#include - -/* - * - * Each stripe contains one buffer per disc. Each buffer can be in - * one of a number of states stored in "flags". Changes between - * these states happen *almost* exclusively under a per-stripe - * spinlock. Some very specific changes can happen in bi_end_io, and - * these are not protected by the spin lock. - * - * The flag bits that are used to represent these states are: - * R5_UPTODATE and R5_LOCKED - * - * State Empty == !UPTODATE, !LOCK - * We have no data, and there is no active request - * State Want == !UPTODATE, LOCK - * A read request is being submitted for this block - * State Dirty == UPTODATE, LOCK - * Some new data is in this buffer, and it is being written out - * State Clean == UPTODATE, !LOCK - * We have valid data which is the same as on disc - * - * The possible state transitions are: - * - * Empty -> Want - on read or write to get old data for parity calc - * Empty -> Dirty - on compute_parity to satisfy write/sync request.(RECONSTRUCT_WRITE) - * Empty -> Clean - on compute_block when computing a block for failed drive - * Want -> Empty - on failed read - * Want -> Clean - on successful completion of read request - * Dirty -> Clean - on successful completion of write request - * Dirty -> Clean - on failed write - * Clean -> Dirty - on compute_parity to satisfy write/sync (RECONSTRUCT or RMW) - * - * The Want->Empty, Want->Clean, Dirty->Clean, transitions - * all happen in b_end_io at interrupt time. - * Each sets the Uptodate bit before releasing the Lock bit. - * This leaves one multi-stage transition: - * Want->Dirty->Clean - * This is safe because thinking that a Clean buffer is actually dirty - * will at worst delay some action, and the stripe will be scheduled - * for attention after the transition is complete. - * - * There is one possibility that is not covered by these states. That - * is if one drive has failed and there is a spare being rebuilt. We - * can't distinguish between a clean block that has been generated - * from parity calculations, and a clean block that has been - * successfully written to the spare ( or to parity when resyncing). - * To distingush these states we have a stripe bit STRIPE_INSYNC that - * is set whenever a write is scheduled to the spare, or to the parity - * disc if there is no spare. A sync request clears this bit, and - * when we find it set with no buffers locked, we know the sync is - * complete. - * - * Buffers for the md device that arrive via make_request are attached - * to the appropriate stripe in one of two lists linked on b_reqnext. - * One list (bh_read) for read requests, one (bh_write) for write. - * There should never be more than one buffer on the two lists - * together, but we are not guaranteed of that so we allow for more. - * - * If a buffer is on the read list when the associated cache buffer is - * Uptodate, the data is copied into the read buffer and it's b_end_io - * routine is called. This may happen in the end_request routine only - * if the buffer has just successfully been read. end_request should - * remove the buffers from the list and then set the Uptodate bit on - * the buffer. Other threads may do this only if they first check - * that the Uptodate bit is set. Once they have checked that they may - * take buffers off the read queue. - * - * When a buffer on the write list is committed for write it is copied - * into the cache buffer, which is then marked dirty, and moved onto a - * third list, the written list (bh_written). Once both the parity - * block and the cached buffer are successfully written, any buffer on - * a written list can be returned with b_end_io. - * - * The write list and read list both act as fifos. The read list is - * protected by the device_lock. The write and written lists are - * protected by the stripe lock. The device_lock, which can be - * claimed while the stipe lock is held, is only for list - * manipulations and will only be held for a very short time. It can - * be claimed from interrupts. - * - * - * Stripes in the stripe cache can be on one of two lists (or on - * neither). The "inactive_list" contains stripes which are not - * currently being used for any request. They can freely be reused - * for another stripe. The "handle_list" contains stripes that need - * to be handled in some way. Both of these are fifo queues. Each - * stripe is also (potentially) linked to a hash bucket in the hash - * table so that it can be found by sector number. Stripes that are - * not hashed must be on the inactive_list, and will normally be at - * the front. All stripes start life this way. - * - * The inactive_list, handle_list and hash bucket lists are all protected by the - * device_lock. - * - stripes on the inactive_list never have their stripe_lock held. - * - stripes have a reference counter. If count==0, they are on a list. - * - If a stripe might need handling, STRIPE_HANDLE is set. - * - When refcount reaches zero, then if STRIPE_HANDLE it is put on - * handle_list else inactive_list - * - * This, combined with the fact that STRIPE_HANDLE is only ever - * cleared while a stripe has a non-zero count means that if the - * refcount is 0 and STRIPE_HANDLE is set, then it is on the - * handle_list and if recount is 0 and STRIPE_HANDLE is not set, then - * the stripe is on inactive_list. - * - * The possible transitions are: - * activate an unhashed/inactive stripe (get_active_stripe()) - * lockdev check-hash unlink-stripe cnt++ clean-stripe hash-stripe unlockdev - * activate a hashed, possibly active stripe (get_active_stripe()) - * lockdev check-hash if(!cnt++)unlink-stripe unlockdev - * attach a request to an active stripe (add_stripe_bh()) - * lockdev attach-buffer unlockdev - * handle a stripe (handle_stripe()) - * lockstripe clrSTRIPE_HANDLE ... - * (lockdev check-buffers unlockdev) .. - * change-state .. - * record io/ops needed unlockstripe schedule io/ops - * release an active stripe (release_stripe()) - * lockdev if (!--cnt) { if STRIPE_HANDLE, add to handle_list else add to inactive-list } unlockdev - * - * The refcount counts each thread that have activated the stripe, - * plus raid5d if it is handling it, plus one for each active request - * on a cached buffer, and plus one if the stripe is undergoing stripe - * operations. - * - * Stripe operations are performed outside the stripe lock, - * the stripe operations are: - * -copying data between the stripe cache and user application buffers - * -computing blocks to save a disk access, or to recover a missing block - * -updating the parity on a write operation (reconstruct write and - * read-modify-write) - * -checking parity correctness - * -running i/o to disk - * These operations are carried out by raid5_run_ops which uses the async_tx - * api to (optionally) offload operations to dedicated hardware engines. - * When requesting an operation handle_stripe sets the pending bit for the - * operation and increments the count. raid5_run_ops is then run whenever - * the count is non-zero. - * There are some critical dependencies between the operations that prevent some - * from being requested while another is in flight. - * 1/ Parity check operations destroy the in cache version of the parity block, - * so we prevent parity dependent operations like writes and compute_blocks - * from starting while a check is in progress. Some dma engines can perform - * the check without damaging the parity block, in these cases the parity - * block is re-marked up to date (assuming the check was successful) and is - * not re-read from disk. - * 2/ When a write operation is requested we immediately lock the affected - * blocks, and mark them as not up to date. This causes new read requests - * to be held off, as well as parity checks and compute block operations. - * 3/ Once a compute block operation has been requested handle_stripe treats - * that block as if it is up to date. raid5_run_ops guaruntees that any - * operation that is dependent on the compute block result is initiated after - * the compute block completes. - */ - -/* - * Operations state - intermediate states that are visible outside of sh->lock - * In general _idle indicates nothing is running, _run indicates a data - * processing operation is active, and _result means the data processing result - * is stable and can be acted upon. For simple operations like biofill and - * compute that only have an _idle and _run state they are indicated with - * sh->state flags (STRIPE_BIOFILL_RUN and STRIPE_COMPUTE_RUN) - */ -/** - * enum check_states - handles syncing / repairing a stripe - * @check_state_idle - check operations are quiesced - * @check_state_run - check operation is running - * @check_state_result - set outside lock when check result is valid - * @check_state_compute_run - check failed and we are repairing - * @check_state_compute_result - set outside lock when compute result is valid - */ -enum check_states { - check_state_idle = 0, - check_state_run, /* parity check */ - check_state_check_result, - check_state_compute_run, /* parity repair */ - check_state_compute_result, -}; - -/** - * enum reconstruct_states - handles writing or expanding a stripe - */ -enum reconstruct_states { - reconstruct_state_idle = 0, - reconstruct_state_prexor_drain_run, /* prexor-write */ - reconstruct_state_drain_run, /* write */ - reconstruct_state_run, /* expand */ - reconstruct_state_prexor_drain_result, - reconstruct_state_drain_result, - reconstruct_state_result, -}; - -struct stripe_head { - struct hlist_node hash; - struct list_head lru; /* inactive_list or handle_list */ - struct raid5_private_data *raid_conf; - sector_t sector; /* sector of this row */ - int pd_idx; /* parity disk index */ - unsigned long state; /* state flags */ - atomic_t count; /* nr of active thread/requests */ - spinlock_t lock; - int bm_seq; /* sequence number for bitmap flushes */ - int disks; /* disks in stripe */ - enum check_states check_state; - enum reconstruct_states reconstruct_state; - /* stripe_operations - * @target - STRIPE_OP_COMPUTE_BLK target - */ - struct stripe_operations { - int target; - u32 zero_sum_result; - } ops; - struct r5dev { - struct bio req; - struct bio_vec vec; - struct page *page; - struct bio *toread, *read, *towrite, *written; - sector_t sector; /* sector of this page */ - unsigned long flags; - } dev[1]; /* allocated with extra space depending of RAID geometry */ -}; - -/* stripe_head_state - collects and tracks the dynamic state of a stripe_head - * for handle_stripe. It is only valid under spin_lock(sh->lock); - */ -struct stripe_head_state { - int syncing, expanding, expanded; - int locked, uptodate, to_read, to_write, failed, written; - int to_fill, compute, req_compute, non_overwrite; - int failed_num; - unsigned long ops_request; -}; - -/* r6_state - extra state data only relevant to r6 */ -struct r6_state { - int p_failed, q_failed, qd_idx, failed_num[2]; -}; - -/* Flags */ -#define R5_UPTODATE 0 /* page contains current data */ -#define R5_LOCKED 1 /* IO has been submitted on "req" */ -#define R5_OVERWRITE 2 /* towrite covers whole page */ -/* and some that are internal to handle_stripe */ -#define R5_Insync 3 /* rdev && rdev->in_sync at start */ -#define R5_Wantread 4 /* want to schedule a read */ -#define R5_Wantwrite 5 -#define R5_Overlap 7 /* There is a pending overlapping request on this block */ -#define R5_ReadError 8 /* seen a read error here recently */ -#define R5_ReWrite 9 /* have tried to over-write the readerror */ - -#define R5_Expanded 10 /* This block now has post-expand data */ -#define R5_Wantcompute 11 /* compute_block in progress treat as - * uptodate - */ -#define R5_Wantfill 12 /* dev->toread contains a bio that needs - * filling - */ -#define R5_Wantdrain 13 /* dev->towrite needs to be drained */ -/* - * Write method - */ -#define RECONSTRUCT_WRITE 1 -#define READ_MODIFY_WRITE 2 -/* not a write method, but a compute_parity mode */ -#define CHECK_PARITY 3 - -/* - * Stripe state - */ -#define STRIPE_HANDLE 2 -#define STRIPE_SYNCING 3 -#define STRIPE_INSYNC 4 -#define STRIPE_PREREAD_ACTIVE 5 -#define STRIPE_DELAYED 6 -#define STRIPE_DEGRADED 7 -#define STRIPE_BIT_DELAY 8 -#define STRIPE_EXPANDING 9 -#define STRIPE_EXPAND_SOURCE 10 -#define STRIPE_EXPAND_READY 11 -#define STRIPE_IO_STARTED 12 /* do not count towards 'bypass_count' */ -#define STRIPE_FULL_WRITE 13 /* all blocks are set to be overwritten */ -#define STRIPE_BIOFILL_RUN 14 -#define STRIPE_COMPUTE_RUN 15 -/* - * Operation request flags - */ -#define STRIPE_OP_BIOFILL 0 -#define STRIPE_OP_COMPUTE_BLK 1 -#define STRIPE_OP_PREXOR 2 -#define STRIPE_OP_BIODRAIN 3 -#define STRIPE_OP_POSTXOR 4 -#define STRIPE_OP_CHECK 5 - -/* - * Plugging: - * - * To improve write throughput, we need to delay the handling of some - * stripes until there has been a chance that several write requests - * for the one stripe have all been collected. - * In particular, any write request that would require pre-reading - * is put on a "delayed" queue until there are no stripes currently - * in a pre-read phase. Further, if the "delayed" queue is empty when - * a stripe is put on it then we "plug" the queue and do not process it - * until an unplug call is made. (the unplug_io_fn() is called). - * - * When preread is initiated on a stripe, we set PREREAD_ACTIVE and add - * it to the count of prereading stripes. - * When write is initiated, or the stripe refcnt == 0 (just in case) we - * clear the PREREAD_ACTIVE flag and decrement the count - * Whenever the 'handle' queue is empty and the device is not plugged, we - * move any strips from delayed to handle and clear the DELAYED flag and set - * PREREAD_ACTIVE. - * In stripe_handle, if we find pre-reading is necessary, we do it if - * PREREAD_ACTIVE is set, else we set DELAYED which will send it to the delayed queue. - * HANDLE gets cleared if stripe_handle leave nothing locked. - */ - - -struct disk_info { - mdk_rdev_t *rdev; -}; - -struct raid5_private_data { - struct hlist_head *stripe_hashtbl; - mddev_t *mddev; - struct disk_info *spare; - int chunk_size, level, algorithm; - int max_degraded; - int raid_disks; - int max_nr_stripes; - - /* used during an expand */ - sector_t expand_progress; /* MaxSector when no expand happening */ - sector_t expand_lo; /* from here up to expand_progress it out-of-bounds - * as we haven't flushed the metadata yet - */ - int previous_raid_disks; - - struct list_head handle_list; /* stripes needing handling */ - struct list_head hold_list; /* preread ready stripes */ - struct list_head delayed_list; /* stripes that have plugged requests */ - struct list_head bitmap_list; /* stripes delaying awaiting bitmap update */ - struct bio *retry_read_aligned; /* currently retrying aligned bios */ - struct bio *retry_read_aligned_list; /* aligned bios retry list */ - atomic_t preread_active_stripes; /* stripes with scheduled io */ - atomic_t active_aligned_reads; - atomic_t pending_full_writes; /* full write backlog */ - int bypass_count; /* bypassed prereads */ - int bypass_threshold; /* preread nice */ - struct list_head *last_hold; /* detect hold_list promotions */ - - atomic_t reshape_stripes; /* stripes with pending writes for reshape */ - /* unfortunately we need two cache names as we temporarily have - * two caches. - */ - int active_name; - char cache_name[2][20]; - struct kmem_cache *slab_cache; /* for allocating stripes */ - - int seq_flush, seq_write; - int quiesce; - - int fullsync; /* set to 1 if a full sync is needed, - * (fresh device added). - * Cleared when a sync completes. - */ - - struct page *spare_page; /* Used when checking P/Q in raid6 */ - - /* - * Free stripes pool - */ - atomic_t active_stripes; - struct list_head inactive_list; - wait_queue_head_t wait_for_stripe; - wait_queue_head_t wait_for_overlap; - int inactive_blocked; /* release of inactive stripes blocked, - * waiting for 25% to be free - */ - int pool_size; /* number of disks in stripeheads in pool */ - spinlock_t device_lock; - struct disk_info *disks; -}; - -typedef struct raid5_private_data raid5_conf_t; - -#define mddev_to_conf(mddev) ((raid5_conf_t *) mddev->private) - -/* - * Our supported algorithms - */ -#define ALGORITHM_LEFT_ASYMMETRIC 0 -#define ALGORITHM_RIGHT_ASYMMETRIC 1 -#define ALGORITHM_LEFT_SYMMETRIC 2 -#define ALGORITHM_RIGHT_SYMMETRIC 3 - -#endif -- cgit v1.2.3 From 8b2b5c217c20b5460218ab8731295f2e46c7dd29 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 31 Mar 2009 14:27:03 +1100 Subject: md: move LEVEL_* definition from md_k.h to md_u.h .. as they are part of the user-space interface. Also move MdpMinorShift into there so we can remove duplication. Lastly move mdp_major in. It is less obviously part of the user-space interface, but do_mounts_md.c uses it, and it is acting a bit like user-space. Signed-off-by: NeilBrown --- include/linux/raid/md.h | 2 -- include/linux/raid/md_k.h | 10 ---------- include/linux/raid/md_u.h | 17 +++++++++++++++++ 3 files changed, 17 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/raid/md.h b/include/linux/raid/md.h index 82bea14cae1..8bfaf6b1d30 100644 --- a/include/linux/raid/md.h +++ b/include/linux/raid/md.h @@ -52,8 +52,6 @@ */ #define MD_PATCHLEVEL_VERSION 3 -extern int mdp_major; - extern int register_md_personality(struct mdk_personality *p); extern int unregister_md_personality(struct mdk_personality *p); extern mdk_thread_t * md_register_thread(void (*run) (mddev_t *mddev), diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h index 4aedb9fe2bd..758ec2842d9 100644 --- a/include/linux/raid/md_k.h +++ b/include/linux/raid/md_k.h @@ -20,16 +20,6 @@ #ifdef CONFIG_BLOCK -#define LEVEL_MULTIPATH (-4) -#define LEVEL_LINEAR (-1) -#define LEVEL_FAULTY (-5) - -/* we need a value for 'no level specified' and 0 - * means 'raid0', so we need something else. This is - * for internal use only - */ -#define LEVEL_NONE (-1000000) - #define MaxSector (~(sector_t)0) typedef struct mddev_s mddev_t; diff --git a/include/linux/raid/md_u.h b/include/linux/raid/md_u.h index 7192035fc4b..2f824aa889f 100644 --- a/include/linux/raid/md_u.h +++ b/include/linux/raid/md_u.h @@ -46,6 +46,12 @@ #define STOP_ARRAY_RO _IO (MD_MAJOR, 0x33) #define RESTART_ARRAY_RW _IO (MD_MAJOR, 0x34) +/* 63 partitions with the alternate major number (mdp) */ +#define MdpMinorShift 6 +#ifdef __KERNEL__ +extern int mdp_major; +#endif + typedef struct mdu_version_s { int major; int minor; @@ -85,6 +91,17 @@ typedef struct mdu_array_info_s { } mdu_array_info_t; +/* non-obvious values for 'level' */ +#define LEVEL_MULTIPATH (-4) +#define LEVEL_LINEAR (-1) +#define LEVEL_FAULTY (-5) + +/* we need a value for 'no level specified' and 0 + * means 'raid0', so we need something else. This is + * for internal use only + */ +#define LEVEL_NONE (-1000000) + typedef struct mdu_disk_info_s { /* * configuration/status of one particular disk -- cgit v1.2.3 From 92022950c6b1bb3da90b2976b20271cdfd98b8a3 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 31 Mar 2009 14:33:13 +1100 Subject: md: move most content from md.h to md_k.h The extern function definitions are kernel-internal definitions, so they belong in md_k.h The MD_*_VERSION values could reasonably go in a number of places, but md_u.h seems most reasonable. This leaves almost nothing in md.h. It will go soon. Signed-off-by: NeilBrown --- include/linux/raid/md.h | 40 ---------------------------------------- include/linux/raid/md_k.h | 22 ++++++++++++++++++++++ include/linux/raid/md_u.h | 18 ++++++++++++++++++ 3 files changed, 40 insertions(+), 40 deletions(-) (limited to 'include/linux') diff --git a/include/linux/raid/md.h b/include/linux/raid/md.h index 8bfaf6b1d30..71c4fd19c31 100644 --- a/include/linux/raid/md.h +++ b/include/linux/raid/md.h @@ -34,46 +34,6 @@ #ifdef CONFIG_MD -/* - * Different major versions are not compatible. - * Different minor versions are only downward compatible. - * Different patchlevel versions are downward and upward compatible. - */ -#define MD_MAJOR_VERSION 0 -#define MD_MINOR_VERSION 90 -/* - * MD_PATCHLEVEL_VERSION indicates kernel functionality. - * >=1 means different superblock formats are selectable using SET_ARRAY_INFO - * and major_version/minor_version accordingly - * >=2 means that Internal bitmaps are supported by setting MD_SB_BITMAP_PRESENT - * in the super status byte - * >=3 means that bitmap superblock version 4 is supported, which uses - * little-ending representation rather than host-endian - */ -#define MD_PATCHLEVEL_VERSION 3 - -extern int register_md_personality(struct mdk_personality *p); -extern int unregister_md_personality(struct mdk_personality *p); -extern mdk_thread_t * md_register_thread(void (*run) (mddev_t *mddev), - mddev_t *mddev, const char *name); -extern void md_unregister_thread(mdk_thread_t *thread); -extern void md_wakeup_thread(mdk_thread_t *thread); -extern void md_check_recovery(mddev_t *mddev); -extern void md_write_start(mddev_t *mddev, struct bio *bi); -extern void md_write_end(mddev_t *mddev); -extern void md_done_sync(mddev_t *mddev, int blocks, int ok); -extern void md_error(mddev_t *mddev, mdk_rdev_t *rdev); - -extern void md_super_write(mddev_t *mddev, mdk_rdev_t *rdev, - sector_t sector, int size, struct page *page); -extern void md_super_wait(mddev_t *mddev); -extern int sync_page_io(struct block_device *bdev, sector_t sector, int size, - struct page *page, int rw); -extern void md_do_sync(mddev_t *mddev); -extern void md_new_event(mddev_t *mddev); -extern int md_allow_write(mddev_t *mddev); -extern void md_wait_for_blocked_rdev(mdk_rdev_t *rdev, mddev_t *mddev); - #endif /* CONFIG_MD */ #endif diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h index 758ec2842d9..4c5e2d00ff5 100644 --- a/include/linux/raid/md_k.h +++ b/include/linux/raid/md_k.h @@ -390,3 +390,25 @@ static inline void safe_put_page(struct page *p) #endif /* CONFIG_BLOCK */ #endif + +extern int register_md_personality(struct mdk_personality *p); +extern int unregister_md_personality(struct mdk_personality *p); +extern mdk_thread_t * md_register_thread(void (*run) (mddev_t *mddev), + mddev_t *mddev, const char *name); +extern void md_unregister_thread(mdk_thread_t *thread); +extern void md_wakeup_thread(mdk_thread_t *thread); +extern void md_check_recovery(mddev_t *mddev); +extern void md_write_start(mddev_t *mddev, struct bio *bi); +extern void md_write_end(mddev_t *mddev); +extern void md_done_sync(mddev_t *mddev, int blocks, int ok); +extern void md_error(mddev_t *mddev, mdk_rdev_t *rdev); + +extern void md_super_write(mddev_t *mddev, mdk_rdev_t *rdev, + sector_t sector, int size, struct page *page); +extern void md_super_wait(mddev_t *mddev); +extern int sync_page_io(struct block_device *bdev, sector_t sector, int size, + struct page *page, int rw); +extern void md_do_sync(mddev_t *mddev); +extern void md_new_event(mddev_t *mddev); +extern int md_allow_write(mddev_t *mddev); +extern void md_wait_for_blocked_rdev(mdk_rdev_t *rdev, mddev_t *mddev); diff --git a/include/linux/raid/md_u.h b/include/linux/raid/md_u.h index 2f824aa889f..fb1abb3367e 100644 --- a/include/linux/raid/md_u.h +++ b/include/linux/raid/md_u.h @@ -15,6 +15,24 @@ #ifndef _MD_U_H #define _MD_U_H +/* + * Different major versions are not compatible. + * Different minor versions are only downward compatible. + * Different patchlevel versions are downward and upward compatible. + */ +#define MD_MAJOR_VERSION 0 +#define MD_MINOR_VERSION 90 +/* + * MD_PATCHLEVEL_VERSION indicates kernel functionality. + * >=1 means different superblock formats are selectable using SET_ARRAY_INFO + * and major_version/minor_version accordingly + * >=2 means that Internal bitmaps are supported by setting MD_SB_BITMAP_PRESENT + * in the super status byte + * >=3 means that bitmap superblock version 4 is supported, which uses + * little-ending representation rather than host-endian + */ +#define MD_PATCHLEVEL_VERSION 3 + /* ioctls */ /* status */ -- cgit v1.2.3 From bff61975b3d6c18ee31457cc5b4d73042f44915f Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 31 Mar 2009 14:33:13 +1100 Subject: md: move lots of #include lines out of .h files and into .c This makes the includes more explicit, and is preparation for moving md_k.h to drivers/md/md.h Remove include/raid/md.h as its only remaining use was to #include other files. Signed-off-by: NeilBrown --- include/linux/raid/md.h | 39 --------------------------------------- include/linux/raid/md_k.h | 3 --- include/linux/raid/xor.h | 2 -- 3 files changed, 44 deletions(-) delete mode 100644 include/linux/raid/md.h (limited to 'include/linux') diff --git a/include/linux/raid/md.h b/include/linux/raid/md.h deleted file mode 100644 index 71c4fd19c31..00000000000 --- a/include/linux/raid/md.h +++ /dev/null @@ -1,39 +0,0 @@ -/* - md.h : Multiple Devices driver for Linux - Copyright (C) 1996-98 Ingo Molnar, Gadi Oxman - Copyright (C) 1994-96 Marc ZYNGIER - or - - - This program is free software; you can redistribute it and/or modify - it under the terms of the GNU General Public License as published by - the Free Software Foundation; either version 2, or (at your option) - any later version. - - You should have received a copy of the GNU General Public License - (for example /usr/src/linux/COPYING); if not, write to the Free - Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. -*/ - -#ifndef _MD_H -#define _MD_H - -#include -#include - -/* - * 'md_p.h' holds the 'physical' layout of RAID devices - * 'md_u.h' holds the user <=> kernel API - * - * 'md_k.h' holds kernel internal definitions - */ - -#include -#include -#include - -#ifdef CONFIG_MD - -#endif /* CONFIG_MD */ -#endif - diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h index 4c5e2d00ff5..e78b3c1d55f 100644 --- a/include/linux/raid/md_k.h +++ b/include/linux/raid/md_k.h @@ -15,9 +15,6 @@ #ifndef _MD_K_H #define _MD_K_H -/* and dm-bio-list.h is not under include/linux because.... ??? */ -#include "../../../drivers/md/dm-bio-list.h" - #ifdef CONFIG_BLOCK #define MaxSector (~(sector_t)0) diff --git a/include/linux/raid/xor.h b/include/linux/raid/xor.h index 3e120587ead..5a210959e3f 100644 --- a/include/linux/raid/xor.h +++ b/include/linux/raid/xor.h @@ -1,8 +1,6 @@ #ifndef _XOR_H #define _XOR_H -#include - #define MAX_XOR_BLOCKS 4 extern void xor_blocks(unsigned int count, unsigned int bytes, -- cgit v1.2.3 From 43b2e5d86d8bdd77386226db0bc961529492c043 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 31 Mar 2009 14:33:13 +1100 Subject: md: move md_k.h from include/linux/raid/ to drivers/md/ It really is nicer to keep related code together.. Signed-off-by: NeilBrown --- include/linux/raid/md_k.h | 411 ---------------------------------------------- 1 file changed, 411 deletions(-) delete mode 100644 include/linux/raid/md_k.h (limited to 'include/linux') diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h deleted file mode 100644 index e78b3c1d55f..00000000000 --- a/include/linux/raid/md_k.h +++ /dev/null @@ -1,411 +0,0 @@ -/* - md_k.h : kernel internal structure of the Linux MD driver - Copyright (C) 1996-98 Ingo Molnar, Gadi Oxman - - This program is free software; you can redistribute it and/or modify - it under the terms of the GNU General Public License as published by - the Free Software Foundation; either version 2, or (at your option) - any later version. - - You should have received a copy of the GNU General Public License - (for example /usr/src/linux/COPYING); if not, write to the Free - Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. -*/ - -#ifndef _MD_K_H -#define _MD_K_H - -#ifdef CONFIG_BLOCK - -#define MaxSector (~(sector_t)0) - -typedef struct mddev_s mddev_t; -typedef struct mdk_rdev_s mdk_rdev_t; - -/* - * options passed in raidrun: - */ - -/* Currently this must fit in an 'int' */ -#define MAX_CHUNK_SIZE (1<<30) - -/* - * MD's 'extended' device - */ -struct mdk_rdev_s -{ - struct list_head same_set; /* RAID devices within the same set */ - - sector_t size; /* Device size (in blocks) */ - mddev_t *mddev; /* RAID array if running */ - int last_events; /* IO event timestamp */ - - struct block_device *bdev; /* block device handle */ - - struct page *sb_page; - int sb_loaded; - __u64 sb_events; - sector_t data_offset; /* start of data in array */ - sector_t sb_start; /* offset of the super block (in 512byte sectors) */ - int sb_size; /* bytes in the superblock */ - int preferred_minor; /* autorun support */ - - struct kobject kobj; - - /* A device can be in one of three states based on two flags: - * Not working: faulty==1 in_sync==0 - * Fully working: faulty==0 in_sync==1 - * Working, but not - * in sync with array - * faulty==0 in_sync==0 - * - * It can never have faulty==1, in_sync==1 - * This reduces the burden of testing multiple flags in many cases - */ - - unsigned long flags; -#define Faulty 1 /* device is known to have a fault */ -#define In_sync 2 /* device is in_sync with rest of array */ -#define WriteMostly 4 /* Avoid reading if at all possible */ -#define BarriersNotsupp 5 /* BIO_RW_BARRIER is not supported */ -#define AllReserved 6 /* If whole device is reserved for - * one array */ -#define AutoDetected 7 /* added by auto-detect */ -#define Blocked 8 /* An error occured on an externally - * managed array, don't allow writes - * until it is cleared */ -#define StateChanged 9 /* Faulty or Blocked has changed during - * interrupt, so it needs to be - * notified by the thread */ - wait_queue_head_t blocked_wait; - - int desc_nr; /* descriptor index in the superblock */ - int raid_disk; /* role of device in array */ - int saved_raid_disk; /* role that device used to have in the - * array and could again if we did a partial - * resync from the bitmap - */ - sector_t recovery_offset;/* If this device has been partially - * recovered, this is where we were - * up to. - */ - - atomic_t nr_pending; /* number of pending requests. - * only maintained for arrays that - * support hot removal - */ - atomic_t read_errors; /* number of consecutive read errors that - * we have tried to ignore. - */ - atomic_t corrected_errors; /* number of corrected read errors, - * for reporting to userspace and storing - * in superblock. - */ - struct work_struct del_work; /* used for delayed sysfs removal */ - - struct sysfs_dirent *sysfs_state; /* handle for 'state' - * sysfs entry */ -}; - -struct mddev_s -{ - void *private; - struct mdk_personality *pers; - dev_t unit; - int md_minor; - struct list_head disks; - unsigned long flags; -#define MD_CHANGE_DEVS 0 /* Some device status has changed */ -#define MD_CHANGE_CLEAN 1 /* transition to or from 'clean' */ -#define MD_CHANGE_PENDING 2 /* superblock update in progress */ - - int ro; - - struct gendisk *gendisk; - - struct kobject kobj; - int hold_active; -#define UNTIL_IOCTL 1 -#define UNTIL_STOP 2 - - /* Superblock information */ - int major_version, - minor_version, - patch_version; - int persistent; - int external; /* metadata is - * managed externally */ - char metadata_type[17]; /* externally set*/ - int chunk_size; - time_t ctime, utime; - int level, layout; - char clevel[16]; - int raid_disks; - int max_disks; - sector_t size; /* used size of component devices */ - sector_t array_sectors; /* exported array size */ - __u64 events; - - char uuid[16]; - - /* If the array is being reshaped, we need to record the - * new shape and an indication of where we are up to. - * This is written to the superblock. - * If reshape_position is MaxSector, then no reshape is happening (yet). - */ - sector_t reshape_position; - int delta_disks, new_level, new_layout, new_chunk; - - struct mdk_thread_s *thread; /* management thread */ - struct mdk_thread_s *sync_thread; /* doing resync or reconstruct */ - sector_t curr_resync; /* last block scheduled */ - unsigned long resync_mark; /* a recent timestamp */ - sector_t resync_mark_cnt;/* blocks written at resync_mark */ - sector_t curr_mark_cnt; /* blocks scheduled now */ - - sector_t resync_max_sectors; /* may be set by personality */ - - sector_t resync_mismatches; /* count of sectors where - * parity/replica mismatch found - */ - - /* allow user-space to request suspension of IO to regions of the array */ - sector_t suspend_lo; - sector_t suspend_hi; - /* if zero, use the system-wide default */ - int sync_speed_min; - int sync_speed_max; - - /* resync even though the same disks are shared among md-devices */ - int parallel_resync; - - int ok_start_degraded; - /* recovery/resync flags - * NEEDED: we might need to start a resync/recover - * RUNNING: a thread is running, or about to be started - * SYNC: actually doing a resync, not a recovery - * RECOVER: doing recovery, or need to try it. - * INTR: resync needs to be aborted for some reason - * DONE: thread is done and is waiting to be reaped - * REQUEST: user-space has requested a sync (used with SYNC) - * CHECK: user-space request for for check-only, no repair - * RESHAPE: A reshape is happening - * - * If neither SYNC or RESHAPE are set, then it is a recovery. - */ -#define MD_RECOVERY_RUNNING 0 -#define MD_RECOVERY_SYNC 1 -#define MD_RECOVERY_RECOVER 2 -#define MD_RECOVERY_INTR 3 -#define MD_RECOVERY_DONE 4 -#define MD_RECOVERY_NEEDED 5 -#define MD_RECOVERY_REQUESTED 6 -#define MD_RECOVERY_CHECK 7 -#define MD_RECOVERY_RESHAPE 8 -#define MD_RECOVERY_FROZEN 9 - - unsigned long recovery; - int recovery_disabled; /* if we detect that recovery - * will always fail, set this - * so we don't loop trying */ - - int in_sync; /* know to not need resync */ - struct mutex reconfig_mutex; - atomic_t active; /* general refcount */ - atomic_t openers; /* number of active opens */ - - int changed; /* true if we might need to reread partition info */ - int degraded; /* whether md should consider - * adding a spare - */ - int barriers_work; /* initialised to true, cleared as soon - * as a barrier request to slave - * fails. Only supported - */ - struct bio *biolist; /* bios that need to be retried - * because BIO_RW_BARRIER is not supported - */ - - atomic_t recovery_active; /* blocks scheduled, but not written */ - wait_queue_head_t recovery_wait; - sector_t recovery_cp; - sector_t resync_min; /* user requested sync - * starts here */ - sector_t resync_max; /* resync should pause - * when it gets here */ - - struct sysfs_dirent *sysfs_state; /* handle for 'array_state' - * file in sysfs. - */ - struct sysfs_dirent *sysfs_action; /* handle for 'sync_action' */ - - struct work_struct del_work; /* used for delayed sysfs removal */ - - spinlock_t write_lock; - wait_queue_head_t sb_wait; /* for waiting on superblock updates */ - atomic_t pending_writes; /* number of active superblock writes */ - - unsigned int safemode; /* if set, update "clean" superblock - * when no writes pending. - */ - unsigned int safemode_delay; - struct timer_list safemode_timer; - atomic_t writes_pending; - struct request_queue *queue; /* for plugging ... */ - - atomic_t write_behind; /* outstanding async IO */ - unsigned int max_write_behind; /* 0 = sync */ - - struct bitmap *bitmap; /* the bitmap for the device */ - struct file *bitmap_file; /* the bitmap file */ - long bitmap_offset; /* offset from superblock of - * start of bitmap. May be - * negative, but not '0' - */ - long default_bitmap_offset; /* this is the offset to use when - * hot-adding a bitmap. It should - * eventually be settable by sysfs. - */ - - struct list_head all_mddevs; -}; - - -static inline void rdev_dec_pending(mdk_rdev_t *rdev, mddev_t *mddev) -{ - int faulty = test_bit(Faulty, &rdev->flags); - if (atomic_dec_and_test(&rdev->nr_pending) && faulty) - set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); -} - -static inline void md_sync_acct(struct block_device *bdev, unsigned long nr_sectors) -{ - atomic_add(nr_sectors, &bdev->bd_contains->bd_disk->sync_io); -} - -struct mdk_personality -{ - char *name; - int level; - struct list_head list; - struct module *owner; - int (*make_request)(struct request_queue *q, struct bio *bio); - int (*run)(mddev_t *mddev); - int (*stop)(mddev_t *mddev); - void (*status)(struct seq_file *seq, mddev_t *mddev); - /* error_handler must set ->faulty and clear ->in_sync - * if appropriate, and should abort recovery if needed - */ - void (*error_handler)(mddev_t *mddev, mdk_rdev_t *rdev); - int (*hot_add_disk) (mddev_t *mddev, mdk_rdev_t *rdev); - int (*hot_remove_disk) (mddev_t *mddev, int number); - int (*spare_active) (mddev_t *mddev); - sector_t (*sync_request)(mddev_t *mddev, sector_t sector_nr, int *skipped, int go_faster); - int (*resize) (mddev_t *mddev, sector_t sectors); - int (*check_reshape) (mddev_t *mddev); - int (*start_reshape) (mddev_t *mddev); - int (*reconfig) (mddev_t *mddev, int layout, int chunk_size); - /* quiesce moves between quiescence states - * 0 - fully active - * 1 - no new requests allowed - * others - reserved - */ - void (*quiesce) (mddev_t *mddev, int state); -}; - - -struct md_sysfs_entry { - struct attribute attr; - ssize_t (*show)(mddev_t *, char *); - ssize_t (*store)(mddev_t *, const char *, size_t); -}; - - -static inline char * mdname (mddev_t * mddev) -{ - return mddev->gendisk ? mddev->gendisk->disk_name : "mdX"; -} - -/* - * iterates through some rdev ringlist. It's safe to remove the - * current 'rdev'. Dont touch 'tmp' though. - */ -#define rdev_for_each_list(rdev, tmp, head) \ - list_for_each_entry_safe(rdev, tmp, head, same_set) - -/* - * iterates through the 'same array disks' ringlist - */ -#define rdev_for_each(rdev, tmp, mddev) \ - list_for_each_entry_safe(rdev, tmp, &((mddev)->disks), same_set) - -#define rdev_for_each_rcu(rdev, mddev) \ - list_for_each_entry_rcu(rdev, &((mddev)->disks), same_set) - -typedef struct mdk_thread_s { - void (*run) (mddev_t *mddev); - mddev_t *mddev; - wait_queue_head_t wqueue; - unsigned long flags; - struct task_struct *tsk; - unsigned long timeout; -} mdk_thread_t; - -#define THREAD_WAKEUP 0 - -#define __wait_event_lock_irq(wq, condition, lock, cmd) \ -do { \ - wait_queue_t __wait; \ - init_waitqueue_entry(&__wait, current); \ - \ - add_wait_queue(&wq, &__wait); \ - for (;;) { \ - set_current_state(TASK_UNINTERRUPTIBLE); \ - if (condition) \ - break; \ - spin_unlock_irq(&lock); \ - cmd; \ - schedule(); \ - spin_lock_irq(&lock); \ - } \ - current->state = TASK_RUNNING; \ - remove_wait_queue(&wq, &__wait); \ -} while (0) - -#define wait_event_lock_irq(wq, condition, lock, cmd) \ -do { \ - if (condition) \ - break; \ - __wait_event_lock_irq(wq, condition, lock, cmd); \ -} while (0) - -static inline void safe_put_page(struct page *p) -{ - if (p) put_page(p); -} - -#endif /* CONFIG_BLOCK */ -#endif - - -extern int register_md_personality(struct mdk_personality *p); -extern int unregister_md_personality(struct mdk_personality *p); -extern mdk_thread_t * md_register_thread(void (*run) (mddev_t *mddev), - mddev_t *mddev, const char *name); -extern void md_unregister_thread(mdk_thread_t *thread); -extern void md_wakeup_thread(mdk_thread_t *thread); -extern void md_check_recovery(mddev_t *mddev); -extern void md_write_start(mddev_t *mddev, struct bio *bi); -extern void md_write_end(mddev_t *mddev); -extern void md_done_sync(mddev_t *mddev, int blocks, int ok); -extern void md_error(mddev_t *mddev, mdk_rdev_t *rdev); - -extern void md_super_write(mddev_t *mddev, mdk_rdev_t *rdev, - sector_t sector, int size, struct page *page); -extern void md_super_wait(mddev_t *mddev); -extern int sync_page_io(struct block_device *bdev, sector_t sector, int size, - struct page *page, int rw); -extern void md_do_sync(mddev_t *mddev); -extern void md_new_event(mddev_t *mddev); -extern int md_allow_write(mddev_t *mddev); -extern void md_wait_for_blocked_rdev(mdk_rdev_t *rdev, mddev_t *mddev); -- cgit v1.2.3 From f701d589aa34d7531183c9ac6f7713ba14212b02 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 31 Mar 2009 15:09:39 +1100 Subject: md/raid6: move raid6 data processing to raid6_pq.ko Move the raid6 data processing routines into a standalone module (raid6_pq) to prepare them to be called from async_tx wrappers and other non-md drivers/modules. This precludes a circular dependency of raid456 needing the async modules for data processing while those modules in turn depend on raid456 for the base level synchronous raid6 routines. To support this move: 1/ The exportable definitions in raid6.h move to include/linux/raid/pq.h 2/ The raid6_call, recovery calls, and table symbols are exported 3/ Extra #ifdef __KERNEL__ statements to enable the userspace raid6test to compile Signed-off-by: Dan Williams Signed-off-by: NeilBrown --- include/linux/raid/pq.h | 132 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 132 insertions(+) create mode 100644 include/linux/raid/pq.h (limited to 'include/linux') diff --git a/include/linux/raid/pq.h b/include/linux/raid/pq.h new file mode 100644 index 00000000000..d92480f8285 --- /dev/null +++ b/include/linux/raid/pq.h @@ -0,0 +1,132 @@ +/* -*- linux-c -*- ------------------------------------------------------- * + * + * Copyright 2003 H. Peter Anvin - All Rights Reserved + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, Inc., 53 Temple Place Ste 330, + * Boston MA 02111-1307, USA; either version 2 of the License, or + * (at your option) any later version; incorporated herein by reference. + * + * ----------------------------------------------------------------------- */ + +#ifndef LINUX_RAID_RAID6_H +#define LINUX_RAID_RAID6_H + +#ifdef __KERNEL__ + +/* Set to 1 to use kernel-wide empty_zero_page */ +#define RAID6_USE_EMPTY_ZERO_PAGE 0 +#include + +/* We need a pre-zeroed page... if we don't want to use the kernel-provided + one define it here */ +#if RAID6_USE_EMPTY_ZERO_PAGE +# define raid6_empty_zero_page empty_zero_page +#else +extern const char raid6_empty_zero_page[PAGE_SIZE]; +#endif + +#else /* ! __KERNEL__ */ +/* Used for testing in user space */ + +#include +#include +#include +#include +#include +#include + +/* Not standard, but glibc defines it */ +#define BITS_PER_LONG __WORDSIZE + +typedef uint8_t u8; +typedef uint16_t u16; +typedef uint32_t u32; +typedef uint64_t u64; + +#ifndef PAGE_SIZE +# define PAGE_SIZE 4096 +#endif +extern const char raid6_empty_zero_page[PAGE_SIZE]; + +#define __init +#define __exit +#define __attribute_const__ __attribute__((const)) +#define noinline __attribute__((noinline)) + +#define preempt_enable() +#define preempt_disable() +#define cpu_has_feature(x) 1 +#define enable_kernel_altivec() +#define disable_kernel_altivec() + +#define EXPORT_SYMBOL(sym) +#define MODULE_LICENSE(licence) +#define subsys_initcall(x) +#define module_exit(x) +#endif /* __KERNEL__ */ + +/* Routine choices */ +struct raid6_calls { + void (*gen_syndrome)(int, size_t, void **); + int (*valid)(void); /* Returns 1 if this routine set is usable */ + const char *name; /* Name of this routine set */ + int prefer; /* Has special performance attribute */ +}; + +/* Selected algorithm */ +extern struct raid6_calls raid6_call; + +/* Algorithm list */ +extern const struct raid6_calls * const raid6_algos[]; +int raid6_select_algo(void); + +/* Return values from chk_syndrome */ +#define RAID6_OK 0 +#define RAID6_P_BAD 1 +#define RAID6_Q_BAD 2 +#define RAID6_PQ_BAD 3 + +/* Galois field tables */ +extern const u8 raid6_gfmul[256][256] __attribute__((aligned(256))); +extern const u8 raid6_gfexp[256] __attribute__((aligned(256))); +extern const u8 raid6_gfinv[256] __attribute__((aligned(256))); +extern const u8 raid6_gfexi[256] __attribute__((aligned(256))); + +/* Recovery routines */ +void raid6_2data_recov(int disks, size_t bytes, int faila, int failb, + void **ptrs); +void raid6_datap_recov(int disks, size_t bytes, int faila, void **ptrs); +void raid6_dual_recov(int disks, size_t bytes, int faila, int failb, + void **ptrs); + +/* Some definitions to allow code to be compiled for testing in userspace */ +#ifndef __KERNEL__ + +# define jiffies raid6_jiffies() +# define printk printf +# define GFP_KERNEL 0 +# define __get_free_pages(x, y) ((unsigned long)mmap(NULL, PAGE_SIZE << (y), \ + PROT_READ|PROT_WRITE, \ + MAP_PRIVATE|MAP_ANONYMOUS,\ + 0, 0)) +# define free_pages(x, y) munmap((void *)(x), (y)*PAGE_SIZE) + +static inline void cpu_relax(void) +{ + /* Nothing */ +} + +#undef HZ +#define HZ 1000 +static inline uint32_t raid6_jiffies(void) +{ + struct timeval tv; + gettimeofday(&tv, NULL); + return tv.tv_sec*1000 + tv.tv_usec/1000; +} + +#endif /* ! __KERNEL__ */ + +#endif /* LINUX_RAID_RAID6_H */ -- cgit v1.2.3 From 853116a10544206b6b2cf42ebc9d78fba2668888 Mon Sep 17 00:00:00 2001 From: David Brownell Date: Wed, 14 Jan 2009 23:03:17 -0800 Subject: regulator: add get_status() Based on previous LKML discussions: * Update docs for regulator sysfs class attributes to highlight the fact that all current attributes are intended to be control inputs, including notably "state" and "opmode" which previously implied otherwise. * Define a new regulator driver get_status() method, which is the first method reporting regulator outputs instead of inputs. It can report on/off and error status; or instead of simply "on", report the actual operating mode. For the moment, this is a sysfs-only interface, not accessible to regulator clients. Such clients can use the current notification interfaces to detect errors, if the regulator reports them. Signed-off-by: David Brownell Signed-off-by: Liam Girdwood --- include/linux/regulator/driver.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 2dae05705f1..6e957aae762 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -21,6 +21,17 @@ struct regulator_dev; struct regulator_init_data; +enum regulator_status { + REGULATOR_STATUS_OFF, + REGULATOR_STATUS_ON, + REGULATOR_STATUS_ERROR, + /* fast/normal/idle/standby are flavors of "on" */ + REGULATOR_STATUS_FAST, + REGULATOR_STATUS_NORMAL, + REGULATOR_STATUS_IDLE, + REGULATOR_STATUS_STANDBY, +}; + /** * struct regulator_ops - regulator operations. * @@ -72,6 +83,12 @@ struct regulator_ops { int (*set_mode) (struct regulator_dev *, unsigned int mode); unsigned int (*get_mode) (struct regulator_dev *); + /* report regulator status ... most other accessors report + * control inputs, this reports results of combining inputs + * from Linux (and other sources) with the actual load. + */ + int (*get_status)(struct regulator_dev *); + /* get most efficient regulator operating mode for load */ unsigned int (*get_optimum_mode) (struct regulator_dev *, int input_uV, int output_uV, int load_uA); -- cgit v1.2.3 From b136fb4463d13eea129bf090a8a465bba6bf0003 Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Mon, 19 Jan 2009 18:20:58 +0000 Subject: Regulator: Push lock out of _notifier_call_chain + add voltage change event. Regulator: Push lock out of _notifier_call_chain and into caller functions (side effect of fixing deadlock in regulator_force_disable) + Add a voltage changed event. Signed-off-by: Jonathan Cameron Signed-off-by: Liam Girdwood --- include/linux/regulator/consumer.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index 801bf77ff4e..533f4e26db9 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -88,6 +88,7 @@ * FAIL Regulator output has failed. * OVER_TEMP Regulator over temp. * FORCE_DISABLE Regulator shut down by software. + * VOLTAGE_CHANGE Regulator voltage changed. * * NOTE: These events can be OR'ed together when passed into handler. */ @@ -98,6 +99,7 @@ #define REGULATOR_EVENT_FAIL 0x08 #define REGULATOR_EVENT_OVER_TEMP 0x10 #define REGULATOR_EVENT_FORCE_DISABLE 0x20 +#define REGULATOR_EVENT_VOLTAGE_CHANGE 0x40 struct regulator; -- cgit v1.2.3 From 0527100fd11d9710c7e153d791da78824b7b46fa Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 19 Jan 2009 13:37:02 +0000 Subject: regulator: Pass regulator init data as explict argument when registering Rather than having the regulator init data read from the platform_data member of the struct device that is registered for the regulator make the init data an explict argument passed in when registering. This allows drivers to use the platform data for their own purposes if they wish. Signed-off-by: Mark Brown Signed-off-by: Liam Girdwood --- include/linux/regulator/driver.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 6e957aae762..2254ad93b78 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -138,7 +138,8 @@ struct regulator_desc { }; struct regulator_dev *regulator_register(struct regulator_desc *regulator_desc, - struct device *dev, void *driver_data); + struct device *dev, struct regulator_init_data *init_data, + void *driver_data); void regulator_unregister(struct regulator_dev *rdev); int regulator_notifier_call_chain(struct regulator_dev *rdev, -- cgit v1.2.3 From 93c62da23a717f59933ec799688da42f71d8c6c4 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 19 Jan 2009 13:37:03 +0000 Subject: regulator: Allow init data to be supplied for bq24022 Previously it was not possible to do so, making it impossible for machines to configure the driver. Signed-off-by: Mark Brown Signed-off-by: Liam Girdwood --- include/linux/regulator/bq24022.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/bq24022.h b/include/linux/regulator/bq24022.h index e84b0a9feda..a6d014005d4 100644 --- a/include/linux/regulator/bq24022.h +++ b/include/linux/regulator/bq24022.h @@ -10,6 +10,8 @@ * */ +struct regulator_init_data; + /** * bq24022_mach_info - platform data for bq24022 * @gpio_nce: GPIO line connected to the nCE pin, used to enable / disable charging @@ -18,4 +20,5 @@ struct bq24022_mach_info { int gpio_nce; int gpio_iset2; + struct regulator_init_data *init_data; }; -- cgit v1.2.3 From bcf3402c50a48d51462f37f72129d9c4369702b4 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 19 Jan 2009 13:37:04 +0000 Subject: regulator: Allow init_data to be passed to fixed voltage regulators Signed-off-by: Mark Brown Signed-off-by: Liam Girdwood --- include/linux/regulator/fixed.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/fixed.h b/include/linux/regulator/fixed.h index 1387a5d2190..91b4da31f1b 100644 --- a/include/linux/regulator/fixed.h +++ b/include/linux/regulator/fixed.h @@ -14,9 +14,12 @@ #ifndef __REGULATOR_FIXED_H #define __REGULATOR_FIXED_H +struct regulator_init_data; + struct fixed_voltage_config { const char *supply_name; int microvolts; + struct regulator_init_data *init_data; }; #endif -- cgit v1.2.3 From 1fa9ad52b07811ebf258f3f6907de8dbf020ec2d Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Wed, 21 Jan 2009 14:08:40 +0000 Subject: regulator: Hoist struct regulator_dev out of core to fix notifiers Commit 872ed3fe176833f7d43748eb88010da4bbd2f983 caused regulator drivers to take the struct regulator_dev lock themselves which requires that the struct be visible to them. Band aid this by making the struct visible. Signed-off-by: Mark Brown Signed-off-by: Liam Girdwood --- include/linux/regulator/driver.h | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 2254ad93b78..c263e36e564 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -137,6 +137,38 @@ struct regulator_desc { struct module *owner; }; +/* + * struct regulator_dev + * + * Voltage / Current regulator class device. One for each + * regulator. + * + * This should *not* be used directly by anything except the regulator + * core and notification injection (which should take the mutex and do + * no other direct access). + */ +struct regulator_dev { + struct regulator_desc *desc; + int use_count; + + /* lists we belong to */ + struct list_head list; /* list of all regulators */ + struct list_head slist; /* list of supplied regulators */ + + /* lists we own */ + struct list_head consumer_list; /* consumers we supply */ + struct list_head supply_list; /* regulators we supply */ + + struct blocking_notifier_head notifier; + struct mutex mutex; /* consumer lock */ + struct module *owner; + struct device dev; + struct regulation_constraints *constraints; + struct regulator_dev *supply; /* for tree */ + + void *reg_data; /* regulator_dev data */ +}; + struct regulator_dev *regulator_register(struct regulator_desc *regulator_desc, struct device *dev, struct regulator_init_data *init_data, void *driver_data); -- cgit v1.2.3 From 90ca563b1030bece8a4f15a910e39a46f059ff48 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 20 Jan 2009 16:29:05 -0800 Subject: regulator: fix header file missing kernel-doc Fix regulator/driver.h missing kernel-doc: Warning(linux-next-20090120//include/linux/regulator/driver.h:108): No description found for parameter 'get_status' Signed-off-by: Randy Dunlap cc: Liam Girdwood cc: Mark Brown Signed-off-by: Liam Girdwood --- include/linux/regulator/driver.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index c263e36e564..eb8773b05ac 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -51,6 +51,7 @@ enum regulator_status { * * @set_mode: Set the operating mode for the regulator. * @get_mode: Get the current operating mode for the regulator. + * @get_status: Report the regulator status. * @get_optimum_mode: Get the most efficient operating mode for the regulator * when running with the specified parameters. * -- cgit v1.2.3 From 1dd68f01886a2d5cabbbe90b86e82f70917de89c Mon Sep 17 00:00:00 2001 From: Liam Girdwood Date: Mon, 2 Feb 2009 21:43:31 +0000 Subject: regulator: email - update email address and regulator webpage. Remove deceased email address and update to new address. Also update website details in MAINTAINERS with correct page. Signed-off-by: Liam Girdwood --- include/linux/regulator/consumer.h | 2 +- include/linux/regulator/driver.h | 2 +- include/linux/regulator/machine.h | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index 533f4e26db9..df6c4bcf38f 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -3,7 +3,7 @@ * * Copyright (C) 2007, 2008 Wolfson Microelectronics PLC. * - * Author: Liam Girdwood + * Author: Liam Girdwood * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index eb8773b05ac..0cf37bc85c4 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -3,7 +3,7 @@ * * Copyright (C) 2007, 2008 Wolfson Microelectronics PLC. * - * Author: Liam Girdwood + * Author: Liam Girdwood * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h index 3794773b23d..5aa00ee36a3 100644 --- a/include/linux/regulator/machine.h +++ b/include/linux/regulator/machine.h @@ -3,7 +3,7 @@ * * Copyright (C) 2007, 2008 Wolfson Microelectronics PLC. * - * Author: Liam Girdwood + * Author: Liam Girdwood * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as -- cgit v1.2.3 From a308466c24b4f42bab6945026e938874d22cde50 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 26 Feb 2009 19:24:19 +0000 Subject: regulator: Allow regulators to set the initial operating mode This is useful when wishing to run in a fixed operating mode that isn't the default. Signed-off-by: Mark Brown Signed-off-by: Liam Girdwood --- include/linux/regulator/machine.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h index 5aa00ee36a3..1eb861cf4b2 100644 --- a/include/linux/regulator/machine.h +++ b/include/linux/regulator/machine.h @@ -83,6 +83,7 @@ struct regulator_state { * @state_standby: State for regulator when system is suspended in standby * mode. * @initial_state: Suspend state to set by default. + * @initial_mode: Mode to set at startup. */ struct regulation_constraints { @@ -111,6 +112,9 @@ struct regulation_constraints { struct regulator_state state_standby; suspend_state_t initial_state; /* suspend state to set at init */ + /* mode to set on startup */ + unsigned int initial_mode; + /* constriant flags */ unsigned always_on:1; /* regulator never off when system is on */ unsigned boot_on:1; /* bootloader/firmware enabled regulator */ -- cgit v1.2.3 From 4367cfdc7c657ad8a797f51b9ffd3c64b31910e7 Mon Sep 17 00:00:00 2001 From: David Brownell Date: Thu, 26 Feb 2009 11:48:36 -0800 Subject: regulator: enumerate voltages (v2) Add a basic mechanism for regulators to report the discrete voltages they support: list_voltage() enumerates them using selectors numbered from 0 to an upper bound. Use those methods to force machine-level constraints into bounds. (Example: regulator supports 1.8V, 2.4V, 2.6V, 3.3V, and board constraints for that rail are 2.0V to 3.6V ... so the range of voltages is then 2.4V to 3.3V on this board.) Export those voltages to the regulator consumer interface, so for example regulator hooked up to an MMC/SD/SDIO slot can report the actual voltage options available to cards connected there. Signed-off-by: David Brownell Acked-by: Mark Brown Signed-off-by: Liam Girdwood --- include/linux/regulator/consumer.h | 2 ++ include/linux/regulator/driver.h | 9 +++++++++ 2 files changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index df6c4bcf38f..277f4b964df 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -142,6 +142,8 @@ int regulator_bulk_disable(int num_consumers, void regulator_bulk_free(int num_consumers, struct regulator_bulk_data *consumers); +int regulator_count_voltages(struct regulator *regulator); +int regulator_list_voltage(struct regulator *regulator, unsigned selector); int regulator_set_voltage(struct regulator *regulator, int min_uV, int max_uV); int regulator_get_voltage(struct regulator *regulator); int regulator_set_current_limit(struct regulator *regulator, diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 0cf37bc85c4..2255468d456 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -45,6 +45,10 @@ enum regulator_status { * @set_voltage: Set the voltage for the regulator within the range specified. * The driver should select the voltage closest to min_uV. * @get_voltage: Return the currently configured voltage for the regulator. + * @list_voltage: Return one of the supported voltages, in microvolts; zero + * if the selector indicates a voltage that is unusable on this system; + * or negative errno. Selectors range from zero to one less than + * regulator_desc.n_voltages. Voltages may be reported in any order. * * @set_current_limit: Configure a limit for a current-limited regulator. * @get_current_limit: Get the limit for a current-limited regulator. @@ -66,6 +70,9 @@ enum regulator_status { */ struct regulator_ops { + /* enumerate supported voltages */ + int (*list_voltage) (struct regulator_dev *, unsigned selector); + /* get/set regulator voltage */ int (*set_voltage) (struct regulator_dev *, int min_uV, int max_uV); int (*get_voltage) (struct regulator_dev *); @@ -124,6 +131,7 @@ enum regulator_type { * * @name: Identifying name for the regulator. * @id: Numerical identifier for the regulator. + * @n_voltages: Number of selectors available for ops.list_voltage(). * @ops: Regulator operations table. * @irq: Interrupt number for the regulator. * @type: Indicates if the regulator is a voltage or current regulator. @@ -132,6 +140,7 @@ enum regulator_type { struct regulator_desc { const char *name; int id; + unsigned n_voltages; struct regulator_ops *ops; int irq; enum regulator_type type; -- cgit v1.2.3 From 3b2a6061afe6fcc44437cd5ec641b0aeb2825ee3 Mon Sep 17 00:00:00 2001 From: David Brownell Date: Thu, 26 Feb 2009 13:28:41 -0800 Subject: regulator: get_status() grows kerneldoc Add kerneldoc for the new get_status() message. Fix the existing kerneldoc for that struct in two ways: (a) Syntax, making sure parameter descriptions immediately follow the one-line struct description and that the first blank lines is before any more expansive description; (b) Presentation for a few points, to highlight the fact that the previous "get" methods exist only to report the current configuration, not to display actual status. Signed-off-by: David Brownell Signed-off-by: Liam Girdwood --- include/linux/regulator/driver.h | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 2255468d456..4848d8dacd9 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -35,11 +35,8 @@ enum regulator_status { /** * struct regulator_ops - regulator operations. * - * This struct describes regulator operations which can be implemented by - * regulator chip drivers. - * - * @enable: Enable the regulator. - * @disable: Disable the regulator. + * @enable: Configure the regulator as enabled. + * @disable: Configure the regulator as disabled. * @is_enabled: Return 1 if the regulator is enabled, 0 otherwise. * * @set_voltage: Set the voltage for the regulator within the range specified. @@ -51,11 +48,11 @@ enum regulator_status { * regulator_desc.n_voltages. Voltages may be reported in any order. * * @set_current_limit: Configure a limit for a current-limited regulator. - * @get_current_limit: Get the limit for a current-limited regulator. + * @get_current_limit: Get the configured limit for a current-limited regulator. * - * @set_mode: Set the operating mode for the regulator. - * @get_mode: Get the current operating mode for the regulator. - * @get_status: Report the regulator status. + * @get_mode: Get the configured operating mode for the regulator. + * @get_status: Return actual (not as-configured) status of regulator, as a + * REGULATOR_STATUS value (or negative errno) * @get_optimum_mode: Get the most efficient operating mode for the regulator * when running with the specified parameters. * @@ -67,6 +64,9 @@ enum regulator_status { * suspended. * @set_suspend_mode: Set the operating mode for the regulator when the * system is suspended. + * + * This struct describes regulator operations which can be implemented by + * regulator chip drivers. */ struct regulator_ops { @@ -94,6 +94,7 @@ struct regulator_ops { /* report regulator status ... most other accessors report * control inputs, this reports results of combining inputs * from Linux (and other sources) with the actual load. + * returns REGULATOR_STATUS_* or negative errno. */ int (*get_status)(struct regulator_dev *); -- cgit v1.2.3 From fa16a5c13a2fc1433cfff38a083b4f8c5138d022 Mon Sep 17 00:00:00 2001 From: David Brownell Date: Sun, 8 Feb 2009 10:37:06 -0800 Subject: regulator: twl4030 regulators Support most of the LDO regulators in the twl4030 family chips. In the case of LDOs supporting MMC/SD, the voltage controls are used; but in most other cases, the regulator framework is only used to enable/disable a supplies, conserving power when a given voltage rail is not needed. The drivers/mfd/twl4030-core.c code already sets up the various regulators according to board-specific configuration, and knows that some chips don't provide the full set of voltage rails. The omitted regulators are intended to be under hardware control, such as during the hardware-mediated system powerup, powerdown, and suspend states. Unless/until software hooks are known to be safe, they won't be exported here. These regulators implement the new get_status() operation, but can't realistically implement get_mode(); the status output is effectively the result of a vote, with the relevant hardware inputs not exposed. Signed-off-by: David Brownell Acked-by: Mark Brown Signed-off-by: Liam Girdwood --- include/linux/i2c/twl4030.h | 47 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 47 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i2c/twl4030.h b/include/linux/i2c/twl4030.h index 8137f660a5c..0dc80ef2497 100644 --- a/include/linux/i2c/twl4030.h +++ b/include/linux/i2c/twl4030.h @@ -218,6 +218,53 @@ int twl4030_i2c_read(u8 mod_no, u8 *value, u8 reg, unsigned num_bytes); /*----------------------------------------------------------------------*/ +/* Power bus message definitions */ + +#define DEV_GRP_NULL 0x0 +#define DEV_GRP_P1 0x1 +#define DEV_GRP_P2 0x2 +#define DEV_GRP_P3 0x4 + +#define RES_GRP_RES 0x0 +#define RES_GRP_PP 0x1 +#define RES_GRP_RC 0x2 +#define RES_GRP_PP_RC 0x3 +#define RES_GRP_PR 0x4 +#define RES_GRP_PP_PR 0x5 +#define RES_GRP_RC_PR 0x6 +#define RES_GRP_ALL 0x7 + +#define RES_TYPE2_R0 0x0 + +#define RES_TYPE_ALL 0x7 + +#define RES_STATE_WRST 0xF +#define RES_STATE_ACTIVE 0xE +#define RES_STATE_SLEEP 0x8 +#define RES_STATE_OFF 0x0 + +/* + * Power Bus Message Format ... these can be sent individually by Linux, + * but are usually part of downloaded scripts that are run when various + * power events are triggered. + * + * Broadcast Message (16 Bits): + * DEV_GRP[15:13] MT[12] RES_GRP[11:9] RES_TYPE2[8:7] RES_TYPE[6:4] + * RES_STATE[3:0] + * + * Singular Message (16 Bits): + * DEV_GRP[15:13] MT[12] RES_ID[11:4] RES_STATE[3:0] + */ + +#define MSG_BROADCAST(devgrp, grp, type, type2, state) \ + ( (devgrp) << 13 | 1 << 12 | (grp) << 9 | (type2) << 7 \ + | (type) << 4 | (state)) + +#define MSG_SINGULAR(devgrp, id, state) \ + ((devgrp) << 13 | 0 << 12 | (id) << 4 | (state)) + +/*----------------------------------------------------------------------*/ + struct twl4030_bci_platform_data { int *battery_tmp_tbl; unsigned int tblsize; -- cgit v1.2.3 From 5c13941acc513669c7d07b28789c3f9ba66ddddf Mon Sep 17 00:00:00 2001 From: David Brownell Date: Wed, 11 Mar 2009 03:30:43 -0800 Subject: MMC: regulator utilities Glue between MMC and regulator stacks ... verified with some OMAP3 boards using adjustable and configured-as-fixed regulators on several MMC controllers. These calls are intended to be used by MMC host adapters using at least one regulator per host. Examples include slots with regulators supporting multiple voltages and ones using multiple voltage rails (e.g. DAT4..DAT7 using a separate supply, or a split rail chip like certain SDIO WLAN or eMMC solutions). Signed-off-by: David Brownell Acked-by: Pierre Ossman Signed-off-by: Liam Girdwood --- include/linux/mmc/host.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 4e457256bd3..3e7615e9087 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -192,5 +192,10 @@ static inline void mmc_signal_sdio_irq(struct mmc_host *host) wake_up_process(host->sdio_irq_thread); } +struct regulator; + +int mmc_regulator_get_ocrmask(struct regulator *supply); +int mmc_regulator_set_ocr(struct regulator *supply, unsigned short vdd_bit); + #endif -- cgit v1.2.3 From cacf90f24e80cec9334f98e0377149f943fe9f16 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 2 Mar 2009 16:32:46 +0000 Subject: regulator: Allow boot_on regulators to be disabled by clients Rather than incrementing the reference count for boot_on regulators (which prevents them being disabled later on) simply force the regulator to be enabled when applying the constraints. Previously boot_on was essentially equivalent to always_on. Signed-off-by: Mark Brown Signed-off-by: Liam Girdwood --- include/linux/regulator/machine.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h index 1eb861cf4b2..5de7aa3b02a 100644 --- a/include/linux/regulator/machine.h +++ b/include/linux/regulator/machine.h @@ -73,7 +73,9 @@ struct regulator_state { * * @always_on: Set if the regulator should never be disabled. * @boot_on: Set if the regulator is enabled when the system is initially - * started. + * started. If the regulator is not enabled by the hardware or + * bootloader then it will be enabled when the constraints are + * applied. * @apply_uV: Apply the voltage constraint when initialising. * * @input_uV: Input voltage for regulator when supplied by another regulator. -- cgit v1.2.3 From ca7255614e0861e36480103f4a402a115803d7b5 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 16 Mar 2009 19:36:34 +0000 Subject: regulator: Support disabling of unused regulators by machines At present it is not possible for machine constraints to disable regulators which have been left on when the system starts, for example as a result of fixed default configurations in hardware. This means that power may be wasted by these regulators if they are not in use. Provide intial support for this with a late_initcall which will disable any unused regulators if the machine has enabled this feature by calling regulator_has_full_constraints(). If this has not been called then print a warning to encourage users to fully specify their constraints so that we can change this to be the default behaviour in future. Signed-off-by: Mark Brown Signed-off-by: Liam Girdwood --- include/linux/regulator/machine.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h index 5de7aa3b02a..bac64fa390f 100644 --- a/include/linux/regulator/machine.h +++ b/include/linux/regulator/machine.h @@ -166,4 +166,6 @@ struct regulator_init_data { int regulator_suspend_prepare(suspend_state_t state); +void regulator_has_full_constraints(void); + #endif -- cgit v1.2.3 From 7f1e2ca9f04b02794597f60e7b1d43f0a1317939 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 13 Mar 2009 12:21:27 +0100 Subject: hrtimer: fix rq->lock inversion (again) It appears I inadvertly introduced rq->lock recursion to the hrtimer_start() path when I delegated running already expired timers to softirq context. This patch fixes it by introducing a __hrtimer_start_range_ns() method that will not use raise_softirq_irqoff() but __raise_softirq_irqoff() which avoids the wakeup. It then also changes schedule() to check for pending softirqs and do the wakeup then, I'm not quite sure I like this last bit, nor am I convinced its really needed. Signed-off-by: Peter Zijlstra Cc: Peter Zijlstra Cc: paulus@samba.org LKML-Reference: <20090313112301.096138802@chello.nl> Signed-off-by: Ingo Molnar --- include/linux/hrtimer.h | 5 +++++ include/linux/interrupt.h | 1 + 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index bd37078c2d7..0d2f7c8a33d 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -336,6 +336,11 @@ extern int hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode); extern int hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, unsigned long range_ns, const enum hrtimer_mode mode); +extern int +__hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, + unsigned long delta_ns, + const enum hrtimer_mode mode, int wakeup); + extern int hrtimer_cancel(struct hrtimer *timer); extern int hrtimer_try_to_cancel(struct hrtimer *timer); diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index c68bffd182b..4528bf70866 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -294,6 +294,7 @@ extern void softirq_init(void); #define __raise_softirq_irqoff(nr) do { or_softirq_pending(1UL << (nr)); } while (0) extern void raise_softirq_irqoff(unsigned int nr); extern void raise_softirq(unsigned int nr); +extern void wakeup_softirqd(void); /* This is the worklist that queues up per-cpu softirq work. * -- cgit v1.2.3 From a08915ba594da66145f33a972db578a58b9135f1 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 31 Mar 2009 20:15:13 +0200 Subject: ide-cd: use scatterlists for PIO transfers (fs requests) * Export ide_pio_bytes(). * Add ->last_xfer_len field to struct ide_cmd. * Add ide_cd_error_cmd() helper to ide-cd. * Convert ide-cd to use scatterlists also for PIO transfers (fs requests only for now) and get rid of partial completions (except when the error happens -- which is still subject to change later because looking at ATAPI spec it seems that the device is free to error the whole transfer with setting the Error bit only on the last transfer chunk). * Update ide_cd_{prepare_rw,restore_request,do_request}() accordingly. * Inline ide_cd_restore_request() into cdrom_start_rw(). Cc: Borislav Petkov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index d5d832271f4..c2841c0c36c 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -352,6 +352,8 @@ struct ide_cmd { unsigned int nbytes; unsigned int nleft; + unsigned int last_xfer_len; + struct scatterlist *cursg; unsigned int cursg_ofs; @@ -1226,6 +1228,8 @@ ide_startstop_t ide_issue_pc(ide_drive_t *, struct ide_cmd *); ide_startstop_t do_rw_taskfile(ide_drive_t *, struct ide_cmd *); +void ide_pio_bytes(ide_drive_t *, struct ide_cmd *, unsigned int, unsigned int); + void ide_finish_cmd(ide_drive_t *, struct ide_cmd *, u8); int ide_raw_taskfile(ide_drive_t *, struct ide_cmd *, u8 *, u16); -- cgit v1.2.3 From 06a449e30135aabb6686c95bf0c42b46d169a3b3 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 31 Mar 2009 20:15:13 +0200 Subject: ide-cd: fix non-SECTOR_SIZE-multiples PIO transfers for fs requests We now support arbitrary number of bytes per-IRQ also for fs requests so remove ide_cd_check_transfer_size() and IDE_AFLAG_LIMIT_NFRAMES. Cc: Borislav Petkov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index c2841c0c36c..cb501bf78f7 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -458,11 +458,6 @@ enum { IDE_AFLAG_TOCADDR_AS_BCD = (1 << 3), /* TOC track numbers are in BCD. */ IDE_AFLAG_TOCTRACKS_AS_BCD = (1 << 4), - /* - * Drive does not provide data in multiples of SECTOR_SIZE - * when more than one interrupt is needed. - */ - IDE_AFLAG_LIMIT_NFRAMES = (1 << 5), /* Saved TOC information is current. */ IDE_AFLAG_TOC_VALID = (1 << 6), /* We think that the drive door is locked. */ -- cgit v1.2.3 From 35c9b4daf4c94b30e5cede597d98016ebf31b5ad Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 31 Mar 2009 20:15:19 +0200 Subject: ide: add ->dma_clear method and remove ->dma_timeout one All custom ->dma_timeout implementations call the generic one thus it is possible to have only an optional method for resetting DMA engine instead: * Add ->dma_clear method and convert hpt366, pdc202xx_old and sl82c105 host drivers to use it. * Always use ide_dma_timeout() in ide_dma_timeout_retry() and remove ->dma_timeout method. * Make ide_dma_timeout() static. There should be no functional changes caused by this patch. Acked-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index cb501bf78f7..d3035f2f125 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -716,8 +716,9 @@ struct ide_dma_ops { int (*dma_end)(struct ide_drive_s *); int (*dma_test_irq)(struct ide_drive_s *); void (*dma_lost_irq)(struct ide_drive_s *); + /* below ones are optional */ int (*dma_timer_expiry)(struct ide_drive_s *); - void (*dma_timeout)(struct ide_drive_s *); + void (*dma_clear)(struct ide_drive_s *); /* * The following method is optional and only required to be * implemented for the SFF-8038i compatible controllers. @@ -1461,7 +1462,6 @@ static inline int config_drive_for_dma(ide_drive_t *drive) { return 0; } #endif /* CONFIG_BLK_DEV_IDEDMA_SFF */ void ide_dma_lost_irq(ide_drive_t *); -void ide_dma_timeout(ide_drive_t *); ide_startstop_t ide_dma_timeout_retry(ide_drive_t *, int); #else -- cgit v1.2.3 From 4453011f959a5f5c6c7a33aea54fe17f5e43a867 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 31 Mar 2009 20:15:20 +0200 Subject: ide: destroy DMA mappings after ending DMA (v2) Move ide_destroy_dmatable() call out from ->dma_end method to {ide_pc,cdrom_newpc,ide_dma}_intr(), ide_dma_timeout_retry() and sgiioc4_resetproc(). This causes minor/safe behavior changes w.r.t.: * cmd64x.c::cmd64{8,x}_dma_end() * cs5536.c::cs5536_dma_end() * icside.c::icside_dma_end() * it821x.c::it821x_dma_end() * scc_pata.c::__scc_dma_end() * sl82c105.c::sl82c105_dma_end() * tx4939ide.c::tx4939ide_dma_end() v2: * Fix build for CONFIG_BLK_DEV_IDEDMA=n (reported by Randy Dunlap). Cc: Randy Dunlap Acked-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index d3035f2f125..b6c4942fde1 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1479,6 +1479,7 @@ static inline ide_startstop_t ide_dma_timeout_retry(ide_drive_t *drive, int erro static inline void ide_release_dma_engine(ide_hwif_t *hwif) { ; } static inline int ide_build_sglist(ide_drive_t *drive, struct ide_cmd *cmd) { return 0; } +static inline void ide_destroy_dmatable(ide_drive_t *drive) { ; } #endif /* CONFIG_BLK_DEV_IDEDMA */ #ifdef CONFIG_BLK_DEV_IDEACPI -- cgit v1.2.3 From 5ae5412d9a23b05ab08461b202bad21ad8f6b66d Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 31 Mar 2009 20:15:20 +0200 Subject: ide: add ide_dma_prepare() helper * Add ide_dma_prepare() helper. * Convert ide_issue_pc() and do_rw_taskfile() to use it. * Make ide_build_sglist() static. There should be no functional changes caused by this patch. Acked-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index b6c4942fde1..78892e2a432 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1443,7 +1443,8 @@ ide_startstop_t ide_dma_intr(ide_drive_t *); int ide_allocate_dma_engine(ide_hwif_t *); void ide_release_dma_engine(ide_hwif_t *); -int ide_build_sglist(ide_drive_t *, struct ide_cmd *); +int ide_dma_prepare(ide_drive_t *, struct ide_cmd *); + void ide_destroy_dmatable(ide_drive_t *); #ifdef CONFIG_BLK_DEV_IDEDMA_SFF @@ -1477,8 +1478,8 @@ static inline void ide_check_dma_crc(ide_drive_t *drive) { ; } static inline ide_startstop_t ide_dma_intr(ide_drive_t *drive) { return ide_stopped; } static inline ide_startstop_t ide_dma_timeout_retry(ide_drive_t *drive, int error) { return ide_stopped; } static inline void ide_release_dma_engine(ide_hwif_t *hwif) { ; } -static inline int ide_build_sglist(ide_drive_t *drive, - struct ide_cmd *cmd) { return 0; } +static inline int ide_dma_prepare(ide_drive_t *drive, + struct ide_cmd *cmd) { return 1; } static inline void ide_destroy_dmatable(ide_drive_t *drive) { ; } #endif /* CONFIG_BLK_DEV_IDEDMA */ -- cgit v1.2.3 From 8a4a5738ba499083cf4c5668895efe220b1946d3 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 31 Mar 2009 20:15:21 +0200 Subject: ide: add ->dma_check method * Add (an optional) ->dma_check method for checking if DMA can be used for a given command and fail DMA setup in ide_dma_prepare() if necessary. * Convert alim15x3 and trm290 host drivers to use ->dma_check. * Rename ali15x3_dma_setup() to ali_dma_check() while at it. There should be no functional changes caused by this patch. Acked-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 78892e2a432..b350667b83a 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -717,6 +717,7 @@ struct ide_dma_ops { int (*dma_test_irq)(struct ide_drive_s *); void (*dma_lost_irq)(struct ide_drive_s *); /* below ones are optional */ + int (*dma_check)(struct ide_drive_s *, struct ide_cmd *); int (*dma_timer_expiry)(struct ide_drive_s *); void (*dma_clear)(struct ide_drive_s *); /* -- cgit v1.2.3 From f094d4d83bccee9277ddb6aadccf35747889426b Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 31 Mar 2009 20:15:24 +0200 Subject: ide: sanitize ide_build_sglist() and ide_destroy_dmatable() * Move ide_map_sg() calls out from ide_build_sglist() to ide_dma_prepare(). * Pass command to ide_destroy_dmatable(). * Rename ide_build_sglist() to ide_dma_map_sg() and ide_destroy_dmatable() to ide_dma_unmap_sg(). There should be no functional changes caused by this patch. Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index b350667b83a..03c520917b7 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1445,8 +1445,7 @@ int ide_allocate_dma_engine(ide_hwif_t *); void ide_release_dma_engine(ide_hwif_t *); int ide_dma_prepare(ide_drive_t *, struct ide_cmd *); - -void ide_destroy_dmatable(ide_drive_t *); +void ide_dma_unmap_sg(ide_drive_t *, struct ide_cmd *); #ifdef CONFIG_BLK_DEV_IDEDMA_SFF int config_drive_for_dma(ide_drive_t *); @@ -1481,7 +1480,8 @@ static inline ide_startstop_t ide_dma_timeout_retry(ide_drive_t *drive, int erro static inline void ide_release_dma_engine(ide_hwif_t *hwif) { ; } static inline int ide_dma_prepare(ide_drive_t *drive, struct ide_cmd *cmd) { return 1; } -static inline void ide_destroy_dmatable(ide_drive_t *drive) { ; } +static inline void ide_dma_unmap_sg(ide_drive_t *drive, + struct ide_cmd *cmd) { ; } #endif /* CONFIG_BLK_DEV_IDEDMA */ #ifdef CONFIG_BLK_DEV_IDEACPI -- cgit v1.2.3 From 41fa9f863baacd32dd049daf8050d55a0c9e6f1a Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 31 Mar 2009 20:15:25 +0200 Subject: ide: decrease size of ->pc_buf field in struct ide_atapi_pc struct ide_atapi_pc is often allocated on the stack and size of ->pc_buf size is 256 bytes. However since only ide_floppy_create_read_capacity_cmd() and idetape_create_inquiry_cmd() require such size allocate buffers for these pc-s explicitely and decrease ->pc_buf size to 64 bytes. Cc: Borislav Petkov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 03c520917b7..0f48fbd4602 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -377,7 +377,7 @@ enum { * With each packet command, we allocate a buffer of IDE_PC_BUFFER_SIZE bytes. * This is used for several packet commands (not for READ/WRITE commands). */ -#define IDE_PC_BUFFER_SIZE 256 +#define IDE_PC_BUFFER_SIZE 64 #define ATAPI_WAIT_PC (60 * HZ) struct ide_atapi_pc { -- cgit v1.2.3 From 349d12a1fe57d49287a539909cf14f362634342d Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 31 Mar 2009 20:15:26 +0200 Subject: ide-floppy: use ide_pio_bytes() * Fix ide_init_sg_cmd() setup for non-fs requests. * Convert ide_pc_intr() to use ide_pio_bytes() for floppy media. * Remove no longer needed ide_io_buffers() and sg/sg_cnt fields from struct ide_atapi_pc. * Remove partial completions; kill idefloppy_update_buffers(), as a result. * Add some more debugging statements. Signed-off-by: Bartlomiej Zolnierkiewicz Signed-off-by: Borislav Petkov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 0f48fbd4602..836c4c6cb7e 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -415,9 +415,6 @@ struct ide_atapi_pc { struct idetape_bh *bh; char *b_data; - struct scatterlist *sg; - unsigned int sg_cnt; - unsigned long timeout; }; @@ -1177,8 +1174,6 @@ void ide_tf_read(ide_drive_t *, struct ide_cmd *); void ide_input_data(ide_drive_t *, struct ide_cmd *, void *, unsigned int); void ide_output_data(ide_drive_t *, struct ide_cmd *, void *, unsigned int); -int ide_io_buffers(ide_drive_t *, struct ide_atapi_pc *, unsigned int, int); - extern void SELECT_DRIVE(ide_drive_t *); void SELECT_MASK(ide_drive_t *, int); -- cgit v1.2.3 From ecf3a31d2a08a419bdf919456f1724f5b72bde2c Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Tue, 31 Mar 2009 20:15:30 +0200 Subject: ide: turn set_irq() method into write_devctl() method Turn set_irq() method with its software reset hack into write_devctl() method (for just writing a value into the device control register) at last... Signed-off-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 836c4c6cb7e..ccb70abe991 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -655,8 +655,7 @@ struct ide_tp_ops { void (*exec_command)(struct hwif_s *, u8); u8 (*read_status)(struct hwif_s *); u8 (*read_altstatus)(struct hwif_s *); - - void (*set_irq)(struct hwif_s *, int); + void (*write_devctl)(struct hwif_s *, u8); void (*tf_load)(ide_drive_t *, struct ide_cmd *); void (*tf_read)(ide_drive_t *, struct ide_cmd *); @@ -1165,8 +1164,7 @@ void ide_tf_dump(const char *, struct ide_taskfile *); void ide_exec_command(ide_hwif_t *, u8); u8 ide_read_status(ide_hwif_t *); u8 ide_read_altstatus(ide_hwif_t *); - -void ide_set_irq(ide_hwif_t *, int); +void ide_write_devctl(ide_hwif_t *, u8); void ide_tf_load(ide_drive_t *, struct ide_cmd *); void ide_tf_read(ide_drive_t *, struct ide_cmd *); -- cgit v1.2.3 From 6762511934e6e7287ce3c8baac0d52ef64e3787b Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Tue, 31 Mar 2009 20:15:30 +0200 Subject: ide: rename IDE_TFLAG_IN_[HOB_]FEATURE The feature register has never been readable -- when its location is read, one gets the error register value; hence rename IDE_TFLAG_IN_[HOB_]FEATURE into IDE_TFLAG_IN_[HOB_]ERROR and introduce the 'hob_error' field into the 'struct ide_taskfile' (despite the error register not really depending on the HOB bit). Signed-off-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index ccb70abe991..e919c865f0c 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -265,7 +265,7 @@ enum { IDE_TFLAG_WRITE = (1 << 12), IDE_TFLAG_CUSTOM_HANDLER = (1 << 13), IDE_TFLAG_DMA_PIO_FALLBACK = (1 << 14), - IDE_TFLAG_IN_HOB_FEATURE = (1 << 15), + IDE_TFLAG_IN_HOB_ERROR = (1 << 15), IDE_TFLAG_IN_HOB_NSECT = (1 << 16), IDE_TFLAG_IN_HOB_LBAL = (1 << 17), IDE_TFLAG_IN_HOB_LBAM = (1 << 18), @@ -273,10 +273,10 @@ enum { IDE_TFLAG_IN_HOB_LBA = IDE_TFLAG_IN_HOB_LBAL | IDE_TFLAG_IN_HOB_LBAM | IDE_TFLAG_IN_HOB_LBAH, - IDE_TFLAG_IN_HOB = IDE_TFLAG_IN_HOB_FEATURE | + IDE_TFLAG_IN_HOB = IDE_TFLAG_IN_HOB_ERROR | IDE_TFLAG_IN_HOB_NSECT | IDE_TFLAG_IN_HOB_LBA, - IDE_TFLAG_IN_FEATURE = (1 << 20), + IDE_TFLAG_IN_ERROR = (1 << 20), IDE_TFLAG_IN_NSECT = (1 << 21), IDE_TFLAG_IN_LBAL = (1 << 22), IDE_TFLAG_IN_LBAM = (1 << 23), @@ -310,8 +310,12 @@ enum { struct ide_taskfile { u8 hob_data; /* 0: high data byte (for TASKFILE IOCTL) */ + /* 1-5: additional data to support LBA48 */ + union { + u8 hob_error; /* read: error */ + u8 hob_feature; /* write: feature */ + }; - u8 hob_feature; /* 1-5: additional data to support LBA48 */ u8 hob_nsect; u8 hob_lbal; u8 hob_lbam; -- cgit v1.2.3 From abb596b25edac1ec1acc4ef53df190771661c3d2 Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Tue, 31 Mar 2009 20:15:32 +0200 Subject: ide: turn selectproc() method into dev_select() method (take 5) Turn selectproc() method into dev_select() method by teaching it to write to the device register and moving it from 'struct ide_port_ops' to 'struct ide_tp_ops'. Signed-off-by: Sergei Shtylyov Cc: benh@kernel.crashing.org Cc: petkovbb@gmail.com [bart: add ->dev_select to at91_ide.c and tx4939.c (__BIG_ENDIAN case)] Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index e919c865f0c..c69181c61fd 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -603,7 +603,7 @@ struct ide_drive_s { unsigned int bios_cyl; /* BIOS/fdisk/LILO number of cyls */ unsigned int cyl; /* "real" number of cyls */ - unsigned int drive_data; /* used by set_pio_mode/selectproc */ + unsigned int drive_data; /* used by set_pio_mode/dev_select() */ unsigned int failures; /* current failure count */ unsigned int max_failures; /* maximum allowed failure count */ u64 probed_capacity;/* initial reported media capacity (ide-cd only currently) */ @@ -661,6 +661,7 @@ struct ide_tp_ops { u8 (*read_altstatus)(struct hwif_s *); void (*write_devctl)(struct hwif_s *, u8); + void (*dev_select)(ide_drive_t *); void (*tf_load)(ide_drive_t *, struct ide_cmd *); void (*tf_read)(ide_drive_t *, struct ide_cmd *); @@ -678,7 +679,6 @@ extern const struct ide_tp_ops default_tp_ops; * @init_dev: host specific initialization of a device * @set_pio_mode: routine to program host for PIO mode * @set_dma_mode: routine to program host for DMA mode - * @selectproc: tweaks hardware to select drive * @reset_poll: chipset polling based on hba specifics * @pre_reset: chipset specific changes to default for device-hba resets * @resetproc: routine to reset controller after a disk reset @@ -695,7 +695,6 @@ struct ide_port_ops { void (*init_dev)(ide_drive_t *); void (*set_pio_mode)(ide_drive_t *, const u8); void (*set_dma_mode)(ide_drive_t *, const u8); - void (*selectproc)(ide_drive_t *); int (*reset_poll)(ide_drive_t *); void (*pre_reset)(ide_drive_t *); void (*resetproc)(ide_drive_t *); @@ -1170,6 +1169,7 @@ u8 ide_read_status(ide_hwif_t *); u8 ide_read_altstatus(ide_hwif_t *); void ide_write_devctl(ide_hwif_t *, u8); +void ide_dev_select(ide_drive_t *); void ide_tf_load(ide_drive_t *, struct ide_cmd *); void ide_tf_read(ide_drive_t *, struct ide_cmd *); -- cgit v1.2.3 From fdd88f0af616db59a6a36bdf0185181d2b779f53 Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Tue, 31 Mar 2009 20:15:33 +0200 Subject: ide: inline SELECT_DRIVE() Since SELECT_DRIVE() has boiled down to a mere dev_select() method call, it now makes sense to just inline it... Signed-off-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index c69181c61fd..a5d26f66ef7 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1176,7 +1176,6 @@ void ide_tf_read(ide_drive_t *, struct ide_cmd *); void ide_input_data(ide_drive_t *, struct ide_cmd *, void *, unsigned int); void ide_output_data(ide_drive_t *, struct ide_cmd *, void *, unsigned int); -extern void SELECT_DRIVE(ide_drive_t *); void SELECT_MASK(ide_drive_t *, int); u8 ide_read_error(ide_drive_t *); -- cgit v1.2.3 From 3e93cd671813e204c258f1e6c797959920cf7772 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 29 Mar 2009 19:00:13 -0400 Subject: Take fs_struct handling to new file (fs/fs_struct.c) Pure code move; two new helper functions for nfsd and daemonize (unshare_fs_struct() and daemonize_fs_struct() resp.; for now - the same code as used to be in callers). unshare_fs_struct() exported (for nfsd, as copy_fs_struct()/exit_fs() used to be), copy_fs_struct() and exit_fs() don't need exports anymore. Signed-off-by: Al Viro --- include/linux/fs_struct.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs_struct.h b/include/linux/fs_struct.h index 18b467dbe27..298cef1c079 100644 --- a/include/linux/fs_struct.h +++ b/include/linux/fs_struct.h @@ -20,5 +20,7 @@ extern void set_fs_root(struct fs_struct *, struct path *); extern void set_fs_pwd(struct fs_struct *, struct path *); extern struct fs_struct *copy_fs_struct(struct fs_struct *); extern void put_fs_struct(struct fs_struct *); +extern void daemonize_fs_struct(void); +extern int unshare_fs_struct(void); #endif /* _LINUX_FS_STRUCT_H */ -- cgit v1.2.3 From 498052bba55ecaff58db6a1436b0e25bfd75a7ff Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 30 Mar 2009 07:20:30 -0400 Subject: New locking/refcounting for fs_struct * all changes of current->fs are done under task_lock and write_lock of old fs->lock * refcount is not atomic anymore (same protection) * its decrements are done when removing reference from current; at the same time we decide whether to free it. * put_fs_struct() is gone * new field - ->in_exec. Set by check_unsafe_exec() if we are trying to do execve() and only subthreads share fs_struct. Cleared when finishing exec (success and failure alike). Makes CLONE_FS fail with -EAGAIN if set. * check_unsafe_exec() may fail with -EAGAIN if another execve() from subthread is in progress. Signed-off-by: Al Viro --- include/linux/fs_struct.h | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs_struct.h b/include/linux/fs_struct.h index 298cef1c079..78a05bfcd8e 100644 --- a/include/linux/fs_struct.h +++ b/include/linux/fs_struct.h @@ -4,12 +4,10 @@ #include struct fs_struct { - atomic_t count; /* This usage count is used by check_unsafe_exec() for - * security checking purposes - therefore it may not be - * incremented, except by clone(CLONE_FS). - */ + int users; rwlock_t lock; int umask; + int in_exec; struct path root, pwd; }; @@ -19,7 +17,7 @@ extern void exit_fs(struct task_struct *); extern void set_fs_root(struct fs_struct *, struct path *); extern void set_fs_pwd(struct fs_struct *, struct path *); extern struct fs_struct *copy_fs_struct(struct fs_struct *); -extern void put_fs_struct(struct fs_struct *); +extern void free_fs_struct(struct fs_struct *); extern void daemonize_fs_struct(void); extern int unshare_fs_struct(void); -- cgit v1.2.3 From ce3b0f8d5c2203301fc87f3aaaed73e5819e2a48 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 29 Mar 2009 19:08:22 -0400 Subject: New helper - current_umask() current->fs->umask is what most of fs_struct users are doing. Put that into a helper function. Signed-off-by: Al Viro --- include/linux/fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 87e7bfc5ebd..3d7bd5447ca 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1741,6 +1741,8 @@ extern void drop_collected_mounts(struct vfsmount *); extern int vfs_statfs(struct dentry *, struct kstatfs *); +extern int current_umask(void); + /* /sys/fs */ extern struct kobject *fs_kobj; -- cgit v1.2.3 From 5ad4e53bd5406ee214ddc5a41f03f779b8b2d526 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 29 Mar 2009 19:50:06 -0400 Subject: Get rid of indirect include of fs_struct.h Don't pull it in sched.h; very few files actually need it and those can include directly. sched.h itself only needs forward declaration of struct fs_struct; Signed-off-by: Al Viro --- include/linux/mnt_namespace.h | 2 ++ include/linux/nsproxy.h | 1 + include/linux/sched.h | 3 ++- 3 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mnt_namespace.h b/include/linux/mnt_namespace.h index 830bbcd449d..3a059298cc1 100644 --- a/include/linux/mnt_namespace.h +++ b/include/linux/mnt_namespace.h @@ -22,6 +22,8 @@ struct proc_mounts { int event; }; +struct fs_struct; + extern struct mnt_namespace *copy_mnt_ns(unsigned long, struct mnt_namespace *, struct fs_struct *); extern void __put_mnt_ns(struct mnt_namespace *ns); diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h index afad7dec1b3..7b370c7cfef 100644 --- a/include/linux/nsproxy.h +++ b/include/linux/nsproxy.h @@ -8,6 +8,7 @@ struct mnt_namespace; struct uts_namespace; struct ipc_namespace; struct pid_namespace; +struct fs_struct; /* * A structure to contain pointers to all per-process diff --git a/include/linux/sched.h b/include/linux/sched.h index 29df6374d2d..b4e065ea0de 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -68,7 +68,7 @@ struct sched_param { #include #include #include -#include +#include #include #include #include @@ -97,6 +97,7 @@ struct futex_pi_state; struct robust_list_head; struct bio; struct bts_tracer; +struct fs_struct; /* * List of flags we want to share for kernel threads, -- cgit v1.2.3 From 47e4491b40df73c3b117e3d80b31b5b512a4b19f Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 1 Apr 2009 07:07:16 -0400 Subject: Cleanup after commit 585d3bc06f4ca57f975a5a1f698f65a45ea66225 fsync_bdev() export and a bunch of stubs for !CONFIG_BLOCK case had been left behind Signed-off-by: Al Viro --- include/linux/buffer_head.h | 12 ------------ include/linux/fs.h | 12 ++++++++++++ 2 files changed, 12 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index f19fd9045ea..fc91665d39d 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -332,22 +332,10 @@ extern int __set_page_dirty_buffers(struct page *page); static inline void buffer_init(void) {} static inline int try_to_free_buffers(struct page *page) { return 1; } -static inline int sync_blockdev(struct block_device *bdev) { return 0; } static inline int inode_has_buffers(struct inode *inode) { return 0; } static inline void invalidate_inode_buffers(struct inode *inode) {} static inline int remove_inode_buffers(struct inode *inode) { return 1; } static inline int sync_mapping_buffers(struct address_space *mapping) { return 0; } -static inline void invalidate_bdev(struct block_device *bdev) {} - -static inline struct super_block *freeze_bdev(struct block_device *sb) -{ - return NULL; -} - -static inline int thaw_bdev(struct block_device *bdev, struct super_block *sb) -{ - return 0; -} #endif /* CONFIG_BLOCK */ #endif /* _LINUX_BUFFER_HEAD_H */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 3d7bd5447ca..67413472559 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1886,6 +1886,18 @@ extern int fsync_super(struct super_block *); extern int fsync_no_super(struct block_device *); #else static inline void bd_forget(struct inode *inode) {} +static inline int sync_blockdev(struct block_device *bdev) { return 0; } +static inline void invalidate_bdev(struct block_device *bdev) {} + +static inline struct super_block *freeze_bdev(struct block_device *sb) +{ + return NULL; +} + +static inline int thaw_bdev(struct block_device *bdev, struct super_block *sb) +{ + return 0; +} #endif extern const struct file_operations def_blk_fops; extern const struct file_operations def_chr_fops; -- cgit v1.2.3 From ced117c73edc917e96dea7cca98c91383f0792f7 Mon Sep 17 00:00:00 2001 From: Dmitri Vorobiev Date: Tue, 31 Mar 2009 00:41:20 +0300 Subject: Remove two unneeded exports and make two symbols static in fs/mpage.c Commit 29a814d2ee0e43c2980f33f91c1311ec06c0aa35 (vfs: add hooks for ext4's delayed allocation support) exported the following functions mpage_bio_submit() __mpage_writepage() for the benefit of ext4's delayed allocation support. Since commit a1d6cc563bfdf1bf2829d3e6ce4d8b774251796b (ext4: Rework the ext4_da_writepages() function), these functions are not used by the ext4 driver anymore. However, the now unnecessary exports still remain, and this patch removes those. Moreover, these two functions can become static again. The issue was spotted by namespacecheck. Signed-off-by: Dmitri Vorobiev Reviewed-by: Aneesh Kumar K.V Signed-off-by: Al Viro --- include/linux/mpage.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mpage.h b/include/linux/mpage.h index 5c42821da2d..068a0c9946a 100644 --- a/include/linux/mpage.h +++ b/include/linux/mpage.h @@ -11,21 +11,11 @@ */ #ifdef CONFIG_BLOCK -struct mpage_data { - struct bio *bio; - sector_t last_block_in_bio; - get_block_t *get_block; - unsigned use_writepage; -}; - struct writeback_control; -struct bio *mpage_bio_submit(int rw, struct bio *bio); int mpage_readpages(struct address_space *mapping, struct list_head *pages, unsigned nr_pages, get_block_t get_block); int mpage_readpage(struct page *page, get_block_t get_block); -int __mpage_writepage(struct page *page, struct writeback_control *wbc, - void *data); int mpage_writepages(struct address_space *mapping, struct writeback_control *wbc, get_block_t get_block); int mpage_writepage(struct page *page, get_block_t *get_block, -- cgit v1.2.3 From ae149b6bec64a09373ba20fce75f8aa6b14b78fd Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Tue, 31 Mar 2009 15:19:15 -0700 Subject: proc tty: add struct tty_operations::proc_fops Used for gradual switch of TTY drivers from using ->read_proc which helps with gradual switch from ->read_proc for the whole tree. As side effect, fix possible race condition when ->data initialized after PDE is hooked into proc tree. ->proc_fops takes precedence over ->read_proc. Signed-off-by: Alexey Dobriyan Cc: Alan Cox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tty_driver.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index 08e088334db..c9a69575ded 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -264,6 +264,7 @@ struct tty_operations { int (*poll_get_char)(struct tty_driver *driver, int line); void (*poll_put_char)(struct tty_driver *driver, int line, char ch); #endif + const struct file_operations *proc_fops; }; struct tty_driver { -- cgit v1.2.3 From 0f043a81ebe84be3576667f04fdda481609e3816 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Tue, 31 Mar 2009 15:19:25 -0700 Subject: proc tty: remove struct tty_operations::read_proc struct tty_operations::proc_fops took it's place and there is one less create_proc_read_entry() user now! Signed-off-by: Alexey Dobriyan Cc: Alan Cox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tty_driver.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index c9a69575ded..8615d661ab6 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -252,8 +252,6 @@ struct tty_operations { void (*set_ldisc)(struct tty_struct *tty); void (*wait_until_sent)(struct tty_struct *tty, int timeout); void (*send_xchar)(struct tty_struct *tty, char ch); - int (*read_proc)(char *page, char **start, off_t off, - int count, int *eof, void *data); int (*tiocmget)(struct tty_struct *tty, struct file *file); int (*tiocmset)(struct tty_struct *tty, struct file *file, unsigned int set, unsigned int clear); -- cgit v1.2.3 From 9de1581e75ba9d7979766d4ab6d56f0f2d87f7c6 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 31 Mar 2009 15:19:29 -0700 Subject: get_mm_hiwater_xxx: trivial, s/define/inline/ Andrew pointed out get_mm_hiwater_xxx() evaluate "mm" argument thrice/twice, make them inline. Signed-off-by: Oleg Nesterov Cc: Hugh Dickins Reviewed-by: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 29df6374d2d..481fad3a9b4 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -391,8 +391,15 @@ extern void arch_unmap_area_topdown(struct mm_struct *, unsigned long); (mm)->hiwater_vm = (mm)->total_vm; \ } while (0) -#define get_mm_hiwater_rss(mm) max((mm)->hiwater_rss, get_mm_rss(mm)) -#define get_mm_hiwater_vm(mm) max((mm)->hiwater_vm, (mm)->total_vm) +static inline unsigned long get_mm_hiwater_rss(struct mm_struct *mm) +{ + return max(mm->hiwater_rss, get_mm_rss(mm)); +} + +static inline unsigned long get_mm_hiwater_vm(struct mm_struct *mm) +{ + return max(mm->hiwater_vm, mm->total_vm); +} extern void set_dumpable(struct mm_struct *mm, int value); extern int get_dumpable(struct mm_struct *mm); -- cgit v1.2.3 From ee99c71c59f897436ec65debb99372b3146f9985 Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Tue, 31 Mar 2009 15:19:31 -0700 Subject: mm: introduce for_each_populated_zone() macro Impact: cleanup In almost cases, for_each_zone() is used with populated_zone(). It's because almost function doesn't need memoryless node information. Therefore, for_each_populated_zone() can help to make code simplify. This patch has no functional change. [akpm@linux-foundation.org: small cleanup] Signed-off-by: KOSAKI Motohiro Cc: KAMEZAWA Hiroyuki Cc: Mel Gorman Reviewed-by: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 1aca6cebbb7..26ef24076b7 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -806,6 +806,14 @@ extern struct zone *next_zone(struct zone *zone); zone; \ zone = next_zone(zone)) +#define for_each_populated_zone(zone) \ + for (zone = (first_online_pgdat())->node_zones; \ + zone; \ + zone = next_zone(zone)) \ + if (!populated_zone(zone)) \ + ; /* do nothing */ \ + else + static inline struct zone *zonelist_zone(struct zoneref *zoneref) { return zoneref->zone; -- cgit v1.2.3 From e3a7cca1ef4c1af9b0acef9bd66eff6582a737b5 Mon Sep 17 00:00:00 2001 From: Edward Shishkin Date: Tue, 31 Mar 2009 15:19:39 -0700 Subject: vfs: add/use account_page_dirtied() Add a helper function account_page_dirtied(). Use that from two callsites. reiser4 adds a function which adds a third callsite. Signed-off-by: Edward Shishkin Cc: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index b1ea37fc7a2..2223f8dfa56 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -834,6 +834,7 @@ int __set_page_dirty_nobuffers(struct page *page); int __set_page_dirty_no_writeback(struct page *page); int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page); +void account_page_dirtied(struct page *page, struct address_space *mapping); int set_page_dirty(struct page *page); int set_page_dirty_lock(struct page *page); int clear_page_dirty_for_io(struct page *page); -- cgit v1.2.3 From d1d7487173eab8352125cf6cc271940f24254bd4 Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Tue, 31 Mar 2009 15:23:14 -0700 Subject: mm: remove pagevec_swap_free() pagevec_swap_free() is now unused. Signed-off-by: KOSAKI Motohiro Cc: Johannes Weiner Cc: Rik van Riel Acked-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagevec.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h index 7b2886fa7fd..bab82f4c571 100644 --- a/include/linux/pagevec.h +++ b/include/linux/pagevec.h @@ -24,7 +24,6 @@ void __pagevec_release(struct pagevec *pvec); void __pagevec_free(struct pagevec *pvec); void ____pagevec_lru_add(struct pagevec *pvec, enum lru_list lru); void pagevec_strip(struct pagevec *pvec); -void pagevec_swap_free(struct pagevec *pvec); unsigned pagevec_lookup(struct pagevec *pvec, struct address_space *mapping, pgoff_t start, unsigned nr_pages); unsigned pagevec_lookup_tag(struct pagevec *pvec, -- cgit v1.2.3 From 610a77e04a8d9fe8764dc484e2182fa251ce1cc2 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Tue, 31 Mar 2009 15:23:16 -0700 Subject: memdup_user(): introduce I notice there are many places doing copy_from_user() which follows kmalloc(): dst = kmalloc(len, GFP_KERNEL); if (!dst) return -ENOMEM; if (copy_from_user(dst, src, len)) { kfree(dst); return -EFAULT } memdup_user() is a wrapper of the above code. With this new function, we don't have to write 'len' twice, which can lead to typos/mistakes. It also produces smaller code and kernel text. A quick grep shows 250+ places where memdup_user() *may* be used. I'll prepare a patchset to do this conversion. Signed-off-by: Li Zefan Cc: KOSAKI Motohiro Cc: Americo Wang Cc: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/string.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/string.h b/include/linux/string.h index d18fc198aa2..8852739f36d 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -12,6 +12,7 @@ #include /* for NULL */ extern char *strndup_user(const char __user *, long); +extern void *memdup_user(const void __user *, size_t); /* * Include machine specific inline routines -- cgit v1.2.3 From 6a11f75b6a17b5d9ac5025f8d048382fd1f47377 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Tue, 31 Mar 2009 15:23:17 -0700 Subject: generic debug pagealloc CONFIG_DEBUG_PAGEALLOC is now supported by x86, powerpc, sparc64, and s390. This patch implements it for the rest of the architectures by filling the pages with poison byte patterns after free_pages() and verifying the poison patterns before alloc_pages(). This generic one cannot detect invalid page accesses immediately but invalid read access may cause invalid dereference by poisoned memory and invalid write access can be detected after a long delay. Signed-off-by: Akinobu Mita Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 4 ++++ include/linux/page-debug-flags.h | 30 ++++++++++++++++++++++++++++++ include/linux/poison.h | 3 +++ 3 files changed, 37 insertions(+) create mode 100644 include/linux/page-debug-flags.h (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index d84feb7bdbf..ddadb4defe0 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -11,6 +11,7 @@ #include #include #include +#include #include #include @@ -174,6 +175,9 @@ struct vm_area_struct { #ifdef CONFIG_NUMA struct mempolicy *vm_policy; /* NUMA policy for the VMA */ #endif +#ifdef CONFIG_WANT_PAGE_DEBUG_FLAGS + unsigned long debug_flags; /* Use atomic bitops on this */ +#endif }; struct core_thread { diff --git a/include/linux/page-debug-flags.h b/include/linux/page-debug-flags.h new file mode 100644 index 00000000000..b0638fd91e9 --- /dev/null +++ b/include/linux/page-debug-flags.h @@ -0,0 +1,30 @@ +#ifndef LINUX_PAGE_DEBUG_FLAGS_H +#define LINUX_PAGE_DEBUG_FLAGS_H + +/* + * page->debug_flags bits: + * + * PAGE_DEBUG_FLAG_POISON is set for poisoned pages. This is used to + * implement generic debug pagealloc feature. The pages are filled with + * poison patterns and set this flag after free_pages(). The poisoned + * pages are verified whether the patterns are not corrupted and clear + * the flag before alloc_pages(). + */ + +enum page_debug_flags { + PAGE_DEBUG_FLAG_POISON, /* Page is poisoned */ +}; + +/* + * Ensure that CONFIG_WANT_PAGE_DEBUG_FLAGS reliably + * gets turned off when no debug features are enabling it! + */ + +#ifdef CONFIG_WANT_PAGE_DEBUG_FLAGS +#if !defined(CONFIG_PAGE_POISONING) \ +/* && !defined(CONFIG_PAGE_DEBUG_SOMETHING_ELSE) && ... */ +#error WANT_PAGE_DEBUG_FLAGS is turned on with no debug features! +#endif +#endif /* CONFIG_WANT_PAGE_DEBUG_FLAGS */ + +#endif /* LINUX_PAGE_DEBUG_FLAGS_H */ diff --git a/include/linux/poison.h b/include/linux/poison.h index 9f31683728f..6729f7dcd60 100644 --- a/include/linux/poison.h +++ b/include/linux/poison.h @@ -17,6 +17,9 @@ */ #define TIMER_ENTRY_STATIC ((void *) 0x74737461) +/********** mm/debug-pagealloc.c **********/ +#define PAGE_POISON 0xaa + /********** mm/slab.c **********/ /* * Magic nums for obj red zoning. -- cgit v1.2.3 From 704503d836042d4a4c7685b7036e7de0418fbc0f Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Tue, 31 Mar 2009 15:23:18 -0700 Subject: mm: fix proc_dointvec_userhz_jiffies "breakage" Addresses http://bugzilla.kernel.org/show_bug.cgi?id=9838 On i386, HZ=1000, jiffies_to_clock_t() converts time in a somewhat strange way from the user's point of view: # echo 500 >/proc/sys/vm/dirty_writeback_centisecs # cat /proc/sys/vm/dirty_writeback_centisecs 499 So, we have 5000 jiffies converted to only 499 clock ticks and reported back. TICK_NSEC = 999848 ACTHZ = 256039 Keeping in-kernel variable in units passed from userspace will fix issue of course, but this probably won't be right for every sysctl. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Alexey Dobriyan Cc: Peter Zijlstra Cc: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/writeback.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 7300ecdc480..93445477f86 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -109,8 +109,8 @@ extern int dirty_background_ratio; extern unsigned long dirty_background_bytes; extern int vm_dirty_ratio; extern unsigned long vm_dirty_bytes; -extern int dirty_writeback_interval; -extern int dirty_expire_interval; +extern unsigned int dirty_writeback_interval; +extern unsigned int dirty_expire_interval; extern int vm_highmem_is_dirtyable; extern int block_dump; extern int laptop_mode; -- cgit v1.2.3 From c2fdf3a9b2d52842808a8e551b53b55dd9b45030 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Tue, 31 Mar 2009 15:23:19 -0700 Subject: mm: enable hashdist by default on 64bit NUMA On PowerPC we allocate large boot time hashes on node 0. This leads to an imbalance in the free memory, for example on a 64GB box (4 x 16GB nodes): Free memory: Node 0: 97.03% Node 1: 98.54% Node 2: 98.42% Node 3: 98.53% If we switch to using vmalloc (like ia64 and x86-64) things are more balanced: Free memory: Node 0: 97.53% Node 1: 98.35% Node 2: 98.33% Node 3: 98.33% For many HPC applications we are limited by the free available memory on the smallest node, so even though the same amount of memory is used the better balancing helps. Since all 64bit NUMA capable architectures should have sufficient vmalloc space, it makes sense to enable it via CONFIG_64BIT. Signed-off-by: Anton Blanchard Acked-by: David S. Miller Acked-by: Benjamin Herrenschmidt Acked-by: Ralf Baechle Cc: Heiko Carstens Cc: Martin Schwidefsky Cc: Ivan Kokshaysky Cc: Richard Henderson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 455d83219fa..bc3ab707369 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -146,10 +146,10 @@ extern void *alloc_large_system_hash(const char *tablename, #define HASH_EARLY 0x00000001 /* Allocating during early boot? */ -/* Only NUMA needs hash distribution. - * IA64 and x86_64 have sufficient vmalloc space. +/* Only NUMA needs hash distribution. 64bit NUMA architectures have + * sufficient vmalloc space. */ -#if defined(CONFIG_NUMA) && (defined(CONFIG_IA64) || defined(CONFIG_X86_64)) +#if defined(CONFIG_NUMA) && defined(CONFIG_64BIT) #define HASHDIST_DEFAULT 1 #else #define HASHDIST_DEFAULT 0 -- cgit v1.2.3 From c2ec175c39f62949438354f603f4aa170846aabb Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Tue, 31 Mar 2009 15:23:21 -0700 Subject: mm: page_mkwrite change prototype to match fault Change the page_mkwrite prototype to take a struct vm_fault, and return VM_FAULT_xxx flags. There should be no functional change. This makes it possible to return much more detailed error information to the VM (and also can provide more information eg. virtual_address to the driver, which might be important in some special cases). This is required for a subsequent fix. And will also make it easier to merge page_mkwrite() with fault() in future. Signed-off-by: Nick Piggin Cc: Chris Mason Cc: Trond Myklebust Cc: Miklos Szeredi Cc: Steven Whitehouse Cc: Mark Fasheh Cc: Joel Becker Cc: Artem Bityutskiy Cc: Felix Blyakher Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/buffer_head.h | 2 +- include/linux/mm.h | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index f19fd9045ea..3d7bcde2e33 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -216,7 +216,7 @@ int cont_write_begin(struct file *, struct address_space *, loff_t, get_block_t *, loff_t *); int generic_cont_expand_simple(struct inode *inode, loff_t size); int block_commit_write(struct page *page, unsigned from, unsigned to); -int block_page_mkwrite(struct vm_area_struct *vma, struct page *page, +int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, get_block_t get_block); void block_sync_page(struct page *); sector_t generic_block_bmap(struct address_space *, sector_t, get_block_t *); diff --git a/include/linux/mm.h b/include/linux/mm.h index 2223f8dfa56..aeabe953ba4 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -135,6 +135,7 @@ extern pgprot_t protection_map[16]; #define FAULT_FLAG_WRITE 0x01 /* Fault was a write access */ #define FAULT_FLAG_NONLINEAR 0x02 /* Fault was via a nonlinear mapping */ +#define FAULT_FLAG_MKWRITE 0x04 /* Fault was mkwrite of existing pte */ /* * This interface is used by x86 PAT code to identify a pfn mapping that is @@ -187,7 +188,7 @@ struct vm_operations_struct { /* notification that a previously read-only page is about to become * writable, if an error is returned it will cause a SIGBUS */ - int (*page_mkwrite)(struct vm_area_struct *vma, struct page *page); + int (*page_mkwrite)(struct vm_area_struct *vma, struct vm_fault *vmf); /* called by access_process_vm when get_user_pages() fails, typically * for use by special VMAs that can switch between memory and hardware -- cgit v1.2.3 From f4112de6b679d84bd9b9681c7504be7bdfb7c7d5 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Tue, 31 Mar 2009 15:23:25 -0700 Subject: mm: introduce debug_kmap_atomic x86 has debug_kmap_atomic_prot() which is error checking function for kmap_atomic. It is usefull for the other architectures, although it needs CONFIG_TRACE_IRQFLAGS_SUPPORT. This patch exposes it to the other architectures. Signed-off-by: Akinobu Mita Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/highmem.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 13875ce9112..7ff5c55f9b5 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -187,4 +187,16 @@ static inline void copy_highpage(struct page *to, struct page *from) kunmap_atomic(vto, KM_USER1); } +#if defined(CONFIG_DEBUG_HIGHMEM) && defined(CONFIG_TRACE_IRQFLAGS_SUPPORT) + +void debug_kmap_atomic(enum km_type type); + +#else + +static inline void debug_kmap_atomic(enum km_type type) +{ +} + +#endif + #endif /* _LINUX_HIGHMEM_H */ -- cgit v1.2.3 From 33925b25d2c00a29664f1994ab350a9bff70f7a2 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 31 Mar 2009 15:23:26 -0700 Subject: nommu: there is no mlock() for NOMMU, so don't provide the bits The mlock() facility does not exist for NOMMU since all mappings are effectively locked anyway, so we don't make the bits available when they're not useful. Signed-off-by: David Howells Reviewed-by: KOSAKI Motohiro Cc: Peter Zijlstra Cc: Greg Ungerer Cc: Johannes Weiner Cc: Rik van Riel Cc: Lee Schermerhorn Cc: Enrik Berkhan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 219a523ecdb..61df1779b2a 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -96,6 +96,8 @@ enum pageflags { PG_swapbacked, /* Page is backed by RAM/swap */ #ifdef CONFIG_UNEVICTABLE_LRU PG_unevictable, /* Page is "unevictable" */ +#endif +#ifdef CONFIG_HAVE_MLOCKED_PAGE_BIT PG_mlocked, /* Page is vma mlocked */ #endif #ifdef CONFIG_IA64_UNCACHED_ALLOCATOR @@ -234,20 +236,20 @@ PAGEFLAG_FALSE(SwapCache) #ifdef CONFIG_UNEVICTABLE_LRU PAGEFLAG(Unevictable, unevictable) __CLEARPAGEFLAG(Unevictable, unevictable) TESTCLEARFLAG(Unevictable, unevictable) +#else +PAGEFLAG_FALSE(Unevictable) TESTCLEARFLAG_FALSE(Unevictable) + SETPAGEFLAG_NOOP(Unevictable) CLEARPAGEFLAG_NOOP(Unevictable) + __CLEARPAGEFLAG_NOOP(Unevictable) +#endif +#ifdef CONFIG_HAVE_MLOCKED_PAGE_BIT #define MLOCK_PAGES 1 PAGEFLAG(Mlocked, mlocked) __CLEARPAGEFLAG(Mlocked, mlocked) TESTSCFLAG(Mlocked, mlocked) - #else - #define MLOCK_PAGES 0 PAGEFLAG_FALSE(Mlocked) SETPAGEFLAG_NOOP(Mlocked) TESTCLEARFLAG_FALSE(Mlocked) - -PAGEFLAG_FALSE(Unevictable) TESTCLEARFLAG_FALSE(Unevictable) - SETPAGEFLAG_NOOP(Unevictable) CLEARPAGEFLAG_NOOP(Unevictable) - __CLEARPAGEFLAG_NOOP(Unevictable) #endif #ifdef CONFIG_IA64_UNCACHED_ALLOCATOR @@ -367,9 +369,13 @@ static inline void __ClearPageTail(struct page *page) #ifdef CONFIG_UNEVICTABLE_LRU #define __PG_UNEVICTABLE (1 << PG_unevictable) -#define __PG_MLOCKED (1 << PG_mlocked) #else #define __PG_UNEVICTABLE 0 +#endif + +#ifdef CONFIG_HAVE_MLOCKED_PAGE_BIT +#define __PG_MLOCKED (1 << PG_mlocked) +#else #define __PG_MLOCKED 0 #endif -- cgit v1.2.3 From 327c0e968645f2601a43f5ea7c19c7b3a5fa0a34 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Tue, 31 Mar 2009 15:23:31 -0700 Subject: vmscan: fix it to take care of nodemask try_to_free_pages() is used for the direct reclaim of up to SWAP_CLUSTER_MAX pages when watermarks are low. The caller to alloc_pages_nodemask() can specify a nodemask of nodes that are allowed to be used but this is not passed to try_to_free_pages(). This can lead to unnecessary reclaim of pages that are unusable by the caller and int the worst case lead to allocation failure as progress was not been make where it is needed. This patch passes the nodemask used for alloc_pages_nodemask() to try_to_free_pages(). Reviewed-by: KOSAKI Motohiro Acked-by: Mel Gorman Signed-off-by: KAMEZAWA Hiroyuki Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index d3021557887..b8b0c4ce83e 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -212,7 +212,7 @@ static inline void lru_cache_add_active_file(struct page *page) /* linux/mm/vmscan.c */ extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, - gfp_t gfp_mask); + gfp_t gfp_mask, nodemask_t *mask); extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem, gfp_t gfp_mask, bool noswap, unsigned int swappiness); -- cgit v1.2.3 From 9fab5619bdd7f84cdd22cc760778f759f9819a33 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Tue, 31 Mar 2009 15:23:33 -0700 Subject: shmem: writepage directly to swap Synopsis: if shmem_writepage calls swap_writepage directly, most shmem swap loads benefit, and a catastrophic interaction between SLUB and some flash storage is avoided. shmem_writepage() has always been peculiar in making no attempt to write: it has just transferred a shmem page from file cache to swap cache, then let that page make its way around the LRU again before being written and freed. The idea was that people use tmpfs because they want those pages to stay in RAM; so although we give it an overflow to swap, we should resist writing too soon, giving those pages a second chance before they can be reclaimed. That was always questionable, and I've toyed with this patch for years; but never had a clear justification to depart from the original design. It became more questionable in 2.6.28, when the split LRU patches classed shmem and tmpfs pages as SwapBacked rather than as file_cache: that in itself gives them more resistance to reclaim than normal file pages. I prepared this patch for 2.6.29, but the merge window arrived before I'd completed gathering statistics to justify sending it in. Then while comparing SLQB against SLUB, running SLUB on a laptop I'd habitually used with SLAB, I found SLUB to run my tmpfs kbuild swapping tests five times slower than SLAB or SLQB - other machines slower too, but nowhere near so bad. Simpler "cp -a" swapping tests showed the same. slub_max_order=0 brings sanity to all, but heavy swapping is too far from normal to justify such a tuning. The crucial factor on that laptop turns out to be that I'm using an SD card for swap. What happens is this: By default, SLUB uses order-2 pages for shmem_inode_cache (and many other fs inodes), so creating tmpfs files under memory pressure brings lumpy reclaim into play. One subpage of the order is chosen from the bottom of the LRU as usual, then the other three picked out from their random positions on the LRUs. In a tmpfs load, many of these pages will be ones which already passed through shmem_writepage, so already have swap allocated. And though their offsets on swap were probably allocated sequentially, now that the pages are picked off at random, their swap offsets are scattered. But the flash storage on the SD card is very sensitive to having its writes merged: once swap is written at scattered offsets, performance falls apart. Rotating disk seeks increase too, but less disastrously. So: stop giving shmem/tmpfs pages a second pass around the LRU, write them out to swap as soon as their swap has been allocated. It's surely possible to devise an artificial load which runs faster the old way, one whose sizing is such that the tmpfs pages on their second pass are the ones that are wanted again, and other pages not. But I've not yet found such a load: on all machines, under the loads I've tried, immediate swap_writepage speeds up shmem swapping: especially when using the SLUB allocator (and more effectively than slub_max_order=0), but also with the others; and it also reduces the variance between runs. How much faster varies widely: a factor of five is rare, 5% is common. One load which might have suffered: imagine a swapping shmem load in a limited mem_cgroup on a machine with plenty of memory. Before 2.6.29 the swapcache was not charged, and such a load would have run quickest with the shmem swapcache never written to swap. But now swapcache is charged, so even this load benefits from shmem_writepage directly to swap. Apologies for the #ifndef CONFIG_SWAP swap_writepage() stub in swap.h: it's silly because that will never get called; but refactoring shmem.c sensibly according to CONFIG_SWAP will be a separate task. Signed-off-by: Hugh Dickins Acked-by: Pekka Enberg Acked-by: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index b8b0c4ce83e..62d81435347 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -382,6 +382,11 @@ static inline struct page *swapin_readahead(swp_entry_t swp, gfp_t gfp_mask, return NULL; } +static inline int swap_writepage(struct page *p, struct writeback_control *wbc) +{ + return 0; +} + static inline struct page *lookup_swap_cache(swp_entry_t swp) { return NULL; -- cgit v1.2.3 From a8af78982ff4c0b3731527b0217d286a343a3089 Mon Sep 17 00:00:00 2001 From: Magnus Damm Date: Tue, 31 Mar 2009 15:23:37 -0700 Subject: pm: rework includes, remove arch ifdefs Make the following header file changes: - remove arch ifdefs and asm/suspend.h from linux/suspend.h - add asm/suspend.h to disk.c (for arch_prepare_suspend()) - add linux/io.h to swsusp.c (for ioremap()) - x86 32/64 bit compile fixes Signed-off-by: Magnus Damm Cc: Paul Mundt Acked-by: "Rafael J. Wysocki" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/suspend.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/suspend.h b/include/linux/suspend.h index c7d9bb1832b..3e3a4364cbf 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -1,9 +1,6 @@ #ifndef _LINUX_SUSPEND_H #define _LINUX_SUSPEND_H -#if defined(CONFIG_X86) || defined(CONFIG_FRV) || defined(CONFIG_PPC32) || defined(CONFIG_PPC64) -#include -#endif #include #include #include -- cgit v1.2.3 From 53d6660836f233df66490707365ab177e5fb2bb4 Mon Sep 17 00:00:00 2001 From: "J. R. Okajima" Date: Tue, 31 Mar 2009 15:23:43 -0700 Subject: loop: add ioctl to resize a loop device Add the ability to 'resize' the loop device on the fly. One practical application is a loop file with XFS filesystem, already mounted: You can easily enlarge the file (append some bytes) and then call ioctl(fd, LOOP_SET_CAPACITY, new); The loop driver will learn about the new size and you can use xfs_growfs later on, which will allow you to use full capacity of the loop file without the need to unmount. Test app: #include #include #include #include #include #include #include #include #include #include #include #define _GNU_SOURCE #include char *me; void usage(FILE *f) { fprintf(f, "%s [options] loop_dev [backend_file]\n" "-s, --set new_size_in_bytes\n" "\twhen backend_file is given, " "it will be expanded too while keeping the original contents\n", me); } struct option opts[] = { { .name = "set", .has_arg = 1, .flag = NULL, .val = 's' }, { .name = "help", .has_arg = 0, .flag = NULL, .val = 'h' } }; void err_size(char *name, __u64 old) { fprintf(stderr, "size must be larger than current %s (%llu)\n", name, old); } int main(int argc, char *argv[]) { int fd, err, c, i, bfd; ssize_t ssz; size_t sz; __u64 old, new, append; char a[BUFSIZ]; struct stat st; FILE *out; char *backend, *dev; err = EINVAL; out = stderr; me = argv[0]; new = 0; while ((c = getopt_long(argc, argv, "s:h", opts, &i)) != -1) { switch (c) { case 's': errno = 0; new = strtoull(optarg, NULL, 0); if (errno) { err = errno; perror(argv[i]); goto out; } break; case 'h': err = 0; out = stdout; goto err; default: perror(argv[i]); goto err; } } if (optind < argc) dev = argv[optind++]; else goto err; fd = open(dev, O_RDONLY); if (fd < 0) { err = errno; perror(dev); goto out; } err = ioctl(fd, BLKGETSIZE64, &old); if (err) { err = errno; perror("ioctl BLKGETSIZE64"); goto out; } if (!new) { printf("%llu\n", old); goto out; } if (new < old) { err = EINVAL; err_size(dev, old); goto out; } if (optind < argc) { backend = argv[optind++]; bfd = open(backend, O_WRONLY|O_APPEND); if (bfd < 0) { err = errno; perror(backend); goto out; } err = fstat(bfd, &st); if (err) { err = errno; perror(backend); goto out; } if (new < st.st_size) { err = EINVAL; err_size(backend, st.st_size); goto out; } append = new - st.st_size; sz = sizeof(a); while (append > 0) { if (append < sz) sz = append; ssz = write(bfd, a, sz); if (ssz != sz) { err = errno; perror(backend); goto out; } append -= sz; } err = fsync(bfd); if (err) { err = errno; perror(backend); goto out; } } err = ioctl(fd, LOOP_SET_CAPACITY, new); if (err) { err = errno; perror("ioctl LOOP_SET_CAPACITY"); } goto out; err: usage(out); out: return err; } Signed-off-by: J. R. Okajima Signed-off-by: Tomas Matejicek Cc: Cc: Karel Zak Cc: Jens Axboe Cc: Al Viro Cc: Christoph Hellwig Cc: Akinobu Mita Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/loop.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/loop.h b/include/linux/loop.h index 6ffd6db5bb0..40725447f5e 100644 --- a/include/linux/loop.h +++ b/include/linux/loop.h @@ -160,5 +160,6 @@ int loop_unregister_transfer(int number); #define LOOP_SET_STATUS64 0x4C04 #define LOOP_GET_STATUS64 0x4C05 #define LOOP_CHANGE_FD 0x4C06 +#define LOOP_SET_CAPACITY 0x4C07 #endif -- cgit v1.2.3 From c2d7543851849a6923680cdd7e1047ed1a84a1c5 Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Tue, 31 Mar 2009 15:23:46 -0700 Subject: filesystem freeze: allow SysRq emergency thaw to thaw frozen filesystems Now that the filesystem freeze operation has been elevated to the VFS, and is just an ioctl away, some sort of safety net for unintentionally frozen root filesystems may be in order. The timeout thaw originally proposed did not get merged, but perhaps something like this would be useful in emergencies. For example, freeze /path/to/mountpoint may freeze your root filesystem if you forgot that you had that unmounted. I chose 'j' as the last remaining character other than 'h' which is sort of reserved for help (because help is generated on any unknown character). I've tested this on a non-root fs with multiple (nested) freezers, as well as on a system rendered unresponsive due to a frozen root fs. [randy.dunlap@oracle.com: emergency thaw only if CONFIG_BLOCK enabled] Signed-off-by: Eric Sandeen Cc: Takashi Sato Signed-off-by: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 87e7bfc5ebd..61211ad823f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1878,6 +1878,7 @@ extern struct block_device *open_by_devnum(dev_t, fmode_t); extern void invalidate_bdev(struct block_device *); extern int sync_blockdev(struct block_device *bdev); extern struct super_block *freeze_bdev(struct block_device *); +extern void emergency_thaw_all(void); extern int thaw_bdev(struct block_device *bdev, struct super_block *sb); extern int fsync_bdev(struct block_device *); extern int fsync_super(struct super_block *); -- cgit v1.2.3 From 311d07611e8b354cc1ee6546e4c574c01111adc8 Mon Sep 17 00:00:00 2001 From: Cyrill Gorcunov Date: Tue, 31 Mar 2009 15:23:51 -0700 Subject: introduce pr_cont() macro We cover all log-levels by pr_... macros except KERN_CONT one. Add it for convenience. Signed-off-by: Cyrill Gorcunov Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Harvey Harrison Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index f81d80f47dc..e720b0da775 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -353,6 +353,8 @@ static inline char *pack_hex_byte(char *buf, u8 byte) printk(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__) #define pr_info(fmt, ...) \ printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__) +#define pr_cont(fmt, ...) \ + printk(KERN_CONT fmt, ##__VA_ARGS__) /* If you are writing a driver, please use dev_dbg instead */ #if defined(DEBUG) -- cgit v1.2.3 From bcd0b235bf3808dec5115c381cd55568f63b85f0 Mon Sep 17 00:00:00 2001 From: Davide Libenzi Date: Tue, 31 Mar 2009 15:24:18 -0700 Subject: eventfd: improve support for semaphore-like behavior People started using eventfd in a semaphore-like way where before they were using pipes. That is, counter-based resource access. Where a "wait()" returns immediately by decrementing the counter by one, if counter is greater than zero. Otherwise will wait. And where a "post(count)" will add count to the counter releasing the appropriate amount of waiters. If eventfd the "post" (write) part is fine, while the "wait" (read) does not dequeue 1, but the whole counter value. The problem with eventfd is that a read() on the fd returns and wipes the whole counter, making the use of it as semaphore a little bit more cumbersome. You can do a read() followed by a write() of COUNTER-1, but IMO it's pretty easy and cheap to make this work w/out extra steps. This patch introduces a new eventfd flag that tells eventfd to only dequeue 1 from the counter, allowing simple read/write to make it behave like a semaphore. Simple test here: http://www.xmailserver.org/eventfd-sem.c To be back-compatible with earlier kernels, userspace applications should probe for the availability of this feature via #ifdef EFD_SEMAPHORE fd = eventfd2 (CNT, EFD_SEMAPHORE); if (fd == -1 && errno == EINVAL) #else #endif Signed-off-by: Davide Libenzi Cc: Tested-by: Michael Kerrisk Cc: Ulrich Drepper Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/eventfd.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h index a667637b54e..f45a8ae5f82 100644 --- a/include/linux/eventfd.h +++ b/include/linux/eventfd.h @@ -13,10 +13,20 @@ /* For O_CLOEXEC and O_NONBLOCK */ #include -/* Flags for eventfd2. */ +/* + * CAREFUL: Check include/asm-generic/fcntl.h when defining + * new flags, since they might collide with O_* ones. We want + * to re-use O_* flags that couldn't possibly have a meaning + * from eventfd, in order to leave a free define-space for + * shared O_* flags. + */ +#define EFD_SEMAPHORE (1 << 0) #define EFD_CLOEXEC O_CLOEXEC #define EFD_NONBLOCK O_NONBLOCK +#define EFD_SHARED_FCNTL_FLAGS (O_CLOEXEC | O_NONBLOCK) +#define EFD_FLAGS_SET (EFD_SHARED_FCNTL_FLAGS | EFD_SEMAPHORE) + struct file *eventfd_fget(int fd); int eventfd_signal(struct file *file, int n); -- cgit v1.2.3 From 4ede816ac36e027db5fe0051ad9c73f76db63772 Mon Sep 17 00:00:00 2001 From: Davide Libenzi Date: Tue, 31 Mar 2009 15:24:20 -0700 Subject: epoll keyed wakeups: add __wake_up_locked_key() and __wake_up_sync_key() This patchset introduces wakeup hints for some of the most popular (from epoll POV) devices, so that epoll code can avoid spurious wakeups on its waiters. The problem with epoll is that the callback-based wakeups do not, ATM, carry any information about the events the wakeup is related to. So the only choice epoll has (not being able to call f_op->poll() from inside the callback), is to add the file* to a ready-list and resolve the real events later on, at epoll_wait() (or its own f_op->poll()) time. This can cause spurious wakeups, since the wake_up() itself might be for an event the caller is not interested into. The rate of these spurious wakeup can be pretty high in case of many network sockets being monitored. By allowing devices to report the events the wakeups refer to (at least the two major classes - POLLIN/POLLOUT), we are able to spare useless wakeups by proper handling inside the epoll's poll callback. Epoll will have in any case to call f_op->poll() on the file* later on, since the change to be done in order to have the full event set sent via wakeup, is too invasive for the way our f_op->poll() system works (the full event set is calculated inside the poll function - there are too many of them to even start thinking the change - also poll/select would need change too). Epoll is changed in a way that both devices which send event hints, and the ones that don't, are correctly handled. The former will gain some efficiency though. As a general rule for devices, would be to add an event mask by using key-aware wakeup macros, when making up poll wait queues. I tested it (together with the epoll's poll fix patch Andrew has in -mm) and wakeups for the supported devices are correctly filtered. Test program available here: http://www.xmailserver.org/epoll_test.c This patch: Nothing revolutionary here. Just using the available "key" that our wakeup core already support. The __wake_up_locked_key() was no brainer, since both __wake_up_locked() and __wake_up_locked_key() are thin wrappers around __wake_up_common(). The __wake_up_sync() function had a body, so the choice was between borrowing the body for __wake_up_sync_key() and calling it from __wake_up_sync(), or make an inline and calling it from both. I chose the former since in most archs it all resolves to "mov $0, REG; jmp ADDR". Signed-off-by: Davide Libenzi Cc: Alan Cox Cc: Ingo Molnar Cc: David Miller Cc: William Lee Irwin III Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/wait.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/wait.h b/include/linux/wait.h index a210ede73b5..0d2eeb03a71 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -135,8 +135,11 @@ static inline void __remove_wait_queue(wait_queue_head_t *head, void __wake_up_common(wait_queue_head_t *q, unsigned int mode, int nr_exclusive, int sync, void *key); void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key); -extern void __wake_up_locked(wait_queue_head_t *q, unsigned int mode); -extern void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr); +void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key); +void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr, + void *key); +void __wake_up_locked(wait_queue_head_t *q, unsigned int mode); +void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr); void __wake_up_bit(wait_queue_head_t *, void *, int); int __wait_on_bit(wait_queue_head_t *, struct wait_bit_queue *, int (*)(void *), unsigned); int __wait_on_bit_lock(wait_queue_head_t *, struct wait_bit_queue *, int (*)(void *), unsigned); -- cgit v1.2.3 From c0da37753695e010776ccf2200a5731e0f88a9f3 Mon Sep 17 00:00:00 2001 From: Davide Libenzi Date: Tue, 31 Mar 2009 15:24:20 -0700 Subject: epoll keyed wakeups: introduce new *_poll() wakeup macros Introduce new wakeup macros that allow passing an event mask to the wakeup targets. They exactly mimic their non-_poll() counterpart, with the added event mask passing capability. I did add only the ones currently requested, avoiding the _nr() and _all() for the moment. Signed-off-by: Davide Libenzi Cc: Alan Cox Cc: Ingo Molnar Cc: David Miller Cc: William Lee Irwin III Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/wait.h | 22 +++++++++------------- 1 file changed, 9 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/wait.h b/include/linux/wait.h index 0d2eeb03a71..5d631c17eae 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -158,21 +158,17 @@ wait_queue_head_t *bit_waitqueue(void *, int); #define wake_up_interruptible_all(x) __wake_up(x, TASK_INTERRUPTIBLE, 0, NULL) #define wake_up_interruptible_sync(x) __wake_up_sync((x), TASK_INTERRUPTIBLE, 1) -#ifdef CONFIG_DEBUG_LOCK_ALLOC /* - * macro to avoid include hell + * Wakeup macros to be used to report events to the targets. */ -#define wake_up_nested(x, s) \ -do { \ - unsigned long flags; \ - \ - spin_lock_irqsave_nested(&(x)->lock, flags, (s)); \ - wake_up_locked(x); \ - spin_unlock_irqrestore(&(x)->lock, flags); \ -} while (0) -#else -#define wake_up_nested(x, s) wake_up(x) -#endif +#define wake_up_poll(x, m) \ + __wake_up(x, TASK_NORMAL, 1, (void *) (m)) +#define wake_up_locked_poll(x, m) \ + __wake_up_locked_key((x), TASK_NORMAL, (void *) (m)) +#define wake_up_interruptible_poll(x, m) \ + __wake_up(x, TASK_INTERRUPTIBLE, 1, (void *) (m)) +#define wake_up_interruptible_sync_poll(x, m) \ + __wake_up_sync_key((x), TASK_INTERRUPTIBLE, 1, (void *) (m)) #define __wait_event(wq, condition) \ do { \ -- cgit v1.2.3 From 364fdbc00fbdd409ade63500710123fe323aa164 Mon Sep 17 00:00:00 2001 From: Anton Vorontsov Date: Tue, 31 Mar 2009 15:24:36 -0700 Subject: spi_mpc83xx: rework chip selects handling The main purpose of this patch is to pass 'struct spi_device' to the chip select handling routines. This is needed so that we could implement full-fledged OpenFirmware support for this driver. While at it, also: - Replace two {de,activate}_cs routines by single cs_contol(). - Don't duplicate platform data callbacks in mpc83xx_spi struct. Signed-off-by: Anton Vorontsov Cc: David Brownell Cc: Benjamin Herrenschmidt Cc: Kumar Gala Cc: Grant Likely Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fsl_devices.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsl_devices.h b/include/linux/fsl_devices.h index d9051d717d2..7bc1b643d37 100644 --- a/include/linux/fsl_devices.h +++ b/include/linux/fsl_devices.h @@ -95,14 +95,15 @@ struct fsl_usb2_platform_data { #define FSL_USB2_PORT0_ENABLED 0x00000001 #define FSL_USB2_PORT1_ENABLED 0x00000002 +struct spi_device; + struct fsl_spi_platform_data { u32 initial_spmode; /* initial SPMODE value */ u16 bus_num; bool qe_mode; /* board specific information */ u16 max_chipselect; - void (*activate_cs)(u8 cs, u8 polarity); - void (*deactivate_cs)(u8 cs, u8 polarity); + void (*cs_control)(struct spi_device *spi, bool on); u32 sysclk; }; -- cgit v1.2.3 From 35b4b3c0c1265f1a7342574be393c157601401f0 Mon Sep 17 00:00:00 2001 From: Anton Vorontsov Date: Tue, 31 Mar 2009 15:24:37 -0700 Subject: spi_mpc83xx: add OF platform driver bindings Implement full support for OF SPI bindings. Now the driver can manage its own chip selects without any help from the board files and/or fsl_soc constructors. The "legacy" code is well isolated and could be removed as time goes by. Signed-off-by: Anton Vorontsov Cc: David Brownell Cc: Benjamin Herrenschmidt Cc: Kumar Gala Cc: Grant Likely Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fsl_devices.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fsl_devices.h b/include/linux/fsl_devices.h index 7bc1b643d37..7ef1caf5026 100644 --- a/include/linux/fsl_devices.h +++ b/include/linux/fsl_devices.h @@ -99,7 +99,7 @@ struct spi_device; struct fsl_spi_platform_data { u32 initial_spmode; /* initial SPMODE value */ - u16 bus_num; + s16 bus_num; bool qe_mode; /* board specific information */ u16 max_chipselect; -- cgit v1.2.3 From 79955898f961a870cbcc58f6ae13f3741a909da5 Mon Sep 17 00:00:00 2001 From: Ian Kent Date: Tue, 31 Mar 2009 15:24:45 -0700 Subject: autofs4: fix kernel includes autofs_dev-ioctl.h is included by both the kernel module and user space tools and it includes two kernel header files. Compiles work if the kernel headers are installed but fail otherwise. Signed-off-by: Ian Kent Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/auto_dev-ioctl.h | 7 ++++++- include/linux/auto_fs.h | 6 ++++-- 2 files changed, 10 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/auto_dev-ioctl.h b/include/linux/auto_dev-ioctl.h index 91a773993a5..850f39b33e7 100644 --- a/include/linux/auto_dev-ioctl.h +++ b/include/linux/auto_dev-ioctl.h @@ -10,8 +10,13 @@ #ifndef _LINUX_AUTO_DEV_IOCTL_H #define _LINUX_AUTO_DEV_IOCTL_H +#include + +#ifdef __KERNEL__ #include -#include +#else +#include +#endif /* __KERNEL__ */ #define AUTOFS_DEVICE_NAME "autofs" diff --git a/include/linux/auto_fs.h b/include/linux/auto_fs.h index c21e5972a3e..63265852b7d 100644 --- a/include/linux/auto_fs.h +++ b/include/linux/auto_fs.h @@ -17,11 +17,13 @@ #ifdef __KERNEL__ #include #include +#include +#include +#else #include +#include #endif /* __KERNEL__ */ -#include - /* This file describes autofs v3 */ #define AUTOFS_PROTO_VERSION 3 -- cgit v1.2.3 From 78d89ef40c2ff7265df077e20c4d76be7d415204 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Tue, 31 Mar 2009 15:24:48 -0700 Subject: rtc: convert LEAP_YEAR into an inline - the LEAP_YEAR macro is buggy - it references its arg multiple times. Fix this by turning it into a C function. - give it a more approriate name - Move it to rtc.h so that other .c files can use it, instead of copying it. Cc: dann frazier Acked-by: Alessandro Zummo Cc: stephane eranian Cc: "Luck, Tony" Cc: David Brownell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rtc.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 4046b75563c..60f88a7fb13 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -99,6 +99,7 @@ struct rtc_pll_info { #ifdef __KERNEL__ +#include #include extern int rtc_month_days(unsigned int month, unsigned int year); @@ -232,6 +233,11 @@ int rtc_register(rtc_task_t *task); int rtc_unregister(rtc_task_t *task); int rtc_control(rtc_task_t *t, unsigned int cmd, unsigned long arg); +static inline bool is_leap_year(unsigned int year) +{ + return (!(year % 4) && (year % 100)) || !(year % 400); +} + #endif /* __KERNEL__ */ #endif /* _LINUX_RTC_H_ */ -- cgit v1.2.3 From 614c0dc93284404be2a4d5750c79bb95f2b6c980 Mon Sep 17 00:00:00 2001 From: Krzysztof Helt Date: Tue, 31 Mar 2009 15:25:15 -0700 Subject: cirrusfb: add accelerator constant Add an accelerator constant so almost all Cirrus are recognized as accelerators by the fbset command. Signed-off-by: Krzysztof Helt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index 31527e17076..fe7d0d7907a 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -123,6 +123,7 @@ struct dentry; #define FB_ACCEL_TRIDENT_3DIMAGE 51 /* Trident 3DImage */ #define FB_ACCEL_TRIDENT_BLADE3D 52 /* Trident Blade3D */ #define FB_ACCEL_TRIDENT_BLADEXP 53 /* Trident BladeXP */ +#define FB_ACCEL_CIRRUS_ALPINE 53 /* Cirrus Logic 543x/544x/5480 */ #define FB_ACCEL_NEOMAGIC_NM2070 90 /* NeoMagic NM2070 */ #define FB_ACCEL_NEOMAGIC_NM2090 91 /* NeoMagic NM2090 */ #define FB_ACCEL_NEOMAGIC_NM2093 92 /* NeoMagic NM2093 */ -- cgit v1.2.3 From 6a7f2829b5f8be124e168265f176dbbbea8861a0 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Tue, 31 Mar 2009 15:25:19 -0700 Subject: fbdev: uninline lock_fb_info() Before: text data bss dec hex filename 3648 2910 32 6590 19be drivers/video/backlight/backlight.o 3226 2812 32 6070 17b6 drivers/video/backlight/lcd.o 30990 16688 8480 56158 db5e drivers/video/console/fbcon.o 15488 8400 24 23912 5d68 drivers/video/fbmem.o After: text data bss dec hex filename 3537 2870 32 6439 1927 drivers/video/backlight/backlight.o 3131 2772 32 5935 172f drivers/video/backlight/lcd.o 30876 16648 8480 56004 dac4 drivers/video/console/fbcon.o 15506 8400 24 23930 5d7a drivers/video/fbmem.o Cc: Andrea Righi Cc: Geert Uytterhoeven Cc: Krzysztof Helt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fb.h | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index fe7d0d7907a..f563c501393 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -961,15 +961,7 @@ extern struct fb_info *registered_fb[FB_MAX]; extern int num_registered_fb; extern struct class *fb_class; -static inline int lock_fb_info(struct fb_info *info) -{ - mutex_lock(&info->lock); - if (!info->fbops) { - mutex_unlock(&info->lock); - return 0; - } - return 1; -} +extern int lock_fb_info(struct fb_info *info); static inline void unlock_fb_info(struct fb_info *info) { -- cgit v1.2.3 From 6fd5c665d8fe9da5f2081f0b3ca8054f0f730b1a Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Wed, 1 Apr 2009 21:42:23 +0200 Subject: include/linux/hdreg.h: cover struct hd_driveid with #ifndef/#endif __KERNEL__ Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/hdreg.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hdreg.h b/include/linux/hdreg.h index ed21bd3dbd2..47fcb05af8b 100644 --- a/include/linux/hdreg.h +++ b/include/linux/hdreg.h @@ -448,6 +448,7 @@ enum { #define __NEW_HD_DRIVE_ID +#ifndef __KERNEL__ /* * Structure returned by HDIO_GET_IDENTITY, as per ANSI NCITS ATA6 rev.1b spec. * @@ -699,6 +700,7 @@ struct hd_driveid { * 7:0 Signature */ }; +#endif /* __KERNEL__ */ /* * IDE "nice" flags. These are used on a per drive basis to determine -- cgit v1.2.3 From dafd01cc14a38690c87981eb2670d9c95f799ffd Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Wed, 1 Apr 2009 21:42:25 +0200 Subject: include/linux/hdreg.h: cover WIN_* and friends with #ifndef/#endif __KERNEL__ Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/hdreg.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hdreg.h b/include/linux/hdreg.h index 47fcb05af8b..101eb91de22 100644 --- a/include/linux/hdreg.h +++ b/include/linux/hdreg.h @@ -191,6 +191,7 @@ typedef struct hd_drive_hob_hdr { #define TASKFILE_INVALID 0x7fff #endif +#ifndef __KERNEL__ /* ATA/ATAPI Commands pre T13 Spec */ #define WIN_NOP 0x00 /* @@ -379,6 +380,7 @@ typedef struct hd_drive_hob_hdr { #define SECURITY_ERASE_UNIT 0xBD #define SECURITY_FREEZE_LOCK 0xBE #define SECURITY_DISABLE_PASSWORD 0xBF +#endif /* __KERNEL__ */ struct hd_geometry { unsigned char heads; -- cgit v1.2.3 From 4fe6e30645de0b7a179892d83049580bf72bcff2 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Wed, 1 Apr 2009 21:42:25 +0200 Subject: include/linux/hdreg.h: remove unused defines * Move HD_IRQ define to drivers/block/hd.c (only user). * Remove unused *_STAT, *_ERR, HD_*, CD, IO, REL and TAG_MASK defines. Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/hdreg.h | 58 --------------------------------------------------- 1 file changed, 58 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hdreg.h b/include/linux/hdreg.h index 101eb91de22..3bc8f9f986b 100644 --- a/include/linux/hdreg.h +++ b/include/linux/hdreg.h @@ -3,64 +3,6 @@ #ifdef __KERNEL__ #include - -/* - * This file contains some defines for the AT-hd-controller. - * Various sources. - */ - -/* ide.c has its own port definitions in "ide.h" */ - -#define HD_IRQ 14 - -/* Hd controller regs. Ref: IBM AT Bios-listing */ -#define HD_DATA 0x1f0 /* _CTL when writing */ -#define HD_ERROR 0x1f1 /* see err-bits */ -#define HD_NSECTOR 0x1f2 /* nr of sectors to read/write */ -#define HD_SECTOR 0x1f3 /* starting sector */ -#define HD_LCYL 0x1f4 /* starting cylinder */ -#define HD_HCYL 0x1f5 /* high byte of starting cyl */ -#define HD_CURRENT 0x1f6 /* 101dhhhh , d=drive, hhhh=head */ -#define HD_STATUS 0x1f7 /* see status-bits */ -#define HD_FEATURE HD_ERROR /* same io address, read=error, write=feature */ -#define HD_PRECOMP HD_FEATURE /* obsolete use of this port - predates IDE */ -#define HD_COMMAND HD_STATUS /* same io address, read=status, write=cmd */ - -#define HD_CMD 0x3f6 /* used for resets */ -#define HD_ALTSTATUS 0x3f6 /* same as HD_STATUS but doesn't clear irq */ - -/* remainder is shared between hd.c, ide.c, ide-cd.c, and the hdparm utility */ - -/* Bits of HD_STATUS */ -#define ERR_STAT 0x01 -#define INDEX_STAT 0x02 -#define ECC_STAT 0x04 /* Corrected error */ -#define DRQ_STAT 0x08 -#define SEEK_STAT 0x10 -#define SRV_STAT 0x10 -#define WRERR_STAT 0x20 -#define READY_STAT 0x40 -#define BUSY_STAT 0x80 - -/* Bits for HD_ERROR */ -#define MARK_ERR 0x01 /* Bad address mark */ -#define ILI_ERR 0x01 /* Illegal Length Indication (ATAPI) */ -#define TRK0_ERR 0x02 /* couldn't find track 0 */ -#define EOM_ERR 0x02 /* End Of Media (ATAPI) */ -#define ABRT_ERR 0x04 /* Command aborted */ -#define MCR_ERR 0x08 /* media change request */ -#define ID_ERR 0x10 /* ID field not found */ -#define MC_ERR 0x20 /* media changed */ -#define ECC_ERR 0x40 /* Uncorrectable ECC error */ -#define BBD_ERR 0x80 /* pre-EIDE meaning: block marked bad */ -#define ICRC_ERR 0x80 /* new meaning: CRC error during transfer */ -#define LFS_ERR 0xf0 /* Last Failed Sense (ATAPI) */ - -/* Bits of HD_NSECTOR */ -#define CD 0x01 -#define IO 0x02 -#define REL 0x04 -#define TAG_MASK 0xf8 #endif /* __KERNEL__ */ #include -- cgit v1.2.3 From eae6c2b6414fc6673ac5415442fe463c01005366 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Wed, 1 Apr 2009 21:42:26 +0200 Subject: remove include from All users that need have been fixed to include it directly. Cc: Christoph Hellwig Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/hdreg.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hdreg.h b/include/linux/hdreg.h index 3bc8f9f986b..29ee2873f4a 100644 --- a/include/linux/hdreg.h +++ b/include/linux/hdreg.h @@ -1,10 +1,6 @@ #ifndef _LINUX_HDREG_H #define _LINUX_HDREG_H -#ifdef __KERNEL__ -#include -#endif /* __KERNEL__ */ - #include /* -- cgit v1.2.3 From d9de451989a88a2003ca06e524aca4665c0c7f06 Mon Sep 17 00:00:00 2001 From: Hans-Christian Egtvedt Date: Wed, 1 Apr 2009 15:47:02 +0200 Subject: dw_dmac: add cyclic API to DW DMA driver This patch adds a cyclic DMA interface to the DW DMA driver. This is very useful if you want to use the DMA controller in combination with a sound device which uses cyclic buffers. Using a DMA channel for cyclic DMA will disable the possibility to use it as a normal DMA engine until the user calls the cyclic free function on the DMA channel. Also a cyclic DMA list can not be prepared if the channel is already active. Signed-off-by: Hans-Christian Egtvedt Acked-by: Haavard Skinnemoen Acked-by: Maciej Sosnowski Signed-off-by: Dan Williams --- include/linux/dw_dmac.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dw_dmac.h b/include/linux/dw_dmac.h index d797dde247f..c8aad713a04 100644 --- a/include/linux/dw_dmac.h +++ b/include/linux/dw_dmac.h @@ -74,4 +74,23 @@ struct dw_dma_slave { #define DWC_CFGL_HS_DST_POL (1 << 18) /* dst handshake active low */ #define DWC_CFGL_HS_SRC_POL (1 << 19) /* src handshake active low */ +/* DMA API extensions */ +struct dw_cyclic_desc { + struct dw_desc **desc; + unsigned long periods; + void (*period_callback)(void *param); + void *period_callback_param; +}; + +struct dw_cyclic_desc *dw_dma_cyclic_prep(struct dma_chan *chan, + dma_addr_t buf_addr, size_t buf_len, size_t period_len, + enum dma_data_direction direction); +void dw_dma_cyclic_free(struct dma_chan *chan); +int dw_dma_cyclic_start(struct dma_chan *chan); +void dw_dma_cyclic_stop(struct dma_chan *chan); + +dma_addr_t dw_dma_get_src_addr(struct dma_chan *chan); + +dma_addr_t dw_dma_get_dst_addr(struct dma_chan *chan); + #endif /* DW_DMAC_H */ -- cgit v1.2.3 From 45194e4f89fbdd97a2b7d2698c05f0b00c19e820 Mon Sep 17 00:00:00 2001 From: Cheng Renquan Date: Thu, 2 Apr 2009 19:55:28 +0100 Subject: dm target: remove struct tt_internal The tt_internal is really just a list_head to manage registered target_type in a double linked list, Here embed the list_head into target_type directly, 1. to avoid kmalloc/kfree; 2. then tt_internal is really unneeded; Cc: stable@kernel.org Signed-off-by: Cheng Renquan Signed-off-by: Alasdair G Kergon Reviewed-by: Alasdair G Kergon --- include/linux/device-mapper.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 8209e08969f..66ec05a5795 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -139,6 +139,9 @@ struct target_type { dm_ioctl_fn ioctl; dm_merge_fn merge; dm_busy_fn busy; + + /* For internal device-mapper use. */ + struct list_head list; }; struct io_restrictions { -- cgit v1.2.3 From ec44ab9d6681ddf9026b593e866bec9c0e075e1d Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Thu, 2 Apr 2009 19:55:30 +0100 Subject: dm log: remove struct dm_dirty_log_internal Remove the 'dm_dirty_log_internal' structure. The resulting cleanup eliminates extra memory allocations. Therefore exposing the internal list_head to the external 'dm_dirty_log_type' structure is a worthwhile compromise. Signed-off-by: Mike Snitzer Signed-off-by: Alasdair G Kergon --- include/linux/dm-dirty-log.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dm-dirty-log.h b/include/linux/dm-dirty-log.h index 600c5fb2daa..727602b686d 100644 --- a/include/linux/dm-dirty-log.h +++ b/include/linux/dm-dirty-log.h @@ -28,6 +28,9 @@ struct dm_dirty_log_type { const char *name; struct module *module; + /* For internal device-mapper use */ + struct list_head list; + int (*ctr)(struct dm_dirty_log *log, struct dm_target *ti, unsigned argc, char **argv); void (*dtr)(struct dm_dirty_log *log); -- cgit v1.2.3 From 7513c2a761d69d2a93f17146b3563527d3618ba0 Mon Sep 17 00:00:00 2001 From: Jonathan Brassow Date: Thu, 2 Apr 2009 19:55:30 +0100 Subject: dm raid1: add is_remote_recovering hook for clusters The logging API needs an extra function to make cluster mirroring possible. This new function allows us to check whether a mirror region is being recovered on another machine in the cluster. This helps us prevent simultaneous recovery I/O and process I/O to the same locations on disk. Cluster-aware log modules will implement this function. Single machine log modules will not. So, there is no performance penalty for single machine mirrors. Signed-off-by: Jonathan Brassow Acked-by: Heinz Mauelshagen Signed-off-by: Alasdair G Kergon --- include/linux/dm-dirty-log.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dm-dirty-log.h b/include/linux/dm-dirty-log.h index 727602b686d..5e8b11d88f6 100644 --- a/include/linux/dm-dirty-log.h +++ b/include/linux/dm-dirty-log.h @@ -116,6 +116,16 @@ struct dm_dirty_log_type { */ int (*status)(struct dm_dirty_log *log, status_type_t status_type, char *result, unsigned maxlen); + + /* + * is_remote_recovering is necessary for cluster mirroring. It provides + * a way to detect recovery on another node, so we aren't writing + * concurrently. This function is likely to block (when a cluster log + * is used). + * + * Returns: 0, 1 + */ + int (*is_remote_recovering)(struct dm_dirty_log *log, region_t region); }; int dm_dirty_log_type_register(struct dm_dirty_log_type *type); -- cgit v1.2.3 From ee3b4290aec03022cfb67c9adba9f1b3215245f0 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Thu, 2 Apr 2009 16:56:30 -0700 Subject: generic debug pagealloc: build fix This fixes a build failure with generic debug pagealloc: mm/debug-pagealloc.c: In function 'set_page_poison': mm/debug-pagealloc.c:8: error: 'struct page' has no member named 'debug_flags' mm/debug-pagealloc.c: In function 'clear_page_poison': mm/debug-pagealloc.c:13: error: 'struct page' has no member named 'debug_flags' mm/debug-pagealloc.c: In function 'page_poison': mm/debug-pagealloc.c:18: error: 'struct page' has no member named 'debug_flags' mm/debug-pagealloc.c: At top level: mm/debug-pagealloc.c:120: error: redefinition of 'kernel_map_pages' include/linux/mm.h:1278: error: previous definition of 'kernel_map_pages' was here mm/debug-pagealloc.c: In function 'kernel_map_pages': mm/debug-pagealloc.c:122: error: 'debug_pagealloc_enabled' undeclared (first use in this function) by fixing - debug_flags should be in struct page - define DEBUG_PAGEALLOC config option for all architectures Signed-off-by: Akinobu Mita Reported-by: Alexander Beregalov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index ddadb4defe0..0e80e26ecf2 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -95,6 +95,9 @@ struct page { void *virtual; /* Kernel virtual address (NULL if not kmapped, ie. highmem) */ #endif /* WANT_PAGE_VIRTUAL */ +#ifdef CONFIG_WANT_PAGE_DEBUG_FLAGS + unsigned long debug_flags; /* Use atomic bitops on this */ +#endif }; /* @@ -175,9 +178,6 @@ struct vm_area_struct { #ifdef CONFIG_NUMA struct mempolicy *vm_policy; /* NUMA policy for the VMA */ #endif -#ifdef CONFIG_WANT_PAGE_DEBUG_FLAGS - unsigned long debug_flags; /* Use atomic bitops on this */ -#endif }; struct core_thread { -- cgit v1.2.3 From 33e5d76979cf01e3834814fe0aea569d1d602c1a Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 2 Apr 2009 16:56:32 -0700 Subject: nommu: fix a number of issues with the per-MM VMA patch Fix a number of issues with the per-MM VMA patch: (1) Make mmap_pages_allocated an atomic_long_t, just in case this is used on a NOMMU system with more than 2G pages. Makes no difference on a 32-bit system. (2) Report vma->vm_pgoff * PAGE_SIZE as a 64-bit value, not a 32-bit value, lest it overflow. (3) Move the allocation of the vm_area_struct slab back for fork.c. (4) Use KMEM_CACHE() for both vm_area_struct and vm_region slabs. (5) Use BUG_ON() rather than if () BUG(). (6) Make the default validate_nommu_regions() a static inline rather than a #define. (7) Make free_page_series()'s objection to pages with a refcount != 1 more informative. (8) Adjust the __put_nommu_region() banner comment to indicate that the semaphore must be held for writing. (9) Limit the number of warnings about munmaps of non-mmapped regions. Reported-by: Andrew Morton Signed-off-by: David Howells Cc: Greg Ungerer Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index aeabe953ba4..bff1f0d475c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1079,7 +1079,7 @@ static inline void setup_per_cpu_pageset(void) {} #endif /* nommu.c */ -extern atomic_t mmap_pages_allocated; +extern atomic_long_t mmap_pages_allocated; /* prio_tree.c */ void vma_prio_tree_add(struct vm_area_struct *, struct vm_area_struct *old); -- cgit v1.2.3 From 8e2c3795c78d5c4e2e1f14ce751e9d08decbe9d3 Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Thu, 2 Apr 2009 16:56:44 -0700 Subject: add fiemap.h to header-y Include fiemap.h in header-y; it defines the interface for the FS_IOC_FIEMAP file mapping ioctl. Signed-off-by: Eric Sandeen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/Kbuild | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index a67b6227d27..ca9b9b9bd33 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -67,6 +67,7 @@ header-y += falloc.h header-y += fd.h header-y += fdreg.h header-y += fib_rules.h +header-y += fiemap.h header-y += firewire-cdev.h header-y += firewire-constants.h header-y += fuse.h -- cgit v1.2.3 From 9a896c9a48ac6704c0ce8ee081b836644d0afe40 Mon Sep 17 00:00:00 2001 From: Lee Schermerhorn Date: Thu, 2 Apr 2009 16:56:45 -0700 Subject: mm: define a UNIQUE value for AS_UNEVICTABLE flag A new "address_space flag"--AS_MM_ALL_LOCKS--was defined to use the next available AS flag while the Unevictable LRU was under development. The Unevictable LRU was using the same flag and "no one" noticed. Current mainline, since 2.6.28, has same value for two symbolic flag names. So, define a unique flag value for AS_UNEVICTABLE--up close to the other flags, [at the cost of an additional #ifdef] so we'll notice next time. Note that #ifdef is not actually required, if we don't mind having the unused flag value defined. Replace #defines with an enum. Signed-off-by: Lee Schermerhorn Cc: [2.6.28.x, 2.6.29.x] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 01ca0856caf..076a7dc67c2 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -18,9 +18,14 @@ * Bits in mapping->flags. The lower __GFP_BITS_SHIFT bits are the page * allocation mode flags. */ -#define AS_EIO (__GFP_BITS_SHIFT + 0) /* IO error on async write */ -#define AS_ENOSPC (__GFP_BITS_SHIFT + 1) /* ENOSPC on async write */ -#define AS_MM_ALL_LOCKS (__GFP_BITS_SHIFT + 2) /* under mm_take_all_locks() */ +enum mapping_flags { + AS_EIO = __GFP_BITS_SHIFT + 0, /* IO error on async write */ + AS_ENOSPC = __GFP_BITS_SHIFT + 1, /* ENOSPC on async write */ + AS_MM_ALL_LOCKS = __GFP_BITS_SHIFT + 2, /* under mm_take_all_locks() */ +#ifdef CONFIG_UNEVICTABLE_LRU + AS_UNEVICTABLE = __GFP_BITS_SHIFT + 3, /* e.g., ramdisk, SHM_LOCK */ +#endif +}; static inline void mapping_set_error(struct address_space *mapping, int error) { @@ -33,7 +38,6 @@ static inline void mapping_set_error(struct address_space *mapping, int error) } #ifdef CONFIG_UNEVICTABLE_LRU -#define AS_UNEVICTABLE (__GFP_BITS_SHIFT + 2) /* e.g., ramdisk, SHM_LOCK */ static inline void mapping_set_unevictable(struct address_space *mapping) { -- cgit v1.2.3 From bf6aede712334d7338d5c47a5ee5ba3883c82a61 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Thu, 2 Apr 2009 16:56:54 -0700 Subject: workqueue: add to_delayed_work() helper function It is a fairly common operation to have a pointer to a work and to need a pointer to the delayed work it is contained in. In particular, all delayed works which want to rearm themselves will have to do that. So it would seem fair to offer a helper function for this operation. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Jean Delvare Acked-by: Ingo Molnar Cc: "David S. Miller" Cc: Herbert Xu Cc: Benjamin Herrenschmidt Cc: Martin Schwidefsky Cc: Greg KH Cc: Pekka Enberg Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/workqueue.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 3cd51e579ab..13e1adf55c4 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -41,6 +41,11 @@ struct delayed_work { struct timer_list timer; }; +static inline struct delayed_work *to_delayed_work(struct work_struct *work) +{ + return container_of(work, struct delayed_work, work); +} + struct execute_work { struct work_struct work; }; -- cgit v1.2.3 From 06c421ee0d5af95c8c6749ca0ba620cd5010707f Mon Sep 17 00:00:00 2001 From: Kevin Hilman Date: Thu, 2 Apr 2009 16:56:56 -0700 Subject: memory_accessor: new interface for reading/writing persistent memory Add an interface by which other kernel code can read/write persistent memory such as I2C or SPI EEPROMs, or devices which provide NVRAM. Use cases include storage of board-specific configuration data like Ethernet addresses and sensor calibrations. Original idea, review and improvement suggestions by David Brownell. Acked-by: David Brownell Signed-off-by: Kevin Hilman Cc: Jean Delvare Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memory.h b/include/linux/memory.h index 3fdc10806d3..42767d1a62e 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -99,4 +99,15 @@ enum mem_add_context { BOOT, HOTPLUG }; #define hotplug_memory_notifier(fn, pri) do { } while (0) #endif +/* + * 'struct memory_accessor' is a generic interface to provide + * in-kernel access to persistent memory such as i2c or SPI EEPROMs + */ +struct memory_accessor { + ssize_t (*read)(struct memory_accessor *, char *buf, off_t offset, + size_t count); + ssize_t (*write)(struct memory_accessor *, const char *buf, + off_t offset, size_t count); +}; + #endif /* _LINUX_MEMORY_H_ */ -- cgit v1.2.3 From 7274ec8bd71e99018642f474528ea7de4bb3ae25 Mon Sep 17 00:00:00 2001 From: Kevin Hilman Date: Thu, 2 Apr 2009 16:56:57 -0700 Subject: memory_accessor: implement the new memory_accessor interface for I2C EEPROM In the case of at24, the platform code registers a 'setup' callback with the at24_platform_data. When the at24 driver detects an EEPROM, it fills out the read and write functions of the memory_accessor and calls the setup callback passing the memory_accessor struct. The platform code can then use the read/write functions in the memory_accessor struct for reading and writing the EEPROM. Signed-off-by: Kevin Hilman Cc: David Brownell Cc: Jean Delvare Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/i2c/at24.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i2c/at24.h b/include/linux/i2c/at24.h index f6edd522a92..8ace93024d6 100644 --- a/include/linux/i2c/at24.h +++ b/include/linux/i2c/at24.h @@ -2,6 +2,7 @@ #define _LINUX_AT24_H #include +#include /* * As seen through Linux I2C, differences between the most common types of I2C @@ -23,6 +24,9 @@ struct at24_platform_data { #define AT24_FLAG_READONLY 0x40 /* sysfs-entry will be read-only */ #define AT24_FLAG_IRUGO 0x20 /* sysfs-entry will be world-readable */ #define AT24_FLAG_TAKE8ADDR 0x10 /* take always 8 addresses (24c00) */ + + void (*setup)(struct memory_accessor *, void *context); + void *context; }; #endif /* _LINUX_AT24_H */ -- cgit v1.2.3 From 14dd1ff0f9e75dd4ae2f1ff8e48becb76d14f4ab Mon Sep 17 00:00:00 2001 From: David Brownell Date: Thu, 2 Apr 2009 16:56:58 -0700 Subject: memory_accessor: implement the new memory_accessor interfaces for SPI EEPROMs - Define new setup() hook to export the accessor - Implement accessor methods Moves some error checking out of the sysfs interface code into the layer below it, which is now shared by both sysfs and memory access code. Signed-off-by: David Brownell Signed-off-by: Kevin Hilman Cc: Jean Delvare Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/spi/eeprom.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/eeprom.h b/include/linux/spi/eeprom.h index 1085212c446..306e7b1c69e 100644 --- a/include/linux/spi/eeprom.h +++ b/include/linux/spi/eeprom.h @@ -1,6 +1,8 @@ #ifndef __LINUX_SPI_EEPROM_H #define __LINUX_SPI_EEPROM_H +#include + /* * Put one of these structures in platform_data for SPI EEPROMS handled * by the "at25" driver. On SPI, most EEPROMS understand the same core @@ -17,6 +19,10 @@ struct spi_eeprom { #define EE_ADDR2 0x0002 /* 16 bit addrs */ #define EE_ADDR3 0x0004 /* 24 bit addrs */ #define EE_READONLY 0x0008 /* disallow writes */ + + /* for exporting this chip's data to other kernel code */ + void (*setup)(struct memory_accessor *mem, void *context); + void *context; }; #endif /* __LINUX_SPI_EEPROM_H */ -- cgit v1.2.3 From 6f2c55b843836d26528c56a0968689accaedbc67 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Thu, 2 Apr 2009 16:56:59 -0700 Subject: Simplify copy_thread() First argument unused since 2.3.11. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Alexey Dobriyan Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 481fad3a9b4..9186f8c5d5f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1975,7 +1975,8 @@ extern void mm_release(struct task_struct *, struct mm_struct *); /* Allocate a new mm structure and copy contents from tsk->mm */ extern struct mm_struct *dup_mm(struct task_struct *tsk); -extern int copy_thread(int, unsigned long, unsigned long, unsigned long, struct task_struct *, struct pt_regs *); +extern int copy_thread(unsigned long, unsigned long, unsigned long, + struct task_struct *, struct pt_regs *); extern void flush_thread(void); extern void exit_thread(void); -- cgit v1.2.3 From 96615841e170f0108832e64a90d51b469573a472 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Thu, 2 Apr 2009 16:57:01 -0700 Subject: rtc-v3020: add ability to access v3020 chip with GPIOs The v3020 RTC can be connected to GPIOs as well as to memory-like interface. Add ability to use GPIO bit-bang for v3020 read-write access. [akpm@linux-foundation.org: fix off-by-one in error path] Signed-off-by: Mike Rapoport Acked-by: Alessandro Zummo Cc: David Brownell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rtc-v3020.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rtc-v3020.h b/include/linux/rtc-v3020.h index bf74e63c98f..8ba646e610d 100644 --- a/include/linux/rtc-v3020.h +++ b/include/linux/rtc-v3020.h @@ -14,6 +14,12 @@ * is used depends on the board. */ struct v3020_platform_data { int leftshift; /* (1<<(leftshift)) & readl() */ + + int use_gpio:1; + unsigned int gpio_cs; + unsigned int gpio_wr; + unsigned int gpio_rd; + unsigned int gpio_io; }; #define V3020_STATUS_0 0x00 -- cgit v1.2.3 From bfb9bcdbda9a61bca469bf899a589918c60c4c18 Mon Sep 17 00:00:00 2001 From: Michael Buesch Date: Thu, 2 Apr 2009 16:57:07 -0700 Subject: spi-gpio: allow operation without CS signal Change spi-gpio so that it is possible to drive SPI communications over GPIO without the need for a chipselect signal. This is useful in very small setups where there's only one slave device on the bus. This patch does not affect existing setups. I use this for a tiny communication channel between an embedded device and a microcontroller. There are not enough GPIOs available for chipselect and it's not needed anyway in this case. Signed-off-by: Michael Buesch Cc: David Brownell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/spi/spi_gpio.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi_gpio.h b/include/linux/spi/spi_gpio.h index 0f01a0f1f40..ca6782ee4b9 100644 --- a/include/linux/spi/spi_gpio.h +++ b/include/linux/spi/spi_gpio.h @@ -25,10 +25,16 @@ * ... * }; * + * If chipselect is not used (there's only one device on the bus), assign + * SPI_GPIO_NO_CHIPSELECT to the controller_data: + * .controller_data = (void *) SPI_GPIO_NO_CHIPSELECT; + * * If the bitbanged bus is later switched to a "native" controller, * that platform_device and controller_data should be removed. */ +#define SPI_GPIO_NO_CHIPSELECT ((unsigned long)-1l) + /** * struct spi_gpio_platform_data - parameter for bitbanged SPI master * @sck: number of the GPIO used for clock output -- cgit v1.2.3 From 039fd8ce6258e01ec29f1637f9bf1868dd877c55 Mon Sep 17 00:00:00 2001 From: Cyrus Massoumi Date: Thu, 2 Apr 2009 16:57:12 -0700 Subject: ext3: remove the BKL in ext3/ioctl.c Reformat ext3/ioctl.c to make it look more like ext4/ioctl.c and remove the BKL around ext3_ioctl(). Signed-off-by: Cyrus Massoumi Cc: Acked-by: Jan Kara Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ext3_fs.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h index dd495b8c309..e263acaa405 100644 --- a/include/linux/ext3_fs.h +++ b/include/linux/ext3_fs.h @@ -893,9 +893,8 @@ extern int ext3_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len); /* ioctl.c */ -extern int ext3_ioctl (struct inode *, struct file *, unsigned int, - unsigned long); -extern long ext3_compat_ioctl (struct file *, unsigned int, unsigned long); +extern long ext3_ioctl(struct file *, unsigned int, unsigned long); +extern long ext3_compat_ioctl(struct file *, unsigned int, unsigned long); /* namei.c */ extern int ext3_orphan_add(handle_t *, struct inode *); -- cgit v1.2.3 From d20a390a0ee2bf2f692c539c6ce1c829e1080bb5 Mon Sep 17 00:00:00 2001 From: Paul Menage Date: Thu, 2 Apr 2009 16:57:22 -0700 Subject: cgroups: fix cgroup.h comments Fix the style of some multi-line comments in cgroup.h to match Documentation/CodingStyle Signed-off-by: Paul Menage Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cgroup.h | 71 +++++++++++++++++++++++++++++--------------------- 1 file changed, 41 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 499900d0cee..bb8feb9fecc 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -47,14 +47,18 @@ enum cgroup_subsys_id { /* Per-subsystem/per-cgroup state maintained by the system. */ struct cgroup_subsys_state { - /* The cgroup that this subsystem is attached to. Useful + /* + * The cgroup that this subsystem is attached to. Useful * for subsystems that want to know about the cgroup - * hierarchy structure */ + * hierarchy structure + */ struct cgroup *cgroup; - /* State maintained by the cgroup system to allow subsystems + /* + * State maintained by the cgroup system to allow subsystems * to be "busy". Should be accessed via css_get(), - * css_tryget() and and css_put(). */ + * css_tryget() and and css_put(). + */ atomic_t refcnt; @@ -120,8 +124,10 @@ static inline void css_put(struct cgroup_subsys_state *css) enum { /* Control Group is dead */ CGRP_REMOVED, - /* Control Group has previously had a child cgroup or a task, - * but no longer (only if CGRP_NOTIFY_ON_RELEASE is set) */ + /* + * Control Group has previously had a child cgroup or a task, + * but no longer (only if CGRP_NOTIFY_ON_RELEASE is set) + */ CGRP_RELEASABLE, /* Control Group requires release notifications to userspace */ CGRP_NOTIFY_ON_RELEASE, @@ -130,9 +136,10 @@ enum { struct cgroup { unsigned long flags; /* "unsigned long" so bitops work */ - /* count users of this cgroup. >0 means busy, but doesn't - * necessarily indicate the number of tasks in the - * cgroup */ + /* + * count users of this cgroup. >0 means busy, but doesn't + * necessarily indicate the number of tasks in the cgroup + */ atomic_t count; /* @@ -142,7 +149,7 @@ struct cgroup { struct list_head sibling; /* my parent's children */ struct list_head children; /* my children */ - struct cgroup *parent; /* my parent */ + struct cgroup *parent; /* my parent */ struct dentry *dentry; /* cgroup fs entry, RCU protected */ /* Private pointers for each registered subsystem */ @@ -177,11 +184,12 @@ struct cgroup { struct rcu_head rcu_head; }; -/* A css_set is a structure holding pointers to a set of +/* + * A css_set is a structure holding pointers to a set of * cgroup_subsys_state objects. This saves space in the task struct * object and speeds up fork()/exit(), since a single inc/dec and a - * list_add()/del() can bump the reference count on the entire - * cgroup set for a task. + * list_add()/del() can bump the reference count on the entire cgroup + * set for a task. */ struct css_set { @@ -226,13 +234,8 @@ struct cgroup_map_cb { void *state; }; -/* struct cftype: - * - * The files in the cgroup filesystem mostly have a very simple read/write - * handling, some common function will take care of it. Nevertheless some cases - * (read tasks) are special and therefore I define this structure for every - * kind of file. - * +/* + * struct cftype: handler definitions for cgroup control files * * When reading/writing to a file: * - the cgroup to use is file->f_dentry->d_parent->d_fsdata @@ -241,8 +244,10 @@ struct cgroup_map_cb { #define MAX_CFTYPE_NAME 64 struct cftype { - /* By convention, the name should begin with the name of the - * subsystem, followed by a period */ + /* + * By convention, the name should begin with the name of the + * subsystem, followed by a period + */ char name[MAX_CFTYPE_NAME]; int private; @@ -321,13 +326,17 @@ struct cgroup_scanner { struct ptr_heap *heap; }; -/* Add a new file to the given cgroup directory. Should only be - * called by subsystems from within a populate() method */ +/* + * Add a new file to the given cgroup directory. Should only be + * called by subsystems from within a populate() method + */ int cgroup_add_file(struct cgroup *cgrp, struct cgroup_subsys *subsys, const struct cftype *cft); -/* Add a set of new files to the given cgroup directory. Should - * only be called by subsystems from within a populate() method */ +/* + * Add a set of new files to the given cgroup directory. Should + * only be called by subsystems from within a populate() method + */ int cgroup_add_files(struct cgroup *cgrp, struct cgroup_subsys *subsys, const struct cftype cft[], @@ -419,7 +428,8 @@ struct cgroup_iter { struct list_head *task; }; -/* To iterate across the tasks in a cgroup: +/* + * To iterate across the tasks in a cgroup: * * 1) call cgroup_iter_start to intialize an iterator * @@ -428,9 +438,10 @@ struct cgroup_iter { * * 3) call cgroup_iter_end() to destroy the iterator. * - * Or, call cgroup_scan_tasks() to iterate through every task in a cpuset. - * - cgroup_scan_tasks() holds the css_set_lock when calling the test_task() - * callback, but not while calling the process_task() callback. + * Or, call cgroup_scan_tasks() to iterate through every task in a + * cgroup - cgroup_scan_tasks() holds the css_set_lock when calling + * the test_task() callback, but not while calling the process_task() + * callback. */ void cgroup_iter_start(struct cgroup *cgrp, struct cgroup_iter *it); struct task_struct *cgroup_iter_next(struct cgroup *cgrp, -- cgit v1.2.3 From 313e924c0852943e67335fad9d2608701f0dfe8e Mon Sep 17 00:00:00 2001 From: Grzegorz Nosek Date: Thu, 2 Apr 2009 16:57:23 -0700 Subject: cgroups: relax ns_can_attach checks to allow attaching to grandchild cgroups The ns_proxy cgroup allows moving processes to child cgroups only one level deep at a time. This commit relaxes this restriction and makes it possible to attach tasks directly to grandchild cgroups, e.g.: ($pid is in the root cgroup) echo $pid > /cgroup/CG1/CG2/tasks Previously this operation would fail with -EPERM and would have to be performed as two steps: echo $pid > /cgroup/CG1/tasks echo $pid > /cgroup/CG1/CG2/tasks Also, the target cgroup no longer needs to be empty to move a task there. Signed-off-by: Grzegorz Nosek Acked-by: Serge Hallyn Reviewed-by: Li Zefan Cc: Paul Menage Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cgroup.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index bb8feb9fecc..788c4964c14 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -348,8 +348,8 @@ int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen); int cgroup_task_count(const struct cgroup *cgrp); -/* Return true if the cgroup is a descendant of the current cgroup */ -int cgroup_is_descendant(const struct cgroup *cgrp); +/* Return true if cgrp is a descendant of the task's cgroup */ +int cgroup_is_descendant(const struct cgroup *cgrp, struct task_struct *task); /* Control Group subsystem type. See Documentation/cgroups.txt for details */ -- cgit v1.2.3 From 38460b48d06440de46b34cb778bd6c4855030754 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Thu, 2 Apr 2009 16:57:25 -0700 Subject: cgroup: CSS ID support Patch for Per-CSS(Cgroup Subsys State) ID and private hierarchy code. This patch attaches unique ID to each css and provides following. - css_lookup(subsys, id) returns pointer to struct cgroup_subysys_state of id. - css_get_next(subsys, id, rootid, depth, foundid) returns the next css under "root" by scanning When cgroup_subsys->use_id is set, an id for css is maintained. The cgroup framework only parepares - css_id of root css for subsys - id is automatically attached at creation of css. - id is *not* freed automatically. Because the cgroup framework don't know lifetime of cgroup_subsys_state. free_css_id() function is provided. This must be called by subsys. There are several reasons to develop this. - Saving space .... For example, memcg's swap_cgroup is array of pointers to cgroup. But it is not necessary to be very fast. By replacing pointers(8bytes per ent) to ID (2byes per ent), we can reduce much amount of memory usage. - Scanning without lock. CSS_ID provides "scan id under this ROOT" function. By this, scanning css under root can be written without locks. ex) do { rcu_read_lock(); next = cgroup_get_next(subsys, id, root, &found); /* check sanity of next here */ css_tryget(); rcu_read_unlock(); id = found + 1 } while(...) Characteristics: - Each css has unique ID under subsys. - Lifetime of ID is controlled by subsys. - css ID contains "ID" and "Depth in hierarchy" and stack of hierarchy - Allowed ID is 1-65535, ID 0 is UNUSED ID. Design Choices: - scan-by-ID v.s. scan-by-tree-walk. As /proc's pid scan does, scan-by-ID is robust when scanning is done by following kind of routine. scan -> rest a while(release a lock) -> conitunue from interrupted memcg's hierarchical reclaim does this. - When subsys->use_id is set, # of css in the system is limited to 65535. [bharata@linux.vnet.ibm.com: remove rcu_read_lock() from css_get_next()] Signed-off-by: KAMEZAWA Hiroyuki Acked-by: Paul Menage Cc: Li Zefan Cc: Balbir Singh Cc: Daisuke Nishimura Signed-off-by: Bharata B Rao Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cgroup.h | 50 ++++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/idr.h | 1 + 2 files changed, 51 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 788c4964c14..9a23bb09820 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -15,6 +15,7 @@ #include #include #include +#include #ifdef CONFIG_CGROUPS @@ -22,6 +23,7 @@ struct cgroupfs_root; struct cgroup_subsys; struct inode; struct cgroup; +struct css_id; extern int cgroup_init_early(void); extern int cgroup_init(void); @@ -63,6 +65,8 @@ struct cgroup_subsys_state { atomic_t refcnt; unsigned long flags; + /* ID for this css, if possible */ + struct css_id *id; }; /* bits in struct cgroup_subsys_state flags field */ @@ -373,6 +377,11 @@ struct cgroup_subsys { int active; int disabled; int early_init; + /* + * True if this subsys uses ID. ID is not available before cgroup_init() + * (not available in early_init time.) + */ + bool use_id; #define MAX_CGROUP_TYPE_NAMELEN 32 const char *name; @@ -395,6 +404,9 @@ struct cgroup_subsys { */ struct cgroupfs_root *root; struct list_head sibling; + /* used when use_id == true */ + struct idr idr; + spinlock_t id_lock; }; #define SUBSYS(_x) extern struct cgroup_subsys _x ## _subsys; @@ -450,6 +462,44 @@ void cgroup_iter_end(struct cgroup *cgrp, struct cgroup_iter *it); int cgroup_scan_tasks(struct cgroup_scanner *scan); int cgroup_attach_task(struct cgroup *, struct task_struct *); +/* + * CSS ID is ID for cgroup_subsys_state structs under subsys. This only works + * if cgroup_subsys.use_id == true. It can be used for looking up and scanning. + * CSS ID is assigned at cgroup allocation (create) automatically + * and removed when subsys calls free_css_id() function. This is because + * the lifetime of cgroup_subsys_state is subsys's matter. + * + * Looking up and scanning function should be called under rcu_read_lock(). + * Taking cgroup_mutex()/hierarchy_mutex() is not necessary for following calls. + * But the css returned by this routine can be "not populated yet" or "being + * destroyed". The caller should check css and cgroup's status. + */ + +/* + * Typically Called at ->destroy(), or somewhere the subsys frees + * cgroup_subsys_state. + */ +void free_css_id(struct cgroup_subsys *ss, struct cgroup_subsys_state *css); + +/* Find a cgroup_subsys_state which has given ID */ + +struct cgroup_subsys_state *css_lookup(struct cgroup_subsys *ss, int id); + +/* + * Get a cgroup whose id is greater than or equal to id under tree of root. + * Returning a cgroup_subsys_state or NULL. + */ +struct cgroup_subsys_state *css_get_next(struct cgroup_subsys *ss, int id, + struct cgroup_subsys_state *root, int *foundid); + +/* Returns true if root is ancestor of cg */ +bool css_is_ancestor(struct cgroup_subsys_state *cg, + struct cgroup_subsys_state *root); + +/* Get id and depth of css */ +unsigned short css_id(struct cgroup_subsys_state *css); +unsigned short css_depth(struct cgroup_subsys_state *css); + #else /* !CONFIG_CGROUPS */ static inline int cgroup_init_early(void) { return 0; } diff --git a/include/linux/idr.h b/include/linux/idr.h index dd846df8cd3..e968db71e33 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -106,6 +106,7 @@ int idr_get_new(struct idr *idp, void *ptr, int *id); int idr_get_new_above(struct idr *idp, void *ptr, int starting_id, int *id); int idr_for_each(struct idr *idp, int (*fn)(int id, void *p, void *data), void *data); +void *idr_get_next(struct idr *idp, int *nextid); void *idr_replace(struct idr *idp, void *ptr, int id); void idr_remove(struct idr *idp, int id); void idr_remove_all(struct idr *idp); -- cgit v1.2.3 From ec64f51545fffbc4cb968f0cea56341a4b07e85a Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Thu, 2 Apr 2009 16:57:26 -0700 Subject: cgroup: fix frequent -EBUSY at rmdir In following situation, with memory subsystem, /groupA use_hierarchy==1 /01 some tasks /02 some tasks /03 some tasks /04 empty When tasks under 01/02/03 hit limit on /groupA, hierarchical reclaim is triggered and the kernel walks tree under groupA. In this case, rmdir /groupA/04 fails with -EBUSY frequently because of temporal refcnt from the kernel. In general. cgroup can be rmdir'd if there are no children groups and no tasks. Frequent fails of rmdir() is not useful to users. (And the reason for -EBUSY is unknown to users.....in most cases) This patch tries to modify above behavior, by - retries if css_refcnt is got by someone. - add "return value" to pre_destroy() and allows subsystem to say "we're really busy!" Signed-off-by: KAMEZAWA Hiroyuki Cc: Paul Menage Cc: Li Zefan Cc: Balbir Singh Cc: Daisuke Nishimura Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cgroup.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 9a23bb09820..7d824b80b3d 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -135,6 +135,10 @@ enum { CGRP_RELEASABLE, /* Control Group requires release notifications to userspace */ CGRP_NOTIFY_ON_RELEASE, + /* + * A thread in rmdir() is wating for this cgroup. + */ + CGRP_WAIT_ON_RMDIR, }; struct cgroup { @@ -360,7 +364,7 @@ int cgroup_is_descendant(const struct cgroup *cgrp, struct task_struct *task); struct cgroup_subsys { struct cgroup_subsys_state *(*create)(struct cgroup_subsys *ss, struct cgroup *cgrp); - void (*pre_destroy)(struct cgroup_subsys *ss, struct cgroup *cgrp); + int (*pre_destroy)(struct cgroup_subsys *ss, struct cgroup *cgrp); void (*destroy)(struct cgroup_subsys *ss, struct cgroup *cgrp); int (*can_attach)(struct cgroup_subsys *ss, struct cgroup *cgrp, struct task_struct *tsk); -- cgit v1.2.3 From 099fca3225b39f7a3ed853036038054172b55581 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Thu, 2 Apr 2009 16:57:29 -0700 Subject: cgroups: show correct file mode We have some read-only files and write-only files, but currently they are all set to 0644, which is counter-intuitive and cause trouble for some cgroup tools like libcgroup. This patch adds 'mode' to struct cftype to allow cgroup subsys to set it's own files' file mode, and for the most cases cft->mode can be default to 0 and cgroup will figure out proper mode. Acked-by: Paul Menage Reviewed-by: KAMEZAWA Hiroyuki Signed-off-by: Li Zefan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cgroup.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 7d824b80b3d..b2816fba530 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -258,6 +258,11 @@ struct cftype { */ char name[MAX_CFTYPE_NAME]; int private; + /* + * If not 0, file mode is set to this value, otherwise it will + * be figured out automatically + */ + mode_t mode; /* * If non-zero, defines the maximum length of string that can -- cgit v1.2.3 From 0b7f569e45bb6be142d87017030669a6a7d327a1 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Thu, 2 Apr 2009 16:57:38 -0700 Subject: memcg: fix OOM killer under memcg This patch tries to fix OOM Killer problems caused by hierarchy. Now, memcg itself has OOM KILL function (in oom_kill.c) and tries to kill a task in memcg. But, when hierarchy is used, it's broken and correct task cannot be killed. For example, in following cgroup /groupA/ hierarchy=1, limit=1G, 01 nolimit 02 nolimit All tasks' memory usage under /groupA, /groupA/01, groupA/02 is limited to groupA's 1Gbytes but OOM Killer just kills tasks in groupA. This patch provides makes the bad process be selected from all tasks under hierarchy. BTW, currently, oom_jiffies is updated against groupA in above case. oom_jiffies of tree should be updated. To see how oom_jiffies is used, please check mem_cgroup_oom_called() callers. [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: const fix] Signed-off-by: KAMEZAWA Hiroyuki Cc: Paul Menage Cc: Li Zefan Cc: Balbir Singh Cc: Daisuke Nishimura Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cgroup.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index b2816fba530..43763bd772b 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -503,7 +503,7 @@ struct cgroup_subsys_state *css_get_next(struct cgroup_subsys *ss, int id, /* Returns true if root is ancestor of cg */ bool css_is_ancestor(struct cgroup_subsys_state *cg, - struct cgroup_subsys_state *root); + const struct cgroup_subsys_state *root); /* Get id and depth of css */ unsigned short css_id(struct cgroup_subsys_state *css); -- cgit v1.2.3 From e222432bfa7dcf6ec008622a978c9f284ed5e3a9 Mon Sep 17 00:00:00 2001 From: Balbir Singh Date: Thu, 2 Apr 2009 16:57:39 -0700 Subject: memcg: show memcg information during OOM Add RSS and swap to OOM output from memcg Display memcg values like failcnt, usage and limit when an OOM occurs due to memcg. Thanks to Johannes Weiner, Li Zefan, David Rientjes, Kamezawa Hiroyuki, Daisuke Nishimura and KOSAKI Motohiro for review. Sample output ------------- Task in /a/x killed as a result of limit of /a memory: usage 1048576kB, limit 1048576kB, failcnt 4183 memory+swap: usage 1400964kB, limit 9007199254740991kB, failcnt 0 [akpm@linux-foundation.org: compilation fix] [akpm@linux-foundation.org: fix kerneldoc and whitespace] [akpm@linux-foundation.org: add printk facility level] Signed-off-by: Balbir Singh Cc: KAMEZAWA Hiroyuki Cc: Daisuke Nishimura Cc: Li Zefan Cc: Paul Menage Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 326f45c8653..7aba9f26462 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -104,6 +104,8 @@ struct zone_reclaim_stat *mem_cgroup_get_reclaim_stat(struct mem_cgroup *memcg, struct zone *zone); struct zone_reclaim_stat* mem_cgroup_get_reclaim_stat_from_page(struct page *page); +extern void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, + struct task_struct *p); #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP extern int do_swap_account; @@ -270,6 +272,11 @@ mem_cgroup_get_reclaim_stat_from_page(struct page *page) return NULL; } +static inline void +mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p) +{ +} + #endif /* CONFIG_CGROUP_MEM_CONT */ #endif /* _LINUX_MEMCONTROL_H */ -- cgit v1.2.3 From c137b5ece4b111e46981aae7da77315b9909809f Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Thu, 2 Apr 2009 16:57:40 -0700 Subject: memcg: remove mem_cgroup_calc_mapped_ratio() Currently, mem_cgroup_calc_mapped_ratio() is unused at all. it can be removed and KAMEZAWA-san suggested it. Signed-off-by: KOSAKI Motohiro Cc: KAMEZAWA Hiroyuki Acked-by: Balbir Singh Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 7aba9f26462..4562d09ab96 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -88,7 +88,6 @@ extern void mem_cgroup_end_migration(struct mem_cgroup *mem, /* * For memory reclaim. */ -extern int mem_cgroup_calc_mapped_ratio(struct mem_cgroup *mem); extern long mem_cgroup_reclaim_imbalance(struct mem_cgroup *mem); extern int mem_cgroup_get_reclaim_priority(struct mem_cgroup *mem); @@ -211,11 +210,6 @@ static inline void mem_cgroup_end_migration(struct mem_cgroup *mem, { } -static inline int mem_cgroup_calc_mapped_ratio(struct mem_cgroup *mem) -{ - return 0; -} - static inline int mem_cgroup_reclaim_imbalance(struct mem_cgroup *mem) { return 0; -- cgit v1.2.3 From 3918b96e03b2b8dd05889320623f6870e81d35ec Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Thu, 2 Apr 2009 16:57:41 -0700 Subject: memcg: remove mem_cgroup_reclaim_imbalance() remnants commit 4f98a2fee8acdb4ac84545df98cccecfd130f8db (vmscan: split LRU lists into anon & file sets) removed mem_cgroup_reclaim_imbalance(), but there are some leftovers in memcontrol.h. Signed-off-by: KOSAKI Motohiro Cc: KAMEZAWA Hiroyuki Cc: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 4562d09ab96..18146c980b6 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -88,8 +88,6 @@ extern void mem_cgroup_end_migration(struct mem_cgroup *mem, /* * For memory reclaim. */ -extern long mem_cgroup_reclaim_imbalance(struct mem_cgroup *mem); - extern int mem_cgroup_get_reclaim_priority(struct mem_cgroup *mem); extern void mem_cgroup_note_reclaim_priority(struct mem_cgroup *mem, int priority); @@ -210,11 +208,6 @@ static inline void mem_cgroup_end_migration(struct mem_cgroup *mem, { } -static inline int mem_cgroup_reclaim_imbalance(struct mem_cgroup *mem) -{ - return 0; -} - static inline int mem_cgroup_get_reclaim_priority(struct mem_cgroup *mem) { return 0; -- cgit v1.2.3 From a3b2d692690aef228e493b1beaafe5364cab3237 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Thu, 2 Apr 2009 16:57:45 -0700 Subject: cgroups: use css id in swap cgroup for saving memory v5 Try to use CSS ID for records in swap_cgroup. By this, on 64bit machine, size of swap_cgroup goes down to 2 bytes from 8bytes. This means, when 2GB of swap is equipped, (assume the page size is 4096bytes) From size of swap_cgroup = 2G/4k * 8 = 4Mbytes. To size of swap_cgroup = 2G/4k * 2 = 1Mbytes. Reduction is large. Of course, there are trade-offs. This CSS ID will add overhead to swap-in/swap-out/swap-free. But in general, - swap is a resource which the user tend to avoid use. - If swap is never used, swap_cgroup area is not used. - Reading traditional manuals, size of swap should be proportional to size of memory. Memory size of machine is increasing now. I think reducing size of swap_cgroup makes sense. Note: - ID->CSS lookup routine has no locks, it's under RCU-Read-Side. - memcg can be obsolete at rmdir() but not freed while refcnt from swap_cgroup is available. Changelog v4->v5: - reworked on to memcg-charge-swapcache-to-proper-memcg.patch Changlog ->v4: - fixed not configured case. - deleted unnecessary comments. - fixed NULL pointer bug. - fixed message in dmesg. [nishimura@mxp.nes.nec.co.jp: css_tryget can be called twice in !PageCgroupUsed case] Signed-off-by: KAMEZAWA Hiroyuki Cc: Li Zefan Cc: Balbir Singh Cc: Paul Menage Cc: Hugh Dickins Signed-off-by: Daisuke Nishimura Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page_cgroup.h | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h index 602cc1fdee9..7339c7bf733 100644 --- a/include/linux/page_cgroup.h +++ b/include/linux/page_cgroup.h @@ -91,24 +91,23 @@ static inline void page_cgroup_init(void) #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP #include -extern struct mem_cgroup * -swap_cgroup_record(swp_entry_t ent, struct mem_cgroup *mem); -extern struct mem_cgroup *lookup_swap_cgroup(swp_entry_t ent); +extern unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id); +extern unsigned short lookup_swap_cgroup(swp_entry_t ent); extern int swap_cgroup_swapon(int type, unsigned long max_pages); extern void swap_cgroup_swapoff(int type); #else #include static inline -struct mem_cgroup *swap_cgroup_record(swp_entry_t ent, struct mem_cgroup *mem) +unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id) { - return NULL; + return 0; } static inline -struct mem_cgroup *lookup_swap_cgroup(swp_entry_t ent) +unsigned short lookup_swap_cgroup(swp_entry_t ent) { - return NULL; + return 0; } static inline int -- cgit v1.2.3 From bd1a8ab73edd449fecda633449cc277b856ad4f5 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Thu, 2 Apr 2009 16:57:50 -0700 Subject: cgroups: add 'data' field to struct cgroup_scanner We need to pass some data to test_task() or process_task() in some cases. Will be used later. Signed-off-by: Li Zefan Cc: KAMEZAWA Hiroyuki Cc: Paul Menage Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cgroup.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 43763bd772b..4316a546beb 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -337,6 +337,7 @@ struct cgroup_scanner { void (*process_task)(struct task_struct *p, struct cgroup_scanner *scan); struct ptr_heap *heap; + void *data; }; /* -- cgit v1.2.3 From a1bc5a4eee990a1f290735c8694d0aebdad095fa Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Thu, 2 Apr 2009 16:57:54 -0700 Subject: cpusets: replace zone allowed functions with node allowed The cpuset_zone_allowed() variants are actually only a function of the zone's node. Cc: Paul Menage Acked-by: Christoph Lameter Cc: Randy Dunlap Signed-off-by: David Rientjes Cc: Ingo Molnar Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cpuset.h | 33 +++++++++++++++++++++++++++------ 1 file changed, 27 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 2e0d79678de..05ea1dd7d68 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -12,6 +12,7 @@ #include #include #include +#include #ifdef CONFIG_CPUSETS @@ -29,19 +30,29 @@ void cpuset_init_current_mems_allowed(void); void cpuset_update_task_memory_state(void); int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask); -extern int __cpuset_zone_allowed_softwall(struct zone *z, gfp_t gfp_mask); -extern int __cpuset_zone_allowed_hardwall(struct zone *z, gfp_t gfp_mask); +extern int __cpuset_node_allowed_softwall(int node, gfp_t gfp_mask); +extern int __cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask); -static int inline cpuset_zone_allowed_softwall(struct zone *z, gfp_t gfp_mask) +static inline int cpuset_node_allowed_softwall(int node, gfp_t gfp_mask) { return number_of_cpusets <= 1 || - __cpuset_zone_allowed_softwall(z, gfp_mask); + __cpuset_node_allowed_softwall(node, gfp_mask); } -static int inline cpuset_zone_allowed_hardwall(struct zone *z, gfp_t gfp_mask) +static inline int cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask) { return number_of_cpusets <= 1 || - __cpuset_zone_allowed_hardwall(z, gfp_mask); + __cpuset_node_allowed_hardwall(node, gfp_mask); +} + +static inline int cpuset_zone_allowed_softwall(struct zone *z, gfp_t gfp_mask) +{ + return cpuset_node_allowed_softwall(zone_to_nid(z), gfp_mask); +} + +static inline int cpuset_zone_allowed_hardwall(struct zone *z, gfp_t gfp_mask) +{ + return cpuset_node_allowed_hardwall(zone_to_nid(z), gfp_mask); } extern int cpuset_mems_allowed_intersects(const struct task_struct *tsk1, @@ -112,6 +123,16 @@ static inline int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask) return 1; } +static inline int cpuset_node_allowed_softwall(int node, gfp_t gfp_mask) +{ + return 1; +} + +static inline int cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask) +{ + return 1; +} + static inline int cpuset_zone_allowed_softwall(struct zone *z, gfp_t gfp_mask) { return 1; -- cgit v1.2.3 From 43918f2bf4806675943416d539d9d5e4d585ebff Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Thu, 2 Apr 2009 16:58:00 -0700 Subject: signals: remove 'handler' parameter to tracehook functions Container-init must behave like global-init to processes within the container and hence it must be immune to unhandled fatal signals from within the container (i.e SIG_DFL signals that terminate the process). But the same container-init must behave like a normal process to processes in ancestor namespaces and so if it receives the same fatal signal from a process in ancestor namespace, the signal must be processed. Implementing these semantics requires that send_signal() determine pid namespace of the sender but since signals can originate from workqueues/ interrupt-handlers, determining pid namespace of sender may not always be possible or safe. This patchset implements the design/simplified semantics suggested by Oleg Nesterov. The simplified semantics for container-init are: - container-init must never be terminated by a signal from a descendant process. - container-init must never be immune to SIGKILL from an ancestor namespace (so a process in parent namespace must always be able to terminate a descendant container). - container-init may be immune to unhandled fatal signals (like SIGUSR1) even if they are from ancestor namespace. SIGKILL/SIGSTOP are the only reliable signals to a container-init from ancestor namespace. This patch: Based on an earlier patch submitted by Oleg Nesterov and comments from Roland McGrath (http://lkml.org/lkml/2008/11/19/258). The handler parameter is currently unused in the tracehook functions. Besides, the tracehook functions are called with siglock held, so the functions can check the handler if they later need to. Removing the parameter simiplifies changes to sig_ignored() in a follow-on patch. Signed-off-by: Sukadev Bhattiprolu Acked-by: Roland McGrath Signed-off-by: Oleg Nesterov Cc: "Eric W. Biederman" Cc: Daniel Lezcano Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tracehook.h | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 6186a789d6c..eb4c6545b38 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -388,17 +388,14 @@ static inline void tracehook_signal_handler(int sig, siginfo_t *info, * tracehook_consider_ignored_signal - suppress short-circuit of ignored signal * @task: task receiving the signal * @sig: signal number being sent - * @handler: %SIG_IGN or %SIG_DFL * * Return zero iff tracing doesn't care to examine this ignored signal, * so it can short-circuit normal delivery and never even get queued. - * Either @handler is %SIG_DFL and @sig's default is ignore, or it's %SIG_IGN. * * Called with @task->sighand->siglock held. */ static inline int tracehook_consider_ignored_signal(struct task_struct *task, - int sig, - void __user *handler) + int sig) { return (task_ptrace(task) & PT_PTRACED) != 0; } @@ -407,19 +404,17 @@ static inline int tracehook_consider_ignored_signal(struct task_struct *task, * tracehook_consider_fatal_signal - suppress special handling of fatal signal * @task: task receiving the signal * @sig: signal number being sent - * @handler: %SIG_DFL or %SIG_IGN * * Return nonzero to prevent special handling of this termination signal. - * Normally @handler is %SIG_DFL. It can be %SIG_IGN if @sig is ignored, - * in which case force_sig() is about to reset it to %SIG_DFL. + * Normally handler for signal is %SIG_DFL. It can be %SIG_IGN if @sig is + * ignored, in which case force_sig() is about to reset it to %SIG_DFL. * When this returns zero, this signal might cause a quick termination * that does not give the debugger a chance to intercept the signal. * * Called with or without @task->sighand->siglock held. */ static inline int tracehook_consider_fatal_signal(struct task_struct *task, - int sig, - void __user *handler) + int sig) { return (task_ptrace(task) & PT_PTRACED) != 0; } -- cgit v1.2.3 From 4576145c1ecdaaea9ef8976a48335206aa1ebf91 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Thu, 2 Apr 2009 16:58:14 -0700 Subject: ptrace: fix possible zombie leak on PTRACE_DETACH When ptrace_detach() takes tasklist, the tracee can be SIGKILL'ed. If it has already passed exit_notify() we can leak a zombie, because a) ptracing disables the auto-reaping logic, and b) ->real_parent was not notified about the child's death. ptrace_detach() should follow the ptrace_exit's logic, change the code accordingly. Signed-off-by: Oleg Nesterov Cc: Jerome Marchand Cc: Roland McGrath Tested-by: Denys Vlasenko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ptrace.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 98b93ca4db0..1a2b0cb5553 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -94,6 +94,7 @@ extern void ptrace_notify(int exit_code); extern void __ptrace_link(struct task_struct *child, struct task_struct *new_parent); extern void __ptrace_unlink(struct task_struct *child); +extern int __ptrace_detach(struct task_struct *tracer, struct task_struct *p); extern void ptrace_fork(struct task_struct *task, unsigned long clone_flags); #define PTRACE_MODE_READ 1 #define PTRACE_MODE_ATTACH 2 -- cgit v1.2.3 From 39c626ae47c469abdfd30c6e42eff884931380d6 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Thu, 2 Apr 2009 16:58:18 -0700 Subject: forget_original_parent: split out the un-ptrace part By discussion with Roland. - Rename ptrace_exit() to exit_ptrace(), and change it to do all the necessary work with ->ptraced list by its own. - Move this code from exit.c to ptrace.c - Update the comment in ptrace_detach() to explain the rechecking of the child->ptrace. Signed-off-by: Oleg Nesterov Cc: "Eric W. Biederman" Cc: "Metzger, Markus T" Cc: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ptrace.h | 2 +- include/linux/sched.h | 5 +++++ 2 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 1a2b0cb5553..67c15653fc2 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -94,7 +94,7 @@ extern void ptrace_notify(int exit_code); extern void __ptrace_link(struct task_struct *child, struct task_struct *new_parent); extern void __ptrace_unlink(struct task_struct *child); -extern int __ptrace_detach(struct task_struct *tracer, struct task_struct *p); +extern void exit_ptrace(struct task_struct *tracer); extern void ptrace_fork(struct task_struct *task, unsigned long clone_flags); #define PTRACE_MODE_READ 1 #define PTRACE_MODE_ATTACH 2 diff --git a/include/linux/sched.h b/include/linux/sched.h index 9186f8c5d5f..b47c94e7560 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2061,6 +2061,11 @@ static inline int thread_group_empty(struct task_struct *p) #define delay_group_leader(p) \ (thread_group_leader(p) && !thread_group_empty(p)) +static inline int task_detached(struct task_struct *p) +{ + return p->exit_signal == -1; +} + /* * Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring * subscriptions and synchronises with wait4(). Also used in procfs. Also -- cgit v1.2.3 From bb24c679a51b1a9b726b901330649e3861814ac0 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Thu, 2 Apr 2009 16:58:20 -0700 Subject: tracehook_notify_death: use task_detached() helper Now that task_detached() is exported, change tracehook_notify_death() to use this helper, nobody else checks ->exit_signal == -1 by hand. Signed-off-by: Oleg Nesterov Cc: "Eric W. Biederman" Cc: "Metzger, Markus T" Acked-by: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tracehook.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index eb4c6545b38..c7aa154f4bf 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -502,7 +502,7 @@ static inline int tracehook_notify_jctl(int notify, int why) static inline int tracehook_notify_death(struct task_struct *task, void **death_cookie, int group_dead) { - if (task->exit_signal == -1) + if (task_detached(task)) return task->ptrace ? SIGCHLD : DEATH_REAP; /* -- cgit v1.2.3 From 40e8a10de2c9f87e892dcd5a6f9d1b208329ffea Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Thu, 2 Apr 2009 16:58:25 -0700 Subject: cpu hotplug: remove unused cpuhotplug_mutex_lock() cpuhotplug_mutex_lock() is not used, remove it. Signed-off-by: Lai Jiangshan Cc: Ingo Molnar Cc: Rusty Russell Acked-by: Gautham R Shenoy Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cpu.h | 16 ---------------- 1 file changed, 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index c2747ac2ae4..2643d848df9 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -23,7 +23,6 @@ #include #include #include -#include struct cpu { int node_id; /* The node which contains the CPU */ @@ -103,16 +102,6 @@ extern struct sysdev_class cpu_sysdev_class; #ifdef CONFIG_HOTPLUG_CPU /* Stop CPUs going up and down. */ -static inline void cpuhotplug_mutex_lock(struct mutex *cpu_hp_mutex) -{ - mutex_lock(cpu_hp_mutex); -} - -static inline void cpuhotplug_mutex_unlock(struct mutex *cpu_hp_mutex) -{ - mutex_unlock(cpu_hp_mutex); -} - extern void get_online_cpus(void); extern void put_online_cpus(void); #define hotcpu_notifier(fn, pri) { \ @@ -126,11 +115,6 @@ int cpu_down(unsigned int cpu); #else /* CONFIG_HOTPLUG_CPU */ -static inline void cpuhotplug_mutex_lock(struct mutex *cpu_hp_mutex) -{ } -static inline void cpuhotplug_mutex_unlock(struct mutex *cpu_hp_mutex) -{ } - #define get_online_cpus() do { } while (0) #define put_online_cpus() do { } while (0) #define hotcpu_notifier(fn, pri) do { (void)(fn); } while (0) -- cgit v1.2.3 From a50b0aa4bd9a7d42112442a385f3dc0e775284dd Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Thu, 2 Apr 2009 16:58:29 -0700 Subject: struct linux_binprm: drop unused fields Signed-off-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/binfmts.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 77b4a9e4600..6638b8148de 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -35,8 +35,7 @@ struct linux_binprm{ #endif struct mm_struct *mm; unsigned long p; /* current top of mem */ - unsigned int sh_bang:1, - misc_bang:1, + unsigned int cred_prepared:1,/* true if creds already prepared (multiple * preps happen for interpreters) */ cap_effective:1;/* true if has elevated effective capabilities, -- cgit v1.2.3 From 1f80769ffd36e74357fe896dc43dddf1af1510f3 Mon Sep 17 00:00:00 2001 From: Paul Fulghum Date: Thu, 2 Apr 2009 16:58:30 -0700 Subject: synclink_gt: add clock options Add support for x8 asynchronous sample rate and ability to specify base clock frequency. Signed-off-by: Paul Fulghum Acked-by: Alan Cox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/synclink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/synclink.h b/include/linux/synclink.h index 99b8bdb17b2..0ff2779c44d 100644 --- a/include/linux/synclink.h +++ b/include/linux/synclink.h @@ -125,6 +125,7 @@ #define MGSL_MODE_MONOSYNC 3 #define MGSL_MODE_BISYNC 4 #define MGSL_MODE_RAW 6 +#define MGSL_MODE_BASE_CLOCK 7 #define MGSL_BUS_TYPE_ISA 1 #define MGSL_BUS_TYPE_EISA 2 -- cgit v1.2.3 From 6dda81f4384b94930826eded254d8c16f89a9248 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Thu, 2 Apr 2009 16:58:35 -0700 Subject: pids: document task_pgrp/task_session is not safe without tasklist/rcu Even if task == current, it is not safe to dereference the result of task_pgrp/task_session. We can race with another thread which changes the special pid via setpgid/setsid. Document this. The next 2 patches give an example of the unsafe usage, we have more bad users. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Oleg Nesterov Cc: Louis Rilling Cc: "Eric W. Biederman" Cc: Pavel Emelyanov Cc: Sukadev Bhattiprolu Cc: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index b47c94e7560..722dd313bf8 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1489,6 +1489,11 @@ static inline struct pid *task_tgid(struct task_struct *task) return task->group_leader->pids[PIDTYPE_PID].pid; } +/* + * Without tasklist or rcu lock it is not safe to dereference + * the result of task_pgrp/task_session even if task == current, + * we can race with another thread doing sys_setsid/sys_setpgid. + */ static inline struct pid *task_pgrp(struct task_struct *task) { return task->group_leader->pids[PIDTYPE_PGID].pid; -- cgit v1.2.3 From 52ee2dfdd4f51cf422ea6a96a0846dc94244aa37 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Thu, 2 Apr 2009 16:58:38 -0700 Subject: pids: refactor vnr/nr_ns helpers to make them safe Inho, the safety rules for vnr/nr_ns helpers are horrible and buggy. task_pid_nr_ns(task) needs rcu/tasklist depending on task == current. As for "special" pids, vnr/nr_ns helpers always need rcu. However, if task != current, they are unsafe even under rcu lock, we can't trust task->group_leader without the special checks. And almost every helper has a callsite which needs a fix. Also, it is a bit annoying that the implementations of, say, task_pgrp_vnr() and task_pgrp_nr_ns() are not "symmetrical". This patch introduces the new helper, __task_pid_nr_ns(), which is always safe to use, and turns all other helpers into the trivial wrappers. After this I'll send another patch which converts task_tgid_xxx() as well, they're are a bit special. Signed-off-by: Oleg Nesterov Cc: Louis Rilling Cc: "Eric W. Biederman" Cc: Pavel Emelyanov Cc: Sukadev Bhattiprolu Cc: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 27 ++++++++++++++++++++------- 1 file changed, 20 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 722dd313bf8..49df878a0ca 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1519,17 +1519,23 @@ struct pid_namespace; * * see also pid_nr() etc in include/linux/pid.h */ +pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, + struct pid_namespace *ns); static inline pid_t task_pid_nr(struct task_struct *tsk) { return tsk->pid; } -pid_t task_pid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns); +static inline pid_t task_pid_nr_ns(struct task_struct *tsk, + struct pid_namespace *ns) +{ + return __task_pid_nr_ns(tsk, PIDTYPE_PID, ns); +} static inline pid_t task_pid_vnr(struct task_struct *tsk) { - return pid_vnr(task_pid(tsk)); + return __task_pid_nr_ns(tsk, PIDTYPE_PID, NULL); } @@ -1551,11 +1557,15 @@ static inline pid_t task_pgrp_nr(struct task_struct *tsk) return tsk->signal->__pgrp; } -pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns); +static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk, + struct pid_namespace *ns) +{ + return __task_pid_nr_ns(tsk, PIDTYPE_PGID, ns); +} static inline pid_t task_pgrp_vnr(struct task_struct *tsk) { - return pid_vnr(task_pgrp(tsk)); + return __task_pid_nr_ns(tsk, PIDTYPE_PGID, NULL); } @@ -1564,14 +1574,17 @@ static inline pid_t task_session_nr(struct task_struct *tsk) return tsk->signal->__session; } -pid_t task_session_nr_ns(struct task_struct *tsk, struct pid_namespace *ns); +static inline pid_t task_session_nr_ns(struct task_struct *tsk, + struct pid_namespace *ns) +{ + return __task_pid_nr_ns(tsk, PIDTYPE_SID, ns); +} static inline pid_t task_session_vnr(struct task_struct *tsk) { - return pid_vnr(task_session(tsk)); + return __task_pid_nr_ns(tsk, PIDTYPE_SID, NULL); } - /** * pid_alive - check that a task structure is not stale * @p: Task structure to be checked. -- cgit v1.2.3 From 1b0f7ffd0ea27cd3a0b9ca04e3df9522048c32a3 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Thu, 2 Apr 2009 16:58:39 -0700 Subject: pids: kill signal_struct-> __pgrp/__session and friends We are wasting 2 words in signal_struct without any reason to implement task_pgrp_nr() and task_session_nr(). task_session_nr() has no callers since 2e2ba22ea4fd4bb85f0fa37c521066db6775cbef, we can remove it. task_pgrp_nr() is still (I believe wrongly) used in fs/autofsX and fs/coda. This patch reimplements task_pgrp_nr() via task_pgrp_nr_ns(), and kills __pgrp/__session and the related helpers. The change in drivers/char/tty_io.c is cosmetic, but hopefully makes sense anyway. Signed-off-by: Oleg Nesterov Acked-by: Alan Cox [tty parts] Cc: Cedric Le Goater Cc: Dave Hansen Cc: Eric Biederman Cc: Pavel Emelyanov Cc: Serge Hallyn Cc: Sukadev Bhattiprolu Cc: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 43 ++++++------------------------------------- 1 file changed, 6 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 49df878a0ca..206ac003e8c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -547,25 +547,8 @@ struct signal_struct { struct list_head cpu_timers[3]; - /* job control IDs */ - - /* - * pgrp and session fields are deprecated. - * use the task_session_Xnr and task_pgrp_Xnr routines below - */ - - union { - pid_t pgrp __deprecated; - pid_t __pgrp; - }; - struct pid *tty_old_pgrp; - union { - pid_t session __deprecated; - pid_t __session; - }; - /* boolean value for session group leader */ int leader; @@ -1469,16 +1452,6 @@ static inline int rt_task(struct task_struct *p) return rt_prio(p->prio); } -static inline void set_task_session(struct task_struct *tsk, pid_t session) -{ - tsk->signal->__session = session; -} - -static inline void set_task_pgrp(struct task_struct *tsk, pid_t pgrp) -{ - tsk->signal->__pgrp = pgrp; -} - static inline struct pid *task_pid(struct task_struct *task) { return task->pids[PIDTYPE_PID].pid; @@ -1552,11 +1525,6 @@ static inline pid_t task_tgid_vnr(struct task_struct *tsk) } -static inline pid_t task_pgrp_nr(struct task_struct *tsk) -{ - return tsk->signal->__pgrp; -} - static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) { @@ -1569,11 +1537,6 @@ static inline pid_t task_pgrp_vnr(struct task_struct *tsk) } -static inline pid_t task_session_nr(struct task_struct *tsk) -{ - return tsk->signal->__session; -} - static inline pid_t task_session_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) { @@ -1585,6 +1548,12 @@ static inline pid_t task_session_vnr(struct task_struct *tsk) return __task_pid_nr_ns(tsk, PIDTYPE_SID, NULL); } +/* obsolete, do not use */ +static inline pid_t task_pgrp_nr(struct task_struct *tsk) +{ + return task_pgrp_nr_ns(tsk, &init_pid_ns); +} + /** * pid_alive - check that a task structure is not stale * @p: Task structure to be checked. -- cgit v1.2.3 From 7c5ff4f92e2b47c56d777a5adbadd9a52841b635 Mon Sep 17 00:00:00 2001 From: Harry Ciao Date: Thu, 2 Apr 2009 16:58:48 -0700 Subject: pci: Add AMD8111 PCI Bridge PCI Device ID Add the PCI Device ID of the PCI Bridge Controller on AMD8111 chip. Signed-off-by: Harry Ciao Cc: Doug Thompson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pci_ids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index cb14fd26083..170f8b1f22d 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -526,6 +526,7 @@ #define PCI_DEVICE_ID_AMD_OPUS_7443 0x7443 #define PCI_DEVICE_ID_AMD_VIPER_7443 0x7443 #define PCI_DEVICE_ID_AMD_OPUS_7445 0x7445 +#define PCI_DEVICE_ID_AMD_8111_PCI 0x7460 #define PCI_DEVICE_ID_AMD_8111_LPC 0x7468 #define PCI_DEVICE_ID_AMD_8111_IDE 0x7469 #define PCI_DEVICE_ID_AMD_8111_SMBUS2 0x746a -- cgit v1.2.3 From 04d491ab2a53008a1aa98ac09561768c7f3adda3 Mon Sep 17 00:00:00 2001 From: Neil Horman Date: Thu, 2 Apr 2009 16:58:57 -0700 Subject: kexec: add dmesg log symbols to /proc/vmcoreinfo lists It would be nice to be able to extract the dmesg log from a vmcore file without needing to keep the debug symbols for the running kernel handy all the time. We have a facility to do this in /proc/vmcore. This patch adds the log_buf and log_end symbols to the vmcoreinfo area so that tools (like makedumpfile) can easily extract the dmesg logs from a vmcore image. [akpm@linux-foundation.org: several fixes and cleanups] [akpm@linux-foundation.org: fix unused log_buf_kexec_setup()] [akpm@linux-foundation.org: build fix] Signed-off-by: Neil Horman Cc: Simon Horman Acked-by: Vivek Goyal Cc: Neil Horman Cc: Simon Horman Cc: Vivek Goyal Cc: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index e720b0da775..556d781e69f 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -242,6 +242,7 @@ extern struct ratelimit_state printk_ratelimit_state; extern int printk_ratelimit(void); extern bool printk_timed_ratelimit(unsigned long *caller_jiffies, unsigned int interval_msec); +void log_buf_kexec_setup(void); #else static inline int vprintk(const char *s, va_list args) __attribute__ ((format (printf, 1, 0))); @@ -253,6 +254,9 @@ static inline int printk_ratelimit(void) { return 0; } static inline bool printk_timed_ratelimit(unsigned long *caller_jiffies, \ unsigned int interval_msec) \ { return false; } +static inline void log_buf_kexec_setup(void) +{ +} #endif extern int printk_needs_cpu(int cpu); -- cgit v1.2.3 From f3554f4bc69803ac2baaf7cf2aa4339e1f4b693e Mon Sep 17 00:00:00 2001 From: Gerd Hoffmann Date: Thu, 2 Apr 2009 16:59:23 -0700 Subject: preadv/pwritev: Add preadv and pwritev system calls. This patch adds preadv and pwritev system calls. These syscalls are a pretty straightforward combination of pread and readv (same for write). They are quite useful for doing vectored I/O in threaded applications. Using lseek+readv instead opens race windows you'll have to plug with locking. Other systems have such system calls too, for example NetBSD, check here: http://www.daemon-systems.org/man/preadv.2.html The application-visible interface provided by glibc should look like this to be compatible to the existing implementations in the *BSD family: ssize_t preadv(int d, const struct iovec *iov, int iovcnt, off_t offset); ssize_t pwritev(int d, const struct iovec *iov, int iovcnt, off_t offset); This prototype has one problem though: On 32bit archs is the (64bit) offset argument unaligned, which the syscall ABI of several archs doesn't allow to do. At least s390 needs a wrapper in glibc to handle this. As we'll need a wrappers in glibc anyway I've decided to push problem to glibc entriely and use a syscall prototype which works without arch-specific wrappers inside the kernel: The offset argument is explicitly splitted into two 32bit values. The patch sports the actual system call implementation and the windup in the x86 system call tables. Other archs follow as separate patches. Signed-off-by: Gerd Hoffmann Cc: Arnd Bergmann Cc: Al Viro Cc: Cc: Cc: Ralf Baechle Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compat.h | 6 ++++++ include/linux/syscalls.h | 4 ++++ 2 files changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index b880864672d..9723edd6455 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -191,6 +191,12 @@ asmlinkage ssize_t compat_sys_readv(unsigned long fd, const struct compat_iovec __user *vec, unsigned long vlen); asmlinkage ssize_t compat_sys_writev(unsigned long fd, const struct compat_iovec __user *vec, unsigned long vlen); +asmlinkage ssize_t compat_sys_preadv(unsigned long fd, + const struct compat_iovec __user *vec, + unsigned long vlen, u32 pos_high, u32 pos_low); +asmlinkage ssize_t compat_sys_pwritev(unsigned long fd, + const struct compat_iovec __user *vec, + unsigned long vlen, u32 pos_high, u32 pos_low); int compat_do_execve(char * filename, compat_uptr_t __user *argv, compat_uptr_t __user *envp, struct pt_regs * regs); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index f9f900cfd06..b299a82a05e 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -461,6 +461,10 @@ asmlinkage long sys_pread64(unsigned int fd, char __user *buf, size_t count, loff_t pos); asmlinkage long sys_pwrite64(unsigned int fd, const char __user *buf, size_t count, loff_t pos); +asmlinkage long sys_preadv(unsigned long fd, const struct iovec __user *vec, + unsigned long vlen, u32 pos_high, u32 pos_low); +asmlinkage long sys_pwritev(unsigned long fd, const struct iovec __user *vec, + unsigned long vlen, u32 pos_high, u32 pos_low); asmlinkage long sys_getcwd(char __user *buf, unsigned long size); asmlinkage long sys_mkdir(const char __user *pathname, int mode); asmlinkage long sys_chdir(const char __user *filename); -- cgit v1.2.3 From e8c158bb313c1df421eab7dc4299cd39cbbf5895 Mon Sep 17 00:00:00 2001 From: Robin Holt Date: Thu, 2 Apr 2009 16:59:45 -0700 Subject: Factor out #ifdefs from kernel/spinlock.c to LOCK_CONTENDED_FLAGS SGI has observed that on large systems, interrupts are not serviced for a long period of time when waiting for a rwlock. The following patch series re-enables irqs while waiting for the lock, resembling the code which is already there for spinlocks. I only made the ia64 version, because the patch adds some overhead to the fast path. I assume there is currently no demand to have this for other architectures, because the systems are not so large. Of course, the possibility to implement raw_{read|write}_lock_flags for any architecture is still there. This patch: The new macro LOCK_CONTENDED_FLAGS expands to the correct implementation depending on the config options, so that IRQ's are re-enabled when possible, but they remain disabled if CONFIG_LOCKDEP is set. Signed-off-by: Petr Tesarik Signed-off-by: Robin Holt Cc: Cc: Ingo Molnar Cc: Peter Zijlstra Cc: "Luck, Tony" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/lockdep.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 5a58ea3e91e..da5a5a1f4cd 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -364,6 +364,23 @@ do { \ #endif /* CONFIG_LOCK_STAT */ +#ifdef CONFIG_LOCKDEP + +/* + * On lockdep we dont want the hand-coded irq-enable of + * _raw_*_lock_flags() code, because lockdep assumes + * that interrupts are not re-enabled during lock-acquire: + */ +#define LOCK_CONTENDED_FLAGS(_lock, try, lock, lockfl, flags) \ + LOCK_CONTENDED((_lock), (try), (lock)) + +#else /* CONFIG_LOCKDEP */ + +#define LOCK_CONTENDED_FLAGS(_lock, try, lock, lockfl, flags) \ + lockfl((_lock), (flags)) + +#endif /* CONFIG_LOCKDEP */ + #ifdef CONFIG_GENERIC_HARDIRQS extern void early_init_irq_lock_class(void); #else -- cgit v1.2.3 From f5f7eac41db827a47b2163330eecd7bb55ae9f12 Mon Sep 17 00:00:00 2001 From: Robin Holt Date: Thu, 2 Apr 2009 16:59:46 -0700 Subject: Allow rwlocks to re-enable interrupts Pass the original flags to rwlock arch-code, so that it can re-enable interrupts if implemented for that architecture. Initially, make __raw_read_lock_flags and __raw_write_lock_flags stubs which just do the same thing as non-flags variants. Signed-off-by: Petr Tesarik Signed-off-by: Robin Holt Acked-by: Peter Zijlstra Cc: Acked-by: Ingo Molnar Cc: "Luck, Tony" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/spinlock.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index a0c66a2e00a..252b245cfcf 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -153,9 +153,11 @@ do { \ extern int _raw_spin_trylock(spinlock_t *lock); extern void _raw_spin_unlock(spinlock_t *lock); extern void _raw_read_lock(rwlock_t *lock); +#define _raw_read_lock_flags(lock, flags) _raw_read_lock(lock) extern int _raw_read_trylock(rwlock_t *lock); extern void _raw_read_unlock(rwlock_t *lock); extern void _raw_write_lock(rwlock_t *lock); +#define _raw_write_lock_flags(lock, flags) _raw_write_lock(lock) extern int _raw_write_trylock(rwlock_t *lock); extern void _raw_write_unlock(rwlock_t *lock); #else @@ -165,9 +167,13 @@ do { \ # define _raw_spin_trylock(lock) __raw_spin_trylock(&(lock)->raw_lock) # define _raw_spin_unlock(lock) __raw_spin_unlock(&(lock)->raw_lock) # define _raw_read_lock(rwlock) __raw_read_lock(&(rwlock)->raw_lock) +# define _raw_read_lock_flags(lock, flags) \ + __raw_read_lock_flags(&(lock)->raw_lock, *(flags)) # define _raw_read_trylock(rwlock) __raw_read_trylock(&(rwlock)->raw_lock) # define _raw_read_unlock(rwlock) __raw_read_unlock(&(rwlock)->raw_lock) # define _raw_write_lock(rwlock) __raw_write_lock(&(rwlock)->raw_lock) +# define _raw_write_lock_flags(lock, flags) \ + __raw_write_lock_flags(&(lock)->raw_lock, *(flags)) # define _raw_write_trylock(rwlock) __raw_write_trylock(&(rwlock)->raw_lock) # define _raw_write_unlock(rwlock) __raw_write_unlock(&(rwlock)->raw_lock) #endif -- cgit v1.2.3 From f7ab34ea723ed304b19698efca85d6f40cecd99b Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 3 Apr 2009 01:34:35 -0400 Subject: ext3: Add replace-on-truncate hueristics for data=writeback mode In data=writeback mode, start an asynchronous flush when closing a file which had been previously truncated down to zero. This lowers the probability of data loss in the case of applications that attempt to replace a file using truncate. Signed-off-by: "Theodore Ts'o" --- include/linux/ext3_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h index dd495b8c309..d2630c56cb3 100644 --- a/include/linux/ext3_fs.h +++ b/include/linux/ext3_fs.h @@ -208,6 +208,7 @@ static inline __u32 ext3_mask_flags(umode_t mode, __u32 flags) #define EXT3_STATE_JDATA 0x00000001 /* journaled data exists */ #define EXT3_STATE_NEW 0x00000002 /* inode is newly created */ #define EXT3_STATE_XATTR 0x00000004 /* has in-inode xattrs */ +#define EXT3_STATE_FLUSH_ON_CLOSE 0x00000008 /* Used to pass group descriptor data when online resize is done */ struct ext3_new_group_input { -- cgit v1.2.3 From 3d544f411f2971eb82f5c52322251eb04494542a Mon Sep 17 00:00:00 2001 From: Pekka Enberg Date: Tue, 24 Mar 2009 11:59:23 +0200 Subject: kmemtrace, fs, security: move alloc_secdata() and free_secdata() to linux/security.h Impact: cleanup We want to remove percpu.h from rcupdate.h (for upcoming kmemtrace changes), but this is not possible currently without breaking the build because fs.h has implicit include file depedencies: it uses GFP_* types in inlines but does not include gfp.h. In practice most fs.h using .c files get gfp.h included implicitly, via an indirect route: via rcupdate.h inclusion - so this underlying problem gets masked in practice. So we want to solve fs.h's dependency on gfp.h. gfp.h can not be included here directly because it is not exported and it would break the build the following way: /home/mingo/tip/usr/include/linux/bsg.h:11: found __[us]{8,16,32,64} type without #include /home/mingo/tip/usr/include/linux/fs.h:11: included file 'linux/gfp.h' is not exported make[3]: *** [/home/mingo/tip/usr/include/linux/.check] Error 1 make[2]: *** [linux] Error 2 As suggested by Alexey Dobriyan, move alloc_secdata() and free_secdata() to linux/security.h - they belong there. This also cleans fs.h of GFP_* usage. Suggested-by: Alexey Dobriyan Signed-off-by: Pekka Enberg Cc: Eduard - Gabriel Munteanu LKML-Reference: <1237906803.25315.96.camel@penberg-laptop> Signed-off-by: Ingo Molnar --- include/linux/fs.h | 21 --------------------- include/linux/security.h | 24 ++++++++++++++++++++++++ 2 files changed, 24 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 61211ad823f..fc4dc28c573 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2382,27 +2382,6 @@ ssize_t simple_attr_read(struct file *file, char __user *buf, ssize_t simple_attr_write(struct file *file, const char __user *buf, size_t len, loff_t *ppos); - -#ifdef CONFIG_SECURITY -static inline char *alloc_secdata(void) -{ - return (char *)get_zeroed_page(GFP_KERNEL); -} - -static inline void free_secdata(void *secdata) -{ - free_page((unsigned long)secdata); -} -#else -static inline char *alloc_secdata(void) -{ - return (char *)1; -} - -static inline void free_secdata(void *secdata) -{ } -#endif /* CONFIG_SECURITY */ - struct ctl_table; int proc_nr_files(struct ctl_table *table, int write, struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos); diff --git a/include/linux/security.h b/include/linux/security.h index 54ed15799a8..d5fd6163606 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -32,6 +32,7 @@ #include #include #include +#include #include /* Maximum number of letters for an LSM name string */ @@ -2953,5 +2954,28 @@ static inline void securityfs_remove(struct dentry *dentry) #endif +#ifdef CONFIG_SECURITY + +static inline char *alloc_secdata(void) +{ + return (char *)get_zeroed_page(GFP_KERNEL); +} + +static inline void free_secdata(void *secdata) +{ + free_page((unsigned long)secdata); +} + +#else + +static inline char *alloc_secdata(void) +{ + return (char *)1; +} + +static inline void free_secdata(void *secdata) +{ } +#endif /* CONFIG_SECURITY */ + #endif /* ! __LINUX_SECURITY_H */ -- cgit v1.2.3 From 76791ab2d5e00c1eef728a8df4347ba133760fb8 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 25 Mar 2009 16:48:35 +0100 Subject: kmemtrace, fs: uninline simple_transaction_set() Impact: cleanup We want to remove percpu.h from rcupdate.h (for upcoming kmemtrace changes), but this is not possible currently without breaking the build because fs.h has an implicit include file depedency: it uses PAGE_SIZE but does not include asm/page.h which defines it. This problem gets masked in practice because most fs.h using sites use rcupreempt.h (and other headers) which includes percpu.h which brings in asm/page.h indirectly. We cannot add asm/page.h to asm/fs.h because page.h is not an exported header. Move simple_transaction_set() to the other simple-transaction file helpers in fs/libfs.c. This removes the include file hell and also reduces kernel size a bit. Acked-by: Al Viro Cc: Alexey Dobriyan Cc: Pekka Enberg Cc: Eduard - Gabriel Munteanu Cc: paulmck@linux.vnet.ibm.com LKML-Reference: <1237898630.25315.83.camel@penberg-laptop> Signed-off-by: Ingo Molnar --- include/linux/fs.h | 14 +------------- 1 file changed, 1 insertion(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index fc4dc28c573..e4de2b543a7 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2323,19 +2323,7 @@ ssize_t simple_transaction_read(struct file *file, char __user *buf, size_t size, loff_t *pos); int simple_transaction_release(struct inode *inode, struct file *file); -static inline void simple_transaction_set(struct file *file, size_t n) -{ - struct simple_transaction_argresp *ar = file->private_data; - - BUG_ON(n > SIMPLE_TRANSACTION_LIMIT); - - /* - * The barrier ensures that ar->size will really remain zero until - * ar->data is ready for reading. - */ - smp_mb(); - ar->size = n; -} +void simple_transaction_set(struct file *file, size_t n); /* * simple attribute files -- cgit v1.2.3 From 21e5445928af0d80f7cf803a77f2b65e9e147890 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 25 Mar 2009 16:29:05 +0100 Subject: kmemtrace, fs: fix linux/fdtable.h header file dependencies Impact: cleanup We want to remove percpu.h from rcupdate.h (for upcoming kmemtrace changes), but this is not possible currently without breaking the build because fdtable.h has an implicit include file dependency: it uses __init does not include init.h. This can cause build failures on non-x86 architectures: /home/mingo/tip/include/linux/fdtable.h:66: error: expected '=', ',', ';', 'asm' or '__attribute__' before 'files_defer_init' make[2]: *** [fs/locks.o] Error 1 We got this header included indirectly via rcupdate.h's percpu.h inclusion - but if that is not there the build will break. Fix it. Cc: Pekka Enberg Cc: Eduard - Gabriel Munteanu Cc: paulmck@linux.vnet.ibm.com LKML-Reference: <1237898630.25315.83.camel@penberg-laptop> Signed-off-by: Ingo Molnar --- include/linux/fdtable.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h index 09d6c5bbddd..a2ec74bc481 100644 --- a/include/linux/fdtable.h +++ b/include/linux/fdtable.h @@ -5,12 +5,14 @@ #ifndef __LINUX_FDTABLE_H #define __LINUX_FDTABLE_H -#include #include #include #include #include #include +#include + +#include /* * The default fd array needs to be at least BITS_PER_LONG, -- cgit v1.2.3 From aa84442d674ef83e1cbf2bce52a20ecff4ce515e Mon Sep 17 00:00:00 2001 From: Pekka Enberg Date: Tue, 24 Mar 2009 10:54:46 +0200 Subject: kmemtrace, security: fix linux/key.h header file dependencies MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Impact: cleanup We want to remove percpu.h from rcupdate.h (for upcoming kmemtrace changes), but this is not possible currently without breaking the build because key.h has an implicit include file dependency on rwsem.h: CC [M] fs/cifs/cifs_spnego.o In file included from include/keys/user-type.h:15, from fs/cifs/cifs_spnego.c:24: include/linux/key.h:128: error: field ‘sem’ has incomplete type make[2]: *** [fs/cifs/cifs_spnego.o] Error 1 make[1]: *** [fs/cifs] Error 2 make: *** [fs] Error 2 Fix it by making the dependency explicit. Signed-off-by: Pekka Enberg Cc: Eduard - Gabriel Munteanu LKML-Reference: <1237884886.25315.39.camel@penberg-laptop> Signed-off-by: Ingo Molnar --- include/linux/key.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/key.h b/include/linux/key.h index 21d32a142c0..e544f466d69 100644 --- a/include/linux/key.h +++ b/include/linux/key.h @@ -20,6 +20,7 @@ #include #include #include +#include #include #ifdef __KERNEL__ -- cgit v1.2.3 From b1f77b0581b8fd837acb4a973f7d5496cae6efee Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 13 Mar 2009 03:20:49 +0100 Subject: kmemtrace, rcu: fix linux/rcutree.h and linux/rcuclassic.h dependencies Impact: build fix for all non-x86 architectures We want to remove percpu.h from rcuclassic.h/rcutree.h (for upcoming kmemtrace changes) but that would break the DECLARE_PER_CPU based declarations in these files. Move the quiescent counter management functions to their respective RCU implementation .c files - they were slightly above the inlining limit anyway. Cc: Pekka Enberg Cc: Eduard - Gabriel Munteanu Cc: paulmck@linux.vnet.ibm.com LKML-Reference: <1237898630.25315.83.camel@penberg-laptop> Signed-off-by: Ingo Molnar --- include/linux/rcuclassic.h | 15 ++------------- include/linux/rcutree.h | 26 ++------------------------ 2 files changed, 4 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcuclassic.h b/include/linux/rcuclassic.h index 80044a4f3ab..2d688b4461f 100644 --- a/include/linux/rcuclassic.h +++ b/include/linux/rcuclassic.h @@ -108,25 +108,14 @@ struct rcu_data { struct rcu_head barrier; }; -DECLARE_PER_CPU(struct rcu_data, rcu_data); -DECLARE_PER_CPU(struct rcu_data, rcu_bh_data); - /* * Increment the quiescent state counter. * The counter is a bit degenerated: We do not need to know * how many quiescent states passed, just if there was at least * one since the start of the grace period. Thus just a flag. */ -static inline void rcu_qsctr_inc(int cpu) -{ - struct rcu_data *rdp = &per_cpu(rcu_data, cpu); - rdp->passed_quiesc = 1; -} -static inline void rcu_bh_qsctr_inc(int cpu) -{ - struct rcu_data *rdp = &per_cpu(rcu_bh_data, cpu); - rdp->passed_quiesc = 1; -} +extern void rcu_qsctr_inc(int cpu); +extern void rcu_bh_qsctr_inc(int cpu); extern int rcu_pending(int cpu); extern int rcu_needs_cpu(int cpu); diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index a722fb67bb2..5d6f425260b 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -236,30 +236,8 @@ struct rcu_state { #endif /* #ifdef CONFIG_NO_HZ */ }; -extern struct rcu_state rcu_state; -DECLARE_PER_CPU(struct rcu_data, rcu_data); - -extern struct rcu_state rcu_bh_state; -DECLARE_PER_CPU(struct rcu_data, rcu_bh_data); - -/* - * Increment the quiescent state counter. - * The counter is a bit degenerated: We do not need to know - * how many quiescent states passed, just if there was at least - * one since the start of the grace period. Thus just a flag. - */ -static inline void rcu_qsctr_inc(int cpu) -{ - struct rcu_data *rdp = &per_cpu(rcu_data, cpu); - rdp->passed_quiesc = 1; - rdp->passed_quiesc_completed = rdp->completed; -} -static inline void rcu_bh_qsctr_inc(int cpu) -{ - struct rcu_data *rdp = &per_cpu(rcu_bh_data, cpu); - rdp->passed_quiesc = 1; - rdp->passed_quiesc_completed = rdp->completed; -} +extern void rcu_qsctr_inc(int cpu); +extern void rcu_bh_qsctr_inc(int cpu); extern int rcu_pending(int cpu); extern int rcu_needs_cpu(int cpu); -- cgit v1.2.3 From a979241c532f07c201fe94e0a632107268f02578 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 25 Mar 2009 16:42:24 +0100 Subject: kmemtrace, rcu: fix rcupreempt.c data structure dependencies Impact: cleanup We want to remove percpu.h from rcupreempt.h, but if we do that the percpu primitives there wont build anymore. Move them to the .c file instead. Cc: Pekka Enberg Cc: Eduard - Gabriel Munteanu Cc: paulmck@linux.vnet.ibm.com LKML-Reference: <1237898630.25315.83.camel@penberg-laptop> Signed-off-by: Ingo Molnar --- include/linux/rcupreempt.h | 51 ++++++++-------------------------------------- 1 file changed, 9 insertions(+), 42 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupreempt.h b/include/linux/rcupreempt.h index 74304b4538d..3eb8fdd1944 100644 --- a/include/linux/rcupreempt.h +++ b/include/linux/rcupreempt.h @@ -40,30 +40,15 @@ #include #include -struct rcu_dyntick_sched { - int dynticks; - int dynticks_snap; - int sched_qs; - int sched_qs_snap; - int sched_dynticks_snap; -}; - -DECLARE_PER_CPU(struct rcu_dyntick_sched, rcu_dyntick_sched); - -static inline void rcu_qsctr_inc(int cpu) -{ - struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu); - - rdssp->sched_qs++; -} -#define rcu_bh_qsctr_inc(cpu) +extern void rcu_qsctr_inc(int cpu); +static inline void rcu_bh_qsctr_inc(int cpu) { } /* * Someone might want to pass call_rcu_bh as a function pointer. * So this needs to just be a rename and not a macro function. * (no parentheses) */ -#define call_rcu_bh call_rcu +#define call_rcu_bh call_rcu /** * call_rcu_sched - Queue RCU callback for invocation after sched grace period. @@ -117,30 +102,12 @@ extern struct rcupreempt_trace *rcupreempt_trace_cpu(int cpu); struct softirq_action; #ifdef CONFIG_NO_HZ - -static inline void rcu_enter_nohz(void) -{ - static DEFINE_RATELIMIT_STATE(rs, 10 * HZ, 1); - - smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */ - __get_cpu_var(rcu_dyntick_sched).dynticks++; - WARN_ON_RATELIMIT(__get_cpu_var(rcu_dyntick_sched).dynticks & 0x1, &rs); -} - -static inline void rcu_exit_nohz(void) -{ - static DEFINE_RATELIMIT_STATE(rs, 10 * HZ, 1); - - __get_cpu_var(rcu_dyntick_sched).dynticks++; - smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */ - WARN_ON_RATELIMIT(!(__get_cpu_var(rcu_dyntick_sched).dynticks & 0x1), - &rs); -} - -#else /* CONFIG_NO_HZ */ -#define rcu_enter_nohz() do { } while (0) -#define rcu_exit_nohz() do { } while (0) -#endif /* CONFIG_NO_HZ */ +extern void rcu_enter_nohz(void); +extern void rcu_exit_nohz(void); +#else +# define rcu_enter_nohz() do { } while (0) +# define rcu_exit_nohz() do { } while (0) +#endif /* * A context switch is a grace period for rcupreempt synchronize_rcu() -- cgit v1.2.3 From ac44021fccd8f1f2b267b004f23a2e8d7ef05f7b Mon Sep 17 00:00:00 2001 From: Eduard - Gabriel Munteanu Date: Mon, 23 Mar 2009 15:12:21 +0200 Subject: kmemtrace, rcu: don't include unnecessary headers, allow kmemtrace w/ tracepoints Impact: cleanup linux/percpu.h includes linux/slab.h, which generates circular inclusion dependencies when trying to switch kmemtrace to use tracepoints instead of markers. This patch allows tracing within slab headers' inline functions. Signed-off-by: Pekka Enberg Cc: Eduard - Gabriel Munteanu Cc: paulmck@linux.vnet.ibm.com LKML-Reference: <1237898630.25315.83.camel@penberg-laptop> Signed-off-by: Ingo Molnar --- include/linux/rcuclassic.h | 1 - include/linux/rcupdate.h | 1 - include/linux/rcupreempt.h | 2 +- include/linux/rcutree.h | 1 - 4 files changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcuclassic.h b/include/linux/rcuclassic.h index 2d688b4461f..bfd92e1e5d2 100644 --- a/include/linux/rcuclassic.h +++ b/include/linux/rcuclassic.h @@ -36,7 +36,6 @@ #include #include #include -#include #include #include diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 528343e6da5..15fbb3ca634 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -36,7 +36,6 @@ #include #include #include -#include #include #include #include diff --git a/include/linux/rcupreempt.h b/include/linux/rcupreempt.h index 3eb8fdd1944..fce522782ff 100644 --- a/include/linux/rcupreempt.h +++ b/include/linux/rcupreempt.h @@ -36,7 +36,7 @@ #include #include #include -#include +#include #include #include diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 5d6f425260b..0cdda00f2b2 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -33,7 +33,6 @@ #include #include #include -#include #include #include -- cgit v1.2.3 From ca2b84cb3c4a0d4d2143b46ec072cdff5d1b3b87 Mon Sep 17 00:00:00 2001 From: Eduard - Gabriel Munteanu Date: Mon, 23 Mar 2009 15:12:24 +0200 Subject: kmemtrace: use tracepoints kmemtrace now uses tracepoints instead of markers. We no longer need to use format specifiers to pass arguments. Signed-off-by: Eduard - Gabriel Munteanu [ folded: Use the new TP_PROTO and TP_ARGS to fix the build. ] [ folded: fix build when CONFIG_KMEMTRACE is disabled. ] [ folded: define tracepoints when CONFIG_TRACEPOINTS is enabled. ] Signed-off-by: Pekka Enberg LKML-Reference: Signed-off-by: Ingo Molnar --- include/linux/slab_def.h | 10 +++++----- include/linux/slub_def.h | 12 ++++-------- 2 files changed, 9 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index f4523651fa4..5ac9b0bcaf9 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -73,8 +73,8 @@ found: ret = kmem_cache_alloc_notrace(cachep, flags); - kmemtrace_mark_alloc(KMEMTRACE_TYPE_KMALLOC, _THIS_IP_, ret, - size, slab_buffer_size(cachep), flags); + trace_kmalloc(_THIS_IP_, ret, + size, slab_buffer_size(cachep), flags); return ret; } @@ -128,9 +128,9 @@ found: ret = kmem_cache_alloc_node_notrace(cachep, flags, node); - kmemtrace_mark_alloc_node(KMEMTRACE_TYPE_KMALLOC, _THIS_IP_, - ret, size, slab_buffer_size(cachep), - flags, node); + trace_kmalloc_node(_THIS_IP_, ret, + size, slab_buffer_size(cachep), + flags, node); return ret; } diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index a1f90528e70..5046f90c117 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -233,8 +233,7 @@ static __always_inline void *kmalloc_large(size_t size, gfp_t flags) unsigned int order = get_order(size); void *ret = (void *) __get_free_pages(flags | __GFP_COMP, order); - kmemtrace_mark_alloc(KMEMTRACE_TYPE_KMALLOC, _THIS_IP_, ret, - size, PAGE_SIZE << order, flags); + trace_kmalloc(_THIS_IP_, ret, size, PAGE_SIZE << order, flags); return ret; } @@ -255,9 +254,7 @@ static __always_inline void *kmalloc(size_t size, gfp_t flags) ret = kmem_cache_alloc_notrace(s, flags); - kmemtrace_mark_alloc(KMEMTRACE_TYPE_KMALLOC, - _THIS_IP_, ret, - size, s->size, flags); + trace_kmalloc(_THIS_IP_, ret, size, s->size, flags); return ret; } @@ -296,9 +293,8 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) ret = kmem_cache_alloc_node_notrace(s, flags, node); - kmemtrace_mark_alloc_node(KMEMTRACE_TYPE_KMALLOC, - _THIS_IP_, ret, - size, s->size, flags, node); + trace_kmalloc_node(_THIS_IP_, ret, + size, s->size, flags, node); return ret; } -- cgit v1.2.3 From 07fe7cb7c7c179f473fd9c823348fd3eb5dad369 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 3 Apr 2009 16:42:35 +0100 Subject: Create a dynamically sized pool of threads for doing very slow work items Create a dynamically sized pool of threads for doing very slow work items, such as invoking mkdir() or rmdir() - things that may take a long time and may sleep, holding mutexes/semaphores and hogging a thread, and are thus unsuitable for workqueues. The number of threads is always at least a settable minimum, but more are started when there's more work to do, up to a limit. Because of the nature of the load, it's not suitable for a 1-thread-per-CPU type pool. A system with one CPU may well want several threads. This is used by FS-Cache to do slow caching operations in the background, such as looking up, creating or deleting cache objects. Signed-off-by: David Howells Acked-by: Serge Hallyn Acked-by: Steve Dickson Acked-by: Trond Myklebust Acked-by: Al Viro Tested-by: Daire Byrne --- include/linux/slow-work.h | 88 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 88 insertions(+) create mode 100644 include/linux/slow-work.h (limited to 'include/linux') diff --git a/include/linux/slow-work.h b/include/linux/slow-work.h new file mode 100644 index 00000000000..4dd754af393 --- /dev/null +++ b/include/linux/slow-work.h @@ -0,0 +1,88 @@ +/* Worker thread pool for slow items, such as filesystem lookups or mkdirs + * + * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#ifndef _LINUX_SLOW_WORK_H +#define _LINUX_SLOW_WORK_H + +#ifdef CONFIG_SLOW_WORK + +struct slow_work; + +/* + * The operations used to support slow work items + */ +struct slow_work_ops { + /* get a ref on a work item + * - return 0 if successful, -ve if not + */ + int (*get_ref)(struct slow_work *work); + + /* discard a ref to a work item */ + void (*put_ref)(struct slow_work *work); + + /* execute a work item */ + void (*execute)(struct slow_work *work); +}; + +/* + * A slow work item + * - A reference is held on the parent object by the thread pool when it is + * queued + */ +struct slow_work { + unsigned long flags; +#define SLOW_WORK_PENDING 0 /* item pending (further) execution */ +#define SLOW_WORK_EXECUTING 1 /* item currently executing */ +#define SLOW_WORK_ENQ_DEFERRED 2 /* item enqueue deferred */ +#define SLOW_WORK_VERY_SLOW 3 /* item is very slow */ + const struct slow_work_ops *ops; /* operations table for this item */ + struct list_head link; /* link in queue */ +}; + +/** + * slow_work_init - Initialise a slow work item + * @work: The work item to initialise + * @ops: The operations to use to handle the slow work item + * + * Initialise a slow work item. + */ +static inline void slow_work_init(struct slow_work *work, + const struct slow_work_ops *ops) +{ + work->flags = 0; + work->ops = ops; + INIT_LIST_HEAD(&work->link); +} + +/** + * slow_work_init - Initialise a very slow work item + * @work: The work item to initialise + * @ops: The operations to use to handle the slow work item + * + * Initialise a very slow work item. This item will be restricted such that + * only a certain number of the pool threads will be able to execute items of + * this type. + */ +static inline void vslow_work_init(struct slow_work *work, + const struct slow_work_ops *ops) +{ + work->flags = 1 << SLOW_WORK_VERY_SLOW; + work->ops = ops; + INIT_LIST_HEAD(&work->link); +} + +extern int slow_work_enqueue(struct slow_work *work); +extern int slow_work_register_user(void); +extern void slow_work_unregister_user(void); + + +#endif /* CONFIG_SLOW_WORK */ +#endif /* _LINUX_SLOW_WORK_H */ -- cgit v1.2.3 From 12e22c5e4bc08ab4b05ac079fe40d9891c5e81a0 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 3 Apr 2009 16:42:35 +0100 Subject: Make the slow work pool configurable Make the slow work pool configurable through /proc/sys/kernel/slow-work. (*) /proc/sys/kernel/slow-work/min-threads The minimum number of threads that should be in the pool as long as it is in use. This may be anywhere between 2 and max-threads. (*) /proc/sys/kernel/slow-work/max-threads The maximum number of threads that should in the pool. This may be anywhere between min-threads and 255 or NR_CPUS * 2, whichever is greater. (*) /proc/sys/kernel/slow-work/vslow-percentage The percentage of active threads in the pool that may be used to execute very slow work items. This may be between 1 and 99. The resultant number is bounded to between 1 and one fewer than the number of active threads. This ensures there is always at least one thread that can process very slow work items, and always at least one thread that won't. Signed-off-by: David Howells Acked-by: Serge Hallyn Acked-by: Steve Dickson Acked-by: Trond Myklebust Acked-by: Al Viro Tested-by: Daire Byrne --- include/linux/slow-work.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/slow-work.h b/include/linux/slow-work.h index 4dd754af393..8262809dfa8 100644 --- a/include/linux/slow-work.h +++ b/include/linux/slow-work.h @@ -14,6 +14,8 @@ #ifdef CONFIG_SLOW_WORK +#include + struct slow_work; /* @@ -83,6 +85,9 @@ extern int slow_work_enqueue(struct slow_work *work); extern int slow_work_register_user(void); extern void slow_work_unregister_user(void); +#ifdef CONFIG_SYSCTL +extern ctl_table slow_work_sysctls[]; +#endif #endif /* CONFIG_SLOW_WORK */ #endif /* _LINUX_SLOW_WORK_H */ -- cgit v1.2.3 From 8f0aa2f25b31ba27db84259141e52ee6ec0d2820 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 3 Apr 2009 16:42:35 +0100 Subject: Document the slow work thread pool Document the slow work thread pool. Signed-off-by: David Howells Acked-by: Steve Dickson Acked-by: Trond Myklebust Acked-by: Al Viro Tested-by: Daire Byrne --- include/linux/slow-work.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/slow-work.h b/include/linux/slow-work.h index 8262809dfa8..85958277f83 100644 --- a/include/linux/slow-work.h +++ b/include/linux/slow-work.h @@ -7,6 +7,8 @@ * modify it under the terms of the GNU General Public Licence * as published by the Free Software Foundation; either version * 2 of the Licence, or (at your option) any later version. + * + * See Documentation/slow-work.txt */ #ifndef _LINUX_SLOW_WORK_H -- cgit v1.2.3 From 03fb3d2af96c2783c3a5bc03f3d984cf422f0e69 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 3 Apr 2009 16:42:35 +0100 Subject: FS-Cache: Release page->private after failed readahead The attached patch causes read_cache_pages() to release page-private data on a page for which add_to_page_cache() fails. If the filler function fails, then the problematic page is left attached to the pagecache (with appropriate flags set, one presumes) and the remaining to-be-attached pages are invalidated and discarded. This permits pages with caching references associated with them to be cleaned up. The invalidatepage() address space op is called (indirectly) to do the honours. Signed-off-by: David Howells Acked-by: Steve Dickson Acked-by: Trond Myklebust Acked-by: Rik van Riel Acked-by: Al Viro Tested-by: Daire Byrne --- include/linux/page-flags.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 61df1779b2a..9d99e7471ad 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -182,7 +182,7 @@ static inline int TestClearPage##uname(struct page *page) { return 0; } struct page; /* forward declaration */ -TESTPAGEFLAG(Locked, locked) +TESTPAGEFLAG(Locked, locked) TESTSETFLAG(Locked, locked) PAGEFLAG(Error, error) PAGEFLAG(Referenced, referenced) TESTCLEARFLAG(Referenced, referenced) PAGEFLAG(Dirty, dirty) TESTSCFLAG(Dirty, dirty) __CLEARPAGEFLAG(Dirty, dirty) -- cgit v1.2.3 From 266cf658efcf6ac33541a46740f74f50c79d2b6b Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 3 Apr 2009 16:42:36 +0100 Subject: FS-Cache: Recruit a page flags for cache management Recruit a page flag to aid in cache management. The following extra flag is defined: (1) PG_fscache (PG_private_2) The marked page is backed by a local cache and is pinning resources in the cache driver. If PG_fscache is set, then things that checked for PG_private will now also check for that. This includes things like truncation and page invalidation. The function page_has_private() had been added to make the checks for both PG_private and PG_private_2 at the same time. Signed-off-by: David Howells Acked-by: Steve Dickson Acked-by: Trond Myklebust Acked-by: Rik van Riel Acked-by: Al Viro Tested-by: Daire Byrne --- include/linux/page-flags.h | 38 +++++++++++++++++++++++++++++++++----- 1 file changed, 33 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 9d99e7471ad..62214c7d2d9 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -82,6 +82,7 @@ enum pageflags { PG_arch_1, PG_reserved, PG_private, /* If pagecache, has fs-private data */ + PG_private_2, /* If pagecache, has fs aux data */ PG_writeback, /* Page is under writeback */ #ifdef CONFIG_PAGEFLAGS_EXTENDED PG_head, /* A head page */ @@ -108,6 +109,12 @@ enum pageflags { /* Filesystems */ PG_checked = PG_owner_priv_1, + /* Two page bits are conscripted by FS-Cache to maintain local caching + * state. These bits are set on pages belonging to the netfs's inodes + * when those inodes are being locally cached. + */ + PG_fscache = PG_private_2, /* page backed by cache */ + /* XEN */ PG_pinned = PG_owner_priv_1, PG_savepinned = PG_dirty, @@ -194,8 +201,6 @@ PAGEFLAG(Checked, checked) /* Used by some filesystems */ PAGEFLAG(Pinned, pinned) TESTSCFLAG(Pinned, pinned) /* Xen */ PAGEFLAG(SavePinned, savepinned); /* Xen */ PAGEFLAG(Reserved, reserved) __CLEARPAGEFLAG(Reserved, reserved) -PAGEFLAG(Private, private) __CLEARPAGEFLAG(Private, private) - __SETPAGEFLAG(Private, private) PAGEFLAG(SwapBacked, swapbacked) __CLEARPAGEFLAG(SwapBacked, swapbacked) __PAGEFLAG(SlobPage, slob_page) @@ -204,6 +209,16 @@ __PAGEFLAG(SlobFree, slob_free) __PAGEFLAG(SlubFrozen, slub_frozen) __PAGEFLAG(SlubDebug, slub_debug) +/* + * Private page markings that may be used by the filesystem that owns the page + * for its own purposes. + * - PG_private and PG_private_2 cause releasepage() and co to be invoked + */ +PAGEFLAG(Private, private) __SETPAGEFLAG(Private, private) + __CLEARPAGEFLAG(Private, private) +PAGEFLAG(Private2, private_2) TESTSCFLAG(Private2, private_2) +PAGEFLAG(OwnerPriv1, owner_priv_1) TESTCLEARFLAG(OwnerPriv1, owner_priv_1) + /* * Only test-and-set exist for PG_writeback. The unconditional operators are * risky: they bypass page accounting. @@ -384,9 +399,10 @@ static inline void __ClearPageTail(struct page *page) * these flags set. It they are, there is a problem. */ #define PAGE_FLAGS_CHECK_AT_FREE \ - (1 << PG_lru | 1 << PG_private | 1 << PG_locked | \ - 1 << PG_buddy | 1 << PG_writeback | 1 << PG_reserved | \ - 1 << PG_slab | 1 << PG_swapcache | 1 << PG_active | \ + (1 << PG_lru | 1 << PG_locked | \ + 1 << PG_private | 1 << PG_private_2 | \ + 1 << PG_buddy | 1 << PG_writeback | 1 << PG_reserved | \ + 1 << PG_slab | 1 << PG_swapcache | 1 << PG_active | \ __PG_UNEVICTABLE | __PG_MLOCKED) /* @@ -397,4 +413,16 @@ static inline void __ClearPageTail(struct page *page) #define PAGE_FLAGS_CHECK_AT_PREP ((1 << NR_PAGEFLAGS) - 1) #endif /* !__GENERATING_BOUNDS_H */ + +/** + * page_has_private - Determine if page has private stuff + * @page: The page to be checked + * + * Determine if a page has private stuff, indicating that release routines + * should be invoked upon it. + */ +#define page_has_private(page) \ + ((page)->flags & ((1 << PG_private) | \ + (1 << PG_private_2))) + #endif /* PAGE_FLAGS_H */ -- cgit v1.2.3 From 2d6fff637037395cc946ef910a880b5fa67b5370 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 3 Apr 2009 16:42:36 +0100 Subject: FS-Cache: Add the FS-Cache netfs API and documentation Add the API for a generic facility (FS-Cache) by which filesystems (such as AFS or NFS) may call on local caching capabilities without having to know anything about how the cache works, or even if there is a cache: +---------+ | | +--------------+ | NFS |--+ | | | | | +-->| CacheFS | +---------+ | +----------+ | | /dev/hda5 | | | | | +--------------+ +---------+ +-->| | | | | | |--+ | AFS |----->| FS-Cache | | | | |--+ +---------+ +-->| | | | | | | +--------------+ +---------+ | +----------+ | | | | | | +-->| CacheFiles | | ISOFS |--+ | /var/cache | | | +--------------+ +---------+ General documentation and documentation of the netfs specific API are provided in addition to the header files. As this patch stands, it is possible to build a filesystem against the facility and attempt to use it. All that will happen is that all requests will be immediately denied as if no cache is present. Further patches will implement the core of the facility. The facility will transfer requests from networking filesystems to appropriate caches if possible, or else gracefully deny them. If this facility is disabled in the kernel configuration, then all its operations will trivially reduce to nothing during compilation. WHY NOT I_MAPPING? ================== I have added my own API to implement caching rather than using i_mapping to do this for a number of reasons. These have been discussed a lot on the LKML and CacheFS mailing lists, but to summarise the basics: (1) Most filesystems don't do hole reportage. Holes in files are treated as blocks of zeros and can't be distinguished otherwise, making it difficult to distinguish blocks that have been read from the network and cached from those that haven't. (2) The backing inode must be fully populated before being exposed to userspace through the main inode because the VM/VFS goes directly to the backing inode and does not interrogate the front inode's VM ops. Therefore: (a) The backing inode must fit entirely within the cache. (b) All backed files currently open must fit entirely within the cache at the same time. (c) A working set of files in total larger than the cache may not be cached. (d) A file may not grow larger than the available space in the cache. (e) A file that's open and cached, and remotely grows larger than the cache is potentially stuffed. (3) Writes go to the backing filesystem, and can only be transferred to the network when the file is closed. (4) There's no record of what changes have been made, so the whole file must be written back. (5) The pages belong to the backing filesystem, and all metadata associated with that page are relevant only to the backing filesystem, and not anything stacked atop it. OVERVIEW ======== FS-Cache provides (or will provide) the following facilities: (1) Caches can be added / removed at any time, even whilst in use. (2) Adds a facility by which tags can be used to refer to caches, even if they're not available yet. (3) More than one cache can be used at once. Caches can be selected explicitly by use of tags. (4) The netfs is provided with an interface that allows either party to withdraw caching facilities from a file (required for (1)). (5) A netfs may annotate cache objects that belongs to it. This permits the storage of coherency maintenance data. (6) Cache objects will be pinnable and space reservations will be possible. (7) The interface to the netfs returns as few errors as possible, preferring rather to let the netfs remain oblivious. (8) Cookies are used to represent indices, files and other objects to the netfs. The simplest cookie is just a NULL pointer - indicating nothing cached there. (9) The netfs is allowed to propose - dynamically - any index hierarchy it desires, though it must be aware that the index search function is recursive, stack space is limited, and indices can only be children of indices. (10) Indices can be used to group files together to reduce key size and to make group invalidation easier. The use of indices may make lookup quicker, but that's cache dependent. (11) Data I/O is effectively done directly to and from the netfs's pages. The netfs indicates that page A is at index B of the data-file represented by cookie C, and that it should be read or written. The cache backend may or may not start I/O on that page, but if it does, a netfs callback will be invoked to indicate completion. The I/O may be either synchronous or asynchronous. (12) Cookies can be "retired" upon release. At this point FS-Cache will mark them as obsolete and the index hierarchy rooted at that point will get recycled. (13) The netfs provides a "match" function for index searches. In addition to saying whether a match was made or not, this can also specify that an entry should be updated or deleted. FS-Cache maintains a virtual index tree in which all indices, files, objects and pages are kept. Bits of this tree may actually reside in one or more caches. FSDEF | +------------------------------------+ | | NFS AFS | | +--------------------------+ +-----------+ | | | | homedir mirror afs.org redhat.com | | | +------------+ +---------------+ +----------+ | | | | | | 00001 00002 00007 00125 vol00001 vol00002 | | | | | +---+---+ +-----+ +---+ +------+------+ +-----+----+ | | | | | | | | | | | | | PG0 PG1 PG2 PG0 XATTR PG0 PG1 DIRENT DIRENT DIRENT R/W R/O Bak | | PG0 +-------+ | | 00001 00003 | +---+---+ | | | PG0 PG1 PG2 In the example above, two netfs's can be seen to be backed: NFS and AFS. These have different index hierarchies: (*) The NFS primary index will probably contain per-server indices. Each server index is indexed by NFS file handles to get data file objects. Each data file objects can have an array of pages, but may also have further child objects, such as extended attributes and directory entries. Extended attribute objects themselves have page-array contents. (*) The AFS primary index contains per-cell indices. Each cell index contains per-logical-volume indices. Each of volume index contains up to three indices for the read-write, read-only and backup mirrors of those volumes. Each of these contains vnode data file objects, each of which contains an array of pages. The very top index is the FS-Cache master index in which individual netfs's have entries. Any index object may reside in more than one cache, provided it only has index children. Any index with non-index object children will be assumed to only reside in one cache. The FS-Cache overview can be found in: Documentation/filesystems/caching/fscache.txt The netfs API to FS-Cache can be found in: Documentation/filesystems/caching/netfs-api.txt Signed-off-by: David Howells Acked-by: Steve Dickson Acked-by: Trond Myklebust Acked-by: Al Viro Tested-by: Daire Byrne --- include/linux/fscache.h | 548 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 548 insertions(+) create mode 100644 include/linux/fscache.h (limited to 'include/linux') diff --git a/include/linux/fscache.h b/include/linux/fscache.h new file mode 100644 index 00000000000..feb3b0e0af4 --- /dev/null +++ b/include/linux/fscache.h @@ -0,0 +1,548 @@ +/* General filesystem caching interface + * + * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * NOTE!!! See: + * + * Documentation/filesystems/caching/netfs-api.txt + * + * for a description of the network filesystem interface declared here. + */ + +#ifndef _LINUX_FSCACHE_H +#define _LINUX_FSCACHE_H + +#include +#include +#include +#include + +#if defined(CONFIG_FSCACHE) || defined(CONFIG_FSCACHE_MODULE) +#define fscache_available() (1) +#define fscache_cookie_valid(cookie) (cookie) +#else +#define fscache_available() (0) +#define fscache_cookie_valid(cookie) (0) +#endif + + +/* + * overload PG_private_2 to give us PG_fscache - this is used to indicate that + * a page is currently backed by a local disk cache + */ +#define PageFsCache(page) PagePrivate2((page)) +#define SetPageFsCache(page) SetPagePrivate2((page)) +#define ClearPageFsCache(page) ClearPagePrivate2((page)) +#define TestSetPageFsCache(page) TestSetPagePrivate2((page)) +#define TestClearPageFsCache(page) TestClearPagePrivate2((page)) + +/* pattern used to fill dead space in an index entry */ +#define FSCACHE_INDEX_DEADFILL_PATTERN 0x79 + +struct pagevec; +struct fscache_cache_tag; +struct fscache_cookie; +struct fscache_netfs; + +typedef void (*fscache_rw_complete_t)(struct page *page, + void *context, + int error); + +/* result of index entry consultation */ +enum fscache_checkaux { + FSCACHE_CHECKAUX_OKAY, /* entry okay as is */ + FSCACHE_CHECKAUX_NEEDS_UPDATE, /* entry requires update */ + FSCACHE_CHECKAUX_OBSOLETE, /* entry requires deletion */ +}; + +/* + * fscache cookie definition + */ +struct fscache_cookie_def { + /* name of cookie type */ + char name[16]; + + /* cookie type */ + uint8_t type; +#define FSCACHE_COOKIE_TYPE_INDEX 0 +#define FSCACHE_COOKIE_TYPE_DATAFILE 1 + + /* select the cache into which to insert an entry in this index + * - optional + * - should return a cache identifier or NULL to cause the cache to be + * inherited from the parent if possible or the first cache picked + * for a non-index file if not + */ + struct fscache_cache_tag *(*select_cache)( + const void *parent_netfs_data, + const void *cookie_netfs_data); + + /* get an index key + * - should store the key data in the buffer + * - should return the amount of amount stored + * - not permitted to return an error + * - the netfs data from the cookie being used as the source is + * presented + */ + uint16_t (*get_key)(const void *cookie_netfs_data, + void *buffer, + uint16_t bufmax); + + /* get certain file attributes from the netfs data + * - this function can be absent for an index + * - not permitted to return an error + * - the netfs data from the cookie being used as the source is + * presented + */ + void (*get_attr)(const void *cookie_netfs_data, uint64_t *size); + + /* get the auxilliary data from netfs data + * - this function can be absent if the index carries no state data + * - should store the auxilliary data in the buffer + * - should return the amount of amount stored + * - not permitted to return an error + * - the netfs data from the cookie being used as the source is + * presented + */ + uint16_t (*get_aux)(const void *cookie_netfs_data, + void *buffer, + uint16_t bufmax); + + /* consult the netfs about the state of an object + * - this function can be absent if the index carries no state data + * - the netfs data from the cookie being used as the target is + * presented, as is the auxilliary data + */ + enum fscache_checkaux (*check_aux)(void *cookie_netfs_data, + const void *data, + uint16_t datalen); + + /* get an extra reference on a read context + * - this function can be absent if the completion function doesn't + * require a context + */ + void (*get_context)(void *cookie_netfs_data, void *context); + + /* release an extra reference on a read context + * - this function can be absent if the completion function doesn't + * require a context + */ + void (*put_context)(void *cookie_netfs_data, void *context); + + /* indicate pages that now have cache metadata retained + * - this function should mark the specified pages as now being cached + * - the pages will have been marked with PG_fscache before this is + * called, so this is optional + */ + void (*mark_pages_cached)(void *cookie_netfs_data, + struct address_space *mapping, + struct pagevec *cached_pvec); + + /* indicate the cookie is no longer cached + * - this function is called when the backing store currently caching + * a cookie is removed + * - the netfs should use this to clean up any markers indicating + * cached pages + * - this is mandatory for any object that may have data + */ + void (*now_uncached)(void *cookie_netfs_data); +}; + +/* + * fscache cached network filesystem type + * - name, version and ops must be filled in before registration + * - all other fields will be set during registration + */ +struct fscache_netfs { + uint32_t version; /* indexing version */ + const char *name; /* filesystem name */ + struct fscache_cookie *primary_index; + struct list_head link; /* internal link */ +}; + +/* + * slow-path functions for when there is actually caching available, and the + * netfs does actually have a valid token + * - these are not to be called directly + * - these are undefined symbols when FS-Cache is not configured and the + * optimiser takes care of not using them + */ + +/** + * fscache_register_netfs - Register a filesystem as desiring caching services + * @netfs: The description of the filesystem + * + * Register a filesystem as desiring caching services if they're available. + * + * See Documentation/filesystems/caching/netfs-api.txt for a complete + * description. + */ +static inline +int fscache_register_netfs(struct fscache_netfs *netfs) +{ + return 0; +} + +/** + * fscache_unregister_netfs - Indicate that a filesystem no longer desires + * caching services + * @netfs: The description of the filesystem + * + * Indicate that a filesystem no longer desires caching services for the + * moment. + * + * See Documentation/filesystems/caching/netfs-api.txt for a complete + * description. + */ +static inline +void fscache_unregister_netfs(struct fscache_netfs *netfs) +{ +} + +/** + * fscache_lookup_cache_tag - Look up a cache tag + * @name: The name of the tag to search for + * + * Acquire a specific cache referral tag that can be used to select a specific + * cache in which to cache an index. + * + * See Documentation/filesystems/caching/netfs-api.txt for a complete + * description. + */ +static inline +struct fscache_cache_tag *fscache_lookup_cache_tag(const char *name) +{ + return NULL; +} + +/** + * fscache_release_cache_tag - Release a cache tag + * @tag: The tag to release + * + * Release a reference to a cache referral tag previously looked up. + * + * See Documentation/filesystems/caching/netfs-api.txt for a complete + * description. + */ +static inline +void fscache_release_cache_tag(struct fscache_cache_tag *tag) +{ +} + +/** + * fscache_acquire_cookie - Acquire a cookie to represent a cache object + * @parent: The cookie that's to be the parent of this one + * @def: A description of the cache object, including callback operations + * @netfs_data: An arbitrary piece of data to be kept in the cookie to + * represent the cache object to the netfs + * + * This function is used to inform FS-Cache about part of an index hierarchy + * that can be used to locate files. This is done by requesting a cookie for + * each index in the path to the file. + * + * See Documentation/filesystems/caching/netfs-api.txt for a complete + * description. + */ +static inline +struct fscache_cookie *fscache_acquire_cookie( + struct fscache_cookie *parent, + const struct fscache_cookie_def *def, + void *netfs_data) +{ + return NULL; +} + +/** + * fscache_relinquish_cookie - Return the cookie to the cache, maybe discarding + * it + * @cookie: The cookie being returned + * @retire: True if the cache object the cookie represents is to be discarded + * + * This function returns a cookie to the cache, forcibly discarding the + * associated cache object if retire is set to true. + * + * See Documentation/filesystems/caching/netfs-api.txt for a complete + * description. + */ +static inline +void fscache_relinquish_cookie(struct fscache_cookie *cookie, int retire) +{ +} + +/** + * fscache_update_cookie - Request that a cache object be updated + * @cookie: The cookie representing the cache object + * + * Request an update of the index data for the cache object associated with the + * cookie. + * + * See Documentation/filesystems/caching/netfs-api.txt for a complete + * description. + */ +static inline +void fscache_update_cookie(struct fscache_cookie *cookie) +{ +} + +/** + * fscache_pin_cookie - Pin a data-storage cache object in its cache + * @cookie: The cookie representing the cache object + * + * Permit data-storage cache objects to be pinned in the cache. + * + * See Documentation/filesystems/caching/netfs-api.txt for a complete + * description. + */ +static inline +int fscache_pin_cookie(struct fscache_cookie *cookie) +{ + return -ENOBUFS; +} + +/** + * fscache_pin_cookie - Unpin a data-storage cache object in its cache + * @cookie: The cookie representing the cache object + * + * Permit data-storage cache objects to be unpinned from the cache. + * + * See Documentation/filesystems/caching/netfs-api.txt for a complete + * description. + */ +static inline +void fscache_unpin_cookie(struct fscache_cookie *cookie) +{ +} + +/** + * fscache_attr_changed - Notify cache that an object's attributes changed + * @cookie: The cookie representing the cache object + * + * Send a notification to the cache indicating that an object's attributes have + * changed. This includes the data size. These attributes will be obtained + * through the get_attr() cookie definition op. + * + * See Documentation/filesystems/caching/netfs-api.txt for a complete + * description. + */ +static inline +int fscache_attr_changed(struct fscache_cookie *cookie) +{ + return -ENOBUFS; +} + +/** + * fscache_reserve_space - Reserve data space for a cached object + * @cookie: The cookie representing the cache object + * @i_size: The amount of space to be reserved + * + * Reserve an amount of space in the cache for the cache object attached to a + * cookie so that a write to that object within the space can always be + * honoured. + * + * See Documentation/filesystems/caching/netfs-api.txt for a complete + * description. + */ +static inline +int fscache_reserve_space(struct fscache_cookie *cookie, loff_t size) +{ + return -ENOBUFS; +} + +/** + * fscache_read_or_alloc_page - Read a page from the cache or allocate a block + * in which to store it + * @cookie: The cookie representing the cache object + * @page: The netfs page to fill if possible + * @end_io_func: The callback to invoke when and if the page is filled + * @context: An arbitrary piece of data to pass on to end_io_func() + * @gfp: The conditions under which memory allocation should be made + * + * Read a page from the cache, or if that's not possible make a potential + * one-block reservation in the cache into which the page may be stored once + * fetched from the server. + * + * If the page is not backed by the cache object, or if it there's some reason + * it can't be, -ENOBUFS will be returned and nothing more will be done for + * that page. + * + * Else, if that page is backed by the cache, a read will be initiated directly + * to the netfs's page and 0 will be returned by this function. The + * end_io_func() callback will be invoked when the operation terminates on a + * completion or failure. Note that the callback may be invoked before the + * return. + * + * Else, if the page is unbacked, -ENODATA is returned and a block may have + * been allocated in the cache. + * + * See Documentation/filesystems/caching/netfs-api.txt for a complete + * description. + */ +static inline +int fscache_read_or_alloc_page(struct fscache_cookie *cookie, + struct page *page, + fscache_rw_complete_t end_io_func, + void *context, + gfp_t gfp) +{ + return -ENOBUFS; +} + +/** + * fscache_read_or_alloc_pages - Read pages from the cache and/or allocate + * blocks in which to store them + * @cookie: The cookie representing the cache object + * @mapping: The netfs inode mapping to which the pages will be attached + * @pages: A list of potential netfs pages to be filled + * @end_io_func: The callback to invoke when and if each page is filled + * @context: An arbitrary piece of data to pass on to end_io_func() + * @gfp: The conditions under which memory allocation should be made + * + * Read a set of pages from the cache, or if that's not possible, attempt to + * make a potential one-block reservation for each page in the cache into which + * that page may be stored once fetched from the server. + * + * If some pages are not backed by the cache object, or if it there's some + * reason they can't be, -ENOBUFS will be returned and nothing more will be + * done for that pages. + * + * Else, if some of the pages are backed by the cache, a read will be initiated + * directly to the netfs's page and 0 will be returned by this function. The + * end_io_func() callback will be invoked when the operation terminates on a + * completion or failure. Note that the callback may be invoked before the + * return. + * + * Else, if a page is unbacked, -ENODATA is returned and a block may have + * been allocated in the cache. + * + * Because the function may want to return all of -ENOBUFS, -ENODATA and 0 in + * regard to different pages, the return values are prioritised in that order. + * Any pages submitted for reading are removed from the pages list. + * + * See Documentation/filesystems/caching/netfs-api.txt for a complete + * description. + */ +static inline +int fscache_read_or_alloc_pages(struct fscache_cookie *cookie, + struct address_space *mapping, + struct list_head *pages, + unsigned *nr_pages, + fscache_rw_complete_t end_io_func, + void *context, + gfp_t gfp) +{ + return -ENOBUFS; +} + +/** + * fscache_alloc_page - Allocate a block in which to store a page + * @cookie: The cookie representing the cache object + * @page: The netfs page to allocate a page for + * @gfp: The conditions under which memory allocation should be made + * + * Request Allocation a block in the cache in which to store a netfs page + * without retrieving any contents from the cache. + * + * If the page is not backed by a file then -ENOBUFS will be returned and + * nothing more will be done, and no reservation will be made. + * + * Else, a block will be allocated if one wasn't already, and 0 will be + * returned + * + * See Documentation/filesystems/caching/netfs-api.txt for a complete + * description. + */ +static inline +int fscache_alloc_page(struct fscache_cookie *cookie, + struct page *page, + gfp_t gfp) +{ + return -ENOBUFS; +} + +/** + * fscache_write_page - Request storage of a page in the cache + * @cookie: The cookie representing the cache object + * @page: The netfs page to store + * @gfp: The conditions under which memory allocation should be made + * + * Request the contents of the netfs page be written into the cache. This + * request may be ignored if no cache block is currently allocated, in which + * case it will return -ENOBUFS. + * + * If a cache block was already allocated, a write will be initiated and 0 will + * be returned. The PG_fscache_write page bit is set immediately and will then + * be cleared at the completion of the write to indicate the success or failure + * of the operation. Note that the completion may happen before the return. + * + * See Documentation/filesystems/caching/netfs-api.txt for a complete + * description. + */ +static inline +int fscache_write_page(struct fscache_cookie *cookie, + struct page *page, + gfp_t gfp) +{ + return -ENOBUFS; +} + +/** + * fscache_uncache_page - Indicate that caching is no longer required on a page + * @cookie: The cookie representing the cache object + * @page: The netfs page that was being cached. + * + * Tell the cache that we no longer want a page to be cached and that it should + * remove any knowledge of the netfs page it may have. + * + * Note that this cannot cancel any outstanding I/O operations between this + * page and the cache. + * + * See Documentation/filesystems/caching/netfs-api.txt for a complete + * description. + */ +static inline +void fscache_uncache_page(struct fscache_cookie *cookie, + struct page *page) +{ +} + +/** + * fscache_check_page_write - Ask if a page is being writing to the cache + * @cookie: The cookie representing the cache object + * @page: The netfs page that is being cached. + * + * Ask the cache if a page is being written to the cache. + * + * See Documentation/filesystems/caching/netfs-api.txt for a complete + * description. + */ +static inline +bool fscache_check_page_write(struct fscache_cookie *cookie, + struct page *page) +{ + return false; +} + +/** + * fscache_wait_on_page_write - Wait for a page to complete writing to the cache + * @cookie: The cookie representing the cache object + * @page: The netfs page that is being cached. + * + * Ask the cache to wake us up when a page is no longer being written to the + * cache. + * + * See Documentation/filesystems/caching/netfs-api.txt for a complete + * description. + */ +static inline +void fscache_wait_on_page_write(struct fscache_cookie *cookie, + struct page *page) +{ +} + +#endif /* _LINUX_FSCACHE_H */ -- cgit v1.2.3 From 0dfc41d1efcc4180abfd32f68f0ade540e636ff6 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 3 Apr 2009 16:42:36 +0100 Subject: FS-Cache: Add the FS-Cache cache backend API and documentation Add the API for a generic facility (FS-Cache) by which caches may declare them selves open for business, and may obtain work to be done from network filesystems. The header file is included by: #include Documentation for the API is also added to: Documentation/filesystems/caching/backend-api.txt This API is not usable without the implementation of the utility functions which will be added in further patches. Signed-off-by: David Howells Acked-by: Steve Dickson Acked-by: Trond Myklebust Acked-by: Al Viro Tested-by: Daire Byrne --- include/linux/fscache-cache.h | 509 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 509 insertions(+) create mode 100644 include/linux/fscache-cache.h (limited to 'include/linux') diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h new file mode 100644 index 00000000000..b2a9a484c4c --- /dev/null +++ b/include/linux/fscache-cache.h @@ -0,0 +1,509 @@ +/* General filesystem caching backing cache interface + * + * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * NOTE!!! See: + * + * Documentation/filesystems/caching/backend-api.txt + * + * for a description of the cache backend interface declared here. + */ + +#ifndef _LINUX_FSCACHE_CACHE_H +#define _LINUX_FSCACHE_CACHE_H + +#include +#include +#include + +#define NR_MAXCACHES BITS_PER_LONG + +struct fscache_cache; +struct fscache_cache_ops; +struct fscache_object; +struct fscache_operation; + +#ifdef CONFIG_FSCACHE_PROC +extern struct proc_dir_entry *proc_fscache; +#endif + +/* + * cache tag definition + */ +struct fscache_cache_tag { + struct list_head link; + struct fscache_cache *cache; /* cache referred to by this tag */ + unsigned long flags; +#define FSCACHE_TAG_RESERVED 0 /* T if tag is reserved for a cache */ + atomic_t usage; + char name[0]; /* tag name */ +}; + +/* + * cache definition + */ +struct fscache_cache { + const struct fscache_cache_ops *ops; + struct fscache_cache_tag *tag; /* tag representing this cache */ + struct kobject *kobj; /* system representation of this cache */ + struct list_head link; /* link in list of caches */ + size_t max_index_size; /* maximum size of index data */ + char identifier[36]; /* cache label */ + + /* node management */ + struct work_struct op_gc; /* operation garbage collector */ + struct list_head object_list; /* list of data/index objects */ + struct list_head op_gc_list; /* list of ops to be deleted */ + spinlock_t object_list_lock; + spinlock_t op_gc_list_lock; + atomic_t object_count; /* no. of live objects in this cache */ + struct fscache_object *fsdef; /* object for the fsdef index */ + unsigned long flags; +#define FSCACHE_IOERROR 0 /* cache stopped on I/O error */ +#define FSCACHE_CACHE_WITHDRAWN 1 /* cache has been withdrawn */ +}; + +extern wait_queue_head_t fscache_cache_cleared_wq; + +/* + * operation to be applied to a cache object + * - retrieval initiation operations are done in the context of the process + * that issued them, and not in an async thread pool + */ +typedef void (*fscache_operation_release_t)(struct fscache_operation *op); +typedef void (*fscache_operation_processor_t)(struct fscache_operation *op); + +struct fscache_operation { + union { + struct work_struct fast_work; /* record for fast ops */ + struct slow_work slow_work; /* record for (very) slow ops */ + }; + struct list_head pend_link; /* link in object->pending_ops */ + struct fscache_object *object; /* object to be operated upon */ + + unsigned long flags; +#define FSCACHE_OP_TYPE 0x000f /* operation type */ +#define FSCACHE_OP_FAST 0x0001 /* - fast op, processor may not sleep for disk */ +#define FSCACHE_OP_SLOW 0x0002 /* - (very) slow op, processor may sleep for disk */ +#define FSCACHE_OP_MYTHREAD 0x0003 /* - processing is done be issuing thread, not pool */ +#define FSCACHE_OP_WAITING 4 /* cleared when op is woken */ +#define FSCACHE_OP_EXCLUSIVE 5 /* exclusive op, other ops must wait */ +#define FSCACHE_OP_DEAD 6 /* op is now dead */ + + atomic_t usage; + unsigned debug_id; /* debugging ID */ + + /* operation processor callback + * - can be NULL if FSCACHE_OP_WAITING is going to be used to perform + * the op in a non-pool thread */ + fscache_operation_processor_t processor; + + /* operation releaser */ + fscache_operation_release_t release; +}; + +extern atomic_t fscache_op_debug_id; +extern const struct slow_work_ops fscache_op_slow_work_ops; + +extern void fscache_enqueue_operation(struct fscache_operation *); +extern void fscache_put_operation(struct fscache_operation *); + +/** + * fscache_operation_init - Do basic initialisation of an operation + * @op: The operation to initialise + * @release: The release function to assign + * + * Do basic initialisation of an operation. The caller must still set flags, + * object, either fast_work or slow_work if necessary, and processor if needed. + */ +static inline void fscache_operation_init(struct fscache_operation *op, + fscache_operation_release_t release) +{ + atomic_set(&op->usage, 1); + op->debug_id = atomic_inc_return(&fscache_op_debug_id); + op->release = release; + INIT_LIST_HEAD(&op->pend_link); +} + +/** + * fscache_operation_init_slow - Do additional initialisation of a slow op + * @op: The operation to initialise + * @processor: The processor function to assign + * + * Do additional initialisation of an operation as required for slow work. + */ +static inline +void fscache_operation_init_slow(struct fscache_operation *op, + fscache_operation_processor_t processor) +{ + op->processor = processor; + slow_work_init(&op->slow_work, &fscache_op_slow_work_ops); +} + +/* + * data read operation + */ +struct fscache_retrieval { + struct fscache_operation op; + struct address_space *mapping; /* netfs pages */ + fscache_rw_complete_t end_io_func; /* function to call on I/O completion */ + void *context; /* netfs read context (pinned) */ + struct list_head to_do; /* list of things to be done by the backend */ + unsigned long start_time; /* time at which retrieval started */ +}; + +typedef int (*fscache_page_retrieval_func_t)(struct fscache_retrieval *op, + struct page *page, + gfp_t gfp); + +typedef int (*fscache_pages_retrieval_func_t)(struct fscache_retrieval *op, + struct list_head *pages, + unsigned *nr_pages, + gfp_t gfp); + +/** + * fscache_get_retrieval - Get an extra reference on a retrieval operation + * @op: The retrieval operation to get a reference on + * + * Get an extra reference on a retrieval operation. + */ +static inline +struct fscache_retrieval *fscache_get_retrieval(struct fscache_retrieval *op) +{ + atomic_inc(&op->op.usage); + return op; +} + +/** + * fscache_enqueue_retrieval - Enqueue a retrieval operation for processing + * @op: The retrieval operation affected + * + * Enqueue a retrieval operation for processing by the FS-Cache thread pool. + */ +static inline void fscache_enqueue_retrieval(struct fscache_retrieval *op) +{ + fscache_enqueue_operation(&op->op); +} + +/** + * fscache_put_retrieval - Drop a reference to a retrieval operation + * @op: The retrieval operation affected + * + * Drop a reference to a retrieval operation. + */ +static inline void fscache_put_retrieval(struct fscache_retrieval *op) +{ + fscache_put_operation(&op->op); +} + +/* + * cached page storage work item + * - used to do three things: + * - batch writes to the cache + * - do cache writes asynchronously + * - defer writes until cache object lookup completion + */ +struct fscache_storage { + struct fscache_operation op; + pgoff_t store_limit; /* don't write more than this */ +}; + +/* + * cache operations + */ +struct fscache_cache_ops { + /* name of cache provider */ + const char *name; + + /* allocate an object record for a cookie */ + struct fscache_object *(*alloc_object)(struct fscache_cache *cache, + struct fscache_cookie *cookie); + + /* look up the object for a cookie */ + void (*lookup_object)(struct fscache_object *object); + + /* finished looking up */ + void (*lookup_complete)(struct fscache_object *object); + + /* increment the usage count on this object (may fail if unmounting) */ + struct fscache_object *(*grab_object)(struct fscache_object *object); + + /* pin an object in the cache */ + int (*pin_object)(struct fscache_object *object); + + /* unpin an object in the cache */ + void (*unpin_object)(struct fscache_object *object); + + /* store the updated auxilliary data on an object */ + void (*update_object)(struct fscache_object *object); + + /* discard the resources pinned by an object and effect retirement if + * necessary */ + void (*drop_object)(struct fscache_object *object); + + /* dispose of a reference to an object */ + void (*put_object)(struct fscache_object *object); + + /* sync a cache */ + void (*sync_cache)(struct fscache_cache *cache); + + /* notification that the attributes of a non-index object (such as + * i_size) have changed */ + int (*attr_changed)(struct fscache_object *object); + + /* reserve space for an object's data and associated metadata */ + int (*reserve_space)(struct fscache_object *object, loff_t i_size); + + /* request a backing block for a page be read or allocated in the + * cache */ + fscache_page_retrieval_func_t read_or_alloc_page; + + /* request backing blocks for a list of pages be read or allocated in + * the cache */ + fscache_pages_retrieval_func_t read_or_alloc_pages; + + /* request a backing block for a page be allocated in the cache so that + * it can be written directly */ + fscache_page_retrieval_func_t allocate_page; + + /* request backing blocks for pages be allocated in the cache so that + * they can be written directly */ + fscache_pages_retrieval_func_t allocate_pages; + + /* write a page to its backing block in the cache */ + int (*write_page)(struct fscache_storage *op, struct page *page); + + /* detach backing block from a page (optional) + * - must release the cookie lock before returning + * - may sleep + */ + void (*uncache_page)(struct fscache_object *object, + struct page *page); + + /* dissociate a cache from all the pages it was backing */ + void (*dissociate_pages)(struct fscache_cache *cache); +}; + +/* + * data file or index object cookie + * - a file will only appear in one cache + * - a request to cache a file may or may not be honoured, subject to + * constraints such as disk space + * - indices are created on disk just-in-time + */ +struct fscache_cookie { + atomic_t usage; /* number of users of this cookie */ + atomic_t n_children; /* number of children of this cookie */ + spinlock_t lock; + struct hlist_head backing_objects; /* object(s) backing this file/index */ + const struct fscache_cookie_def *def; /* definition */ + struct fscache_cookie *parent; /* parent of this entry */ + void *netfs_data; /* back pointer to netfs */ + struct radix_tree_root stores; /* pages to be stored on this cookie */ +#define FSCACHE_COOKIE_PENDING_TAG 0 /* pages tag: pending write to cache */ + + unsigned long flags; +#define FSCACHE_COOKIE_LOOKING_UP 0 /* T if non-index cookie being looked up still */ +#define FSCACHE_COOKIE_CREATING 1 /* T if non-index object being created still */ +#define FSCACHE_COOKIE_NO_DATA_YET 2 /* T if new object with no cached data yet */ +#define FSCACHE_COOKIE_PENDING_FILL 3 /* T if pending initial fill on object */ +#define FSCACHE_COOKIE_FILLING 4 /* T if filling object incrementally */ +#define FSCACHE_COOKIE_UNAVAILABLE 5 /* T if cookie is unavailable (error, etc) */ +}; + +extern struct fscache_cookie fscache_fsdef_index; + +/* + * on-disk cache file or index handle + */ +struct fscache_object { + enum fscache_object_state { + FSCACHE_OBJECT_INIT, /* object in initial unbound state */ + FSCACHE_OBJECT_LOOKING_UP, /* looking up object */ + FSCACHE_OBJECT_CREATING, /* creating object */ + + /* active states */ + FSCACHE_OBJECT_AVAILABLE, /* cleaning up object after creation */ + FSCACHE_OBJECT_ACTIVE, /* object is usable */ + FSCACHE_OBJECT_UPDATING, /* object is updating */ + + /* terminal states */ + FSCACHE_OBJECT_DYING, /* object waiting for accessors to finish */ + FSCACHE_OBJECT_LC_DYING, /* object cleaning up after lookup/create */ + FSCACHE_OBJECT_ABORT_INIT, /* abort the init state */ + FSCACHE_OBJECT_RELEASING, /* releasing object */ + FSCACHE_OBJECT_RECYCLING, /* retiring object */ + FSCACHE_OBJECT_WITHDRAWING, /* withdrawing object */ + FSCACHE_OBJECT_DEAD, /* object is now dead */ + } state; + + int debug_id; /* debugging ID */ + int n_children; /* number of child objects */ + int n_ops; /* number of ops outstanding on object */ + int n_obj_ops; /* number of object ops outstanding on object */ + int n_in_progress; /* number of ops in progress */ + int n_exclusive; /* number of exclusive ops queued */ + spinlock_t lock; /* state and operations lock */ + + unsigned long lookup_jif; /* time at which lookup started */ + unsigned long event_mask; /* events this object is interested in */ + unsigned long events; /* events to be processed by this object + * (order is important - using fls) */ +#define FSCACHE_OBJECT_EV_REQUEUE 0 /* T if object should be requeued */ +#define FSCACHE_OBJECT_EV_UPDATE 1 /* T if object should be updated */ +#define FSCACHE_OBJECT_EV_CLEARED 2 /* T if accessors all gone */ +#define FSCACHE_OBJECT_EV_ERROR 3 /* T if fatal error occurred during processing */ +#define FSCACHE_OBJECT_EV_RELEASE 4 /* T if netfs requested object release */ +#define FSCACHE_OBJECT_EV_RETIRE 5 /* T if netfs requested object retirement */ +#define FSCACHE_OBJECT_EV_WITHDRAW 6 /* T if cache requested object withdrawal */ + + unsigned long flags; +#define FSCACHE_OBJECT_LOCK 0 /* T if object is busy being processed */ +#define FSCACHE_OBJECT_PENDING_WRITE 1 /* T if object has pending write */ +#define FSCACHE_OBJECT_WAITING 2 /* T if object is waiting on its parent */ + + struct list_head cache_link; /* link in cache->object_list */ + struct hlist_node cookie_link; /* link in cookie->backing_objects */ + struct fscache_cache *cache; /* cache that supplied this object */ + struct fscache_cookie *cookie; /* netfs's file/index object */ + struct fscache_object *parent; /* parent object */ + struct slow_work work; /* attention scheduling record */ + struct list_head dependents; /* FIFO of dependent objects */ + struct list_head dep_link; /* link in parent's dependents list */ + struct list_head pending_ops; /* unstarted operations on this object */ + pgoff_t store_limit; /* current storage limit */ +}; + +extern const char *fscache_object_states[]; + +#define fscache_object_is_active(obj) \ + (!test_bit(FSCACHE_IOERROR, &(obj)->cache->flags) && \ + (obj)->state >= FSCACHE_OBJECT_AVAILABLE && \ + (obj)->state < FSCACHE_OBJECT_DYING) + +extern const struct slow_work_ops fscache_object_slow_work_ops; + +/** + * fscache_object_init - Initialise a cache object description + * @object: Object description + * + * Initialise a cache object description to its basic values. + * + * See Documentation/filesystems/caching/backend-api.txt for a complete + * description. + */ +static inline +void fscache_object_init(struct fscache_object *object, + struct fscache_cookie *cookie, + struct fscache_cache *cache) +{ + atomic_inc(&cache->object_count); + + object->state = FSCACHE_OBJECT_INIT; + spin_lock_init(&object->lock); + INIT_LIST_HEAD(&object->cache_link); + INIT_HLIST_NODE(&object->cookie_link); + vslow_work_init(&object->work, &fscache_object_slow_work_ops); + INIT_LIST_HEAD(&object->dependents); + INIT_LIST_HEAD(&object->dep_link); + INIT_LIST_HEAD(&object->pending_ops); + object->n_children = 0; + object->n_ops = object->n_in_progress = object->n_exclusive = 0; + object->events = object->event_mask = 0; + object->flags = 0; + object->store_limit = 0; + object->cache = cache; + object->cookie = cookie; + object->parent = NULL; +} + +extern void fscache_object_lookup_negative(struct fscache_object *object); +extern void fscache_obtained_object(struct fscache_object *object); + +/** + * fscache_object_destroyed - Note destruction of an object in a cache + * @cache: The cache from which the object came + * + * Note the destruction and deallocation of an object record in a cache. + */ +static inline void fscache_object_destroyed(struct fscache_cache *cache) +{ + if (atomic_dec_and_test(&cache->object_count)) + wake_up_all(&fscache_cache_cleared_wq); +} + +/** + * fscache_object_lookup_error - Note an object encountered an error + * @object: The object on which the error was encountered + * + * Note that an object encountered a fatal error (usually an I/O error) and + * that it should be withdrawn as soon as possible. + */ +static inline void fscache_object_lookup_error(struct fscache_object *object) +{ + set_bit(FSCACHE_OBJECT_EV_ERROR, &object->events); +} + +/** + * fscache_set_store_limit - Set the maximum size to be stored in an object + * @object: The object to set the maximum on + * @i_size: The limit to set in bytes + * + * Set the maximum size an object is permitted to reach, implying the highest + * byte that may be written. Intended to be called by the attr_changed() op. + * + * See Documentation/filesystems/caching/backend-api.txt for a complete + * description. + */ +static inline +void fscache_set_store_limit(struct fscache_object *object, loff_t i_size) +{ + object->store_limit = i_size >> PAGE_SHIFT; + if (i_size & ~PAGE_MASK) + object->store_limit++; +} + +/** + * fscache_end_io - End a retrieval operation on a page + * @op: The FS-Cache operation covering the retrieval + * @page: The page that was to be fetched + * @error: The error code (0 if successful) + * + * Note the end of an operation to retrieve a page, as covered by a particular + * operation record. + */ +static inline void fscache_end_io(struct fscache_retrieval *op, + struct page *page, int error) +{ + op->end_io_func(page, op->context, error); +} + +/* + * out-of-line cache backend functions + */ +extern void fscache_init_cache(struct fscache_cache *cache, + const struct fscache_cache_ops *ops, + const char *idfmt, + ...) __attribute__ ((format (printf, 3, 4))); + +extern int fscache_add_cache(struct fscache_cache *cache, + struct fscache_object *fsdef, + const char *tagname); +extern void fscache_withdraw_cache(struct fscache_cache *cache); + +extern void fscache_io_error(struct fscache_cache *cache); + +extern void fscache_mark_pages_cached(struct fscache_retrieval *op, + struct pagevec *pagevec); + +extern enum fscache_checkaux fscache_check_aux(struct fscache_object *object, + const void *data, + uint16_t datalen); + +#endif /* _LINUX_FSCACHE_CACHE_H */ -- cgit v1.2.3 From 7394daa8c61dfda4baa687f133748fa0b599b017 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 3 Apr 2009 16:42:37 +0100 Subject: FS-Cache: Add use of /proc and presentation of statistics Make FS-Cache create its /proc interface and present various statistical information through it. Also provide the functions for updating this information. These features are enabled by: CONFIG_FSCACHE_PROC CONFIG_FSCACHE_STATS CONFIG_FSCACHE_HISTOGRAM The /proc directory for FS-Cache is also exported so that caching modules can add their own statistics there too. The FS-Cache module is loadable at this point, and the statistics files can be examined by userspace: cat /proc/fs/fscache/stats cat /proc/fs/fscache/histogram Signed-off-by: David Howells Acked-by: Steve Dickson Acked-by: Trond Myklebust Acked-by: Al Viro Tested-by: Daire Byrne --- include/linux/fscache-cache.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index b2a9a484c4c..84d3532dd3e 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -29,10 +29,6 @@ struct fscache_cache_ops; struct fscache_object; struct fscache_operation; -#ifdef CONFIG_FSCACHE_PROC -extern struct proc_dir_entry *proc_fscache; -#endif - /* * cache tag definition */ -- cgit v1.2.3 From 0e04d4cefcf4d8fbbdb2c50e93ad541582933fd2 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 3 Apr 2009 16:42:37 +0100 Subject: FS-Cache: Add cache tag handling Implement two features of FS-Cache: (1) The ability to request and release cache tags - names by which a cache may be known to a netfs, and thus selected for use. (2) An internal function by which a cache is selected by consulting the netfs, if the netfs wishes to be consulted. Signed-off-by: David Howells Acked-by: Steve Dickson Acked-by: Trond Myklebust Acked-by: Al Viro Tested-by: Daire Byrne --- include/linux/fscache.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fscache.h b/include/linux/fscache.h index feb3b0e0af4..9584c094d69 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -173,6 +173,8 @@ struct fscache_netfs { * - these are undefined symbols when FS-Cache is not configured and the * optimiser takes care of not using them */ +extern struct fscache_cache_tag *__fscache_lookup_cache_tag(const char *); +extern void __fscache_release_cache_tag(struct fscache_cache_tag *); /** * fscache_register_netfs - Register a filesystem as desiring caching services @@ -218,7 +220,10 @@ void fscache_unregister_netfs(struct fscache_netfs *netfs) static inline struct fscache_cache_tag *fscache_lookup_cache_tag(const char *name) { - return NULL; + if (fscache_available()) + return __fscache_lookup_cache_tag(name); + else + return NULL; } /** @@ -233,6 +238,8 @@ struct fscache_cache_tag *fscache_lookup_cache_tag(const char *name) static inline void fscache_release_cache_tag(struct fscache_cache_tag *tag) { + if (fscache_available()) + __fscache_release_cache_tag(tag); } /** -- cgit v1.2.3 From 726dd7ff10c217dd74329c94643dc8ebea27334b Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 3 Apr 2009 16:42:38 +0100 Subject: FS-Cache: Add netfs registration Add functions to register and unregister a network filesystem or other client of the FS-Cache service. This allocates and releases the cookie representing the top-level index for a netfs, and makes it available to the netfs. If the FS-Cache facility is disabled, then the calls are optimised away at compile time. Note that whilst this patch may appear to work with FS-Cache enabled and a netfs attempting to use it, it will leak the cookie it allocates for the netfs as fscache_relinquish_cookie() is implemented in a later patch. This will cause the slab code to emit a warning when the module is removed. Signed-off-by: David Howells Acked-by: Steve Dickson Acked-by: Trond Myklebust Acked-by: Al Viro Tested-by: Daire Byrne --- include/linux/fscache.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 9584c094d69..b195c2e1ef6 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -173,6 +173,8 @@ struct fscache_netfs { * - these are undefined symbols when FS-Cache is not configured and the * optimiser takes care of not using them */ +extern int __fscache_register_netfs(struct fscache_netfs *); +extern void __fscache_unregister_netfs(struct fscache_netfs *); extern struct fscache_cache_tag *__fscache_lookup_cache_tag(const char *); extern void __fscache_release_cache_tag(struct fscache_cache_tag *); @@ -188,7 +190,10 @@ extern void __fscache_release_cache_tag(struct fscache_cache_tag *); static inline int fscache_register_netfs(struct fscache_netfs *netfs) { - return 0; + if (fscache_available()) + return __fscache_register_netfs(netfs); + else + return 0; } /** @@ -205,6 +210,8 @@ int fscache_register_netfs(struct fscache_netfs *netfs) static inline void fscache_unregister_netfs(struct fscache_netfs *netfs) { + if (fscache_available()) + __fscache_unregister_netfs(netfs); } /** -- cgit v1.2.3 From ccc4fc3d11e91477036d1f82bfa2d442f6ce77f0 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 3 Apr 2009 16:42:38 +0100 Subject: FS-Cache: Implement the cookie management part of the netfs API Implement the cookie management part of the FS-Cache netfs client API. The documentation and API header file were added in a previous patch. This patch implements the following three functions: (1) fscache_acquire_cookie(). Acquire a cookie to represent an object to the netfs. If the object in question is a non-index object, then that object and its parent indices will be created on disk at this point if they don't already exist. Index creation is deferred because an index may reside in multiple caches. (2) fscache_relinquish_cookie(). Retire or release a cookie previously acquired. At this point, the object on disk may be destroyed. (3) fscache_update_cookie(). Update the in-cache representation of a cookie. This is used to update the auxiliary data for coherency management purposes. With this patch it is possible to have a netfs instruct a cache backend to look up, validate and create metadata on disk and to destroy it again. The ability to actually store and retrieve data in the objects so created is added in later patches. Note that these functions will never return an error. _All_ errors are handled internally to FS-Cache. The worst that can happen is that fscache_acquire_cookie() may return a NULL pointer - which is considered a negative cookie pointer and can be passed back to any function that takes a cookie without harm. A negative cookie pointer merely suppresses caching at that level. The stub in linux/fscache.h will detect inline the negative cookie pointer and abort the operation as fast as possible. This means that the compiler doesn't have to set up for a call in that case. See the documentation in Documentation/filesystems/caching/netfs-api.txt for more information. Signed-off-by: David Howells Acked-by: Steve Dickson Acked-by: Trond Myklebust Acked-by: Al Viro Tested-by: Daire Byrne --- include/linux/fscache.h | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fscache.h b/include/linux/fscache.h index b195c2e1ef6..245b48646ef 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -178,6 +178,13 @@ extern void __fscache_unregister_netfs(struct fscache_netfs *); extern struct fscache_cache_tag *__fscache_lookup_cache_tag(const char *); extern void __fscache_release_cache_tag(struct fscache_cache_tag *); +extern struct fscache_cookie *__fscache_acquire_cookie( + struct fscache_cookie *, + const struct fscache_cookie_def *, + void *); +extern void __fscache_relinquish_cookie(struct fscache_cookie *, int); +extern void __fscache_update_cookie(struct fscache_cookie *); + /** * fscache_register_netfs - Register a filesystem as desiring caching services * @netfs: The description of the filesystem @@ -269,7 +276,10 @@ struct fscache_cookie *fscache_acquire_cookie( const struct fscache_cookie_def *def, void *netfs_data) { - return NULL; + if (fscache_cookie_valid(parent)) + return __fscache_acquire_cookie(parent, def, netfs_data); + else + return NULL; } /** @@ -287,6 +297,8 @@ struct fscache_cookie *fscache_acquire_cookie( static inline void fscache_relinquish_cookie(struct fscache_cookie *cookie, int retire) { + if (fscache_cookie_valid(cookie)) + __fscache_relinquish_cookie(cookie, retire); } /** @@ -302,6 +314,8 @@ void fscache_relinquish_cookie(struct fscache_cookie *cookie, int retire) static inline void fscache_update_cookie(struct fscache_cookie *cookie) { + if (fscache_cookie_valid(cookie)) + __fscache_update_cookie(cookie); } /** -- cgit v1.2.3 From b510882281d56873e1194021643b7c325336f84f Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 3 Apr 2009 16:42:39 +0100 Subject: FS-Cache: Implement data I/O part of netfs API Implement the data I/O part of the FS-Cache netfs API. The documentation and API header file were added in a previous patch. This patch implements the following functions for the netfs to call: (*) fscache_attr_changed(). Indicate that the object has changed its attributes. The only attribute currently recorded is the file size. Only pages within the set file size will be stored in the cache. This operation is submitted for asynchronous processing, and will return immediately. It will return -ENOMEM if an out of memory error is encountered, -ENOBUFS if the object is not actually cached, or 0 if the operation is successfully queued. (*) fscache_read_or_alloc_page(). (*) fscache_read_or_alloc_pages(). Request data be fetched from the disk, and allocate internal metadata to track the netfs pages and reserve disk space for unknown pages. These operations perform semi-asynchronous data reads. Upon returning they will indicate which pages they think can be retrieved from disk, and will have set in progress attempts to retrieve those pages. These will return, in order of preference, -ENOMEM on memory allocation error, -ERESTARTSYS if a signal interrupted proceedings, -ENODATA if one or more requested pages are not yet cached, -ENOBUFS if the object is not actually cached or if there isn't space for future pages to be cached on this object, or 0 if successful. In the case of the multipage function, the pages for which reads are set in progress will be removed from the list and the page count decreased appropriately. If any read operations should fail, the completion function will be given an error, and will also be passed contextual information to allow the netfs to fall back to querying the server for the absent pages. For each successful read, the page completion function will also be called. Any pages subsequently tracked by the cache will have PG_fscache set upon them on return. fscache_uncache_page() must be called for such pages. If supplied by the netfs, the mark_pages_cached() cookie op will be invoked for any pages now tracked. (*) fscache_alloc_page(). Allocate internal metadata to track a netfs page and reserve disk space. This will return -ENOMEM on memory allocation error, -ERESTARTSYS on signal, -ENOBUFS if the object isn't cached, or there isn't enough space in the cache, or 0 if successful. Any pages subsequently tracked by the cache will have PG_fscache set upon them on return. fscache_uncache_page() must be called for such pages. If supplied by the netfs, the mark_pages_cached() cookie op will be invoked for any pages now tracked. (*) fscache_write_page(). Request data be stored to disk. This may only be called on pages that have been read or alloc'd by the above three functions and have not yet been uncached. This will return -ENOMEM on memory allocation error, -ERESTARTSYS on signal, -ENOBUFS if the object isn't cached, or there isn't immediately enough space in the cache, or 0 if successful. On a successful return, this operation will have queued the page for asynchronous writing to the cache. The page will be returned with PG_fscache_write set until the write completes one way or another. The caller will not be notified if the write fails due to an I/O error. If that happens, the object will become available and all pending writes will be aborted. Note that the cache may batch up page writes, and so it may take a while to get around to writing them out. The caller must assume that until PG_fscache_write is cleared the page is use by the cache. Any changes made to the page may be reflected on disk. The page may even be under DMA. (*) fscache_uncache_page(). Indicate that the cache should stop tracking a page previously read or alloc'd from the cache. If the page was alloc'd only, but unwritten, it will not appear on disk. Signed-off-by: David Howells Acked-by: Steve Dickson Acked-by: Trond Myklebust Acked-by: Al Viro Tested-by: Daire Byrne --- include/linux/fscache.h | 52 ++++++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 47 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 245b48646ef..6d8ee466e0a 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -184,6 +184,24 @@ extern struct fscache_cookie *__fscache_acquire_cookie( void *); extern void __fscache_relinquish_cookie(struct fscache_cookie *, int); extern void __fscache_update_cookie(struct fscache_cookie *); +extern int __fscache_attr_changed(struct fscache_cookie *); +extern int __fscache_read_or_alloc_page(struct fscache_cookie *, + struct page *, + fscache_rw_complete_t, + void *, + gfp_t); +extern int __fscache_read_or_alloc_pages(struct fscache_cookie *, + struct address_space *, + struct list_head *, + unsigned *, + fscache_rw_complete_t, + void *, + gfp_t); +extern int __fscache_alloc_page(struct fscache_cookie *, struct page *, gfp_t); +extern int __fscache_write_page(struct fscache_cookie *, struct page *, gfp_t); +extern void __fscache_uncache_page(struct fscache_cookie *, struct page *); +extern bool __fscache_check_page_write(struct fscache_cookie *, struct page *); +extern void __fscache_wait_on_page_write(struct fscache_cookie *, struct page *); /** * fscache_register_netfs - Register a filesystem as desiring caching services @@ -361,7 +379,10 @@ void fscache_unpin_cookie(struct fscache_cookie *cookie) static inline int fscache_attr_changed(struct fscache_cookie *cookie) { - return -ENOBUFS; + if (fscache_cookie_valid(cookie)) + return __fscache_attr_changed(cookie); + else + return -ENOBUFS; } /** @@ -418,7 +439,11 @@ int fscache_read_or_alloc_page(struct fscache_cookie *cookie, void *context, gfp_t gfp) { - return -ENOBUFS; + if (fscache_cookie_valid(cookie)) + return __fscache_read_or_alloc_page(cookie, page, end_io_func, + context, gfp); + else + return -ENOBUFS; } /** @@ -464,7 +489,12 @@ int fscache_read_or_alloc_pages(struct fscache_cookie *cookie, void *context, gfp_t gfp) { - return -ENOBUFS; + if (fscache_cookie_valid(cookie)) + return __fscache_read_or_alloc_pages(cookie, mapping, pages, + nr_pages, end_io_func, + context, gfp); + else + return -ENOBUFS; } /** @@ -490,7 +520,10 @@ int fscache_alloc_page(struct fscache_cookie *cookie, struct page *page, gfp_t gfp) { - return -ENOBUFS; + if (fscache_cookie_valid(cookie)) + return __fscache_alloc_page(cookie, page, gfp); + else + return -ENOBUFS; } /** @@ -516,7 +549,10 @@ int fscache_write_page(struct fscache_cookie *cookie, struct page *page, gfp_t gfp) { - return -ENOBUFS; + if (fscache_cookie_valid(cookie)) + return __fscache_write_page(cookie, page, gfp); + else + return -ENOBUFS; } /** @@ -537,6 +573,8 @@ static inline void fscache_uncache_page(struct fscache_cookie *cookie, struct page *page) { + if (fscache_cookie_valid(cookie)) + __fscache_uncache_page(cookie, page); } /** @@ -553,6 +591,8 @@ static inline bool fscache_check_page_write(struct fscache_cookie *cookie, struct page *page) { + if (fscache_cookie_valid(cookie)) + return __fscache_check_page_write(cookie, page); return false; } @@ -571,6 +611,8 @@ static inline void fscache_wait_on_page_write(struct fscache_cookie *cookie, struct page *page) { + if (fscache_cookie_valid(cookie)) + __fscache_wait_on_page_write(cookie, page); } #endif /* _LINUX_FSCACHE_H */ -- cgit v1.2.3 From 385e1ca5f21c4680ad6a46a3aa2ea8af99e99c92 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 3 Apr 2009 16:42:39 +0100 Subject: CacheFiles: Permit the page lock state to be monitored Add a function to install a monitor on the page lock waitqueue for a particular page, thus allowing the page being unlocked to be detected. This is used by CacheFiles to detect read completion on a page in the backing filesystem so that it can then copy the data to the waiting netfs page. Signed-off-by: David Howells Acked-by: Steve Dickson Acked-by: Trond Myklebust Acked-by: Rik van Riel Acked-by: Al Viro Tested-by: Daire Byrne --- include/linux/pagemap.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 076a7dc67c2..34da5230faa 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -383,6 +383,11 @@ static inline void wait_on_page_writeback(struct page *page) extern void end_page_writeback(struct page *page); +/* + * Add an arbitrary waiter to a page's wait queue + */ +extern void add_page_wait_queue(struct page *page, wait_queue_t *waiter); + /* * Fault a userspace page into pagetables. Return non-zero on a fault. * -- cgit v1.2.3 From c6a6f19e22da0a3d74214ee010224c9a30a794c1 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 3 Apr 2009 16:42:42 +0100 Subject: NFS: Add FS-Cache option bit and debug bit Add FS-Cache option bit to nfs_server struct. This is set to indicate local on-disk caching is enabled for a particular superblock. Also add debug bit for local caching operations. Signed-off-by: David Howells Acked-by: Steve Dickson Acked-by: Trond Myklebust Acked-by: Al Viro Tested-by: Daire Byrne --- include/linux/nfs_fs.h | 1 + include/linux/nfs_fs_sb.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index bde2557c2a9..fd3e7f9c6fd 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -583,6 +583,7 @@ extern void * nfs_root_data(void); #define NFSDBG_CALLBACK 0x0100 #define NFSDBG_CLIENT 0x0200 #define NFSDBG_MOUNT 0x0400 +#define NFSDBG_FSCACHE 0x0800 #define NFSDBG_ALL 0xFFFF #ifdef __KERNEL__ diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 29b1e40dce9..a749f8564aa 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -96,6 +96,8 @@ struct nfs_server { unsigned int acdirmin; unsigned int acdirmax; unsigned int namelen; + unsigned int options; /* extra options enabled by mount */ +#define NFS_OPTION_FSCACHE 0x00000001 /* - local caching enabled */ struct nfs_fsid fsid; __u64 maxfilesize; /* maximum file size */ -- cgit v1.2.3 From 147272813e043fb44bd112527951da70c1e663de Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 3 Apr 2009 16:42:42 +0100 Subject: NFS: Define and create server-level objects Define and create server-level cache index objects (as managed by nfs_client structs). Each server object is created in the NFS top-level index object and is itself an index into which superblock-level objects are inserted. Ideally there would be one superblock-level object per server, and the former would be folded into the latter; however, since the "nosharecache" option exists this isn't possible. The server object key is a sequence consisting of: (1) NFS version (2) Server address family (eg: AF_INET or AF_INET6) (3) Server port. (4) Server IP address. The key blob is of variable length, depending on the length of (4). The server object is given no coherency data to carry in the auxiliary data permitted by the cache. Signed-off-by: David Howells Acked-by: Steve Dickson Acked-by: Trond Myklebust Acked-by: Al Viro Tested-by: Daire Byrne --- include/linux/nfs_fs_sb.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index a749f8564aa..0a374b9c509 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -64,6 +64,10 @@ struct nfs_client { char cl_ipaddr[48]; unsigned char cl_id_uniquifier; #endif + +#ifdef CONFIG_NFS_FSCACHE + struct fscache_cookie *fscache; /* client index cache cookie */ +#endif }; /* -- cgit v1.2.3 From 08734048b380103f0412f58b84c2f76a2c8b599f Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 3 Apr 2009 16:42:42 +0100 Subject: NFS: Define and create superblock-level objects Define and create superblock-level cache index objects (as managed by nfs_server structs). Each superblock object is created in a server level index object and is itself an index into which inode-level objects are inserted. Ideally there would be one superblock-level object per server, and the former would be folded into the latter; however, since the "nosharecache" option exists this isn't possible. The superblock object key is a sequence consisting of: (1) Certain superblock s_flags. (2) Various connection parameters that serve to distinguish superblocks for sget(). (3) The volume FSID. (4) The security flavour. (5) The uniquifier length. (6) The uniquifier text. This is normally an empty string, unless the fsc=xyz mount option was used to explicitly specify a uniquifier. The key blob is of variable length, depending on the length of (6). The superblock object is given no coherency data to carry in the auxiliary data permitted by the cache. It is assumed that the superblock is always coherent. This patch also adds uniquification handling such that two otherwise identical superblocks, at least one of which is marked "nosharecache", won't end up trying to share the on-disk cache. It will be possible to manually provide a uniquifier through a mount option with a later patch to avoid the error otherwise produced. Signed-off-by: David Howells Acked-by: Steve Dickson Acked-by: Trond Myklebust Acked-by: Al Viro Tested-by: Daire Byrne --- include/linux/nfs_fs_sb.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 0a374b9c509..6ad75948cbf 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -108,6 +108,11 @@ struct nfs_server { unsigned long mount_time; /* when this fs was mounted */ dev_t s_dev; /* superblock dev numbers */ +#ifdef CONFIG_NFS_FSCACHE + struct nfs_fscache_key *fscache_key; /* unique key for superblock */ + struct fscache_cookie *fscache; /* superblock cookie */ +#endif + #ifdef CONFIG_NFS_V4 u32 attr_bitmask[2];/* V4 bitmask representing the set of attributes supported on this -- cgit v1.2.3 From ef79c097bbe9724e13937271b3457df560e00370 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 3 Apr 2009 16:42:43 +0100 Subject: NFS: Use local disk inode cache Bind data storage objects in the local cache to NFS inodes. Signed-off-by: David Howells Acked-by: Steve Dickson Acked-by: Trond Myklebust Acked-by: Al Viro Tested-by: Daire Byrne --- include/linux/nfs_fs.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index fd3e7f9c6fd..8a99e79d5ea 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -185,6 +185,9 @@ struct nfs_inode { fmode_t delegation_state; struct rw_semaphore rwsem; #endif /* CONFIG_NFS_V4*/ +#ifdef CONFIG_NFS_FSCACHE + struct fscache_cookie *fscache; +#endif struct inode vfs_inode; }; @@ -207,6 +210,8 @@ struct nfs_inode { #define NFS_INO_ACL_LRU_SET (2) /* Inode is on the LRU list */ #define NFS_INO_MOUNTPOINT (3) /* inode is remote mountpoint */ #define NFS_INO_FLUSHING (4) /* inode is flushing out data */ +#define NFS_INO_FSCACHE (5) /* inode can be cached by FS-Cache */ +#define NFS_INO_FSCACHE_LOCK (6) /* FS-Cache cookie management lock */ static inline struct nfs_inode *NFS_I(const struct inode *inode) { @@ -260,6 +265,11 @@ static inline int NFS_STALE(const struct inode *inode) return test_bit(NFS_INO_STALE, &NFS_I(inode)->flags); } +static inline int NFS_FSCACHE(const struct inode *inode) +{ + return test_bit(NFS_INO_FSCACHE, &NFS_I(inode)->flags); +} + static inline __u64 NFS_FILEID(const struct inode *inode) { return NFS_I(inode)->fileid; -- cgit v1.2.3 From 6a51091d0775cdc4a923f2172c61925ad416aa32 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 3 Apr 2009 16:42:43 +0100 Subject: NFS: Add some new I/O counters for FS-Cache doing things for NFS Add some new NFS I/O counters for FS-Cache doing things for NFS. A new line is emitted into /proc/pid/mountstats if caching is enabled that looks like: fsc: Where is the number of pages read successfully from the cache, is the number of failed page reads against the cache, is the number of successful page writes to the cache, is the number of failed page writes to the cache, and is the number of NFS pages that have been disconnected from the cache. Signed-off-by: David Howells Acked-by: Steve Dickson Acked-by: Trond Myklebust Acked-by: Al Viro Tested-by: Daire Byrne --- include/linux/nfs_iostat.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_iostat.h b/include/linux/nfs_iostat.h index 1cb9a3fed2b..68b10f5f890 100644 --- a/include/linux/nfs_iostat.h +++ b/include/linux/nfs_iostat.h @@ -116,4 +116,16 @@ enum nfs_stat_eventcounters { __NFSIOS_COUNTSMAX, }; +/* + * NFS local caching servicing counters + */ +enum nfs_stat_fscachecounters { + NFSIOS_FSCACHE_PAGES_READ_OK, + NFSIOS_FSCACHE_PAGES_READ_FAIL, + NFSIOS_FSCACHE_PAGES_WRITTEN_OK, + NFSIOS_FSCACHE_PAGES_WRITTEN_FAIL, + NFSIOS_FSCACHE_PAGES_UNCACHED, + __NFSIOS_FSCACHEMAX, +}; + #endif /* _LINUX_NFS_IOSTAT */ -- cgit v1.2.3 From f42b293d6d5259043a8944b556eeab427c695d57 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 3 Apr 2009 16:42:44 +0100 Subject: NFS: nfs_readpage_async() needs to be accessible as a fallback for local caching nfs_readpage_async() needs to be non-static so that it can be used as a fallback for the local on-disk caching should an EIO crop up when reading the cache. Signed-off-by: David Howells Acked-by: Steve Dickson Acked-by: Trond Myklebust Acked-by: Al Viro Tested-by: Daire Byrne --- include/linux/nfs_fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 8a99e79d5ea..fdffb413b19 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -516,6 +516,8 @@ extern int nfs_readpages(struct file *, struct address_space *, struct list_head *, unsigned); extern int nfs_readpage_result(struct rpc_task *, struct nfs_read_data *); extern void nfs_readdata_release(void *data); +extern int nfs_readpage_async(struct nfs_open_context *, struct inode *, + struct page *); /* * Allocate nfs_read_data structures -- cgit v1.2.3 From 3688e07f83d81941c4a8b20e29602c6d0c883539 Mon Sep 17 00:00:00 2001 From: Kumar Gala Date: Wed, 1 Apr 2009 23:38:49 -0500 Subject: Fix highmem PPC build failure Commit f4112de6b679d84bd9b9681c7504be7bdfb7c7d5 ("mm: introduce debug_kmap_atomic") broke PPC builds with CONFIG_HIGHMEM=y: CC init/main.o In file included from include/linux/highmem.h:25, from include/linux/pagemap.h:11, from include/linux/mempolicy.h:63, from init/main.c:53: arch/powerpc/include/asm/highmem.h: In function 'kmap_atomic_prot': arch/powerpc/include/asm/highmem.h:98: error: implicit declaration of function 'debug_kmap_atomic' In file included from include/linux/pagemap.h:11, from include/linux/mempolicy.h:63, from init/main.c:53: include/linux/highmem.h: At top level: include/linux/highmem.h:196: warning: conflicting types for 'debug_kmap_atomic' include/linux/highmem.h:196: error: static declaration of 'debug_kmap_atomic' follows non-static declaration include/asm/highmem.h:98: error: previous implicit declaration of 'debug_kmap_atomic' was here make[1]: *** [init/main.o] Error 1 make: *** [init] Error 2 Signed-off-by: Kumar Gala Acked-by: Akinobu Mita Signed-off-by: Linus Torvalds --- include/linux/highmem.h | 29 ++++++++++++++--------------- 1 file changed, 14 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 7ff5c55f9b5..1fcb7126a01 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -19,8 +19,21 @@ static inline void flush_kernel_dcache_page(struct page *page) } #endif -#ifdef CONFIG_HIGHMEM +#include + +#if defined(CONFIG_DEBUG_HIGHMEM) && defined(CONFIG_TRACE_IRQFLAGS_SUPPORT) + +void debug_kmap_atomic(enum km_type type); + +#else +static inline void debug_kmap_atomic(enum km_type type) +{ +} + +#endif + +#ifdef CONFIG_HIGHMEM #include /* declarations for linux/mm/highmem.c */ @@ -44,8 +57,6 @@ static inline void *kmap(struct page *page) #define kunmap(page) do { (void) (page); } while (0) -#include - static inline void *kmap_atomic(struct page *page, enum km_type idx) { pagefault_disable(); @@ -187,16 +198,4 @@ static inline void copy_highpage(struct page *to, struct page *from) kunmap_atomic(vto, KM_USER1); } -#if defined(CONFIG_DEBUG_HIGHMEM) && defined(CONFIG_TRACE_IRQFLAGS_SUPPORT) - -void debug_kmap_atomic(enum km_type type); - -#else - -static inline void debug_kmap_atomic(enum km_type type) -{ -} - -#endif - #endif /* _LINUX_HIGHMEM_H */ -- cgit v1.2.3 From 8f912ba4d7cdaf7d31cf39fe5a9b7732308a256d Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Fri, 3 Apr 2009 15:19:32 +0100 Subject: intel-iommu: Add for_each_iommu() and for_each_active_iommu() macros Signed-off-by: David Woodhouse Acked-by: Ingo Molnar --- include/linux/dmar.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmar.h b/include/linux/dmar.h index 2f342746895..0b4aa806998 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -44,6 +44,14 @@ extern struct list_head dmar_drhd_units; #define for_each_drhd_unit(drhd) \ list_for_each_entry(drhd, &dmar_drhd_units, list) +#define for_each_active_iommu(i, drhd) \ + list_for_each_entry(drhd, &dmar_drhd_units, list) \ + if (i=drhd->iommu, drhd->ignored) {} else + +#define for_each_iommu(i, drhd) \ + list_for_each_entry(drhd, &dmar_drhd_units, list) \ + if (i=drhd->iommu, 0) {} else + extern int dmar_table_init(void); extern int dmar_dev_scope_init(void); -- cgit v1.2.3 From f59c7b69bcba31cd355ababe067202b9895d6102 Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Fri, 27 Mar 2009 14:22:42 -0700 Subject: Intel IOMMU Suspend/Resume Support - DMAR This patch implements the suspend and resume feature for Intel IOMMU DMAR. It hooks to kernel suspend and resume interface. When suspend happens, it saves necessary hardware registers. When resume happens, it restores the registers and restarts IOMMU by enabling translation, setting up root entry, and re-enabling queued invalidation. Signed-off-by: Fenghua Yu Acked-by: Ingo Molnar Signed-off-by: David Woodhouse --- include/linux/intel-iommu.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 77214ead1a3..3771cd1f876 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -284,6 +284,14 @@ struct iommu_flush { unsigned int size_order, u64 type, int non_present_entry_flush); }; +enum { + SR_DMAR_FECTL_REG, + SR_DMAR_FEDATA_REG, + SR_DMAR_FEADDR_REG, + SR_DMAR_FEUADDR_REG, + MAX_SR_DMAR_REGS +}; + struct intel_iommu { void __iomem *reg; /* Pointer to hardware regs, virtual addr */ u64 cap; @@ -304,6 +312,8 @@ struct intel_iommu { struct iommu_flush flush; #endif struct q_inval *qi; /* Queued invalidation info */ + u32 *iommu_state; /* Store iommu states between suspend and resume.*/ + #ifdef CONFIG_INTR_REMAP struct ir_table *ir_table; /* Interrupt remapping info */ #endif @@ -322,6 +332,7 @@ extern int alloc_iommu(struct dmar_drhd_unit *drhd); extern void free_iommu(struct intel_iommu *iommu); extern int dmar_enable_qi(struct intel_iommu *iommu); extern void dmar_disable_qi(struct intel_iommu *iommu); +extern int dmar_reenable_qi(struct intel_iommu *iommu); extern void qi_global_iec(struct intel_iommu *iommu); extern int qi_flush_context(struct intel_iommu *iommu, u16 did, u16 sid, -- cgit v1.2.3 From b24696bc55f66fecc30715e003f10fc2555a9271 Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Fri, 27 Mar 2009 14:22:44 -0700 Subject: Intel IOMMU Suspend/Resume Support - Interrupt Remapping This patch enables suspend/resume for interrupt remapping. During suspend, interrupt remapping is disabled. When resume, interrupt remapping is enabled again. Signed-off-by: Fenghua Yu Acked-by: Ingo Molnar Signed-off-by: David Woodhouse --- include/linux/dmar.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmar.h b/include/linux/dmar.h index 0b4aa806998..4a0ce6f27e1 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -108,6 +108,8 @@ struct irte { #ifdef CONFIG_INTR_REMAP extern int intr_remapping_enabled; extern int enable_intr_remapping(int); +extern void disable_intr_remapping(void); +extern int reenable_intr_remapping(int); extern int get_irte(int irq, struct irte *entry); extern int modify_irte(int irq, struct irte *irte_modified); -- cgit v1.2.3 From 161fde083f3403e7aa178dc944bf43c339e18491 Mon Sep 17 00:00:00 2001 From: "Han, Weidong" Date: Fri, 3 Apr 2009 17:15:47 +0800 Subject: intel-iommu: set compatibility format interrupt When extended interrupt mode (x2apic mode) is not supported in a system, it must set compatibility format interrupt to bypass interrupt remapping, otherwise compatibility format interrupts will be blocked. This will be used when interrupt remapping is enabled while x2apic is not supported. Signed-off-by: Weidong Han Acked-by: Ingo Molnar Signed-off-by: David Woodhouse --- include/linux/intel-iommu.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 3771cd1f876..aa8c5317123 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -164,6 +164,7 @@ static inline void dmar_writeq(void __iomem *addr, u64 val) #define DMA_GCMD_QIE (((u32)1) << 26) #define DMA_GCMD_SIRTP (((u32)1) << 24) #define DMA_GCMD_IRE (((u32) 1) << 25) +#define DMA_GCMD_CFI (((u32) 1) << 23) /* GSTS_REG */ #define DMA_GSTS_TES (((u32)1) << 31) @@ -174,6 +175,7 @@ static inline void dmar_writeq(void __iomem *addr, u64 val) #define DMA_GSTS_QIES (((u32)1) << 26) #define DMA_GSTS_IRTPS (((u32)1) << 24) #define DMA_GSTS_IRES (((u32)1) << 25) +#define DMA_GSTS_CFIS (((u32)1) << 23) /* CCMD_REG */ #define DMA_CCMD_ICC (((u64)1) << 63) -- cgit v1.2.3 From ce0d9d7255a55628fd3732bf583c83e90150b699 Mon Sep 17 00:00:00 2001 From: Evgeniy Polyakov Date: Wed, 14 Jan 2009 02:05:27 +0300 Subject: Staging: dst: core files. This patch contains DST core files, which introduce block layer, connector and sysfs registration glue and main headers. Connector is used for the configuration of the node (its type, address, device name and so on). Sysfs provides bits of information about running devices in the following format: +/* + * DST sysfs tree for device called 'storage': + * + * /sys/bus/dst/devices/storage/ + * /sys/bus/dst/devices/storage/type : 192.168.4.80:1025 + * /sys/bus/dst/devices/storage/size : 800 + * /sys/bus/dst/devices/storage/name : storage + */ DST header contains structure definitions and protocol command description. Signed-off-by: Evgeniy Polyakov Signed-off-by: Greg Kroah-Hartman --- include/linux/connector.h | 4 +- include/linux/dst.h | 587 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 590 insertions(+), 1 deletion(-) create mode 100644 include/linux/dst.h (limited to 'include/linux') diff --git a/include/linux/connector.h b/include/linux/connector.h index fc65d219d88..b9966e64604 100644 --- a/include/linux/connector.h +++ b/include/linux/connector.h @@ -39,8 +39,10 @@ #define CN_IDX_V86D 0x4 #define CN_VAL_V86D_UVESAFB 0x1 #define CN_IDX_BB 0x5 /* BlackBoard, from the TSP GPL sampling framework */ +#define CN_DST_IDX 0x6 +#define CN_DST_VAL 0x1 -#define CN_NETLINK_USERS 6 +#define CN_NETLINK_USERS 7 /* * Maximum connector's message size. diff --git a/include/linux/dst.h b/include/linux/dst.h new file mode 100644 index 00000000000..e26fed84b1a --- /dev/null +++ b/include/linux/dst.h @@ -0,0 +1,587 @@ +/* + * 2007+ Copyright (c) Evgeniy Polyakov + * All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef __DST_H +#define __DST_H + +#include +#include + +#define DST_NAMELEN 32 +#define DST_NAME "dst" + +enum { + /* Remove node with given id from storage */ + DST_DEL_NODE = 0, + /* Add remote node with given id to the storage */ + DST_ADD_REMOTE, + /* Add local node with given id to the storage to be exported and used by remote peers */ + DST_ADD_EXPORT, + /* Crypto initialization command (hash/cipher used to protect the connection) */ + DST_CRYPTO, + /* Security attributes for given connection (permissions for example) */ + DST_SECURITY, + /* Register given node in the block layer subsystem */ + DST_START, + DST_CMD_MAX +}; + +struct dst_ctl +{ + /* Storage name */ + char name[DST_NAMELEN]; + /* Command flags */ + __u32 flags; + /* Command itself (see above) */ + __u32 cmd; + /* Maximum number of pages per single request in this device */ + __u32 max_pages; + /* Stale/error transaction scanning timeout in milliseconds */ + __u32 trans_scan_timeout; + /* Maximum number of retry sends before completing transaction as broken */ + __u32 trans_max_retries; + /* Storage size */ + __u64 size; +}; + +/* Reply command carries completion status */ +struct dst_ctl_ack +{ + struct cn_msg msg; + int error; + int unused[3]; +}; + +/* + * Unfortunaltely socket address structure is not exported to userspace + * and is redefined there. + */ +#define SADDR_MAX_DATA 128 + +struct saddr { + /* address family, AF_xxx */ + unsigned short sa_family; + /* 14 bytes of protocol address */ + char sa_data[SADDR_MAX_DATA]; + /* Number of bytes used in sa_data */ + unsigned short sa_data_len; +}; + +/* Address structure */ +struct dst_network_ctl +{ + /* Socket type: datagram, stream...*/ + unsigned int type; + /* Let me guess, is it a Jupiter diameter? */ + unsigned int proto; + /* Peer's address */ + struct saddr addr; +}; + +struct dst_crypto_ctl +{ + /* Cipher and hash names */ + char cipher_algo[DST_NAMELEN]; + char hash_algo[DST_NAMELEN]; + + /* Key sizes. Can be zero for digest for example */ + unsigned int cipher_keysize, hash_keysize; + /* Alignment. Calculated by the DST itself. */ + unsigned int crypto_attached_size; + /* Number of threads to perform crypto operations */ + int thread_num; +}; + +/* Export security attributes have this bits checked in when client connects */ +#define DST_PERM_READ (1<<0) +#define DST_PERM_WRITE (1<<1) + +/* + * Right now it is simple model, where each remote address + * is assigned to set of permissions it is allowed to perform. + * In real world block device does not know anything but + * reading and writing, so it should be more than enough. + */ +struct dst_secure_user +{ + unsigned int permissions; + struct saddr addr; +}; + +/* + * Export control command: device to export and network address to accept + * clients to work with given device + */ +struct dst_export_ctl +{ + char device[DST_NAMELEN]; + struct dst_network_ctl ctl; +}; + +enum { + DST_CFG = 1, /* Request remote configuration */ + DST_IO, /* IO command */ + DST_IO_RESPONSE, /* IO response */ + DST_PING, /* Keepalive message */ + DST_NCMD_MAX, +}; + +struct dst_cmd +{ + /* Network command itself, see above */ + __u32 cmd; + /* + * Size of the attached data + * (in most cases, for READ command it means how many bytes were requested) + */ + __u32 size; + /* Crypto size: number of attached bytes with digest/hmac */ + __u32 csize; + /* Here we can carry secret data */ + __u32 reserved; + /* Read/write bits, see how they are encoded in bio structure */ + __u64 rw; + /* BIO flags */ + __u64 flags; + /* Unique command id (like transaction ID) */ + __u64 id; + /* Sector to start IO from */ + __u64 sector; + /* Hash data is placed after this header */ + __u8 hash[0]; +}; + +/* + * Convert command to/from network byte order. + * We do not use hton*() functions, since there is + * no 64-bit implementation. + */ +static inline void dst_convert_cmd(struct dst_cmd *c) +{ + c->cmd = __cpu_to_be32(c->cmd); + c->csize = __cpu_to_be32(c->csize); + c->size = __cpu_to_be32(c->size); + c->sector = __cpu_to_be64(c->sector); + c->id = __cpu_to_be64(c->id); + c->flags = __cpu_to_be64(c->flags); + c->rw = __cpu_to_be64(c->rw); +} + +/* Transaction id */ +typedef __u64 dst_gen_t; + +#ifdef __KERNEL__ + +#include +#include +#include +#include +#include +#include +#include + +#ifdef CONFIG_DST_DEBUG +#define dprintk(f, a...) printk(KERN_NOTICE f, ##a) +#else +static inline void __attribute__ ((format (printf, 1, 2))) + dprintk(const char *fmt, ...) {} +#endif + +struct dst_node; + +struct dst_trans +{ + /* DST node we are working with */ + struct dst_node *n; + + /* Entry inside transaction tree */ + struct rb_node trans_entry; + + /* Merlin kills this transaction when this memory cell equals zero */ + atomic_t refcnt; + + /* How this transaction should be processed by crypto engine */ + short enc; + /* How many times this transaction was resent */ + short retries; + /* Completion status */ + int error; + + /* When did we send it to the remote peer */ + long send_time; + + /* My name is... + * Well, computers does not speak, they have unique id instead */ + dst_gen_t gen; + + /* Block IO we are working with */ + struct bio *bio; + + /* Network command for above block IO request */ + struct dst_cmd cmd; +}; + +struct dst_crypto_engine +{ + /* What should we do with all block requests */ + struct crypto_hash *hash; + struct crypto_ablkcipher *cipher; + + /* Pool of pages used to encrypt data into before sending */ + int page_num; + struct page **pages; + + /* What to do with current request */ + int enc; + /* Who we are and where do we go */ + struct scatterlist *src, *dst; + + /* Maximum timeout waiting for encryption to be completed */ + long timeout; + /* IV is a 64-bit sequential counter */ + u64 iv; + + /* Secret data */ + void *private; + + /* Cached temporary data lives here */ + int size; + void *data; +}; + +struct dst_state +{ + /* The main state protection */ + struct mutex state_lock; + + /* Polling machinery for sockets */ + wait_queue_t wait; + wait_queue_head_t *whead; + /* Most of events are being waited here */ + wait_queue_head_t thread_wait; + + /* Who owns this? */ + struct dst_node *node; + + /* Network address for this state */ + struct dst_network_ctl ctl; + + /* Permissions to work with: read-only or rw connection */ + u32 permissions; + + /* Called when we need to clean private data */ + void (* cleanup)(struct dst_state *st); + + /* Used by the server: BIO completion queues BIOs here */ + struct list_head request_list; + spinlock_t request_lock; + + /* Guess what? No, it is not number of planets */ + atomic_t refcnt; + + /* This flags is set when connection should be dropped */ + int need_exit; + + /* + * Socket to work with. Second pointer is used for + * lockless check if socket was changed before performing + * next action (like working with cached polling result) + */ + struct socket *socket, *read_socket; + + /* Cached preallocated data */ + void *data; + unsigned int size; + + /* Currently processed command */ + struct dst_cmd cmd; +}; + +struct dst_info +{ + /* Device size */ + u64 size; + + /* Local device name for export devices */ + char local[DST_NAMELEN]; + + /* Network setup */ + struct dst_network_ctl net; + + /* Sysfs bits use this */ + struct device device; +}; + +struct dst_node +{ + struct list_head node_entry; + + /* Hi, my name is stored here */ + char name[DST_NAMELEN]; + /* My cache name is stored here */ + char cache_name[DST_NAMELEN]; + + /* Block device attached to given node. + * Only valid for exporting nodes */ + struct block_device *bdev; + /* Network state machine for given peer */ + struct dst_state *state; + + /* Block IO machinery */ + struct request_queue *queue; + struct gendisk *disk; + + /* Number of threads in processing pool */ + int thread_num; + /* Maximum number of pages in single IO */ + int max_pages; + + /* I'm that big in bytes */ + loff_t size; + + /* Exported to userspace node information */ + struct dst_info *info; + + /* + * Security attribute list. + * Used only by exporting node currently. + */ + struct list_head security_list; + struct mutex security_lock; + + /* + * When this unerflows below zero, university collapses. + * But this will not happen, since node will be freed, + * when reference counter reaches zero. + */ + atomic_t refcnt; + + /* How precisely should I be started? */ + int (*start)(struct dst_node *); + + /* Crypto capabilities */ + struct dst_crypto_ctl crypto; + u8 *hash_key; + u8 *cipher_key; + + /* Pool of processing thread */ + struct thread_pool *pool; + + /* Transaction IDs live here */ + atomic_long_t gen; + + /* + * How frequently and how many times transaction + * tree should be scanned to drop stale objects. + */ + long trans_scan_timeout; + int trans_max_retries; + + /* Small gnomes live here */ + struct rb_root trans_root; + struct mutex trans_lock; + + /* + * Transaction cache/memory pool. + * It is big enough to contain not only transaction + * itself, but additional crypto data (digest/hmac). + */ + struct kmem_cache *trans_cache; + mempool_t *trans_pool; + + /* This entity scans transaction tree */ + struct delayed_work trans_work; + + wait_queue_head_t wait; +}; + +/* Kernel representation of the security attribute */ +struct dst_secure +{ + struct list_head sec_entry; + struct dst_secure_user sec; +}; + +int dst_process_bio(struct dst_node *n, struct bio *bio); + +int dst_node_init_connected(struct dst_node *n, struct dst_network_ctl *r); +int dst_node_init_listened(struct dst_node *n, struct dst_export_ctl *le); + +static inline struct dst_state *dst_state_get(struct dst_state *st) +{ + BUG_ON(atomic_read(&st->refcnt) == 0); + atomic_inc(&st->refcnt); + return st; +} + +void dst_state_put(struct dst_state *st); + +struct dst_state *dst_state_alloc(struct dst_node *n); +int dst_state_socket_create(struct dst_state *st); +void dst_state_socket_release(struct dst_state *st); + +void dst_state_exit_connected(struct dst_state *st); + +int dst_state_schedule_receiver(struct dst_state *st); + +void dst_dump_addr(struct socket *sk, struct sockaddr *sa, char *str); + +static inline void dst_state_lock(struct dst_state *st) +{ + mutex_lock(&st->state_lock); +} + +static inline void dst_state_unlock(struct dst_state *st) +{ + mutex_unlock(&st->state_lock); +} + +void dst_poll_exit(struct dst_state *st); +int dst_poll_init(struct dst_state *st); + +static inline unsigned int dst_state_poll(struct dst_state *st) +{ + unsigned int revents = POLLHUP | POLLERR; + + dst_state_lock(st); + if (st->socket) + revents = st->socket->ops->poll(NULL, st->socket, NULL); + dst_state_unlock(st); + + return revents; +} + +static inline int dst_thread_setup(void *private, void *data) +{ + return 0; +} + +void dst_node_put(struct dst_node *n); + +static inline struct dst_node *dst_node_get(struct dst_node *n) +{ + atomic_inc(&n->refcnt); + return n; +} + +int dst_data_recv(struct dst_state *st, void *data, unsigned int size); +int dst_recv_cdata(struct dst_state *st, void *cdata); +int dst_data_send_header(struct socket *sock, + void *data, unsigned int size, int more); + +int dst_send_bio(struct dst_state *st, struct dst_cmd *cmd, struct bio *bio); + +int dst_process_io(struct dst_state *st); +int dst_export_crypto(struct dst_node *n, struct bio *bio); +int dst_export_send_bio(struct bio *bio); +int dst_start_export(struct dst_node *n); + +int __init dst_export_init(void); +void dst_export_exit(void); + +/* Private structure for export block IO requests */ +struct dst_export_priv +{ + struct list_head request_entry; + struct dst_state *state; + struct bio *bio; + struct dst_cmd cmd; +}; + +static inline void dst_trans_get(struct dst_trans *t) +{ + atomic_inc(&t->refcnt); +} + +struct dst_trans *dst_trans_search(struct dst_node *node, dst_gen_t gen); +int dst_trans_remove(struct dst_trans *t); +int dst_trans_remove_nolock(struct dst_trans *t); +void dst_trans_put(struct dst_trans *t); + +/* + * Convert bio into network command. + */ +static inline void dst_bio_to_cmd(struct bio *bio, struct dst_cmd *cmd, + u32 command, u64 id) +{ + cmd->cmd = command; + cmd->flags = (bio->bi_flags << BIO_POOL_BITS) >> BIO_POOL_BITS; + cmd->rw = bio->bi_rw; + cmd->size = bio->bi_size; + cmd->csize = 0; + cmd->id = id; + cmd->sector = bio->bi_sector; +}; + +int dst_trans_send(struct dst_trans *t); +int dst_trans_crypto(struct dst_trans *t); + +int dst_node_crypto_init(struct dst_node *n, struct dst_crypto_ctl *ctl); +void dst_node_crypto_exit(struct dst_node *n); + +static inline int dst_need_crypto(struct dst_node *n) +{ + struct dst_crypto_ctl *c = &n->crypto; + /* + * Logical OR is appropriate here, but boolean one produces + * more optimal code, so it is used instead. + */ + return (c->hash_algo[0] | c->cipher_algo[0]); +} + +int dst_node_trans_init(struct dst_node *n, unsigned int size); +void dst_node_trans_exit(struct dst_node *n); + +/* + * Pool of threads. + * Ready list contains threads currently free to be used, + * active one contains threads with some work scheduled for them. + * Caller can wait in given queue when thread is ready. + */ +struct thread_pool +{ + int thread_num; + struct mutex thread_lock; + struct list_head ready_list, active_list; + + wait_queue_head_t wait; +}; + +void thread_pool_del_worker(struct thread_pool *p); +void thread_pool_del_worker_id(struct thread_pool *p, unsigned int id); +int thread_pool_add_worker(struct thread_pool *p, + char *name, + unsigned int id, + void *(* init)(void *data), + void (* cleanup)(void *data), + void *data); + +void thread_pool_destroy(struct thread_pool *p); +struct thread_pool *thread_pool_create(int num, char *name, + void *(* init)(void *data), + void (* cleanup)(void *data), + void *data); + +int thread_pool_schedule(struct thread_pool *p, + int (* setup)(void *stored_private, void *setup_data), + int (* action)(void *stored_private, void *setup_data), + void *setup_data, long timeout); +int thread_pool_schedule_private(struct thread_pool *p, + int (* setup)(void *private, void *data), + int (* action)(void *private, void *data), + void *data, long timeout, void *id); + +#endif /* __KERNEL__ */ +#endif /* __DST_H */ -- cgit v1.2.3 From 7237d3de78ff89ec2e18eae5fe962d063024fef5 Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Mon, 30 Mar 2009 13:55:30 -0800 Subject: x86, ACPI: add support for x2apic ACPI extensions All logical processors with APIC ID values of 255 and greater will have their APIC reported through Processor X2APIC structure (type-9 entry type) and all logical processors with APIC ID less than 255 will have their APIC reported through legacy Processor Local APIC (type-0 entry type) only. This is the same case even for NMI structure reporting. The Processor X2APIC Affinity structure provides the association between the X2APIC ID of a logical processor and the proximity domain to which the logical processor belongs. For OSPM, Procssor IDs outside the 0-254 range are to be declared as Device() objects in the ACPI namespace. Signed-off-by: Suresh Siddha Signed-off-by: Len Brown --- include/linux/acpi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 6fce2fc2d12..a6989e51754 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -96,6 +96,7 @@ void acpi_table_print_madt_entry (struct acpi_subtable_header *madt); /* the following four functions are architecture-dependent */ void acpi_numa_slit_init (struct acpi_table_slit *slit); void acpi_numa_processor_affinity_init (struct acpi_srat_cpu_affinity *pa); +void acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa); void acpi_numa_memory_affinity_init (struct acpi_srat_mem_affinity *ma); void acpi_numa_arch_fixup(void); -- cgit v1.2.3 From 2f425878b6a71571341dcd3f9e9d1a6f6355da9c Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Fri, 3 Apr 2009 08:27:32 +0300 Subject: nfsd: don't use the deferral service, return NFS4ERR_DELAY On an NFSv4.1 server cache miss that causes an upcall, NFS4ERR_DELAY will be returned. It is up to the NFSv4.1 client to resend only the operations that have not been processed. Initialize rq_usedeferral to 1 in svc_process(). It sill be turned off in nfsd4_proc_compound() only when NFSv4.1 Sessions are used. Note: this isn't an adequate solution on its own. It's acceptable as a way to get some minimal 4.1 up and working, but we're going to have to find a way to avoid returning DELAY in all common cases before 4.1 can really be considered ready. Signed-off-by: Andy Adamson Signed-off-by: Benny Halevy [nfsd41: reverse rq_nodeferral negative logic] Signed-off-by: Benny Halevy [sunrpc: initialize rq_usedeferral] Signed-off-by: Andy Adamson Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 9f9f699dd46..815dd589d4d 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -230,6 +230,7 @@ struct svc_rqst { struct svc_cred rq_cred; /* auth info */ void * rq_xprt_ctxt; /* transport specific context ptr */ struct svc_deferred_req*rq_deferred; /* deferred request we are replaying */ + int rq_usedeferral; /* use deferral */ size_t rq_xprt_hlen; /* xprt header len */ struct xdr_buf rq_arg; -- cgit v1.2.3 From 18df1884a872a2cc405a578cfd0d3adc8d227277 Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Fri, 3 Apr 2009 08:27:36 +0300 Subject: nfs41: common protocol definitions Define all NFSv4.1 common operation and error code constants. Note that some of the definitions are used by both the nfs41 client and the server code. This patch is duplicated in the nfs41 and nfsd41 sessions patchset. Signed-off-by: Andy Adamson Signed-off-by: Benny Halevy [nfs41: add exchange id flags] Signed-off-by: Mike Sager Signed-off-by: Benny Halevy [removed server-only hunk changing NFSERR_REPLAY_ME] Signed-off-by: Benny Halevy [nfs41: add SEQ4_XX to nfs41-common-protocol] Signed-off-by: Andy Adamson Signed-off-by: Benny Halevy [nfs41: generic error code update] [nfs41: reverse EXCHGID4_INVAL_FLAG_MASK_{A,R}] Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- include/linux/nfs4.h | 128 ++++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 127 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index b912311a56b..29ed600e193 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -21,6 +21,7 @@ #define NFS4_FHSIZE 128 #define NFS4_MAXPATHLEN PATH_MAX #define NFS4_MAXNAMLEN NAME_MAX +#define NFS4_MAX_SESSIONID_LEN 16 #define NFS4_ACCESS_READ 0x0001 #define NFS4_ACCESS_LOOKUP 0x0002 @@ -38,6 +39,7 @@ #define NFS4_OPEN_RESULT_CONFIRM 0x0002 #define NFS4_OPEN_RESULT_LOCKTYPE_POSIX 0x0004 +#define NFS4_SHARE_ACCESS_MASK 0x000F #define NFS4_SHARE_ACCESS_READ 0x0001 #define NFS4_SHARE_ACCESS_WRITE 0x0002 #define NFS4_SHARE_ACCESS_BOTH 0x0003 @@ -45,6 +47,19 @@ #define NFS4_SHARE_DENY_WRITE 0x0002 #define NFS4_SHARE_DENY_BOTH 0x0003 +/* nfs41 */ +#define NFS4_SHARE_WANT_MASK 0xFF00 +#define NFS4_SHARE_WANT_NO_PREFERENCE 0x0000 +#define NFS4_SHARE_WANT_READ_DELEG 0x0100 +#define NFS4_SHARE_WANT_WRITE_DELEG 0x0200 +#define NFS4_SHARE_WANT_ANY_DELEG 0x0300 +#define NFS4_SHARE_WANT_NO_DELEG 0x0400 +#define NFS4_SHARE_WANT_CANCEL 0x0500 + +#define NFS4_SHARE_WHEN_MASK 0xF0000 +#define NFS4_SHARE_SIGNAL_DELEG_WHEN_RESRC_AVAIL 0x10000 +#define NFS4_SHARE_PUSH_DELEG_WHEN_UNCONTENDED 0x20000 + #define NFS4_SET_TO_SERVER_TIME 0 #define NFS4_SET_TO_CLIENT_TIME 1 @@ -88,6 +103,31 @@ #define NFS4_ACE_GENERIC_EXECUTE 0x001200A0 #define NFS4_ACE_MASK_ALL 0x001F01FF +#define EXCHGID4_FLAG_SUPP_MOVED_REFER 0x00000001 +#define EXCHGID4_FLAG_SUPP_MOVED_MIGR 0x00000002 +#define EXCHGID4_FLAG_USE_NON_PNFS 0x00010000 +#define EXCHGID4_FLAG_USE_PNFS_MDS 0x00020000 +#define EXCHGID4_FLAG_USE_PNFS_DS 0x00040000 +#define EXCHGID4_FLAG_UPD_CONFIRMED_REC_A 0x40000000 +#define EXCHGID4_FLAG_CONFIRMED_R 0x80000000 +/* + * Since the validity of these bits depends on whether + * they're set in the argument or response, have separate + * invalid flag masks for arg (_A) and resp (_R). + */ +#define EXCHGID4_FLAG_MASK_A 0x40070003 +#define EXCHGID4_FLAG_MASK_R 0x80070003 + +#define SEQ4_STATUS_CB_PATH_DOWN 0x00000001 +#define SEQ4_STATUS_CB_GSS_CONTEXTS_EXPIRING 0x00000002 +#define SEQ4_STATUS_CB_GSS_CONTEXTS_EXPIRED 0x00000004 +#define SEQ4_STATUS_EXPIRED_ALL_STATE_REVOKED 0x00000008 +#define SEQ4_STATUS_EXPIRED_SOME_STATE_REVOKED 0x00000010 +#define SEQ4_STATUS_ADMIN_STATE_REVOKED 0x00000020 +#define SEQ4_STATUS_RECALLABLE_STATE_REVOKED 0x00000040 +#define SEQ4_STATUS_LEASE_MOVED 0x00000080 +#define SEQ4_STATUS_RESTART_RECLAIM_NEEDED 0x00000100 + #define NFS4_MAX_UINT64 (~(u64)0) enum nfs4_acl_whotype { @@ -154,6 +194,28 @@ enum nfs_opnum4 { OP_VERIFY = 37, OP_WRITE = 38, OP_RELEASE_LOCKOWNER = 39, + + /* nfs41 */ + OP_BACKCHANNEL_CTL = 40, + OP_BIND_CONN_TO_SESSION = 41, + OP_EXCHANGE_ID = 42, + OP_CREATE_SESSION = 43, + OP_DESTROY_SESSION = 44, + OP_FREE_STATEID = 45, + OP_GET_DIR_DELEGATION = 46, + OP_GETDEVICEINFO = 47, + OP_GETDEVICELIST = 48, + OP_LAYOUTCOMMIT = 49, + OP_LAYOUTGET = 50, + OP_LAYOUTRETURN = 51, + OP_SECINFO_NO_NAME = 52, + OP_SEQUENCE = 53, + OP_SET_SSV = 54, + OP_TEST_STATEID = 55, + OP_WANT_DELEGATION = 56, + OP_DESTROY_CLIENTID = 57, + OP_RECLAIM_COMPLETE = 58, + OP_ILLEGAL = 10044, }; @@ -230,7 +292,48 @@ enum nfsstat4 { NFS4ERR_DEADLOCK = 10045, NFS4ERR_FILE_OPEN = 10046, NFS4ERR_ADMIN_REVOKED = 10047, - NFS4ERR_CB_PATH_DOWN = 10048 + NFS4ERR_CB_PATH_DOWN = 10048, + + /* nfs41 */ + NFS4ERR_BADIOMODE = 10049, + NFS4ERR_BADLAYOUT = 10050, + NFS4ERR_BAD_SESSION_DIGEST = 10051, + NFS4ERR_BADSESSION = 10052, + NFS4ERR_BADSLOT = 10053, + NFS4ERR_COMPLETE_ALREADY = 10054, + NFS4ERR_CONN_NOT_BOUND_TO_SESSION = 10055, + NFS4ERR_DELEG_ALREADY_WANTED = 10056, + NFS4ERR_BACK_CHAN_BUSY = 10057, /* backchan reqs outstanding */ + NFS4ERR_LAYOUTTRYLATER = 10058, + NFS4ERR_LAYOUTUNAVAILABLE = 10059, + NFS4ERR_NOMATCHING_LAYOUT = 10060, + NFS4ERR_RECALLCONFLICT = 10061, + NFS4ERR_UNKNOWN_LAYOUTTYPE = 10062, + NFS4ERR_SEQ_MISORDERED = 10063, /* unexpected seq.id in req */ + NFS4ERR_SEQUENCE_POS = 10064, /* [CB_]SEQ. op not 1st op */ + NFS4ERR_REQ_TOO_BIG = 10065, /* request too big */ + NFS4ERR_REP_TOO_BIG = 10066, /* reply too big */ + NFS4ERR_REP_TOO_BIG_TO_CACHE = 10067, /* rep. not all cached */ + NFS4ERR_RETRY_UNCACHED_REP = 10068, /* retry & rep. uncached */ + NFS4ERR_UNSAFE_COMPOUND = 10069, /* retry/recovery too hard */ + NFS4ERR_TOO_MANY_OPS = 10070, /* too many ops in [CB_]COMP */ + NFS4ERR_OP_NOT_IN_SESSION = 10071, /* op needs [CB_]SEQ. op */ + NFS4ERR_HASH_ALG_UNSUPP = 10072, /* hash alg. not supp. */ + /* Error 10073 is unused. */ + NFS4ERR_CLIENTID_BUSY = 10074, /* clientid has state */ + NFS4ERR_PNFS_IO_HOLE = 10075, /* IO to _SPARSE file hole */ + NFS4ERR_SEQ_FALSE_RETRY = 10076, /* retry not origional */ + NFS4ERR_BAD_HIGH_SLOT = 10077, /* sequence arg bad */ + NFS4ERR_DEADSESSION = 10078, /* persistent session dead */ + NFS4ERR_ENCR_ALG_UNSUPP = 10079, /* SSV alg mismatch */ + NFS4ERR_PNFS_NO_LAYOUT = 10080, /* direct I/O with no layout */ + NFS4ERR_NOT_ONLY_OP = 10081, /* bad compound */ + NFS4ERR_WRONG_CRED = 10082, /* permissions:state change */ + NFS4ERR_WRONG_TYPE = 10083, /* current operation mismatch */ + NFS4ERR_DIRDELEG_UNAVAIL = 10084, /* no directory delegation */ + NFS4ERR_REJECT_DELEG = 10085, /* on callback */ + NFS4ERR_RETURNCONFLICT = 10086, /* outstanding layoutreturn */ + NFS4ERR_DELEG_REVOKED = 10087, /* deleg./layout revoked */ }; /* @@ -391,6 +494,29 @@ enum { NFSPROC4_CLNT_GETACL, NFSPROC4_CLNT_SETACL, NFSPROC4_CLNT_FS_LOCATIONS, + + /* nfs41 */ + NFSPROC4_CLNT_EXCHANGE_ID, + NFSPROC4_CLNT_CREATE_SESSION, + NFSPROC4_CLNT_DESTROY_SESSION, + NFSPROC4_CLNT_SEQUENCE, + NFSPROC4_CLNT_GET_LEASE_TIME, +}; + +/* nfs41 types */ +struct nfs4_sessionid { + unsigned char data[NFS4_MAX_SESSIONID_LEN]; +}; + +/* Create Session Flags */ +#define SESSION4_PERSIST 0x001 +#define SESSION4_BACK_CHAN 0x002 +#define SESSION4_RDMA 0x004 + +enum state_protect_how4 { + SP4_NONE = 0, + SP4_MACH_CRED = 1, + SP4_SSV = 2 }; #endif -- cgit v1.2.3 From 10add806c38c022d18af48f3ec28c91b4eaf7bb3 Mon Sep 17 00:00:00 2001 From: Marc Eshel Date: Fri, 3 Apr 2009 08:27:40 +0300 Subject: nfsd41: define nfs41 error codes Define all error code present in http://tools.ietf.org/html/draft-ietf-nfsv4-minorversion1-29. Signed-off-by: Benny Halevy [nfsd41: clean up error code definitions] [nfsd41: change NFSERR_REPLAY_ME] Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- include/linux/nfs.h | 1 - include/linux/nfsd/nfsd.h | 43 ++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 42 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs.h b/include/linux/nfs.h index 54af92c1c70..214d499718f 100644 --- a/include/linux/nfs.h +++ b/include/linux/nfs.h @@ -109,7 +109,6 @@ NFSERR_FILE_OPEN = 10046, /* v4 */ NFSERR_ADMIN_REVOKED = 10047, /* v4 */ NFSERR_CB_PATH_DOWN = 10048, /* v4 */ - NFSERR_REPLAY_ME = 10049 /* v4 */ }; /* NFSv2 file types - beware, these are not the same in NFSv3 */ diff --git a/include/linux/nfsd/nfsd.h b/include/linux/nfsd/nfsd.h index 54beda12d26..ab9616d0920 100644 --- a/include/linux/nfsd/nfsd.h +++ b/include/linux/nfsd/nfsd.h @@ -249,7 +249,44 @@ void nfsd_lockd_shutdown(void); #define nfserr_cb_path_down cpu_to_be32(NFSERR_CB_PATH_DOWN) #define nfserr_locked cpu_to_be32(NFSERR_LOCKED) #define nfserr_wrongsec cpu_to_be32(NFSERR_WRONGSEC) -#define nfserr_replay_me cpu_to_be32(NFSERR_REPLAY_ME) +#define nfserr_badiomode cpu_to_be32(NFS4ERR_BADIOMODE) +#define nfserr_badlayout cpu_to_be32(NFS4ERR_BADLAYOUT) +#define nfserr_bad_session_digest cpu_to_be32(NFS4ERR_BAD_SESSION_DIGEST) +#define nfserr_badsession cpu_to_be32(NFS4ERR_BADSESSION) +#define nfserr_badslot cpu_to_be32(NFS4ERR_BADSLOT) +#define nfserr_complete_already cpu_to_be32(NFS4ERR_COMPLETE_ALREADY) +#define nfserr_conn_not_bound_to_session cpu_to_be32(NFS4ERR_CONN_NOT_BOUND_TO_SESSION) +#define nfserr_deleg_already_wanted cpu_to_be32(NFS4ERR_DELEG_ALREADY_WANTED) +#define nfserr_back_chan_busy cpu_to_be32(NFS4ERR_BACK_CHAN_BUSY) +#define nfserr_layouttrylater cpu_to_be32(NFS4ERR_LAYOUTTRYLATER) +#define nfserr_layoutunavailable cpu_to_be32(NFS4ERR_LAYOUTUNAVAILABLE) +#define nfserr_nomatching_layout cpu_to_be32(NFS4ERR_NOMATCHING_LAYOUT) +#define nfserr_recallconflict cpu_to_be32(NFS4ERR_RECALLCONFLICT) +#define nfserr_unknown_layouttype cpu_to_be32(NFS4ERR_UNKNOWN_LAYOUTTYPE) +#define nfserr_seq_misordered cpu_to_be32(NFS4ERR_SEQ_MISORDERED) +#define nfserr_sequence_pos cpu_to_be32(NFS4ERR_SEQUENCE_POS) +#define nfserr_req_too_big cpu_to_be32(NFS4ERR_REQ_TOO_BIG) +#define nfserr_rep_too_big cpu_to_be32(NFS4ERR_REP_TOO_BIG) +#define nfserr_rep_too_big_to_cache cpu_to_be32(NFS4ERR_REP_TOO_BIG_TO_CACHE) +#define nfserr_retry_uncached_rep cpu_to_be32(NFS4ERR_RETRY_UNCACHED_REP) +#define nfserr_unsafe_compound cpu_to_be32(NFS4ERR_UNSAFE_COMPOUND) +#define nfserr_too_many_ops cpu_to_be32(NFS4ERR_TOO_MANY_OPS) +#define nfserr_op_not_in_session cpu_to_be32(NFS4ERR_OP_NOT_IN_SESSION) +#define nfserr_hash_alg_unsupp cpu_to_be32(NFS4ERR_HASH_ALG_UNSUPP) +#define nfserr_clientid_busy cpu_to_be32(NFS4ERR_CLIENTID_BUSY) +#define nfserr_pnfs_io_hole cpu_to_be32(NFS4ERR_PNFS_IO_HOLE) +#define nfserr_seq_false_retry cpu_to_be32(NFS4ERR_SEQ_FALSE_RETRY) +#define nfserr_bad_high_slot cpu_to_be32(NFS4ERR_BAD_HIGH_SLOT) +#define nfserr_deadsession cpu_to_be32(NFS4ERR_DEADSESSION) +#define nfserr_encr_alg_unsupp cpu_to_be32(NFS4ERR_ENCR_ALG_UNSUPP) +#define nfserr_pnfs_no_layout cpu_to_be32(NFS4ERR_PNFS_NO_LAYOUT) +#define nfserr_not_only_op cpu_to_be32(NFS4ERR_NOT_ONLY_OP) +#define nfserr_wrong_cred cpu_to_be32(NFS4ERR_WRONG_CRED) +#define nfserr_wrong_type cpu_to_be32(NFS4ERR_WRONG_TYPE) +#define nfserr_dirdeleg_unavail cpu_to_be32(NFS4ERR_DIRDELEG_UNAVAIL) +#define nfserr_reject_deleg cpu_to_be32(NFS4ERR_REJECT_DELEG) +#define nfserr_returnconflict cpu_to_be32(NFS4ERR_RETURNCONFLICT) +#define nfserr_deleg_revoked cpu_to_be32(NFS4ERR_DELEG_REVOKED) /* error codes for internal use */ /* if a request fails due to kmalloc failure, it gets dropped. @@ -258,6 +295,10 @@ void nfsd_lockd_shutdown(void); #define nfserr_dropit cpu_to_be32(30000) /* end-of-file indicator in readdir */ #define nfserr_eof cpu_to_be32(30001) +/* replay detected */ +#define nfserr_replay_me cpu_to_be32(11001) +/* nfs41 replay detected */ +#define nfserr_replay_cache cpu_to_be32(11002) /* Check for dir entries '.' and '..' */ #define isdotent(n, l) (l < 3 && n[0] == '.' && (l == 1 || n[1] == '.')) -- cgit v1.2.3 From 7116ed6b9973021ff43edeb10f4cb834db94000f Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Fri, 3 Apr 2009 08:27:43 +0300 Subject: nfsd41: sessions basic data types This patch provides basic data structures representing the nfs41 sessions and slots, plus helpers for keeping a reference count on the session and freeing it. Note that our server only support a headerpadsz of 0 and it ignores backchannel attributes at the moment. Signed-off-by: Benny Halevy [nfsd41: remove headerpadsz from channel attributes] [nfsd41: embed nfsd4_channel in nfsd4_session] Signed-off-by: Andy Adamson Signed-off-by: Benny Halevy [nfsd41: use bool inuse for slot state] Signed-off-by: Benny Halevy [nfsd41 remove sl_session from nfsd4_slot] Signed-off-by: Andy Adamson Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- include/linux/nfsd/state.h | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfsd/state.h b/include/linux/nfsd/state.h index a6e4a00fa39..baea7f1fdb4 100644 --- a/include/linux/nfsd/state.h +++ b/include/linux/nfsd/state.h @@ -99,6 +99,39 @@ struct nfs4_callback { struct rpc_clnt * cb_client; }; +struct nfsd4_slot { + bool sl_inuse; + u32 sl_seqid; +}; + +struct nfsd4_session { + struct kref se_ref; + struct list_head se_hash; /* hash by sessionid */ + struct list_head se_perclnt; + u32 se_flags; + struct nfs4_client *se_client; /* for expire_client */ + struct nfs4_sessionid se_sessionid; + u32 se_fmaxreq_sz; + u32 se_fmaxresp_sz; + u32 se_fmaxresp_cached; + u32 se_fmaxops; + u32 se_fnumslots; + struct nfsd4_slot *se_slots; /* forward channel slots */ +}; + +static inline void +nfsd4_put_session(struct nfsd4_session *ses) +{ + extern void free_session(struct kref *kref); + kref_put(&ses->se_ref, free_session); +} + +static inline void +nfsd4_get_session(struct nfsd4_session *ses) +{ + kref_get(&ses->se_ref); +} + #define HEXDIR_LEN 33 /* hex version of 16 byte md5 of cl_name plus '\0' */ /* -- cgit v1.2.3 From 9fb870702d02c05f9410423bfff3f63e46e26180 Mon Sep 17 00:00:00 2001 From: Marc Eshel Date: Fri, 3 Apr 2009 08:27:46 +0300 Subject: nfsd41: introduce nfs4_client cl_sessions list [get rid of CONFIG_NFSD_V4_1] Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- include/linux/nfsd/state.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfsd/state.h b/include/linux/nfsd/state.h index baea7f1fdb4..7faefc7c9d9 100644 --- a/include/linux/nfsd/state.h +++ b/include/linux/nfsd/state.h @@ -163,6 +163,9 @@ struct nfs4_client { struct nfs4_callback cl_callback; /* callback info */ atomic_t cl_count; /* ref count */ u32 cl_firststate; /* recovery dir creation */ + + /* for nfs41 */ + struct list_head cl_sessions; }; /* struct nfs4_client_reset -- cgit v1.2.3 From 5282fd724b667b7d65f2e41e405a825e58a78813 Mon Sep 17 00:00:00 2001 From: Marc Eshel Date: Fri, 3 Apr 2009 08:27:52 +0300 Subject: nfsd41: sessionid hashing Simple sessionid hashing using its monotonically increasing sequence number. Locking considerations: sessionid_hashtbl access is controlled by the sessionid_lock spin lock. It must be taken for insert, delete, and lookup. nfsd4_sequence looks up the session id and if the session is found, it calls nfsd4_get_session (still under the sessionid_lock). nfsd4_destroy_session calls nfsd4_put_session after unhashing it, so when the session's kref reaches zero it's going to get freed. Signed-off-by: Benny Halevy [we don't use a prime for sessionid hash table size] [use sessionid_lock spin lock] Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- include/linux/nfsd/state.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfsd/state.h b/include/linux/nfsd/state.h index 7faefc7c9d9..5b3a6660f3a 100644 --- a/include/linux/nfsd/state.h +++ b/include/linux/nfsd/state.h @@ -132,6 +132,13 @@ nfsd4_get_session(struct nfsd4_session *ses) kref_get(&ses->se_ref); } +/* formatted contents of nfs4_sessionid */ +struct nfsd4_sessionid { + clientid_t clientid; + u32 sequence; + u32 reserved; +}; + #define HEXDIR_LEN 33 /* hex version of 16 byte md5 of cl_name plus '\0' */ /* -- cgit v1.2.3 From 2db134eb3b39faefc7fbfb200156d175edba2f68 Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Fri, 3 Apr 2009 08:27:55 +0300 Subject: nfsd41: xdr infrastructure Define nfsd41_dec_ops vector and add it to nfsd4_minorversion for minorversion 1. Note: nfsd4_enc_ops vector is shared for v4.0 and v4.1 since we don't need to filter out obsolete ops as this is done in the decoding phase. exchange_id, create_session, destroy_session, and sequence ops are implemented as stubs returning nfserr_opnotsupp at this stage. [was nfsd41: xdr stubs] [get rid of CONFIG_NFSD_V4_1] Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- include/linux/nfsd/xdr4.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfsd/xdr4.h b/include/linux/nfsd/xdr4.h index fd15ddc3359..28af925c2a3 100644 --- a/include/linux/nfsd/xdr4.h +++ b/include/linux/nfsd/xdr4.h @@ -344,6 +344,22 @@ struct nfsd4_write { nfs4_verifier wr_verifier; /* response */ }; +struct nfsd4_exchange_id { + int foo; /* stub */ +}; + +struct nfsd4_create_session { + int foo; /* stub */ +}; + +struct nfsd4_sequence { + int foo; /* stub */ +}; + +struct nfsd4_destroy_session { + int foo; /* stub */ +}; + struct nfsd4_op { int opnum; __be32 status; @@ -378,6 +394,12 @@ struct nfsd4_op { struct nfsd4_verify verify; struct nfsd4_write write; struct nfsd4_release_lockowner release_lockowner; + + /* NFSv4.1 */ + struct nfsd4_exchange_id exchange_id; + struct nfsd4_create_session create_session; + struct nfsd4_destroy_session destroy_session; + struct nfsd4_sequence sequence; } u; struct nfs4_replay * replay; }; -- cgit v1.2.3 From 069b6ad4bb20abf175ea7875e82e8002154773af Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Fri, 3 Apr 2009 08:27:58 +0300 Subject: nfsd41: proc stubs Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- include/linux/nfsd/xdr4.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfsd/xdr4.h b/include/linux/nfsd/xdr4.h index 28af925c2a3..294940c5809 100644 --- a/include/linux/nfsd/xdr4.h +++ b/include/linux/nfsd/xdr4.h @@ -471,6 +471,18 @@ extern __be32 nfsd4_setclientid(struct svc_rqst *rqstp, extern __be32 nfsd4_setclientid_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *, struct nfsd4_setclientid_confirm *setclientid_confirm); +extern __be32 nfsd4_exchange_id(struct svc_rqst *rqstp, + struct nfsd4_compound_state *, +struct nfsd4_exchange_id *); + extern __be32 nfsd4_create_session(struct svc_rqst *, + struct nfsd4_compound_state *, + struct nfsd4_create_session *); +extern __be32 nfsd4_sequence(struct svc_rqst *, + struct nfsd4_compound_state *, + struct nfsd4_sequence *); +extern __be32 nfsd4_destroy_session(struct svc_rqst *, + struct nfsd4_compound_state *, + struct nfsd4_destroy_session *); extern __be32 nfsd4_process_open1(struct nfsd4_open *open); extern __be32 nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open *open); -- cgit v1.2.3 From 0733d21338747483985a5964e852af160d88e429 Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Fri, 3 Apr 2009 08:28:01 +0300 Subject: nfsd41: exchange_id operation Implement the exchange_id operation confoming to http://tools.ietf.org/html/draft-ietf-nfsv4-minorversion1-28 Based on the client provided name, hash a client id. If a confirmed one is found, compare the op's creds and verifier. If the creds match and the verifier is different then expire the old client (client re-incarnated), otherwise, if both match, assume it's a replay and ignore it. If an unconfirmed client is found, then copy the new creds and verifer if need update, otherwise assume replay. The client is moved to a confirmed state on create_session. In the nfs41 branch set the exchange_id flags to EXCHGID4_FLAG_USE_NON_PNFS | EXCHGID4_FLAG_SUPP_MOVED_REFER (pNFS is not supported, Referrals are supported, Migration is not.). Address various scenarios from section 18.35 of the spec: 1. Check for EXCHGID4_FLAG_UPD_CONFIRMED_REC_A and set EXCHGID4_FLAG_CONFIRMED_R as appropriate. 2. Return error codes per 18.35.4 scenarios. 3. Update client records or generate new client ids depending on scenario. Note: 18.35.4 case 3 probably still needs revisiting. The handling seems not quite right. Signed-off-by: Benny Halevy Signed-off-by: Andy Adamosn Signed-off-by: Benny Halevy [nfsd41: use utsname for major_id (and copy to server_scope)] [nfsd41: fix handling of various exchange id scenarios] Signed-off-by: Mike Sager Signed-off-by: Benny Halevy [nfsd41: reverse use of EXCHGID4_INVAL_FLAG_MASK_A] [simplify nfsd4_encode_exchange_id error handling] [nfsd41: embed an xdr_netobj in nfsd4_exchange_id] [nfsd41: return nfserr_serverfault for spa_how == SP4_MACH_CRED] Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- include/linux/nfsd/state.h | 2 ++ include/linux/nfsd/xdr4.h | 7 ++++++- 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfsd/state.h b/include/linux/nfsd/state.h index 5b3a6660f3a..8d0b1016793 100644 --- a/include/linux/nfsd/state.h +++ b/include/linux/nfsd/state.h @@ -173,6 +173,8 @@ struct nfs4_client { /* for nfs41 */ struct list_head cl_sessions; + u32 cl_seqid; /* seqid for create_session */ + u32 cl_exchange_flags; }; /* struct nfs4_client_reset diff --git a/include/linux/nfsd/xdr4.h b/include/linux/nfsd/xdr4.h index 294940c5809..33ee71e988b 100644 --- a/include/linux/nfsd/xdr4.h +++ b/include/linux/nfsd/xdr4.h @@ -345,7 +345,12 @@ struct nfsd4_write { }; struct nfsd4_exchange_id { - int foo; /* stub */ + nfs4_verifier verifier; + struct xdr_netobj clname; + u32 flags; + clientid_t clientid; + u32 seqid; + int spa_how; }; struct nfsd4_create_session { -- cgit v1.2.3 From a1bcecd29cdf1670df6908a620add4211c0abb7a Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Fri, 3 Apr 2009 08:28:05 +0300 Subject: nfsd41: match clientid establishment method We need to distinguish between client names provided by NFSv4.0 clients SETCLIENTID and those provided by NFSv4.1 via EXCHANGE_ID when looking up the clientid by string. Signed-off-by: Benny Halevy Signed-off-by: Andy Adamson [nfsd41: use boolean values for use_exchange_id argument] Signed-off-by: Benny Halevy [nfsd41: simplify match_clientid_establishment logic] Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- include/linux/nfsd/state.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfsd/state.h b/include/linux/nfsd/state.h index 8d0b1016793..90829db7686 100644 --- a/include/linux/nfsd/state.h +++ b/include/linux/nfsd/state.h @@ -330,7 +330,7 @@ extern void nfsd4_init_recdir(char *recdir_name); extern int nfsd4_recdir_load(void); extern void nfsd4_shutdown_recdir(void); extern int nfs4_client_to_reclaim(const char *name); -extern int nfs4_has_reclaimed_state(const char *name); +extern int nfs4_has_reclaimed_state(const char *name, bool use_exchange_id); extern void nfsd4_recdir_purge_old(void); extern int nfsd4_create_clid_dir(struct nfs4_client *clp); extern void nfsd4_remove_clid_dir(struct nfs4_client *clp); -- cgit v1.2.3 From b85d4c01b76f6969a085d07a767fa45225cb14be Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Fri, 3 Apr 2009 08:28:08 +0300 Subject: nfsd41: sequence operation Implement the sequence operation conforming to http://tools.ietf.org/html/draft-ietf-nfsv4-minorversion1-26 Check for stale clientid (as derived from the sessionid). Enforce slotid range and exactly-once semantics using the slotid and seqid. If everything went well renew the client lease and mark the slot INPROGRESS. Add a struct nfsd4_slot pointer to struct nfsd4_compound_state. To be used for sessions DRC replay. [nfsd41: rename sequence catchthis to cachethis] Signed-off-by: Andy Adamson [pulled some code to set cstate->slot from "nfsd DRC logic"] [use sessionid_lock spin lock] [nfsd41: use bool inuse for slot state] Signed-off-by: Benny Halevy [nfsd: add a struct nfsd4_slot pointer to struct nfsd4_compound_state] Signed-off-by: Andy Adamson Signed-off-by: Benny Halevy [nfsd41: add nfsd4_session pointer to nfsd4_compound_state] [nfsd41: set cstate session] [nfsd41: use cstate session in nfsd4_sequence] Signed-off-by: Andy Adamson Signed-off-by: Benny Halevy [simplify nfsd4_encode_sequence error handling] Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- include/linux/nfsd/xdr4.h | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfsd/xdr4.h b/include/linux/nfsd/xdr4.h index 33ee71e988b..6e28a041008 100644 --- a/include/linux/nfsd/xdr4.h +++ b/include/linux/nfsd/xdr4.h @@ -48,6 +48,9 @@ struct nfsd4_compound_state { struct svc_fh current_fh; struct svc_fh save_fh; struct nfs4_stateowner *replay_owner; + /* For sessions DRC */ + struct nfsd4_session *session; + struct nfsd4_slot *slot; }; struct nfsd4_change_info { @@ -358,7 +361,15 @@ struct nfsd4_create_session { }; struct nfsd4_sequence { - int foo; /* stub */ + struct nfs4_sessionid sessionid; /* request/response */ + u32 seqid; /* request/response */ + u32 slotid; /* request/response */ + u32 maxslots; /* request/response */ + u32 cachethis; /* request */ +#if 0 + u32 target_maxslots; /* response */ + u32 status_flags; /* response */ +#endif /* not yet */ }; struct nfsd4_destroy_session { -- cgit v1.2.3 From 074fe897536f095309c5aaffcf912952882ab2cb Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Fri, 3 Apr 2009 08:28:15 +0300 Subject: nfsd41: DRC save, restore, and clear functions Cache all the result pages, including the rpc header in rq_respages[0], for a request in the slot table cache entry. Cache the statp pointer from nfsd_dispatch which points into rq_respages[0] just past the rpc header. When setting a cache entry, calculate and save the length of the nfs data minus the rpc header for rq_respages[0]. When replaying a cache entry, replace the cached rpc header with the replayed request rpc result header, unless there is not enough room in the cached results first page. In that case, use the cached rpc header. The sessions fore channel maxresponse size cached is set to NFSD_PAGES_PER_SLOT * PAGE_SIZE. For compounds we are cacheing with operations such as READDIR that use the xdr_buf->pages to hold data, we choose to cache the extra page of data rather than copying data from xdr_buf->pages into the xdr_buf->head page. [nfsd41: limit cache to maxresponsesize_cached] [nfsd41: mv nfsd4_set_statp under CONFIG_NFSD_V4_1] [nfsd41: rename nfsd4_move_pages] [nfsd41: rename page_no variable] [nfsd41: rename nfsd4_set_cache_entry] [nfsd41: fix nfsd41_copy_replay_data comment] [nfsd41: add to nfsd4_set_cache_entry] Signed-off-by: Andy Adamson Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- include/linux/nfsd/cache.h | 1 + include/linux/nfsd/state.h | 13 +++++++++++++ include/linux/nfsd/xdr4.h | 4 ++++ 3 files changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfsd/cache.h b/include/linux/nfsd/cache.h index 04b355c801d..a59a2df6d07 100644 --- a/include/linux/nfsd/cache.h +++ b/include/linux/nfsd/cache.h @@ -75,5 +75,6 @@ int nfsd_reply_cache_init(void); void nfsd_reply_cache_shutdown(void); int nfsd_cache_lookup(struct svc_rqst *, int); void nfsd_cache_update(struct svc_rqst *, int, __be32 *); +void nfsd4_set_statp(struct svc_rqst *rqstp, __be32 *statp); #endif /* NFSCACHE_H */ diff --git a/include/linux/nfsd/state.h b/include/linux/nfsd/state.h index 90829db7686..f1edb1d9852 100644 --- a/include/linux/nfsd/state.h +++ b/include/linux/nfsd/state.h @@ -99,9 +99,22 @@ struct nfs4_callback { struct rpc_clnt * cb_client; }; +/* Maximum number of pages per slot cache entry */ +#define NFSD_PAGES_PER_SLOT 1 + +struct nfsd4_cache_entry { + __be32 ce_status; + struct kvec ce_datav; /* encoded NFSv4.1 data in rq_res.head[0] */ + struct page *ce_respages[NFSD_PAGES_PER_SLOT + 1]; + short ce_resused; + int ce_opcnt; + int ce_rpchdrlen; +}; + struct nfsd4_slot { bool sl_inuse; u32 sl_seqid; + struct nfsd4_cache_entry sl_cache_entry; }; struct nfsd4_session { diff --git a/include/linux/nfsd/xdr4.h b/include/linux/nfsd/xdr4.h index 6e28a041008..d091684325a 100644 --- a/include/linux/nfsd/xdr4.h +++ b/include/linux/nfsd/xdr4.h @@ -51,6 +51,8 @@ struct nfsd4_compound_state { /* For sessions DRC */ struct nfsd4_session *session; struct nfsd4_slot *slot; + __be32 *statp; + u32 status; }; struct nfsd4_change_info { @@ -487,6 +489,8 @@ extern __be32 nfsd4_setclientid(struct svc_rqst *rqstp, extern __be32 nfsd4_setclientid_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *, struct nfsd4_setclientid_confirm *setclientid_confirm); +extern void nfsd4_store_cache_entry(struct nfsd4_compoundres *resp); +extern __be32 nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp); extern __be32 nfsd4_exchange_id(struct svc_rqst *rqstp, struct nfsd4_compound_state *, struct nfsd4_exchange_id *); -- cgit v1.2.3 From c3d06f9ce8544fecfe13e377d1e2c2e47fe18dbc Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Fri, 3 Apr 2009 08:28:18 +0300 Subject: nfsd41: hard page limit for DRC Use no more than 1/128th of the number of free pages at nfsd startup for the v4.1 DRC. This is an arbitrary default which should probably end up under the control of an administrator. Signed-off-by: Andy Adamson [moved added fields in struct svc_serv under CONFIG_NFSD_V4_1] Signed-off-by: Benny Halevy [fix set_max_drc calculation of sv_drc_max_pages] [moved NFSD_DRC_SIZE_SHIFT's declaration up in header file] Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- include/linux/nfsd/nfsd.h | 3 +++ include/linux/sunrpc/svc.h | 2 ++ 2 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfsd/nfsd.h b/include/linux/nfsd/nfsd.h index ab9616d0920..1f063d49515 100644 --- a/include/linux/nfsd/nfsd.h +++ b/include/linux/nfsd/nfsd.h @@ -331,6 +331,9 @@ extern struct timeval nfssvc_boot; #define NFSD_LEASE_TIME (nfs4_lease_time()) #define NFSD_LAUNDROMAT_MINTIMEOUT 10 /* seconds */ +/* The percent of nr_free_buffer_pages used by the V4.1 server DRC */ +#define NFSD_DRC_SIZE_SHIFT 7 + /* * The following attributes are currently not supported by the NFSv4 server: * ARCHIVE (deprecated anyway) diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 815dd589d4d..d209c630a4a 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -95,6 +95,8 @@ struct svc_serv { struct module * sv_module; /* optional module to count when * adding threads */ svc_thread_fn sv_function; /* main function for threads */ + unsigned int sv_drc_max_pages; /* Total pages for DRC */ + unsigned int sv_drc_pages_used;/* DRC pages used */ }; /* -- cgit v1.2.3 From da3846a2866ddf239311766ff434a82e7b4ac701 Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Fri, 3 Apr 2009 08:28:22 +0300 Subject: nfsd41: nfsd DRC logic Replay a request in nfsd4_sequence. Add a minorversion to struct nfsd4_compound_state. Pass the current slot to nfs4svc_encode_compound res via struct nfsd4_compoundres to set an NFSv4.1 DRC entry. Signed-off-by: Andy Adamson Signed-off-by: Benny Halevy [nfsd41: use bool inuse for slot state] Signed-off-by: Benny Halevy [nfsd41: use cstate session in nfs4svc_encode_compoundres] [nfsd41 replace nfsd4_set_cache_entry] Signed-off-by: Andy Adamson Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- include/linux/nfsd/xdr4.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfsd/xdr4.h b/include/linux/nfsd/xdr4.h index d091684325a..69cb467cb72 100644 --- a/include/linux/nfsd/xdr4.h +++ b/include/linux/nfsd/xdr4.h @@ -52,6 +52,7 @@ struct nfsd4_compound_state { struct nfsd4_session *session; struct nfsd4_slot *slot; __be32 *statp; + size_t iovlen; u32 status; }; -- cgit v1.2.3 From ec6b5d7b5064fde27aee798b81107ea3a830de85 Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Fri, 3 Apr 2009 08:28:28 +0300 Subject: nfsd41: create_session operation Implement the create_session operation confoming to http://tools.ietf.org/html/draft-ietf-nfsv4-minorversion1-26 Look up the client id (generated by the server on exchange_id, given by the client on create_session). If neither a confirmed or unconfirmed client is found then the client id is stale If a confirmed cilent is found (i.e. we already received create_session for it) then compare the sequence id to determine if it's a replay or possibly a mis-ordered rpc. If the seqid is in order, update the confirmed client seqid and procedd with updating the session parameters. If an unconfirmed client_id is found then verify the creds and seqid. If both match move the client id to confirmed state and proceed with processing the create_session. Currently, we do not support persistent sessions, and RDMA. alloc_init_session generates a new sessionid and creates a session structure. NFSD_PAGES_PER_SLOT is used for the max response cached calculation, and for the counting of DRC pages using the hard limits set in struct srv_serv. A note on NFSD_PAGES_PER_SLOT: Other patches in this series allow for NFSD_PAGES_PER_SLOT + 1 pages to be cached in a DRC slot when the response size is less than NFSD_PAGES_PER_SLOT * PAGE_SIZE but xdr_buf pages are used. e.g. a READDIR operation will encode a small amount of data in the xdr_buf head, and then the READDIR in the xdr_buf pages. So, the hard limit calculation use of pages by a session is underestimated by the number of cached operations using the xdr_buf pages. Yet another patch caches no pages for the solo sequence operation, or any compound where cache_this is False. So the hard limit calculation use of pages by a session is overestimated by the number of these operations in the cache. TODO: improve resource pre-allocation and negotiate session parameters accordingly. Respect and possibly adjust backchannel attributes. Signed-off-by: Marc Eshel Signed-off-by: Dean Hildebrand [nfsd41: remove headerpadsz from channel attributes] Our client and server only support a headerpadsz of 0. [nfsd41: use DRC limits in fore channel init] [nfsd41: do not change CREATE_SESSION back channel attrs] Signed-off-by: Andy Adamson Signed-off-by: Benny Halevy [use sessionid_lock spin lock] [nfsd41: use bool inuse for slot state] Signed-off-by: Benny Halevy [nfsd41 remove sl_session from alloc_init_session] Signed-off-by: Andy Adamson Signed-off-by: Benny Halevy [simplify nfsd4_encode_create_session error handling] [nfsd41: fix comment style in init_forechannel_attrs] [nfsd41: allocate struct nfsd4_session and slot table in one piece] [nfsd41: no need to INIT_LIST_HEAD in alloc_init_session just prior to list_add] Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- include/linux/nfsd/state.h | 7 ++++++- include/linux/nfsd/xdr4.h | 21 ++++++++++++++++++++- 2 files changed, 26 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfsd/state.h b/include/linux/nfsd/state.h index f1edb1d9852..692edf4c2e7 100644 --- a/include/linux/nfsd/state.h +++ b/include/linux/nfsd/state.h @@ -99,8 +99,12 @@ struct nfs4_callback { struct rpc_clnt * cb_client; }; +/* Maximum number of slots per session. 128 is useful for long haul TCP */ +#define NFSD_MAX_SLOTS_PER_SESSION 128 /* Maximum number of pages per slot cache entry */ #define NFSD_PAGES_PER_SLOT 1 +/* Maximum number of operations per session compound */ +#define NFSD_MAX_OPS_PER_COMPOUND 16 struct nfsd4_cache_entry { __be32 ce_status; @@ -129,7 +133,7 @@ struct nfsd4_session { u32 se_fmaxresp_cached; u32 se_fmaxops; u32 se_fnumslots; - struct nfsd4_slot *se_slots; /* forward channel slots */ + struct nfsd4_slot se_slots[]; /* forward channel slots */ }; static inline void @@ -188,6 +192,7 @@ struct nfs4_client { struct list_head cl_sessions; u32 cl_seqid; /* seqid for create_session */ u32 cl_exchange_flags; + struct nfs4_sessionid cl_sessionid; }; /* struct nfs4_client_reset diff --git a/include/linux/nfsd/xdr4.h b/include/linux/nfsd/xdr4.h index 69cb467cb72..9468829adb7 100644 --- a/include/linux/nfsd/xdr4.h +++ b/include/linux/nfsd/xdr4.h @@ -359,8 +359,27 @@ struct nfsd4_exchange_id { int spa_how; }; +struct nfsd4_channel_attrs { + u32 headerpadsz; + u32 maxreq_sz; + u32 maxresp_sz; + u32 maxresp_cached; + u32 maxops; + u32 maxreqs; + u32 nr_rdma_attrs; + u32 rdma_attrs; +}; + struct nfsd4_create_session { - int foo; /* stub */ + clientid_t clientid; + struct nfs4_sessionid sessionid; + u32 seqid; + u32 flags; + struct nfsd4_channel_attrs fore_channel; + struct nfsd4_channel_attrs back_channel; + u32 callback_prog; + u32 uid; + u32 gid; }; struct nfsd4_sequence { -- cgit v1.2.3 From 38eb76a54d803e6792816623651b1a9cb85f8d01 Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Fri, 3 Apr 2009 08:28:32 +0300 Subject: nfsd41: Add a create session replay cache Replace the nfs4_client cl_seqid field with a single struct nfs41_slot used for the create session replay cache. The CREATE_SESSION slot sets the sl_session pointer to NULL. Otherwise, the slot and it's replay cache are used just like the session slots. Fix unconfirmed create_session replay response by initializing the create_session slot sequence id to 0. A future patch will set the CREATE_SESSION cache when a SEQUENCE operation preceeds the CREATE_SESSION operation. This compound is currently only cached in the session slot table. Signed-off-by: Andy Adamson Signed-off-by: Benny Halevy [nfsd41: use bool inuse for slot state] Signed-off-by: Benny Halevy [nfsd41: revert portion of nfsd4_set_cache_entry] Signed-off-by: Andy Adamson Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- include/linux/nfsd/state.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfsd/state.h b/include/linux/nfsd/state.h index 692edf4c2e7..f063df7ad13 100644 --- a/include/linux/nfsd/state.h +++ b/include/linux/nfsd/state.h @@ -190,7 +190,7 @@ struct nfs4_client { /* for nfs41 */ struct list_head cl_sessions; - u32 cl_seqid; /* seqid for create_session */ + struct nfsd4_slot cl_slot; /* create_session slot */ u32 cl_exchange_flags; struct nfs4_sessionid cl_sessionid; }; -- cgit v1.2.3 From bf864a31d50e3e94d6e76537b97d664913906ff8 Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Fri, 3 Apr 2009 08:28:35 +0300 Subject: nfsd41: non-page DRC for solo sequence responses A session inactivity time compound (lease renewal) or a compound where the sequence operation has sa_cachethis set to FALSE do not require any pages to be held in the v4.1 DRC. This is because struct nfsd4_slot is already caching the session information. Add logic to the nfs41 server to not cache response pages for solo sequence responses. Return nfserr_replay_uncached_rep on the operation following the sequence operation when sa_cachethis is FALSE. Signed-off-by: Andy Adamson Signed-off-by: Benny Halevy [nfsd41: use cstate session in nfsd4_replay_cache_entry] [nfsd41: rename nfsd4_no_page_in_cache] [nfsd41 rename nfsd4_enc_no_page_replay] [nfsd41 nfsd4_is_solo_sequence] [nfsd41 change nfsd4_not_cached return] Signed-off-by: Andy Adamson [changed return type to bool] Signed-off-by: Benny Halevy [nfsd41 drop parens in nfsd4_is_solo_sequence call] Signed-off-by: Andy Adamson [changed "== 0" to "!"] Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- include/linux/nfsd/state.h | 1 + include/linux/nfsd/xdr4.h | 15 ++++++++++++++- 2 files changed, 15 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfsd/state.h b/include/linux/nfsd/state.h index f063df7ad13..18dcffa57f7 100644 --- a/include/linux/nfsd/state.h +++ b/include/linux/nfsd/state.h @@ -110,6 +110,7 @@ struct nfsd4_cache_entry { __be32 ce_status; struct kvec ce_datav; /* encoded NFSv4.1 data in rq_res.head[0] */ struct page *ce_respages[NFSD_PAGES_PER_SLOT + 1]; + int ce_cachethis; short ce_resused; int ce_opcnt; int ce_rpchdrlen; diff --git a/include/linux/nfsd/xdr4.h b/include/linux/nfsd/xdr4.h index 9468829adb7..486188810a6 100644 --- a/include/linux/nfsd/xdr4.h +++ b/include/linux/nfsd/xdr4.h @@ -480,6 +480,18 @@ struct nfsd4_compoundres { struct nfsd4_compound_state cstate; }; +static inline bool nfsd4_is_solo_sequence(struct nfsd4_compoundres *resp) +{ + struct nfsd4_compoundargs *args = resp->rqstp->rq_argp; + return args->opcnt == 1; +} + +static inline bool nfsd4_not_cached(struct nfsd4_compoundres *resp) +{ + return !resp->cstate.slot->sl_cache_entry.ce_cachethis || + nfsd4_is_solo_sequence(resp); +} + #define NFS4_SVC_XDRSIZE sizeof(struct nfsd4_compoundargs) static inline void @@ -510,7 +522,8 @@ extern __be32 nfsd4_setclientid_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *, struct nfsd4_setclientid_confirm *setclientid_confirm); extern void nfsd4_store_cache_entry(struct nfsd4_compoundres *resp); -extern __be32 nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp); +extern __be32 nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp, + struct nfsd4_sequence *seq); extern __be32 nfsd4_exchange_id(struct svc_rqst *rqstp, struct nfsd4_compound_state *, struct nfsd4_exchange_id *); -- cgit v1.2.3 From e10e0cfc2f27364c73b28adbd3c8688d97049e73 Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Fri, 3 Apr 2009 08:28:38 +0300 Subject: nfsd41: destroy_session operation Implement the destory_session operation confoming to http://tools.ietf.org/html/draft-ietf-nfsv4-minorversion1-26 [use sessionid_lock spin lock] Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- include/linux/nfsd/xdr4.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfsd/xdr4.h b/include/linux/nfsd/xdr4.h index 486188810a6..a0a2e8317a3 100644 --- a/include/linux/nfsd/xdr4.h +++ b/include/linux/nfsd/xdr4.h @@ -395,7 +395,7 @@ struct nfsd4_sequence { }; struct nfsd4_destroy_session { - int foo; /* stub */ + struct nfs4_sessionid sessionid; }; struct nfsd4_op { -- cgit v1.2.3 From dd453dfd70538cadc02cb47ff8d8cfd0cb8cf435 Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Fri, 3 Apr 2009 08:28:41 +0300 Subject: nfsd: pass nfsd4_compound_state* to nfs4_preprocess_{state,seq}id_op Currently we only use cstate->current_fh, will also be used by nfsd41 code. Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- include/linux/nfsd/state.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfsd/state.h b/include/linux/nfsd/state.h index 18dcffa57f7..836c0d6bbed 100644 --- a/include/linux/nfsd/state.h +++ b/include/linux/nfsd/state.h @@ -333,7 +333,9 @@ struct nfs4_stateid { ((err) != nfserr_stale_stateid) && \ ((err) != nfserr_bad_stateid)) -extern __be32 nfs4_preprocess_stateid_op(struct svc_fh *current_fh, +struct nfsd4_compound_state; + +extern __be32 nfs4_preprocess_stateid_op(struct nfsd4_compound_state *cstate, stateid_t *stateid, int flags, struct file **filp); extern void nfs4_lock_state(void); extern void nfs4_unlock_state(void); -- cgit v1.2.3 From 6668958fac1d05f55420de702f3678d46c1e93a5 Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Fri, 3 Apr 2009 08:28:45 +0300 Subject: nfsd41: stateid handling When sessions are used, stateful operation sequenceid and stateid handling are not used. When sessions are used, on the first open set the seqid to 1, mark state confirmed and skip seqid processing. When sessionas are used the stateid generation number is ignored when it is zero whereas without sessions bad_stateid or stale stateid is returned. Add flags to propagate session use to all stateful ops and down to check_stateid_generation. Signed-off-by: Benny Halevy Signed-off-by: Andy Adamson [nfsd4_has_session should return a boolean, not u32] Signed-off-by: Benny Halevy [nfsd41: pass nfsd4_compoundres * to nfsd4_process_open1] [nfsd41: calculate HAS_SESSION in nfs4_preprocess_stateid_op] [nfsd41: calculate HAS_SESSION in nfs4_preprocess_seqid_op] Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- include/linux/nfsd/state.h | 1 + include/linux/nfsd/xdr4.h | 8 +++++++- 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfsd/state.h b/include/linux/nfsd/state.h index 836c0d6bbed..4d61c873fee 100644 --- a/include/linux/nfsd/state.h +++ b/include/linux/nfsd/state.h @@ -320,6 +320,7 @@ struct nfs4_stateid { }; /* flags for preprocess_seqid_op() */ +#define HAS_SESSION 0x00000001 #define CONFIRM 0x00000002 #define OPEN_STATE 0x00000004 #define LOCK_STATE 0x00000008 diff --git a/include/linux/nfsd/xdr4.h b/include/linux/nfsd/xdr4.h index a0a2e8317a3..b8b3dcba28c 100644 --- a/include/linux/nfsd/xdr4.h +++ b/include/linux/nfsd/xdr4.h @@ -56,6 +56,11 @@ struct nfsd4_compound_state { u32 status; }; +static inline bool nfsd4_has_session(struct nfsd4_compound_state *cs) +{ + return cs->slot != NULL; +} + struct nfsd4_change_info { u32 atomic; u32 before_ctime_sec; @@ -536,7 +541,8 @@ extern __be32 nfsd4_sequence(struct svc_rqst *, extern __be32 nfsd4_destroy_session(struct svc_rqst *, struct nfsd4_compound_state *, struct nfsd4_destroy_session *); -extern __be32 nfsd4_process_open1(struct nfsd4_open *open); +extern __be32 nfsd4_process_open1(struct nfsd4_compound_state *, + struct nfsd4_open *open); extern __be32 nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open *open); extern __be32 nfsd4_open_confirm(struct svc_rqst *rqstp, -- cgit v1.2.3 From d87a8ade95288f28c729e076cd74929f3f199b6c Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Fri, 3 Apr 2009 08:28:53 +0300 Subject: nfsd41: access_valid For nfs41, the open share flags are used also for delegation "wants" and "signals". Check that they are valid. Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- include/linux/nfsd/xdr4.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfsd/xdr4.h b/include/linux/nfsd/xdr4.h index b8b3dcba28c..5e16935a1ea 100644 --- a/include/linux/nfsd/xdr4.h +++ b/include/linux/nfsd/xdr4.h @@ -53,6 +53,7 @@ struct nfsd4_compound_state { struct nfsd4_slot *slot; __be32 *statp; size_t iovlen; + u32 minorversion; u32 status; }; -- cgit v1.2.3 From 8daf220a6a83c47b9648c28bb819c14c60bad7f9 Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Fri, 3 Apr 2009 08:28:59 +0300 Subject: nfsd41: control nfsv4.1 svc via /proc/fs/nfsd/versions Support enabling and disabling nfsv4.1 via /proc/fs/nfsd/versions by writing the strings "+4.1" or "-4.1" correspondingly. Use user mode nfs-utils (rpc.nfsd option) to enable. This will allow us to get rid of CONFIG_NFSD_V4_1 [nfsd41: disable support for minorversion by default] Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- include/linux/nfsd/nfsd.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfsd/nfsd.h b/include/linux/nfsd/nfsd.h index 1f063d49515..70339b7b83c 100644 --- a/include/linux/nfsd/nfsd.h +++ b/include/linux/nfsd/nfsd.h @@ -53,6 +53,7 @@ typedef int (*nfsd_dirop_t)(struct inode *, struct dentry *, int, int); extern struct svc_program nfsd_program; extern struct svc_version nfsd_version2, nfsd_version3, nfsd_version4; +extern u32 nfsd_supported_minorversion; extern struct mutex nfsd_mutex; extern struct svc_serv *nfsd_serv; @@ -149,6 +150,7 @@ int nfsd_set_posix_acl(struct svc_fh *, int, struct posix_acl *); enum vers_op {NFSD_SET, NFSD_CLEAR, NFSD_TEST, NFSD_AVAIL }; int nfsd_vers(int vers, enum vers_op change); +int nfsd_minorversion(u32 minorversion, enum vers_op change); void nfsd_reset_versions(void); int nfsd_create_serv(void); -- cgit v1.2.3 From f3ec22b5b0b4b220ee600bf1a8b6dc045b4e72bd Mon Sep 17 00:00:00 2001 From: Marc Eshel Date: Fri, 3 Apr 2009 08:29:02 +0300 Subject: nfsd41: provide support for minor version 1 at rpc level Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- include/linux/nfsd/nfsd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfsd/nfsd.h b/include/linux/nfsd/nfsd.h index 70339b7b83c..5bed5096874 100644 --- a/include/linux/nfsd/nfsd.h +++ b/include/linux/nfsd/nfsd.h @@ -23,7 +23,7 @@ /* * nfsd version */ -#define NFSD_SUPPORTED_MINOR_VERSION 0 +#define NFSD_SUPPORTED_MINOR_VERSION 1 /* * Flags for nfsd_permission -- cgit v1.2.3 From 7e70570647827345352cf6c17461c9fa166f570a Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Fri, 3 Apr 2009 08:29:11 +0300 Subject: nfsd41: support for 3-word long attribute bitmask Also, use client minorversion to generate supported attrs Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- include/linux/nfsd/nfsd.h | 34 ++++++++++++++++++++++++++++++++-- include/linux/nfsd/xdr4.h | 12 ++++++------ 2 files changed, 38 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfsd/nfsd.h b/include/linux/nfsd/nfsd.h index 5bed5096874..69ca788f8fc 100644 --- a/include/linux/nfsd/nfsd.h +++ b/include/linux/nfsd/nfsd.h @@ -346,7 +346,7 @@ extern struct timeval nfssvc_boot; * TIME_BACKUP (unlikely to be supported any time soon) * TIME_CREATE (unlikely to be supported any time soon) */ -#define NFSD_SUPPORTED_ATTRS_WORD0 \ +#define NFSD4_SUPPORTED_ATTRS_WORD0 \ (FATTR4_WORD0_SUPPORTED_ATTRS | FATTR4_WORD0_TYPE | FATTR4_WORD0_FH_EXPIRE_TYPE \ | FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE | FATTR4_WORD0_LINK_SUPPORT \ | FATTR4_WORD0_SYMLINK_SUPPORT | FATTR4_WORD0_NAMED_ATTR | FATTR4_WORD0_FSID \ @@ -358,7 +358,7 @@ extern struct timeval nfssvc_boot; | FATTR4_WORD0_MAXFILESIZE | FATTR4_WORD0_MAXLINK | FATTR4_WORD0_MAXNAME \ | FATTR4_WORD0_MAXREAD | FATTR4_WORD0_MAXWRITE | FATTR4_WORD0_ACL) -#define NFSD_SUPPORTED_ATTRS_WORD1 \ +#define NFSD4_SUPPORTED_ATTRS_WORD1 \ (FATTR4_WORD1_MODE | FATTR4_WORD1_NO_TRUNC | FATTR4_WORD1_NUMLINKS \ | FATTR4_WORD1_OWNER | FATTR4_WORD1_OWNER_GROUP | FATTR4_WORD1_RAWDEV \ | FATTR4_WORD1_SPACE_AVAIL | FATTR4_WORD1_SPACE_FREE | FATTR4_WORD1_SPACE_TOTAL \ @@ -366,6 +366,35 @@ extern struct timeval nfssvc_boot; | FATTR4_WORD1_TIME_DELTA | FATTR4_WORD1_TIME_METADATA \ | FATTR4_WORD1_TIME_MODIFY | FATTR4_WORD1_TIME_MODIFY_SET | FATTR4_WORD1_MOUNTED_ON_FILEID) +#define NFSD4_SUPPORTED_ATTRS_WORD2 0 + +#define NFSD4_1_SUPPORTED_ATTRS_WORD0 \ + NFSD4_SUPPORTED_ATTRS_WORD0 + +#define NFSD4_1_SUPPORTED_ATTRS_WORD1 \ + NFSD4_SUPPORTED_ATTRS_WORD1 + +#define NFSD4_1_SUPPORTED_ATTRS_WORD2 \ + NFSD4_SUPPORTED_ATTRS_WORD2 + +static inline u32 nfsd_suppattrs0(u32 minorversion) +{ + return minorversion ? NFSD4_1_SUPPORTED_ATTRS_WORD0 + : NFSD4_SUPPORTED_ATTRS_WORD0; +} + +static inline u32 nfsd_suppattrs1(u32 minorversion) +{ + return minorversion ? NFSD4_1_SUPPORTED_ATTRS_WORD1 + : NFSD4_SUPPORTED_ATTRS_WORD1; +} + +static inline u32 nfsd_suppattrs2(u32 minorversion) +{ + return minorversion ? NFSD4_1_SUPPORTED_ATTRS_WORD2 + : NFSD4_SUPPORTED_ATTRS_WORD2; +} + /* These will return ERR_INVAL if specified in GETATTR or READDIR. */ #define NFSD_WRITEONLY_ATTRS_WORD1 \ (FATTR4_WORD1_TIME_ACCESS_SET | FATTR4_WORD1_TIME_MODIFY_SET) @@ -376,6 +405,7 @@ extern struct timeval nfssvc_boot; #define NFSD_WRITEABLE_ATTRS_WORD1 \ (FATTR4_WORD1_MODE | FATTR4_WORD1_OWNER | FATTR4_WORD1_OWNER_GROUP \ | FATTR4_WORD1_TIME_ACCESS_SET | FATTR4_WORD1_TIME_MODIFY_SET) +#define NFSD_WRITEABLE_ATTRS_WORD2 0 #endif /* CONFIG_NFSD_V4 */ diff --git a/include/linux/nfsd/xdr4.h b/include/linux/nfsd/xdr4.h index 5e16935a1ea..c07d8fe7bb0 100644 --- a/include/linux/nfsd/xdr4.h +++ b/include/linux/nfsd/xdr4.h @@ -102,7 +102,7 @@ struct nfsd4_create { u32 specdata2; } dev; /* NF4BLK, NF4CHR */ } u; - u32 cr_bmval[2]; /* request */ + u32 cr_bmval[3]; /* request */ struct iattr cr_iattr; /* request */ struct nfsd4_change_info cr_cinfo; /* response */ struct nfs4_acl *cr_acl; @@ -117,7 +117,7 @@ struct nfsd4_delegreturn { }; struct nfsd4_getattr { - u32 ga_bmval[2]; /* request */ + u32 ga_bmval[3]; /* request */ struct svc_fh *ga_fhp; /* response */ }; @@ -218,7 +218,7 @@ struct nfsd4_open { stateid_t op_delegate_stateid; /* request - response */ u32 op_create; /* request */ u32 op_createmode; /* request */ - u32 op_bmval[2]; /* request */ + u32 op_bmval[3]; /* request */ union { /* request */ struct iattr iattr; /* UNCHECKED4,GUARDED4 */ nfs4_verifier verf; /* EXCLUSIVE4 */ @@ -271,7 +271,7 @@ struct nfsd4_readdir { nfs4_verifier rd_verf; /* request */ u32 rd_dircount; /* request */ u32 rd_maxcount; /* request */ - u32 rd_bmval[2]; /* request */ + u32 rd_bmval[3]; /* request */ struct svc_rqst *rd_rqstp; /* response */ struct svc_fh * rd_fhp; /* response */ @@ -313,7 +313,7 @@ struct nfsd4_secinfo { struct nfsd4_setattr { stateid_t sa_stateid; /* request */ - u32 sa_bmval[2]; /* request */ + u32 sa_bmval[3]; /* request */ struct iattr sa_iattr; /* request */ struct nfs4_acl *sa_acl; }; @@ -339,7 +339,7 @@ struct nfsd4_setclientid_confirm { /* also used for NVERIFY */ struct nfsd4_verify { - u32 ve_bmval[2]; /* request */ + u32 ve_bmval[3]; /* request */ u32 ve_attrlen; /* request */ char * ve_attrval; /* request */ }; -- cgit v1.2.3 From 8c18f2052e756e7d5dea712fc6e7ed70c00e8a39 Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Fri, 3 Apr 2009 08:29:14 +0300 Subject: nfsd41: SUPPATTR_EXCLCREAT attribute Return bitmask for supported EXCLUSIVE4_1 create attributes. Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- include/linux/nfs4.h | 2 ++ include/linux/nfsd/nfsd.h | 14 +++++++++++++- 2 files changed, 15 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 29ed600e193..ec3cd49b04f 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -404,6 +404,8 @@ enum lock_type4 { #define FATTR4_WORD0_UNIQUE_HANDLES (1UL << 9) #define FATTR4_WORD0_LEASE_TIME (1UL << 10) #define FATTR4_WORD0_RDATTR_ERROR (1UL << 11) +/* Mandatory in NFSv4.1 */ +#define FATTR4_WORD2_SUPPATTR_EXCLCREAT (1UL << 11) /* Recommended Attributes */ #define FATTR4_WORD0_ACL (1UL << 12) diff --git a/include/linux/nfsd/nfsd.h b/include/linux/nfsd/nfsd.h index 69ca788f8fc..0ec4d142c50 100644 --- a/include/linux/nfsd/nfsd.h +++ b/include/linux/nfsd/nfsd.h @@ -375,7 +375,7 @@ extern struct timeval nfssvc_boot; NFSD4_SUPPORTED_ATTRS_WORD1 #define NFSD4_1_SUPPORTED_ATTRS_WORD2 \ - NFSD4_SUPPORTED_ATTRS_WORD2 + (NFSD4_SUPPORTED_ATTRS_WORD2 | FATTR4_WORD2_SUPPATTR_EXCLCREAT) static inline u32 nfsd_suppattrs0(u32 minorversion) { @@ -407,6 +407,18 @@ static inline u32 nfsd_suppattrs2(u32 minorversion) | FATTR4_WORD1_TIME_ACCESS_SET | FATTR4_WORD1_TIME_MODIFY_SET) #define NFSD_WRITEABLE_ATTRS_WORD2 0 +#define NFSD_SUPPATTR_EXCLCREAT_WORD0 \ + NFSD_WRITEABLE_ATTRS_WORD0 +/* + * we currently store the exclusive create verifier in the v_{a,m}time + * attributes so the client can't set these at create time using EXCLUSIVE4_1 + */ +#define NFSD_SUPPATTR_EXCLCREAT_WORD1 \ + (NFSD_WRITEABLE_ATTRS_WORD1 & \ + ~(FATTR4_WORD1_TIME_ACCESS_SET | FATTR4_WORD1_TIME_MODIFY_SET)) +#define NFSD_SUPPATTR_EXCLCREAT_WORD2 \ + NFSD_WRITEABLE_ATTRS_WORD2 + #endif /* CONFIG_NFSD_V4 */ #endif /* LINUX_NFSD_NFSD_H */ -- cgit v1.2.3 From 79fb54abd285b442e1f30f851902f3ddf58e7704 Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Fri, 3 Apr 2009 08:29:17 +0300 Subject: nfsd41: CREATE_EXCLUSIVE4_1 Implement the CREATE_EXCLUSIVE4_1 open mode conforming to http://tools.ietf.org/html/draft-ietf-nfsv4-minorversion1-26 This mode allows the client to atomically create a file if it doesn't exist while setting some of its attributes. It must be implemented if the server supports persistent reply cache and/or pnfs. Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- include/linux/nfs4.h | 8 +++++++- include/linux/nfsd/xdr4.h | 10 ++++------ 2 files changed, 11 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index ec3cd49b04f..e3f0cbcbd0d 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -368,7 +368,13 @@ enum opentype4 { enum createmode4 { NFS4_CREATE_UNCHECKED = 0, NFS4_CREATE_GUARDED = 1, - NFS4_CREATE_EXCLUSIVE = 2 + NFS4_CREATE_EXCLUSIVE = 2, + /* + * New to NFSv4.1. If session is persistent, + * GUARDED4 MUST be used. Otherwise, use + * EXCLUSIVE4_1 instead of EXCLUSIVE4. + */ + NFS4_CREATE_EXCLUSIVE4_1 = 3 }; enum limit_by4 { diff --git a/include/linux/nfsd/xdr4.h b/include/linux/nfsd/xdr4.h index c07d8fe7bb0..f80d6013fdc 100644 --- a/include/linux/nfsd/xdr4.h +++ b/include/linux/nfsd/xdr4.h @@ -219,10 +219,8 @@ struct nfsd4_open { u32 op_create; /* request */ u32 op_createmode; /* request */ u32 op_bmval[3]; /* request */ - union { /* request */ - struct iattr iattr; /* UNCHECKED4,GUARDED4 */ - nfs4_verifier verf; /* EXCLUSIVE4 */ - } u; + struct iattr iattr; /* UNCHECKED4, GUARDED4, EXCLUSIVE4_1 */ + nfs4_verifier verf; /* EXCLUSIVE4 */ clientid_t op_clientid; /* request */ struct xdr_netobj op_owner; /* request */ u32 op_seqid; /* request */ @@ -236,8 +234,8 @@ struct nfsd4_open { struct nfs4_stateowner *op_stateowner; /* used during processing */ struct nfs4_acl *op_acl; }; -#define op_iattr u.iattr -#define op_verf u.verf +#define op_iattr iattr +#define op_verf verf struct nfsd4_open_confirm { stateid_t oc_req_stateid /* request */; -- cgit v1.2.3 From 276dbf997043cbf38f0087624e0f9c51742c8885 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Sat, 4 Apr 2009 01:45:37 +0100 Subject: intel-iommu: Handle PCI domains appropriately. We were comparing {bus,devfn} and assuming that a match meant it was the same device. It doesn't -- the same {bus,devfn} can exist in multiple PCI domains. Include domain number in device identification (and call it 'segment' in most places, because there's already a lot of references to 'domain' which means something else, and this code is infected with ACPI thinking already). Signed-off-by: David Woodhouse --- include/linux/dmar.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/dmar.h b/include/linux/dmar.h index 4a0ce6f27e1..e397dc342cd 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -34,6 +34,7 @@ struct dmar_drhd_unit { u64 reg_base_addr; /* register base address*/ struct pci_dev **devices; /* target device array */ int devices_cnt; /* target device count */ + u16 segment; /* PCI domain */ u8 ignored:1; /* ignore drhd */ u8 include_all:1; struct intel_iommu *iommu; -- cgit v1.2.3 From 1f24b5a8ecbb2a3c7080f418974d40e3ffedb221 Mon Sep 17 00:00:00 2001 From: David Brownell Date: Thu, 26 Mar 2009 00:42:41 -0700 Subject: [MTD] driver model updates Update driver model support in the MTD framework, so it fits better into the current udev-based hotplug framework: - Each mtd_info now has a device node. MTD drivers should set the dev.parent field to point to the physical device, before setting up partitions or otherwise declaring MTDs. - Those device nodes always map to /sys/class/mtdX device nodes, which no longer depend on MTD_CHARDEV. - Those mtdX sysfs nodes have a "starter set" of attributes; it's not yet sufficient to replace /proc/mtd. - Enabling MTD_CHARDEV provides /sys/class/mtdXro/ nodes and the /sys/class/mtd*/dev attributes (for udev, mdev, etc). - Include a MODULE_ALIAS_CHARDEV_MAJOR macro. It'll work with udev creating the /dev/mtd* nodes, not just a static rootfs. So the sysfs structure is pretty much what you'd expect, except that readonly chardev nodes are a bit quirky. Signed-off-by: David Brownell Signed-off-by: David Woodhouse --- include/linux/mtd/mtd.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index 0c079fd307a..5675b63a063 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -11,6 +11,7 @@ #include #include #include +#include #include #include @@ -237,6 +238,7 @@ struct mtd_info { void *priv; struct module *owner; + struct device dev; int usecount; /* If the driver is something smart, like UBI, it may need to maintain @@ -247,6 +249,11 @@ struct mtd_info { void (*put_device) (struct mtd_info *mtd); }; +static inline struct mtd_info *dev_to_mtd(struct device *dev) +{ + return dev ? container_of(dev, struct mtd_info, dev) : NULL; +} + static inline uint32_t mtd_div_by_eb(uint64_t sz, struct mtd_info *mtd) { if (mtd->erasesize_shift) -- cgit v1.2.3 From 601cc11d054ae4b5e9b5babec3d8e4667a2cb9b5 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 3 Apr 2009 08:03:22 -0700 Subject: Make non-compat preadv/pwritev use native register size Instead of always splitting the file offset into 32-bit 'high' and 'low' parts, just split them into the largest natural word-size - which in C terms is 'unsigned long'. This allows 64-bit architectures to avoid the unnecessary 32-bit shifting and masking for native format (while the compat interfaces will obviously always have to do it). This also changes the order of 'high' and 'low' to be "low first". Why? Because when we have it like this, the 64-bit system calls now don't use the "pos_high" argument at all, and it makes more sense for the native system call to simply match the user-mode prototype. This results in a much more natural calling convention, and allows the compiler to generate much more straightforward code. On x86-64, we now generate testq %rcx, %rcx # pos_l js .L122 #, movq %rcx, -48(%rbp) # pos_l, pos from the C source loff_t pos = pos_from_hilo(pos_h, pos_l); ... if (pos < 0) return -EINVAL; and the 'pos_h' register isn't even touched. It used to generate code like mov %r8d, %r8d # pos_low, pos_low salq $32, %rcx #, tmp71 movq %r8, %rax # pos_low, pos.386 orq %rcx, %rax # tmp71, pos.386 js .L122 #, movq %rax, -48(%rbp) # pos.386, pos which isn't _that_ horrible, but it does show how the natural word size is just a more sensible interface (same arguments will hold in the user level glibc wrapper function, of course, so the kernel side is just half of the equation!) Note: in all cases the user code wrapper can again be the same. You can just do #define HALF_BITS (sizeof(unsigned long)*4) __syscall(PWRITEV, fd, iov, count, offset, (offset >> HALF_BITS) >> HALF_BITS); or something like that. That way the user mode wrapper will also be nicely passing in a zero (it won't actually have to do the shifts, the compiler will understand what is going on) for the last argument. And that is a good idea, even if nobody will necessarily ever care: if we ever do move to a 128-bit lloff_t, this particular system call might be left alone. Of course, that will be the least of our worries if we really ever need to care, so this may not be worth really caring about. [ Fixed for lost 'loff_t' cast noticed by Andrew Morton ] Acked-by: Gerd Hoffmann Cc: H. Peter Anvin Cc: Andrew Morton Cc: linux-api@vger.kernel.org Cc: linux-arch@vger.kernel.org Cc: Ingo Molnar Cc: Ralf Baechle > Cc: Al Viro Signed-off-by: Linus Torvalds --- include/linux/compat.h | 4 ++-- include/linux/syscalls.h | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 9723edd6455..f2ded21f9a3 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -193,10 +193,10 @@ asmlinkage ssize_t compat_sys_writev(unsigned long fd, const struct compat_iovec __user *vec, unsigned long vlen); asmlinkage ssize_t compat_sys_preadv(unsigned long fd, const struct compat_iovec __user *vec, - unsigned long vlen, u32 pos_high, u32 pos_low); + unsigned long vlen, u32 pos_low, u32 pos_high); asmlinkage ssize_t compat_sys_pwritev(unsigned long fd, const struct compat_iovec __user *vec, - unsigned long vlen, u32 pos_high, u32 pos_low); + unsigned long vlen, u32 pos_low, u32 pos_high); int compat_do_execve(char * filename, compat_uptr_t __user *argv, compat_uptr_t __user *envp, struct pt_regs * regs); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index b299a82a05e..18771cac2f8 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -462,9 +462,9 @@ asmlinkage long sys_pread64(unsigned int fd, char __user *buf, asmlinkage long sys_pwrite64(unsigned int fd, const char __user *buf, size_t count, loff_t pos); asmlinkage long sys_preadv(unsigned long fd, const struct iovec __user *vec, - unsigned long vlen, u32 pos_high, u32 pos_low); + unsigned long vlen, unsigned long pos_l, unsigned long pos_h); asmlinkage long sys_pwritev(unsigned long fd, const struct iovec __user *vec, - unsigned long vlen, u32 pos_high, u32 pos_low); + unsigned long vlen, unsigned long pos_l, unsigned long pos_h); asmlinkage long sys_getcwd(char __user *buf, unsigned long size); asmlinkage long sys_mkdir(const char __user *pathname, int mode); asmlinkage long sys_chdir(const char __user *filename); -- cgit v1.2.3 From 3206450355100eae8e033645318b95bb60f1faff Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Fri, 6 Feb 2009 15:27:13 +0100 Subject: mfd: Support active high IRQs on WM835x Signed-off-by: Mark Brown Signed-off-by: Samuel Ortiz --- include/linux/mfd/wm8350/core.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/wm8350/core.h b/include/linux/mfd/wm8350/core.h index 980669d50dc..42cca672f34 100644 --- a/include/linux/mfd/wm8350/core.h +++ b/include/linux/mfd/wm8350/core.h @@ -640,9 +640,11 @@ struct wm8350 { * * @init: Function called during driver initialisation. Should be * used by the platform to configure GPIO functions and similar. + * @irq_high: Set if WM8350 IRQ is active high. */ struct wm8350_platform_data { int (*init)(struct wm8350 *wm8350); + int irq_high; }; -- cgit v1.2.3 From a23a175795cdb202619ac176129b2f0c2a5c9456 Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Tue, 17 Feb 2009 10:06:41 +0100 Subject: mfd: convert DS1WM to use MFD core This patch converts the DS1WM driver into an MFD cell. It also calculates the bus_shift parameter from the memory resource size. Signed-off-by: Philipp Zabel Signed-off-by: Samuel Ortiz --- include/linux/ds1wm.h | 12 ------------ include/linux/mfd/ds1wm.h | 5 +++++ 2 files changed, 5 insertions(+), 12 deletions(-) delete mode 100644 include/linux/ds1wm.h create mode 100644 include/linux/mfd/ds1wm.h (limited to 'include/linux') diff --git a/include/linux/ds1wm.h b/include/linux/ds1wm.h deleted file mode 100644 index d3c65e48a2e..00000000000 --- a/include/linux/ds1wm.h +++ /dev/null @@ -1,12 +0,0 @@ -/* platform data for the DS1WM driver */ - -struct ds1wm_platform_data { - int bus_shift; /* number of shifts needed to calculate the - * offset between DS1WM registers; - * e.g. on h5xxx and h2200 this is 2 - * (registers aligned to 4-byte boundaries), - * while on hx4700 this is 1 */ - int active_high; - void (*enable)(struct platform_device *pdev); - void (*disable)(struct platform_device *pdev); -}; diff --git a/include/linux/mfd/ds1wm.h b/include/linux/mfd/ds1wm.h new file mode 100644 index 00000000000..d4898ba1820 --- /dev/null +++ b/include/linux/mfd/ds1wm.h @@ -0,0 +1,5 @@ +/* MFD cell driver data for the DS1WM driver */ + +struct ds1wm_driver_data { + int active_high; +}; -- cgit v1.2.3 From b72019dbd126e60bb5f9f350f76127b1527facba Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Tue, 17 Feb 2009 10:06:52 +0100 Subject: mfd: remove unused PASIC3 bus_shift field Removes the now-unused bus_shift field from pasic3_platform_data. Signed-off-by: Philipp Zabel Signed-off-by: Samuel Ortiz --- include/linux/mfd/htc-pasic3.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/htc-pasic3.h b/include/linux/mfd/htc-pasic3.h index b4294f12c4f..3d3ed67bd96 100644 --- a/include/linux/mfd/htc-pasic3.h +++ b/include/linux/mfd/htc-pasic3.h @@ -48,7 +48,6 @@ struct pasic3_leds_machinfo { struct pasic3_platform_data { struct pasic3_leds_machinfo *led_pdata; - unsigned int bus_shift; unsigned int clock_rate; }; -- cgit v1.2.3 From 7d33ccbeecd8393cc690cf9a71008236cdd7cc2c Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Tue, 17 Feb 2009 10:09:19 +0100 Subject: mfd: remove DS1WM clock handling This driver requests a clock that usually is supplied by the MFD in which the DS1WM is contained. Currently, it is impossible for a MFD to register their clocks with the generic clock API due to different implementations across architectures. For now, this patch removes the clock handling from DS1WM altogether, trusting that the MFD enable/disable functions will switch the clock if needed. The clock rate is obtained from a new parameter in driver_data. Signed-off-by: Philipp Zabel Signed-off-by: Samuel Ortiz --- include/linux/mfd/ds1wm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/ds1wm.h b/include/linux/mfd/ds1wm.h index d4898ba1820..be469a357cb 100644 --- a/include/linux/mfd/ds1wm.h +++ b/include/linux/mfd/ds1wm.h @@ -2,4 +2,5 @@ struct ds1wm_driver_data { int active_high; + int clock_rate; }; -- cgit v1.2.3 From 81ec5364a58c0545b694dee02fe65b9ae48f37b6 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 12 Dec 2007 17:27:03 +0100 Subject: [MTD] [NAND] Add support for 4KiB pages. Signed-off-by: Thomas Gleixner Signed-off-by: Sebastian Siewior Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index db5b63da2a7..7efb9be3466 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -43,8 +43,8 @@ extern void nand_wait_ready(struct mtd_info *mtd); * is supported now. If you add a chip with bigger oobsize/page * adjust this accordingly. */ -#define NAND_MAX_OOBSIZE 64 -#define NAND_MAX_PAGESIZE 2048 +#define NAND_MAX_OOBSIZE 128 +#define NAND_MAX_PAGESIZE 4096 /* * Constants for hardware specific CLE/ALE/NCE function -- cgit v1.2.3 From 1faa16d22877f4839bd433547d770c676d1d964c Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 6 Apr 2009 14:48:01 +0200 Subject: block: change the request allocation/congestion logic to be sync/async based This makes sure that we never wait on async IO for sync requests, instead of doing the split on writes vs reads. Signed-off-by: Jens Axboe Signed-off-by: Linus Torvalds --- include/linux/backing-dev.h | 12 +++++------ include/linux/blkdev.h | 52 ++++++++++++++++++++++++++++++--------------- 2 files changed, 41 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index bee52abb8a4..0ec2c594868 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -24,8 +24,8 @@ struct dentry; */ enum bdi_state { BDI_pdflush, /* A pdflush thread is working this device */ - BDI_write_congested, /* The write queue is getting full */ - BDI_read_congested, /* The read queue is getting full */ + BDI_async_congested, /* The async (write) queue is getting full */ + BDI_sync_congested, /* The sync queue is getting full */ BDI_unused, /* Available bits start here */ }; @@ -215,18 +215,18 @@ static inline int bdi_congested(struct backing_dev_info *bdi, int bdi_bits) static inline int bdi_read_congested(struct backing_dev_info *bdi) { - return bdi_congested(bdi, 1 << BDI_read_congested); + return bdi_congested(bdi, 1 << BDI_sync_congested); } static inline int bdi_write_congested(struct backing_dev_info *bdi) { - return bdi_congested(bdi, 1 << BDI_write_congested); + return bdi_congested(bdi, 1 << BDI_async_congested); } static inline int bdi_rw_congested(struct backing_dev_info *bdi) { - return bdi_congested(bdi, (1 << BDI_read_congested)| - (1 << BDI_write_congested)); + return bdi_congested(bdi, (1 << BDI_sync_congested) | + (1 << BDI_async_congested)); } void clear_bdi_congested(struct backing_dev_info *bdi, int rw); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 465d6babc84..67dae3bd881 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -38,6 +38,10 @@ struct request; typedef void (rq_end_io_fn)(struct request *, int); struct request_list { + /* + * count[], starved[], and wait[] are indexed by + * BLK_RW_SYNC/BLK_RW_ASYNC + */ int count[2]; int starved[2]; int elvpriv; @@ -66,6 +70,11 @@ enum rq_cmd_type_bits { REQ_TYPE_ATA_PC, }; +enum { + BLK_RW_ASYNC = 0, + BLK_RW_SYNC = 1, +}; + /* * For request of type REQ_TYPE_LINUX_BLOCK, rq->cmd[0] is the opcode being * sent down (similar to how REQ_TYPE_BLOCK_PC means that ->cmd[] holds a @@ -103,7 +112,7 @@ enum rq_flag_bits { __REQ_QUIET, /* don't worry about errors */ __REQ_PREEMPT, /* set for "ide_preempt" requests */ __REQ_ORDERED_COLOR, /* is before or after barrier */ - __REQ_RW_SYNC, /* request is sync (O_DIRECT) */ + __REQ_RW_SYNC, /* request is sync (sync write or read) */ __REQ_ALLOCED, /* request came from our alloc pool */ __REQ_RW_META, /* metadata io request */ __REQ_COPY_USER, /* contains copies of user pages */ @@ -438,8 +447,8 @@ struct request_queue #define QUEUE_FLAG_CLUSTER 0 /* cluster several segments into 1 */ #define QUEUE_FLAG_QUEUED 1 /* uses generic tag queueing */ #define QUEUE_FLAG_STOPPED 2 /* queue is stopped */ -#define QUEUE_FLAG_READFULL 3 /* read queue has been filled */ -#define QUEUE_FLAG_WRITEFULL 4 /* write queue has been filled */ +#define QUEUE_FLAG_SYNCFULL 3 /* read queue has been filled */ +#define QUEUE_FLAG_ASYNCFULL 4 /* write queue has been filled */ #define QUEUE_FLAG_DEAD 5 /* queue being torn down */ #define QUEUE_FLAG_REENTER 6 /* Re-entrancy avoidance */ #define QUEUE_FLAG_PLUGGED 7 /* queue is plugged */ @@ -611,32 +620,41 @@ enum { #define rq_data_dir(rq) ((rq)->cmd_flags & 1) /* - * We regard a request as sync, if it's a READ or a SYNC write. + * We regard a request as sync, if either a read or a sync write */ -#define rq_is_sync(rq) (rq_data_dir((rq)) == READ || (rq)->cmd_flags & REQ_RW_SYNC) +static inline bool rw_is_sync(unsigned int rw_flags) +{ + return !(rw_flags & REQ_RW) || (rw_flags & REQ_RW_SYNC); +} + +static inline bool rq_is_sync(struct request *rq) +{ + return rw_is_sync(rq->cmd_flags); +} + #define rq_is_meta(rq) ((rq)->cmd_flags & REQ_RW_META) -static inline int blk_queue_full(struct request_queue *q, int rw) +static inline int blk_queue_full(struct request_queue *q, int sync) { - if (rw == READ) - return test_bit(QUEUE_FLAG_READFULL, &q->queue_flags); - return test_bit(QUEUE_FLAG_WRITEFULL, &q->queue_flags); + if (sync) + return test_bit(QUEUE_FLAG_SYNCFULL, &q->queue_flags); + return test_bit(QUEUE_FLAG_ASYNCFULL, &q->queue_flags); } -static inline void blk_set_queue_full(struct request_queue *q, int rw) +static inline void blk_set_queue_full(struct request_queue *q, int sync) { - if (rw == READ) - queue_flag_set(QUEUE_FLAG_READFULL, q); + if (sync) + queue_flag_set(QUEUE_FLAG_SYNCFULL, q); else - queue_flag_set(QUEUE_FLAG_WRITEFULL, q); + queue_flag_set(QUEUE_FLAG_ASYNCFULL, q); } -static inline void blk_clear_queue_full(struct request_queue *q, int rw) +static inline void blk_clear_queue_full(struct request_queue *q, int sync) { - if (rw == READ) - queue_flag_clear(QUEUE_FLAG_READFULL, q); + if (sync) + queue_flag_clear(QUEUE_FLAG_SYNCFULL, q); else - queue_flag_clear(QUEUE_FLAG_WRITEFULL, q); + queue_flag_clear(QUEUE_FLAG_ASYNCFULL, q); } -- cgit v1.2.3 From a1f242524c3c1f5d40f1c9c343427e34d1aadd6e Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 6 Apr 2009 14:48:02 +0200 Subject: Add WRITE_SYNC_PLUG and SWRITE_SYNC_PLUG (S)WRITE_SYNC always unplugs the device right after IO submission. Sometimes we want to build up a queue before doing so, so add variants that explicitly DON'T unplug the queue. The caller must then do that after submitting all the IO. Signed-off-by: Jens Axboe Signed-off-by: Linus Torvalds --- include/linux/fs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index a09e17c8f5f..ea0510978f7 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -96,7 +96,10 @@ struct inodes_stat_t { #define READ_SYNC (READ | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG)) #define READ_META (READ | (1 << BIO_RW_META)) #define WRITE_SYNC (WRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG)) +#define WRITE_SYNC_PLUG (WRITE | (1 << BIO_RW_SYNCIO)) #define SWRITE_SYNC (SWRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG)) +#define SWRITE_SYNC_PLUG \ + (SWRITE | (1 << BIO_RW_SYNCIO)) #define WRITE_BARRIER (WRITE | (1 << BIO_RW_BARRIER)) #define DISCARD_NOBARRIER (1 << BIO_RW_DISCARD) #define DISCARD_BARRIER ((1 << BIO_RW_DISCARD) | (1 << BIO_RW_BARRIER)) -- cgit v1.2.3 From aeb6fafb8fa53266d70ca7474fcda2bdaf96524a Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 6 Apr 2009 14:48:07 +0200 Subject: block: Add flag for telling the IO schedulers NOT to anticipate more IO By default, CFQ will anticipate more IO from a given io context if the previously completed IO was sync. This used to be fine, since the only sync IO was reads and O_DIRECT writes. But with more "normal" sync writes being used now, we don't want to anticipate for those. Add a bio/request flag that informs the IO scheduler that this is a sync request that we should not idle for. Introduce WRITE_ODIRECT specifically for O_DIRECT writes, and make sure that the other sync writes set this flag. Signed-off-by: Jens Axboe Signed-off-by: Linus Torvalds --- include/linux/bio.h | 19 +++++++++++-------- include/linux/blkdev.h | 3 +++ include/linux/fs.h | 9 +++++---- 3 files changed, 19 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index b05b1d4d17d..b900d2c67d2 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -145,20 +145,21 @@ struct bio { * bit 2 -- barrier * Insert a serialization point in the IO queue, forcing previously * submitted IO to be completed before this one is issued. - * bit 3 -- synchronous I/O hint: the block layer will unplug immediately - * Note that this does NOT indicate that the IO itself is sync, just - * that the block layer will not postpone issue of this IO by plugging. - * bit 4 -- metadata request + * bit 3 -- synchronous I/O hint. + * bit 4 -- Unplug the device immediately after submitting this bio. + * bit 5 -- metadata request * Used for tracing to differentiate metadata and data IO. May also * get some preferential treatment in the IO scheduler - * bit 5 -- discard sectors + * bit 6 -- discard sectors * Informs the lower level device that this range of sectors is no longer * used by the file system and may thus be freed by the device. Used * for flash based storage. - * bit 6 -- fail fast device errors - * bit 7 -- fail fast transport errors - * bit 8 -- fail fast driver errors + * bit 7 -- fail fast device errors + * bit 8 -- fail fast transport errors + * bit 9 -- fail fast driver errors * Don't want driver retries for any fast fail whatever the reason. + * bit 10 -- Tell the IO scheduler not to wait for more requests after this + one has been submitted, even if it is a SYNC request. */ #define BIO_RW 0 /* Must match RW in req flags (blkdev.h) */ #define BIO_RW_AHEAD 1 /* Must match FAILFAST in req flags */ @@ -170,6 +171,7 @@ struct bio { #define BIO_RW_FAILFAST_DEV 7 #define BIO_RW_FAILFAST_TRANSPORT 8 #define BIO_RW_FAILFAST_DRIVER 9 +#define BIO_RW_NOIDLE 10 #define bio_rw_flagged(bio, flag) ((bio)->bi_rw & (1 << (flag))) @@ -188,6 +190,7 @@ struct bio { #define bio_rw_ahead(bio) bio_rw_flagged(bio, BIO_RW_AHEAD) #define bio_rw_meta(bio) bio_rw_flagged(bio, BIO_RW_META) #define bio_discard(bio) bio_rw_flagged(bio, BIO_RW_DISCARD) +#define bio_noidle(bio) bio_rw_flagged(bio, BIO_RW_NOIDLE) /* * upper 16 bits of bi_rw define the io priority of this bio diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 67dae3bd881..e03660964e0 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -118,6 +118,7 @@ enum rq_flag_bits { __REQ_COPY_USER, /* contains copies of user pages */ __REQ_INTEGRITY, /* integrity metadata has been remapped */ __REQ_UNPLUG, /* unplug queue on submission */ + __REQ_NOIDLE, /* Don't anticipate more IO after this one */ __REQ_NR_BITS, /* stops here */ }; @@ -145,6 +146,7 @@ enum rq_flag_bits { #define REQ_COPY_USER (1 << __REQ_COPY_USER) #define REQ_INTEGRITY (1 << __REQ_INTEGRITY) #define REQ_UNPLUG (1 << __REQ_UNPLUG) +#define REQ_NOIDLE (1 << __REQ_NOIDLE) #define BLK_MAX_CDB 16 @@ -633,6 +635,7 @@ static inline bool rq_is_sync(struct request *rq) } #define rq_is_meta(rq) ((rq)->cmd_flags & REQ_RW_META) +#define rq_noidle(rq) ((rq)->cmd_flags & REQ_NOIDLE) static inline int blk_queue_full(struct request_queue *q, int sync) { diff --git a/include/linux/fs.h b/include/linux/fs.h index ea0510978f7..cae5720f431 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -95,11 +95,12 @@ struct inodes_stat_t { #define SWRITE 3 /* for ll_rw_block() - wait for buffer lock */ #define READ_SYNC (READ | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG)) #define READ_META (READ | (1 << BIO_RW_META)) -#define WRITE_SYNC (WRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG)) -#define WRITE_SYNC_PLUG (WRITE | (1 << BIO_RW_SYNCIO)) -#define SWRITE_SYNC (SWRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG)) +#define WRITE_SYNC_PLUG (WRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_NOIDLE)) +#define WRITE_SYNC (WRITE_SYNC_PLUG | (1 << BIO_RW_UNPLUG)) +#define WRITE_ODIRECT (WRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG)) #define SWRITE_SYNC_PLUG \ - (SWRITE | (1 << BIO_RW_SYNCIO)) + (SWRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_NOIDLE)) +#define SWRITE_SYNC (SWRITE_SYNC_PLUG | (1 << BIO_RW_UNPLUG)) #define WRITE_BARRIER (WRITE | (1 << BIO_RW_BARRIER)) #define DISCARD_NOBARRIER (1 << BIO_RW_DISCARD) #define DISCARD_BARRIER ((1 << BIO_RW_DISCARD) | (1 << BIO_RW_BARRIER)) -- cgit v1.2.3 From 1bd465e6b0e2b559db47420fea686507a01cfab0 Mon Sep 17 00:00:00 2001 From: Guennadi Liakhovetski Date: Sat, 10 Jan 2009 18:54:39 +0000 Subject: leds: allow led-drivers to use a variable range of brightness values This patch allows drivers to override the default maximum brightness value of 255. We take care to preserve backwards-compatibility as much as possible, so that user-space ABI doesn't change for existing drivers. LED trigger code has also been updated to use the per-LED maximum. Signed-off-by: Guennadi Liakhovetski Signed-off-by: Richard Purdie --- include/linux/leds.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/leds.h b/include/linux/leds.h index 24489da701e..17d277e0c4a 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -30,6 +30,7 @@ enum led_brightness { struct led_classdev { const char *name; int brightness; + int max_brightness; int flags; /* Lower 16 bits reflect status */ -- cgit v1.2.3 From 41c42ff5dbe29b7b826e6736f960959c76e7acf0 Mon Sep 17 00:00:00 2001 From: Luotao Fu Date: Wed, 11 Feb 2009 13:24:40 -0800 Subject: leds: simple driver for pwm driven LEDs Add a simple driver for pwm driver LEDs. pwm_id and period can be defined in board file. It is developed for pxa, however it is probably generic enough to be used on other platforms with pwm. Signed-off-by: Luotao Fu Signed-off-by: Andrew Morton Signed-off-by: Richard Purdie --- include/linux/leds_pwm.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) create mode 100644 include/linux/leds_pwm.h (limited to 'include/linux') diff --git a/include/linux/leds_pwm.h b/include/linux/leds_pwm.h new file mode 100644 index 00000000000..33a07116748 --- /dev/null +++ b/include/linux/leds_pwm.h @@ -0,0 +1,21 @@ +/* + * PWM LED driver data - see drivers/leds/leds-pwm.c + */ +#ifndef __LINUX_LEDS_PWM_H +#define __LINUX_LEDS_PWM_H + +struct led_pwm { + const char *name; + const char *default_trigger; + unsigned pwm_id; + u8 active_low; + unsigned max_brightness; + unsigned pwm_period_ns; +}; + +struct led_pwm_platform_data { + int num_leds; + struct led_pwm *leds; +}; + +#endif -- cgit v1.2.3 From defb512d2576992c63ba1c18c24eea31cfeaa26e Mon Sep 17 00:00:00 2001 From: Richard Purdie Date: Tue, 17 Feb 2009 15:04:07 +0000 Subject: leds: Add suspend/resume state flags to leds-gpio Add an option to preserve LED state when suspending/resuming to the LED gpio driver. Based on a suggestion from Robert Jarzmik. Tested-by: Robert Jarzmik Signed-off-by: Richard Purdie --- include/linux/leds.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/leds.h b/include/linux/leds.h index 17d277e0c4a..376fe07732e 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -141,7 +141,8 @@ struct gpio_led { const char *name; const char *default_trigger; unsigned gpio; - u8 active_low; + u8 active_low : 1; + u8 retain_state_suspended : 1; }; struct gpio_led_platform_data { -- cgit v1.2.3 From 0b56129be72c38179697b7441aacbe133d515ff9 Mon Sep 17 00:00:00 2001 From: Kim Kyuwon Date: Wed, 4 Mar 2009 11:59:29 -0800 Subject: leds: add BD2802GU LED driver ROHM BD2802GU is a RGB LED controller attached to i2c bus and specifically engineered for decoration purposes. This RGB controller incorporates lighting patterns and illuminates. This driver is designed to minimize power consumption, so when there is no emitting LED, it enters to reset state. And because the BD2802GU has lots of features that can't be covered by the current LED framework, it provides Advanced Configuration Function(ADF) mode, so that user applications can set registers of BD2802GU directly. Here are basic usage examples : ; to turn on LED (not blink) $ echo 1 > /sys/class/leds/led1_R/brightness ; to blink LED $ echo timer > /sys/class/leds/led1_R/trigger $ echo 1 > /sys/class/leds/led1_R/delay_on $ echo 1 > /sys/class/leds/led1_R/delay_off ; to turn off LED $ echo 0 > /sys/class/leds/led1_R/brightness [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Kim Kyuwon Signed-off-by: Andrew Morton Signed-off-by: Richard Purdie --- include/linux/leds-bd2802.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) create mode 100644 include/linux/leds-bd2802.h (limited to 'include/linux') diff --git a/include/linux/leds-bd2802.h b/include/linux/leds-bd2802.h new file mode 100644 index 00000000000..42f854a1a19 --- /dev/null +++ b/include/linux/leds-bd2802.h @@ -0,0 +1,26 @@ +/* + * leds-bd2802.h - RGB LED Driver + * + * Copyright (C) 2009 Samsung Electronics + * Kim Kyuwon + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * Datasheet: http://www.rohm.com/products/databook/driver/pdf/bd2802gu-e.pdf + * + */ +#ifndef _LEDS_BD2802_H_ +#define _LEDS_BD2802_H_ + +struct bd2802_led_platform_data{ + int reset_gpio; + u8 rgb_time; +}; + +#define RGB_TIME(slopedown, slopeup, waveform) \ + ((slopedown) << 6 | (slopeup) << 4 | (waveform)) + +#endif /* _LEDS_BD2802_H_ */ + -- cgit v1.2.3 From e3ee703366da3a4ce80f24b47a5df56cd816c5d6 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Mon, 6 Apr 2009 18:12:24 +0200 Subject: i2c: Deprecate client_register and client_unregister methods The new i2c binding model makes the client_register and client_unregister methods of struct i2c_adapter useless, so we can remove them with the rest of the legacy model. Signed-off-by: Jean Delvare --- include/linux/i2c.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index c86c3b07604..00ee11eb909 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -353,8 +353,8 @@ struct i2c_adapter { void *algo_data; /* --- administration stuff. */ - int (*client_register)(struct i2c_client *); - int (*client_unregister)(struct i2c_client *); + int (*client_register)(struct i2c_client *) __deprecated; + int (*client_unregister)(struct i2c_client *) __deprecated; /* data fields that are valid for all devices */ u8 level; /* nesting level for lockdep */ -- cgit v1.2.3 From 7c8ad4aff0699197469327d0e50d1e48f2ccb39b Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Mon, 6 Apr 2009 18:12:25 +0200 Subject: i2c: Delete many unused driver IDs Delete many unused I2C driver IDs. We should be able to get rid of i2c_driver.id pretty soon now. Signed-off-by: Jean Delvare --- include/linux/i2c-id.h | 37 ------------------------------------- 1 file changed, 37 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c-id.h b/include/linux/i2c-id.h index f27604af837..ee9fbc17240 100644 --- a/include/linux/i2c-id.h +++ b/include/linux/i2c-id.h @@ -33,47 +33,10 @@ #define I2C_DRIVERID_MSP3400 1 #define I2C_DRIVERID_TUNER 2 -#define I2C_DRIVERID_TEA6420 5 /* audio matrix switch */ -#define I2C_DRIVERID_TEA6415C 6 /* video matrix switch */ -#define I2C_DRIVERID_TDA9840 7 /* stereo sound processor */ -#define I2C_DRIVERID_SAA7111A 8 /* video input processor */ -#define I2C_DRIVERID_SAA7185B 13 /* video encoder */ -#define I2C_DRIVERID_SAA7110 22 /* video decoder */ -#define I2C_DRIVERID_SAA5249 24 /* SAA5249 and compatibles */ #define I2C_DRIVERID_TDA7432 27 /* Stereo sound processor */ #define I2C_DRIVERID_TVAUDIO 29 /* Generic TV sound driver */ -#define I2C_DRIVERID_TDA9875 32 /* TV sound decoder chip */ -#define I2C_DRIVERID_BT819 40 /* video decoder */ -#define I2C_DRIVERID_BT856 41 /* video encoder */ -#define I2C_DRIVERID_VPX3220 42 /* video decoder+vbi/vtxt */ -#define I2C_DRIVERID_ADV7175 48 /* ADV 7175/7176 video encoder */ -#define I2C_DRIVERID_SAA7114 49 /* video decoder */ -#define I2C_DRIVERID_ADV7170 54 /* video encoder */ -#define I2C_DRIVERID_SAA7191 57 /* video decoder */ -#define I2C_DRIVERID_INDYCAM 58 /* SGI IndyCam */ -#define I2C_DRIVERID_OVCAMCHIP 61 /* OmniVision CMOS image sens. */ -#define I2C_DRIVERID_SAA6752HS 67 /* MPEG2 encoder */ -#define I2C_DRIVERID_TVEEPROM 68 /* TV EEPROM */ -#define I2C_DRIVERID_WM8775 69 /* wm8775 audio processor */ -#define I2C_DRIVERID_CS53L32A 70 /* cs53l32a audio processor */ -#define I2C_DRIVERID_CX25840 71 /* cx2584x video encoder */ -#define I2C_DRIVERID_SAA7127 72 /* saa7127 video encoder */ #define I2C_DRIVERID_SAA711X 73 /* saa711x video encoders */ #define I2C_DRIVERID_INFRARED 75 /* I2C InfraRed on Video boards */ -#define I2C_DRIVERID_TVP5150 76 /* TVP5150 video decoder */ -#define I2C_DRIVERID_WM8739 77 /* wm8739 audio processor */ -#define I2C_DRIVERID_UPD64083 78 /* upd64083 video processor */ -#define I2C_DRIVERID_UPD64031A 79 /* upd64031a video processor */ -#define I2C_DRIVERID_SAA717X 80 /* saa717x video encoder */ -#define I2C_DRIVERID_BT866 85 /* Conexant bt866 video encoder */ -#define I2C_DRIVERID_KS0127 86 /* Samsung ks0127 video decoder */ -#define I2C_DRIVERID_TLV320AIC23B 87 /* TI TLV320AIC23B audio codec */ -#define I2C_DRIVERID_VP27SMPX 93 /* Panasonic VP27s tuner internal MPX */ -#define I2C_DRIVERID_M52790 95 /* Mitsubishi M52790SP/FP AV switch */ -#define I2C_DRIVERID_CS5345 96 /* cs5345 audio processor */ -#define I2C_DRIVERID_AU8522 97 /* Auvitek au8522 */ - -#define I2C_DRIVERID_OV7670 1048 /* Omnivision 7670 camera */ /* * ---- Adapter types ---------------------------------------------------- -- cgit v1.2.3 From abe213d7f6fb87f48f4324320733f666db1bc11b Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Mon, 6 Apr 2009 18:12:25 +0200 Subject: i2c: Delete unused i2c-algo-sgi helper module The i2c-algo-sgi code was merged into the vino driver, so we can delete it now. Signed-off-by: Jean Delvare --- include/linux/i2c-algo-sgi.h | 26 -------------------------- 1 file changed, 26 deletions(-) delete mode 100644 include/linux/i2c-algo-sgi.h (limited to 'include/linux') diff --git a/include/linux/i2c-algo-sgi.h b/include/linux/i2c-algo-sgi.h deleted file mode 100644 index 3b7715024e6..00000000000 --- a/include/linux/i2c-algo-sgi.h +++ /dev/null @@ -1,26 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License version 2 as published by the Free Software Foundation. - * - * Copyright (C) 2003 Ladislav Michl - */ - -#ifndef I2C_ALGO_SGI_H -#define I2C_ALGO_SGI_H 1 - -#include - -struct i2c_algo_sgi_data { - void *data; /* private data for lowlevel routines */ - unsigned (*getctrl)(void *data); - void (*setctrl)(void *data, unsigned val); - unsigned (*rdata)(void *data); - void (*wdata)(void *data, unsigned val); - - int xfer_timeout; - int ack_timeout; -}; - -int i2c_sgi_add_bus(struct i2c_adapter *); - -#endif /* I2C_ALGO_SGI_H */ -- cgit v1.2.3 From f0ad670d7061efad138df19aefe569263c4ea37b Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Mon, 6 Apr 2009 12:00:36 +0300 Subject: nfsd41: define NFSD_DRC_SIZE_SHIFT in set_max_drc Fixes the following compiler error: fs/nfsd/nfssvc.c: In function 'set_max_drc': fs/nfsd/nfssvc.c:240: error: 'NFSD_DRC_SIZE_SHIFT' undeclared CONFIG_NFSD_V4 is not set Reported-by: Alexander Beregalov Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- include/linux/nfsd/nfsd.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfsd/nfsd.h b/include/linux/nfsd/nfsd.h index 0ec4d142c50..2b49d676d0c 100644 --- a/include/linux/nfsd/nfsd.h +++ b/include/linux/nfsd/nfsd.h @@ -333,9 +333,6 @@ extern struct timeval nfssvc_boot; #define NFSD_LEASE_TIME (nfs4_lease_time()) #define NFSD_LAUNDROMAT_MINTIMEOUT 10 /* seconds */ -/* The percent of nr_free_buffer_pages used by the V4.1 server DRC */ -#define NFSD_DRC_SIZE_SHIFT 7 - /* * The following attributes are currently not supported by the NFSv4 server: * ARCHIVE (deprecated anyway) -- cgit v1.2.3 From 04826f43d4f0a4d56423eb8abb9f2ec9987df5b5 Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Mon, 6 Apr 2009 12:00:49 +0300 Subject: nfsd41: define nfsd4_set_statp as noop for !CONFIG_NFSD_V4 Fixes following modpost error: ERROR: "nfsd4_set_statp" [fs/nfsd/nfsd.ko] undefined! Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- include/linux/nfsd/cache.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfsd/cache.h b/include/linux/nfsd/cache.h index a59a2df6d07..5bccaab8105 100644 --- a/include/linux/nfsd/cache.h +++ b/include/linux/nfsd/cache.h @@ -75,6 +75,13 @@ int nfsd_reply_cache_init(void); void nfsd_reply_cache_shutdown(void); int nfsd_cache_lookup(struct svc_rqst *, int); void nfsd_cache_update(struct svc_rqst *, int, __be32 *); + +#ifdef CONFIG_NFSD_V4 void nfsd4_set_statp(struct svc_rqst *rqstp, __be32 *statp); +#else /* CONFIG_NFSD_V4 */ +static inline void nfsd4_set_statp(struct svc_rqst *rqstp, __be32 *statp) +{ +} +#endif /* CONFIG_NFSD_V4 */ #endif /* NFSCACHE_H */ -- cgit v1.2.3 From 46a0fac9438764533245928b78d35fbaa5d7adf4 Mon Sep 17 00:00:00 2001 From: Shawn Bohrer Date: Mon, 6 Apr 2009 17:32:07 +0100 Subject: 8250_pci: add support for National Instruments 843x RS232 devices This implements basic support for all 843x RS232 devices, but does not add DMA support. This means that sustained data transfers at high baud rates may not be possible on multiple ports simultaneously. Signed-off-by: Shawn Bohrer Signed-off-by: Alan Cox Signed-off-by: Linus Torvalds --- include/linux/pci_ids.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 170f8b1f22d..449e7d9d549 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -944,6 +944,20 @@ #define PCI_DEVICE_ID_SUN_TOMATILLO 0xa801 #define PCI_DEVICE_ID_SUN_CASSINI 0xabba +#define PCI_VENDOR_ID_NI 0x1093 +#define PCI_DEVICE_ID_NI_PXI8430_2322 0x7080 +#define PCI_DEVICE_ID_NI_PCI8430_2322 0x70db +#define PCI_DEVICE_ID_NI_PXI8430_2324 0x70dd +#define PCI_DEVICE_ID_NI_PCI8430_2324 0x70df +#define PCI_DEVICE_ID_NI_PXI8430_2328 0x70e2 +#define PCI_DEVICE_ID_NI_PCI8430_2328 0x70e4 +#define PCI_DEVICE_ID_NI_PXI8430_23216 0x70e6 +#define PCI_DEVICE_ID_NI_PCI8430_23216 0x70e7 +#define PCI_DEVICE_ID_NI_PXI8432_2322 0x70e8 +#define PCI_DEVICE_ID_NI_PCI8432_2322 0x70ea +#define PCI_DEVICE_ID_NI_PXI8432_2324 0x70ec +#define PCI_DEVICE_ID_NI_PCI8432_2324 0x70ee + #define PCI_VENDOR_ID_CMD 0x1095 #define PCI_DEVICE_ID_CMD_643 0x0643 #define PCI_DEVICE_ID_CMD_646 0x0646 -- cgit v1.2.3 From 04bf7e745b841619d2f14f2f8b6f2c97f1c6757e Mon Sep 17 00:00:00 2001 From: Will Page Date: Mon, 6 Apr 2009 17:32:15 +0100 Subject: 8250_pci: add support for National Instruments legacy 8420 RS232 boards Signed-off-by: Will Page Signed-off-by: Shawn Bohrer Signed-off-by: Alan Cox Signed-off-by: Linus Torvalds --- include/linux/pci_ids.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 449e7d9d549..ee98cd57088 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -945,6 +945,18 @@ #define PCI_DEVICE_ID_SUN_CASSINI 0xabba #define PCI_VENDOR_ID_NI 0x1093 +#define PCI_DEVICE_ID_NI_PCI2322 0xd130 +#define PCI_DEVICE_ID_NI_PCI2324 0xd140 +#define PCI_DEVICE_ID_NI_PCI2328 0xd150 +#define PCI_DEVICE_ID_NI_PXI8422_2322 0xd190 +#define PCI_DEVICE_ID_NI_PXI8422_2324 0xd1a0 +#define PCI_DEVICE_ID_NI_PXI8420_2322 0xd1d0 +#define PCI_DEVICE_ID_NI_PXI8420_2324 0xd1e0 +#define PCI_DEVICE_ID_NI_PXI8420_2328 0xd1f0 +#define PCI_DEVICE_ID_NI_PXI8420_23216 0xd1f1 +#define PCI_DEVICE_ID_NI_PCI2322I 0xd250 +#define PCI_DEVICE_ID_NI_PCI2324I 0xd270 +#define PCI_DEVICE_ID_NI_PCI23216 0xd2b0 #define PCI_DEVICE_ID_NI_PXI8430_2322 0x7080 #define PCI_DEVICE_ID_NI_PCI8430_2322 0x70db #define PCI_DEVICE_ID_NI_PXI8430_2324 0x70dd -- cgit v1.2.3 From 06e82df015afad2d96d030f76f5e4d13e6dcdfa4 Mon Sep 17 00:00:00 2001 From: Alexander Beregalov Date: Mon, 6 Apr 2009 17:34:34 +0100 Subject: mux: fix build problem Fixes: In file included from drivers/serial/mux.c:37: include/linux/serial_core.h: In function 'uart_handle_sysrq_char': include/linux/serial_core.h:467: error: 'struct uart_port' has no member named 'sysrq' include/linux/serial_core.h:468: error: 'struct uart_port' has no member named 'sysrq' Signed-off-by: Alexander Beregalov Signed-off-by: Alan Cox Signed-off-by: Linus Torvalds --- include/linux/serial_core.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index df9245c7bd3..83e4b3ff9cd 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -277,7 +277,7 @@ struct uart_port { struct uart_icount icount; /* statistics */ struct console *cons; /* struct console, if any */ -#ifdef CONFIG_SERIAL_CORE_CONSOLE +#if defined(CONFIG_SERIAL_CORE_CONSOLE) || defined(SUPPORT_SYSRQ) unsigned long sysrq; /* sysrq timeout */ #endif -- cgit v1.2.3