From e74e396204bfcb67570ba4517b08f5918e69afea Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 30 Mar 2009 19:07:44 +0900 Subject: percpu: use dynamic percpu allocator as the default percpu allocator This patch makes most !CONFIG_HAVE_SETUP_PER_CPU_AREA archs use dynamic percpu allocator. The first chunk is allocated using embedding helper and 8k is reserved for modules. This ensures that the new allocator behaves almost identically to the original allocator as long as static percpu variables are concerned, so it shouldn't introduce much breakage. s390 and alpha use custom SHIFT_PERCPU_PTR() to work around addressing range limit the addressing model imposes. Unfortunately, this breaks if the address is specified using a variable, so for now, the two archs aren't converted. The following architectures are affected by this change. * sh * arm * cris * mips * sparc(32) * blackfin * avr32 * parisc (broken, under investigation) * m32r * powerpc(32) As this change makes the dynamic allocator the default one, CONFIG_HAVE_DYNAMIC_PER_CPU_AREA is replaced with its invert - CONFIG_HAVE_LEGACY_PER_CPU_AREA, which is added to yet-to-be converted archs. These archs implement their own setup_per_cpu_areas() and the conversion is not trivial. * powerpc(64) * sparc(64) * ia64 * alpha * s390 Boot and batch alloc/free tests on x86_32 with debug code (x86_32 doesn't use default first chunk initialization). Compile tested on sparc(32), powerpc(32), arm and alpha. Kyle McMartin reported that this change breaks parisc. The problem is still under investigation and he is okay with pushing this patch forward and fixing parisc later. [ Impact: use dynamic allocator for most archs w/o custom percpu setup ] Signed-off-by: Tejun Heo Acked-by: Rusty Russell Acked-by: David S. Miller Acked-by: Benjamin Herrenschmidt Acked-by: Martin Schwidefsky Reviewed-by: Christoph Lameter Cc: Paul Mundt Cc: Russell King Cc: Mikael Starvik Cc: Ralf Baechle Cc: Bryan Wu Cc: Kyle McMartin Cc: Matthew Wilcox Cc: Grant Grundler Cc: Hirokazu Takata Cc: Richard Henderson Cc: Ivan Kokshaysky Cc: Heiko Carstens Cc: Ingo Molnar --- include/linux/percpu.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 26fd9d12f05..e5000343dd6 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -34,7 +34,7 @@ #ifdef CONFIG_SMP -#ifdef CONFIG_HAVE_DYNAMIC_PER_CPU_AREA +#ifndef CONFIG_HAVE_LEGACY_PER_CPU_AREA /* minimum unit size, also is the maximum supported allocation size */ #define PCPU_MIN_UNIT_SIZE PFN_ALIGN(64 << 10) @@ -80,7 +80,7 @@ extern ssize_t __init pcpu_embed_first_chunk( extern void *__alloc_reserved_percpu(size_t size, size_t align); -#else /* CONFIG_HAVE_DYNAMIC_PER_CPU_AREA */ +#else /* CONFIG_HAVE_LEGACY_PER_CPU_AREA */ struct percpu_data { void *ptrs[1]; @@ -99,11 +99,15 @@ struct percpu_data { (__typeof__(ptr))__p->ptrs[(cpu)]; \ }) -#endif /* CONFIG_HAVE_DYNAMIC_PER_CPU_AREA */ +#endif /* CONFIG_HAVE_LEGACY_PER_CPU_AREA */ extern void *__alloc_percpu(size_t size, size_t align); extern void free_percpu(void *__pdata); +#ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA +extern void __init setup_per_cpu_areas(void); +#endif + #else /* CONFIG_SMP */ #define per_cpu_ptr(ptr, cpu) ({ (void)(cpu); (ptr); }) @@ -124,6 +128,8 @@ static inline void free_percpu(void *p) kfree(p); } +static inline void __init setup_per_cpu_areas(void) { } + #endif /* CONFIG_SMP */ #define alloc_percpu(type) (type *)__alloc_percpu(sizeof(type), \ -- cgit v1.2.3 From 7c756e6e19e71f0327760d8955f7077118ebb2b1 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 24 Jun 2009 15:13:50 +0900 Subject: percpu: implement optional weak percpu definitions Some archs (alpha and s390) need to use weak definitions for percpu variables in modules so that the compiler generates external references for them. This patch implements weak percpu definitions which arch can enable by defining ARCH_NEEDS_WEAK_PER_CPU in arch percpu header file. This weak definition adds the following two restrictions on percpu variable definitions. 1. percpu symbols must be unique whether static or not 2. percpu variables can't be defined inside a function To ensure that these restrictions are observed in generic code, config option DEBUG_FORCE_WEAK_PER_CPU enables weak percpu definitions for all cases. This patch is inspired by Ivan Kokshaysky's alpha percpu patch. [ Impact: stricter rules for percpu variables, one more debug config option ] Signed-off-by: Tejun Heo Cc: Ingo Molnar Cc: David Howells Cc: Ivan Kokshaysky --- include/linux/percpu-defs.h | 65 ++++++++++++++++++++++++++++++++++++++------- 1 file changed, 56 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h index 8f921d74f49..cf32838ad0f 100644 --- a/include/linux/percpu-defs.h +++ b/include/linux/percpu-defs.h @@ -10,21 +10,68 @@ /* * Base implementations of per-CPU variable declarations and definitions, where * the section in which the variable is to be placed is provided by the - * 'section' argument. This may be used to affect the parameters governing the + * 'sec' argument. This may be used to affect the parameters governing the * variable's storage. * * NOTE! The sections for the DECLARE and for the DEFINE must match, lest * linkage errors occur due the compiler generating the wrong code to access * that section. */ -#define DECLARE_PER_CPU_SECTION(type, name, section) \ - extern \ - __attribute__((__section__(PER_CPU_BASE_SECTION section))) \ - PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name - -#define DEFINE_PER_CPU_SECTION(type, name, section) \ - __attribute__((__section__(PER_CPU_BASE_SECTION section))) \ - PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name +#define __PCPU_ATTRS(sec) \ + __attribute__((section(PER_CPU_BASE_SECTION sec))) \ + PER_CPU_ATTRIBUTES + +#define __PCPU_DUMMY_ATTRS \ + __attribute__((section(".discard"), unused)) + +/* + * s390 and alpha modules require percpu variables to be defined as + * weak to force the compiler to generate GOT based external + * references for them. This is necessary because percpu sections + * will be located outside of the usually addressable area. + * + * This definition puts the following two extra restrictions when + * defining percpu variables. + * + * 1. The symbol must be globally unique, even the static ones. + * 2. Static percpu variables cannot be defined inside a function. + * + * Archs which need weak percpu definitions should define + * ARCH_NEEDS_WEAK_PER_CPU in asm/percpu.h when necessary. + * + * To ensure that the generic code observes the above two + * restrictions, if CONFIG_DEBUG_FORCE_WEAK_PER_CPU is set weak + * definition is used for all cases. + */ +#if defined(ARCH_NEEDS_WEAK_PER_CPU) || defined(CONFIG_DEBUG_FORCE_WEAK_PER_CPU) +/* + * __pcpu_scope_* dummy variable is used to enforce scope. It + * receives the static modifier when it's used in front of + * DEFINE_PER_CPU() and will trigger build failure if + * DECLARE_PER_CPU() is used for the same variable. + * + * __pcpu_unique_* dummy variable is used to enforce symbol uniqueness + * such that hidden weak symbol collision, which will cause unrelated + * variables to share the same address, can be detected during build. + */ +#define DECLARE_PER_CPU_SECTION(type, name, sec) \ + extern __PCPU_DUMMY_ATTRS char __pcpu_scope_##name; \ + extern __PCPU_ATTRS(sec) __weak __typeof__(type) per_cpu__##name + +#define DEFINE_PER_CPU_SECTION(type, name, sec) \ + __PCPU_DUMMY_ATTRS char __pcpu_scope_##name; \ + __PCPU_DUMMY_ATTRS char __pcpu_unique_##name; \ + __PCPU_ATTRS(sec) __weak __typeof__(type) per_cpu__##name +#else +/* + * Normal declaration and definition macros. + */ +#define DECLARE_PER_CPU_SECTION(type, name, sec) \ + extern __PCPU_ATTRS(sec) __typeof__(type) per_cpu__##name + +#define DEFINE_PER_CPU_SECTION(type, name, sec) \ + __PCPU_ATTRS(sec) __typeof__(type) per_cpu__##name +#endif /* * Variant on the per-CPU variable declaration/definition theme used for -- cgit v1.2.3 From 1a8dd307cc0a2119be4e578c517795464e6dabba Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 29 Jun 2009 17:45:39 +0900 Subject: percpu: use __weak only in the definition of weak percpu variables __weak is necessary only for definition and might even not work in declaration. Drop it from declaration. This change was suggested by Ivan Kokshaysky. Signed-off-by: Tejun Heo Acked-by: Ivan Kokshaysky --- include/linux/percpu-defs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h index cf32838ad0f..9b7a53cc16e 100644 --- a/include/linux/percpu-defs.h +++ b/include/linux/percpu-defs.h @@ -56,7 +56,7 @@ */ #define DECLARE_PER_CPU_SECTION(type, name, sec) \ extern __PCPU_DUMMY_ATTRS char __pcpu_scope_##name; \ - extern __PCPU_ATTRS(sec) __weak __typeof__(type) per_cpu__##name + extern __PCPU_ATTRS(sec) __typeof__(type) per_cpu__##name #define DEFINE_PER_CPU_SECTION(type, name, sec) \ __PCPU_DUMMY_ATTRS char __pcpu_scope_##name; \ -- cgit v1.2.3 From 788e5abc5441e9046dd91c995c6f1f75bbd144bf Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sat, 4 Jul 2009 08:10:58 +0900 Subject: percpu: drop @unit_size from embed first chunk allocator The only extra feature @unit_size provides is making dead space at the end of the first chunk which doesn't have any valid usecase. Drop the parameter. This will increase consistency with generalized 4k allocator. James Bottomley spotted missing conversion for the default setup_per_cpu_areas() which caused build breakage on all arcsh which use it. [ Impact: drop unused code path ] Signed-off-by: Tejun Heo Cc: James Bottomley Cc: Ingo Molnar --- 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 e5000343dd6..83bff053bd1 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -69,7 +69,7 @@ extern size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_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); + ssize_t dyn_size); /* * Use this to get to a cpu's version of the per-cpu object -- cgit v1.2.3 From d4b95f80399471e4bce5e992700ff7f06ef91f6a Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sat, 4 Jul 2009 08:10:59 +0900 Subject: x86,percpu: generalize 4k first chunk allocator Generalize and move x86 setup_pcpu_4k() into pcpu_4k_first_chunk(). setup_pcpu_4k() now is a simple wrapper around the generalized version. Other than taking size parameters and using arch supplied callbacks to allocate/free memory, pcpu_4k_first_chunk() is identical to the original implementation. This simplifies arch code and will help converting more archs to dynamic percpu allocator. While at it, s/pcpu_populate_pte_fn_t/pcpu_fc_populate_pte_fn_t/ for consistency. [ Impact: code reorganization and generalization ] Signed-off-by: Tejun Heo Cc: Ingo Molnar --- include/linux/percpu.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 83bff053bd1..41b5bfab419 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -59,18 +59,26 @@ extern void *pcpu_base_addr; typedef struct page * (*pcpu_get_page_fn_t)(unsigned int cpu, int pageno); -typedef void (*pcpu_populate_pte_fn_t)(unsigned long addr); +typedef void * (*pcpu_fc_alloc_fn_t)(unsigned int cpu, size_t size); +typedef void (*pcpu_fc_free_fn_t)(void *ptr, size_t size); +typedef void (*pcpu_fc_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 dyn_size, ssize_t unit_size, void *base_addr, - pcpu_populate_pte_fn_t populate_pte_fn); + pcpu_fc_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); +extern ssize_t __init pcpu_4k_first_chunk( + size_t static_size, size_t reserved_size, + pcpu_fc_alloc_fn_t alloc_fn, + pcpu_fc_free_fn_t free_fn, + pcpu_fc_populate_pte_fn_t populate_pte_fn); + /* * 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 8c4bfc6e8801616ab2e01c38140b2159b388d2ff Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sat, 4 Jul 2009 08:10:59 +0900 Subject: x86,percpu: generalize lpage first chunk allocator Generalize and move x86 setup_pcpu_lpage() into pcpu_lpage_first_chunk(). setup_pcpu_lpage() now is a simple wrapper around the generalized version. Other than taking size parameters and using arch supplied callbacks to allocate/free/map memory, pcpu_lpage_first_chunk() is identical to the original implementation. This simplifies arch code and will help converting more archs to dynamic percpu allocator. While at it, factor out pcpu_calc_fc_sizes() which is common to pcpu_embed_first_chunk() and pcpu_lpage_first_chunk(). [ Impact: code reorganization and generalization ] Signed-off-by: Tejun Heo Cc: Ingo Molnar --- include/linux/percpu.h | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'include/linux') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 41b5bfab419..9f6bfd7d4b9 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -62,6 +62,7 @@ typedef struct page * (*pcpu_get_page_fn_t)(unsigned int cpu, int pageno); typedef void * (*pcpu_fc_alloc_fn_t)(unsigned int cpu, size_t size); typedef void (*pcpu_fc_free_fn_t)(void *ptr, size_t size); typedef void (*pcpu_fc_populate_pte_fn_t)(unsigned long addr); +typedef void (*pcpu_fc_map_fn_t)(void *ptr, size_t size, void *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, @@ -79,6 +80,32 @@ extern ssize_t __init pcpu_4k_first_chunk( pcpu_fc_free_fn_t free_fn, pcpu_fc_populate_pte_fn_t populate_pte_fn); +#ifdef CONFIG_NEED_MULTIPLE_NODES +extern ssize_t __init pcpu_lpage_first_chunk( + size_t static_size, size_t reserved_size, + ssize_t dyn_size, size_t lpage_size, + pcpu_fc_alloc_fn_t alloc_fn, + pcpu_fc_free_fn_t free_fn, + pcpu_fc_map_fn_t map_fn); + +extern void *pcpu_lpage_remapped(void *kaddr); +#else +static inline ssize_t __init pcpu_lpage_first_chunk( + size_t static_size, size_t reserved_size, + ssize_t dyn_size, size_t lpage_size, + pcpu_fc_alloc_fn_t alloc_fn, + pcpu_fc_free_fn_t free_fn, + pcpu_fc_map_fn_t map_fn) +{ + return -EINVAL; +} + +static inline void *pcpu_lpage_remapped(void *kaddr) +{ + return NULL; +} +#endif + /* * 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 38a6be525460f52ac6f2de1c3f73c5615a8853cd Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sat, 4 Jul 2009 08:10:59 +0900 Subject: percpu: simplify pcpu_setup_first_chunk() Now that all first chunk allocator helpers allocate and map the first chunk themselves, there's no need to have optional default alloc/map in pcpu_setup_first_chunk(). Drop @populate_pte_fn and only leave @dyn_size optional and make all other params mandatory. This makes it much easier to follow what pcpu_setup_first_chunk() is doing and what actual differences tweaking each parameter results in. [ Impact: drop unused code path ] Signed-off-by: Tejun Heo Cc: Ingo Molnar --- include/linux/percpu.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 9f6bfd7d4b9..ec64357e176 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -66,9 +66,8 @@ typedef void (*pcpu_fc_map_fn_t)(void *ptr, size_t size, void *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 dyn_size, ssize_t unit_size, - void *base_addr, - pcpu_fc_populate_pte_fn_t populate_pte_fn); + ssize_t dyn_size, size_t unit_size, + void *base_addr); extern ssize_t __init pcpu_embed_first_chunk( size_t static_size, size_t reserved_size, -- cgit v1.2.3 From ce3141a277ff6cc37e51008b8888dc2cb7456ef1 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sat, 4 Jul 2009 08:11:00 +0900 Subject: percpu: drop pcpu_chunk->page[] percpu core doesn't need to tack all the allocated pages. It needs to know whether certain pages are populated and a way to reverse map address to page when freeing. This patch drops pcpu_chunk->page[] and use populated bitmap and vmalloc_to_page() lookup instead. Using vmalloc_to_page() exclusively is also possible but complicates first chunk handling, inflates cache footprint and prevents non-standard memory allocation for percpu memory. pcpu_chunk->page[] was used to track each page's allocation and allowed asymmetric population which happens during failure path; however, with single bitmap for all units, this is no longer possible. Bite the bullet and rewrite (de)populate functions so that things are done in clearly separated steps such that asymmetric population doesn't happen. This makes the (de)population process much more modular and will also ease implementing non-standard memory usage in the future (e.g. large pages). This makes @get_page_fn parameter to pcpu_setup_first_chunk() unnecessary. The parameter is dropped and all first chunk helpers are updated accordingly. Please note that despite the volume most changes to first chunk helpers are symbol renames for variables which don't need to be referenced outside of the helper anymore. This change reduces memory usage and cache footprint of pcpu_chunk. Now only #unit_pages bits are necessary per chunk. [ Impact: reduced memory usage and cache footprint for bookkeeping ] Signed-off-by: Tejun Heo Cc: Ingo Molnar Cc: David Miller --- include/linux/percpu.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index ec64357e176..63c8b7a23e6 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -58,13 +58,12 @@ extern void *pcpu_base_addr; -typedef struct page * (*pcpu_get_page_fn_t)(unsigned int cpu, int pageno); typedef void * (*pcpu_fc_alloc_fn_t)(unsigned int cpu, size_t size); typedef void (*pcpu_fc_free_fn_t)(void *ptr, size_t size); typedef void (*pcpu_fc_populate_pte_fn_t)(unsigned long addr); typedef void (*pcpu_fc_map_fn_t)(void *ptr, size_t size, void *addr); -extern size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn, +extern size_t __init pcpu_setup_first_chunk( size_t static_size, size_t reserved_size, ssize_t dyn_size, size_t unit_size, void *base_addr); -- cgit v1.2.3 From 2f39e637ea240efb74cf807d31c93a71a0b89174 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sat, 4 Jul 2009 08:11:00 +0900 Subject: percpu: allow non-linear / sparse cpu -> unit mapping Currently cpu and unit are always identity mapped. To allow more efficient large page support on NUMA and lazy allocation for possible but offline cpus, cpu -> unit mapping needs to be non-linear and/or sparse. This can be easily implemented by adding a cpu -> unit mapping array and using it whenever looking up the matching unit for a cpu. The only unusal conversion is in pcpu_chunk_addr_search(). The passed in address is unit0 based and unit0 might not be in use so it needs to be converted to address of an in-use unit. This is easily done by adding the unit offset for the current processor. [ Impact: allows non-linear/sparse cpu -> unit mapping, no visible change yet ] Signed-off-by: Tejun Heo Cc: Ingo Molnar Cc: David Miller --- include/linux/percpu.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 63c8b7a23e6..1e0e8878dc2 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -57,6 +57,7 @@ #endif extern void *pcpu_base_addr; +extern const int *pcpu_unit_map; typedef void * (*pcpu_fc_alloc_fn_t)(unsigned int cpu, size_t size); typedef void (*pcpu_fc_free_fn_t)(void *ptr, size_t size); @@ -66,7 +67,7 @@ typedef void (*pcpu_fc_map_fn_t)(void *ptr, size_t size, void *addr); extern size_t __init pcpu_setup_first_chunk( size_t static_size, size_t reserved_size, ssize_t dyn_size, size_t unit_size, - void *base_addr); + void *base_addr, const int *unit_map); extern ssize_t __init pcpu_embed_first_chunk( size_t static_size, size_t reserved_size, -- cgit v1.2.3 From a530b7958612bafe2027e21359083dba84f0b3b4 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sat, 4 Jul 2009 08:11:00 +0900 Subject: percpu: teach large page allocator about NUMA Large page first chunk allocator is primarily used for NUMA machines; however, its NUMA handling is extremely simplistic. Regardless of their proximity, each cpu is put into separate large page just to return most of the allocated space back wasting large amount of vmalloc space and increasing cache footprint. This patch teachs NUMA details to large page allocator. Given processor proximity information, pcpu_lpage_build_unit_map() will find fitting cpu -> unit mapping in which cpus in LOCAL_DISTANCE share the same large page and not too much virtual address space is wasted. This greatly reduces the unit and thus chunk size and wastes much less address space for the first chunk. For example, on 4/4 NUMA machine, the original code occupied 16MB of virtual space for the first chunk while the new code only uses 4MB - one 2MB page for each node. [ Impact: much better space efficiency on NUMA machines ] Signed-off-by: Tejun Heo Cc: Ingo Molnar Cc: Jan Beulich Cc: Andi Kleen Cc: David Miller --- include/linux/percpu.h | 24 ++++++++++++++++++++++-- 1 file changed, 22 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 1e0e8878dc2..8ce91af4aa1 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -62,6 +62,7 @@ extern const int *pcpu_unit_map; typedef void * (*pcpu_fc_alloc_fn_t)(unsigned int cpu, size_t size); typedef void (*pcpu_fc_free_fn_t)(void *ptr, size_t size); typedef void (*pcpu_fc_populate_pte_fn_t)(unsigned long addr); +typedef int (pcpu_fc_cpu_distance_fn_t)(unsigned int from, unsigned int to); typedef void (*pcpu_fc_map_fn_t)(void *ptr, size_t size, void *addr); extern size_t __init pcpu_setup_first_chunk( @@ -80,18 +81,37 @@ extern ssize_t __init pcpu_4k_first_chunk( pcpu_fc_populate_pte_fn_t populate_pte_fn); #ifdef CONFIG_NEED_MULTIPLE_NODES +extern int __init pcpu_lpage_build_unit_map( + size_t static_size, size_t reserved_size, + ssize_t *dyn_sizep, size_t *unit_sizep, + size_t lpage_size, int *unit_map, + pcpu_fc_cpu_distance_fn_t cpu_distance_fn); + extern ssize_t __init pcpu_lpage_first_chunk( size_t static_size, size_t reserved_size, - ssize_t dyn_size, size_t lpage_size, + size_t dyn_size, size_t unit_size, + size_t lpage_size, const int *unit_map, + int nr_units, pcpu_fc_alloc_fn_t alloc_fn, pcpu_fc_free_fn_t free_fn, pcpu_fc_map_fn_t map_fn); extern void *pcpu_lpage_remapped(void *kaddr); #else +static inline int pcpu_lpage_build_unit_map( + size_t static_size, size_t reserved_size, + ssize_t *dyn_sizep, size_t *unit_sizep, + size_t lpage_size, int *unit_map, + pcpu_fc_cpu_distance_fn_t cpu_distance_fn) +{ + return -EINVAL; +} + static inline ssize_t __init pcpu_lpage_first_chunk( size_t static_size, size_t reserved_size, - ssize_t dyn_size, size_t lpage_size, + size_t dyn_size, size_t unit_size, + size_t lpage_size, const int *unit_map, + int nr_units, pcpu_fc_alloc_fn_t alloc_fn, pcpu_fc_free_fn_t free_fn, pcpu_fc_map_fn_t map_fn) -- cgit v1.2.3 From a76761b621bcd8336065c4fe3a74f046858bc34c Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 15 Jul 2009 23:35:14 +0900 Subject: percpu: add dummy pcpu_lpage_remapped() for !CONFIG_SMP !CONFIG_SMP was missing pcpu_lpage_remapped() definition causing build failure. Add dummy implementation. This was discovered by linux-next testing. Signed-off-by: Tejun Heo Cc: Randy Dunlap Cc: Kamalesh Babulal Cc: Stephen Rothwell --- include/linux/percpu.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 8ce91af4aa1..e134c822963 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -184,6 +184,11 @@ static inline void free_percpu(void *p) static inline void __init setup_per_cpu_areas(void) { } +static inline void *pcpu_lpage_remapped(void *kaddr) +{ + return NULL; +} + #endif /* CONFIG_SMP */ #define alloc_percpu(type) (type *)__alloc_percpu(sizeof(type), \ -- cgit v1.2.3 From ff663cf8705bea101d5f73cf471855c85242575e Mon Sep 17 00:00:00 2001 From: Zhenyu Wang Date: Thu, 23 Jul 2009 17:25:49 +0100 Subject: agp: Add generic support for graphics dma remapping New driver hooks for support graphics memory dma remapping are introduced in this patch. It makes generic code can tell if current device needs dma remapping, then call driver provided interfaces for mapping and unmapping. Change has also been made to handle scratch_page in remapping case. Signed-off-by: Zhenyu Wang Signed-off-by: David Woodhouse --- include/linux/agp_backend.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/agp_backend.h b/include/linux/agp_backend.h index 76fa794fdac..8a294d65b9b 100644 --- a/include/linux/agp_backend.h +++ b/include/linux/agp_backend.h @@ -79,9 +79,13 @@ struct agp_memory { u32 physical; bool is_bound; bool is_flushed; - bool vmalloc_flag; + bool vmalloc_flag; + bool sg_vmalloc_flag; /* list of agp_memory mapped to the aperture */ struct list_head mapped_list; + /* DMA-mapped addresses */ + struct scatterlist *sg_list; + int num_sg; }; #define AGP_NORMAL_MEMORY 0 -- cgit v1.2.3 From f692775d7e0a22477143cd884e45c955448ac7d2 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Wed, 29 Jul 2009 09:28:45 +0100 Subject: intel-agp: fix sglist allocation to avoid vmalloc() Signed-off-by: David Woodhouse --- include/linux/agp_backend.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/agp_backend.h b/include/linux/agp_backend.h index 8a294d65b9b..880130f7311 100644 --- a/include/linux/agp_backend.h +++ b/include/linux/agp_backend.h @@ -80,7 +80,6 @@ struct agp_memory { bool is_bound; bool is_flushed; bool vmalloc_flag; - bool sg_vmalloc_flag; /* list of agp_memory mapped to the aperture */ struct list_head mapped_list; /* DMA-mapped addresses */ -- cgit v1.2.3 From fa56d4cb4022c8b313c3b99236e1b87effc3655b Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 23 Jun 2009 11:29:11 +0000 Subject: ide: allow ide_dev_read_id() to be called from the IRQ context * Un-static __ide_wait_stat(). * Allow ide_dev_read_id() helper to be called from the IRQ context by adding irq_ctx flag and using mdelay()/__ide_wait_stat() when needed. * Switch ide_driveid_update() to set irq_ctx flag. This change is needed for the consecutive patch which fixes races in handling of user-space SET XFER commands but for improved bisectability and clarity it is better to do it in a separate patch. Signed-off-by: Bartlomiej Zolnierkiewicz Signed-off-by: David S. Miller --- 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 edc93a6d931..cb6cd0459a5 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1081,6 +1081,7 @@ extern void ide_fixstring(u8 *, const int, const int); int ide_busy_sleep(ide_drive_t *, unsigned long, int); +int __ide_wait_stat(ide_drive_t *, u8, u8, unsigned long, u8 *); 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 *); @@ -1169,7 +1170,7 @@ int ide_no_data_taskfile(ide_drive_t *, struct ide_cmd *); int ide_taskfile_ioctl(ide_drive_t *, unsigned long); -int ide_dev_read_id(ide_drive_t *, u8, u16 *); +int ide_dev_read_id(ide_drive_t *, u8, u16 *, int); extern int ide_driveid_update(ide_drive_t *); extern int ide_config_drive_speed(ide_drive_t *, u8); -- cgit v1.2.3 From 665d66e8fad60a5a162c4615f27f916ad1a6d567 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 23 Jun 2009 11:35:51 +0000 Subject: ide: fix races in handling of user-space SET XFER commands * Make cmd->tf_flags field 'u16' and add IDE_TFLAG_SET_XFER taskfile flag. * Update ide_finish_cmd() to set xfer / re-read id if the new flag is set. * Convert set_xfer_rate() (write handler for /proc/ide/hd?/current_speed) and ide_cmd_ioctl() (HDIO_DRIVE_CMD ioctl handler) to use the new flag. * Remove no longer needed disable_irq_nosync() + enable_irq() from ide_config_drive_speed(). Signed-off-by: Bartlomiej Zolnierkiewicz Signed-off-by: David S. Miller --- 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 cb6cd0459a5..803c1ae3123 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -258,6 +258,7 @@ enum { IDE_TFLAG_DYN = (1 << 5), IDE_TFLAG_FS = (1 << 6), IDE_TFLAG_MULTI_PIO = (1 << 7), + IDE_TFLAG_SET_XFER = (1 << 8), }; enum { @@ -294,7 +295,7 @@ struct ide_cmd { } out, in; } valid; - u8 tf_flags; + u16 tf_flags; u8 ftf_flags; /* for TASKFILE ioctl */ int protocol; -- cgit v1.2.3 From 00ae4064b1445524752575dd84df227c0687c99d Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 14 Aug 2009 15:00:49 +0900 Subject: percpu: rename 4k first chunk allocator to page Page size isn't always 4k depending on arch and configuration. Rename 4k first chunk allocator to page. Signed-off-by: Tejun Heo Cc: David Howells --- 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 e134c822963..7989f61b03f 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -74,7 +74,7 @@ extern ssize_t __init pcpu_embed_first_chunk( size_t static_size, size_t reserved_size, ssize_t dyn_size); -extern ssize_t __init pcpu_4k_first_chunk( +extern ssize_t __init pcpu_page_first_chunk( size_t static_size, size_t reserved_size, pcpu_fc_alloc_fn_t alloc_fn, pcpu_fc_free_fn_t free_fn, -- cgit v1.2.3 From 08fc45806103e59a37418e84719b878f9bb32540 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 14 Aug 2009 15:00:49 +0900 Subject: percpu: build first chunk allocators selectively There's no need to build unused first chunk allocators in. Define CONFIG_NEED_PER_CPU_*_FIRST_CHUNK and let archs enable them selectively. Signed-off-by: Tejun Heo --- include/linux/percpu.h | 27 +++++---------------------- 1 file changed, 5 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 7989f61b03f..e26788e0da4 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -70,17 +70,21 @@ extern size_t __init pcpu_setup_first_chunk( ssize_t dyn_size, size_t unit_size, void *base_addr, const int *unit_map); +#ifdef CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK extern ssize_t __init pcpu_embed_first_chunk( size_t static_size, size_t reserved_size, ssize_t dyn_size); +#endif +#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK extern ssize_t __init pcpu_page_first_chunk( size_t static_size, size_t reserved_size, pcpu_fc_alloc_fn_t alloc_fn, pcpu_fc_free_fn_t free_fn, pcpu_fc_populate_pte_fn_t populate_pte_fn); +#endif -#ifdef CONFIG_NEED_MULTIPLE_NODES +#ifdef CONFIG_NEED_PER_CPU_LPAGE_FIRST_CHUNK extern int __init pcpu_lpage_build_unit_map( size_t static_size, size_t reserved_size, ssize_t *dyn_sizep, size_t *unit_sizep, @@ -98,27 +102,6 @@ extern ssize_t __init pcpu_lpage_first_chunk( extern void *pcpu_lpage_remapped(void *kaddr); #else -static inline int pcpu_lpage_build_unit_map( - size_t static_size, size_t reserved_size, - ssize_t *dyn_sizep, size_t *unit_sizep, - size_t lpage_size, int *unit_map, - pcpu_fc_cpu_distance_fn_t cpu_distance_fn) -{ - return -EINVAL; -} - -static inline ssize_t __init pcpu_lpage_first_chunk( - size_t static_size, size_t reserved_size, - size_t dyn_size, size_t unit_size, - size_t lpage_size, const int *unit_map, - int nr_units, - pcpu_fc_alloc_fn_t alloc_fn, - pcpu_fc_free_fn_t free_fn, - pcpu_fc_map_fn_t map_fn) -{ - return -EINVAL; -} - static inline void *pcpu_lpage_remapped(void *kaddr) { return NULL; -- cgit v1.2.3 From f58dc01ba2ca9fe3ab2ba4ca43d9c8a735cf62d8 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 14 Aug 2009 15:00:50 +0900 Subject: percpu: generalize first chunk allocator selection Now that all first chunk allocators are in mm/percpu.c, it makes sense to make generalize percpu_alloc kernel parameter. Define PCPU_FC_* and set pcpu_chosen_fc using early_param() in mm/percpu.c. Arch code can use the set value to determine which first chunk allocator to use. Signed-off-by: Tejun Heo --- include/linux/percpu.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index e26788e0da4..9be05cbe5ee 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -59,6 +59,18 @@ extern void *pcpu_base_addr; extern const int *pcpu_unit_map; +enum pcpu_fc { + PCPU_FC_AUTO, + PCPU_FC_EMBED, + PCPU_FC_PAGE, + PCPU_FC_LPAGE, + + PCPU_FC_NR, +}; +extern const char *pcpu_fc_names[PCPU_FC_NR]; + +extern enum pcpu_fc pcpu_chosen_fc; + typedef void * (*pcpu_fc_alloc_fn_t)(unsigned int cpu, size_t size); typedef void (*pcpu_fc_free_fn_t)(void *ptr, size_t size); typedef void (*pcpu_fc_populate_pte_fn_t)(unsigned long addr); -- cgit v1.2.3 From 9a7737691e90d3cce0e5248f91826c50e5aa3fcf Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 14 Aug 2009 15:00:50 +0900 Subject: percpu: drop @static_size from first chunk allocators First chunk allocators assume percpu areas have been linked using one of PERCPU_*() macros and depend on __per_cpu_load symbol defined by those macros, so there isn't much point in passing in static area size explicitly when it can be easily calculated from __per_cpu_start and __per_cpu_end. Drop @static_size from all percpu first chunk allocators and helpers. Signed-off-by: Tejun Heo --- include/linux/percpu.h | 18 ++++++++---------- 1 file changed, 8 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 9be05cbe5ee..be2fc8fb9b6 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -84,13 +84,12 @@ extern size_t __init pcpu_setup_first_chunk( #ifdef CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK extern ssize_t __init pcpu_embed_first_chunk( - size_t static_size, size_t reserved_size, - ssize_t dyn_size); + size_t reserved_size, ssize_t dyn_size); #endif #ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK extern ssize_t __init pcpu_page_first_chunk( - size_t static_size, size_t reserved_size, + size_t reserved_size, pcpu_fc_alloc_fn_t alloc_fn, pcpu_fc_free_fn_t free_fn, pcpu_fc_populate_pte_fn_t populate_pte_fn); @@ -98,16 +97,15 @@ extern ssize_t __init pcpu_page_first_chunk( #ifdef CONFIG_NEED_PER_CPU_LPAGE_FIRST_CHUNK extern int __init pcpu_lpage_build_unit_map( - size_t static_size, size_t reserved_size, - ssize_t *dyn_sizep, size_t *unit_sizep, - size_t lpage_size, int *unit_map, + size_t reserved_size, ssize_t *dyn_sizep, + size_t *unit_sizep, size_t lpage_size, + int *unit_map, pcpu_fc_cpu_distance_fn_t cpu_distance_fn); extern ssize_t __init pcpu_lpage_first_chunk( - size_t static_size, size_t reserved_size, - size_t dyn_size, size_t unit_size, - size_t lpage_size, const int *unit_map, - int nr_units, + size_t reserved_size, size_t dyn_size, + size_t unit_size, size_t lpage_size, + const int *unit_map, int nr_units, pcpu_fc_alloc_fn_t alloc_fn, pcpu_fc_free_fn_t free_fn, pcpu_fc_map_fn_t map_fn); -- cgit v1.2.3 From 1d9d32572163b30be81dbe1409dfa7ea9763d0e8 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 14 Aug 2009 15:00:50 +0900 Subject: percpu: make @dyn_size mandatory for pcpu_setup_first_chunk() Now that all actual first chunk allocation and copying happen in the first chunk allocators and helpers, there's no reason for pcpu_setup_first_chunk() to try to determine @dyn_size automatically. The only left user is page first chunk allocator. Make it determine dyn_size like other allocators and make @dyn_size mandatory for pcpu_setup_first_chunk(). 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 be2fc8fb9b6..0cfdd14d096 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -79,7 +79,7 @@ typedef void (*pcpu_fc_map_fn_t)(void *ptr, size_t size, void *addr); extern size_t __init pcpu_setup_first_chunk( size_t static_size, size_t reserved_size, - ssize_t dyn_size, size_t unit_size, + size_t dyn_size, size_t unit_size, void *base_addr, const int *unit_map); #ifdef CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK -- cgit v1.2.3 From 3cbc85652767c38b252c8de55f9fd180b29e4c0d Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 14 Aug 2009 15:00:50 +0900 Subject: percpu: add @align to pcpu_fc_alloc_fn_t pcpu_fc_alloc_fn_t is about to see more interesting usage, add @align parameter. Signed-off-by: Tejun Heo --- include/linux/percpu.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 0cfdd14d096..d385dbcf190 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -71,7 +71,8 @@ extern const char *pcpu_fc_names[PCPU_FC_NR]; extern enum pcpu_fc pcpu_chosen_fc; -typedef void * (*pcpu_fc_alloc_fn_t)(unsigned int cpu, size_t size); +typedef void * (*pcpu_fc_alloc_fn_t)(unsigned int cpu, size_t size, + size_t align); typedef void (*pcpu_fc_free_fn_t)(void *ptr, size_t size); typedef void (*pcpu_fc_populate_pte_fn_t)(unsigned long addr); typedef int (pcpu_fc_cpu_distance_fn_t)(unsigned int from, unsigned int to); -- cgit v1.2.3 From 033e48fb82958053113178264ddb9d5038d5e38b Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 14 Aug 2009 15:00:51 +0900 Subject: percpu: move pcpu_lpage_build_unit_map() and pcpul_lpage_dump_cfg() upward Unit map handling will be generalized and extended and used for embedding sparse first chunk and other purposes. Relocate two unit_map related functions upward in preparation. This patch just moves the code without any actual change. Signed-off-by: Tejun Heo --- include/linux/percpu.h | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index d385dbcf190..570fb18de2b 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -78,6 +78,14 @@ typedef void (*pcpu_fc_populate_pte_fn_t)(unsigned long addr); typedef int (pcpu_fc_cpu_distance_fn_t)(unsigned int from, unsigned int to); typedef void (*pcpu_fc_map_fn_t)(void *ptr, size_t size, void *addr); +#ifdef CONFIG_NEED_PER_CPU_LPAGE_FIRST_CHUNK +extern int __init pcpu_lpage_build_unit_map( + size_t reserved_size, ssize_t *dyn_sizep, + size_t *unit_sizep, size_t lpage_size, + int *unit_map, + pcpu_fc_cpu_distance_fn_t cpu_distance_fn); +#endif + extern size_t __init pcpu_setup_first_chunk( size_t static_size, size_t reserved_size, size_t dyn_size, size_t unit_size, @@ -97,12 +105,6 @@ extern ssize_t __init pcpu_page_first_chunk( #endif #ifdef CONFIG_NEED_PER_CPU_LPAGE_FIRST_CHUNK -extern int __init pcpu_lpage_build_unit_map( - size_t reserved_size, ssize_t *dyn_sizep, - size_t *unit_sizep, size_t lpage_size, - int *unit_map, - pcpu_fc_cpu_distance_fn_t cpu_distance_fn); - extern ssize_t __init pcpu_lpage_first_chunk( size_t reserved_size, size_t dyn_size, size_t unit_size, size_t lpage_size, -- cgit v1.2.3 From fd1e8a1fe2b54df6c185b4fa65f181f50b9c4d4e Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 14 Aug 2009 15:00:51 +0900 Subject: percpu: introduce pcpu_alloc_info and pcpu_group_info Till now, non-linear cpu->unit map was expressed using an integer array which maps each cpu to a unit and used only by lpage allocator. Although how many units have been placed in a single contiguos area (group) is known while building unit_map, the information is lost when the result is recorded into the unit_map array. For lpage allocator, as all allocations are done by lpages and whether two adjacent lpages are in the same group or not is irrelevant, this didn't cause any problem. Non-linear cpu->unit mapping will be used for sparse embedding and this grouping information is necessary for that. This patch introduces pcpu_alloc_info which contains all the information necessary for initializing percpu allocator. pcpu_alloc_info contains array of pcpu_group_info which describes how units are grouped and mapped to cpus. pcpu_group_info also has base_offset field to specify its offset from the chunk's base address. pcpu_build_alloc_info() initializes this field as if all groups are allocated back-to-back as is currently done but this will be used to sparsely place groups. pcpu_alloc_info is a rather complex data structure which contains a flexible array which in turn points to nested cpu_map arrays. * pcpu_alloc_alloc_info() and pcpu_free_alloc_info() are provided to help dealing with pcpu_alloc_info. * pcpu_lpage_build_unit_map() is updated to build pcpu_alloc_info, generalized and renamed to pcpu_build_alloc_info(). @cpu_distance_fn may be NULL indicating that all cpus are of LOCAL_DISTANCE. * pcpul_lpage_dump_cfg() is updated to process pcpu_alloc_info, generalized and renamed to pcpu_dump_alloc_info(). It now also prints which group each alloc unit belongs to. * pcpu_setup_first_chunk() now takes pcpu_alloc_info instead of the separate parameters. All first chunk allocators are updated to use pcpu_build_alloc_info() to build alloc_info and call pcpu_setup_first_chunk() with it. This has the side effect of packing units for sparse possible cpus. ie. if cpus 0, 2 and 4 are possible, they'll be assigned unit 0, 1 and 2 instead of 0, 2 and 4. * x86 setup_pcpu_lpage() is updated to deal with alloc_info. * sparc64 setup_per_cpu_areas() is updated to build alloc_info. Although the changes made by this patch are pretty pervasive, it doesn't cause any behavior difference other than packing of sparse cpus. It mostly changes how information is passed among initialization functions and makes room for more flexibility. Signed-off-by: Tejun Heo Cc: Ingo Molnar Cc: David Miller --- include/linux/percpu.h | 42 +++++++++++++++++++++++++++++------------- 1 file changed, 29 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 570fb18de2b..77b86be8ce4 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -59,6 +59,25 @@ extern void *pcpu_base_addr; extern const int *pcpu_unit_map; +struct pcpu_group_info { + int nr_units; /* aligned # of units */ + unsigned long base_offset; /* base address offset */ + unsigned int *cpu_map; /* unit->cpu map, empty + * entries contain NR_CPUS */ +}; + +struct pcpu_alloc_info { + size_t static_size; + size_t reserved_size; + size_t dyn_size; + size_t unit_size; + size_t atom_size; + size_t alloc_size; + size_t __ai_size; /* internal, don't use */ + int nr_groups; /* 0 if grouping unnecessary */ + struct pcpu_group_info groups[]; +}; + enum pcpu_fc { PCPU_FC_AUTO, PCPU_FC_EMBED, @@ -78,18 +97,17 @@ typedef void (*pcpu_fc_populate_pte_fn_t)(unsigned long addr); typedef int (pcpu_fc_cpu_distance_fn_t)(unsigned int from, unsigned int to); typedef void (*pcpu_fc_map_fn_t)(void *ptr, size_t size, void *addr); -#ifdef CONFIG_NEED_PER_CPU_LPAGE_FIRST_CHUNK -extern int __init pcpu_lpage_build_unit_map( - size_t reserved_size, ssize_t *dyn_sizep, - size_t *unit_sizep, size_t lpage_size, - int *unit_map, +extern struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups, + int nr_units); +extern void __init pcpu_free_alloc_info(struct pcpu_alloc_info *ai); + +extern struct pcpu_alloc_info * __init pcpu_build_alloc_info( + size_t reserved_size, ssize_t dyn_size, + size_t atom_size, pcpu_fc_cpu_distance_fn_t cpu_distance_fn); -#endif -extern size_t __init pcpu_setup_first_chunk( - size_t static_size, size_t reserved_size, - size_t dyn_size, size_t unit_size, - void *base_addr, const int *unit_map); +extern size_t __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, + void *base_addr); #ifdef CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK extern ssize_t __init pcpu_embed_first_chunk( @@ -106,9 +124,7 @@ extern ssize_t __init pcpu_page_first_chunk( #ifdef CONFIG_NEED_PER_CPU_LPAGE_FIRST_CHUNK extern ssize_t __init pcpu_lpage_first_chunk( - size_t reserved_size, size_t dyn_size, - size_t unit_size, size_t lpage_size, - const int *unit_map, int nr_units, + const struct pcpu_alloc_info *ai, pcpu_fc_alloc_fn_t alloc_fn, pcpu_fc_free_fn_t free_fn, pcpu_fc_map_fn_t map_fn); -- cgit v1.2.3 From fb435d5233f8b6f9b93c11d6304d8e98fed03234 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 14 Aug 2009 15:00:51 +0900 Subject: percpu: add pcpu_unit_offsets[] Currently units are mapped sequentially into address space. This patch adds pcpu_unit_offsets[] which allows units to be mapped to arbitrary offsets from the chunk base address. This is necessary to allow sparse embedding which might would need to allocate address ranges and memory areas which aren't aligned to unit size but allocation atom size (page or large page size). This also simplifies things a bit by removing the need to calculate offset from unit number. With this change, there's no need for the arch code to know pcpu_unit_size. Update pcpu_setup_first_chunk() and first chunk allocators to return regular 0 or -errno return code instead of unit size or -errno. Signed-off-by: Tejun Heo Cc: David S. Miller --- include/linux/percpu.h | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 77b86be8ce4..a7ec840f596 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -57,7 +57,7 @@ #endif extern void *pcpu_base_addr; -extern const int *pcpu_unit_map; +extern const unsigned long *pcpu_unit_offsets; struct pcpu_group_info { int nr_units; /* aligned # of units */ @@ -106,25 +106,23 @@ extern struct pcpu_alloc_info * __init pcpu_build_alloc_info( size_t atom_size, pcpu_fc_cpu_distance_fn_t cpu_distance_fn); -extern size_t __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, - void *base_addr); +extern int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, + void *base_addr); #ifdef CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK -extern ssize_t __init pcpu_embed_first_chunk( - size_t reserved_size, ssize_t dyn_size); +extern int __init pcpu_embed_first_chunk(size_t reserved_size, + ssize_t dyn_size); #endif #ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK -extern ssize_t __init pcpu_page_first_chunk( - size_t reserved_size, +extern int __init pcpu_page_first_chunk(size_t reserved_size, pcpu_fc_alloc_fn_t alloc_fn, pcpu_fc_free_fn_t free_fn, pcpu_fc_populate_pte_fn_t populate_pte_fn); #endif #ifdef CONFIG_NEED_PER_CPU_LPAGE_FIRST_CHUNK -extern ssize_t __init pcpu_lpage_first_chunk( - const struct pcpu_alloc_info *ai, +extern int __init pcpu_lpage_first_chunk(const struct pcpu_alloc_info *ai, pcpu_fc_alloc_fn_t alloc_fn, pcpu_fc_free_fn_t free_fn, pcpu_fc_map_fn_t map_fn); -- cgit v1.2.3 From ca23e405e06d5fffb005df004c72781f76062f51 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 14 Aug 2009 15:00:52 +0900 Subject: vmalloc: implement pcpu_get_vm_areas() To directly use spread NUMA memories for percpu units, percpu allocator will be updated to allow sparsely mapping units in a chunk. As the distances between units can be very large, this makes allocating single vmap area for each chunk undesirable. This patch implements pcpu_get_vm_areas() and pcpu_free_vm_areas() which allocates and frees sparse congruent vmap areas. pcpu_get_vm_areas() take @offsets and @sizes array which define distances and sizes of vmap areas. It scans down from the top of vmalloc area looking for the top-most address which can accomodate all the areas. The top-down scan is to avoid interacting with regular vmallocs which can push up these congruent areas up little by little ending up wasting address space and page table. To speed up top-down scan, the highest possible address hint is maintained. Although the scan is linear from the hint, given the usual large holes between memory addresses between NUMA nodes, the scanning is highly likely to finish after finding the first hole for the last unit which is scanned first. Signed-off-by: Tejun Heo Cc: Nick Piggin --- include/linux/vmalloc.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index a43ebec3a7b..227c2a585e4 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -115,4 +115,10 @@ extern rwlock_t vmlist_lock; extern struct vm_struct *vmlist; extern __init void vm_area_register_early(struct vm_struct *vm, size_t align); +struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, + const size_t *sizes, int nr_vms, + size_t align, gfp_t gfp_mask); + +void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms); + #endif /* _LINUX_VMALLOC_H */ -- cgit v1.2.3 From c8826dd538602d730ed2c18c6753f1bbfa6c4933 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 14 Aug 2009 15:00:52 +0900 Subject: percpu: update embedding first chunk allocator to handle sparse units Now that percpu core can handle very sparse units, given that vmalloc space is large enough, embedding first chunk allocator can use any memory to build the first chunk. This patch teaches pcpu_embed_first_chunk() about distances between cpus and to use alloc/free callbacks to allocate node specific areas for each group and use them for the first chunk. This brings the benefits of embedding allocator to NUMA configurations - no extra TLB pressure with the flexibility of unified dynamic allocator and no need to restructure arch code to build memory layout suitable for percpu. With units put into atom_size aligned groups according to cpu distances, using large page for dynamic chunks is also easily possible with falling back to reuglar pages if large allocation fails. Embedding allocator users are converted to specify NULL cpu_distance_fn, so this patch doesn't cause any visible behavior difference. Following patches will convert them. Signed-off-by: Tejun Heo --- include/linux/percpu.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index a7ec840f596..25359932740 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -110,8 +110,11 @@ extern int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, void *base_addr); #ifdef CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK -extern int __init pcpu_embed_first_chunk(size_t reserved_size, - ssize_t dyn_size); +extern int __init pcpu_embed_first_chunk(size_t reserved_size, ssize_t dyn_size, + size_t atom_size, + pcpu_fc_cpu_distance_fn_t cpu_distance_fn, + pcpu_fc_alloc_fn_t alloc_fn, + pcpu_fc_free_fn_t free_fn); #endif #ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK -- cgit v1.2.3 From e933a73f48e3b2d40cfa56d81e2646f194b5a66a Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 14 Aug 2009 15:00:53 +0900 Subject: percpu: kill lpage first chunk allocator With x86 converted to embedding allocator, lpage doesn't have any user left. Kill it along with cpa handling code. Signed-off-by: Tejun Heo Cc: Jan Beulich --- include/linux/percpu.h | 16 ---------------- 1 file changed, 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 25359932740..878836ca999 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -82,7 +82,6 @@ enum pcpu_fc { PCPU_FC_AUTO, PCPU_FC_EMBED, PCPU_FC_PAGE, - PCPU_FC_LPAGE, PCPU_FC_NR, }; @@ -95,7 +94,6 @@ typedef void * (*pcpu_fc_alloc_fn_t)(unsigned int cpu, size_t size, typedef void (*pcpu_fc_free_fn_t)(void *ptr, size_t size); typedef void (*pcpu_fc_populate_pte_fn_t)(unsigned long addr); typedef int (pcpu_fc_cpu_distance_fn_t)(unsigned int from, unsigned int to); -typedef void (*pcpu_fc_map_fn_t)(void *ptr, size_t size, void *addr); extern struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups, int nr_units); @@ -124,20 +122,6 @@ extern int __init pcpu_page_first_chunk(size_t reserved_size, pcpu_fc_populate_pte_fn_t populate_pte_fn); #endif -#ifdef CONFIG_NEED_PER_CPU_LPAGE_FIRST_CHUNK -extern int __init pcpu_lpage_first_chunk(const struct pcpu_alloc_info *ai, - pcpu_fc_alloc_fn_t alloc_fn, - pcpu_fc_free_fn_t free_fn, - pcpu_fc_map_fn_t map_fn); - -extern void *pcpu_lpage_remapped(void *kaddr); -#else -static inline void *pcpu_lpage_remapped(void *kaddr) -{ - return NULL; -} -#endif - /* * 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 0396c215f301e92677d1e9a064b405e31501dc1d Mon Sep 17 00:00:00 2001 From: David Vrabel Date: Tue, 25 Aug 2009 16:41:06 +0100 Subject: uwb: avoid radio controller reset loops If a radio controller reset attempt occurs while a probe() or remove() is in progress it fails and is retried endlessly, potentially preventing the probe() or remove() from completing. If a reset fails, sleep for a bit before retrying the reset. This allows the probe()/remove() to complete. Signed-off-by: David Vrabel --- include/linux/uwb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/uwb.h b/include/linux/uwb.h index c02128991ff..7fc9746f22c 100644 --- a/include/linux/uwb.h +++ b/include/linux/uwb.h @@ -597,7 +597,7 @@ void uwb_rc_neh_grok(struct uwb_rc *, void *, size_t); void uwb_rc_neh_error(struct uwb_rc *, int); void uwb_rc_reset_all(struct uwb_rc *rc); void uwb_rc_pre_reset(struct uwb_rc *rc); -void uwb_rc_post_reset(struct uwb_rc *rc); +int uwb_rc_post_reset(struct uwb_rc *rc); /** * uwb_rsv_is_owner - is the owner of this reservation the RC? -- cgit v1.2.3 From 9e36fda0b359d2a6ae039c3d7e71a04502a77898 Mon Sep 17 00:00:00 2001 From: Venkatesh Pallipadi Date: Fri, 10 Jul 2009 09:57:35 -0700 Subject: x86, pat: Add PAT reserve free to io_mapping* APIs io_mapping_* interfaces were added, mainly for graphics drivers. Make this interface go through the PAT reserve/free, instead of hardcoding WC mapping. This makes sure that there are no aliases due to unconditional WC setting. Signed-off-by: Venkatesh Pallipadi Signed-off-by: Suresh Siddha Signed-off-by: H. Peter Anvin --- include/linux/io-mapping.h | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h index 0adb0f91568..97eb928b492 100644 --- a/include/linux/io-mapping.h +++ b/include/linux/io-mapping.h @@ -49,23 +49,30 @@ static inline struct io_mapping * io_mapping_create_wc(resource_size_t base, unsigned long size) { struct io_mapping *iomap; - - if (!is_io_mapping_possible(base, size)) - return NULL; + pgprot_t prot; iomap = kmalloc(sizeof(*iomap), GFP_KERNEL); if (!iomap) - return NULL; + goto out_err; + + if (iomap_create_wc(base, size, &prot)) + goto out_free; iomap->base = base; iomap->size = size; - iomap->prot = pgprot_writecombine(__pgprot(__PAGE_KERNEL)); + iomap->prot = prot; return iomap; + +out_free: + kfree(iomap); +out_err: + return NULL; } static inline void io_mapping_free(struct io_mapping *mapping) { + iomap_free(mapping->base, mapping->size); kfree(mapping); } -- cgit v1.2.3 From 46cf98cdaef5471926010b5bddf84c44ec177fdd Mon Sep 17 00:00:00 2001 From: Venkatesh Pallipadi Date: Fri, 10 Jul 2009 09:57:37 -0700 Subject: x86, pat: Generalize the use of page flag PG_uncached Only IA64 was using PG_uncached as of now. We now intend to use this bit in x86 as well, to keep track of memory type of those addresses that have page struct for them. So, generalize the use of that bit across ia64 and x86. Signed-off-by: Venkatesh Pallipadi Signed-off-by: Suresh Siddha Signed-off-by: H. Peter Anvin --- include/linux/page-flags.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index e2e5ce54359..2b87acfc5f8 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -99,7 +99,7 @@ enum pageflags { #ifdef CONFIG_HAVE_MLOCKED_PAGE_BIT PG_mlocked, /* Page is vma mlocked */ #endif -#ifdef CONFIG_IA64_UNCACHED_ALLOCATOR +#ifdef CONFIG_ARCH_USES_PG_UNCACHED PG_uncached, /* Page has been mapped as uncached */ #endif __NR_PAGEFLAGS, @@ -257,7 +257,7 @@ PAGEFLAG_FALSE(Mlocked) SETPAGEFLAG_NOOP(Mlocked) TESTCLEARFLAG_FALSE(Mlocked) #endif -#ifdef CONFIG_IA64_UNCACHED_ALLOCATOR +#ifdef CONFIG_ARCH_USES_PG_UNCACHED PAGEFLAG(Uncached, uncached) #else PAGEFLAG_FALSE(Uncached) -- cgit v1.2.3 From f726f30e32305a34a203ff975e60885aa7556c6a Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Tue, 4 Aug 2009 19:08:24 +0000 Subject: dma: Add set_dma_mask hook to struct dma_map_ops POWERPC needs this hook. SPARC could use it too. Signed-off-by: FUJITA Tomonori Acked-by: Becky Bruce Signed-off-by: Benjamin Herrenschmidt --- include/linux/dma-mapping.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index c0f6c3cd788..91b76184606 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -58,6 +58,7 @@ struct dma_map_ops { 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 (*set_dma_mask)(struct device *dev, u64 mask); int is_phys; }; -- cgit v1.2.3 From 6d703a81ad5fdd102334751ddacb053ecc6ff046 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Tue, 1 Sep 2009 17:52:57 -0700 Subject: ide: convert to ->proc_fops ->read_proc, ->write_proc are going away, ->proc_fops should be used instead. The only tricky place is IDENTIFY handling: if for some reason taskfile_lib_get_identify() fails, buffer _is_ changed and at least first byte is overwritten. Emulate old behaviour with returning that first byte to userspace and reporting length=1 despite overall -E. Signed-off-by: Alexey Dobriyan Signed-off-by: David S. Miller --- include/linux/ide.h | 24 +++--------------------- 1 file changed, 3 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 803c1ae3123..e4135d6e055 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -919,8 +919,7 @@ __IDE_PROC_DEVSET(_name, _min, _max, NULL, NULL) typedef struct { const char *name; mode_t mode; - read_proc_t *read_proc; - write_proc_t *write_proc; + const struct file_operations *proc_fops; } ide_proc_entry_t; void proc_ide_create(void); @@ -932,24 +931,8 @@ void ide_proc_unregister_port(ide_hwif_t *); void ide_proc_register_driver(ide_drive_t *, struct ide_driver *); void ide_proc_unregister_driver(ide_drive_t *, struct ide_driver *); -read_proc_t proc_ide_read_capacity; -read_proc_t proc_ide_read_geometry; - -/* - * Standard exit stuff: - */ -#define PROC_IDE_READ_RETURN(page,start,off,count,eof,len) \ -{ \ - len -= off; \ - if (len < count) { \ - *eof = 1; \ - if (len <= 0) \ - return 0; \ - } else \ - len = count; \ - *start = page + off; \ - return len; \ -} +extern const struct file_operations ide_capacity_proc_fops; +extern const struct file_operations ide_geometry_proc_fops; #else static inline void proc_ide_create(void) { ; } static inline void proc_ide_destroy(void) { ; } @@ -961,7 +944,6 @@ static inline void ide_proc_register_driver(ide_drive_t *drive, struct ide_driver *driver) { ; } static inline void ide_proc_unregister_driver(ide_drive_t *drive, struct ide_driver *driver) { ; } -#define PROC_IDE_READ_RETURN(page,start,off,count,eof,len) return 0; #endif enum { -- cgit v1.2.3 From 69575d388603365f2afbf4166df93152df59b165 Mon Sep 17 00:00:00 2001 From: Shane Wang Date: Tue, 1 Sep 2009 18:25:07 -0700 Subject: x86, intel_txt: clean up the impact on generic code, unbreak non-x86 Move tboot.h from asm to linux to fix the build errors of intel_txt patch on non-X86 platforms. Remove the tboot code from generic code init/main.c and kernel/cpu.c. Signed-off-by: Shane Wang Signed-off-by: H. Peter Anvin --- include/linux/tboot.h | 162 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 162 insertions(+) create mode 100644 include/linux/tboot.h (limited to 'include/linux') diff --git a/include/linux/tboot.h b/include/linux/tboot.h new file mode 100644 index 00000000000..bf2a0c74887 --- /dev/null +++ b/include/linux/tboot.h @@ -0,0 +1,162 @@ +/* + * tboot.h: shared data structure with tboot and kernel and functions + * used by kernel for runtime support of Intel(R) Trusted + * Execution Technology + * + * Copyright (c) 2006-2009, Intel Corporation + * + * 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_TBOOT_H +#define _LINUX_TBOOT_H + +/* these must have the values from 0-5 in this order */ +enum { + TB_SHUTDOWN_REBOOT = 0, + TB_SHUTDOWN_S5, + TB_SHUTDOWN_S4, + TB_SHUTDOWN_S3, + TB_SHUTDOWN_HALT, + TB_SHUTDOWN_WFS +}; + +#ifdef CONFIG_INTEL_TXT +#include +/* used to communicate between tboot and the launched kernel */ + +#define TB_KEY_SIZE 64 /* 512 bits */ + +#define MAX_TB_MAC_REGIONS 32 + +struct tboot_mac_region { + u64 start; /* must be 64 byte -aligned */ + u32 size; /* must be 64 byte -granular */ +} __packed; + +/* GAS - Generic Address Structure (ACPI 2.0+) */ +struct tboot_acpi_generic_address { + u8 space_id; + u8 bit_width; + u8 bit_offset; + u8 access_width; + u64 address; +} __packed; + +/* + * combines Sx info from FADT and FACS tables per ACPI 2.0+ spec + * (http://www.acpi.info/) + */ +struct tboot_acpi_sleep_info { + struct tboot_acpi_generic_address pm1a_cnt_blk; + struct tboot_acpi_generic_address pm1b_cnt_blk; + struct tboot_acpi_generic_address pm1a_evt_blk; + struct tboot_acpi_generic_address pm1b_evt_blk; + u16 pm1a_cnt_val; + u16 pm1b_cnt_val; + u64 wakeup_vector; + u32 vector_width; + u64 kernel_s3_resume_vector; +} __packed; + +/* + * shared memory page used for communication between tboot and kernel + */ +struct tboot { + /* + * version 3+ fields: + */ + + /* TBOOT_UUID */ + u8 uuid[16]; + + /* version number: 5 is current */ + u32 version; + + /* physical addr of tb_log_t log */ + u32 log_addr; + + /* + * physical addr of entry point for tboot shutdown and + * type of shutdown (TB_SHUTDOWN_*) being requested + */ + u32 shutdown_entry; + u32 shutdown_type; + + /* kernel-specified ACPI info for Sx shutdown */ + struct tboot_acpi_sleep_info acpi_sinfo; + + /* tboot location in memory (physical) */ + u32 tboot_base; + u32 tboot_size; + + /* memory regions (phys addrs) for tboot to MAC on S3 */ + u8 num_mac_regions; + struct tboot_mac_region mac_regions[MAX_TB_MAC_REGIONS]; + + + /* + * version 4+ fields: + */ + + /* symmetric key for use by kernel; will be encrypted on S3 */ + u8 s3_key[TB_KEY_SIZE]; + + + /* + * version 5+ fields: + */ + + /* used to 4byte-align num_in_wfs */ + u8 reserved_align[3]; + + /* number of processors in wait-for-SIPI */ + u32 num_in_wfs; +} __packed; + +/* + * UUID for tboot data struct to facilitate matching + * defined as {663C8DFF-E8B3-4b82-AABF-19EA4D057A08} by tboot, which is + * represented as {} in the char array used here + */ +#define TBOOT_UUID {0xff, 0x8d, 0x3c, 0x66, 0xb3, 0xe8, 0x82, 0x4b, 0xbf,\ + 0xaa, 0x19, 0xea, 0x4d, 0x5, 0x7a, 0x8} + +extern struct tboot *tboot; + +static inline int tboot_enabled(void) +{ + return tboot != NULL; +} + +extern void tboot_probe(void); +extern void tboot_shutdown(u32 shutdown_type); +extern void tboot_sleep(u8 sleep_state, u32 pm1a_control, u32 pm1b_control); +extern struct acpi_table_header *tboot_get_dmar_table( + struct acpi_table_header *dmar_tbl); +extern int tboot_force_iommu(void); + +#else + +#define tboot_probe() do { } while (0) +#define tboot_shutdown(shutdown_type) do { } while (0) +#define tboot_sleep(sleep_state, pm1a_control, pm1b_control) \ + do { } while (0) +#define tboot_get_dmar_table(dmar_tbl) (dmar_tbl) +#define tboot_force_iommu() 0 + +#endif /* !CONFIG_INTEL_TXT */ + +#endif /* _LINUX_TBOOT_H */ -- cgit v1.2.3 From cede3930f0ca6fef353fa01306c72a01420bd45e Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Mon, 31 Aug 2009 21:34:36 +0000 Subject: powerpc: Fix some late PowerMac G5 with PCIe ATI graphics A misconfiguration by the firmware of the U4 PCIe bridge on PowerMac G5 with the U4 bridge (latest generations, may also affect the iMac G5 "iSight") is causing us to re-assign the PCI BARs of the video card, which can get it out of sync with the firmware, thus breaking offb. This works around it by fixing up the bridge configuration properly at boot time. It also fixes a bug where the firmware provides us with an incorrect set of accessible regions in the device-tree. Signed-off-by: Benjamin Herrenschmidt --- 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 73b46b6b904..c86bb6e3dfc 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -877,6 +877,7 @@ #define PCI_DEVICE_ID_APPLE_SH_SUNGEM 0x0051 #define PCI_DEVICE_ID_APPLE_U3L_AGP 0x0058 #define PCI_DEVICE_ID_APPLE_U3H_AGP 0x0059 +#define PCI_DEVICE_ID_APPLE_U4_PCIE 0x005b #define PCI_DEVICE_ID_APPLE_IPID2_AGP 0x0066 #define PCI_DEVICE_ID_APPLE_IPID2_ATA 0x0069 #define PCI_DEVICE_ID_APPLE_IPID2_FW 0x006a -- cgit v1.2.3 From 711d57796f5ce2d02d6e62c9034afbb16aedda31 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Mon, 27 Jul 2009 23:37:48 +0300 Subject: PCI: expose function reset capability in sysfs Some devices allow an individual function to be reset without affecting other functions in the same device: that's what pci_reset_function does. For devices that have this support, expose reset attribite in sysfs. This is useful e.g. for virtualization, where a qemu userspace process wants to reset the device when the guest is reset, to emulate machine reboot as closely as possible. Acked-by: Greg Kroah-Hartman Signed-off-by: Michael S. Tsirkin Signed-off-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 115fb7ba508..a90f9402079 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -276,6 +276,7 @@ struct pci_dev { unsigned int state_saved:1; unsigned int is_physfn:1; unsigned int is_virtfn:1; + unsigned int reset_fn:1; pci_dev_flags_t dev_flags; atomic_t enable_cnt; /* pci_enable_device has been called */ -- cgit v1.2.3 From 1d4a433fc4e9c7dbfc2069a8f1a1f4338b982427 Mon Sep 17 00:00:00 2001 From: Dave Jones Date: Thu, 6 Aug 2009 15:13:59 -0400 Subject: PCI: Document pci_ids.h addition policy. IDs should generally only be added to pci_ids.h when they're shared across several files in the tree. IDs that are just used by a single driver should be defined in the driver instead. Perhaps documenting this is a good idea to prevent things being moved there, as it still seems to be happening judging from the git log. (based on discussion w/gregkh and others). Acked-by: Greg Kroah-Hartman Signed-off-by: Dave Jones Signed-off-by: Jesse Barnes --- include/linux/pci_ids.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 73b46b6b904..6235ce2bea0 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2,6 +2,9 @@ * PCI Class, Vendor and Device IDs * * Please keep sorted. + * + * Do not add new entries to this file unless the definitions + * are shared between multiple drivers. */ /* Device classes and subclasses */ -- cgit v1.2.3 From deb2d2ecd43dfc51efe71eed7128fda514da96c6 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Tue, 11 Aug 2009 15:52:06 +1000 Subject: PCI/GPU: implement VGA arbitration on Linux Background: Graphic devices are accessed through ranges in I/O or memory space. While most modern devices allow relocation of such ranges, some "Legacy" VGA devices implemented on PCI will typically have the same "hard-decoded" addresses as they did on ISA. For more details see "PCI Bus Binding to IEEE Std 1275-1994 Standard for Boot (Initialization Configuration) Firmware Revision 2.1" Section 7, Legacy Devices. The Resource Access Control (RAC) module inside the X server currently does the task of arbitration when more than one legacy device co-exists on the same machine. But the problem happens when these devices are trying to be accessed by different userspace clients (e.g. two server in parallel). Their address assignments conflict. Therefore an arbitration scheme _outside_ of the X server is needed to control the sharing of these resources. This document introduces the operation of the VGA arbiter implemented for Linux kernel. Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Tiago Vignatti Signed-off-by: Dave Airlie Signed-off-by: Jesse Barnes --- include/linux/pci.h | 2 + include/linux/vgaarb.h | 195 +++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 197 insertions(+) create mode 100644 include/linux/vgaarb.h (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index a90f9402079..6dbb1fd30e5 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -806,6 +806,8 @@ int pci_cfg_space_size_ext(struct pci_dev *dev); int pci_cfg_space_size(struct pci_dev *dev); unsigned char pci_bus_max_busnr(struct pci_bus *bus); +int pci_set_vga_state(struct pci_dev *pdev, bool decode, + unsigned int command_bits, bool change_bridge); /* kmem_cache style wrapper around pci_alloc_consistent() */ #include diff --git a/include/linux/vgaarb.h b/include/linux/vgaarb.h new file mode 100644 index 00000000000..68229ce80fd --- /dev/null +++ b/include/linux/vgaarb.h @@ -0,0 +1,195 @@ +/* + * vgaarb.c + * + * (C) Copyright 2005 Benjamin Herrenschmidt + * (C) Copyright 2007 Paulo R. Zanoni + * (C) Copyright 2007, 2009 Tiago Vignatti + */ + +#ifndef LINUX_VGA_H + +#include + +/* Legacy VGA regions */ +#define VGA_RSRC_NONE 0x00 +#define VGA_RSRC_LEGACY_IO 0x01 +#define VGA_RSRC_LEGACY_MEM 0x02 +#define VGA_RSRC_LEGACY_MASK (VGA_RSRC_LEGACY_IO | VGA_RSRC_LEGACY_MEM) +/* Non-legacy access */ +#define VGA_RSRC_NORMAL_IO 0x04 +#define VGA_RSRC_NORMAL_MEM 0x08 + +/* Passing that instead of a pci_dev to use the system "default" + * device, that is the one used by vgacon. Archs will probably + * have to provide their own vga_default_device(); + */ +#define VGA_DEFAULT_DEVICE (NULL) + +/* For use by clients */ + +/** + * vga_set_legacy_decoding + * + * @pdev: pci device of the VGA card + * @decodes: bit mask of what legacy regions the card decodes + * + * Indicates to the arbiter if the card decodes legacy VGA IOs, + * legacy VGA Memory, both, or none. All cards default to both, + * the card driver (fbdev for example) should tell the arbiter + * if it has disabled legacy decoding, so the card can be left + * out of the arbitration process (and can be safe to take + * interrupts at any time. + */ +extern void vga_set_legacy_decoding(struct pci_dev *pdev, + unsigned int decodes); + +/** + * vga_get - acquire & locks VGA resources + * + * pdev: pci device of the VGA card or NULL for the system default + * rsrc: bit mask of resources to acquire and lock + * interruptible: blocking should be interruptible by signals ? + * + * This function acquires VGA resources for the given + * card and mark those resources locked. If the resource requested + * are "normal" (and not legacy) resources, the arbiter will first check + * wether the card is doing legacy decoding for that type of resource. If + * yes, the lock is "converted" into a legacy resource lock. + * The arbiter will first look for all VGA cards that might conflict + * and disable their IOs and/or Memory access, inlcuding VGA forwarding + * on P2P bridges if necessary, so that the requested resources can + * be used. Then, the card is marked as locking these resources and + * the IO and/or Memory accesse are enabled on the card (including + * VGA forwarding on parent P2P bridges if any). + * This function will block if some conflicting card is already locking + * one of the required resources (or any resource on a different bus + * segment, since P2P bridges don't differenciate VGA memory and IO + * afaik). You can indicate wether this blocking should be interruptible + * by a signal (for userland interface) or not. + * Must not be called at interrupt time or in atomic context. + * If the card already owns the resources, the function succeeds. + * Nested calls are supported (a per-resource counter is maintained) + */ + +extern int vga_get(struct pci_dev *pdev, unsigned int rsrc, + int interruptible); + +/** + * vga_get_interruptible + * + * Shortcut to vga_get + */ + +static inline int vga_get_interruptible(struct pci_dev *pdev, + unsigned int rsrc) +{ + return vga_get(pdev, rsrc, 1); +} + +/** + * vga_get_interruptible + * + * Shortcut to vga_get + */ + +static inline int vga_get_uninterruptible(struct pci_dev *pdev, + unsigned int rsrc) +{ + return vga_get(pdev, rsrc, 0); +} + +/** + * vga_tryget - try to acquire & lock legacy VGA resources + * + * @pdev: pci devivce of VGA card or NULL for system default + * @rsrc: bit mask of resources to acquire and lock + * + * This function performs the same operation as vga_get(), but + * will return an error (-EBUSY) instead of blocking if the resources + * are already locked by another card. It can be called in any context + */ + +extern int vga_tryget(struct pci_dev *pdev, unsigned int rsrc); + +/** + * vga_put - release lock on legacy VGA resources + * + * @pdev: pci device of VGA card or NULL for system default + * @rsrc: but mask of resource to release + * + * This function releases resources previously locked by vga_get() + * or vga_tryget(). The resources aren't disabled right away, so + * that a subsequence vga_get() on the same card will succeed + * immediately. Resources have a counter, so locks are only + * released if the counter reaches 0. + */ + +extern void vga_put(struct pci_dev *pdev, unsigned int rsrc); + + +/** + * vga_default_device + * + * This can be defined by the platform. The default implementation + * is rather dumb and will probably only work properly on single + * vga card setups and/or x86 platforms. + * + * If your VGA default device is not PCI, you'll have to return + * NULL here. In this case, I assume it will not conflict with + * any PCI card. If this is not true, I'll have to define two archs + * hooks for enabling/disabling the VGA default device if that is + * possible. This may be a problem with real _ISA_ VGA cards, in + * addition to a PCI one. I don't know at this point how to deal + * with that card. Can theirs IOs be disabled at all ? If not, then + * I suppose it's a matter of having the proper arch hook telling + * us about it, so we basically never allow anybody to succeed a + * vga_get()... + */ + +#ifndef __ARCH_HAS_VGA_DEFAULT_DEVICE +extern struct pci_dev *vga_default_device(void); +#endif + +/** + * vga_conflicts + * + * Architectures should define this if they have several + * independant PCI domains that can afford concurrent VGA + * decoding + */ + +#ifndef __ARCH_HAS_VGA_CONFLICT +static inline int vga_conflicts(struct pci_dev *p1, struct pci_dev *p2) +{ + return 1; +} +#endif + +/* + * Register a client with the VGA arbitration logic + * return value: number of VGA devices in system. + * + * Clients have two callback mechanisms they can use. + * irq enable/disable callback - + * If a client can't disable its GPUs VGA resources, then we + * need to be able to ask it to turn off its irqs when we + * turn off its mem and io decoding. + * set_vga_decode + * If a client can disable its GPU VGA resource, it will + * get a callback from this to set the encode/decode state + * + * Clients with disable abilities should check the return value + * of this function and if the VGA device count is > 1, should + * disable VGA decoding resources. + * + * Rationale: we cannot disable VGA decode resources unconditionally + * some single GPU laptops seem to require ACPI or BIOS access to the + * VGA registers to control things like backlights etc. + * Hopefully newer multi-GPU laptops do something saner, and desktops + * won't have any special ACPI for this. + */ +int vga_client_register(struct pci_dev *pdev, void *cookie, + void (*irq_set_state)(void *cookie, bool state), + unsigned int (*set_vga_decode)(void *cookie, bool state)); + +#endif /* LINUX_VGA_H */ -- cgit v1.2.3 From 260d703adc5f275e3ba7ddff6e2e0217bc613b35 Mon Sep 17 00:00:00 2001 From: Mike Mason Date: Thu, 30 Jul 2009 15:33:21 -0700 Subject: PCI: support for PCI Express fundamental reset This is the first of three patches that implement a bit field that PCI Express device drivers can use to indicate they need a fundamental reset during error recovery. By default, the EEH framework on powerpc does what's known as a "hot reset" during recovery of a PCI Express device. We've found a case where the device needs a "fundamental reset" to recover properly. The current PCI error recovery and EEH frameworks do not support this distinction. The attached patch (courtesy of Richard Lary) adds a bit field to pci_dev that indicates whether the device requires a fundamental reset during recovery. These patches supersede the previously submitted patch that implemented a fundamental reset bit field. Signed-off-by: Mike Mason Signed-off-by: Richard Lary Signed-off-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 6dbb1fd30e5..da90217a7b0 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -273,6 +273,7 @@ struct pci_dev { unsigned int ari_enabled:1; /* ARI forwarding */ unsigned int is_managed:1; unsigned int is_pcie:1; + unsigned int needs_freset:1; /* Dev requires fundamental reset */ unsigned int state_saved:1; unsigned int is_physfn:1; unsigned int is_virtfn:1; -- cgit v1.2.3 From 6ac3bd527007eeecb148b67ca47b21731fd8a503 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Wed, 19 Aug 2009 15:21:57 +1000 Subject: PCI/vgaarb: cleanup some warnings + cleanup some comments. Fix some warnings reported in linux-next + also cleanup some comment errors noticed by Pekka Paalanen. Signed-off-by: Dave Airlie Signed-off-by: Jesse Barnes --- include/linux/vgaarb.h | 49 +++++++++++++++++++++++++++---------------------- 1 file changed, 27 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vgaarb.h b/include/linux/vgaarb.h index 68229ce80fd..e81c64af80c 100644 --- a/include/linux/vgaarb.h +++ b/include/linux/vgaarb.h @@ -46,9 +46,9 @@ extern void vga_set_legacy_decoding(struct pci_dev *pdev, /** * vga_get - acquire & locks VGA resources * - * pdev: pci device of the VGA card or NULL for the system default - * rsrc: bit mask of resources to acquire and lock - * interruptible: blocking should be interruptible by signals ? + * @pdev: pci device of the VGA card or NULL for the system default + * @rsrc: bit mask of resources to acquire and lock + * @interruptible: blocking should be interruptible by signals ? * * This function acquires VGA resources for the given * card and mark those resources locked. If the resource requested @@ -81,19 +81,19 @@ extern int vga_get(struct pci_dev *pdev, unsigned int rsrc, */ static inline int vga_get_interruptible(struct pci_dev *pdev, - unsigned int rsrc) + unsigned int rsrc) { return vga_get(pdev, rsrc, 1); } /** - * vga_get_interruptible + * vga_get_uninterruptible * * Shortcut to vga_get */ static inline int vga_get_uninterruptible(struct pci_dev *pdev, - unsigned int rsrc) + unsigned int rsrc) { return vga_get(pdev, rsrc, 0); } @@ -165,28 +165,33 @@ static inline int vga_conflicts(struct pci_dev *p1, struct pci_dev *p2) } #endif -/* - * Register a client with the VGA arbitration logic - * return value: number of VGA devices in system. - * - * Clients have two callback mechanisms they can use. - * irq enable/disable callback - - * If a client can't disable its GPUs VGA resources, then we - * need to be able to ask it to turn off its irqs when we - * turn off its mem and io decoding. - * set_vga_decode - * If a client can disable its GPU VGA resource, it will - * get a callback from this to set the encode/decode state - * - * Clients with disable abilities should check the return value - * of this function and if the VGA device count is > 1, should - * disable VGA decoding resources. +/** + * vga_client_register + * + * @pdev: pci device of the VGA client + * @cookie: client cookie to be used in callbacks + * @irq_set_state: irq state change callback + * @set_vga_decode: vga decode change callback + * + * return value: 0 on success, -1 on failure + * Register a client with the VGA arbitration logic + * + * Clients have two callback mechanisms they can use. + * irq enable/disable callback - + * If a client can't disable its GPUs VGA resources, then we + * need to be able to ask it to turn off its irqs when we + * turn off its mem and io decoding. + * set_vga_decode + * If a client can disable its GPU VGA resource, it will + * get a callback from this to set the encode/decode state * * Rationale: we cannot disable VGA decode resources unconditionally * some single GPU laptops seem to require ACPI or BIOS access to the * VGA registers to control things like backlights etc. * Hopefully newer multi-GPU laptops do something saner, and desktops * won't have any special ACPI for this. + * They driver will get a callback when VGA arbitration is first used + * by userspace since we some older X servers have issues. */ int vga_client_register(struct pci_dev *pdev, void *cookie, void (*irq_set_state)(void *cookie, bool state), -- cgit v1.2.3 From 825c423a35a80a8fd66398a3f9bde7f0b0187a76 Mon Sep 17 00:00:00 2001 From: Kenji Kaneshige Date: Wed, 29 Jul 2009 14:39:58 +0900 Subject: PCI hotplug: add support for 5.0G link speed Add support for PCI-E 5.0 GT/s in max_bus_speed and cur_bus_speed. Reviewed-by: Matthew Wilcox Signed-off-by: Kenji Kaneshige Signed-off-by: Jesse Barnes --- include/linux/pci_hotplug.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h index 4391741b99d..1b00cc3177f 100644 --- a/include/linux/pci_hotplug.h +++ b/include/linux/pci_hotplug.h @@ -62,7 +62,8 @@ enum pcie_link_width { }; enum pcie_link_speed { - PCIE_2PT5GB = 0x14, + PCIE_2_5GB = 0x14, + PCIE_5_0GB = 0x15, PCIE_LNK_SPEED_UNKNOWN = 0xFF, }; -- cgit v1.2.3 From 9dba910e9de2c4aa15ec1286f10052c107ef48ca Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 3 Sep 2009 15:26:36 +0900 Subject: PCI: separate out pci_add_dynid() Separate out pci_add_dynid() from store_new_id() and export it so that in-kernel code can add PCI IDs dynamically. As the function will be available regardless of HOTPLUG, put it and pull pci_free_dynids() outside of CONFIG_HOTPLUG. This will be used by pci-stub to initialize initial IDs via module param. While at it, remove bogus get_driver() failure check. Signed-off-by: Tejun Heo Acked-by: Greg Kroah-Hartman Reviewed-by: Grant Grundler 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 da90217a7b0..d7566831770 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -796,6 +796,11 @@ int __must_check __pci_register_driver(struct pci_driver *, struct module *, void pci_unregister_driver(struct pci_driver *dev); void pci_remove_behind_bridge(struct pci_dev *dev); struct pci_driver *pci_dev_driver(const struct pci_dev *dev); +int pci_add_dynid(struct pci_driver *drv, + unsigned int vendor, unsigned int device, + unsigned int subvendor, unsigned int subdevice, + unsigned int class, unsigned int class_mask, + unsigned long driver_data); const struct pci_device_id *pci_match_id(const struct pci_device_id *ids, struct pci_dev *dev); int pci_scan_bridge(struct pci_bus *bus, struct pci_dev *dev, int max, -- cgit v1.2.3 From 28760489a3f1e136c5ae8581c0fa8f63511f2f4c Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 9 Sep 2009 14:09:24 -0700 Subject: PCI: pcie: Ensure hotplug ports have a minimum number of resources In general a BIOS may goof or we may hotplug in a hotplug controller. In either case the kernel needs to reserve resources for plugging in more devices in the future instead of creating a minimal resource assignment. We already do this for cardbus bridges I am just adding a variant for pcie bridges. v2: Make testing for pcie hotplug bridges based on a flag. So far we only set the flag for pcie but a header_quirk could easily be added for the non-standard pci hotplug bridges. Signed-off-by: Eric W. Biederman Signed-off-by: Jesse Barnes --- include/linux/pci.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index d7566831770..d80ed872a3c 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -278,6 +278,7 @@ struct pci_dev { unsigned int is_physfn:1; unsigned int is_virtfn:1; unsigned int reset_fn:1; + unsigned int is_hotplug_bridge:1; pci_dev_flags_t dev_flags; atomic_t enable_cnt; /* pci_enable_device has been called */ @@ -1245,6 +1246,9 @@ extern int pci_pci_problems; extern unsigned long pci_cardbus_io_size; extern unsigned long pci_cardbus_mem_size; +extern unsigned long pci_hotplug_io_size; +extern unsigned long pci_hotplug_mem_size; + int pcibios_add_platform_entries(struct pci_dev *dev); void pcibios_disable_device(struct pci_dev *dev); int pcibios_set_pcie_reset_state(struct pci_dev *dev, -- cgit v1.2.3 From e80bb09d2c73d76a2a4cd79e4a83802dd901c642 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 8 Sep 2009 23:14:49 +0200 Subject: PCI PM: Introduce device flag wakeup_prepared Introduce a new PCI device flag, wakeup_prepared, to prevent PCI wake-up preparation code from being executed twice in a row for the same device and for the same purpose. Reviewed-by: Matthew Garrett Signed-off-by: Rafael J. Wysocki Signed-off-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 d80ed872a3c..f5c7cd343e5 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -241,6 +241,7 @@ struct pci_dev { unsigned int d1_support:1; /* Low power state D1 is supported */ unsigned int d2_support:1; /* Low power state D2 is supported */ unsigned int no_d1d2:1; /* Only allow D0 and D3 */ + unsigned int wakeup_prepared:1; #ifdef CONFIG_PCIEASPM struct pcie_link_state *link_state; /* ASPM link state. */ -- cgit v1.2.3 From 48659d31195bb76d688e99dabd816c5472fb1656 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 11 Sep 2009 11:36:23 -0400 Subject: tracing: move tgid out of generic entry and into userstack The userstack trace required the recording of the tgid entry. Unfortunately, it was added to the generic entry where it wasted 4 bytes of every entry and was only used by one entry. This patch moves it out of the generic field and moves it into the only user (userstack_entry). Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 23f7179bf74..06c795b536c 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -34,7 +34,6 @@ struct trace_entry { unsigned char flags; unsigned char preempt_count; int pid; - int tgid; }; #define FTRACE_MAX_EVENT \ -- cgit v1.2.3 From 637e7e864103a7a68c1ce43ada27dfc25c0d113f Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 11 Sep 2009 13:55:35 -0400 Subject: tracing: add lock depth to entries This patch adds the lock depth of the big kernel lock to the generic entry header. This way we can see the depth of the lock and help in removing the BKL. Example: # _------=> CPU# # / _-----=> irqs-off # | / _----=> need-resched # || / _---=> hardirq/softirq # ||| / _--=> preempt-depth # |||| /_--=> lock-depth # |||||/ delay # cmd pid |||||| time | caller # \ / |||||| \ | / -0 2.N..3 5902255250us+: lock_acquire: read rcu_read_lock -0 2.N..3 5902255253us+: lock_release: rcu_read_lock -0 2dN..3 5902255257us+: lock_acquire: xtime_lock -0 2dN..4 5902255259us : lock_acquire: clocksource_lock -0 2dN..4 5902255261us+: lock_release: clocksource_lock Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 06c795b536c..0608b0ff263 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -34,6 +34,7 @@ struct trace_entry { unsigned char flags; unsigned char preempt_count; int pid; + int lock_depth; }; #define FTRACE_MAX_EVENT \ -- cgit v1.2.3 From 65dd2f93febf6345ce9e39d2f6e35ce1122f4a4a Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 30 Jun 2009 16:14:17 -0300 Subject: V4L/DVB (12149): videodev2.h: Reorganize fourcc table With the changes this file suffered along the time, things got a little disorganized. In particular, V4L2_PIX_FMT_YVYU were shown as a device-specific format, instead of yet another variant of YUV. There's no functional change on this patch. It just adds some comments and reorder fourcc formats to their proper places. Signed-off-by: Mauro Carvalho Chehab --- include/linux/videodev2.h | 39 ++++++++++++++++++++++----------------- 1 file changed, 22 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h index 74f16876f38..eddd5ff99c8 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -275,7 +275,9 @@ struct v4l2_pix_format { __u32 priv; /* private data, depends on pixelformat */ }; -/* Pixel format FOURCC depth Description */ +/* Pixel format FOURCC depth Description */ + +/* RGB formats */ #define V4L2_PIX_FMT_RGB332 v4l2_fourcc('R', 'G', 'B', '1') /* 8 RGB-3-3-2 */ #define V4L2_PIX_FMT_RGB444 v4l2_fourcc('R', '4', '4', '4') /* 16 xxxxrrrr ggggbbbb */ #define V4L2_PIX_FMT_RGB555 v4l2_fourcc('R', 'G', 'B', 'O') /* 16 RGB-5-5-5 */ @@ -286,12 +288,20 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_RGB24 v4l2_fourcc('R', 'G', 'B', '3') /* 24 RGB-8-8-8 */ #define V4L2_PIX_FMT_BGR32 v4l2_fourcc('B', 'G', 'R', '4') /* 32 BGR-8-8-8-8 */ #define V4L2_PIX_FMT_RGB32 v4l2_fourcc('R', 'G', 'B', '4') /* 32 RGB-8-8-8-8 */ + +/* Grey formats */ #define V4L2_PIX_FMT_GREY v4l2_fourcc('G', 'R', 'E', 'Y') /* 8 Greyscale */ #define V4L2_PIX_FMT_Y16 v4l2_fourcc('Y', '1', '6', ' ') /* 16 Greyscale */ + +/* Palette formats */ #define V4L2_PIX_FMT_PAL8 v4l2_fourcc('P', 'A', 'L', '8') /* 8 8-bit palette */ + +/* Luminance+Chrominance formats */ #define V4L2_PIX_FMT_YVU410 v4l2_fourcc('Y', 'V', 'U', '9') /* 9 YVU 4:1:0 */ #define V4L2_PIX_FMT_YVU420 v4l2_fourcc('Y', 'V', '1', '2') /* 12 YVU 4:2:0 */ #define V4L2_PIX_FMT_YUYV v4l2_fourcc('Y', 'U', 'Y', 'V') /* 16 YUV 4:2:2 */ +#define V4L2_PIX_FMT_YYUV v4l2_fourcc('Y', 'Y', 'U', 'V') /* 16 YUV 4:2:2 */ +#define V4L2_PIX_FMT_YVYU v4l2_fourcc('Y', 'V', 'Y', 'U') /* 16 YVU 4:2:2 */ #define V4L2_PIX_FMT_UYVY v4l2_fourcc('U', 'Y', 'V', 'Y') /* 16 YUV 4:2:2 */ #define V4L2_PIX_FMT_VYUY v4l2_fourcc('V', 'Y', 'U', 'Y') /* 16 YUV 4:2:2 */ #define V4L2_PIX_FMT_YUV422P v4l2_fourcc('4', '2', '2', 'P') /* 16 YVU422 planar */ @@ -301,6 +311,10 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_YUV555 v4l2_fourcc('Y', 'U', 'V', 'O') /* 16 YUV-5-5-5 */ #define V4L2_PIX_FMT_YUV565 v4l2_fourcc('Y', 'U', 'V', 'P') /* 16 YUV-5-6-5 */ #define V4L2_PIX_FMT_YUV32 v4l2_fourcc('Y', 'U', 'V', '4') /* 32 YUV-8-8-8-8 */ +#define V4L2_PIX_FMT_YUV410 v4l2_fourcc('Y', 'U', 'V', '9') /* 9 YUV 4:1:0 */ +#define V4L2_PIX_FMT_YUV420 v4l2_fourcc('Y', 'U', '1', '2') /* 12 YUV 4:2:0 */ +#define V4L2_PIX_FMT_HI240 v4l2_fourcc('H', 'I', '2', '4') /* 8 8-bit color */ +#define V4L2_PIX_FMT_HM12 v4l2_fourcc('H', 'M', '1', '2') /* 8 YUV 4:2:0 16x16 macroblocks */ /* two planes -- one Y, one Cr + Cb interleaved */ #define V4L2_PIX_FMT_NV12 v4l2_fourcc('N', 'V', '1', '2') /* 12 Y/CbCr 4:2:0 */ @@ -308,25 +322,17 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_NV16 v4l2_fourcc('N', 'V', '1', '6') /* 16 Y/CbCr 4:2:2 */ #define V4L2_PIX_FMT_NV61 v4l2_fourcc('N', 'V', '6', '1') /* 16 Y/CrCb 4:2:2 */ -/* The following formats are not defined in the V4L2 specification */ -#define V4L2_PIX_FMT_YUV410 v4l2_fourcc('Y', 'U', 'V', '9') /* 9 YUV 4:1:0 */ -#define V4L2_PIX_FMT_YUV420 v4l2_fourcc('Y', 'U', '1', '2') /* 12 YUV 4:2:0 */ -#define V4L2_PIX_FMT_YYUV v4l2_fourcc('Y', 'Y', 'U', 'V') /* 16 YUV 4:2:2 */ -#define V4L2_PIX_FMT_HI240 v4l2_fourcc('H', 'I', '2', '4') /* 8 8-bit color */ -#define V4L2_PIX_FMT_HM12 v4l2_fourcc('H', 'M', '1', '2') /* 8 YUV 4:2:0 16x16 macroblocks */ - -/* see http://www.siliconimaging.com/RGB%20Bayer.htm */ +/* Bayer formats - see http://www.siliconimaging.com/RGB%20Bayer.htm */ #define V4L2_PIX_FMT_SBGGR8 v4l2_fourcc('B', 'A', '8', '1') /* 8 BGBG.. GRGR.. */ #define V4L2_PIX_FMT_SGBRG8 v4l2_fourcc('G', 'B', 'R', 'G') /* 8 GBGB.. RGRG.. */ #define V4L2_PIX_FMT_SGRBG8 v4l2_fourcc('G', 'R', 'B', 'G') /* 8 GRGR.. BGBG.. */ - -/* - * 10bit raw bayer, expanded to 16 bits - * xxxxrrrrrrrrrrxxxxgggggggggg xxxxggggggggggxxxxbbbbbbbbbb... - */ -#define V4L2_PIX_FMT_SGRBG10 v4l2_fourcc('B', 'A', '1', '0') -/* 10bit raw bayer DPCM compressed to 8 bits */ +#define V4L2_PIX_FMT_SGRBG10 v4l2_fourcc('B', 'A', '1', '0') /* 10bit raw bayer */ + /* 10bit raw bayer DPCM compressed to 8 bits */ #define V4L2_PIX_FMT_SGRBG10DPCM8 v4l2_fourcc('B', 'D', '1', '0') + /* + * 10bit raw bayer, expanded to 16 bits + * xxxxrrrrrrrrrrxxxxgggggggggg xxxxggggggggggxxxxbbbbbbbbbb... + */ #define V4L2_PIX_FMT_SBGGR16 v4l2_fourcc('B', 'Y', 'R', '2') /* 16 BGBG.. GRGR.. */ /* compressed formats */ @@ -350,7 +356,6 @@ struct v4l2_pix_format { #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 */ #define V4L2_PIX_FMT_OV511 v4l2_fourcc('O', '5', '1', '1') /* ov511 JPEG */ #define V4L2_PIX_FMT_OV518 v4l2_fourcc('O', '5', '1', '8') /* ov518 JPEG */ -- cgit v1.2.3 From de05f63430e8cb8cde0a21260bc6b01765111e5c Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Fri, 26 Jun 2009 12:15:38 -0300 Subject: V4L/DVB (12187): uvcvideo: Move UVC definitions to linux/usb/video.h To make UVC constants accessible by a future UVC gadget driver, move them from drivers/media/video/uvc/uvcvideo.h to include/linux/usb/video.h. Signed-off-by: Laurent Pinchart Signed-off-by: Mauro Carvalho Chehab --- include/linux/usb/video.h | 164 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 164 insertions(+) create mode 100644 include/linux/usb/video.h (limited to 'include/linux') diff --git a/include/linux/usb/video.h b/include/linux/usb/video.h new file mode 100644 index 00000000000..be436d9ee47 --- /dev/null +++ b/include/linux/usb/video.h @@ -0,0 +1,164 @@ +/* + * USB Video Class definitions. + * + * Copyright (C) 2009 Laurent Pinchart + * + * This file holds USB constants and structures defined by the USB Device + * Class Definition for Video Devices. Unless otherwise stated, comments + * below reference relevant sections of the USB Video Class 1.1 specification + * available at + * + * http://www.usb.org/developers/devclass_docs/USB_Video_Class_1_1.zip + */ + +#ifndef __LINUX_USB_VIDEO_H +#define __LINUX_USB_VIDEO_H + +#include + +/* -------------------------------------------------------------------------- + * UVC constants + */ + +/* A.2. Video Interface Subclass Codes */ +#define UVC_SC_UNDEFINED 0x00 +#define UVC_SC_VIDEOCONTROL 0x01 +#define UVC_SC_VIDEOSTREAMING 0x02 +#define UVC_SC_VIDEO_INTERFACE_COLLECTION 0x03 + +/* A.3. Video Interface Protocol Codes */ +#define UVC_PC_PROTOCOL_UNDEFINED 0x00 + +/* A.5. Video Class-Specific VC Interface Descriptor Subtypes */ +#define UVC_VC_DESCRIPTOR_UNDEFINED 0x00 +#define UVC_VC_HEADER 0x01 +#define UVC_VC_INPUT_TERMINAL 0x02 +#define UVC_VC_OUTPUT_TERMINAL 0x03 +#define UVC_VC_SELECTOR_UNIT 0x04 +#define UVC_VC_PROCESSING_UNIT 0x05 +#define UVC_VC_EXTENSION_UNIT 0x06 + +/* A.6. Video Class-Specific VS Interface Descriptor Subtypes */ +#define UVC_VS_UNDEFINED 0x00 +#define UVC_VS_INPUT_HEADER 0x01 +#define UVC_VS_OUTPUT_HEADER 0x02 +#define UVC_VS_STILL_IMAGE_FRAME 0x03 +#define UVC_VS_FORMAT_UNCOMPRESSED 0x04 +#define UVC_VS_FRAME_UNCOMPRESSED 0x05 +#define UVC_VS_FORMAT_MJPEG 0x06 +#define UVC_VS_FRAME_MJPEG 0x07 +#define UVC_VS_FORMAT_MPEG2TS 0x0a +#define UVC_VS_FORMAT_DV 0x0c +#define UVC_VS_COLORFORMAT 0x0d +#define UVC_VS_FORMAT_FRAME_BASED 0x10 +#define UVC_VS_FRAME_FRAME_BASED 0x11 +#define UVC_VS_FORMAT_STREAM_BASED 0x12 + +/* A.7. Video Class-Specific Endpoint Descriptor Subtypes */ +#define UVC_EP_UNDEFINED 0x00 +#define UVC_EP_GENERAL 0x01 +#define UVC_EP_ENDPOINT 0x02 +#define UVC_EP_INTERRUPT 0x03 + +/* A.8. Video Class-Specific Request Codes */ +#define UVC_RC_UNDEFINED 0x00 +#define UVC_SET_CUR 0x01 +#define UVC_GET_CUR 0x81 +#define UVC_GET_MIN 0x82 +#define UVC_GET_MAX 0x83 +#define UVC_GET_RES 0x84 +#define UVC_GET_LEN 0x85 +#define UVC_GET_INFO 0x86 +#define UVC_GET_DEF 0x87 + +/* A.9.1. VideoControl Interface Control Selectors */ +#define UVC_VC_CONTROL_UNDEFINED 0x00 +#define UVC_VC_VIDEO_POWER_MODE_CONTROL 0x01 +#define UVC_VC_REQUEST_ERROR_CODE_CONTROL 0x02 + +/* A.9.2. Terminal Control Selectors */ +#define UVC_TE_CONTROL_UNDEFINED 0x00 + +/* A.9.3. Selector Unit Control Selectors */ +#define UVC_SU_CONTROL_UNDEFINED 0x00 +#define UVC_SU_INPUT_SELECT_CONTROL 0x01 + +/* A.9.4. Camera Terminal Control Selectors */ +#define UVC_CT_CONTROL_UNDEFINED 0x00 +#define UVC_CT_SCANNING_MODE_CONTROL 0x01 +#define UVC_CT_AE_MODE_CONTROL 0x02 +#define UVC_CT_AE_PRIORITY_CONTROL 0x03 +#define UVC_CT_EXPOSURE_TIME_ABSOLUTE_CONTROL 0x04 +#define UVC_CT_EXPOSURE_TIME_RELATIVE_CONTROL 0x05 +#define UVC_CT_FOCUS_ABSOLUTE_CONTROL 0x06 +#define UVC_CT_FOCUS_RELATIVE_CONTROL 0x07 +#define UVC_CT_FOCUS_AUTO_CONTROL 0x08 +#define UVC_CT_IRIS_ABSOLUTE_CONTROL 0x09 +#define UVC_CT_IRIS_RELATIVE_CONTROL 0x0a +#define UVC_CT_ZOOM_ABSOLUTE_CONTROL 0x0b +#define UVC_CT_ZOOM_RELATIVE_CONTROL 0x0c +#define UVC_CT_PANTILT_ABSOLUTE_CONTROL 0x0d +#define UVC_CT_PANTILT_RELATIVE_CONTROL 0x0e +#define UVC_CT_ROLL_ABSOLUTE_CONTROL 0x0f +#define UVC_CT_ROLL_RELATIVE_CONTROL 0x10 +#define UVC_CT_PRIVACY_CONTROL 0x11 + +/* A.9.5. Processing Unit Control Selectors */ +#define UVC_PU_CONTROL_UNDEFINED 0x00 +#define UVC_PU_BACKLIGHT_COMPENSATION_CONTROL 0x01 +#define UVC_PU_BRIGHTNESS_CONTROL 0x02 +#define UVC_PU_CONTRAST_CONTROL 0x03 +#define UVC_PU_GAIN_CONTROL 0x04 +#define UVC_PU_POWER_LINE_FREQUENCY_CONTROL 0x05 +#define UVC_PU_HUE_CONTROL 0x06 +#define UVC_PU_SATURATION_CONTROL 0x07 +#define UVC_PU_SHARPNESS_CONTROL 0x08 +#define UVC_PU_GAMMA_CONTROL 0x09 +#define UVC_PU_WHITE_BALANCE_TEMPERATURE_CONTROL 0x0a +#define UVC_PU_WHITE_BALANCE_TEMPERATURE_AUTO_CONTROL 0x0b +#define UVC_PU_WHITE_BALANCE_COMPONENT_CONTROL 0x0c +#define UVC_PU_WHITE_BALANCE_COMPONENT_AUTO_CONTROL 0x0d +#define UVC_PU_DIGITAL_MULTIPLIER_CONTROL 0x0e +#define UVC_PU_DIGITAL_MULTIPLIER_LIMIT_CONTROL 0x0f +#define UVC_PU_HUE_AUTO_CONTROL 0x10 +#define UVC_PU_ANALOG_VIDEO_STANDARD_CONTROL 0x11 +#define UVC_PU_ANALOG_LOCK_STATUS_CONTROL 0x12 + +/* A.9.7. VideoStreaming Interface Control Selectors */ +#define UVC_VS_CONTROL_UNDEFINED 0x00 +#define UVC_VS_PROBE_CONTROL 0x01 +#define UVC_VS_COMMIT_CONTROL 0x02 +#define UVC_VS_STILL_PROBE_CONTROL 0x03 +#define UVC_VS_STILL_COMMIT_CONTROL 0x04 +#define UVC_VS_STILL_IMAGE_TRIGGER_CONTROL 0x05 +#define UVC_VS_STREAM_ERROR_CODE_CONTROL 0x06 +#define UVC_VS_GENERATE_KEY_FRAME_CONTROL 0x07 +#define UVC_VS_UPDATE_FRAME_SEGMENT_CONTROL 0x08 +#define UVC_VS_SYNC_DELAY_CONTROL 0x09 + +/* B.1. USB Terminal Types */ +#define UVC_TT_VENDOR_SPECIFIC 0x0100 +#define UVC_TT_STREAMING 0x0101 + +/* B.2. Input Terminal Types */ +#define UVC_ITT_VENDOR_SPECIFIC 0x0200 +#define UVC_ITT_CAMERA 0x0201 +#define UVC_ITT_MEDIA_TRANSPORT_INPUT 0x0202 + +/* B.3. Output Terminal Types */ +#define UVC_OTT_VENDOR_SPECIFIC 0x0300 +#define UVC_OTT_DISPLAY 0x0301 +#define UVC_OTT_MEDIA_TRANSPORT_OUTPUT 0x0302 + +/* B.4. External Terminal Types */ +#define UVC_EXTERNAL_VENDOR_SPECIFIC 0x0400 +#define UVC_COMPOSITE_CONNECTOR 0x0401 +#define UVC_SVIDEO_CONNECTOR 0x0402 +#define UVC_COMPONENT_CONNECTOR 0x0403 + +/* 2.4.2.2. Status Packet Type */ +#define UVC_STATUS_TYPE_CONTROL 1 +#define UVC_STATUS_TYPE_STREAMING 2 + +#endif /* __LINUX_USB_VIDEO_H */ + -- cgit v1.2.3 From ef5b5b7e73038f2c7d0d1b020c6eac6435c2b552 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Sat, 20 Jun 2009 05:37:27 -0300 Subject: V4L/DVB (12212): v4l2: add RDS API to videodev2.h Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/linux/videodev2.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h index eddd5ff99c8..22fc99d58d3 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -1186,6 +1186,7 @@ struct v4l2_modulator { #define V4L2_TUNER_CAP_LANG2 0x0020 #define V4L2_TUNER_CAP_SAP 0x0020 #define V4L2_TUNER_CAP_LANG1 0x0040 +#define V4L2_TUNER_CAP_RDS 0x0080 /* Flags for the 'rxsubchans' field */ #define V4L2_TUNER_SUB_MONO 0x0001 @@ -1193,6 +1194,7 @@ struct v4l2_modulator { #define V4L2_TUNER_SUB_LANG2 0x0004 #define V4L2_TUNER_SUB_SAP 0x0004 #define V4L2_TUNER_SUB_LANG1 0x0008 +#define V4L2_TUNER_SUB_RDS 0x0010 /* Values for the 'audmode' field */ #define V4L2_TUNER_MODE_MONO 0x0000 @@ -1217,6 +1219,27 @@ struct v4l2_hw_freq_seek { __u32 reserved[8]; }; +/* + * R D S + */ + +struct v4l2_rds_data { + __u8 lsb; + __u8 msb; + __u8 block; +} __attribute__ ((packed)); + +#define V4L2_RDS_BLOCK_MSK 0x7 +#define V4L2_RDS_BLOCK_A 0 +#define V4L2_RDS_BLOCK_B 1 +#define V4L2_RDS_BLOCK_C 2 +#define V4L2_RDS_BLOCK_D 3 +#define V4L2_RDS_BLOCK_C_ALT 4 +#define V4L2_RDS_BLOCK_INVALID 7 + +#define V4L2_RDS_BLOCK_CORRECTED 0x40 +#define V4L2_RDS_BLOCK_ERROR 0x80 + /* * A U D I O */ -- cgit v1.2.3 From 1cb662a3144992259edfd3cf9f54a6b25a913a0f Mon Sep 17 00:00:00 2001 From: Andreas Oberritter Date: Tue, 14 Jul 2009 20:28:50 -0300 Subject: V4L/DVB (12275): Add two new ioctls: DMX_ADD_PID and DMX_REMOVE_PID DMX_ADD_PID allows to add multiple PIDs to a transport stream filter previously set up with DMX_SET_PES_FILTER and output=DMX_OUT_TSDEMUX_TAP. DMX_REMOVE_PID is used to drop a PID from a filter. These ioctls are to be used by readers of /dev/dvb/adapterX/demuxY. They may be called at any time, i.e. before or after the first filter on the shared file descriptor was started. They make it possible to record multiple services without the need to de- or re-multiplex TS packets. To accomplish this, dmxdev_filter->feed.ts has been converted to a list of struct dmxdev_feeds, each containing a PID value and a pointer to a struct dmx_ts_feed. Signed-off-by: Andreas Oberritter Signed-off-by: Mauro Carvalho Chehab --- include/linux/dvb/dmx.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dvb/dmx.h b/include/linux/dvb/dmx.h index fef943738a2..f078f3ac82d 100644 --- a/include/linux/dvb/dmx.h +++ b/include/linux/dvb/dmx.h @@ -151,5 +151,7 @@ struct dmx_stc { #define DMX_GET_CAPS _IOR('o', 48, dmx_caps_t) #define DMX_SET_SOURCE _IOW('o', 49, dmx_source_t) #define DMX_GET_STC _IOWR('o', 50, struct dmx_stc) +#define DMX_ADD_PID _IOW('o', 51, __u16) +#define DMX_REMOVE_PID _IOW('o', 52, __u16) #endif /*_DVBDMX_H_*/ -- cgit v1.2.3 From 6ace40effd34331a604c5eeae90838cf8dd7eb8f Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Sat, 20 Jun 2009 09:50:39 -0300 Subject: V4L/DVB (12316): v4l: add V4L2_CAP_RDS_OUTPUT and V4L2_CAP_MODULATOR caps Add capabilities to describe an FM transmitter device. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/linux/videodev2.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h index 22fc99d58d3..293ba181f95 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -252,10 +252,12 @@ struct v4l2_capability { #define V4L2_CAP_RDS_CAPTURE 0x00000100 /* RDS data capture */ #define V4L2_CAP_VIDEO_OUTPUT_OVERLAY 0x00000200 /* Can do video output overlay */ #define V4L2_CAP_HW_FREQ_SEEK 0x00000400 /* Can do hardware frequency seek */ +#define V4L2_CAP_RDS_OUTPUT 0x00000800 /* Is an RDS encoder */ #define V4L2_CAP_TUNER 0x00010000 /* has a tuner */ #define V4L2_CAP_AUDIO 0x00020000 /* has audio support */ #define V4L2_CAP_RADIO 0x00040000 /* is a radio device */ +#define V4L2_CAP_MODULATOR 0x00080000 /* has a modulator */ #define V4L2_CAP_READWRITE 0x01000000 /* read/write systemcalls */ #define V4L2_CAP_ASYNCIO 0x02000000 /* async I/O */ -- cgit v1.2.3 From 6b5a9492ca0c991bab1ac495624e17520e9edf18 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Tue, 11 Aug 2009 18:47:18 -0300 Subject: V4L/DVB (12543): v4l: introduce string control support. The upcoming RDS encoder needs support for string controls. This patch implements the core implementation. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/linux/videodev2.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h index 293ba181f95..9ab4cbe676f 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -167,6 +167,7 @@ enum v4l2_ctrl_type { V4L2_CTRL_TYPE_BUTTON = 4, V4L2_CTRL_TYPE_INTEGER64 = 5, V4L2_CTRL_TYPE_CTRL_CLASS = 6, + V4L2_CTRL_TYPE_STRING = 7, }; enum v4l2_tuner_type { @@ -795,11 +796,12 @@ struct v4l2_control { struct v4l2_ext_control { __u32 id; - __u32 reserved2[2]; + __u32 size; + __u32 reserved2[1]; union { __s32 value; __s64 value64; - void *reserved; + char *string; }; } __attribute__ ((packed)); -- cgit v1.2.3 From 6b4249413abb634d9b2ff44c685da744f02e49d1 Mon Sep 17 00:00:00 2001 From: Eduardo Valentin Date: Sat, 8 Aug 2009 08:38:58 -0300 Subject: V4L/DVB (12548): v4l2: video device: Add V4L2_CTRL_CLASS_FM_TX controls This patch adds a new class of extended controls. This class is intended to support FM Radio Modulators properties such as: rds, audio limiters, audio compression, pilot tone generation, tuning power levels and preemphasis properties. Signed-off-by: Eduardo Valentin Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/linux/videodev2.h | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 'include/linux') diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h index 9ab4cbe676f..5758066cb57 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -817,6 +817,7 @@ struct v4l2_ext_controls { #define V4L2_CTRL_CLASS_USER 0x00980000 /* Old-style 'user' controls */ #define V4L2_CTRL_CLASS_MPEG 0x00990000 /* MPEG-compression controls */ #define V4L2_CTRL_CLASS_CAMERA 0x009a0000 /* Camera class controls */ +#define V4L2_CTRL_CLASS_FM_TX 0x009b0000 /* FM Modulator control class */ #define V4L2_CTRL_ID_MASK (0x0fffffff) #define V4L2_CTRL_ID2CLASS(id) ((id) & 0x0fff0000UL) @@ -1156,6 +1157,39 @@ enum v4l2_exposure_auto_type { #define V4L2_CID_PRIVACY (V4L2_CID_CAMERA_CLASS_BASE+16) +/* FM Modulator class control IDs */ +#define V4L2_CID_FM_TX_CLASS_BASE (V4L2_CTRL_CLASS_FM_TX | 0x900) +#define V4L2_CID_FM_TX_CLASS (V4L2_CTRL_CLASS_FM_TX | 1) + +#define V4L2_CID_RDS_TX_DEVIATION (V4L2_CID_FM_TX_CLASS_BASE + 1) +#define V4L2_CID_RDS_TX_PI (V4L2_CID_FM_TX_CLASS_BASE + 2) +#define V4L2_CID_RDS_TX_PTY (V4L2_CID_FM_TX_CLASS_BASE + 3) +#define V4L2_CID_RDS_TX_PS_NAME (V4L2_CID_FM_TX_CLASS_BASE + 5) +#define V4L2_CID_RDS_TX_RADIO_TEXT (V4L2_CID_FM_TX_CLASS_BASE + 6) + +#define V4L2_CID_AUDIO_LIMITER_ENABLED (V4L2_CID_FM_TX_CLASS_BASE + 64) +#define V4L2_CID_AUDIO_LIMITER_RELEASE_TIME (V4L2_CID_FM_TX_CLASS_BASE + 65) +#define V4L2_CID_AUDIO_LIMITER_DEVIATION (V4L2_CID_FM_TX_CLASS_BASE + 66) + +#define V4L2_CID_AUDIO_COMPRESSION_ENABLED (V4L2_CID_FM_TX_CLASS_BASE + 80) +#define V4L2_CID_AUDIO_COMPRESSION_GAIN (V4L2_CID_FM_TX_CLASS_BASE + 81) +#define V4L2_CID_AUDIO_COMPRESSION_THRESHOLD (V4L2_CID_FM_TX_CLASS_BASE + 82) +#define V4L2_CID_AUDIO_COMPRESSION_ATTACK_TIME (V4L2_CID_FM_TX_CLASS_BASE + 83) +#define V4L2_CID_AUDIO_COMPRESSION_RELEASE_TIME (V4L2_CID_FM_TX_CLASS_BASE + 84) + +#define V4L2_CID_PILOT_TONE_ENABLED (V4L2_CID_FM_TX_CLASS_BASE + 96) +#define V4L2_CID_PILOT_TONE_DEVIATION (V4L2_CID_FM_TX_CLASS_BASE + 97) +#define V4L2_CID_PILOT_TONE_FREQUENCY (V4L2_CID_FM_TX_CLASS_BASE + 98) + +#define V4L2_CID_TUNE_PREEMPHASIS (V4L2_CID_FM_TX_CLASS_BASE + 112) +enum v4l2_preemphasis { + V4L2_PREEMPHASIS_DISABLED = 0, + V4L2_PREEMPHASIS_50_uS = 1, + V4L2_PREEMPHASIS_75_uS = 2, +}; +#define V4L2_CID_TUNE_POWER_LEVEL (V4L2_CID_FM_TX_CLASS_BASE + 113) +#define V4L2_CID_TUNE_ANTENNA_CAPACITOR (V4L2_CID_FM_TX_CLASS_BASE + 114) + /* * T U N I N G */ -- cgit v1.2.3 From 1e3c1f7695a446742e24ea1f0c80715be98edbc4 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Mon, 31 Aug 2009 11:32:46 -0300 Subject: V4L/DVB (12625): Add new V4L2_FMT_FLAG_EMULATED flag to videodev2.h V4L2_FMT_FLAG_EMULATED 0x0002 This format is not native to the device but emulated through software (usually libv4l2), where possible try to use a native format instead for better performance. Signed-off-by: Hans de Goede 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 5758066cb57..3689d7d81fe 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -375,6 +375,7 @@ struct v4l2_fmtdesc { }; #define V4L2_FMT_FLAG_COMPRESSED 0x0001 +#define V4L2_FMT_FLAG_EMULATED 0x0002 #if 1 /* Experimental Frame Size and frame rate enumeration */ -- cgit v1.2.3 From 16bb8eb1b73bf940d30ff88cae622bfcd3790f61 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Sat, 12 Sep 2009 19:04:54 -0400 Subject: tracing: allow filter predicates to handle ksym symbols This patch increases the max string used by predicates to handle KSYM_SYMBOL_LEN. Also moves an include to look nicer. Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 0608b0ff263..bd099ba82cc 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -1,8 +1,8 @@ #ifndef _LINUX_FTRACE_EVENT_H #define _LINUX_FTRACE_EVENT_H -#include #include +#include #include struct trace_array; @@ -135,7 +135,7 @@ struct ftrace_event_call { }; #define MAX_FILTER_PRED 32 -#define MAX_FILTER_STR_VAL 128 +#define MAX_FILTER_STR_VAL 256 /* Should handle KSYM_SYMBOL_LEN */ extern void destroy_preds(struct ftrace_event_call *call); extern int filter_match_preds(struct ftrace_event_call *call, void *rec); -- cgit v1.2.3 From 7f53866932fd08add06ee2f93ead129949158490 Mon Sep 17 00:00:00 2001 From: Alex Chiang Date: Thu, 10 Sep 2009 12:34:09 -0600 Subject: PCI Hotplug: convert acpi_pci_detect_ejectable() to take an acpi_handle acpi_pci_detect_ejectable() goes through effort to convert its struct pci_bus arg to an acpi_handle, but every time we use this interface, we already have the handle available. So let's just use the handle instead of converting back and forth. Reviewed-by: Kenji Kaneshige Tested-by: Kenji Kaneshige Signed-off-by: Alex Chiang Signed-off-by: Jesse Barnes --- include/linux/pci_hotplug.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h index 1b00cc3177f..f0c31ae3f84 100644 --- a/include/linux/pci_hotplug.h +++ b/include/linux/pci_hotplug.h @@ -231,7 +231,7 @@ extern acpi_status acpi_get_hp_params_from_firmware(struct pci_bus *bus, struct hotplug_params *hpp); int acpi_get_hp_hw_control_from_firmware(struct pci_dev *dev, u32 flags); int acpi_pci_check_ejectable(struct pci_bus *pbus, acpi_handle handle); -int acpi_pci_detect_ejectable(struct pci_bus *pbus); +int acpi_pci_detect_ejectable(acpi_handle handle); #endif #endif -- cgit v1.2.3 From d136f1bd366fdb7e747ca7e0218171e7a00a98a5 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Sat, 12 Sep 2009 03:03:15 +0000 Subject: genetlink: fix netns vs. netlink table locking Since my commits introducing netns awareness into genetlink we can get this problem: BUG: scheduling while atomic: modprobe/1178/0x00000002 2 locks held by modprobe/1178: #0: (genl_mutex){+.+.+.}, at: [] genl_register_mc_grou #1: (rcu_read_lock){.+.+..}, at: [] genl_register_mc_g Pid: 1178, comm: modprobe Not tainted 2.6.31-rc8-wl-34789-g95cb731-dirty # Call Trace: [] __schedule_bug+0x85/0x90 [] schedule+0x108/0x588 [] netlink_table_grab+0xa1/0xf0 [] netlink_change_ngroups+0x47/0x100 [] genl_register_mc_group+0x12f/0x290 because I overlooked that netlink_table_grab() will schedule, thinking it was just the rwlock. However, in the contention case, that isn't actually true. Fix this by letting the code grab the netlink table lock first and then the RCU for netns protection. Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- include/linux/netlink.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 0fbecbbe8e9..080f6ba9e73 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -176,12 +176,16 @@ struct netlink_skb_parms #define NETLINK_CREDS(skb) (&NETLINK_CB((skb)).creds) +extern void netlink_table_grab(void); +extern void netlink_table_ungrab(void); + extern struct sock *netlink_kernel_create(struct net *net, int unit,unsigned int groups, void (*input)(struct sk_buff *skb), struct mutex *cb_mutex, struct module *module); extern void netlink_kernel_release(struct sock *sk); +extern int __netlink_change_ngroups(struct sock *sk, unsigned int groups); extern int netlink_change_ngroups(struct sock *sk, unsigned int groups); extern void netlink_clear_multicast_users(struct sock *sk, unsigned int group); extern void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err); -- cgit v1.2.3 From 6a29172ba90e49c046245610caff9848307bfd6a Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Mon, 14 Sep 2009 16:35:15 -0600 Subject: PCI hotplug: clean up acpi_get_hp_params_from_firmware() interface This patch makes acpi_get_hp_params_from_firmware() take a pci_dev rather than a pci_bus and makes it return a standard int errno rather than acpi_status. Signed-off-by: Bjorn Helgaas Reviewed-by: Kenji Kaneshige Acked-by: Kenji Kaneshige Signed-off-by: Jesse Barnes --- include/linux/pci_hotplug.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h index f0c31ae3f84..0a7c2401d94 100644 --- a/include/linux/pci_hotplug.h +++ b/include/linux/pci_hotplug.h @@ -227,7 +227,7 @@ struct hotplug_params { #ifdef CONFIG_ACPI #include #include -extern acpi_status acpi_get_hp_params_from_firmware(struct pci_bus *bus, +int acpi_get_hp_params_from_firmware(struct pci_dev *dev, struct hotplug_params *hpp); int acpi_get_hp_hw_control_from_firmware(struct pci_dev *dev, u32 flags); int acpi_pci_check_ejectable(struct pci_bus *pbus, acpi_handle handle); -- cgit v1.2.3 From 8838400db5193c37588813c2eb1249b821781950 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Mon, 14 Sep 2009 16:35:20 -0600 Subject: PCI hotplug: add pci_configure_slot() This patch adds a new pci_configure_slot() function that programs the PCI bus characteristics for a newly-added device. This is based on code in pciehp_pci.c, but should be generic enough to be used by pciehp, shpchp, and acpiphp. The hotplug_params struct and the program_hpp_typeX() functions are based on the ACPI definitions, but they aren't really ACPI-specific, and there's no alternate implementation, so I don't see the need to abstract them yet. Signed-off-by: Bjorn Helgaas Reviewed-by: Alex Chiang Reviewed-by: Kenji Kaneshige Acked-by: Kenji Kaneshige Signed-off-by: Jesse Barnes --- include/linux/pci_hotplug.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h index 0a7c2401d94..1cdef831737 100644 --- a/include/linux/pci_hotplug.h +++ b/include/linux/pci_hotplug.h @@ -232,6 +232,15 @@ int acpi_get_hp_params_from_firmware(struct pci_dev *dev, int acpi_get_hp_hw_control_from_firmware(struct pci_dev *dev, u32 flags); int acpi_pci_check_ejectable(struct pci_bus *pbus, acpi_handle handle); int acpi_pci_detect_ejectable(acpi_handle handle); +#define pci_get_hp_params(dev, hpp) acpi_get_hp_params_from_firmware(dev, hpp) +#else +static inline int pci_get_hp_params(struct pci_dev *dev, + struct hotplug_params *hpp) +{ + return -ENODEV; +} #endif + +void pci_configure_slot(struct pci_dev *dev); #endif -- cgit v1.2.3 From e81995bb1c0077a312cb621abc406a36f65a986a Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Mon, 14 Sep 2009 16:35:35 -0600 Subject: PCI hotplug: acpiphp: use generic pci_configure_slot() Use the generic pci_configure_slot() rather than the acpiphp-specific decode_hpp() and program_hpp(). Unlike the previous acpiphp-specific code, pci_configure_slot() programs PCIe settings when an _HPX method provides them, so acpiphp-managed PCIe devices can now be configured. Signed-off-by: Bjorn Helgaas Reviewed-by: Kenji Kaneshige Acked-by: Kenji Kaneshige Signed-off-by: Jesse Barnes --- include/linux/pci_hotplug.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h index 1cdef831737..652ba797696 100644 --- a/include/linux/pci_hotplug.h +++ b/include/linux/pci_hotplug.h @@ -227,12 +227,10 @@ struct hotplug_params { #ifdef CONFIG_ACPI #include #include -int acpi_get_hp_params_from_firmware(struct pci_dev *dev, - struct hotplug_params *hpp); +int pci_get_hp_params(struct pci_dev *dev, struct hotplug_params *hpp); int acpi_get_hp_hw_control_from_firmware(struct pci_dev *dev, u32 flags); int acpi_pci_check_ejectable(struct pci_bus *pbus, acpi_handle handle); int acpi_pci_detect_ejectable(acpi_handle handle); -#define pci_get_hp_params(dev, hpp) acpi_get_hp_params_from_firmware(dev, hpp) #else static inline int pci_get_hp_params(struct pci_dev *dev, struct hotplug_params *hpp) -- cgit v1.2.3 From 75c78500ddad74b229cd0691496b8549490496a2 Mon Sep 17 00:00:00 2001 From: Moni Shoua Date: Tue, 15 Sep 2009 02:37:40 -0700 Subject: bonding: remap muticast addresses without using dev_close() and dev_open() This patch fixes commit e36b9d16c6a6d0f59803b3ef04ff3c22c3844c10. The approach there is to call dev_close()/dev_open() whenever the device type is changed in order to remap the device IP multicast addresses to HW multicast addresses. This approach suffers from 2 drawbacks: *. It assumes tha the device is UP when calling dev_close(), or otherwise dev_close() has no affect. It is worth to mention that initscripts (Redhat) and sysconfig (Suse) doesn't act the same in this matter. *. dev_close() has other side affects, like deleting entries from the routing table, which might be unnecessary. The fix here is to directly remap the IP multicast addresses to HW multicast addresses for a bonding device that changes its type, and nothing else. Reported-by: Jason Gunthorpe Signed-off-by: Moni Shoua Signed-off-by: David S. Miller --- include/linux/igmp.h | 2 ++ include/linux/netdevice.h | 3 ++- include/linux/notifier.h | 2 ++ 3 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 92fbd8cbd68..fe158e0e20e 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -233,6 +233,8 @@ extern void ip_mc_init_dev(struct in_device *); extern void ip_mc_destroy_dev(struct in_device *); extern void ip_mc_up(struct in_device *); extern void ip_mc_down(struct in_device *); +extern void ip_mc_unmap(struct in_device *); +extern void ip_mc_remap(struct in_device *); extern void ip_mc_dec_group(struct in_device *in_dev, __be32 addr); extern void ip_mc_inc_group(struct in_device *in_dev, __be32 addr); extern void ip_mc_rejoin_group(struct ip_mc_list *im); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 65ee1929b2b..f46db6c7a73 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1873,7 +1873,8 @@ extern void __dev_addr_unsync(struct dev_addr_list **to, int *to_count, struct extern int dev_set_promiscuity(struct net_device *dev, int inc); extern int dev_set_allmulti(struct net_device *dev, int inc); extern void netdev_state_change(struct net_device *dev); -extern void netdev_bonding_change(struct net_device *dev); +extern void netdev_bonding_change(struct net_device *dev, + unsigned long event); extern void netdev_features_change(struct net_device *dev); /* Load a device via the kmod */ extern void dev_load(struct net *net, const char *name); diff --git a/include/linux/notifier.h b/include/linux/notifier.h index 81bc252dc8a..44428d247db 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -199,6 +199,8 @@ static inline int notifier_to_errno(int ret) #define NETDEV_FEAT_CHANGE 0x000B #define NETDEV_BONDING_FAILOVER 0x000C #define NETDEV_PRE_UP 0x000D +#define NETDEV_BONDING_OLDTYPE 0x000E +#define NETDEV_BONDING_NEWTYPE 0x000F #define SYS_DOWN 0x0001 /* Notify of system down */ #define SYS_RESTART SYS_DOWN -- cgit v1.2.3 From 29a020d35f629619c67fa5e32acaaac3f8a1ba90 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 15 Sep 2009 02:39:20 -0700 Subject: [PATCH] net: kmemcheck annotation in struct socket struct socket has a 16 bit hole that triggers kmemcheck warnings. As suggested by Ingo, use kmemcheck annotations Signed-off-by: Eric Dumazet Acked-by: Ingo Molnar Signed-off-by: David S. Miller --- include/linux/net.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index 4fc2ffd527f..9040a10584f 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -57,6 +57,7 @@ typedef enum { #include #include #include /* For O_CLOEXEC and O_NONBLOCK */ +#include struct poll_table_struct; struct pipe_inode_info; @@ -127,7 +128,11 @@ enum sock_shutdown_cmd { */ struct socket { socket_state state; + + kmemcheck_bitfield_begin(type); short type; + kmemcheck_bitfield_end(type); + unsigned long flags; /* * Please keep fasync_list & wait fields in the same cache line -- cgit v1.2.3 From 8b815477f382f96deefbe5bd4404fa7b31cf5dcf Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 14 Sep 2009 01:17:30 +0000 Subject: RxRPC: Declare the security index constants symbolically Declare the security index constants symbolically rather than just referring to them numerically. Signed-off-by: David Howells Signed-off-by: David S. Miller --- include/linux/rxrpc.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rxrpc.h b/include/linux/rxrpc.h index f7b826b565c..a53915cd558 100644 --- a/include/linux/rxrpc.h +++ b/include/linux/rxrpc.h @@ -58,5 +58,12 @@ struct sockaddr_rxrpc { #define RXRPC_SECURITY_AUTH 1 /* authenticated packets */ #define RXRPC_SECURITY_ENCRYPT 2 /* encrypted packets */ +/* + * RxRPC security indices + */ +#define RXRPC_SECURITY_NONE 0 /* no security protocol */ +#define RXRPC_SECURITY_RXKAD 2 /* kaserver or kerberos 4 */ +#define RXRPC_SECURITY_RXGK 4 /* gssapi-based */ +#define RXRPC_SECURITY_RXK5 5 /* kerberos 5 */ #endif /* _LINUX_RXRPC_H */ -- cgit v1.2.3 From 5f3edc1b1ead6d9bd45a85c551f44eff8fe76b9f Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 10 Sep 2009 13:42:00 +0200 Subject: sched: Hook sched_balance_self() into sched_class::select_task_rq() Rather ugly patch to fully place the sched_balance_self() code inside the fair class. Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- 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 f3d74bd04d1..5d3c9900943 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -811,6 +811,7 @@ enum cpu_idle_type { #define SD_SERIALIZE 0x0400 /* Only a single load balancing instance */ #define SD_WAKE_IDLE_FAR 0x0800 /* Gain latency sacrificing cache hit */ #define SD_PREFER_SIBLING 0x1000 /* Prefer to place tasks in a sibling domain */ +#define SD_BALANCE_WAKE 0x2000 /* Balance on wakeup */ enum powersavings_balance_level { POWERSAVINGS_BALANCE_NONE = 0, /* No power saving load balance */ @@ -1032,7 +1033,7 @@ struct sched_class { void (*put_prev_task) (struct rq *rq, struct task_struct *p); #ifdef CONFIG_SMP - int (*select_task_rq)(struct task_struct *p, int sync); + int (*select_task_rq)(struct task_struct *p, int flag, int sync); unsigned long (*load_balance) (struct rq *this_rq, int this_cpu, struct rq *busiest, unsigned long max_load_move, -- cgit v1.2.3 From e9c8431185d6c406887190519f6dbdd112641686 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 15 Sep 2009 14:43:03 +0200 Subject: sched: Add TASK_WAKING We're going to want to drop rq->lock in try_to_wake_up() for a longer period of time, however we also want to deal with concurrent waking of the same task, which is currently handled by holding rq->lock. So introduce a new TASK state, namely TASK_WAKING, which indicates someone is already waking the task (other wakers will fail p->state & state). We also keep preemption disabled over the whole ttwu(). Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- 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 5d3c9900943..3b0ca66bd6c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -190,6 +190,7 @@ extern unsigned long long time_sync_thresh; /* in tsk->state again */ #define TASK_DEAD 64 #define TASK_WAKEKILL 128 +#define TASK_WAKING 256 /* Convenience macros for the sake of set_task_state */ #define TASK_KILLABLE (TASK_WAKEKILL | TASK_UNINTERRUPTIBLE) -- cgit v1.2.3 From c88d5910890ad35af283344417891344604f0438 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 10 Sep 2009 13:50:02 +0200 Subject: sched: Merge select_task_rq_fair() and sched_balance_self() The problem with wake_idle() is that is doesn't respect things like cpu_power, which means it doesn't deal well with SMT nor the recent RT interaction. To cure this, it needs to do what sched_balance_self() does, which leads to the possibility of merging select_task_rq_fair() and sched_balance_self(). Modify sched_balance_self() to: - update_shares() when walking up the domain tree, (it only called it for the top domain, but it should have done this anyway), which allows us to remove this ugly bit from try_to_wake_up(). - do wake_affine() on the smallest domain that contains both this (the waking) and the prev (the wakee) cpu for WAKE invocations. Then use the top-down balance steps it had to replace wake_idle(). This leads to the dissapearance of SD_WAKE_BALANCE and SD_WAKE_IDLE_FAR, with SD_WAKE_IDLE replaced with SD_BALANCE_WAKE. SD_WAKE_AFFINE needs SD_BALANCE_WAKE to be effective. Touch all topology bits to replace the old with new SD flags -- platforms might need re-tuning, enabling SD_BALANCE_WAKE conditionally on a NUMA distance seems like a good additional feature, magny-core and small nehalem systems would want this enabled, systems with slow interconnects would not. Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- include/linux/sched.h | 7 +++---- include/linux/topology.h | 16 ++++------------ 2 files changed, 7 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 3b0ca66bd6c..c30bf3d516d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -803,16 +803,15 @@ enum cpu_idle_type { #define SD_BALANCE_NEWIDLE 0x0002 /* Balance when about to become idle */ #define SD_BALANCE_EXEC 0x0004 /* Balance on exec */ #define SD_BALANCE_FORK 0x0008 /* Balance on fork, clone */ -#define SD_WAKE_IDLE 0x0010 /* Wake to idle CPU on task wakeup */ +#define SD_BALANCE_WAKE 0x0010 /* Balance on wakeup */ #define SD_WAKE_AFFINE 0x0020 /* Wake task to waking CPU */ -#define SD_WAKE_BALANCE 0x0040 /* Perform balancing at task wakeup */ + #define SD_SHARE_CPUPOWER 0x0080 /* Domain members share cpu power */ #define SD_POWERSAVINGS_BALANCE 0x0100 /* Balance for power savings */ #define SD_SHARE_PKG_RESOURCES 0x0200 /* Domain members share cpu pkg resources */ #define SD_SERIALIZE 0x0400 /* Only a single load balancing instance */ -#define SD_WAKE_IDLE_FAR 0x0800 /* Gain latency sacrificing cache hit */ + #define SD_PREFER_SIBLING 0x1000 /* Prefer to place tasks in a sibling domain */ -#define SD_BALANCE_WAKE 0x2000 /* Balance on wakeup */ enum powersavings_balance_level { POWERSAVINGS_BALANCE_NONE = 0, /* No power saving load balance */ diff --git a/include/linux/topology.h b/include/linux/topology.h index 85e8cf7d393..6a8cd15555b 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -95,14 +95,12 @@ int arch_update_cpu_topology(void); | 1*SD_BALANCE_NEWIDLE \ | 1*SD_BALANCE_EXEC \ | 1*SD_BALANCE_FORK \ - | 0*SD_WAKE_IDLE \ + | 1*SD_BALANCE_WAKE \ | 1*SD_WAKE_AFFINE \ - | 1*SD_WAKE_BALANCE \ | 1*SD_SHARE_CPUPOWER \ | 0*SD_POWERSAVINGS_BALANCE \ | 0*SD_SHARE_PKG_RESOURCES \ | 0*SD_SERIALIZE \ - | 0*SD_WAKE_IDLE_FAR \ | 0*SD_PREFER_SIBLING \ , \ .last_balance = jiffies, \ @@ -129,13 +127,11 @@ int arch_update_cpu_topology(void); | 1*SD_BALANCE_NEWIDLE \ | 1*SD_BALANCE_EXEC \ | 1*SD_BALANCE_FORK \ - | 1*SD_WAKE_IDLE \ + | 1*SD_BALANCE_WAKE \ | 1*SD_WAKE_AFFINE \ - | 1*SD_WAKE_BALANCE \ | 0*SD_SHARE_CPUPOWER \ | 1*SD_SHARE_PKG_RESOURCES \ | 0*SD_SERIALIZE \ - | 0*SD_WAKE_IDLE_FAR \ | sd_balance_for_mc_power() \ | sd_power_saving_flags() \ , \ @@ -163,13 +159,11 @@ int arch_update_cpu_topology(void); | 1*SD_BALANCE_NEWIDLE \ | 1*SD_BALANCE_EXEC \ | 1*SD_BALANCE_FORK \ - | 1*SD_WAKE_IDLE \ + | 1*SD_BALANCE_WAKE \ | 0*SD_WAKE_AFFINE \ - | 1*SD_WAKE_BALANCE \ | 0*SD_SHARE_CPUPOWER \ | 0*SD_SHARE_PKG_RESOURCES \ | 0*SD_SERIALIZE \ - | 0*SD_WAKE_IDLE_FAR \ | sd_balance_for_package_power() \ | sd_power_saving_flags() \ , \ @@ -191,14 +185,12 @@ int arch_update_cpu_topology(void); | 1*SD_BALANCE_NEWIDLE \ | 0*SD_BALANCE_EXEC \ | 0*SD_BALANCE_FORK \ - | 0*SD_WAKE_IDLE \ + | 0*SD_BALANCE_WAKE \ | 1*SD_WAKE_AFFINE \ - | 0*SD_WAKE_BALANCE \ | 0*SD_SHARE_CPUPOWER \ | 0*SD_POWERSAVINGS_BALANCE \ | 0*SD_SHARE_PKG_RESOURCES \ | 1*SD_SERIALIZE \ - | 1*SD_WAKE_IDLE_FAR \ | 0*SD_PREFER_SIBLING \ , \ .last_balance = jiffies, \ -- cgit v1.2.3 From 78e7ed53c9f42f04f9401ada6f7047db60781676 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 3 Sep 2009 13:16:51 +0200 Subject: sched: Tweak wake_idx When merging select_task_rq_fair() and sched_balance_self() we lost the use of wake_idx, restore that and set them to 0 to make wake balancing more aggressive. Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- include/linux/topology.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/topology.h b/include/linux/topology.h index 6a8cd15555b..fef57040a4e 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -120,7 +120,7 @@ int arch_update_cpu_topology(void); .imbalance_pct = 125, \ .cache_nice_tries = 1, \ .busy_idx = 2, \ - .wake_idx = 1, \ + .wake_idx = 0, \ .forkexec_idx = 1, \ \ .flags = 1*SD_LOAD_BALANCE \ @@ -152,7 +152,7 @@ int arch_update_cpu_topology(void); .busy_idx = 2, \ .idle_idx = 1, \ .newidle_idx = 2, \ - .wake_idx = 1, \ + .wake_idx = 0, \ .forkexec_idx = 1, \ \ .flags = 1*SD_LOAD_BALANCE \ -- cgit v1.2.3 From 6bd7821f905a8d6c471f0d6675f5cb7ea448d791 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 11 Sep 2009 18:42:15 +0200 Subject: sched: Fix some domain tunings CPU level should have WAKE_AFFINE, whereas ALLNODES is dubious. Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- include/linux/topology.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/topology.h b/include/linux/topology.h index fef57040a4e..c87edcd8796 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -160,7 +160,7 @@ int arch_update_cpu_topology(void); | 1*SD_BALANCE_EXEC \ | 1*SD_BALANCE_FORK \ | 1*SD_BALANCE_WAKE \ - | 0*SD_WAKE_AFFINE \ + | 1*SD_WAKE_AFFINE \ | 0*SD_SHARE_CPUPOWER \ | 0*SD_SHARE_PKG_RESOURCES \ | 0*SD_SERIALIZE \ @@ -186,7 +186,7 @@ int arch_update_cpu_topology(void); | 0*SD_BALANCE_EXEC \ | 0*SD_BALANCE_FORK \ | 0*SD_BALANCE_WAKE \ - | 1*SD_WAKE_AFFINE \ + | 0*SD_WAKE_AFFINE \ | 0*SD_SHARE_CPUPOWER \ | 0*SD_POWERSAVINGS_BALANCE \ | 0*SD_SHARE_PKG_RESOURCES \ -- cgit v1.2.3 From 0ec9fab3d186d9cbb00c0f694d4a260d07c198d9 Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Tue, 15 Sep 2009 15:07:03 +0200 Subject: sched: Improve latencies and throughput Make the idle balancer more agressive, to improve a x264 encoding workload provided by Jason Garrett-Glaser: NEXT_BUDDY NO_LB_BIAS encoded 600 frames, 252.82 fps, 22096.60 kb/s encoded 600 frames, 250.69 fps, 22096.60 kb/s encoded 600 frames, 245.76 fps, 22096.60 kb/s NO_NEXT_BUDDY LB_BIAS encoded 600 frames, 344.44 fps, 22096.60 kb/s encoded 600 frames, 346.66 fps, 22096.60 kb/s encoded 600 frames, 352.59 fps, 22096.60 kb/s NO_NEXT_BUDDY NO_LB_BIAS encoded 600 frames, 425.75 fps, 22096.60 kb/s encoded 600 frames, 425.45 fps, 22096.60 kb/s encoded 600 frames, 422.49 fps, 22096.60 kb/s Peter pointed out that this is better done via newidle_idx, not via LB_BIAS, newidle balancing should look for where there is load _now_, not where there was load 2 ticks ago. Worst-case latencies are improved as well as no buddies means less vruntime spread. (as per prior lkml discussions) This change improves kbuild-peak parallelism as well. Reported-by: Jason Garrett-Glaser Signed-off-by: Mike Galbraith Signed-off-by: Peter Zijlstra LKML-Reference: <1253011667.9128.16.camel@marge.simson.net> Signed-off-by: Ingo Molnar --- include/linux/topology.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/topology.h b/include/linux/topology.h index c87edcd8796..4298745615a 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -151,7 +151,7 @@ int arch_update_cpu_topology(void); .cache_nice_tries = 1, \ .busy_idx = 2, \ .idle_idx = 1, \ - .newidle_idx = 2, \ + .newidle_idx = 0, \ .wake_idx = 0, \ .forkexec_idx = 1, \ \ -- cgit v1.2.3 From b8a543ea5a5896830a9969bacfd047f9d15940b2 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 15 Sep 2009 15:22:03 +0200 Subject: sched: Reduce forkexec_idx If we're looking to place a new task, we might as well find the idlest position _now_, not 1 tick ago. Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- include/linux/topology.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/topology.h b/include/linux/topology.h index 4298745615a..936ab2b3768 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -121,7 +121,7 @@ int arch_update_cpu_topology(void); .cache_nice_tries = 1, \ .busy_idx = 2, \ .wake_idx = 0, \ - .forkexec_idx = 1, \ + .forkexec_idx = 0, \ \ .flags = 1*SD_LOAD_BALANCE \ | 1*SD_BALANCE_NEWIDLE \ @@ -153,7 +153,7 @@ int arch_update_cpu_topology(void); .idle_idx = 1, \ .newidle_idx = 0, \ .wake_idx = 0, \ - .forkexec_idx = 1, \ + .forkexec_idx = 0, \ \ .flags = 1*SD_LOAD_BALANCE \ | 1*SD_BALANCE_NEWIDLE \ -- cgit v1.2.3 From 47fe38fcff0517e67d395c039d2e26d2de688a60 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 2 Sep 2009 13:49:18 +0200 Subject: x86: sched: Provide arch implementations using aperf/mperf APERF/MPERF support for cpu_power. APERF/MPERF is arch defined to be a relative scale of work capacity per logical cpu, this is assumed to include SMT and Turbo mode. APERF/MPERF are specified to both reset to 0 when either counter wraps, which is highly inconvenient, since that'll give a blimp when that happens. The manual specifies writing 0 to the counters after each read, but that's 1) too expensive, and 2) destroys the possibility of sharing these counters with other users, so we live with the blimp - the other existing user does too. Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- include/linux/sched.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index c30bf3d516d..fc4c0f9393d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -992,6 +992,9 @@ static inline int test_sd_parent(struct sched_domain *sd, int flag) return 0; } +unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu); +unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu); + #else /* CONFIG_SMP */ struct sched_domain_attr; @@ -1003,6 +1006,7 @@ partition_sched_domains(int ndoms_new, struct cpumask *doms_new, } #endif /* !CONFIG_SMP */ + struct io_context; /* See blkdev.h */ -- cgit v1.2.3 From 0763a660a84220cc3900fd32abdd7ad109e2278d Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 14 Sep 2009 19:37:39 +0200 Subject: sched: Rename select_task_rq() argument In order to be able to rename the sync argument, we need to rename the current flag argument. Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index fc4c0f9393d..5c116f03d74 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1037,7 +1037,7 @@ struct sched_class { void (*put_prev_task) (struct rq *rq, struct task_struct *p); #ifdef CONFIG_SMP - int (*select_task_rq)(struct task_struct *p, int flag, int sync); + int (*select_task_rq)(struct task_struct *p, int sd_flag, int sync); unsigned long (*load_balance) (struct rq *this_rq, int this_cpu, struct rq *busiest, unsigned long max_load_move, -- cgit v1.2.3 From 7d47872146398dbede13223299fe1cb368ebc781 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 14 Sep 2009 19:55:44 +0200 Subject: sched: Rename sync arguments In order to extend the functions to have more than 1 flag (sync), rename the argument to flags, and explicitly define a WF_ space for individual flags. Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- include/linux/sched.h | 9 +++++++-- include/linux/wait.h | 4 ++-- 2 files changed, 9 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 5c116f03d74..3b07168b6f0 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1024,6 +1024,11 @@ struct uts_namespace; struct rq; struct sched_domain; +/* + * wake flags + */ +#define WF_SYNC 0x01 /* waker goes to sleep after wakup */ + struct sched_class { const struct sched_class *next; @@ -1031,13 +1036,13 @@ struct sched_class { void (*dequeue_task) (struct rq *rq, struct task_struct *p, int sleep); void (*yield_task) (struct rq *rq); - void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int sync); + void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags); struct task_struct * (*pick_next_task) (struct rq *rq); void (*put_prev_task) (struct rq *rq, struct task_struct *p); #ifdef CONFIG_SMP - int (*select_task_rq)(struct task_struct *p, int sd_flag, int sync); + int (*select_task_rq)(struct task_struct *p, int sd_flag, int flags); unsigned long (*load_balance) (struct rq *this_rq, int this_cpu, struct rq *busiest, unsigned long max_load_move, diff --git a/include/linux/wait.h b/include/linux/wait.h index cf3c2f5dba5..a48e16b77d5 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -26,8 +26,8 @@ #include typedef struct __wait_queue wait_queue_t; -typedef int (*wait_queue_func_t)(wait_queue_t *wait, unsigned mode, int sync, void *key); -int default_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key); +typedef int (*wait_queue_func_t)(wait_queue_t *wait, unsigned mode, int flags, void *key); +int default_wake_function(wait_queue_t *wait, unsigned mode, int flags, void *key); struct __wait_queue { unsigned int flags; -- cgit v1.2.3 From a7558e01056f5191ff2ecff53b075dcb9e484188 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 14 Sep 2009 20:02:34 +0200 Subject: sched: Add WF_FORK Avoid the cache buddies from biasing the time distribution away from fork()ers. Normally the next buddy will be the preferred scheduling target, but this makes fork()s prefer to run the new child, whereas we prefer to run the parent, since that will generate more work. Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- 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 3b07168b6f0..ee1f8899309 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1028,6 +1028,7 @@ struct sched_domain; * wake flags */ #define WF_SYNC 0x01 /* waker goes to sleep after wakup */ +#define WF_FORK 0x02 /* child wakeup after fork */ struct sched_class { const struct sched_class *next; -- cgit v1.2.3 From 2f82af08fcc7dc01a7e98a49a5995a77e32a2925 Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Mon, 14 Sep 2009 03:25:28 -0400 Subject: Nicolas Pitre has a new email address Due to problems at cam.org, my nico@cam.org email address is no longer valid. FRom now on, nico@fluxnic.net should be used instead. Signed-off-by: Nicolas Pitre Signed-off-by: Linus Torvalds --- include/linux/mtd/partitions.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/partitions.h b/include/linux/mtd/partitions.h index b70313d33ff..274b6196091 100644 --- a/include/linux/mtd/partitions.h +++ b/include/linux/mtd/partitions.h @@ -1,7 +1,7 @@ /* * MTD partitioning layer definitions * - * (C) 2000 Nicolas Pitre + * (C) 2000 Nicolas Pitre * * This code is GPL */ -- cgit v1.2.3 From b4028437876866aba4747a655ede00f892089e14 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 11 May 2009 14:16:57 -0700 Subject: Driver core: move dev_get/set_drvdata to drivers/base/dd.c No one should directly access the driver_data field, so remove the field and make it private. We dynamically create the private field now if it is needed, to handle drivers that call get/set before they are registered with the driver core. Also update the copyright notices on these files while we are there. Cc: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 16 ++++------------ 1 file changed, 4 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index a2864297505..c0bd23048be 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -2,7 +2,8 @@ * device.h - generic, centralized driver model * * Copyright (c) 2001-2003 Patrick Mochel - * Copyright (c) 2004-2007 Greg Kroah-Hartman + * Copyright (c) 2004-2009 Greg Kroah-Hartman + * Copyright (c) 2008-2009 Novell Inc. * * This file is released under the GPLv2 * @@ -381,7 +382,6 @@ struct device { struct bus_type *bus; /* type of bus device is on */ 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 */ struct dev_pm_info power; @@ -447,16 +447,6 @@ static inline void set_dev_node(struct device *dev, int node) } #endif -static inline void *dev_get_drvdata(const struct device *dev) -{ - return dev->driver_data; -} - -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; @@ -490,6 +480,8 @@ extern int device_rename(struct device *dev, char *new_name); extern int device_move(struct device *dev, struct device *new_parent, enum dpm_order dpm_order); extern const char *device_get_nodename(struct device *dev, const char **tmp); +extern void *dev_get_drvdata(const struct device *dev); +extern void dev_set_drvdata(struct device *dev, void *data); /* * Root device objects for grouping under /sys/devices -- cgit v1.2.3 From a5b8b1ada6dd76503884f5492b995cd29eefae0f Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Fri, 17 Jul 2009 15:06:08 +0100 Subject: Driver core: Add accessor for device platform data For consistency with driver data provide a dev_get_platdata() accessor for reading the platform data from a device. Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index c0bd23048be..3f33f17f556 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -494,6 +494,11 @@ static inline struct device *root_device_register(const char *name) } extern void root_device_unregister(struct device *root); +static inline void *dev_get_platdata(const struct device *dev) +{ + return dev->platform_data; +} + /* * Manual binding of a device to driver. See drivers/base/bus.c * for information on use. -- cgit v1.2.3 From a4dbd6740df0872cdf0a86841f75beec8381964d Mon Sep 17 00:00:00 2001 From: David Brownell Date: Wed, 24 Jun 2009 10:06:31 -0700 Subject: driver model: constify attribute groups Let attribute group vectors be declared "const". We'd like to let most attribute metadata live in read-only sections... this is a start. Signed-off-by: David Brownell Signed-off-by: Greg Kroah-Hartman --- include/linux/attribute_container.h | 2 +- include/linux/device.h | 6 +++--- include/linux/netdevice.h | 2 +- include/linux/transport_class.h | 2 +- 4 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/attribute_container.h b/include/linux/attribute_container.h index 794ad74b1d6..c3ab81428c6 100644 --- a/include/linux/attribute_container.h +++ b/include/linux/attribute_container.h @@ -17,7 +17,7 @@ struct attribute_container { struct list_head node; struct klist containers; struct class *class; - struct attribute_group *grp; + const struct attribute_group *grp; struct device_attribute **attrs; int (*match)(struct attribute_container *, struct device *); #define ATTRIBUTE_CONTAINER_NO_CLASSDEVS 0x01 diff --git a/include/linux/device.h b/include/linux/device.h index 3f33f17f556..e19e40a3dcb 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -131,7 +131,7 @@ struct device_driver { void (*shutdown) (struct device *dev); int (*suspend) (struct device *dev, pm_message_t state); int (*resume) (struct device *dev); - struct attribute_group **groups; + const struct attribute_group **groups; const struct dev_pm_ops *pm; @@ -288,7 +288,7 @@ extern void class_destroy(struct class *cls); */ struct device_type { const char *name; - struct attribute_group **groups; + const struct attribute_group **groups; int (*uevent)(struct device *dev, struct kobj_uevent_env *env); char *(*nodename)(struct device *dev); void (*release)(struct device *dev); @@ -412,7 +412,7 @@ struct device { struct klist_node knode_class; struct class *class; - struct attribute_group **groups; /* optional groups */ + const struct attribute_group **groups; /* optional groups */ void (*release)(struct device *dev); }; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 65ee1929b2b..a9aa4b5917d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -895,7 +895,7 @@ struct net_device /* class/net/name entry */ struct device dev; /* space for optional statistics and wireless sysfs groups */ - struct attribute_group *sysfs_groups[3]; + const struct attribute_group *sysfs_groups[3]; /* rtnetlink link ops */ const struct rtnl_link_ops *rtnl_link_ops; diff --git a/include/linux/transport_class.h b/include/linux/transport_class.h index eaec1ea9558..9ae8da3e640 100644 --- a/include/linux/transport_class.h +++ b/include/linux/transport_class.h @@ -55,7 +55,7 @@ struct anon_transport_class cls = { \ struct transport_container { struct attribute_container ac; - struct attribute_group *statistics; + const struct attribute_group *statistics; }; #define attribute_container_to_transport_container(x) \ -- cgit v1.2.3 From ccb86a6907c9ba7b5be5f521362fc308e80bed34 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Mon, 20 Jul 2009 10:29:34 +0300 Subject: uio: add generic driver for PCI 2.3 devices This adds a generic uio driver that can bind to any PCI device. First user will be virtualization where a qemu userspace process needs to give guest OS access to the device. Interrupts are handled using the Interrupt Disable bit in the PCI command register and Interrupt Status bit in the PCI status register. All devices compliant to PCI 2.3 (circa 2002) and all compliant PCI Express devices should support these bits. Driver detects this support, and won't bind to devices which do not support the Interrupt Disable Bit in the command register. It's expected that more features of interest to virtualization will be added to this driver in the future. Possibilities are: mmap for device resources, MSI/MSI-X, eventfd (to interface with kvm), iommu. Signed-off-by: Michael S. Tsirkin Acked-by: Chris Wright Signed-off-by: Hans J. Koch Acked-by: Jesse Barnes Signed-off-by: Greg Kroah-Hartman --- include/linux/pci_regs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci_regs.h b/include/linux/pci_regs.h index fcaee42c7ac..dd0bed4f1cf 100644 --- a/include/linux/pci_regs.h +++ b/include/linux/pci_regs.h @@ -42,6 +42,7 @@ #define PCI_COMMAND_INTX_DISABLE 0x400 /* INTx Emulation Disable */ #define PCI_STATUS 0x06 /* 16 bits */ +#define PCI_STATUS_INTERRUPT 0x08 /* Interrupt status */ #define PCI_STATUS_CAP_LIST 0x10 /* Support Capability List */ #define PCI_STATUS_66MHZ 0x20 /* Support 66 Mhz PCI 2.1 bus */ #define PCI_STATUS_UDF 0x40 /* Support User Definable Features [obsolete] */ -- cgit v1.2.3 From 4622709445705c1e423d2addcfd8ccae052fe0ba Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Tue, 4 Aug 2009 12:55:34 +0200 Subject: Driver core: Add support for compatibility classes When turning class devices into bus devices, we may need to temporarily add links in sysfs so that user-space applications are not confused. This is done by adding the following API: * Functions to register and unregister compatibility classes. These appear in sysfs at the same location as regular classes, but instead of class devices, they contain links to bus devices. * Functions to create and delete such links. Additionally, the caller can optionally pass a target device to which a "device" link should point (typically that would be the device's parent), to fully emulate the original class device. The i2c subsystem will be the first user of this API, as i2c adapters are being converted from class devices to bus devices. Signed-off-by: Jean Delvare Signed-off-by: Kay Sievers --- include/linux/device.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index e19e40a3dcb..62ff53a6793 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -225,6 +225,14 @@ extern void class_unregister(struct class *class); __class_register(class, &__key); \ }) +struct class_compat; +struct class_compat *class_compat_register(const char *name); +void class_compat_unregister(struct class_compat *cls); +int class_compat_create_link(struct class_compat *cls, struct device *dev, + struct device *device_link); +void class_compat_remove_link(struct class_compat *cls, struct device *dev, + struct device *device_link); + extern void class_dev_iter_init(struct class_dev_iter *iter, struct class *class, struct device *start, -- cgit v1.2.3 From 2b2af54a5bb6f7e80ccf78f20084b93c398c3a8b Mon Sep 17 00:00:00 2001 From: Kay Sievers Date: Thu, 30 Apr 2009 15:23:42 +0200 Subject: Driver Core: devtmpfs - kernel-maintained tmpfs-based /dev Devtmpfs lets the kernel create a tmpfs instance called devtmpfs very early at kernel initialization, before any driver-core device is registered. Every device with a major/minor will provide a device node in devtmpfs. Devtmpfs can be changed and altered by userspace at any time, and in any way needed - just like today's udev-mounted tmpfs. Unmodified udev versions will run just fine on top of it, and will recognize an already existing kernel-created device node and use it. The default node permissions are root:root 0600. Proper permissions and user/group ownership, meaningful symlinks, all other policy still needs to be applied by userspace. If a node is created by devtmps, devtmpfs will remove the device node when the device goes away. If the device node was created by userspace, or the devtmpfs created node was replaced by userspace, it will no longer be removed by devtmpfs. If it is requested to auto-mount it, it makes init=/bin/sh work without any further userspace support. /dev will be fully populated and dynamic, and always reflect the current device state of the kernel. With the commonly used dynamic device numbers, it solves the problem where static devices nodes may point to the wrong devices. It is intended to make the initial bootup logic simpler and more robust, by de-coupling the creation of the inital environment, to reliably run userspace processes, from a complex userspace bootstrap logic to provide a working /dev. Signed-off-by: Kay Sievers Signed-off-by: Jan Blunck Tested-By: Harald Hoyer Tested-By: Scott James Remnant Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 10 ++++++++++ include/linux/shmem_fs.h | 3 +++ 2 files changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 62ff53a6793..847b763e40e 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -552,6 +552,16 @@ extern void put_device(struct device *dev); extern void wait_for_device_probe(void); +#ifdef CONFIG_DEVTMPFS +extern int devtmpfs_create_node(struct device *dev); +extern int devtmpfs_delete_node(struct device *dev); +extern int devtmpfs_mount(const char *mountpoint); +#else +static inline int devtmpfs_create_node(struct device *dev) { return 0; } +static inline int devtmpfs_delete_node(struct device *dev) { return 0; } +static inline int devtmpfs_mount(const char *mountpoint) { return 0; } +#endif + /* drivers/base/power/shutdown.c */ extern void device_shutdown(void); diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 6d3f2f449ea..deee7afd8d6 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -38,6 +38,9 @@ static inline struct shmem_inode_info *SHMEM_I(struct inode *inode) return container_of(inode, struct shmem_inode_info, vfs_inode); } +extern int init_tmpfs(void); +extern int shmem_fill_super(struct super_block *sb, void *data, int silent); + #ifdef CONFIG_TMPFS_POSIX_ACL int shmem_check_acl(struct inode *, int); int shmem_acl_init(struct inode *, struct inode *); -- cgit v1.2.3 From fe832a3a48737b24f95fab202b1c67fb588b071d Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 15 Sep 2009 23:51:31 -0400 Subject: tracing: remove notrace from __kprobes annotation When ftrace had issues with NMIs, it was needed to annotate all the areas that kprobes had issues with notrace. Now that ftrace is NMI safe, the functions that limit ftrace from tracing are just a small few. Kprobes is too big of a set for ftrace not to trace. Remove the coupling. Signed-off-by: Steven Rostedt --- include/linux/kprobes.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index bcd9c07848b..3a46b7b7abb 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -48,13 +48,13 @@ #define KPROBE_HIT_SSDONE 0x00000008 /* Attach to insert probes on any functions which should be ignored*/ -#define __kprobes __attribute__((__section__(".kprobes.text"))) notrace +#define __kprobes __attribute__((__section__(".kprobes.text"))) #else /* CONFIG_KPROBES */ typedef int kprobe_opcode_t; struct arch_specific_insn { int dummy; }; -#define __kprobes notrace +#define __kprobes #endif /* CONFIG_KPROBES */ struct kprobe; -- cgit v1.2.3 From 59abf02644c45f1591e1374ee7bb45dc757fcb88 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 16 Sep 2009 08:28:30 +0200 Subject: sched: Add SD_PREFER_LOCAL And turn it on for NUMA and MC domains. This improves locality in balancing decisions by keeping up to capacity amount of tasks local before looking for idle CPUs. (and twice the capacity if SD_POWERSAVINGS_BALANCE is set.) Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- include/linux/sched.h | 2 +- include/linux/topology.h | 2 ++ 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index ee1f8899309..b4a39bb2b4a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -805,7 +805,7 @@ enum cpu_idle_type { #define SD_BALANCE_FORK 0x0008 /* Balance on fork, clone */ #define SD_BALANCE_WAKE 0x0010 /* Balance on wakeup */ #define SD_WAKE_AFFINE 0x0020 /* Wake task to waking CPU */ - +#define SD_PREFER_LOCAL 0x0040 /* Prefer to keep tasks local to this domain */ #define SD_SHARE_CPUPOWER 0x0080 /* Domain members share cpu power */ #define SD_POWERSAVINGS_BALANCE 0x0100 /* Balance for power savings */ #define SD_SHARE_PKG_RESOURCES 0x0200 /* Domain members share cpu pkg resources */ diff --git a/include/linux/topology.h b/include/linux/topology.h index 936ab2b3768..a6614b0242a 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -129,6 +129,7 @@ int arch_update_cpu_topology(void); | 1*SD_BALANCE_FORK \ | 1*SD_BALANCE_WAKE \ | 1*SD_WAKE_AFFINE \ + | 1*SD_PREFER_LOCAL \ | 0*SD_SHARE_CPUPOWER \ | 1*SD_SHARE_PKG_RESOURCES \ | 0*SD_SERIALIZE \ @@ -161,6 +162,7 @@ int arch_update_cpu_topology(void); | 1*SD_BALANCE_FORK \ | 1*SD_BALANCE_WAKE \ | 1*SD_WAKE_AFFINE \ + | 1*SD_PREFER_LOCAL \ | 0*SD_SHARE_CPUPOWER \ | 0*SD_SHARE_PKG_RESOURCES \ | 0*SD_SERIALIZE \ -- cgit v1.2.3 From 2c96ce9f2084c1e04d02883e622f74a537a63aea Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 15 Sep 2009 09:43:56 +0200 Subject: fs: remove bdev->bd_inode_backing_dev_info It has been unused since it was introduced in: commit 520808bf20e90fdbdb320264ba7dd5cf9d47dcac Author: Andrew Morton Date: Fri May 21 00:46:17 2004 -0700 [PATCH] block device layer: separate backing_dev_info infrastructure So lets just kill it. Acked-by: Jan Kara Signed-off-by: Jens Axboe --- 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 b21cf6b9c80..db29588874a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -655,7 +655,6 @@ struct block_device { int bd_invalidated; struct gendisk * bd_disk; struct list_head bd_list; - struct backing_dev_info *bd_inode_backing_dev_info; /* * Private data. You must have bd_claim'ed the block_device * to use this. NOTE: bd_claim allows an owner to claim -- cgit v1.2.3 From 1fe06ad89255c211fe100d7f690d10b161398df8 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 15 Sep 2009 15:10:20 +0200 Subject: writeback: get rid of wbc->for_writepages It's only set, it's never checked. Kill it. Acked-by: Jan Kara Signed-off-by: Jens Axboe --- include/linux/writeback.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index d347632f186..48a054e2b71 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -50,7 +50,6 @@ struct writeback_control { unsigned encountered_congestion:1; /* An output: a queue is full */ unsigned for_kupdate:1; /* A kupdate writeback */ unsigned for_reclaim:1; /* Invoked from the page allocator */ - unsigned for_writepages:1; /* This is a writepages() call */ unsigned range_cyclic:1; /* range_start is cyclic */ unsigned more_io:1; /* more io to be dispatched */ /* -- cgit v1.2.3 From 32a88aa1b6dfb901cec64e1898cac78d0f25028a Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 16 Sep 2009 15:02:33 +0200 Subject: fs: Assign bdi in super_block We do this automatically in get_sb_bdev() from the set_bdev_super() callback. Filesystems that have their own private backing_dev_info must assign that in ->fill_super(). Note that ->s_bdi assignment is required for proper writeback! Acked-by: Christoph Hellwig Signed-off-by: Jens Axboe --- 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 db29588874a..90162fb3bf0 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1342,6 +1342,7 @@ struct super_block { int s_nr_dentry_unused; /* # of dentry on lru */ struct block_device *s_bdev; + struct backing_dev_info *s_bdi; struct mtd_info *s_mtd; struct list_head s_instances; struct quota_info s_dquot; /* Diskquota specific options */ -- cgit v1.2.3 From cfc4ba5365449cb6b5c9f68d755a142f17da1e47 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 14 Sep 2009 13:12:40 +0200 Subject: writeback: use RCU to protect bdi_list Now that bdi_writeback_all() no longer handles integrity writeback, it doesn't have to block anymore. This means that we can switch bdi_list reader side protection to RCU. Signed-off-by: Jens Axboe --- include/linux/backing-dev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index f169bcb90b5..859e797f457 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -59,6 +59,7 @@ struct bdi_writeback { struct backing_dev_info { struct list_head bdi_list; + struct rcu_head rcu_head; unsigned long ra_pages; /* max readahead in PAGE_CACHE_SIZE units */ unsigned long state; /* Always use atomic bitops on this */ unsigned int capabilities; /* Device capabilities */ -- cgit v1.2.3 From b6e51316daede0633e9274e1e30391cfa4747877 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 16 Sep 2009 15:13:54 +0200 Subject: writeback: separate starting of sync vs opportunistic writeback bdi_start_writeback() is currently split into two paths, one for WB_SYNC_NONE and one for WB_SYNC_ALL. Add bdi_sync_writeback() for WB_SYNC_ALL writeback and let bdi_start_writeback() handle only WB_SYNC_NONE. Push down the writeback_control allocation and only accept the parameters that make sense for each function. This cleans up the API considerably. Signed-off-by: Jens Axboe --- include/linux/backing-dev.h | 2 +- include/linux/writeback.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 859e797f457..0ee33c2e612 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -101,7 +101,7 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent, const char *fmt, ...); int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev); void bdi_unregister(struct backing_dev_info *bdi); -void bdi_start_writeback(struct writeback_control *wbc); +void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages); int bdi_writeback_task(struct bdi_writeback *wb); int bdi_has_dirty_io(struct backing_dev_info *bdi); diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 48a054e2b71..75cf58666ff 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -68,8 +68,8 @@ struct writeback_control { */ struct bdi_writeback; int inode_wait(void *); -long writeback_inodes_sb(struct super_block *); -long sync_inodes_sb(struct super_block *); +void writeback_inodes_sb(struct super_block *); +void sync_inodes_sb(struct super_block *); void writeback_inodes_wbc(struct writeback_control *wbc); long wb_do_writeback(struct bdi_writeback *wb, int force_wait); void wakeup_flusher_threads(long nr_pages); -- cgit v1.2.3 From 182a85f8a119c789610a9d464f4129ded9f3c107 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 16 Sep 2009 13:24:49 +0200 Subject: sched: Disable wakeup balancing Sysbench thinks SD_BALANCE_WAKE is too agressive and kbuild doesn't really mind too much, SD_BALANCE_NEWIDLE picks up most of the slack. On a dual socket, quad core, dual thread nehalem system: sysbench (--num_threads=16): SD_BALANCE_WAKE-: 13982 tx/s SD_BALANCE_WAKE+: 15688 tx/s kbuild (-j16): SD_BALANCE_WAKE-: 47.648295846 seconds time elapsed ( +- 0.312% ) SD_BALANCE_WAKE+: 47.608607360 seconds time elapsed ( +- 0.026% ) (same within noise) Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- include/linux/topology.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/topology.h b/include/linux/topology.h index a6614b0242a..809b26c0709 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -95,7 +95,7 @@ int arch_update_cpu_topology(void); | 1*SD_BALANCE_NEWIDLE \ | 1*SD_BALANCE_EXEC \ | 1*SD_BALANCE_FORK \ - | 1*SD_BALANCE_WAKE \ + | 0*SD_BALANCE_WAKE \ | 1*SD_WAKE_AFFINE \ | 1*SD_SHARE_CPUPOWER \ | 0*SD_POWERSAVINGS_BALANCE \ @@ -127,7 +127,7 @@ int arch_update_cpu_topology(void); | 1*SD_BALANCE_NEWIDLE \ | 1*SD_BALANCE_EXEC \ | 1*SD_BALANCE_FORK \ - | 1*SD_BALANCE_WAKE \ + | 0*SD_BALANCE_WAKE \ | 1*SD_WAKE_AFFINE \ | 1*SD_PREFER_LOCAL \ | 0*SD_SHARE_CPUPOWER \ @@ -160,7 +160,7 @@ int arch_update_cpu_topology(void); | 1*SD_BALANCE_NEWIDLE \ | 1*SD_BALANCE_EXEC \ | 1*SD_BALANCE_FORK \ - | 1*SD_BALANCE_WAKE \ + | 0*SD_BALANCE_WAKE \ | 1*SD_WAKE_AFFINE \ | 1*SD_PREFER_LOCAL \ | 0*SD_SHARE_CPUPOWER \ -- cgit v1.2.3 From ad4b78bbcbab66998b05d422ac6106b645796e54 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 16 Sep 2009 12:31:31 +0200 Subject: sched: Add new wakeup preemption mode: WAKEUP_RUNNING Create a new wakeup preemption mode, preempt towards tasks that run shorter on avg. It sets next buddy to be sure we actually run the task we preempted for. Test results: root@twins:~# while :; do :; done & [1] 6537 root@twins:~# while :; do :; done & [2] 6538 root@twins:~# while :; do :; done & [3] 6539 root@twins:~# while :; do :; done & [4] 6540 root@twins:/home/peter# ./latt -c4 sleep 4 Entries: 48 (clients=4) Averages: ------------------------------ Max 4750 usec Avg 497 usec Stdev 737 usec root@twins:/home/peter# echo WAKEUP_RUNNING > /debug/sched_features root@twins:/home/peter# ./latt -c4 sleep 4 Entries: 48 (clients=4) Averages: ------------------------------ Max 14 usec Avg 5 usec Stdev 3 usec Disabled by default - needs more testing. Signed-off-by: Peter Zijlstra Acked-by: Mike Galbraith Signed-off-by: Ingo Molnar LKML-Reference: --- 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 b4a39bb2b4a..8af3d249170 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1113,6 +1113,8 @@ struct sched_entity { u64 start_runtime; u64 avg_wakeup; + u64 avg_running; + #ifdef CONFIG_SCHEDSTATS u64 wait_start; u64 wait_max; -- cgit v1.2.3 From d15d6e6cc340566d53d953ffdec2c9e96816fa52 Mon Sep 17 00:00:00 2001 From: "John(Jung-Ik) Lee" Date: Mon, 14 Sep 2009 21:32:33 -0700 Subject: libata: Add pata_atp867x driver for Artop/Acard ATP867X controllers This is a new pata driver for ARTOP 867X 64bit 4-channel UDMA133 ATA ctrls. Based on the Atp867 data sheet rev 1.2, Acard, and in part on early ide codes from Eric Uhrhane . Signed-off-by: John(Jung-Ik) Lee Reviewed-by: Grant Grundler Reviewed-by: Gwendal Gringo Signed-off-by: Jeff Garzik --- 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 8975add8668..3b6b788fe2b 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1529,6 +1529,8 @@ #define PCI_DEVICE_ID_ARTOP_ATP860R 0x0007 #define PCI_DEVICE_ID_ARTOP_ATP865 0x0008 #define PCI_DEVICE_ID_ARTOP_ATP865R 0x0009 +#define PCI_DEVICE_ID_ARTOP_ATP867A 0x000A +#define PCI_DEVICE_ID_ARTOP_ATP867B 0x000B #define PCI_DEVICE_ID_ARTOP_AEC7610 0x8002 #define PCI_DEVICE_ID_ARTOP_AEC7612UW 0x8010 #define PCI_DEVICE_ID_ARTOP_AEC7612U 0x8020 -- cgit v1.2.3