From 5920dadfb4aec6c1372c5570e71bcd3b4837e63c Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 15 Jul 2009 17:11:41 +0900 Subject: libata: accept late unlocking of HPA On certain configurations, HPA isn't or can't be unlocked during probing but it somehow ends up unlocked afterwards. In the following thread, the problem can be reliably reproduced after resuming from STR. The BIOS turns on HPA during boot but forgets to do it during resume. http://thread.gmane.org/gmane.linux.kernel/858310 This patch updates libata revalidation such that it considers native n_sectors. If the device size has increased to match native n_sectors, it's assumed that HPA has been unlocked involuntarily and the device is recognized as the same one. This should be fairly safe while nicely working around the problem. Signed-off-by: Tejun Heo Reported-by: Christof Warlich Signed-off-by: Jeff Garzik --- include/linux/libata.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 79b6d7fd4ac..e5b6e33c657 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -589,6 +589,7 @@ struct ata_device { #endif /* n_sector is CLEAR_BEGIN, read comment above CLEAR_BEGIN */ u64 n_sectors; /* size of device, if ATA */ + u64 n_native_sectors; /* native size, if ATA */ unsigned int class; /* ATA_DEV_xxx */ unsigned long unpark_deadline; -- cgit v1.2.3 From dddac6a7b445de95515f64fdf82fe5dc36c02f26 Mon Sep 17 00:00:00 2001 From: Alan Jenkins Date: Wed, 29 Jul 2009 21:07:55 +0200 Subject: PM / Hibernate: Replace bdget call with simple atomic_inc of i_count Create bdgrab(). This function copies an existing reference to a block_device. It is safe to call from any context. Hibernation code wishes to copy a reference to the active swap device. Right now it calls bdget() under a spinlock, but this is wrong because bdget() can sleep. It doesn't need a full bdget() because we already hold a reference to active swap devices (and the spinlock protects against swapoff). Fixes http://bugzilla.kernel.org/show_bug.cgi?id=13827 Signed-off-by: Alan Jenkins Signed-off-by: Rafael J. Wysocki --- 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 0872372184f..a36ffa5a77a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1946,6 +1946,7 @@ extern void putname(const char *name); extern int register_blkdev(unsigned int, const char *); extern void unregister_blkdev(unsigned int, const char *); extern struct block_device *bdget(dev_t); +extern struct block_device *bdgrab(struct block_device *bdev); extern void bd_set_size(struct block_device *, loff_t size); extern void bd_forget(struct inode *inode); extern void bdput(struct block_device *); -- cgit v1.2.3 From e043e42bdb66885b3ac10d27a01ccb9972e2b0a3 Mon Sep 17 00:00:00 2001 From: OGAWA Hirofumi Date: Wed, 29 Jul 2009 12:15:56 -0700 Subject: pty: avoid forcing 'low_latency' tty flag We really don't want to mark the pty as a low-latency device, because as Alan points out, the ->write method can be called from an IRQ (ppp?), and that means we can't use ->low_latency=1 as we take mutexes in the low_latency case. So rather than using low_latency to force the written data to be pushed to the ldisc handling at 'write()' time, just make the reader side (or the poll function) do the flush when it checks whether there is data to be had. This also fixes the problem with lost data in an emacs compile buffer (bugzilla 13815), and we can thus revert the low_latency pty hack (commit 3a54297478e6578f96fd54bf4daa1751130aca86: "pty: quickfix for the pty ENXIO timing problems"). Signed-off-by: OGAWA Hirofumi Tested-by: Aneesh Kumar K.V [ Modified to do the tty_flush_to_ldisc() inside input_available_p() so that it triggers for both read and poll() - Linus] Signed-off-by: Linus Torvalds --- include/linux/tty.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 1488d8c81aa..e8c6c9136c9 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -394,6 +394,7 @@ extern void __do_SAK(struct tty_struct *tty); extern void disassociate_ctty(int priv); extern void no_tty(void); extern void tty_flip_buffer_push(struct tty_struct *tty); +extern void tty_flush_to_ldisc(struct tty_struct *tty); extern void tty_buffer_free_all(struct tty_struct *tty); extern void tty_buffer_flush(struct tty_struct *tty); extern void tty_buffer_init(struct tty_struct *tty); -- cgit v1.2.3 From 096b7fe012d66ed55e98bc8022405ede0cc80e96 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Wed, 29 Jul 2009 15:04:04 -0700 Subject: cgroups: fix pid namespace bug The bug was introduced by commit cc31edceee04a7b87f2be48f9489ebb72d264844 ("cgroups: convert tasks file to use a seq_file with shared pid array"). We cache a pid array for all threads that are opening the same "tasks" file, but the pids in the array are always from the namespace of the last process that opened the file, so all other threads will read pids from that namespace instead of their own namespaces. To fix it, we maintain a list of pid arrays, which is keyed by pid_ns. The list will be of length 1 at most time. Reported-by: Paul Menage Idea-by: Paul Menage Signed-off-by: Li Zefan Reviewed-by: Serge Hallyn Cc: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cgroup.h | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 665fa70e409..20411d2876f 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -179,14 +179,11 @@ struct cgroup { */ struct list_head release_list; - /* pids_mutex protects the fields below */ + /* pids_mutex protects pids_list and cached pid arrays. */ struct rw_semaphore pids_mutex; - /* Array of process ids in the cgroup */ - pid_t *tasks_pids; - /* How many files are using the current tasks_pids array */ - int pids_use_count; - /* Length of the current tasks_pids array */ - int pids_length; + + /* Linked list of struct cgroup_pids */ + struct list_head pids_list; /* For RCU-protected deletion */ struct rcu_head rcu_head; -- cgit v1.2.3 From 887032670d47366a8c8f25396ea7c14b7b2cc620 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Wed, 29 Jul 2009 15:04:06 -0700 Subject: cgroup avoid permanent sleep at rmdir After commit ec64f51545fffbc4cb968f0cea56341a4b07e85a ("cgroup: fix frequent -EBUSY at rmdir"), cgroup's rmdir (especially against memcg) doesn't return -EBUSY by temporary ref counts. That commit expects all refs after pre_destroy() is temporary but...it wasn't. Then, rmdir can wait permanently. This patch tries to fix that and change followings. - set CGRP_WAIT_ON_RMDIR flag before pre_destroy(). - clear CGRP_WAIT_ON_RMDIR flag when the subsys finds racy case. if there are sleeping ones, wakes them up. - rmdir() sleeps only when CGRP_WAIT_ON_RMDIR flag is set. Tested-by: Daisuke Nishimura Reported-by: Daisuke Nishimura Reviewed-by: Paul Menage Acked-by: Balbir Sigh Signed-off-by: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cgroup.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 20411d2876f..90bba9e6228 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -362,6 +362,23 @@ int cgroup_task_count(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); +/* + * When the subsys has to access css and may add permanent refcnt to css, + * it should take care of racy conditions with rmdir(). Following set of + * functions, is for stop/restart rmdir if necessary. + * Because these will call css_get/put, "css" should be alive css. + * + * cgroup_exclude_rmdir(); + * ...do some jobs which may access arbitrary empty cgroup + * cgroup_release_and_wakeup_rmdir(); + * + * When someone removes a cgroup while cgroup_exclude_rmdir() holds it, + * it sleeps and cgroup_release_and_wakeup_rmdir() will wake him up. + */ + +void cgroup_exclude_rmdir(struct cgroup_subsys_state *css); +void cgroup_release_and_wakeup_rmdir(struct cgroup_subsys_state *css); + /* * Control Group subsystem type. * See Documentation/cgroups/cgroups.txt for details -- cgit v1.2.3 From f5a55efa140f5e9c9dd0f398fef54f20cdb74ec9 Mon Sep 17 00:00:00 2001 From: Dave Jones Date: Wed, 29 Jul 2009 15:04:12 -0700 Subject: pps.h needs Found with make headers_check /usr/include/linux/pps.h:52: found __[us]{8,16,32,64} type without #include Signed-off-by: Dave Jones Cc: Rodolfo Giometti Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pps.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pps.h b/include/linux/pps.h index cfe5c7214ec..0194ab06177 100644 --- a/include/linux/pps.h +++ b/include/linux/pps.h @@ -22,6 +22,8 @@ #ifndef _PPS_H_ #define _PPS_H_ +#include + #define PPS_VERSION "5.3.6" #define PPS_MAX_SOURCES 16 /* should be enough... */ -- cgit v1.2.3 From 534acc057b5a08ec33fa57cdd2f5a09ef124e7f2 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Wed, 29 Jul 2009 15:04:18 -0700 Subject: lib: flexible array implementation Once a structure goes over PAGE_SIZE*2, we see occasional allocation failures. Some people have chosen to switch over to things like vmalloc() that will let them keep array-like access to such a large structures. But, vmalloc() has plenty of downsides. Here's an alternative. I think it's what Andrew was suggesting here: http://lkml.org/lkml/2009/7/2/518 I call it a flexible array. It does all of its work in PAGE_SIZE bits, so never does an order>0 allocation. The base level has PAGE_SIZE-2*sizeof(int) bytes of storage for pointers to the second level. So, with a 32-bit arch, you get about 4MB (4183112 bytes) of total storage when the objects pack nicely into a page. It is half that on 64-bit because the pointers are twice the size. There's a table detailing this in the code. There are kerneldocs for the functions, but here's an overview: flex_array_alloc() - dynamically allocate a base structure flex_array_free() - free the array and all of the second-level pages flex_array_free_parts() - free the second-level pages, but not the base (for static bases) flex_array_put() - copy into the array at the given index flex_array_get() - copy out of the array at the given index flex_array_prealloc() - preallocate the second-level pages between the given indexes to guarantee no allocs will occur at put() time. We could also potentially just pass the "element_size" into each of the API functions instead of storing it internally. That would get us one more base pointer on 32-bit. I've been testing this by running it in userspace. The header and patch that I've been using are here, as well as the little script I'm using to generate the size table which goes in the kerneldocs. http://sr71.net/~dave/linux/flexarray/ [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Dave Hansen Reviewed-by: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/flex_array.h | 47 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 47 insertions(+) create mode 100644 include/linux/flex_array.h (limited to 'include/linux') diff --git a/include/linux/flex_array.h b/include/linux/flex_array.h new file mode 100644 index 00000000000..23c1ec79a31 --- /dev/null +++ b/include/linux/flex_array.h @@ -0,0 +1,47 @@ +#ifndef _FLEX_ARRAY_H +#define _FLEX_ARRAY_H + +#include +#include + +#define FLEX_ARRAY_PART_SIZE PAGE_SIZE +#define FLEX_ARRAY_BASE_SIZE PAGE_SIZE + +struct flex_array_part; + +/* + * This is meant to replace cases where an array-like + * structure has gotten too big to fit into kmalloc() + * and the developer is getting tempted to use + * vmalloc(). + */ + +struct flex_array { + union { + struct { + int element_size; + int total_nr_elements; + struct flex_array_part *parts[0]; + }; + /* + * This little trick makes sure that + * sizeof(flex_array) == PAGE_SIZE + */ + char padding[FLEX_ARRAY_BASE_SIZE]; + }; +}; + +#define FLEX_ARRAY_INIT(size, total) { { {\ + .element_size = (size), \ + .total_nr_elements = (total), \ +} } } + +struct flex_array *flex_array_alloc(int element_size, int total, gfp_t flags); +int flex_array_prealloc(struct flex_array *fa, int start, int end, gfp_t flags); +void flex_array_free(struct flex_array *fa); +void flex_array_free_parts(struct flex_array *fa); +int flex_array_put(struct flex_array *fa, int element_nr, void *src, + gfp_t flags); +void *flex_array_get(struct flex_array *fa, int element_nr); + +#endif /* _FLEX_ARRAY_H */ -- cgit v1.2.3 From 812ed032cdc8138b7546eecc996879756b92d801 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Wed, 29 Jul 2009 15:04:19 -0700 Subject: uio: mark uio.h functions __KERNEL__ only To avoid userspace build failures such as: .../linux/uio.h:37: error: expected `=', `,', `;', `asm' or `__attribute__' before `iov_length' .../linux/uio.h:47: error: expected declaration specifiers or `...' before `size_t' move uio functions inside a __KERNEL__ block. Signed-off-by: Jiri Slaby Acked-by: Sam Ravnborg Cc: Alexander Viro Cc: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/uio.h | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index b7fe13883bd..98c114323a8 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -19,15 +19,6 @@ struct iovec __kernel_size_t iov_len; /* Must be size_t (1003.1g) */ }; -#ifdef __KERNEL__ - -struct kvec { - void *iov_base; /* and that should *never* hold a userland pointer */ - size_t iov_len; -}; - -#endif - /* * UIO_MAXIOV shall be at least 16 1003.1g (5.4.1.1) */ @@ -35,6 +26,13 @@ struct kvec { #define UIO_FASTIOV 8 #define UIO_MAXIOV 1024 +#ifdef __KERNEL__ + +struct kvec { + void *iov_base; /* and that should *never* hold a userland pointer */ + size_t iov_len; +}; + /* * Total number of bytes covered by an iovec. * @@ -53,5 +51,6 @@ static inline size_t iov_length(const struct iovec *iov, unsigned long nr_segs) } unsigned long iov_shorten(struct iovec *iov, unsigned long nr_segs, size_t to); +#endif #endif -- cgit v1.2.3