From 345046673449b5c35840e5cc34a60059cbec9305 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Thu, 10 Jan 2013 19:00:53 +0000 Subject: slab: Move kmalloc related function defs Move these functions higher up in slab.h so that they are grouped with other generic kmalloc related definitions. Acked-by: Glauber Costa Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/slab.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/slab.h b/include/linux/slab.h index 5d168d7e0a28..ccbb37685c6c 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -147,6 +147,15 @@ void kmem_cache_free(struct kmem_cache *, void *); sizeof(struct __struct), __alignof__(struct __struct),\ (__flags), NULL) +/* + * Common kmalloc functions provided by all allocators + */ +void * __must_check __krealloc(const void *, size_t, gfp_t); +void * __must_check krealloc(const void *, size_t, gfp_t); +void kfree(const void *); +void kzfree(const void *); +size_t ksize(const void *); + /* * The largest kmalloc size supported by the slab allocators is * 32 megabyte (2^25) or the maximum allocatable page order if that is @@ -224,15 +233,6 @@ struct seq_file; int cache_show(struct kmem_cache *s, struct seq_file *m); void print_slabinfo_header(struct seq_file *m); -/* - * Common kmalloc functions provided by all allocators - */ -void * __must_check __krealloc(const void *, size_t, gfp_t); -void * __must_check krealloc(const void *, size_t, gfp_t); -void kfree(const void *); -void kzfree(const void *); -size_t ksize(const void *); - /* * Allocator specific definitions. These are mainly used to establish optimized * ways to convert kmalloc() calls to kmem_cache_alloc() invocations by -- cgit v1.2.3 From ce6a50263d4ddeba1f0d08f16716a82770c03690 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Thu, 10 Jan 2013 19:14:19 +0000 Subject: slab: Common kmalloc slab index determination Extract the function to determine the index of the slab within the array of kmalloc caches as well as a function to determine maximum object size from the nr of the kmalloc slab. This is used here only to simplify slub bootstrap but will be used later also for SLAB. Acked-by: Glauber Costa Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/slab.h | 172 +++++++++++++++++++++++++++++++++-------------- include/linux/slub_def.h | 63 ----------------- 2 files changed, 122 insertions(+), 113 deletions(-) (limited to 'include') diff --git a/include/linux/slab.h b/include/linux/slab.h index ccbb37685c6c..c97fe92532d1 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -94,29 +94,6 @@ #define ZERO_OR_NULL_PTR(x) ((unsigned long)(x) <= \ (unsigned long)ZERO_SIZE_PTR) -/* - * Common fields provided in kmem_cache by all slab allocators - * This struct is either used directly by the allocator (SLOB) - * or the allocator must include definitions for all fields - * provided in kmem_cache_common in their definition of kmem_cache. - * - * Once we can do anonymous structs (C11 standard) we could put a - * anonymous struct definition in these allocators so that the - * separate allocations in the kmem_cache structure of SLAB and - * SLUB is no longer needed. - */ -#ifdef CONFIG_SLOB -struct kmem_cache { - unsigned int object_size;/* The original size of the object */ - unsigned int size; /* The aligned/padded/added on size */ - unsigned int align; /* Alignment as calculated */ - unsigned long flags; /* Active flags on the slab */ - const char *name; /* Slab name for sysfs */ - int refcount; /* Use counter */ - void (*ctor)(void *); /* Called on object slot creation */ - struct list_head list; /* List of all slab caches on the system */ -}; -#endif struct mem_cgroup; /* @@ -156,6 +133,35 @@ void kfree(const void *); void kzfree(const void *); size_t ksize(const void *); +#ifdef CONFIG_SLOB +/* + * Common fields provided in kmem_cache by all slab allocators + * This struct is either used directly by the allocator (SLOB) + * or the allocator must include definitions for all fields + * provided in kmem_cache_common in their definition of kmem_cache. + * + * Once we can do anonymous structs (C11 standard) we could put a + * anonymous struct definition in these allocators so that the + * separate allocations in the kmem_cache structure of SLAB and + * SLUB is no longer needed. + */ +struct kmem_cache { + unsigned int object_size;/* The original size of the object */ + unsigned int size; /* The aligned/padded/added on size */ + unsigned int align; /* Alignment as calculated */ + unsigned long flags; /* Active flags on the slab */ + const char *name; /* Slab name for sysfs */ + int refcount; /* Use counter */ + void (*ctor)(void *); /* Called on object slot creation */ + struct list_head list; /* List of all slab caches on the system */ +}; + +#define KMALLOC_MAX_SIZE (1UL << 30) + +#include + +#else /* CONFIG_SLOB */ + /* * The largest kmalloc size supported by the slab allocators is * 32 megabyte (2^25) or the maximum allocatable page order if that is @@ -171,6 +177,99 @@ size_t ksize(const void *); #define KMALLOC_MAX_SIZE (1UL << KMALLOC_SHIFT_HIGH) #define KMALLOC_MAX_ORDER (KMALLOC_SHIFT_HIGH - PAGE_SHIFT) +/* + * Kmalloc subsystem. + */ +#if defined(ARCH_DMA_MINALIGN) && ARCH_DMA_MINALIGN > 8 +#define KMALLOC_MIN_SIZE ARCH_DMA_MINALIGN +#else +#ifdef CONFIG_SLAB +#define KMALLOC_MIN_SIZE 32 +#else +#define KMALLOC_MIN_SIZE 8 +#endif +#endif + +#define KMALLOC_SHIFT_LOW ilog2(KMALLOC_MIN_SIZE) + +/* + * Figure out which kmalloc slab an allocation of a certain size + * belongs to. + * 0 = zero alloc + * 1 = 65 .. 96 bytes + * 2 = 120 .. 192 bytes + * n = 2^(n-1) .. 2^n -1 + */ +static __always_inline int kmalloc_index(size_t size) +{ + if (!size) + return 0; + + if (size <= KMALLOC_MIN_SIZE) + return KMALLOC_SHIFT_LOW; + + if (KMALLOC_MIN_SIZE <= 32 && size > 64 && size <= 96) + return 1; + if (KMALLOC_MIN_SIZE <= 64 && size > 128 && size <= 192) + return 2; + if (size <= 8) return 3; + if (size <= 16) return 4; + if (size <= 32) return 5; + if (size <= 64) return 6; + if (size <= 128) return 7; + if (size <= 256) return 8; + if (size <= 512) return 9; + if (size <= 1024) return 10; + if (size <= 2 * 1024) return 11; + if (size <= 4 * 1024) return 12; + if (size <= 8 * 1024) return 13; + if (size <= 16 * 1024) return 14; + if (size <= 32 * 1024) return 15; + if (size <= 64 * 1024) return 16; + if (size <= 128 * 1024) return 17; + if (size <= 256 * 1024) return 18; + if (size <= 512 * 1024) return 19; + if (size <= 1024 * 1024) return 20; + if (size <= 2 * 1024 * 1024) return 21; + if (size <= 4 * 1024 * 1024) return 22; + if (size <= 8 * 1024 * 1024) return 23; + if (size <= 16 * 1024 * 1024) return 24; + if (size <= 32 * 1024 * 1024) return 25; + if (size <= 64 * 1024 * 1024) return 26; + BUG(); + + /* Will never be reached. Needed because the compiler may complain */ + return -1; +} + +#ifdef CONFIG_SLAB +#include +#elif defined(CONFIG_SLUB) +#include +#else +#error "Unknown slab allocator" +#endif + +/* + * Determine size used for the nth kmalloc cache. + * return size or 0 if a kmalloc cache for that + * size does not exist + */ +static __always_inline int kmalloc_size(int n) +{ + if (n > 2) + return 1 << n; + + if (n == 1 && KMALLOC_MIN_SIZE <= 32) + return 96; + + if (n == 2 && KMALLOC_MIN_SIZE <= 64) + return 192; + + return 0; +} +#endif /* !CONFIG_SLOB */ + /* * Some archs want to perform DMA into kmalloc caches and need a guaranteed * alignment larger than the alignment of a 64-bit integer. @@ -233,33 +332,6 @@ struct seq_file; int cache_show(struct kmem_cache *s, struct seq_file *m); void print_slabinfo_header(struct seq_file *m); -/* - * Allocator specific definitions. These are mainly used to establish optimized - * ways to convert kmalloc() calls to kmem_cache_alloc() invocations by - * selecting the appropriate general cache at compile time. - * - * Allocators must define at least: - * - * kmem_cache_alloc() - * __kmalloc() - * kmalloc() - * - * Those wishing to support NUMA must also define: - * - * kmem_cache_alloc_node() - * kmalloc_node() - * - * See each allocator definition file for additional comments and - * implementation notes. - */ -#ifdef CONFIG_SLUB -#include -#elif defined(CONFIG_SLOB) -#include -#else -#include -#endif - /** * kmalloc_array - allocate memory for an array. * @n: number of elements. diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 9db4825cd393..99c3e05ff1f0 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -115,17 +115,6 @@ struct kmem_cache { struct kmem_cache_node *node[MAX_NUMNODES]; }; -/* - * Kmalloc subsystem. - */ -#if defined(ARCH_DMA_MINALIGN) && ARCH_DMA_MINALIGN > 8 -#define KMALLOC_MIN_SIZE ARCH_DMA_MINALIGN -#else -#define KMALLOC_MIN_SIZE 8 -#endif - -#define KMALLOC_SHIFT_LOW ilog2(KMALLOC_MIN_SIZE) - /* * Maximum kmalloc object size handled by SLUB. Larger object allocations * are passed through to the page allocator. The page allocator "fastpath" @@ -152,58 +141,6 @@ struct kmem_cache { */ extern struct kmem_cache *kmalloc_caches[SLUB_PAGE_SHIFT]; -/* - * Sorry that the following has to be that ugly but some versions of GCC - * have trouble with constant propagation and loops. - */ -static __always_inline int kmalloc_index(size_t size) -{ - if (!size) - return 0; - - if (size <= KMALLOC_MIN_SIZE) - return KMALLOC_SHIFT_LOW; - - if (KMALLOC_MIN_SIZE <= 32 && size > 64 && size <= 96) - return 1; - if (KMALLOC_MIN_SIZE <= 64 && size > 128 && size <= 192) - return 2; - if (size <= 8) return 3; - if (size <= 16) return 4; - if (size <= 32) return 5; - if (size <= 64) return 6; - if (size <= 128) return 7; - if (size <= 256) return 8; - if (size <= 512) return 9; - if (size <= 1024) return 10; - if (size <= 2 * 1024) return 11; - if (size <= 4 * 1024) return 12; -/* - * The following is only needed to support architectures with a larger page - * size than 4k. We need to support 2 * PAGE_SIZE here. So for a 64k page - * size we would have to go up to 128k. - */ - if (size <= 8 * 1024) return 13; - if (size <= 16 * 1024) return 14; - if (size <= 32 * 1024) return 15; - if (size <= 64 * 1024) return 16; - if (size <= 128 * 1024) return 17; - if (size <= 256 * 1024) return 18; - if (size <= 512 * 1024) return 19; - if (size <= 1024 * 1024) return 20; - if (size <= 2 * 1024 * 1024) return 21; - BUG(); - return -1; /* Will never be reached */ - -/* - * What we really wanted to do and cannot do because of compiler issues is: - * int i; - * for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++) - * if (size <= (1 << i)) - * return i; - */ -} - /* * Find the slab cache for a given combination of allocation flags and size. * -- cgit v1.2.3 From e33660165c901d18e7d3df2290db070d3e4b46df Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Thu, 10 Jan 2013 19:14:18 +0000 Subject: slab: Use common kmalloc_index/kmalloc_size functions Make slab use the common functions. We can get rid of a lot of old ugly stuff as a results. Among them the sizes array and the weird include/linux/kmalloc_sizes file and some pretty bad #include statements in slab_def.h. The one thing that is different in slab is that the 32 byte cache will also be created for arches that have page sizes larger than 4K. There are numerous smaller allocations that SLOB and SLUB can handle better because of their support for smaller allocation sizes so lets keep the 32 byte slab also for arches with > 4K pages. Reviewed-by: Glauber Costa Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/kmalloc_sizes.h | 45 ----------------------------------------- include/linux/slab_def.h | 47 +++++++++++-------------------------------- 2 files changed, 12 insertions(+), 80 deletions(-) delete mode 100644 include/linux/kmalloc_sizes.h (limited to 'include') diff --git a/include/linux/kmalloc_sizes.h b/include/linux/kmalloc_sizes.h deleted file mode 100644 index e576b848ce10..000000000000 --- a/include/linux/kmalloc_sizes.h +++ /dev/null @@ -1,45 +0,0 @@ -#if (PAGE_SIZE == 4096) - CACHE(32) -#endif - CACHE(64) -#if L1_CACHE_BYTES < 64 - CACHE(96) -#endif - CACHE(128) -#if L1_CACHE_BYTES < 128 - CACHE(192) -#endif - CACHE(256) - CACHE(512) - CACHE(1024) - CACHE(2048) - CACHE(4096) - CACHE(8192) - CACHE(16384) - CACHE(32768) - CACHE(65536) - CACHE(131072) -#if KMALLOC_MAX_SIZE >= 262144 - CACHE(262144) -#endif -#if KMALLOC_MAX_SIZE >= 524288 - CACHE(524288) -#endif -#if KMALLOC_MAX_SIZE >= 1048576 - CACHE(1048576) -#endif -#if KMALLOC_MAX_SIZE >= 2097152 - CACHE(2097152) -#endif -#if KMALLOC_MAX_SIZE >= 4194304 - CACHE(4194304) -#endif -#if KMALLOC_MAX_SIZE >= 8388608 - CACHE(8388608) -#endif -#if KMALLOC_MAX_SIZE >= 16777216 - CACHE(16777216) -#endif -#if KMALLOC_MAX_SIZE >= 33554432 - CACHE(33554432) -#endif diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index 8bb6e0eaf3c6..e0f30ef9525d 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -11,8 +11,6 @@ */ #include -#include /* kmalloc_sizes.h needs PAGE_SIZE */ -#include /* kmalloc_sizes.h needs L1_CACHE_BYTES */ #include /* @@ -104,15 +102,8 @@ struct kmem_cache { */ }; -/* Size description struct for general caches. */ -struct cache_sizes { - size_t cs_size; - struct kmem_cache *cs_cachep; -#ifdef CONFIG_ZONE_DMA - struct kmem_cache *cs_dmacachep; -#endif -}; -extern struct cache_sizes malloc_sizes[]; +extern struct kmem_cache *kmalloc_caches[PAGE_SHIFT + MAX_ORDER]; +extern struct kmem_cache *kmalloc_dma_caches[PAGE_SHIFT + MAX_ORDER]; void *kmem_cache_alloc(struct kmem_cache *, gfp_t); void *__kmalloc(size_t size, gfp_t flags); @@ -133,26 +124,19 @@ static __always_inline void *kmalloc(size_t size, gfp_t flags) void *ret; if (__builtin_constant_p(size)) { - int i = 0; + int i; if (!size) return ZERO_SIZE_PTR; -#define CACHE(x) \ - if (size <= x) \ - goto found; \ - else \ - i++; -#include -#undef CACHE - return NULL; -found: + i = kmalloc_index(size); + #ifdef CONFIG_ZONE_DMA if (flags & GFP_DMA) - cachep = malloc_sizes[i].cs_dmacachep; + cachep = kmalloc_dma_caches[i]; else #endif - cachep = malloc_sizes[i].cs_cachep; + cachep = kmalloc_caches[i]; ret = kmem_cache_alloc_trace(cachep, flags, size); @@ -186,26 +170,19 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) struct kmem_cache *cachep; if (__builtin_constant_p(size)) { - int i = 0; + int i; if (!size) return ZERO_SIZE_PTR; -#define CACHE(x) \ - if (size <= x) \ - goto found; \ - else \ - i++; -#include -#undef CACHE - return NULL; -found: + i = kmalloc_index(size); + #ifdef CONFIG_ZONE_DMA if (flags & GFP_DMA) - cachep = malloc_sizes[i].cs_dmacachep; + cachep = kmalloc_dma_caches[i]; else #endif - cachep = malloc_sizes[i].cs_cachep; + cachep = kmalloc_caches[i]; return kmem_cache_alloc_node_trace(cachep, flags, node, size); } -- cgit v1.2.3 From 6744f087ba2a49f6d6935d9daa0b20a0f03567b5 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Thu, 10 Jan 2013 19:12:17 +0000 Subject: slab: Common name for the per node structures Rename the structure used for the per node structures in slab to have a name that expresses that fact. Acked-by: Glauber Costa Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/slab_def.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index e0f30ef9525d..8b5b2f6b36d3 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -95,7 +95,7 @@ struct kmem_cache { * pointer for each node since "nodelists" uses the remainder of * available pointers. */ - struct kmem_list3 **nodelists; + struct kmem_cache_node **nodelists; struct array_cache *array[NR_CPUS + MAX_NUMNODES]; /* * Do not add fields after array[] -- cgit v1.2.3 From 6a67368c36e2c0c2578ba62f6264ab739af08cce Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Thu, 10 Jan 2013 19:14:19 +0000 Subject: slab: Rename nodelists to node Have a common naming between both slab caches for future changes. Acked-by: Glauber Costa Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/slab_def.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index 8b5b2f6b36d3..4ff50e8d1a2c 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -95,7 +95,7 @@ struct kmem_cache { * pointer for each node since "nodelists" uses the remainder of * available pointers. */ - struct kmem_cache_node **nodelists; + struct kmem_cache_node **node; struct array_cache *array[NR_CPUS + MAX_NUMNODES]; /* * Do not add fields after array[] -- cgit v1.2.3 From 95a05b428cc675694321c8f762591984f3fd2b1e Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Thu, 10 Jan 2013 19:14:19 +0000 Subject: slab: Common constants for kmalloc boundaries Standardize the constants that describe the smallest and largest object kept in the kmalloc arrays for SLAB and SLUB. Differentiate between the maximum size for which a slab cache is used (KMALLOC_MAX_CACHE_SIZE) and the maximum allocatable size (KMALLOC_MAX_SIZE, KMALLOC_MAX_ORDER). Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/slab.h | 34 ++++++++++++++++++++++++---------- include/linux/slub_def.h | 19 +++---------------- 2 files changed, 27 insertions(+), 26 deletions(-) (limited to 'include') diff --git a/include/linux/slab.h b/include/linux/slab.h index c97fe92532d1..c01780540054 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -163,7 +163,12 @@ struct kmem_cache { #else /* CONFIG_SLOB */ /* - * The largest kmalloc size supported by the slab allocators is + * Kmalloc array related definitions + */ + +#ifdef CONFIG_SLAB +/* + * The largest kmalloc size supported by the SLAB allocators is * 32 megabyte (2^25) or the maximum allocatable page order if that is * less than 32 MB. * @@ -173,9 +178,24 @@ struct kmem_cache { */ #define KMALLOC_SHIFT_HIGH ((MAX_ORDER + PAGE_SHIFT - 1) <= 25 ? \ (MAX_ORDER + PAGE_SHIFT - 1) : 25) +#define KMALLOC_SHIFT_MAX KMALLOC_SHIFT_HIGH +#define KMALLOC_SHIFT_LOW 5 +#else +/* + * SLUB allocates up to order 2 pages directly and otherwise + * passes the request to the page allocator. + */ +#define KMALLOC_SHIFT_HIGH (PAGE_SHIFT + 1) +#define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT) +#define KMALLOC_SHIFT_LOW 3 +#endif -#define KMALLOC_MAX_SIZE (1UL << KMALLOC_SHIFT_HIGH) -#define KMALLOC_MAX_ORDER (KMALLOC_SHIFT_HIGH - PAGE_SHIFT) +/* Maximum allocatable size */ +#define KMALLOC_MAX_SIZE (1UL << KMALLOC_SHIFT_MAX) +/* Maximum size for which we actually use a slab cache */ +#define KMALLOC_MAX_CACHE_SIZE (1UL << KMALLOC_SHIFT_HIGH) +/* Maximum order allocatable via the slab allocagtor */ +#define KMALLOC_MAX_ORDER (KMALLOC_SHIFT_MAX - PAGE_SHIFT) /* * Kmalloc subsystem. @@ -183,15 +203,9 @@ struct kmem_cache { #if defined(ARCH_DMA_MINALIGN) && ARCH_DMA_MINALIGN > 8 #define KMALLOC_MIN_SIZE ARCH_DMA_MINALIGN #else -#ifdef CONFIG_SLAB -#define KMALLOC_MIN_SIZE 32 -#else -#define KMALLOC_MIN_SIZE 8 -#endif +#define KMALLOC_MIN_SIZE (1 << KMALLOC_SHIFT_LOW) #endif -#define KMALLOC_SHIFT_LOW ilog2(KMALLOC_MIN_SIZE) - /* * Figure out which kmalloc slab an allocation of a certain size * belongs to. diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 99c3e05ff1f0..032028ef9a34 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -115,19 +115,6 @@ struct kmem_cache { struct kmem_cache_node *node[MAX_NUMNODES]; }; -/* - * Maximum kmalloc object size handled by SLUB. Larger object allocations - * are passed through to the page allocator. The page allocator "fastpath" - * is relatively slow so we need this value sufficiently high so that - * performance critical objects are allocated through the SLUB fastpath. - * - * This should be dropped to PAGE_SIZE / 2 once the page allocator - * "fastpath" becomes competitive with the slab allocator fastpaths. - */ -#define SLUB_MAX_SIZE (2 * PAGE_SIZE) - -#define SLUB_PAGE_SHIFT (PAGE_SHIFT + 2) - #ifdef CONFIG_ZONE_DMA #define SLUB_DMA __GFP_DMA #else @@ -139,7 +126,7 @@ struct kmem_cache { * We keep the general caches in an array of slab caches that are used for * 2^x bytes of allocations. */ -extern struct kmem_cache *kmalloc_caches[SLUB_PAGE_SHIFT]; +extern struct kmem_cache *kmalloc_caches[KMALLOC_SHIFT_HIGH + 1]; /* * Find the slab cache for a given combination of allocation flags and size. @@ -211,7 +198,7 @@ static __always_inline void *kmalloc_large(size_t size, gfp_t flags) static __always_inline void *kmalloc(size_t size, gfp_t flags) { if (__builtin_constant_p(size)) { - if (size > SLUB_MAX_SIZE) + if (size > KMALLOC_MAX_CACHE_SIZE) return kmalloc_large(size, flags); if (!(flags & SLUB_DMA)) { @@ -247,7 +234,7 @@ kmem_cache_alloc_node_trace(struct kmem_cache *s, static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) { if (__builtin_constant_p(size) && - size <= SLUB_MAX_SIZE && !(flags & SLUB_DMA)) { + size <= KMALLOC_MAX_CACHE_SIZE && !(flags & SLUB_DMA)) { struct kmem_cache *s = kmalloc_slab(size); if (!s) -- cgit v1.2.3 From 9425c58e5445277699ff3c2a87bac1cfebc1b48d Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Thu, 10 Jan 2013 19:12:17 +0000 Subject: slab: Common definition for the array of kmalloc caches Have a common definition fo the kmalloc cache arrays in SLAB and SLUB Acked-by: Glauber Costa Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/slab.h | 5 +++++ include/linux/slab_def.h | 3 --- include/linux/slub_def.h | 6 ------ 3 files changed, 5 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/slab.h b/include/linux/slab.h index c01780540054..f2327a898a85 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -206,6 +206,11 @@ struct kmem_cache { #define KMALLOC_MIN_SIZE (1 << KMALLOC_SHIFT_LOW) #endif +extern struct kmem_cache *kmalloc_caches[KMALLOC_SHIFT_HIGH + 1]; +#ifdef CONFIG_ZONE_DMA +extern struct kmem_cache *kmalloc_dma_caches[KMALLOC_SHIFT_HIGH + 1]; +#endif + /* * Figure out which kmalloc slab an allocation of a certain size * belongs to. diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index 4ff50e8d1a2c..113ec080313f 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -102,9 +102,6 @@ struct kmem_cache { */ }; -extern struct kmem_cache *kmalloc_caches[PAGE_SHIFT + MAX_ORDER]; -extern struct kmem_cache *kmalloc_dma_caches[PAGE_SHIFT + MAX_ORDER]; - void *kmem_cache_alloc(struct kmem_cache *, gfp_t); void *__kmalloc(size_t size, gfp_t flags); diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 032028ef9a34..3701896f7f8a 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -122,12 +122,6 @@ struct kmem_cache { #define SLUB_DMA (__force gfp_t)0 #endif -/* - * We keep the general caches in an array of slab caches that are used for - * 2^x bytes of allocations. - */ -extern struct kmem_cache *kmalloc_caches[KMALLOC_SHIFT_HIGH + 1]; - /* * Find the slab cache for a given combination of allocation flags and size. * -- cgit v1.2.3 From 2c59dd6544212faa5ce761920d2251f4152f408d Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Thu, 10 Jan 2013 19:14:19 +0000 Subject: slab: Common Kmalloc cache determination Extract the optimized lookup functions from slub and put them into slab_common.c. Then make slab use these functions as well. Joonsoo notes that this fixes some issues with constant folding which also reduces the code size for slub. https://lkml.org/lkml/2012/10/20/82 Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/slub_def.h | 41 ++++++++++------------------------------- 1 file changed, 10 insertions(+), 31 deletions(-) (limited to 'include') diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 3701896f7f8a..16341e5316de 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -115,29 +115,6 @@ struct kmem_cache { struct kmem_cache_node *node[MAX_NUMNODES]; }; -#ifdef CONFIG_ZONE_DMA -#define SLUB_DMA __GFP_DMA -#else -/* Disable DMA functionality */ -#define SLUB_DMA (__force gfp_t)0 -#endif - -/* - * Find the slab cache for a given combination of allocation flags and size. - * - * This ought to end up with a global pointer to the right cache - * in kmalloc_caches. - */ -static __always_inline struct kmem_cache *kmalloc_slab(size_t size) -{ - int index = kmalloc_index(size); - - if (index == 0) - return NULL; - - return kmalloc_caches[index]; -} - void *kmem_cache_alloc(struct kmem_cache *, gfp_t); void *__kmalloc(size_t size, gfp_t flags); @@ -195,13 +172,14 @@ static __always_inline void *kmalloc(size_t size, gfp_t flags) if (size > KMALLOC_MAX_CACHE_SIZE) return kmalloc_large(size, flags); - if (!(flags & SLUB_DMA)) { - struct kmem_cache *s = kmalloc_slab(size); + if (!(flags & GFP_DMA)) { + int index = kmalloc_index(size); - if (!s) + if (!index) return ZERO_SIZE_PTR; - return kmem_cache_alloc_trace(s, flags, size); + return kmem_cache_alloc_trace(kmalloc_caches[index], + flags, size); } } return __kmalloc(size, flags); @@ -228,13 +206,14 @@ kmem_cache_alloc_node_trace(struct kmem_cache *s, static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) { if (__builtin_constant_p(size) && - size <= KMALLOC_MAX_CACHE_SIZE && !(flags & SLUB_DMA)) { - struct kmem_cache *s = kmalloc_slab(size); + size <= KMALLOC_MAX_CACHE_SIZE && !(flags & GFP_DMA)) { + int index = kmalloc_index(size); - if (!s) + if (!index) return ZERO_SIZE_PTR; - return kmem_cache_alloc_node_trace(s, flags, node, size); + return kmem_cache_alloc_node_trace(kmalloc_caches[index], + flags, node, size); } return __kmalloc_node(size, flags, node); } -- cgit v1.2.3 From ca34956b804b7554fc4e88826773380d9d5122a8 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Thu, 10 Jan 2013 19:14:19 +0000 Subject: slab: Common definition for kmem_cache_node Put the definitions for the kmem_cache_node structures together so that we have one structure. That will allow us to create more common fields in the future which could yield more opportunities to share code. Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/slub_def.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include') diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 16341e5316de..027276fa8713 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -53,17 +53,6 @@ struct kmem_cache_cpu { #endif }; -struct kmem_cache_node { - spinlock_t list_lock; /* Protect partial list and nr_partial */ - unsigned long nr_partial; - struct list_head partial; -#ifdef CONFIG_SLUB_DEBUG - atomic_long_t nr_slabs; - atomic_long_t total_objects; - struct list_head full; -#endif -}; - /* * Word size structure that can be atomically updated or read and that * contains both the order and the number of objects that a slab of the -- cgit v1.2.3 From c601fd6956e92b0eb268d4af754073c76155b99d Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Tue, 5 Feb 2013 16:36:47 +0000 Subject: slab: Handle ARCH_DMA_MINALIGN correctly James Hogan hit boot problems in next-20130204 on Meta: META213-Thread0 DSP [LogF] kobject (4fc03980): tried to init an initialized object, something is seriously wrong. META213-Thread0 DSP [LogF] META213-Thread0 DSP [LogF] Call trace: META213-Thread0 DSP [LogF] [<4000888c>] _show_stack+0x68/0x7c META213-Thread0 DSP [LogF] [<400088b4>] _dump_stack+0x14/0x28 META213-Thread0 DSP [LogF] [<40103794>] _kobject_init+0x58/0x9c META213-Thread0 DSP [LogF] [<40103810>] _kobject_create+0x38/0x64 META213-Thread0 DSP [LogF] [<40103eac>] _kobject_create_and_add+0x14/0x8c META213-Thread0 DSP [LogF] [<40190ac4>] _mnt_init+0xd8/0x220 META213-Thread0 DSP [LogF] [<40190508>] _vfs_caches_init+0xb0/0x160 META213-Thread0 DSP [LogF] [<401851f4>] _start_kernel+0x274/0x340 META213-Thread0 DSP [LogF] [<40188424>] _metag_start_kernel+0x58/0x6c META213-Thread0 DSP [LogF] [<40000044>] __start+0x44/0x48 META213-Thread0 DSP [LogF] META213-Thread0 DSP [LogF] devtmpfs: initialized META213-Thread0 DSP [LogF] L2 Cache: Not present META213-Thread0 DSP [LogF] BUG: failure at fs/sysfs/dir.c:736/sysfs_read_ns_type()! META213-Thread0 DSP [LogF] Kernel panic - not syncing: BUG! META213-Thread0 DSP [Thread Exit] Thread has exited - return code = 4294967295 And bisected the problem to commit 95a05b4 ("slab: Common constants for kmalloc boundaries"). As it turns out, a fixed KMALLOC_SHIFT_LOW does not work for arches with higher alignment requirements. Determine KMALLOC_SHIFT_LOW from ARCH_DMA_MINALIGN instead. Reported-and-tested-by: James Hogan Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/slab.h | 32 ++++++++++++++++++-------------- 1 file changed, 18 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/linux/slab.h b/include/linux/slab.h index f2327a898a85..0c621752caa6 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -133,6 +133,19 @@ void kfree(const void *); void kzfree(const void *); size_t ksize(const void *); +/* + * Some archs want to perform DMA into kmalloc caches and need a guaranteed + * alignment larger than the alignment of a 64-bit integer. + * Setting ARCH_KMALLOC_MINALIGN in arch headers allows that. + */ +#if defined(ARCH_DMA_MINALIGN) && ARCH_DMA_MINALIGN > 8 +#define ARCH_KMALLOC_MINALIGN ARCH_DMA_MINALIGN +#define KMALLOC_MIN_SIZE ARCH_DMA_MINALIGN +#define KMALLOC_SHIFT_LOW ilog2(ARCH_DMA_MINALIGN) +#else +#define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long) +#endif + #ifdef CONFIG_SLOB /* * Common fields provided in kmem_cache by all slab allocators @@ -179,7 +192,9 @@ struct kmem_cache { #define KMALLOC_SHIFT_HIGH ((MAX_ORDER + PAGE_SHIFT - 1) <= 25 ? \ (MAX_ORDER + PAGE_SHIFT - 1) : 25) #define KMALLOC_SHIFT_MAX KMALLOC_SHIFT_HIGH +#ifndef KMALLOC_SHIFT_LOW #define KMALLOC_SHIFT_LOW 5 +#endif #else /* * SLUB allocates up to order 2 pages directly and otherwise @@ -187,8 +202,10 @@ struct kmem_cache { */ #define KMALLOC_SHIFT_HIGH (PAGE_SHIFT + 1) #define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT) +#ifndef KMALLOC_SHIFT_LOW #define KMALLOC_SHIFT_LOW 3 #endif +#endif /* Maximum allocatable size */ #define KMALLOC_MAX_SIZE (1UL << KMALLOC_SHIFT_MAX) @@ -200,9 +217,7 @@ struct kmem_cache { /* * Kmalloc subsystem. */ -#if defined(ARCH_DMA_MINALIGN) && ARCH_DMA_MINALIGN > 8 -#define KMALLOC_MIN_SIZE ARCH_DMA_MINALIGN -#else +#ifndef KMALLOC_MIN_SIZE #define KMALLOC_MIN_SIZE (1 << KMALLOC_SHIFT_LOW) #endif @@ -289,17 +304,6 @@ static __always_inline int kmalloc_size(int n) } #endif /* !CONFIG_SLOB */ -/* - * Some archs want to perform DMA into kmalloc caches and need a guaranteed - * alignment larger than the alignment of a 64-bit integer. - * Setting ARCH_KMALLOC_MINALIGN in arch headers allows that. - */ -#ifdef ARCH_DMA_MINALIGN -#define ARCH_KMALLOC_MINALIGN ARCH_DMA_MINALIGN -#else -#define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long) -#endif - /* * Setting ARCH_SLAB_MINALIGN in arch headers allows a different alignment. * Intended for arches that get misalignment faults even for 64 bit integer -- cgit v1.2.3 From 462fce46065ec4b200c08619c047b9e5a8fd154a Mon Sep 17 00:00:00 2001 From: Takuya Yoshikawa Date: Wed, 27 Feb 2013 19:41:56 +0900 Subject: KVM: set_memory_region: Drop user_alloc from prepare/commit_memory_region() X86 does not use this any more. The remaining user, s390's !user_alloc check, can be simply removed since KVM_SET_MEMORY_REGION ioctl is no longer supported. Note: fixed powerpc's indentations with spaces to suppress checkpatch errors. Signed-off-by: Takuya Yoshikawa Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index cad77fe09d77..b4757a1cc4c4 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -464,12 +464,10 @@ int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages); int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, struct kvm_memory_slot old, - struct kvm_userspace_memory_region *mem, - bool user_alloc); + struct kvm_userspace_memory_region *mem); void kvm_arch_commit_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem, - struct kvm_memory_slot old, - bool user_alloc); + struct kvm_memory_slot old); bool kvm_largepages_enabled(void); void kvm_disable_largepages(void); /* flush all memory translations */ -- cgit v1.2.3 From 47ae31e257c548abdb199e0d26723139a9a967ba Mon Sep 17 00:00:00 2001 From: Takuya Yoshikawa Date: Wed, 27 Feb 2013 19:43:00 +0900 Subject: KVM: set_memory_region: Drop user_alloc from set_memory_region() Except ia64's stale code, KVM_SET_MEMORY_REGION support, this is only used for sanity checks in __kvm_set_memory_region() which can easily be changed to use slot id instead. Signed-off-by: Takuya Yoshikawa Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index b4757a1cc4c4..84a994c7a5c5 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -453,11 +453,9 @@ id_to_memslot(struct kvm_memslots *slots, int id) } int kvm_set_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem, - bool user_alloc); + struct kvm_userspace_memory_region *mem); int __kvm_set_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem, - bool user_alloc); + struct kvm_userspace_memory_region *mem); void kvm_arch_free_memslot(struct kvm_memory_slot *free, struct kvm_memory_slot *dont); int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages); @@ -553,9 +551,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log); int kvm_vm_ioctl_set_memory_region(struct kvm *kvm, - struct - kvm_userspace_memory_region *mem, - bool user_alloc); + struct kvm_userspace_memory_region *mem); int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level); long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); -- cgit v1.2.3 From 74d0727cb7aaaea48a6353209093be26abc8d160 Mon Sep 17 00:00:00 2001 From: Takuya Yoshikawa Date: Wed, 27 Feb 2013 19:43:44 +0900 Subject: KVM: set_memory_region: Make kvm_mr_change available to arch code This will be used for cleaning up prepare/commit_memory_region() later. Signed-off-by: Takuya Yoshikawa Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 84a994c7a5c5..8eaf61f7b02d 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -452,6 +452,24 @@ id_to_memslot(struct kvm_memslots *slots, int id) return slot; } +/* + * KVM_SET_USER_MEMORY_REGION ioctl allows the following operations: + * - create a new memory slot + * - delete an existing memory slot + * - modify an existing memory slot + * -- move it in the guest physical memory space + * -- just change its flags + * + * Since flags can be changed by some of these operations, the following + * differentiation is the best we can do for __kvm_set_memory_region(): + */ +enum kvm_mr_change { + KVM_MR_CREATE, + KVM_MR_DELETE, + KVM_MR_MOVE, + KVM_MR_FLAGS_ONLY, +}; + int kvm_set_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem); int __kvm_set_memory_region(struct kvm *kvm, -- cgit v1.2.3 From 7b6195a91d60909a2834ab7181e2b9476e6fe749 Mon Sep 17 00:00:00 2001 From: Takuya Yoshikawa Date: Wed, 27 Feb 2013 19:44:34 +0900 Subject: KVM: set_memory_region: Refactor prepare_memory_region() This patch drops the parameter old, a copy of the old memory slot, and adds a new parameter named change to know the change being requested. This not only cleans up the code but also removes extra copying of the memory slot structure. Signed-off-by: Takuya Yoshikawa Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 8eaf61f7b02d..caa72cf7e8e7 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -479,8 +479,8 @@ void kvm_arch_free_memslot(struct kvm_memory_slot *free, int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages); int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, - struct kvm_memory_slot old, - struct kvm_userspace_memory_region *mem); + struct kvm_userspace_memory_region *mem, + enum kvm_mr_change change); void kvm_arch_commit_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem, struct kvm_memory_slot old); -- cgit v1.2.3 From 8482644aea11e0647867732319ccf35879a9acc2 Mon Sep 17 00:00:00 2001 From: Takuya Yoshikawa Date: Wed, 27 Feb 2013 19:45:25 +0900 Subject: KVM: set_memory_region: Refactor commit_memory_region() This patch makes the parameter old a const pointer to the old memory slot and adds a new parameter named change to know the change being requested: the former is for removing extra copying and the latter is for cleaning up the code. Signed-off-by: Takuya Yoshikawa Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index caa72cf7e8e7..ac584cc53581 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -483,7 +483,8 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, enum kvm_mr_change change); void kvm_arch_commit_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem, - struct kvm_memory_slot old); + const struct kvm_memory_slot *old, + enum kvm_mr_change change); bool kvm_largepages_enabled(void); void kvm_disable_largepages(void); /* flush all memory translations */ -- cgit v1.2.3 From a0f155e9646d5f1c263f6f9aae880151100243bb Mon Sep 17 00:00:00 2001 From: Cornelia Huck Date: Thu, 28 Feb 2013 12:33:18 +0100 Subject: KVM: Initialize irqfd from kvm_init(). Currently, eventfd introduces module_init/module_exit functions to initialize/cleanup the irqfd workqueue. This only works, however, if no other module_init/module_exit functions are built into the same module. Let's just move the initialization and cleanup to kvm_init and kvm_exit. This way, it is also clearer where kvm startup may fail. Signed-off-by: Cornelia Huck Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index ac584cc53581..d50fe173028b 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -424,6 +424,19 @@ void kvm_vcpu_uninit(struct kvm_vcpu *vcpu); int __must_check vcpu_load(struct kvm_vcpu *vcpu); void vcpu_put(struct kvm_vcpu *vcpu); +#ifdef __KVM_HAVE_IOAPIC +int kvm_irqfd_init(void); +void kvm_irqfd_exit(void); +#else +static inline int kvm_irqfd_init(void) +{ + return 0; +} + +static inline void kvm_irqfd_exit(void) +{ +} +#endif int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align, struct module *module); void kvm_exit(void); -- cgit v1.2.3 From 060f0ce6ff975decd1e0ee318c08e228bccbee1e Mon Sep 17 00:00:00 2001 From: Cornelia Huck Date: Thu, 28 Feb 2013 12:33:19 +0100 Subject: KVM: Introduce KVM_VIRTIO_CCW_NOTIFY_BUS. Add a new bus type for virtio-ccw devices on s390. Signed-off-by: Cornelia Huck Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index d50fe173028b..9fa13ebc3381 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -149,6 +149,7 @@ struct kvm_io_bus { enum kvm_bus { KVM_MMIO_BUS, KVM_PIO_BUS, + KVM_VIRTIO_CCW_NOTIFY_BUS, KVM_NR_BUSES }; -- cgit v1.2.3 From 2b83451b45d720ca38c03878ce42ff9139cad9e3 Mon Sep 17 00:00:00 2001 From: Cornelia Huck Date: Thu, 28 Feb 2013 12:33:20 +0100 Subject: KVM: ioeventfd for virtio-ccw devices. Enhance KVM_IOEVENTFD with a new flag that allows to attach to virtio-ccw devices on s390 via the KVM_VIRTIO_CCW_NOTIFY_BUS. Signed-off-by: Cornelia Huck Signed-off-by: Marcelo Tosatti --- include/uapi/linux/kvm.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 3c56ba3d80c1..74d0ff3dfd66 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -449,12 +449,15 @@ enum { kvm_ioeventfd_flag_nr_datamatch, kvm_ioeventfd_flag_nr_pio, kvm_ioeventfd_flag_nr_deassign, + kvm_ioeventfd_flag_nr_virtio_ccw_notify, kvm_ioeventfd_flag_nr_max, }; #define KVM_IOEVENTFD_FLAG_DATAMATCH (1 << kvm_ioeventfd_flag_nr_datamatch) #define KVM_IOEVENTFD_FLAG_PIO (1 << kvm_ioeventfd_flag_nr_pio) #define KVM_IOEVENTFD_FLAG_DEASSIGN (1 << kvm_ioeventfd_flag_nr_deassign) +#define KVM_IOEVENTFD_FLAG_VIRTIO_CCW_NOTIFY \ + (1 << kvm_ioeventfd_flag_nr_virtio_ccw_notify) #define KVM_IOEVENTFD_VALID_FLAG_MASK ((1 << kvm_ioeventfd_flag_nr_max) - 1) -- cgit v1.2.3 From 3a08a8f9f0936e182d387afd85fdc5d303381521 Mon Sep 17 00:00:00 2001 From: Raghavendra K T Date: Mon, 4 Mar 2013 23:32:07 +0530 Subject: kvm: Record the preemption status of vcpus using preempt notifiers Note that we mark as preempted only when vcpu's task state was Running during preemption. Thanks Jiannan, Avi for preemption notifier ideas. Thanks Gleb, PeterZ for their precious suggestions. Thanks Srikar for an idea on avoiding rcu lock while checking task state that improved overcommit numbers. Reviewed-by: Chegu Vinod Reviewed-by: Marcelo Tosatti Signed-off-by: Raghavendra K T Signed-off-by: Gleb Natapov --- include/linux/kvm_host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 9fa13ebc3381..0f4941a9c9c8 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -253,6 +253,7 @@ struct kvm_vcpu { bool dy_eligible; } spin_loop; #endif + bool preempted; struct kvm_vcpu_arch arch; }; -- cgit v1.2.3 From 5a20d339c785d98d8b050b9afc098e4184a6098c Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Sun, 3 Mar 2013 13:58:05 +0900 Subject: f2fs: align f2fs maximum name length to linux based filesystem The maximum filename length supported in linux is 255 characters. So let's follow that. Signed-off-by: Namjae Jeon Signed-off-by: Amit Sahrawat Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index f9a12f6243a5..df6fab82f87e 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -139,7 +139,7 @@ struct f2fs_extent { __le32 len; /* lengh of the extent */ } __packed; -#define F2FS_MAX_NAME_LEN 256 +#define F2FS_NAME_LEN 255 #define ADDRS_PER_INODE 923 /* Address Pointers in an Inode */ #define ADDRS_PER_BLOCK 1018 /* Address Pointers in a Direct Block */ #define NIDS_PER_BLOCK 1018 /* Node IDs in an Indirect Block */ @@ -165,7 +165,8 @@ struct f2fs_inode { __le32 i_flags; /* file attributes */ __le32 i_pino; /* parent inode number */ __le32 i_namelen; /* file name length */ - __u8 i_name[F2FS_MAX_NAME_LEN]; /* file name for SPOR */ + __u8 i_name[F2FS_NAME_LEN]; /* file name for SPOR */ + __u8 i_reserved2; /* for backward compatibility */ struct f2fs_extent i_ext; /* caching a largest extent */ @@ -362,10 +363,10 @@ struct f2fs_summary_block { typedef __le32 f2fs_hash_t; /* One directory entry slot covers 8bytes-long file name */ -#define F2FS_NAME_LEN 8 -#define F2FS_NAME_LEN_BITS 3 +#define F2FS_SLOT_LEN 8 +#define F2FS_SLOT_LEN_BITS 3 -#define GET_DENTRY_SLOTS(x) ((x + F2FS_NAME_LEN - 1) >> F2FS_NAME_LEN_BITS) +#define GET_DENTRY_SLOTS(x) ((x + F2FS_SLOT_LEN - 1) >> F2FS_SLOT_LEN_BITS) /* the number of dentry in a block */ #define NR_DENTRY_IN_BLOCK 214 @@ -377,10 +378,10 @@ typedef __le32 f2fs_hash_t; #define SIZE_OF_DENTRY_BITMAP ((NR_DENTRY_IN_BLOCK + BITS_PER_BYTE - 1) / \ BITS_PER_BYTE) #define SIZE_OF_RESERVED (PAGE_SIZE - ((SIZE_OF_DIR_ENTRY + \ - F2FS_NAME_LEN) * \ + F2FS_SLOT_LEN) * \ NR_DENTRY_IN_BLOCK + SIZE_OF_DENTRY_BITMAP)) -/* One directory entry slot representing F2FS_NAME_LEN-sized file name */ +/* One directory entry slot representing F2FS_SLOT_LEN-sized file name */ struct f2fs_dir_entry { __le32 hash_code; /* hash code of file name */ __le32 ino; /* inode number */ @@ -394,7 +395,7 @@ struct f2fs_dentry_block { __u8 dentry_bitmap[SIZE_OF_DENTRY_BITMAP]; __u8 reserved[SIZE_OF_RESERVED]; struct f2fs_dir_entry dentry[NR_DENTRY_IN_BLOCK]; - __u8 filename[NR_DENTRY_IN_BLOCK][F2FS_NAME_LEN]; + __u8 filename[NR_DENTRY_IN_BLOCK][F2FS_SLOT_LEN]; } __packed; /* file types used in inode_info->flags */ -- cgit v1.2.3 From cbe5e6109538ddab57764a88d9f0c2accd0c7d48 Mon Sep 17 00:00:00 2001 From: Lars Ellenberg Date: Fri, 22 Mar 2013 22:17:36 -0600 Subject: lru_cache: introduce lc_get_cumulative() New helper to be able to consolidate more updates into a single transaction. Without this, we can only grab a single refcount on an updated element while preparing a transaction. lc_get_cumulative - like lc_get; also finds to-be-changed elements @lc: the lru cache to operate on @enr: the label to look up Unlike lc_get this also returns the element for @enr, if it is belonging to a pending transaction, so the return values are like for lc_get(), plus: pointer to an element already on the "to_be_changed" list. In this case, the cache was already marked %LC_DIRTY. Caller needs to make sure that the pending transaction is completed, before proceeding to actually use this element. Signed-off-by: Philipp Reisner Signed-off-by: Lars Ellenberg Fixed up by Jens to export lc_get_cumulative(). Signed-off-by: Jens Axboe --- include/linux/lru_cache.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/lru_cache.h b/include/linux/lru_cache.h index 4019013c6593..46262284de47 100644 --- a/include/linux/lru_cache.h +++ b/include/linux/lru_cache.h @@ -256,6 +256,7 @@ extern void lc_destroy(struct lru_cache *lc); extern void lc_set(struct lru_cache *lc, unsigned int enr, int index); extern void lc_del(struct lru_cache *lc, struct lc_element *element); +extern struct lc_element *lc_get_cumulative(struct lru_cache *lc, unsigned int enr); extern struct lc_element *lc_try_get(struct lru_cache *lc, unsigned int enr); extern struct lc_element *lc_find(struct lru_cache *lc, unsigned int enr); extern struct lc_element *lc_get(struct lru_cache *lc, unsigned int enr); -- cgit v1.2.3 From 5bbcf5e6abe97485748b51ea0713cc3012b4a8f0 Mon Sep 17 00:00:00 2001 From: Lars Ellenberg Date: Tue, 19 Mar 2013 18:16:59 +0100 Subject: drbd: adjust upper limit for activity log extents Now that the on-disk activity-log ring buffer size is adjustable, the maximum active set can become larger, and is now limited by the use of 16bit "labels". This increases the maximum working set from 6433 to 65534 extents, each of which covers an area of 4MiB. Which means that if you use the maximum, you'd have to resync more than 250 GiB after an unclean Primary shutdown. With capable backend storage and replication links, this is entirely feasible. Signed-off-by: Philipp Reisner Signed-off-by: Lars Ellenberg Signed-off-by: Jens Axboe --- include/linux/drbd_limits.h | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/drbd_limits.h b/include/linux/drbd_limits.h index 1fa19c5f5e64..1fedf2b17cc8 100644 --- a/include/linux/drbd_limits.h +++ b/include/linux/drbd_limits.h @@ -126,13 +126,12 @@ #define DRBD_RESYNC_RATE_DEF 250 #define DRBD_RESYNC_RATE_SCALE 'k' /* kilobytes */ - /* less than 7 would hit performance unnecessarily. - * 919 slots context information per transaction, - * 32k activity log, 4k transaction size, - * one transaction in flight: - * 919 * 7 = 6433 */ + /* less than 7 would hit performance unnecessarily. */ #define DRBD_AL_EXTENTS_MIN 7 -#define DRBD_AL_EXTENTS_MAX 6433 + /* we use u16 as "slot number", (u16)~0 is "FREE". + * If you use >= 292 kB on-disk ring buffer, + * this is the maximum you can use: */ +#define DRBD_AL_EXTENTS_MAX 0xfffe #define DRBD_AL_EXTENTS_DEF 1237 #define DRBD_AL_EXTENTS_SCALE '1' -- cgit v1.2.3 From 66311274691ec65972cad3626057fa8d00c146d8 Mon Sep 17 00:00:00 2001 From: Lin Ming Date: Sat, 23 Mar 2013 11:42:24 +0800 Subject: block: add a flag to identify PM request Add a flag REQ_PM to identify the request is PM related, such requests will not change the device request queue's runtime status. It is intended to be used in driver's runtime PM callback, so that driver can perform some IO to the device there with the queue's runtime status unaffected. e.g. in SCSI disk's runtime suspend callback, the disk will be put into stopped power state, and this require sending a command to the device. Such command processing should not change the disk's runtime status. Signed-off-by: Lin Ming Signed-off-by: Aaron Lu Acked-by: Alan Stern Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index cdf11191e645..fcc1ce28d5ca 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -175,6 +175,7 @@ enum rq_flag_bits { __REQ_IO_STAT, /* account I/O stat */ __REQ_MIXED_MERGE, /* merge of different types, fail separately */ __REQ_KERNEL, /* direct IO to kernel pages */ + __REQ_PM, /* runtime pm request */ __REQ_NR_BITS, /* stops here */ }; @@ -223,5 +224,6 @@ enum rq_flag_bits { #define REQ_MIXED_MERGE (1 << __REQ_MIXED_MERGE) #define REQ_SECURE (1 << __REQ_SECURE) #define REQ_KERNEL (1 << __REQ_KERNEL) +#define REQ_PM (1 << __REQ_PM) #endif /* __LINUX_BLK_TYPES_H */ -- cgit v1.2.3 From 6c9546675864f51506af69eca388e5d922942c56 Mon Sep 17 00:00:00 2001 From: Lin Ming Date: Sat, 23 Mar 2013 11:42:26 +0800 Subject: block: add runtime pm helpers Add runtime pm helper functions: void blk_pm_runtime_init(struct request_queue *q, struct device *dev) - Initialization function for drivers to call. int blk_pre_runtime_suspend(struct request_queue *q) - If any requests are in the queue, mark last busy and return -EBUSY. Otherwise set q->rpm_status to RPM_SUSPENDING and return 0. void blk_post_runtime_suspend(struct request_queue *q, int err) - If the suspend succeeded then set q->rpm_status to RPM_SUSPENDED. Otherwise set it to RPM_ACTIVE and mark last busy. void blk_pre_runtime_resume(struct request_queue *q) - Set q->rpm_status to RPM_RESUMING. void blk_post_runtime_resume(struct request_queue *q, int err) - If the resume succeeded then set q->rpm_status to RPM_ACTIVE and call __blk_run_queue, then mark last busy and autosuspend. Otherwise set q->rpm_status to RPM_SUSPENDED. The idea and API is designed by Alan Stern and described here: http://marc.info/?l=linux-scsi&m=133727953625963&w=2 Signed-off-by: Lin Ming Signed-off-by: Aaron Lu Acked-by: Alan Stern Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 78feda9bbae2..89d89c7162aa 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -361,6 +361,12 @@ struct request_queue { */ struct kobject kobj; +#ifdef CONFIG_PM_RUNTIME + struct device *dev; + int rpm_status; + unsigned int nr_pending; +#endif + /* * queue settings */ @@ -960,6 +966,27 @@ struct request_queue *blk_alloc_queue(gfp_t); struct request_queue *blk_alloc_queue_node(gfp_t, int); extern void blk_put_queue(struct request_queue *); +/* + * block layer runtime pm functions + */ +#ifdef CONFIG_PM_RUNTIME +extern void blk_pm_runtime_init(struct request_queue *q, struct device *dev); +extern int blk_pre_runtime_suspend(struct request_queue *q); +extern void blk_post_runtime_suspend(struct request_queue *q, int err); +extern void blk_pre_runtime_resume(struct request_queue *q); +extern void blk_post_runtime_resume(struct request_queue *q, int err); +#else +static inline void blk_pm_runtime_init(struct request_queue *q, + struct device *dev) {} +static inline int blk_pre_runtime_suspend(struct request_queue *q) +{ + return -ENOSYS; +} +static inline void blk_post_runtime_suspend(struct request_queue *q, int err) {} +static inline void blk_pre_runtime_resume(struct request_queue *q) {} +static inline void blk_post_runtime_resume(struct request_queue *q, int err) {} +#endif + /* * blk_plug permits building a queue of related requests by holding the I/O * fragments for a short period. This allows merging of sequential requests -- cgit v1.2.3 From 57fb233f078beb5d0437a4ae575fbd4d9eb9c738 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Fri, 24 Aug 2012 04:56:11 -0700 Subject: block: Reorder struct bio_set This is prep work for the next patch, which embeds a struct bio_list in struct bio_set. Signed-off-by: Kent Overstreet CC: Jens Axboe --- include/linux/bio.h | 66 ++++++++++++++++++++++++++--------------------------- 1 file changed, 33 insertions(+), 33 deletions(-) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index 820e7aaad4fd..93d3d17a300d 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -298,39 +298,6 @@ static inline int bio_associate_current(struct bio *bio) { return -ENOENT; } static inline void bio_disassociate_task(struct bio *bio) { } #endif /* CONFIG_BLK_CGROUP */ -/* - * bio_set is used to allow other portions of the IO system to - * allocate their own private memory pools for bio and iovec structures. - * These memory pools in turn all allocate from the bio_slab - * and the bvec_slabs[]. - */ -#define BIO_POOL_SIZE 2 -#define BIOVEC_NR_POOLS 6 -#define BIOVEC_MAX_IDX (BIOVEC_NR_POOLS - 1) - -struct bio_set { - struct kmem_cache *bio_slab; - unsigned int front_pad; - - mempool_t *bio_pool; -#if defined(CONFIG_BLK_DEV_INTEGRITY) - mempool_t *bio_integrity_pool; -#endif - mempool_t *bvec_pool; -}; - -struct biovec_slab { - int nr_vecs; - char *name; - struct kmem_cache *slab; -}; - -/* - * a small number of entries is fine, not going to be performance critical. - * basically we just need to survive - */ -#define BIO_SPLIT_ENTRIES 2 - #ifdef CONFIG_HIGHMEM /* * remember never ever reenable interrupts between a bvec_kmap_irq and @@ -527,6 +494,39 @@ static inline struct bio *bio_list_get(struct bio_list *bl) return bio; } +/* + * bio_set is used to allow other portions of the IO system to + * allocate their own private memory pools for bio and iovec structures. + * These memory pools in turn all allocate from the bio_slab + * and the bvec_slabs[]. + */ +#define BIO_POOL_SIZE 2 +#define BIOVEC_NR_POOLS 6 +#define BIOVEC_MAX_IDX (BIOVEC_NR_POOLS - 1) + +struct bio_set { + struct kmem_cache *bio_slab; + unsigned int front_pad; + + mempool_t *bio_pool; +#if defined(CONFIG_BLK_DEV_INTEGRITY) + mempool_t *bio_integrity_pool; +#endif + mempool_t *bvec_pool; +}; + +struct biovec_slab { + int nr_vecs; + char *name; + struct kmem_cache *slab; +}; + +/* + * a small number of entries is fine, not going to be performance critical. + * basically we just need to survive + */ +#define BIO_SPLIT_ENTRIES 2 + #if defined(CONFIG_BLK_DEV_INTEGRITY) #define bip_vec_idx(bip, idx) (&(bip->bip_vec[(idx)])) -- cgit v1.2.3 From df2cb6daa4cbc34406bc4b1ac9b9335df1083a72 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Mon, 10 Sep 2012 14:33:46 -0700 Subject: block: Avoid deadlocks with bio allocation by stacking drivers Previously, if we ever try to allocate more than once from the same bio set while running under generic_make_request() (i.e. a stacking block driver), we risk deadlock. This is because of the code in generic_make_request() that converts recursion to iteration; any bios we submit won't actually be submitted (so they can complete and eventually be freed) until after we return - this means if we allocate a second bio, we're blocking the first one from ever being freed. Thus if enough threads call into a stacking block driver at the same time with bios that need multiple splits, and the bio_set's reserve gets used up, we deadlock. This can be worked around in the driver code - we could check if we're running under generic_make_request(), then mask out __GFP_WAIT when we go to allocate a bio, and if the allocation fails punt to workqueue and retry the allocation. But this is tricky and not a generic solution. This patch solves it for all users by inverting the previously described technique. We allocate a rescuer workqueue for each bio_set, and then in the allocation code if there are bios on current->bio_list we would be blocking, we punt them to the rescuer workqueue to be submitted. This guarantees forward progress for bio allocations under generic_make_request() provided each bio is submitted before allocating the next, and provided the bios are freed after they complete. Note that this doesn't do anything for allocation from other mempools. Instead of allocating per bio data structures from a mempool, code should use bio_set's front_pad. Tested it by forcing the rescue codepath to be taken (by disabling the first GFP_NOWAIT) attempt, and then ran it with bcache (which does a lot of arbitrary bio splitting) and verified that the rescuer was being invoked. Signed-off-by: Kent Overstreet CC: Jens Axboe Acked-by: Tejun Heo Reviewed-by: Muthukumar Ratty --- include/linux/bio.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index 93d3d17a300d..b31036ff779f 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -513,6 +513,15 @@ struct bio_set { mempool_t *bio_integrity_pool; #endif mempool_t *bvec_pool; + + /* + * Deadlock avoidance for stacking block drivers: see comments in + * bio_alloc_bioset() for details + */ + spinlock_t rescue_lock; + struct bio_list rescue_list; + struct work_struct rescue_work; + struct workqueue_struct *rescue_workqueue; }; struct biovec_slab { -- cgit v1.2.3 From 6fda981cafbf908acd11e1e636fec50e99d56a47 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Fri, 12 Oct 2012 13:18:27 -0700 Subject: block: Fix a buffer overrun in bio_integrity_split() bio_integrity_split() seemed to be confusing pointers and arrays - bip_vec in bio_integrity_payload was an array appended to the end of the payload, so the bio_vecs in struct bio_pair should have come after the bio_integrity_payload they're for. Fix it by making bip_vec a pointer to the inline vecs - a later patch is going to make more use of this pointer. Signed-off-by: Kent Overstreet CC: Jens Axboe CC: Martin K. Petersen --- include/linux/bio.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index b31036ff779f..81004fdcc277 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -182,7 +182,9 @@ struct bio_integrity_payload { unsigned short bip_idx; /* current bip_vec index */ struct work_struct bip_work; /* I/O completion */ - struct bio_vec bip_vec[0]; /* embedded bvec array */ + + struct bio_vec *bip_vec; + struct bio_vec bip_inline_vecs[0];/* embedded bvec array */ }; #endif /* CONFIG_BLK_DEV_INTEGRITY */ -- cgit v1.2.3 From 9f060e2231ca96ca94f2ffcff730acd72606b280 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Fri, 12 Oct 2012 15:29:33 -0700 Subject: block: Convert integrity to bvec_alloc_bs() This adds a pointer to the bvec array to struct bio_integrity_payload, instead of the bvecs always being inline; then the bvecs are allocated with bvec_alloc_bs(). Changed bvec_alloc_bs() and bvec_free_bs() to take a pointer to a mempool instead of the bioset, so that bio integrity can use a different mempool for its bvecs, and thus avoid a potential deadlock. This is eventually for immutable bio vecs - immutable bvecs aren't useful if we still have to copy them, hence the need for the pointer. Less code is always nice too, though. Also, bio_integrity_alloc() was using fs_bio_set if no bio_set was specified. This was wrong - using the bio_set doesn't protect us from memory allocation failures, because we just used kmalloc for the bio_integrity_payload. But it does introduce the possibility of deadlock, if for some reason we weren't supposed to be using fs_bio_set. Signed-off-by: Kent Overstreet CC: Jens Axboe CC: Martin K. Petersen --- include/linux/bio.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index 81004fdcc277..669b1cb18fee 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -213,6 +213,7 @@ extern void bio_pair_release(struct bio_pair *dbio); extern struct bio_set *bioset_create(unsigned int, unsigned int); extern void bioset_free(struct bio_set *); +extern mempool_t *biovec_create_pool(struct bio_set *bs, int pool_entries); extern struct bio *bio_alloc_bioset(gfp_t, int, struct bio_set *); extern void bio_put(struct bio *); @@ -288,8 +289,8 @@ extern struct bio *bio_copy_user_iov(struct request_queue *, int, int, gfp_t); extern int bio_uncopy_user(struct bio *); void zero_fill_bio(struct bio *bio); -extern struct bio_vec *bvec_alloc_bs(gfp_t, int, unsigned long *, struct bio_set *); -extern void bvec_free_bs(struct bio_set *, struct bio_vec *, unsigned int); +extern struct bio_vec *bvec_alloc(gfp_t, int, unsigned long *, mempool_t *); +extern void bvec_free(mempool_t *, struct bio_vec *, unsigned int); extern unsigned int bvec_nr_vecs(unsigned short idx); #ifdef CONFIG_BLK_CGROUP @@ -511,10 +512,11 @@ struct bio_set { unsigned int front_pad; mempool_t *bio_pool; + mempool_t *bvec_pool; #if defined(CONFIG_BLK_DEV_INTEGRITY) mempool_t *bio_integrity_pool; + mempool_t *bvec_integrity_pool; #endif - mempool_t *bvec_pool; /* * Deadlock avoidance for stacking block drivers: see comments in -- cgit v1.2.3 From 054bdf646e36c2f7dc1bf6bc6209dbbb5909164b Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Fri, 28 Sep 2012 13:17:55 -0700 Subject: block: Add bio_advance() This is prep work for immutable bio vecs; we first want to centralize where bvecs are modified. Next two patches convert some existing code to use this function. Signed-off-by: Kent Overstreet CC: Jens Axboe --- include/linux/bio.h | 2 ++ include/linux/blk_types.h | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index 669b1cb18fee..fcb4dba2d8ea 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -248,6 +248,8 @@ extern void bio_endio(struct bio *, int); struct request_queue; extern int bio_phys_segments(struct request_queue *, struct bio *); +extern void bio_advance(struct bio *, unsigned); + extern void bio_init(struct bio *); extern void bio_reset(struct bio *); diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index cdf11191e645..c178d25e588b 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -197,6 +197,8 @@ enum rq_flag_bits { REQ_SECURE) #define REQ_CLONE_MASK REQ_COMMON_MASK +#define BIO_NO_ADVANCE_ITER_MASK (REQ_DISCARD|REQ_WRITE_SAME) + /* This mask is used for both bio and request merge checking */ #define REQ_NOMERGE_FLAGS \ (REQ_NOMERGE | REQ_STARTED | REQ_SOFTBARRIER | REQ_FLUSH | REQ_FUA) -- cgit v1.2.3 From f73a1c7d117d07a96d89475066188a2b79e53c48 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Tue, 25 Sep 2012 15:05:12 -0700 Subject: block: Add bio_end_sector() Just a little convenience macro - main reason to add it now is preparing for immutable bio vecs, it'll reduce the size of the patch that puts bi_sector/bi_size/bi_idx into a struct bvec_iter. Signed-off-by: Kent Overstreet CC: Jens Axboe CC: Lars Ellenberg CC: Jiri Kosina CC: Alasdair Kergon CC: dm-devel@redhat.com CC: Neil Brown CC: Martin Schwidefsky CC: Heiko Carstens CC: linux-s390@vger.kernel.org CC: Chris Mason CC: Steven Whitehouse Acked-by: Steven Whitehouse --- include/linux/bio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index fcb4dba2d8ea..20507eb7c979 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -67,6 +67,7 @@ #define bio_offset(bio) bio_iovec((bio))->bv_offset #define bio_segments(bio) ((bio)->bi_vcnt - (bio)->bi_idx) #define bio_sectors(bio) ((bio)->bi_size >> 9) +#define bio_end_sector(bio) ((bio)->bi_sector + bio_sectors((bio))) static inline unsigned int bio_cur_bytes(struct bio *bio) { -- cgit v1.2.3 From aa8b57aa3d1c06ca53312294ee6dfc767ee3ddb3 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Tue, 5 Feb 2013 15:19:29 -0800 Subject: block: Use bio_sectors() more consistently Bunch of places in the code weren't using it where they could be - this'll reduce the size of the patch that puts bi_sector/bi_size/bi_idx into a struct bvec_iter. Signed-off-by: Kent Overstreet CC: Jens Axboe CC: "Ed L. Cashin" CC: Nick Piggin CC: Jiri Kosina CC: Jim Paris CC: Geoff Levand CC: Alasdair Kergon CC: dm-devel@redhat.com CC: Neil Brown CC: Steven Rostedt Acked-by: Ed Cashin --- include/trace/events/block.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/trace/events/block.h b/include/trace/events/block.h index 9961726523d0..5a28843725df 100644 --- a/include/trace/events/block.h +++ b/include/trace/events/block.h @@ -244,7 +244,7 @@ TRACE_EVENT(block_bio_bounce, __entry->dev = bio->bi_bdev ? bio->bi_bdev->bd_dev : 0; __entry->sector = bio->bi_sector; - __entry->nr_sector = bio->bi_size >> 9; + __entry->nr_sector = bio_sectors(bio); blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size); memcpy(__entry->comm, current->comm, TASK_COMM_LEN); ), @@ -281,7 +281,7 @@ TRACE_EVENT(block_bio_complete, __entry->dev = bio->bi_bdev ? bio->bi_bdev->bd_dev : 0; __entry->sector = bio->bi_sector; - __entry->nr_sector = bio->bi_size >> 9; + __entry->nr_sector = bio_sectors(bio); __entry->error = error; blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size); ), @@ -309,7 +309,7 @@ DECLARE_EVENT_CLASS(block_bio_merge, TP_fast_assign( __entry->dev = bio->bi_bdev->bd_dev; __entry->sector = bio->bi_sector; - __entry->nr_sector = bio->bi_size >> 9; + __entry->nr_sector = bio_sectors(bio); blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size); memcpy(__entry->comm, current->comm, TASK_COMM_LEN); ), @@ -376,7 +376,7 @@ TRACE_EVENT(block_bio_queue, TP_fast_assign( __entry->dev = bio->bi_bdev->bd_dev; __entry->sector = bio->bi_sector; - __entry->nr_sector = bio->bi_size >> 9; + __entry->nr_sector = bio_sectors(bio); blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size); memcpy(__entry->comm, current->comm, TASK_COMM_LEN); ), @@ -404,7 +404,7 @@ DECLARE_EVENT_CLASS(block_get_rq, TP_fast_assign( __entry->dev = bio ? bio->bi_bdev->bd_dev : 0; __entry->sector = bio ? bio->bi_sector : 0; - __entry->nr_sector = bio ? bio->bi_size >> 9 : 0; + __entry->nr_sector = bio ? bio_sectors(bio) : 0; blk_fill_rwbs(__entry->rwbs, bio ? bio->bi_rw : 0, __entry->nr_sector); memcpy(__entry->comm, current->comm, TASK_COMM_LEN); @@ -580,7 +580,7 @@ TRACE_EVENT(block_bio_remap, TP_fast_assign( __entry->dev = bio->bi_bdev->bd_dev; __entry->sector = bio->bi_sector; - __entry->nr_sector = bio->bi_size >> 9; + __entry->nr_sector = bio_sectors(bio); __entry->old_dev = dev; __entry->old_sector = from; blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size); -- cgit v1.2.3 From 9e882242c6193ae6f416f2d8d8db0d9126bd996b Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Mon, 10 Sep 2012 14:41:12 -0700 Subject: block: Add submit_bio_wait(), remove from md Random cleanup - this code was duplicated and it's not really specific to md. Also added the ability to return the actual error code. Signed-off-by: Kent Overstreet CC: Jens Axboe CC: NeilBrown Acked-by: Tejun Heo --- include/linux/bio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index 20507eb7c979..b20a9cd776dd 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -249,6 +249,7 @@ extern void bio_endio(struct bio *, int); struct request_queue; extern int bio_phys_segments(struct request_queue *, struct bio *); +extern int submit_bio_wait(int rw, struct bio *bio); extern void bio_advance(struct bio *, unsigned); extern void bio_init(struct bio *); -- cgit v1.2.3 From 16ac3d63e74f3d6e34e42d6e523b6a61de0020f0 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Mon, 10 Sep 2012 13:57:51 -0700 Subject: block: Add bio_copy_data() This gets open coded quite a bit and it's tricky to get right, so make a generic version and convert some existing users over to it instead. Signed-off-by: Kent Overstreet CC: Jens Axboe --- include/linux/bio.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index b20a9cd776dd..90d36c65cb70 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -286,6 +286,8 @@ static inline void bio_flush_dcache_pages(struct bio *bi) } #endif +extern void bio_copy_data(struct bio *dst, struct bio *src); + extern struct bio *bio_copy_user(struct request_queue *, struct rq_map_data *, unsigned long, unsigned int, int, gfp_t); extern struct bio *bio_copy_user_iov(struct request_queue *, -- cgit v1.2.3 From d74c6d514fe314b8bdab58b487b25992291577ec Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Wed, 6 Feb 2013 12:23:11 -0800 Subject: block: Add bio_for_each_segment_all() __bio_for_each_segment() iterates bvecs from the specified index instead of bio->bv_idx. Currently, the only usage is to walk all the bvecs after the bio has been advanced by specifying 0 index. For immutable bvecs, we need to split these apart; bio_for_each_segment() is going to have a different implementation. This will also help document the intent of code that's using it - bio_for_each_segment_all() is only legal to use for code that owns the bio. Signed-off-by: Kent Overstreet CC: Jens Axboe CC: Neil Brown CC: Boaz Harrosh --- include/linux/bio.h | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index 90d36c65cb70..be2efa09f9bf 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -137,16 +137,27 @@ static inline int bio_has_allocated_vec(struct bio *bio) #define bio_io_error(bio) bio_endio((bio), -EIO) /* - * drivers should not use the __ version unless they _really_ want to - * run through the entire bio and not just pending pieces + * drivers should not use the __ version unless they _really_ know what + * they're doing */ #define __bio_for_each_segment(bvl, bio, i, start_idx) \ for (bvl = bio_iovec_idx((bio), (start_idx)), i = (start_idx); \ i < (bio)->bi_vcnt; \ bvl++, i++) +/* + * drivers should _never_ use the all version - the bio may have been split + * before it got to the driver and the driver won't own all of it + */ +#define bio_for_each_segment_all(bvl, bio, i) \ + for (i = 0; \ + bvl = bio_iovec_idx((bio), (i)), i < (bio)->bi_vcnt; \ + i++) + #define bio_for_each_segment(bvl, bio, i) \ - __bio_for_each_segment(bvl, bio, i, (bio)->bi_idx) + for (i = (bio)->bi_idx; \ + bvl = bio_iovec_idx((bio), (i)), i < (bio)->bi_vcnt; \ + i++) /* * get a reference to a bio, so it won't disappear. the intended use is -- cgit v1.2.3 From a07876064a0b73ab5ef1ebcf14b1cf0231c07858 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Mon, 10 Sep 2012 14:03:28 -0700 Subject: block: Add bio_alloc_pages() More utility code to replace stuff that's getting open coded. Signed-off-by: Kent Overstreet CC: Jens Axboe CC: NeilBrown --- include/linux/bio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index be2efa09f9bf..e25378f2f408 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -298,6 +298,7 @@ static inline void bio_flush_dcache_pages(struct bio *bi) #endif extern void bio_copy_data(struct bio *dst, struct bio *src); +extern int bio_alloc_pages(struct bio *bio, gfp_t gfp); extern struct bio *bio_copy_user(struct request_queue *, struct rq_map_data *, unsigned long, unsigned int, int, gfp_t); -- cgit v1.2.3 From a38352e0ac02dbbd4fa464dc22d1352b5fbd06fd Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Fri, 25 May 2012 13:03:11 -0700 Subject: block: Add an explicit bio flag for bios that own their bvec This is for the new bio splitting code. When we split a bio, if the split occured on a bvec boundry we reuse the bvec for the new bio. But that means bio_free() can't free it, hence the explicit flag. Signed-off-by: Kent Overstreet CC: Jens Axboe Acked-by: Tejun Heo --- include/linux/bio.h | 5 ----- include/linux/blk_types.h | 1 + 2 files changed, 1 insertion(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index e25378f2f408..794bcd0c5039 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -85,11 +85,6 @@ static inline void *bio_data(struct bio *bio) return NULL; } -static inline int bio_has_allocated_vec(struct bio *bio) -{ - return bio->bi_io_vec && bio->bi_io_vec != bio->bi_inline_vecs; -} - /* * will die */ diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index c178d25e588b..538289ffc704 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -117,6 +117,7 @@ struct bio { * BIO_POOL_IDX() */ #define BIO_RESET_BITS 12 +#define BIO_OWNS_VEC 12 /* bio_free() should free bvec */ #define bio_flagged(bio, flag) ((bio)->bi_flags & (1 << (flag))) -- cgit v1.2.3 From 29ed7813ce5c4661261aeebddb1b8660e0860223 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Tue, 4 Sep 2012 09:54:22 -0700 Subject: bio-integrity: Add explicit field for owner of bip_buf This was the only real user of BIO_CLONED, which didn't have very clear semantics. Convert to its own flag so we can get rid of BIO_CLONED. Signed-off-by: Kent Overstreet CC: Jens Axboe CC: Martin K. Petersen --- include/linux/bio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index 794bcd0c5039..ef24466d8f82 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -187,6 +187,7 @@ struct bio_integrity_payload { unsigned short bip_slab; /* slab the bip came from */ unsigned short bip_vcnt; /* # of integrity bio_vecs */ unsigned short bip_idx; /* current bip_vec index */ + unsigned bip_owns_buf:1; /* should free bip_buf */ struct work_struct bip_work; /* I/O completion */ -- cgit v1.2.3 From 84759c6d18c5144432781ddca037d929ee9db8a5 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Wed, 21 Sep 2011 21:43:05 -0700 Subject: Revert "rw_semaphore: remove up/down_read_non_owner" This reverts commit 11b80f459adaf91a712f95e7734a17655a36bf30. Bcache needs rw semaphores for cache coherency in writeback mode - writes have to take a read lock on a per cache device rw sem, and release it when the bio completes. But since this is for bios it's naturally not in the context of the process that originally took the lock. Signed-off-by: Kent Overstreet CC: Christoph Hellwig CC: David Howells --- include/linux/rwsem.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index 8da67d625e13..0616ffe45702 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -133,10 +133,20 @@ do { \ _down_write_nest_lock(sem, &(nest_lock)->dep_map); \ } while (0); +/* + * Take/release a lock when not the owner will release it. + * + * [ This API should be avoided as much as possible - the + * proper abstraction for this case is completions. ] + */ +extern void down_read_non_owner(struct rw_semaphore *sem); +extern void up_read_non_owner(struct rw_semaphore *sem); #else # define down_read_nested(sem, subclass) down_read(sem) # define down_write_nest_lock(sem, nest_lock) down_write(sem) # define down_write_nested(sem, subclass) down_write(sem) +# define down_read_non_owner(sem) down_read(sem) +# define up_read_non_owner(sem) up_read(sem) #endif #endif /* _LINUX_RWSEM_H */ -- cgit v1.2.3 From cafe563591446cf80bfbc2fe3bc72a2e36cf1060 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Sat, 23 Mar 2013 16:11:31 -0700 Subject: bcache: A block layer cache Does writethrough and writeback caching, handles unclean shutdown, and has a bunch of other nifty features motivated by real world usage. See the wiki at http://bcache.evilpiepirate.org for more. Signed-off-by: Kent Overstreet --- include/linux/cgroup_subsys.h | 6 + include/linux/sched.h | 4 + include/trace/events/bcache.h | 271 ++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 281 insertions(+) create mode 100644 include/trace/events/bcache.h (limited to 'include') diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h index f204a7a9cf38..6e7ec64b69ab 100644 --- a/include/linux/cgroup_subsys.h +++ b/include/linux/cgroup_subsys.h @@ -78,3 +78,9 @@ SUBSYS(hugetlb) #endif /* */ + +#ifdef CONFIG_CGROUP_BCACHE +SUBSYS(bcache) +#endif + +/* */ diff --git a/include/linux/sched.h b/include/linux/sched.h index d35d2b6ddbfb..a8482d063bc3 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1576,6 +1576,10 @@ struct task_struct { #ifdef CONFIG_UPROBES struct uprobe_task *utask; #endif +#if defined(CONFIG_BCACHE) || defined(CONFIG_BCACHE_MODULE) + unsigned int sequential_io; + unsigned int sequential_io_avg; +#endif }; /* Future-safe accessor for struct task_struct's cpus_allowed. */ diff --git a/include/trace/events/bcache.h b/include/trace/events/bcache.h new file mode 100644 index 000000000000..3cc5a0b278c3 --- /dev/null +++ b/include/trace/events/bcache.h @@ -0,0 +1,271 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM bcache + +#if !defined(_TRACE_BCACHE_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_BCACHE_H + +#include + +struct search; + +DECLARE_EVENT_CLASS(bcache_request, + + TP_PROTO(struct search *s, struct bio *bio), + + TP_ARGS(s, bio), + + TP_STRUCT__entry( + __field(dev_t, dev ) + __field(unsigned int, orig_major ) + __field(unsigned int, orig_minor ) + __field(sector_t, sector ) + __field(dev_t, orig_sector ) + __field(unsigned int, nr_sector ) + __array(char, rwbs, 6 ) + __array(char, comm, TASK_COMM_LEN ) + ), + + TP_fast_assign( + __entry->dev = bio->bi_bdev->bd_dev; + __entry->orig_major = s->d->disk->major; + __entry->orig_minor = s->d->disk->first_minor; + __entry->sector = bio->bi_sector; + __entry->orig_sector = bio->bi_sector - 16; + __entry->nr_sector = bio->bi_size >> 9; + blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size); + memcpy(__entry->comm, current->comm, TASK_COMM_LEN); + ), + + TP_printk("%d,%d %s %llu + %u [%s] (from %d,%d @ %llu)", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->rwbs, + (unsigned long long)__entry->sector, + __entry->nr_sector, __entry->comm, + __entry->orig_major, __entry->orig_minor, + (unsigned long long)__entry->orig_sector) +); + +DEFINE_EVENT(bcache_request, bcache_request_start, + + TP_PROTO(struct search *s, struct bio *bio), + + TP_ARGS(s, bio) +); + +DEFINE_EVENT(bcache_request, bcache_request_end, + + TP_PROTO(struct search *s, struct bio *bio), + + TP_ARGS(s, bio) +); + +DECLARE_EVENT_CLASS(bcache_bio, + + TP_PROTO(struct bio *bio), + + TP_ARGS(bio), + + TP_STRUCT__entry( + __field(dev_t, dev ) + __field(sector_t, sector ) + __field(unsigned int, nr_sector ) + __array(char, rwbs, 6 ) + __array(char, comm, TASK_COMM_LEN ) + ), + + TP_fast_assign( + __entry->dev = bio->bi_bdev->bd_dev; + __entry->sector = bio->bi_sector; + __entry->nr_sector = bio->bi_size >> 9; + blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size); + memcpy(__entry->comm, current->comm, TASK_COMM_LEN); + ), + + TP_printk("%d,%d %s %llu + %u [%s]", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->rwbs, + (unsigned long long)__entry->sector, + __entry->nr_sector, __entry->comm) +); + + +DEFINE_EVENT(bcache_bio, bcache_passthrough, + + TP_PROTO(struct bio *bio), + + TP_ARGS(bio) +); + +DEFINE_EVENT(bcache_bio, bcache_cache_hit, + + TP_PROTO(struct bio *bio), + + TP_ARGS(bio) +); + +DEFINE_EVENT(bcache_bio, bcache_cache_miss, + + TP_PROTO(struct bio *bio), + + TP_ARGS(bio) +); + +DEFINE_EVENT(bcache_bio, bcache_read_retry, + + TP_PROTO(struct bio *bio), + + TP_ARGS(bio) +); + +DEFINE_EVENT(bcache_bio, bcache_writethrough, + + TP_PROTO(struct bio *bio), + + TP_ARGS(bio) +); + +DEFINE_EVENT(bcache_bio, bcache_writeback, + + TP_PROTO(struct bio *bio), + + TP_ARGS(bio) +); + +DEFINE_EVENT(bcache_bio, bcache_write_skip, + + TP_PROTO(struct bio *bio), + + TP_ARGS(bio) +); + +DEFINE_EVENT(bcache_bio, bcache_btree_read, + + TP_PROTO(struct bio *bio), + + TP_ARGS(bio) +); + +DEFINE_EVENT(bcache_bio, bcache_btree_write, + + TP_PROTO(struct bio *bio), + + TP_ARGS(bio) +); + +DEFINE_EVENT(bcache_bio, bcache_write_dirty, + + TP_PROTO(struct bio *bio), + + TP_ARGS(bio) +); + +DEFINE_EVENT(bcache_bio, bcache_read_dirty, + + TP_PROTO(struct bio *bio), + + TP_ARGS(bio) +); + +DEFINE_EVENT(bcache_bio, bcache_write_moving, + + TP_PROTO(struct bio *bio), + + TP_ARGS(bio) +); + +DEFINE_EVENT(bcache_bio, bcache_read_moving, + + TP_PROTO(struct bio *bio), + + TP_ARGS(bio) +); + +DEFINE_EVENT(bcache_bio, bcache_journal_write, + + TP_PROTO(struct bio *bio), + + TP_ARGS(bio) +); + +DECLARE_EVENT_CLASS(bcache_cache_bio, + + TP_PROTO(struct bio *bio, + sector_t orig_sector, + struct block_device* orig_bdev), + + TP_ARGS(bio, orig_sector, orig_bdev), + + TP_STRUCT__entry( + __field(dev_t, dev ) + __field(dev_t, orig_dev ) + __field(sector_t, sector ) + __field(sector_t, orig_sector ) + __field(unsigned int, nr_sector ) + __array(char, rwbs, 6 ) + __array(char, comm, TASK_COMM_LEN ) + ), + + TP_fast_assign( + __entry->dev = bio->bi_bdev->bd_dev; + __entry->orig_dev = orig_bdev->bd_dev; + __entry->sector = bio->bi_sector; + __entry->orig_sector = orig_sector; + __entry->nr_sector = bio->bi_size >> 9; + blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size); + memcpy(__entry->comm, current->comm, TASK_COMM_LEN); + ), + + TP_printk("%d,%d %s %llu + %u [%s] (from %d,%d %llu)", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->rwbs, + (unsigned long long)__entry->sector, + __entry->nr_sector, __entry->comm, + MAJOR(__entry->orig_dev), MINOR(__entry->orig_dev), + (unsigned long long)__entry->orig_sector) +); + +DEFINE_EVENT(bcache_cache_bio, bcache_cache_insert, + + TP_PROTO(struct bio *bio, + sector_t orig_sector, + struct block_device *orig_bdev), + + TP_ARGS(bio, orig_sector, orig_bdev) +); + +DECLARE_EVENT_CLASS(bcache_gc, + + TP_PROTO(uint8_t *uuid), + + TP_ARGS(uuid), + + TP_STRUCT__entry( + __field(uint8_t *, uuid) + ), + + TP_fast_assign( + __entry->uuid = uuid; + ), + + TP_printk("%pU", __entry->uuid) +); + + +DEFINE_EVENT(bcache_gc, bcache_gc_start, + + TP_PROTO(uint8_t *uuid), + + TP_ARGS(uuid) +); + +DEFINE_EVENT(bcache_gc, bcache_gc_end, + + TP_PROTO(uint8_t *uuid), + + TP_ARGS(uuid) +); + +#endif /* _TRACE_BCACHE_H */ + +/* This part must be outside protection */ +#include -- cgit v1.2.3 From 57df8106932b57427df1eaaa13871857f75b1194 Mon Sep 17 00:00:00 2001 From: Zhang Rui Date: Fri, 8 Feb 2013 14:52:06 +0800 Subject: Thermal: exynos: fix cooling state translation Signed-off-by: Zhang Rui Tested-by: Amit Daniel kachhap --- include/linux/cpu_cooling.h | 7 +++++++ include/linux/thermal.h | 5 ++++- 2 files changed, 11 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/cpu_cooling.h b/include/linux/cpu_cooling.h index 40b4ef54cc7d..bc479b1e0fd9 100644 --- a/include/linux/cpu_cooling.h +++ b/include/linux/cpu_cooling.h @@ -42,6 +42,8 @@ struct thermal_cooling_device *cpufreq_cooling_register( * @cdev: thermal cooling device pointer. */ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev); + +unsigned long cpufreq_cooling_get_level(unsigned int, unsigned int); #else /* !CONFIG_CPU_THERMAL */ static inline struct thermal_cooling_device *cpufreq_cooling_register( const struct cpumask *clip_cpus) @@ -53,6 +55,11 @@ static inline void cpufreq_cooling_unregister( { return; } +static inline unsigned long cpufreq_cooling_get_level(unsigned int, + unsigned int) +{ + return THERMAL_CSTATE_INVALID; +} #endif /* CONFIG_CPU_THERMAL */ #endif /* __CPU_COOLING_H__ */ diff --git a/include/linux/thermal.h b/include/linux/thermal.h index f0bd7f90a90d..5a3b428daaab 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -33,8 +33,11 @@ #define THERMAL_MAX_TRIPS 12 #define THERMAL_NAME_LENGTH 20 +/* invalid cooling state */ +#define THERMAL_CSTATE_INVALID -1UL + /* No upper/lower limit requirement */ -#define THERMAL_NO_LIMIT -1UL +#define THERMAL_NO_LIMIT THERMAL_CSTATE_INVALID /* Unit conversion macros */ #define KELVIN_TO_CELSIUS(t) (long)(((long)t-2732 >= 0) ? \ -- cgit v1.2.3 From f8b587055a793c7719f0d4f41b7b4aeeef43aa2d Mon Sep 17 00:00:00 2001 From: Ezequiel Garcia Date: Wed, 20 Mar 2013 21:38:07 +0000 Subject: thermal: Fix compiler warning The following warning is obtained when CONFIG_NET is not defined: In file included from drivers/thermal/mvebu_thermal.c:27:0: include/linux/thermal.h:254:12: warning: 'thermal_generate_netlink_event' defined but not used [-Wunused-function] This patch fixes the warning by properly inlining thermal_generate_netlink_event(). Signed-off-by: Ezequiel Garcia Signed-off-by: Zhang Rui --- include/linux/thermal.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index f0bd7f90a90d..fd7b8f3e6f42 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -251,7 +251,7 @@ void thermal_unregister_governor(struct thermal_governor *); extern int thermal_generate_netlink_event(struct thermal_zone_device *tz, enum events event); #else -static int thermal_generate_netlink_event(struct thermal_zone_device *tz, +static inline int thermal_generate_netlink_event(struct thermal_zone_device *tz, enum events event) { return 0; -- cgit v1.2.3 From 0e5e4f0e56aca0df1d5648db0be9028bd573b25c Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Fri, 9 Nov 2012 16:33:05 -0700 Subject: NVMe: Add discard support for capable devices This adds discard support to block queues if the nvme device is capable of deallocating blocks as indicated by the controller's optional command support. A discard flagged bio request will submit an NVMe deallocate Data Set Management command for the requested blocks. Signed-off-by: Keith Busch Signed-off-by: Matthew Wilcox --- include/linux/nvme.h | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) (limited to 'include') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 4fa3b0b9b071..bde44c1fd213 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -107,6 +107,12 @@ struct nvme_id_ctrl { __u8 vs[1024]; }; +enum { + NVME_CTRL_ONCS_COMPARE = 1 << 0, + NVME_CTRL_ONCS_WRITE_UNCORRECTABLE = 1 << 1, + NVME_CTRL_ONCS_DSM = 1 << 2, +}; + struct nvme_lbaf { __le16 ms; __u8 ds; @@ -246,6 +252,31 @@ enum { NVME_RW_DSM_COMPRESSED = 1 << 7, }; +struct nvme_dsm_cmd { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 nsid; + __u64 rsvd2[2]; + __le64 prp1; + __le64 prp2; + __le32 nr; + __le32 attributes; + __u32 rsvd12[4]; +}; + +enum { + NVME_DSMGMT_IDR = 1 << 0, + NVME_DSMGMT_IDW = 1 << 1, + NVME_DSMGMT_AD = 1 << 2, +}; + +struct nvme_dsm_range { + __le32 cattr; + __le32 nlb; + __le64 slba; +}; + /* Admin commands */ enum nvme_admin_opcode { @@ -372,6 +403,7 @@ struct nvme_command { struct nvme_create_sq create_sq; struct nvme_delete_queue delete_queue; struct nvme_download_firmware dlfw; + struct nvme_dsm_cmd dsm; }; }; -- cgit v1.2.3 From 13c3b0fcc8e33ba49f252378f6e7290b146042af Mon Sep 17 00:00:00 2001 From: Vishal Verma Date: Mon, 4 Mar 2013 18:40:57 -0700 Subject: NVMe: Move structures & definitions to header file nvme-scsi.c uses several data structures and definitions that were previously private to nvme-core.c. Move the definitions to nvme.h, protected by __KERNEL__. Signed-off-by: Vishal Verma Signed-off-by: Matthew Wilcox --- include/linux/nvme.h | 60 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 60 insertions(+) (limited to 'include') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index bde44c1fd213..6f899add14ab 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -493,4 +493,64 @@ struct nvme_admin_cmd { #define NVME_IOCTL_ADMIN_CMD _IOWR('N', 0x41, struct nvme_admin_cmd) #define NVME_IOCTL_SUBMIT_IO _IOW('N', 0x42, struct nvme_user_io) +#ifdef __KERNEL__ +#include + +#define NVME_IO_TIMEOUT (5 * HZ) + +/* + * Represents an NVM Express device. Each nvme_dev is a PCI function. + */ +struct nvme_dev { + struct list_head node; + struct nvme_queue **queues; + u32 __iomem *dbs; + struct pci_dev *pci_dev; + struct dma_pool *prp_page_pool; + struct dma_pool *prp_small_pool; + int instance; + int queue_count; + int db_stride; + u32 ctrl_config; + struct msix_entry *entry; + struct nvme_bar __iomem *bar; + struct list_head namespaces; + char serial[20]; + char model[40]; + char firmware_rev[8]; + u32 max_hw_sectors; + u16 oncs; +}; + +/* + * An NVM Express namespace is equivalent to a SCSI LUN + */ +struct nvme_ns { + struct list_head list; + + struct nvme_dev *dev; + struct request_queue *queue; + struct gendisk *disk; + + int ns_id; + int lba_shift; +}; + +/* + * The nvme_iod describes the data in an I/O, including the list of PRP + * entries. You can't see it in this data structure because C doesn't let + * me express that. Use nvme_alloc_iod to ensure there's enough space + * allocated to store the PRP list. + */ +struct nvme_iod { + void *private; /* For the use of the submitter of the I/O */ + int npages; /* In the PRP list. 0 means small pool in use */ + int offset; /* Of PRP list */ + int nents; /* Used in scatterlist */ + int length; /* Of data, in bytes */ + dma_addr_t first_dma; + struct scatterlist sg[0]; +}; +#endif + #endif /* _LINUX_NVME_H */ -- cgit v1.2.3 From f8ebf8409abfdaeeb8c847381629a2a8b8e3d816 Mon Sep 17 00:00:00 2001 From: Vishal Verma Date: Wed, 27 Mar 2013 07:13:41 -0400 Subject: NVMe: Add definitions for format command The SCSI emulation has the ability to send format commands, so we need to add the definition of the command. Also add a missing error code. Signed-off-by: Vishal Verma Signed-off-by: Matthew Wilcox --- include/linux/nvme.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 6f899add14ab..f1974cab60cf 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -393,6 +393,16 @@ struct nvme_download_firmware { __u32 rsvd12[4]; }; +struct nvme_format_cmd { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 nsid; + __u64 rsvd2[4]; + __le32 cdw10; + __u32 rsvd11[5]; +}; + struct nvme_command { union { struct nvme_common_command common; @@ -403,6 +413,7 @@ struct nvme_command { struct nvme_create_sq create_sq; struct nvme_delete_queue delete_queue; struct nvme_download_firmware dlfw; + struct nvme_format_cmd format; struct nvme_dsm_cmd dsm; }; }; @@ -420,6 +431,7 @@ enum { NVME_SC_FUSED_FAIL = 0x9, NVME_SC_FUSED_MISSING = 0xa, NVME_SC_INVALID_NS = 0xb, + NVME_SC_CMD_SEQ_ERROR = 0xc, NVME_SC_LBA_RANGE = 0x80, NVME_SC_CAP_EXCEEDED = 0x81, NVME_SC_NS_NOT_READY = 0x82, -- cgit v1.2.3 From b949be5857a4033e00fed67b707774f52619ce60 Mon Sep 17 00:00:00 2001 From: George Spelvin Date: Wed, 27 Mar 2013 14:08:33 +0100 Subject: idr: document exit conditions on idr_for_each_entry better And some manual common subexpression elimination which may help the compiler produce smaller code. Signed-off-by: George Spelvin Signed-off-by: Philipp Reisner Signed-off-by: Jens Axboe --- include/linux/idr.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/idr.h b/include/linux/idr.h index 2640c7e99e51..6ece0583362a 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -122,11 +122,13 @@ static inline void *idr_find(struct idr *idr, int id) * @idp: idr handle * @entry: the type * to use as cursor * @id: id entry's key + * + * @entry and @id do not need to be initialized before the loop, and + * after normal terminatinon @entry is left with the value NULL. This + * is convenient for a "not found" value. */ -#define idr_for_each_entry(idp, entry, id) \ - for (id = 0, entry = (typeof(entry))idr_get_next((idp), &(id)); \ - entry != NULL; \ - ++id, entry = (typeof(entry))idr_get_next((idp), &(id))) +#define idr_for_each_entry(idp, entry, id) \ + for (id = 0; ((entry) = idr_get_next(idp, &(id))) != NULL; ++id) /* * Don't use the following functions. These exist only to suppress -- cgit v1.2.3 From 2bd5ed5d6713594eb2b4d234d01217d506279c7d Mon Sep 17 00:00:00 2001 From: Philipp Reisner Date: Wed, 27 Mar 2013 14:08:40 +0100 Subject: drbd: Fix disconnect to keep the peer disk state if connection breaks during operation The issue was that if the connection broke while we did the gracefull state change to C_DISCONNECTING (C_TEARDOWN), then we returned a success code from the state engine. (SS_CW_NO_NEED) The result of that is that we missed to call the fence-peer script in such a case. Fixed that by introducing a new error code (SS_OUTDATE_WO_CONN). This one should never reach back into user space. Signed-off-by: Philipp Reisner Signed-off-by: Lars Ellenberg Signed-off-by: Jens Axboe --- include/linux/drbd.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/drbd.h b/include/linux/drbd.h index 0c5a18ec322c..316330705fd7 100644 --- a/include/linux/drbd.h +++ b/include/linux/drbd.h @@ -319,7 +319,8 @@ enum drbd_state_rv { SS_IN_TRANSIENT_STATE = -18, /* Retry after the next state change */ SS_CONCURRENT_ST_CHG = -19, /* Concurrent cluster side state change! */ SS_O_VOL_PEER_PRI = -20, - SS_AFTER_LAST_ERROR = -21, /* Keep this at bottom */ + SS_OUTDATE_WO_CONN = -21, + SS_AFTER_LAST_ERROR = -22, /* Keep this at bottom */ }; /* from drbd_strings.c */ -- cgit v1.2.3 From 3990e04df085e0561ab34f84731dc5929585c526 Mon Sep 17 00:00:00 2001 From: Philipp Reisner Date: Wed, 27 Mar 2013 14:08:48 +0100 Subject: drbd: use sched_setscheduler() It was unnoticed for some time that assigning to current->policy is no longer sufficient to set a real time priority for a kernel thread. Reported-by: Charlie Suffin Signed-off-by: Philipp Reisner Signed-off-by: Lars Ellenberg Signed-off-by: Jens Axboe --- include/linux/drbd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/drbd.h b/include/linux/drbd.h index 316330705fd7..1b4d4ee1168f 100644 --- a/include/linux/drbd.h +++ b/include/linux/drbd.h @@ -52,7 +52,7 @@ #endif extern const char *drbd_buildtag(void); -#define REL_VERSION "8.4.2" +#define REL_VERSION "8.4.3" #define API_VERSION 1 #define PRO_VERSION_MIN 86 #define PRO_VERSION_MAX 101 -- cgit v1.2.3 From 5d0f6131a79adfa1fb51309c5f81a2a4ef879dd4 Mon Sep 17 00:00:00 2001 From: Vishal Verma Date: Mon, 4 Mar 2013 18:40:58 -0700 Subject: NVMe: Add nvme-scsi.c Translates SCSI commands in SG_IO ioctl to NVMe commands. Uses the scsi-nvme translation spec from nvmexpress.org as reference. Signed-off-by: Vishal Verma Signed-off-by: Matthew Wilcox --- include/linux/nvme.h | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) (limited to 'include') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index f1974cab60cf..aa575033dbe7 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -546,6 +546,8 @@ struct nvme_ns { int ns_id; int lba_shift; + u64 mode_select_num_blocks; + u32 mode_select_block_len; }; /* @@ -563,6 +565,39 @@ struct nvme_iod { dma_addr_t first_dma; struct scatterlist sg[0]; }; + +/** + * nvme_free_iod - frees an nvme_iod + * @dev: The device that the I/O was submitted to + * @iod: The memory to free + */ +void nvme_free_iod(struct nvme_dev *dev, struct nvme_iod *iod); + +int nvme_setup_prps(struct nvme_dev *dev, struct nvme_common_command *cmd, + struct nvme_iod *iod, int total_len, gfp_t gfp); +struct nvme_iod *nvme_map_user_pages(struct nvme_dev *dev, int write, + unsigned long addr, unsigned length); +void nvme_unmap_user_pages(struct nvme_dev *dev, int write, + struct nvme_iod *iod); +struct nvme_queue *get_nvmeq(struct nvme_dev *dev); +void put_nvmeq(struct nvme_queue *nvmeq); +int nvme_submit_sync_cmd(struct nvme_queue *nvmeq, struct nvme_command *cmd, + u32 *result, unsigned timeout); +int nvme_submit_flush_data(struct nvme_queue *nvmeq, struct nvme_ns *ns); +int nvme_submit_admin_cmd(struct nvme_dev *, struct nvme_command *, + u32 *result); +int nvme_identify(struct nvme_dev *, unsigned nsid, unsigned cns, + dma_addr_t dma_addr); +int nvme_get_features(struct nvme_dev *dev, unsigned fid, unsigned nsid, + dma_addr_t dma_addr, u32 *result); +int nvme_set_features(struct nvme_dev *dev, unsigned fid, unsigned dword11, + dma_addr_t dma_addr, u32 *result); + +struct sg_io_hdr; + +int nvme_sg_io(struct nvme_ns *ns, struct sg_io_hdr __user *u_hdr); +int nvme_sg_get_version_num(int __user *ip); + #endif #endif /* _LINUX_NVME_H */ -- cgit v1.2.3 From fddddb52a6c4e2438f4514ed979183653ca0732a Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Thu, 21 Mar 2013 17:59:14 +0100 Subject: bus: introduce an Marvell EBU MBus driver The Marvell EBU SoCs have a configurable physical address space layout: the physical ranges of memory used to address PCI(e) interfaces, NOR flashes, SRAM and various other types of memory are configurable by software, through a mechanism of so-called 'address decoding windows'. This new driver mvebu-mbus consolidates the existing code to address the configuration of these memory ranges, which is spread into mach-mvebu, mach-orion5x, mach-mv78xx0, mach-dove and mach-kirkwood. Following patches convert each Marvell EBU SoC family to use this driver, therefore removing the old code that was configuring the address decoding windows. It is worth mentioning that the MVEBU_MBUS Kconfig option is intentionally added as a blind option. The new driver implements and exports the mv_mbus_dram_info() function, which is used by various Marvell drivers throughout the tree to get access to window configuration parameters that they require. This function is also implemented in arch/arm/plat-orion/addr-map.c, which ultimately gets removed at the end of this patch series. So, in order to preserve bisectability, we want to ensure that *either* this new driver, *or* the legacy code in plat-orion/addr-map.c gets compiled in. By making MVEBU_MBUS a blind option, we are sure that only a platform that does 'select MVEBU_MBUS' will get this new driver compiled in. Therefore, throughout the next patches that convert the Marvell sub-architectures one after the other to this new driver, we add the 'select MVEBU_MBUS' and also ensure to remove plat-orion/addr-map.c from the build for this specific sub-architecture. This ensures that bisectability is preserved. Ealier versions of this driver had a DT binding, but since those were not yet agreed upon, they were removed. The driver still uses of_device_id to find the SoC specific details according to the string passed to mvebu_mbus_init(). The plan is to re-introduce a proper DT binding as a followup set of patches. Signed-off-by: Thomas Petazzoni Acked-by: Arnd Bergmann Signed-off-by: Jason Cooper --- include/linux/mbus.h | 24 +++++++++++++++++++++++- 1 file changed, 23 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mbus.h b/include/linux/mbus.h index efa1a6d7aca8..462eb9791012 100644 --- a/include/linux/mbus.h +++ b/include/linux/mbus.h @@ -32,6 +32,17 @@ struct mbus_dram_target_info } cs[4]; }; +/* Flags for PCI/PCIe address decoding regions */ +#define MVEBU_MBUS_PCI_IO 0x1 +#define MVEBU_MBUS_PCI_MEM 0x2 +#define MVEBU_MBUS_PCI_WA 0x3 + +/* + * Magic value that explicits that we don't need a remapping-capable + * address decoding window. + */ +#define MVEBU_MBUS_NO_REMAP (0xffffffff) + /* * The Marvell mbus is to be found only on SOCs from the Orion family * at the moment. Provide a dummy stub for other architectures. @@ -44,4 +55,15 @@ static inline const struct mbus_dram_target_info *mv_mbus_dram_info(void) return NULL; } #endif -#endif + +int mvebu_mbus_add_window_remap_flags(const char *devname, phys_addr_t base, + size_t size, phys_addr_t remap, + unsigned int flags); +int mvebu_mbus_add_window(const char *devname, phys_addr_t base, + size_t size); +int mvebu_mbus_del_window(phys_addr_t base, size_t size); +int mvebu_mbus_init(const char *soc, phys_addr_t mbus_phys_base, + size_t mbus_size, phys_addr_t sdram_phys_base, + size_t sdram_size); + +#endif /* __LINUX_MBUS_H */ -- cgit v1.2.3 From ff45262a85dbf1bc74463c5dcea1d71a406d4d8e Mon Sep 17 00:00:00 2001 From: "Kim, Milo" Date: Mon, 18 Feb 2013 21:10:14 -0800 Subject: leds: add new LP5562 LED driver LP5562 can drive up to 4 channels, RGB and White. LEDs can be controlled directly via the led class control interface. LP55xx common driver LP5562 is one of LP55xx family device, so LP55xx common code are used. On the other hand, chip specific configuration is defined in the structure 'lp55xx_device_config' LED pattern data LP5562 has also internal program memory which is used for running various LED patterns. LP5562 driver supports the firmware interface and the predefined pattern data as well. LP5562 device attributes: 'led_pattern' and 'engine_mux' A 'led_pattern' is an index code which runs the predefined pattern data. And 'engine_mux' is updated with the firmware interface is activated. Detailed description has been updated in the documentation files, 'leds-lp55xx.txt' and 'leds-lp5562.txt'. Changes on the header file LP5562 configurable definitions are added. Pattern RGB data is fixed as constant value. (No side effect on other devices, LP5521 or LP5523.) (cooloney@gmail.com: remove redundant mutex_unlock(). Reported by Dan Carpenter ) Signed-off-by: Milo(Woogyom) Kim Signed-off-by: Bryan Wu --- include/linux/platform_data/leds-lp55xx.h | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/platform_data/leds-lp55xx.h b/include/linux/platform_data/leds-lp55xx.h index 1509570d5a3f..1f1041e8b4fc 100644 --- a/include/linux/platform_data/leds-lp55xx.h +++ b/include/linux/platform_data/leds-lp55xx.h @@ -32,6 +32,13 @@ #define LP5521_CLK_INT 1 /* Internal clock */ #define LP5521_CLK_AUTO 2 /* Automatic clock selection */ +/* Bits in LP5562 CONFIG register */ +#define LP5562_PWM_HF LP5521_PWM_HF +#define LP5562_PWRSAVE_EN LP5521_PWRSAVE_EN +#define LP5562_CLK_SRC_EXT LP5521_CLK_SRC_EXT +#define LP5562_CLK_INT LP5521_CLK_INT +#define LP5562_CLK_AUTO LP5521_CLK_AUTO + struct lp55xx_led_config { const char *name; u8 chan_nr; @@ -40,9 +47,9 @@ struct lp55xx_led_config { }; struct lp55xx_predef_pattern { - u8 *r; - u8 *g; - u8 *b; + const u8 *r; + const u8 *g; + const u8 *b; u8 size_r; u8 size_g; u8 size_b; -- cgit v1.2.3 From 39f7e08af3fd9ca1cb94a8270354afb2ea5cfcd3 Mon Sep 17 00:00:00 2001 From: "Kim, Milo" Date: Thu, 14 Mar 2013 04:29:19 -0700 Subject: leds: trigger: use inline functions instead of macros Macros are used in case that an inline function doesn't work. Otherwise, use an empty inline function. (a) Case of !CONFIG_LEDS_TRIGGERS Following macros are replaced with inline functions. led_trigger_register_simple() led_trigger_unregister_simple() led_trigger_event() To make inline types, the structure, 'led_trigger' should be defined. This structure has no member at all. (b) Case of !CONFIG_LEDS_TRIGGER_IDE_DISK ledtrig_ide_activity() macro is replaced with an inline function as well. (c) DEFINE_LED_TRIGGER() and DEFINE_LED_TRIGGER_GLOBAL() Struct 'led_trigger' is defined both cases, with CONFIG_LEDS_TRIGGERS and without CONFIG_LEDS_TRIGGERS. Those macros are moved out of CONFIG_LED_TRIGGERS because of no-dependency on CONFIG_LEDS_TRIGGERS. (d) Fix build errors in mmc-core driver After replacing macros with inline functions, following build errors occur. (condition: CONFIG_LEDS_TRIGGERS is not set) drivers/mmc/core/core.c: In function 'mmc_request_done': drivers/mmc/core/core.c:164:25: error: 'struct mmc_host' has no member named 'led' drivers/mmc/core/core.c: In function 'mmc_start_request': drivers/mmc/core/core.c:254:24: error: 'struct mmc_host' has no member named 'led' make[3]: *** [drivers/mmc/core/core.o] Error 1 The reason of these errors is non-existent member variable, 'led'. It is only valid when CONFIG_LEDS_TRIGGERS is set. But now, it can be used without this dependency. To fix build errors, member 'led' is always used without its config option in 'include/linux/mmc/host.h'. Signed-off-by: Milo(Woogyom) Kim Signed-off-by: Bryan Wu --- include/linux/leds.h | 25 ++++++++++++++----------- include/linux/mmc/host.h | 2 -- 2 files changed, 14 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/linux/leds.h b/include/linux/leds.h index 0d9b5eed714e..2d8c0b4f2f76 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -142,6 +142,10 @@ extern void led_set_brightness(struct led_classdev *led_cdev, /* * LED Triggers */ +/* Registration functions for simple triggers */ +#define DEFINE_LED_TRIGGER(x) static struct led_trigger *x; +#define DEFINE_LED_TRIGGER_GLOBAL(x) struct led_trigger *x; + #ifdef CONFIG_LEDS_TRIGGERS #define TRIG_NAME_MAX 50 @@ -164,9 +168,6 @@ struct led_trigger { extern int led_trigger_register(struct led_trigger *trigger); extern void led_trigger_unregister(struct led_trigger *trigger); -/* Registration functions for simple triggers */ -#define DEFINE_LED_TRIGGER(x) static struct led_trigger *x; -#define DEFINE_LED_TRIGGER_GLOBAL(x) struct led_trigger *x; extern void led_trigger_register_simple(const char *name, struct led_trigger **trigger); extern void led_trigger_unregister_simple(struct led_trigger *trigger); @@ -199,20 +200,22 @@ extern void led_trigger_rename_static(const char *name, #else -/* Triggers aren't active - null macros */ -#define DEFINE_LED_TRIGGER(x) -#define DEFINE_LED_TRIGGER_GLOBAL(x) -#define led_trigger_register_simple(x, y) do {} while(0) -#define led_trigger_unregister_simple(x) do {} while(0) -#define led_trigger_event(x, y) do {} while(0) +/* Trigger has no members */ +struct led_trigger {}; -#endif +/* Trigger inline empty functions */ +static inline void led_trigger_register_simple(const char *name, + struct led_trigger **trigger) {} +static inline void led_trigger_unregister_simple(struct led_trigger *trigger) {} +static inline void led_trigger_event(struct led_trigger *trigger, + enum led_brightness event) {} +#endif /* CONFIG_LEDS_TRIGGERS */ /* Trigger specific functions */ #ifdef CONFIG_LEDS_TRIGGER_IDE_DISK extern void ledtrig_ide_activity(void); #else -#define ledtrig_ide_activity() do {} while(0) +static inline void ledtrig_ide_activity(void) {} #endif /* diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index d6f20cc6415e..357e80efcde0 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -341,9 +341,7 @@ struct mmc_host { mmc_pm_flag_t pm_flags; /* requested pm features */ -#ifdef CONFIG_LEDS_TRIGGERS struct led_trigger *led; /* activity led */ -#endif #ifdef CONFIG_REGULATOR bool regulator_enabled; /* regulator state */ -- cgit v1.2.3 From 48a1d032c954b9b06c3adbf35ef4735dd70ab757 Mon Sep 17 00:00:00 2001 From: "Kim, Milo" Date: Thu, 14 Mar 2013 04:29:24 -0700 Subject: leds: add camera LED triggers Some LED devices support flash/torch functionality through the LED subsystem. This patch enables direct LED trigger controls by the driver. Flash on/off and torch on/off can be done simply by other driver space. Two trigger APIs are added, ledtrig_flash_ctrl() and ledtrig_torch_ctrl(). Signed-off-by: Milo(Woogyom) Kim Signed-off-by: Bryan Wu --- include/linux/leds.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/leds.h b/include/linux/leds.h index 2d8c0b4f2f76..0287ab296689 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -218,6 +218,14 @@ extern void ledtrig_ide_activity(void); static inline void ledtrig_ide_activity(void) {} #endif +#if defined(CONFIG_LEDS_TRIGGER_CAMERA) || defined(CONFIG_LEDS_TRIGGER_CAMERA_MODULE) +extern void ledtrig_flash_ctrl(bool on); +extern void ledtrig_torch_ctrl(bool on); +#else +static inline void ledtrig_flash_ctrl(bool on) {} +static inline void ledtrig_torch_ctrl(bool on) {} +#endif + /* * Generic LED platform data for describing LED names and default triggers. */ -- cgit v1.2.3 From 81f2a5b4a0570a662efd629c176fc1d67e56f7e3 Mon Sep 17 00:00:00 2001 From: "Kim, Milo" Date: Wed, 20 Mar 2013 17:37:04 -0700 Subject: leds: lp55xx: configure the clock detection Now LP55xx provides automatic clock detection API, lp55xx_is_extclk_used(). The clock configuration can be done by the driver itself. (a) Concept The default value is set by each driver with clock selection. The internal clock selection bit is updated in case that the external clock is not detected or clock rate is not 32KHz. (b) Change on LP55xx platform data The clock configuration is done automatically, so no need to define 'update_config' in the platform side. Correlated information are removed in the documentations and header. (c) Definitions moved from header to driver files CONFIG register values are moved each driver, LP5521 and LP5562. Not necessary definitions are removed also. Signed-off-by: Milo(Woogyom) Kim Signed-off-by: Bryan Wu --- include/linux/platform_data/leds-lp55xx.h | 22 ---------------------- 1 file changed, 22 deletions(-) (limited to 'include') diff --git a/include/linux/platform_data/leds-lp55xx.h b/include/linux/platform_data/leds-lp55xx.h index 1f1041e8b4fc..202e290faea8 100644 --- a/include/linux/platform_data/leds-lp55xx.h +++ b/include/linux/platform_data/leds-lp55xx.h @@ -20,25 +20,6 @@ #define LP55XX_CLOCK_INT 1 #define LP55XX_CLOCK_EXT 2 -/* Bits in LP5521 CONFIG register. 'update_config' in lp55xx_platform_data */ -#define LP5521_PWM_HF 0x40 /* PWM: 0 = 256Hz, 1 = 558Hz */ -#define LP5521_PWRSAVE_EN 0x20 /* 1 = Power save mode */ -#define LP5521_CP_MODE_OFF 0 /* Charge pump (CP) off */ -#define LP5521_CP_MODE_BYPASS 8 /* CP forced to bypass mode */ -#define LP5521_CP_MODE_1X5 0x10 /* CP forced to 1.5x mode */ -#define LP5521_CP_MODE_AUTO 0x18 /* Automatic mode selection */ -#define LP5521_R_TO_BATT 4 /* R out: 0 = CP, 1 = Vbat */ -#define LP5521_CLK_SRC_EXT 0 /* Ext-clk source (CLK_32K) */ -#define LP5521_CLK_INT 1 /* Internal clock */ -#define LP5521_CLK_AUTO 2 /* Automatic clock selection */ - -/* Bits in LP5562 CONFIG register */ -#define LP5562_PWM_HF LP5521_PWM_HF -#define LP5562_PWRSAVE_EN LP5521_PWRSAVE_EN -#define LP5562_CLK_SRC_EXT LP5521_CLK_SRC_EXT -#define LP5562_CLK_INT LP5521_CLK_INT -#define LP5562_CLK_AUTO LP5521_CLK_AUTO - struct lp55xx_led_config { const char *name; u8 chan_nr; @@ -86,9 +67,6 @@ struct lp55xx_platform_data { /* Predefined pattern data */ struct lp55xx_predef_pattern *patterns; unsigned int num_patterns; - - /* _CONFIG register */ - u8 update_config; }; #endif /* _LEDS_LP55XX_H */ -- cgit v1.2.3 From 181387da2d64c3129e5b5186c4dd388bc5041d53 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 1 Apr 2013 19:08:06 -0700 Subject: writeback: remove unused bdi_pending_list There's no user left. Remove it. Signed-off-by: Tejun Heo Reviewed-by: Jan Kara Cc: Jens Axboe Cc: Fengguang Wu --- include/linux/backing-dev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 350459910fe1..a5ef27f5411a 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -130,7 +130,6 @@ void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2); extern spinlock_t bdi_lock; extern struct list_head bdi_list; -extern struct list_head bdi_pending_list; static inline int wb_has_dirty_io(struct bdi_writeback *wb) { -- cgit v1.2.3 From 839a8e8660b6777e7fe4e80af1a048aebe2b5977 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 1 Apr 2013 19:08:06 -0700 Subject: writeback: replace custom worker pool implementation with unbound workqueue Writeback implements its own worker pool - each bdi can be associated with a worker thread which is created and destroyed dynamically. The worker thread for the default bdi is always present and serves as the "forker" thread which forks off worker threads for other bdis. there's no reason for writeback to implement its own worker pool when using unbound workqueue instead is much simpler and more efficient. This patch replaces custom worker pool implementation in writeback with an unbound workqueue. The conversion isn't too complicated but the followings are worth mentioning. * bdi_writeback->last_active, task and wakeup_timer are removed. delayed_work ->dwork is added instead. Explicit timer handling is no longer necessary. Everything works by either queueing / modding / flushing / canceling the delayed_work item. * bdi_writeback_thread() becomes bdi_writeback_workfn() which runs off bdi_writeback->dwork. On each execution, it processes bdi->work_list and reschedules itself if there are more things to do. The function also handles low-mem condition, which used to be handled by the forker thread. If the function is running off a rescuer thread, it only writes out limited number of pages so that the rescuer can serve other bdis too. This preserves the flusher creation failure behavior of the forker thread. * INIT_LIST_HEAD(&bdi->bdi_list) is used to tell bdi_writeback_workfn() about on-going bdi unregistration so that it always drains work_list even if it's running off the rescuer. Note that the original code was broken in this regard. Under memory pressure, a bdi could finish unregistration with non-empty work_list. * The default bdi is no longer special. It now is treated the same as any other bdi and bdi_cap_flush_forker() is removed. * BDI_pending is no longer used. Removed. * Some tracepoints become non-applicable. The following TPs are removed - writeback_nothread, writeback_wake_thread, writeback_wake_forker_thread, writeback_thread_start, writeback_thread_stop. Everything, including devices coming and going away and rescuer operation under simulated memory pressure, seems to work fine in my test setup. Signed-off-by: Tejun Heo Reviewed-by: Jan Kara Cc: Jens Axboe Cc: Fengguang Wu Cc: Jeff Moyer --- include/linux/backing-dev.h | 15 +++++---------- include/trace/events/writeback.h | 5 ----- 2 files changed, 5 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index a5ef27f5411a..c3881553f7d1 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -18,6 +18,7 @@ #include #include #include +#include struct page; struct device; @@ -27,7 +28,6 @@ struct dentry; * Bits in backing_dev_info.state */ enum bdi_state { - BDI_pending, /* On its way to being activated */ BDI_wb_alloc, /* Default embedded wb allocated */ BDI_async_congested, /* The async (write) queue is getting full */ BDI_sync_congested, /* The sync queue is getting full */ @@ -53,10 +53,8 @@ struct bdi_writeback { unsigned int nr; unsigned long last_old_flush; /* last old data flush */ - unsigned long last_active; /* last time bdi thread was active */ - struct task_struct *task; /* writeback thread */ - struct timer_list wakeup_timer; /* used for delayed bdi thread wakeup */ + struct delayed_work dwork; /* work item used for writeback */ struct list_head b_dirty; /* dirty inodes */ struct list_head b_io; /* parked for writeback */ struct list_head b_more_io; /* parked for more writeback */ @@ -123,7 +121,7 @@ int bdi_setup_and_register(struct backing_dev_info *, char *, unsigned int); void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages, enum wb_reason reason); void bdi_start_background_writeback(struct backing_dev_info *bdi); -int bdi_writeback_thread(void *data); +void bdi_writeback_workfn(struct work_struct *work); int bdi_has_dirty_io(struct backing_dev_info *bdi); void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi); void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2); @@ -131,6 +129,8 @@ void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2); extern spinlock_t bdi_lock; extern struct list_head bdi_list; +extern struct workqueue_struct *bdi_wq; + static inline int wb_has_dirty_io(struct bdi_writeback *wb) { return !list_empty(&wb->b_dirty) || @@ -335,11 +335,6 @@ static inline bool bdi_cap_swap_backed(struct backing_dev_info *bdi) return bdi->capabilities & BDI_CAP_SWAP_BACKED; } -static inline bool bdi_cap_flush_forker(struct backing_dev_info *bdi) -{ - return bdi == &default_backing_dev_info; -} - static inline bool mapping_cap_writeback_dirty(struct address_space *mapping) { return bdi_cap_writeback_dirty(mapping->backing_dev_info); diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index 6a16fd2e70ed..464ea82e10db 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -183,7 +183,6 @@ DECLARE_EVENT_CLASS(writeback_work_class, DEFINE_EVENT(writeback_work_class, name, \ TP_PROTO(struct backing_dev_info *bdi, struct wb_writeback_work *work), \ TP_ARGS(bdi, work)) -DEFINE_WRITEBACK_WORK_EVENT(writeback_nothread); DEFINE_WRITEBACK_WORK_EVENT(writeback_queue); DEFINE_WRITEBACK_WORK_EVENT(writeback_exec); DEFINE_WRITEBACK_WORK_EVENT(writeback_start); @@ -222,12 +221,8 @@ DEFINE_EVENT(writeback_class, name, \ DEFINE_WRITEBACK_EVENT(writeback_nowork); DEFINE_WRITEBACK_EVENT(writeback_wake_background); -DEFINE_WRITEBACK_EVENT(writeback_wake_thread); -DEFINE_WRITEBACK_EVENT(writeback_wake_forker_thread); DEFINE_WRITEBACK_EVENT(writeback_bdi_register); DEFINE_WRITEBACK_EVENT(writeback_bdi_unregister); -DEFINE_WRITEBACK_EVENT(writeback_thread_start); -DEFINE_WRITEBACK_EVENT(writeback_thread_stop); DECLARE_EVENT_CLASS(wbc_class, TP_PROTO(struct writeback_control *wbc, struct backing_dev_info *bdi), -- cgit v1.2.3 From bb5547acfcd842950b8a22aa83f84af93388b9f2 Mon Sep 17 00:00:00 2001 From: Varun Sethi Date: Fri, 29 Mar 2013 01:23:58 +0530 Subject: iommu/fsl: Make iova dma_addr_t in the iommu_iova_to_phys API. This is required in case of PAMU, as it can support a window size of up to 64G (even on 32bit). Signed-off-by: Varun Sethi Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index ba3b8a98a049..bb0a0fc26729 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -91,8 +91,7 @@ struct iommu_ops { phys_addr_t paddr, size_t size, int prot); size_t (*unmap)(struct iommu_domain *domain, unsigned long iova, size_t size); - phys_addr_t (*iova_to_phys)(struct iommu_domain *domain, - unsigned long iova); + phys_addr_t (*iova_to_phys)(struct iommu_domain *domain, dma_addr_t iova); int (*domain_has_cap)(struct iommu_domain *domain, unsigned long cap); int (*add_device)(struct device *dev); @@ -134,8 +133,7 @@ extern int iommu_map(struct iommu_domain *domain, unsigned long iova, phys_addr_t paddr, size_t size, int prot); extern size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size); -extern phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, - unsigned long iova); +extern phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova); extern int iommu_domain_has_cap(struct iommu_domain *domain, unsigned long cap); extern void iommu_set_fault_handler(struct iommu_domain *domain, @@ -267,8 +265,7 @@ static inline void iommu_domain_window_disable(struct iommu_domain *domain, { } -static inline phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, - unsigned long iova) +static inline phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova) { return 0; } -- cgit v1.2.3 From 80f97f0f73b82444f714651ea053838d27779dca Mon Sep 17 00:00:00 2001 From: Varun Sethi Date: Fri, 29 Mar 2013 01:24:00 +0530 Subject: iommu/fsl: Add the window permission flag as a parameter to iommu_window_enable API. Each iommu window can have access permissions associated with it. Extended the window_enable API to incorporate window access permissions. In case of PAMU each window can have its specific set of permissions. Signed-off-by: Varun Sethi Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index bb0a0fc26729..272781073110 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -104,7 +104,7 @@ struct iommu_ops { /* Window handling functions */ int (*domain_window_enable)(struct iommu_domain *domain, u32 wnd_nr, - phys_addr_t paddr, u64 size); + phys_addr_t paddr, u64 size, int prot); void (*domain_window_disable)(struct iommu_domain *domain, u32 wnd_nr); /* Set the numer of window per domain */ int (*domain_set_windows)(struct iommu_domain *domain, u32 w_count); @@ -169,7 +169,8 @@ extern int iommu_domain_set_attr(struct iommu_domain *domain, enum iommu_attr, /* Window handling function prototypes */ extern int iommu_domain_window_enable(struct iommu_domain *domain, u32 wnd_nr, - phys_addr_t offset, u64 size); + phys_addr_t offset, u64 size, + int prot); extern void iommu_domain_window_disable(struct iommu_domain *domain, u32 wnd_nr); /** * report_iommu_fault() - report about an IOMMU fault to the IOMMU framework @@ -255,7 +256,7 @@ static inline int iommu_unmap(struct iommu_domain *domain, unsigned long iova, static inline int iommu_domain_window_enable(struct iommu_domain *domain, u32 wnd_nr, phys_addr_t paddr, - u64 size) + u64 size, int prot) { return -ENODEV; } -- cgit v1.2.3 From 119f5e448d32c11faf22fe81f6f2d78467a47149 Mon Sep 17 00:00:00 2001 From: Magnus Damm Date: Wed, 13 Mar 2013 20:32:13 +0900 Subject: gpio: Renesas R-Car GPIO driver V3 This patch is V3 of a GPIO driver for the R-Car series of SoCs from Renesas. This driver is designed to be reusable between multiple SoCs that share the same basic building block, but so far it has only been used on R-Car H1 (r8a7779). Each driver instance handles 32 GPIOs with individually maskable IRQs. The driver operates on a single I/O memory range and the 32 GPIOs are hooked up a single interrupt. In the case of R-Car H1 either external IRQ pins or GPIOs with interrupts can be used for on-board interupts. For external IRQs 4 pins are supported, and in the case of GPIO there are 202 GPIOS as 202 interrupts hooked up via 6 driver instances and to the GIC and the Cortex-A9 Quad. At this point this driver is interfacing as a regular platform device driver. In the future DT support will be submitted as an incremental feature patch. Signed-off-by: Magnus Damm Reviewed-by: Linus Walleij Signed-off-by: Simon Horman --- include/linux/platform_data/gpio-rcar.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) create mode 100644 include/linux/platform_data/gpio-rcar.h (limited to 'include') diff --git a/include/linux/platform_data/gpio-rcar.h b/include/linux/platform_data/gpio-rcar.h new file mode 100644 index 000000000000..bebfcd86fb80 --- /dev/null +++ b/include/linux/platform_data/gpio-rcar.h @@ -0,0 +1,25 @@ +/* + * Renesas R-Car GPIO Support + * + * Copyright (C) 2013 Magnus Damm + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef __GPIO_RCAR_H__ +#define __GPIO_RCAR_H__ + +struct gpio_rcar_config { + unsigned int gpio_base; + unsigned int irq_base; + unsigned int number_of_pins; +}; + +#endif /* __GPIO_RCAR_H__ */ -- cgit v1.2.3 From dc3465a943ed2dd5de37d3d60df5c4e11c49efcb Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Sun, 10 Mar 2013 03:27:00 +0100 Subject: gpio-rcar: Add pinctrl support Register the GPIO pin range, and request and free GPIO pins using the pinctrl API. Signed-off-by: Laurent Pinchart Acked-by: Linus Walleij Signed-off-by: Simon Horman --- include/linux/platform_data/gpio-rcar.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/platform_data/gpio-rcar.h b/include/linux/platform_data/gpio-rcar.h index bebfcd86fb80..b253f77a7ddf 100644 --- a/include/linux/platform_data/gpio-rcar.h +++ b/include/linux/platform_data/gpio-rcar.h @@ -20,6 +20,7 @@ struct gpio_rcar_config { unsigned int gpio_base; unsigned int irq_base; unsigned int number_of_pins; + const char *pctl_name; }; #endif /* __GPIO_RCAR_H__ */ -- cgit v1.2.3 From 4aa02c7cbb6816913554dc18ff750a70a4ace796 Mon Sep 17 00:00:00 2001 From: Shawn Guo Date: Wed, 13 Mar 2013 14:03:12 +0800 Subject: video: mxsfb: remove fb_phys/fb_size from platform_data There is no in-tree users of mxsfb_platform_data fb_phys/fb_size. With CMA support in the kernel, there is no real need for platform to reserve memory and pass address and size into driver via platform_data. So let's remove fb_phys/fb_size from mxsfb_platform_data to ease full device tree adoption. Signed-off-by: Shawn Guo --- include/linux/mxsfb.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include') diff --git a/include/linux/mxsfb.h b/include/linux/mxsfb.h index f80af8674342..93696404ee55 100644 --- a/include/linux/mxsfb.h +++ b/include/linux/mxsfb.h @@ -35,15 +35,6 @@ struct mxsfb_platform_data { unsigned dotclk_delay; /* refer manual HW_LCDIF_VDCTRL4 register */ unsigned ld_intf_width; /* refer STMLCDIF_* macros */ - - unsigned fb_size; /* Size of the video memory. If zero a - * default will be used - */ - unsigned long fb_phys; /* physical address for the video memory. If - * zero the framebuffer memory will be dynamically - * allocated. If specified,fb_size must also be specified. - * fb_phys must be unused by Linux. - */ u32 sync; /* sync mask, contains MXSFB specifics not * carried in fb_info->var.sync */ -- cgit v1.2.3 From 36f3e99649baa77b2d22e385b2ea09e8f308c905 Mon Sep 17 00:00:00 2001 From: Shawn Guo Date: Wed, 13 Mar 2013 14:28:19 +0800 Subject: video: mxsfb: remove dotclk_delay from platform_data There is no in-tree mxsfb users using mxsfb_platform_data dotclk_delay. Let's remove it from mxsfb_platform_data to ease full device tree adoption of mxsfb driver. If later we have platform/board need to configure this parameter, we can add it into device tree bindings. Signed-off-by: Shawn Guo --- include/linux/mxsfb.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/mxsfb.h b/include/linux/mxsfb.h index 93696404ee55..b78465cdb26e 100644 --- a/include/linux/mxsfb.h +++ b/include/linux/mxsfb.h @@ -33,7 +33,6 @@ struct mxsfb_platform_data { unsigned default_bpp; - unsigned dotclk_delay; /* refer manual HW_LCDIF_VDCTRL4 register */ unsigned ld_intf_width; /* refer STMLCDIF_* macros */ u32 sync; /* sync mask, contains MXSFB specifics not * carried in fb_info->var.sync -- cgit v1.2.3 From c8b5cfc8797203d5e952592be00a5acacf5cef6a Mon Sep 17 00:00:00 2001 From: Shawn Guo Date: Thu, 14 Mar 2013 13:21:56 +0800 Subject: video: mxsfb: remove mxsfb_platform_data None of mxsfb users uses mxsfb_platform_data now. Let's remove it from mxsfb driver. As the result, include/linux/mxsfb.h gets deleted with a few macros moved into mxsfb.c. Along with the change, the typo "FAILING" in macro name is fixed to be "FALLING". Signed-off-by: Shawn Guo --- include/linux/mxsfb.h | 42 ------------------------------------------ 1 file changed, 42 deletions(-) delete mode 100644 include/linux/mxsfb.h (limited to 'include') diff --git a/include/linux/mxsfb.h b/include/linux/mxsfb.h deleted file mode 100644 index b78465cdb26e..000000000000 --- a/include/linux/mxsfb.h +++ /dev/null @@ -1,42 +0,0 @@ -/* - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2 - * of the License, or (at your option) any later version. - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, - * MA 02110-1301, USA. - */ - -#ifndef __LINUX_MXSFB_H -#define __LINUX_MXSFB_H - -#include - -#define STMLCDIF_8BIT 1 /** pixel data bus to the display is of 8 bit width */ -#define STMLCDIF_16BIT 0 /** pixel data bus to the display is of 16 bit width */ -#define STMLCDIF_18BIT 2 /** pixel data bus to the display is of 18 bit width */ -#define STMLCDIF_24BIT 3 /** pixel data bus to the display is of 24 bit width */ - -#define MXSFB_SYNC_DATA_ENABLE_HIGH_ACT (1 << 6) -#define MXSFB_SYNC_DOTCLK_FAILING_ACT (1 << 7) /* failing/negtive edge sampling */ - -struct mxsfb_platform_data { - struct fb_videomode *mode_list; - unsigned mode_count; - - unsigned default_bpp; - - unsigned ld_intf_width; /* refer STMLCDIF_* macros */ - u32 sync; /* sync mask, contains MXSFB specifics not - * carried in fb_info->var.sync - */ -}; - -#endif /* __LINUX_MXSFB_H */ -- cgit v1.2.3 From 26aafa77df61c4190eae80646211ee6f07c88eaf Mon Sep 17 00:00:00 2001 From: Shawn Guo Date: Tue, 26 Feb 2013 11:07:32 +0800 Subject: spi: mxs-spi: move to use generic DMA helper With the generic DMA device tree helper supported by mxs-dma driver, client devices only need to call dma_request_slave_channel() for requesting a DMA channel from dmaengine. Since mxs is a DT only platform now, along with the changes, the non-DT case handling in probe function also gets removed. Signed-off-by: Shawn Guo Acked-by: Grant Likely Reviewed-by: Arnd Bergmann --- include/linux/spi/mxs-spi.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/spi/mxs-spi.h b/include/linux/spi/mxs-spi.h index 61ae1306db23..4835486f58e5 100644 --- a/include/linux/spi/mxs-spi.h +++ b/include/linux/spi/mxs-spi.h @@ -24,7 +24,7 @@ #ifndef __LINUX_SPI_MXS_SPI_H__ #define __LINUX_SPI_MXS_SPI_H__ -#include +#include #define ssp_is_old(host) ((host)->devid == IMX23_SSP) @@ -137,9 +137,7 @@ struct mxs_ssp { unsigned int clk_rate; enum mxs_ssp_id devid; - int dma_channel; struct dma_chan *dmach; - struct mxs_dma_data dma_data; unsigned int dma_dir; enum dma_transfer_direction slave_dirn; u32 ssp_pio_words[SSP_PIO_NUM]; -- cgit v1.2.3 From deaf39efbc0829f26ae0b8fbe5de820588982f72 Mon Sep 17 00:00:00 2001 From: Simon Glass Date: Mon, 25 Feb 2013 14:08:36 -0800 Subject: mfd: Add ChromeOS EC messages header This file is included verbatim from the ChromeOS EC respository. Ideally we would prefer to avoid changing it, to make it easier to track this rapidly-changing file. Signed-off-by: Simon Glass Signed-off-by: Che-Liang Chiou Signed-off-by: Vincent Palatin Signed-off-by: Samuel Ortiz --- include/linux/mfd/cros_ec_commands.h | 1369 ++++++++++++++++++++++++++++++++++ 1 file changed, 1369 insertions(+) create mode 100644 include/linux/mfd/cros_ec_commands.h (limited to 'include') diff --git a/include/linux/mfd/cros_ec_commands.h b/include/linux/mfd/cros_ec_commands.h new file mode 100644 index 000000000000..86fd06953bcd --- /dev/null +++ b/include/linux/mfd/cros_ec_commands.h @@ -0,0 +1,1369 @@ +/* + * Host communication command constants for ChromeOS EC + * + * Copyright (C) 2012 Google, Inc + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * The ChromeOS EC multi function device is used to mux all the requests + * to the EC device for its multiple features: keyboard controller, + * battery charging and regulator control, firmware update. + * + * NOTE: This file is copied verbatim from the ChromeOS EC Open Source + * project in an attempt to make future updates easy to make. + */ + +#ifndef __CROS_EC_COMMANDS_H +#define __CROS_EC_COMMANDS_H + +/* + * Protocol overview + * + * request: CMD [ P0 P1 P2 ... Pn S ] + * response: ERR [ P0 P1 P2 ... Pn S ] + * + * where the bytes are defined as follow : + * - CMD is the command code. (defined by EC_CMD_ constants) + * - ERR is the error code. (defined by EC_RES_ constants) + * - Px is the optional payload. + * it is not sent if the error code is not success. + * (defined by ec_params_ and ec_response_ structures) + * - S is the checksum which is the sum of all payload bytes. + * + * On LPC, CMD and ERR are sent/received at EC_LPC_ADDR_KERNEL|USER_CMD + * and the payloads are sent/received at EC_LPC_ADDR_KERNEL|USER_PARAM. + * On I2C, all bytes are sent serially in the same message. + */ + +/* Current version of this protocol */ +#define EC_PROTO_VERSION 0x00000002 + +/* Command version mask */ +#define EC_VER_MASK(version) (1UL << (version)) + +/* I/O addresses for ACPI commands */ +#define EC_LPC_ADDR_ACPI_DATA 0x62 +#define EC_LPC_ADDR_ACPI_CMD 0x66 + +/* I/O addresses for host command */ +#define EC_LPC_ADDR_HOST_DATA 0x200 +#define EC_LPC_ADDR_HOST_CMD 0x204 + +/* I/O addresses for host command args and params */ +#define EC_LPC_ADDR_HOST_ARGS 0x800 +#define EC_LPC_ADDR_HOST_PARAM 0x804 +#define EC_HOST_PARAM_SIZE 0x0fc /* Size of param area in bytes */ + +/* I/O addresses for host command params, old interface */ +#define EC_LPC_ADDR_OLD_PARAM 0x880 +#define EC_OLD_PARAM_SIZE 0x080 /* Size of param area in bytes */ + +/* EC command register bit functions */ +#define EC_LPC_CMDR_DATA (1 << 0) /* Data ready for host to read */ +#define EC_LPC_CMDR_PENDING (1 << 1) /* Write pending to EC */ +#define EC_LPC_CMDR_BUSY (1 << 2) /* EC is busy processing a command */ +#define EC_LPC_CMDR_CMD (1 << 3) /* Last host write was a command */ +#define EC_LPC_CMDR_ACPI_BRST (1 << 4) /* Burst mode (not used) */ +#define EC_LPC_CMDR_SCI (1 << 5) /* SCI event is pending */ +#define EC_LPC_CMDR_SMI (1 << 6) /* SMI event is pending */ + +#define EC_LPC_ADDR_MEMMAP 0x900 +#define EC_MEMMAP_SIZE 255 /* ACPI IO buffer max is 255 bytes */ +#define EC_MEMMAP_TEXT_MAX 8 /* Size of a string in the memory map */ + +/* The offset address of each type of data in mapped memory. */ +#define EC_MEMMAP_TEMP_SENSOR 0x00 /* Temp sensors */ +#define EC_MEMMAP_FAN 0x10 /* Fan speeds */ +#define EC_MEMMAP_TEMP_SENSOR_B 0x18 /* Temp sensors (second set) */ +#define EC_MEMMAP_ID 0x20 /* 'E' 'C' */ +#define EC_MEMMAP_ID_VERSION 0x22 /* Version of data in 0x20 - 0x2f */ +#define EC_MEMMAP_THERMAL_VERSION 0x23 /* Version of data in 0x00 - 0x1f */ +#define EC_MEMMAP_BATTERY_VERSION 0x24 /* Version of data in 0x40 - 0x7f */ +#define EC_MEMMAP_SWITCHES_VERSION 0x25 /* Version of data in 0x30 - 0x33 */ +#define EC_MEMMAP_EVENTS_VERSION 0x26 /* Version of data in 0x34 - 0x3f */ +#define EC_MEMMAP_HOST_CMD_FLAGS 0x27 /* Host command interface flags */ +#define EC_MEMMAP_SWITCHES 0x30 +#define EC_MEMMAP_HOST_EVENTS 0x34 +#define EC_MEMMAP_BATT_VOLT 0x40 /* Battery Present Voltage */ +#define EC_MEMMAP_BATT_RATE 0x44 /* Battery Present Rate */ +#define EC_MEMMAP_BATT_CAP 0x48 /* Battery Remaining Capacity */ +#define EC_MEMMAP_BATT_FLAG 0x4c /* Battery State, defined below */ +#define EC_MEMMAP_BATT_DCAP 0x50 /* Battery Design Capacity */ +#define EC_MEMMAP_BATT_DVLT 0x54 /* Battery Design Voltage */ +#define EC_MEMMAP_BATT_LFCC 0x58 /* Battery Last Full Charge Capacity */ +#define EC_MEMMAP_BATT_CCNT 0x5c /* Battery Cycle Count */ +#define EC_MEMMAP_BATT_MFGR 0x60 /* Battery Manufacturer String */ +#define EC_MEMMAP_BATT_MODEL 0x68 /* Battery Model Number String */ +#define EC_MEMMAP_BATT_SERIAL 0x70 /* Battery Serial Number String */ +#define EC_MEMMAP_BATT_TYPE 0x78 /* Battery Type String */ + +/* Number of temp sensors at EC_MEMMAP_TEMP_SENSOR */ +#define EC_TEMP_SENSOR_ENTRIES 16 +/* + * Number of temp sensors at EC_MEMMAP_TEMP_SENSOR_B. + * + * Valid only if EC_MEMMAP_THERMAL_VERSION returns >= 2. + */ +#define EC_TEMP_SENSOR_B_ENTRIES 8 +#define EC_TEMP_SENSOR_NOT_PRESENT 0xff +#define EC_TEMP_SENSOR_ERROR 0xfe +#define EC_TEMP_SENSOR_NOT_POWERED 0xfd +#define EC_TEMP_SENSOR_NOT_CALIBRATED 0xfc +/* + * The offset of temperature value stored in mapped memory. This allows + * reporting a temperature range of 200K to 454K = -73C to 181C. + */ +#define EC_TEMP_SENSOR_OFFSET 200 + +#define EC_FAN_SPEED_ENTRIES 4 /* Number of fans at EC_MEMMAP_FAN */ +#define EC_FAN_SPEED_NOT_PRESENT 0xffff /* Entry not present */ +#define EC_FAN_SPEED_STALLED 0xfffe /* Fan stalled */ + +/* Battery bit flags at EC_MEMMAP_BATT_FLAG. */ +#define EC_BATT_FLAG_AC_PRESENT 0x01 +#define EC_BATT_FLAG_BATT_PRESENT 0x02 +#define EC_BATT_FLAG_DISCHARGING 0x04 +#define EC_BATT_FLAG_CHARGING 0x08 +#define EC_BATT_FLAG_LEVEL_CRITICAL 0x10 + +/* Switch flags at EC_MEMMAP_SWITCHES */ +#define EC_SWITCH_LID_OPEN 0x01 +#define EC_SWITCH_POWER_BUTTON_PRESSED 0x02 +#define EC_SWITCH_WRITE_PROTECT_DISABLED 0x04 +/* Recovery requested via keyboard */ +#define EC_SWITCH_KEYBOARD_RECOVERY 0x08 +/* Recovery requested via dedicated signal (from servo board) */ +#define EC_SWITCH_DEDICATED_RECOVERY 0x10 +/* Was fake developer mode switch; now unused. Remove in next refactor. */ +#define EC_SWITCH_IGNORE0 0x20 + +/* Host command interface flags */ +/* Host command interface supports LPC args (LPC interface only) */ +#define EC_HOST_CMD_FLAG_LPC_ARGS_SUPPORTED 0x01 + +/* Wireless switch flags */ +#define EC_WIRELESS_SWITCH_WLAN 0x01 +#define EC_WIRELESS_SWITCH_BLUETOOTH 0x02 + +/* + * This header file is used in coreboot both in C and ACPI code. The ACPI code + * is pre-processed to handle constants but the ASL compiler is unable to + * handle actual C code so keep it separate. + */ +#ifndef __ACPI__ + +/* LPC command status byte masks */ +/* EC has written a byte in the data register and host hasn't read it yet */ +#define EC_LPC_STATUS_TO_HOST 0x01 +/* Host has written a command/data byte and the EC hasn't read it yet */ +#define EC_LPC_STATUS_FROM_HOST 0x02 +/* EC is processing a command */ +#define EC_LPC_STATUS_PROCESSING 0x04 +/* Last write to EC was a command, not data */ +#define EC_LPC_STATUS_LAST_CMD 0x08 +/* EC is in burst mode. Unsupported by Chrome EC, so this bit is never set */ +#define EC_LPC_STATUS_BURST_MODE 0x10 +/* SCI event is pending (requesting SCI query) */ +#define EC_LPC_STATUS_SCI_PENDING 0x20 +/* SMI event is pending (requesting SMI query) */ +#define EC_LPC_STATUS_SMI_PENDING 0x40 +/* (reserved) */ +#define EC_LPC_STATUS_RESERVED 0x80 + +/* + * EC is busy. This covers both the EC processing a command, and the host has + * written a new command but the EC hasn't picked it up yet. + */ +#define EC_LPC_STATUS_BUSY_MASK \ + (EC_LPC_STATUS_FROM_HOST | EC_LPC_STATUS_PROCESSING) + +/* Host command response codes */ +enum ec_status { + EC_RES_SUCCESS = 0, + EC_RES_INVALID_COMMAND = 1, + EC_RES_ERROR = 2, + EC_RES_INVALID_PARAM = 3, + EC_RES_ACCESS_DENIED = 4, + EC_RES_INVALID_RESPONSE = 5, + EC_RES_INVALID_VERSION = 6, + EC_RES_INVALID_CHECKSUM = 7, + EC_RES_IN_PROGRESS = 8, /* Accepted, command in progress */ + EC_RES_UNAVAILABLE = 9, /* No response available */ + EC_RES_TIMEOUT = 10, /* We got a timeout */ + EC_RES_OVERFLOW = 11, /* Table / data overflow */ +}; + +/* + * Host event codes. Note these are 1-based, not 0-based, because ACPI query + * EC command uses code 0 to mean "no event pending". We explicitly specify + * each value in the enum listing so they won't change if we delete/insert an + * item or rearrange the list (it needs to be stable across platforms, not + * just within a single compiled instance). + */ +enum host_event_code { + EC_HOST_EVENT_LID_CLOSED = 1, + EC_HOST_EVENT_LID_OPEN = 2, + EC_HOST_EVENT_POWER_BUTTON = 3, + EC_HOST_EVENT_AC_CONNECTED = 4, + EC_HOST_EVENT_AC_DISCONNECTED = 5, + EC_HOST_EVENT_BATTERY_LOW = 6, + EC_HOST_EVENT_BATTERY_CRITICAL = 7, + EC_HOST_EVENT_BATTERY = 8, + EC_HOST_EVENT_THERMAL_THRESHOLD = 9, + EC_HOST_EVENT_THERMAL_OVERLOAD = 10, + EC_HOST_EVENT_THERMAL = 11, + EC_HOST_EVENT_USB_CHARGER = 12, + EC_HOST_EVENT_KEY_PRESSED = 13, + /* + * EC has finished initializing the host interface. The host can check + * for this event following sending a EC_CMD_REBOOT_EC command to + * determine when the EC is ready to accept subsequent commands. + */ + EC_HOST_EVENT_INTERFACE_READY = 14, + /* Keyboard recovery combo has been pressed */ + EC_HOST_EVENT_KEYBOARD_RECOVERY = 15, + + /* Shutdown due to thermal overload */ + EC_HOST_EVENT_THERMAL_SHUTDOWN = 16, + /* Shutdown due to battery level too low */ + EC_HOST_EVENT_BATTERY_SHUTDOWN = 17, + + /* + * The high bit of the event mask is not used as a host event code. If + * it reads back as set, then the entire event mask should be + * considered invalid by the host. This can happen when reading the + * raw event status via EC_MEMMAP_HOST_EVENTS but the LPC interface is + * not initialized on the EC, or improperly configured on the host. + */ + EC_HOST_EVENT_INVALID = 32 +}; +/* Host event mask */ +#define EC_HOST_EVENT_MASK(event_code) (1UL << ((event_code) - 1)) + +/* Arguments at EC_LPC_ADDR_HOST_ARGS */ +struct ec_lpc_host_args { + uint8_t flags; + uint8_t command_version; + uint8_t data_size; + /* + * Checksum; sum of command + flags + command_version + data_size + + * all params/response data bytes. + */ + uint8_t checksum; +} __packed; + +/* Flags for ec_lpc_host_args.flags */ +/* + * Args are from host. Data area at EC_LPC_ADDR_HOST_PARAM contains command + * params. + * + * If EC gets a command and this flag is not set, this is an old-style command. + * Command version is 0 and params from host are at EC_LPC_ADDR_OLD_PARAM with + * unknown length. EC must respond with an old-style response (that is, + * withouth setting EC_HOST_ARGS_FLAG_TO_HOST). + */ +#define EC_HOST_ARGS_FLAG_FROM_HOST 0x01 +/* + * Args are from EC. Data area at EC_LPC_ADDR_HOST_PARAM contains response. + * + * If EC responds to a command and this flag is not set, this is an old-style + * response. Command version is 0 and response data from EC is at + * EC_LPC_ADDR_OLD_PARAM with unknown length. + */ +#define EC_HOST_ARGS_FLAG_TO_HOST 0x02 + +/* + * Notes on commands: + * + * Each command is an 8-byte command value. Commands which take params or + * return response data specify structs for that data. If no struct is + * specified, the command does not input or output data, respectively. + * Parameter/response length is implicit in the structs. Some underlying + * communication protocols (I2C, SPI) may add length or checksum headers, but + * those are implementation-dependent and not defined here. + */ + +/*****************************************************************************/ +/* General / test commands */ + +/* + * Get protocol version, used to deal with non-backward compatible protocol + * changes. + */ +#define EC_CMD_PROTO_VERSION 0x00 + +struct ec_response_proto_version { + uint32_t version; +} __packed; + +/* + * Hello. This is a simple command to test the EC is responsive to + * commands. + */ +#define EC_CMD_HELLO 0x01 + +struct ec_params_hello { + uint32_t in_data; /* Pass anything here */ +} __packed; + +struct ec_response_hello { + uint32_t out_data; /* Output will be in_data + 0x01020304 */ +} __packed; + +/* Get version number */ +#define EC_CMD_GET_VERSION 0x02 + +enum ec_current_image { + EC_IMAGE_UNKNOWN = 0, + EC_IMAGE_RO, + EC_IMAGE_RW +}; + +struct ec_response_get_version { + /* Null-terminated version strings for RO, RW */ + char version_string_ro[32]; + char version_string_rw[32]; + char reserved[32]; /* Was previously RW-B string */ + uint32_t current_image; /* One of ec_current_image */ +} __packed; + +/* Read test */ +#define EC_CMD_READ_TEST 0x03 + +struct ec_params_read_test { + uint32_t offset; /* Starting value for read buffer */ + uint32_t size; /* Size to read in bytes */ +} __packed; + +struct ec_response_read_test { + uint32_t data[32]; +} __packed; + +/* + * Get build information + * + * Response is null-terminated string. + */ +#define EC_CMD_GET_BUILD_INFO 0x04 + +/* Get chip info */ +#define EC_CMD_GET_CHIP_INFO 0x05 + +struct ec_response_get_chip_info { + /* Null-terminated strings */ + char vendor[32]; + char name[32]; + char revision[32]; /* Mask version */ +} __packed; + +/* Get board HW version */ +#define EC_CMD_GET_BOARD_VERSION 0x06 + +struct ec_response_board_version { + uint16_t board_version; /* A monotonously incrementing number. */ +} __packed; + +/* + * Read memory-mapped data. + * + * This is an alternate interface to memory-mapped data for bus protocols + * which don't support direct-mapped memory - I2C, SPI, etc. + * + * Response is params.size bytes of data. + */ +#define EC_CMD_READ_MEMMAP 0x07 + +struct ec_params_read_memmap { + uint8_t offset; /* Offset in memmap (EC_MEMMAP_*) */ + uint8_t size; /* Size to read in bytes */ +} __packed; + +/* Read versions supported for a command */ +#define EC_CMD_GET_CMD_VERSIONS 0x08 + +struct ec_params_get_cmd_versions { + uint8_t cmd; /* Command to check */ +} __packed; + +struct ec_response_get_cmd_versions { + /* + * Mask of supported versions; use EC_VER_MASK() to compare with a + * desired version. + */ + uint32_t version_mask; +} __packed; + +/* + * Check EC communcations status (busy). This is needed on i2c/spi but not + * on lpc since it has its own out-of-band busy indicator. + * + * lpc must read the status from the command register. Attempting this on + * lpc will overwrite the args/parameter space and corrupt its data. + */ +#define EC_CMD_GET_COMMS_STATUS 0x09 + +/* Avoid using ec_status which is for return values */ +enum ec_comms_status { + EC_COMMS_STATUS_PROCESSING = 1 << 0, /* Processing cmd */ +}; + +struct ec_response_get_comms_status { + uint32_t flags; /* Mask of enum ec_comms_status */ +} __packed; + + +/*****************************************************************************/ +/* Flash commands */ + +/* Get flash info */ +#define EC_CMD_FLASH_INFO 0x10 + +struct ec_response_flash_info { + /* Usable flash size, in bytes */ + uint32_t flash_size; + /* + * Write block size. Write offset and size must be a multiple + * of this. + */ + uint32_t write_block_size; + /* + * Erase block size. Erase offset and size must be a multiple + * of this. + */ + uint32_t erase_block_size; + /* + * Protection block size. Protection offset and size must be a + * multiple of this. + */ + uint32_t protect_block_size; +} __packed; + +/* + * Read flash + * + * Response is params.size bytes of data. + */ +#define EC_CMD_FLASH_READ 0x11 + +struct ec_params_flash_read { + uint32_t offset; /* Byte offset to read */ + uint32_t size; /* Size to read in bytes */ +} __packed; + +/* Write flash */ +#define EC_CMD_FLASH_WRITE 0x12 + +struct ec_params_flash_write { + uint32_t offset; /* Byte offset to write */ + uint32_t size; /* Size to write in bytes */ + /* + * Data to write. Could really use EC_PARAM_SIZE - 8, but tidiest to + * use a power of 2 so writes stay aligned. + */ + uint8_t data[64]; +} __packed; + +/* Erase flash */ +#define EC_CMD_FLASH_ERASE 0x13 + +struct ec_params_flash_erase { + uint32_t offset; /* Byte offset to erase */ + uint32_t size; /* Size to erase in bytes */ +} __packed; + +/* + * Get/set flash protection. + * + * If mask!=0, sets/clear the requested bits of flags. Depending on the + * firmware write protect GPIO, not all flags will take effect immediately; + * some flags require a subsequent hard reset to take effect. Check the + * returned flags bits to see what actually happened. + * + * If mask=0, simply returns the current flags state. + */ +#define EC_CMD_FLASH_PROTECT 0x15 +#define EC_VER_FLASH_PROTECT 1 /* Command version 1 */ + +/* Flags for flash protection */ +/* RO flash code protected when the EC boots */ +#define EC_FLASH_PROTECT_RO_AT_BOOT (1 << 0) +/* + * RO flash code protected now. If this bit is set, at-boot status cannot + * be changed. + */ +#define EC_FLASH_PROTECT_RO_NOW (1 << 1) +/* Entire flash code protected now, until reboot. */ +#define EC_FLASH_PROTECT_ALL_NOW (1 << 2) +/* Flash write protect GPIO is asserted now */ +#define EC_FLASH_PROTECT_GPIO_ASSERTED (1 << 3) +/* Error - at least one bank of flash is stuck locked, and cannot be unlocked */ +#define EC_FLASH_PROTECT_ERROR_STUCK (1 << 4) +/* + * Error - flash protection is in inconsistent state. At least one bank of + * flash which should be protected is not protected. Usually fixed by + * re-requesting the desired flags, or by a hard reset if that fails. + */ +#define EC_FLASH_PROTECT_ERROR_INCONSISTENT (1 << 5) +/* Entile flash code protected when the EC boots */ +#define EC_FLASH_PROTECT_ALL_AT_BOOT (1 << 6) + +struct ec_params_flash_protect { + uint32_t mask; /* Bits in flags to apply */ + uint32_t flags; /* New flags to apply */ +} __packed; + +struct ec_response_flash_protect { + /* Current value of flash protect flags */ + uint32_t flags; + /* + * Flags which are valid on this platform. This allows the caller + * to distinguish between flags which aren't set vs. flags which can't + * be set on this platform. + */ + uint32_t valid_flags; + /* Flags which can be changed given the current protection state */ + uint32_t writable_flags; +} __packed; + +/* + * Note: commands 0x14 - 0x19 version 0 were old commands to get/set flash + * write protect. These commands may be reused with version > 0. + */ + +/* Get the region offset/size */ +#define EC_CMD_FLASH_REGION_INFO 0x16 +#define EC_VER_FLASH_REGION_INFO 1 + +enum ec_flash_region { + /* Region which holds read-only EC image */ + EC_FLASH_REGION_RO, + /* Region which holds rewritable EC image */ + EC_FLASH_REGION_RW, + /* + * Region which should be write-protected in the factory (a superset of + * EC_FLASH_REGION_RO) + */ + EC_FLASH_REGION_WP_RO, +}; + +struct ec_params_flash_region_info { + uint32_t region; /* enum ec_flash_region */ +} __packed; + +struct ec_response_flash_region_info { + uint32_t offset; + uint32_t size; +} __packed; + +/* Read/write VbNvContext */ +#define EC_CMD_VBNV_CONTEXT 0x17 +#define EC_VER_VBNV_CONTEXT 1 +#define EC_VBNV_BLOCK_SIZE 16 + +enum ec_vbnvcontext_op { + EC_VBNV_CONTEXT_OP_READ, + EC_VBNV_CONTEXT_OP_WRITE, +}; + +struct ec_params_vbnvcontext { + uint32_t op; + uint8_t block[EC_VBNV_BLOCK_SIZE]; +} __packed; + +struct ec_response_vbnvcontext { + uint8_t block[EC_VBNV_BLOCK_SIZE]; +} __packed; + +/*****************************************************************************/ +/* PWM commands */ + +/* Get fan target RPM */ +#define EC_CMD_PWM_GET_FAN_TARGET_RPM 0x20 + +struct ec_response_pwm_get_fan_rpm { + uint32_t rpm; +} __packed; + +/* Set target fan RPM */ +#define EC_CMD_PWM_SET_FAN_TARGET_RPM 0x21 + +struct ec_params_pwm_set_fan_target_rpm { + uint32_t rpm; +} __packed; + +/* Get keyboard backlight */ +#define EC_CMD_PWM_GET_KEYBOARD_BACKLIGHT 0x22 + +struct ec_response_pwm_get_keyboard_backlight { + uint8_t percent; + uint8_t enabled; +} __packed; + +/* Set keyboard backlight */ +#define EC_CMD_PWM_SET_KEYBOARD_BACKLIGHT 0x23 + +struct ec_params_pwm_set_keyboard_backlight { + uint8_t percent; +} __packed; + +/* Set target fan PWM duty cycle */ +#define EC_CMD_PWM_SET_FAN_DUTY 0x24 + +struct ec_params_pwm_set_fan_duty { + uint32_t percent; +} __packed; + +/*****************************************************************************/ +/* + * Lightbar commands. This looks worse than it is. Since we only use one HOST + * command to say "talk to the lightbar", we put the "and tell it to do X" part + * into a subcommand. We'll make separate structs for subcommands with + * different input args, so that we know how much to expect. + */ +#define EC_CMD_LIGHTBAR_CMD 0x28 + +struct rgb_s { + uint8_t r, g, b; +}; + +#define LB_BATTERY_LEVELS 4 +/* List of tweakable parameters. NOTE: It's __packed so it can be sent in a + * host command, but the alignment is the same regardless. Keep it that way. + */ +struct lightbar_params { + /* Timing */ + int google_ramp_up; + int google_ramp_down; + int s3s0_ramp_up; + int s0_tick_delay[2]; /* AC=0/1 */ + int s0a_tick_delay[2]; /* AC=0/1 */ + int s0s3_ramp_down; + int s3_sleep_for; + int s3_ramp_up; + int s3_ramp_down; + + /* Oscillation */ + uint8_t new_s0; + uint8_t osc_min[2]; /* AC=0/1 */ + uint8_t osc_max[2]; /* AC=0/1 */ + uint8_t w_ofs[2]; /* AC=0/1 */ + + /* Brightness limits based on the backlight and AC. */ + uint8_t bright_bl_off_fixed[2]; /* AC=0/1 */ + uint8_t bright_bl_on_min[2]; /* AC=0/1 */ + uint8_t bright_bl_on_max[2]; /* AC=0/1 */ + + /* Battery level thresholds */ + uint8_t battery_threshold[LB_BATTERY_LEVELS - 1]; + + /* Map [AC][battery_level] to color index */ + uint8_t s0_idx[2][LB_BATTERY_LEVELS]; /* AP is running */ + uint8_t s3_idx[2][LB_BATTERY_LEVELS]; /* AP is sleeping */ + + /* Color palette */ + struct rgb_s color[8]; /* 0-3 are Google colors */ +} __packed; + +struct ec_params_lightbar { + uint8_t cmd; /* Command (see enum lightbar_command) */ + union { + struct { + /* no args */ + } dump, off, on, init, get_seq, get_params; + + struct num { + uint8_t num; + } brightness, seq, demo; + + struct reg { + uint8_t ctrl, reg, value; + } reg; + + struct rgb { + uint8_t led, red, green, blue; + } rgb; + + struct lightbar_params set_params; + }; +} __packed; + +struct ec_response_lightbar { + union { + struct dump { + struct { + uint8_t reg; + uint8_t ic0; + uint8_t ic1; + } vals[23]; + } dump; + + struct get_seq { + uint8_t num; + } get_seq; + + struct lightbar_params get_params; + + struct { + /* no return params */ + } off, on, init, brightness, seq, reg, rgb, demo, set_params; + }; +} __packed; + +/* Lightbar commands */ +enum lightbar_command { + LIGHTBAR_CMD_DUMP = 0, + LIGHTBAR_CMD_OFF = 1, + LIGHTBAR_CMD_ON = 2, + LIGHTBAR_CMD_INIT = 3, + LIGHTBAR_CMD_BRIGHTNESS = 4, + LIGHTBAR_CMD_SEQ = 5, + LIGHTBAR_CMD_REG = 6, + LIGHTBAR_CMD_RGB = 7, + LIGHTBAR_CMD_GET_SEQ = 8, + LIGHTBAR_CMD_DEMO = 9, + LIGHTBAR_CMD_GET_PARAMS = 10, + LIGHTBAR_CMD_SET_PARAMS = 11, + LIGHTBAR_NUM_CMDS +}; + +/*****************************************************************************/ +/* Verified boot commands */ + +/* + * Note: command code 0x29 version 0 was VBOOT_CMD in Link EVT; it may be + * reused for other purposes with version > 0. + */ + +/* Verified boot hash command */ +#define EC_CMD_VBOOT_HASH 0x2A + +struct ec_params_vboot_hash { + uint8_t cmd; /* enum ec_vboot_hash_cmd */ + uint8_t hash_type; /* enum ec_vboot_hash_type */ + uint8_t nonce_size; /* Nonce size; may be 0 */ + uint8_t reserved0; /* Reserved; set 0 */ + uint32_t offset; /* Offset in flash to hash */ + uint32_t size; /* Number of bytes to hash */ + uint8_t nonce_data[64]; /* Nonce data; ignored if nonce_size=0 */ +} __packed; + +struct ec_response_vboot_hash { + uint8_t status; /* enum ec_vboot_hash_status */ + uint8_t hash_type; /* enum ec_vboot_hash_type */ + uint8_t digest_size; /* Size of hash digest in bytes */ + uint8_t reserved0; /* Ignore; will be 0 */ + uint32_t offset; /* Offset in flash which was hashed */ + uint32_t size; /* Number of bytes hashed */ + uint8_t hash_digest[64]; /* Hash digest data */ +} __packed; + +enum ec_vboot_hash_cmd { + EC_VBOOT_HASH_GET = 0, /* Get current hash status */ + EC_VBOOT_HASH_ABORT = 1, /* Abort calculating current hash */ + EC_VBOOT_HASH_START = 2, /* Start computing a new hash */ + EC_VBOOT_HASH_RECALC = 3, /* Synchronously compute a new hash */ +}; + +enum ec_vboot_hash_type { + EC_VBOOT_HASH_TYPE_SHA256 = 0, /* SHA-256 */ +}; + +enum ec_vboot_hash_status { + EC_VBOOT_HASH_STATUS_NONE = 0, /* No hash (not started, or aborted) */ + EC_VBOOT_HASH_STATUS_DONE = 1, /* Finished computing a hash */ + EC_VBOOT_HASH_STATUS_BUSY = 2, /* Busy computing a hash */ +}; + +/* + * Special values for offset for EC_VBOOT_HASH_START and EC_VBOOT_HASH_RECALC. + * If one of these is specified, the EC will automatically update offset and + * size to the correct values for the specified image (RO or RW). + */ +#define EC_VBOOT_HASH_OFFSET_RO 0xfffffffe +#define EC_VBOOT_HASH_OFFSET_RW 0xfffffffd + +/*****************************************************************************/ +/* USB charging control commands */ + +/* Set USB port charging mode */ +#define EC_CMD_USB_CHARGE_SET_MODE 0x30 + +struct ec_params_usb_charge_set_mode { + uint8_t usb_port_id; + uint8_t mode; +} __packed; + +/*****************************************************************************/ +/* Persistent storage for host */ + +/* Maximum bytes that can be read/written in a single command */ +#define EC_PSTORE_SIZE_MAX 64 + +/* Get persistent storage info */ +#define EC_CMD_PSTORE_INFO 0x40 + +struct ec_response_pstore_info { + /* Persistent storage size, in bytes */ + uint32_t pstore_size; + /* Access size; read/write offset and size must be a multiple of this */ + uint32_t access_size; +} __packed; + +/* + * Read persistent storage + * + * Response is params.size bytes of data. + */ +#define EC_CMD_PSTORE_READ 0x41 + +struct ec_params_pstore_read { + uint32_t offset; /* Byte offset to read */ + uint32_t size; /* Size to read in bytes */ +} __packed; + +/* Write persistent storage */ +#define EC_CMD_PSTORE_WRITE 0x42 + +struct ec_params_pstore_write { + uint32_t offset; /* Byte offset to write */ + uint32_t size; /* Size to write in bytes */ + uint8_t data[EC_PSTORE_SIZE_MAX]; +} __packed; + +/*****************************************************************************/ +/* Real-time clock */ + +/* RTC params and response structures */ +struct ec_params_rtc { + uint32_t time; +} __packed; + +struct ec_response_rtc { + uint32_t time; +} __packed; + +/* These use ec_response_rtc */ +#define EC_CMD_RTC_GET_VALUE 0x44 +#define EC_CMD_RTC_GET_ALARM 0x45 + +/* These all use ec_params_rtc */ +#define EC_CMD_RTC_SET_VALUE 0x46 +#define EC_CMD_RTC_SET_ALARM 0x47 + +/*****************************************************************************/ +/* Port80 log access */ + +/* Get last port80 code from previous boot */ +#define EC_CMD_PORT80_LAST_BOOT 0x48 + +struct ec_response_port80_last_boot { + uint16_t code; +} __packed; + +/*****************************************************************************/ +/* Thermal engine commands */ + +/* Set thershold value */ +#define EC_CMD_THERMAL_SET_THRESHOLD 0x50 + +struct ec_params_thermal_set_threshold { + uint8_t sensor_type; + uint8_t threshold_id; + uint16_t value; +} __packed; + +/* Get threshold value */ +#define EC_CMD_THERMAL_GET_THRESHOLD 0x51 + +struct ec_params_thermal_get_threshold { + uint8_t sensor_type; + uint8_t threshold_id; +} __packed; + +struct ec_response_thermal_get_threshold { + uint16_t value; +} __packed; + +/* Toggle automatic fan control */ +#define EC_CMD_THERMAL_AUTO_FAN_CTRL 0x52 + +/* Get TMP006 calibration data */ +#define EC_CMD_TMP006_GET_CALIBRATION 0x53 + +struct ec_params_tmp006_get_calibration { + uint8_t index; +} __packed; + +struct ec_response_tmp006_get_calibration { + float s0; + float b0; + float b1; + float b2; +} __packed; + +/* Set TMP006 calibration data */ +#define EC_CMD_TMP006_SET_CALIBRATION 0x54 + +struct ec_params_tmp006_set_calibration { + uint8_t index; + uint8_t reserved[3]; /* Reserved; set 0 */ + float s0; + float b0; + float b1; + float b2; +} __packed; + +/*****************************************************************************/ +/* MKBP - Matrix KeyBoard Protocol */ + +/* + * Read key state + * + * Returns raw data for keyboard cols; see ec_response_mkbp_info.cols for + * expected response size. + */ +#define EC_CMD_MKBP_STATE 0x60 + +/* Provide information about the matrix : number of rows and columns */ +#define EC_CMD_MKBP_INFO 0x61 + +struct ec_response_mkbp_info { + uint32_t rows; + uint32_t cols; + uint8_t switches; +} __packed; + +/* Simulate key press */ +#define EC_CMD_MKBP_SIMULATE_KEY 0x62 + +struct ec_params_mkbp_simulate_key { + uint8_t col; + uint8_t row; + uint8_t pressed; +} __packed; + +/* Configure keyboard scanning */ +#define EC_CMD_MKBP_SET_CONFIG 0x64 +#define EC_CMD_MKBP_GET_CONFIG 0x65 + +/* flags */ +enum mkbp_config_flags { + EC_MKBP_FLAGS_ENABLE = 1, /* Enable keyboard scanning */ +}; + +enum mkbp_config_valid { + EC_MKBP_VALID_SCAN_PERIOD = 1 << 0, + EC_MKBP_VALID_POLL_TIMEOUT = 1 << 1, + EC_MKBP_VALID_MIN_POST_SCAN_DELAY = 1 << 3, + EC_MKBP_VALID_OUTPUT_SETTLE = 1 << 4, + EC_MKBP_VALID_DEBOUNCE_DOWN = 1 << 5, + EC_MKBP_VALID_DEBOUNCE_UP = 1 << 6, + EC_MKBP_VALID_FIFO_MAX_DEPTH = 1 << 7, +}; + +/* Configuration for our key scanning algorithm */ +struct ec_mkbp_config { + uint32_t valid_mask; /* valid fields */ + uint8_t flags; /* some flags (enum mkbp_config_flags) */ + uint8_t valid_flags; /* which flags are valid */ + uint16_t scan_period_us; /* period between start of scans */ + /* revert to interrupt mode after no activity for this long */ + uint32_t poll_timeout_us; + /* + * minimum post-scan relax time. Once we finish a scan we check + * the time until we are due to start the next one. If this time is + * shorter this field, we use this instead. + */ + uint16_t min_post_scan_delay_us; + /* delay between setting up output and waiting for it to settle */ + uint16_t output_settle_us; + uint16_t debounce_down_us; /* time for debounce on key down */ + uint16_t debounce_up_us; /* time for debounce on key up */ + /* maximum depth to allow for fifo (0 = no keyscan output) */ + uint8_t fifo_max_depth; +} __packed; + +struct ec_params_mkbp_set_config { + struct ec_mkbp_config config; +} __packed; + +struct ec_response_mkbp_get_config { + struct ec_mkbp_config config; +} __packed; + +/* Run the key scan emulation */ +#define EC_CMD_KEYSCAN_SEQ_CTRL 0x66 + +enum ec_keyscan_seq_cmd { + EC_KEYSCAN_SEQ_STATUS = 0, /* Get status information */ + EC_KEYSCAN_SEQ_CLEAR = 1, /* Clear sequence */ + EC_KEYSCAN_SEQ_ADD = 2, /* Add item to sequence */ + EC_KEYSCAN_SEQ_START = 3, /* Start running sequence */ + EC_KEYSCAN_SEQ_COLLECT = 4, /* Collect sequence summary data */ +}; + +enum ec_collect_flags { + /* + * Indicates this scan was processed by the EC. Due to timing, some + * scans may be skipped. + */ + EC_KEYSCAN_SEQ_FLAG_DONE = 1 << 0, +}; + +struct ec_collect_item { + uint8_t flags; /* some flags (enum ec_collect_flags) */ +}; + +struct ec_params_keyscan_seq_ctrl { + uint8_t cmd; /* Command to send (enum ec_keyscan_seq_cmd) */ + union { + struct { + uint8_t active; /* still active */ + uint8_t num_items; /* number of items */ + /* Current item being presented */ + uint8_t cur_item; + } status; + struct { + /* + * Absolute time for this scan, measured from the + * start of the sequence. + */ + uint32_t time_us; + uint8_t scan[0]; /* keyscan data */ + } add; + struct { + uint8_t start_item; /* First item to return */ + uint8_t num_items; /* Number of items to return */ + } collect; + }; +} __packed; + +struct ec_result_keyscan_seq_ctrl { + union { + struct { + uint8_t num_items; /* Number of items */ + /* Data for each item */ + struct ec_collect_item item[0]; + } collect; + }; +} __packed; + +/*****************************************************************************/ +/* Temperature sensor commands */ + +/* Read temperature sensor info */ +#define EC_CMD_TEMP_SENSOR_GET_INFO 0x70 + +struct ec_params_temp_sensor_get_info { + uint8_t id; +} __packed; + +struct ec_response_temp_sensor_get_info { + char sensor_name[32]; + uint8_t sensor_type; +} __packed; + +/*****************************************************************************/ + +/* + * Note: host commands 0x80 - 0x87 are reserved to avoid conflict with ACPI + * commands accidentally sent to the wrong interface. See the ACPI section + * below. + */ + +/*****************************************************************************/ +/* Host event commands */ + +/* + * Host event mask params and response structures, shared by all of the host + * event commands below. + */ +struct ec_params_host_event_mask { + uint32_t mask; +} __packed; + +struct ec_response_host_event_mask { + uint32_t mask; +} __packed; + +/* These all use ec_response_host_event_mask */ +#define EC_CMD_HOST_EVENT_GET_B 0x87 +#define EC_CMD_HOST_EVENT_GET_SMI_MASK 0x88 +#define EC_CMD_HOST_EVENT_GET_SCI_MASK 0x89 +#define EC_CMD_HOST_EVENT_GET_WAKE_MASK 0x8d + +/* These all use ec_params_host_event_mask */ +#define EC_CMD_HOST_EVENT_SET_SMI_MASK 0x8a +#define EC_CMD_HOST_EVENT_SET_SCI_MASK 0x8b +#define EC_CMD_HOST_EVENT_CLEAR 0x8c +#define EC_CMD_HOST_EVENT_SET_WAKE_MASK 0x8e +#define EC_CMD_HOST_EVENT_CLEAR_B 0x8f + +/*****************************************************************************/ +/* Switch commands */ + +/* Enable/disable LCD backlight */ +#define EC_CMD_SWITCH_ENABLE_BKLIGHT 0x90 + +struct ec_params_switch_enable_backlight { + uint8_t enabled; +} __packed; + +/* Enable/disable WLAN/Bluetooth */ +#define EC_CMD_SWITCH_ENABLE_WIRELESS 0x91 + +struct ec_params_switch_enable_wireless { + uint8_t enabled; +} __packed; + +/*****************************************************************************/ +/* GPIO commands. Only available on EC if write protect has been disabled. */ + +/* Set GPIO output value */ +#define EC_CMD_GPIO_SET 0x92 + +struct ec_params_gpio_set { + char name[32]; + uint8_t val; +} __packed; + +/* Get GPIO value */ +#define EC_CMD_GPIO_GET 0x93 + +struct ec_params_gpio_get { + char name[32]; +} __packed; +struct ec_response_gpio_get { + uint8_t val; +} __packed; + +/*****************************************************************************/ +/* I2C commands. Only available when flash write protect is unlocked. */ + +/* Read I2C bus */ +#define EC_CMD_I2C_READ 0x94 + +struct ec_params_i2c_read { + uint16_t addr; + uint8_t read_size; /* Either 8 or 16. */ + uint8_t port; + uint8_t offset; +} __packed; +struct ec_response_i2c_read { + uint16_t data; +} __packed; + +/* Write I2C bus */ +#define EC_CMD_I2C_WRITE 0x95 + +struct ec_params_i2c_write { + uint16_t data; + uint16_t addr; + uint8_t write_size; /* Either 8 or 16. */ + uint8_t port; + uint8_t offset; +} __packed; + +/*****************************************************************************/ +/* Charge state commands. Only available when flash write protect unlocked. */ + +/* Force charge state machine to stop in idle mode */ +#define EC_CMD_CHARGE_FORCE_IDLE 0x96 + +struct ec_params_force_idle { + uint8_t enabled; +} __packed; + +/*****************************************************************************/ +/* Console commands. Only available when flash write protect is unlocked. */ + +/* Snapshot console output buffer for use by EC_CMD_CONSOLE_READ. */ +#define EC_CMD_CONSOLE_SNAPSHOT 0x97 + +/* + * Read next chunk of data from saved snapshot. + * + * Response is null-terminated string. Empty string, if there is no more + * remaining output. + */ +#define EC_CMD_CONSOLE_READ 0x98 + +/*****************************************************************************/ + +/* + * Cut off battery power output if the battery supports. + * + * For unsupported battery, just don't implement this command and lets EC + * return EC_RES_INVALID_COMMAND. + */ +#define EC_CMD_BATTERY_CUT_OFF 0x99 + +/*****************************************************************************/ +/* Temporary debug commands. TODO: remove this crosbug.com/p/13849 */ + +/* + * Dump charge state machine context. + * + * Response is a binary dump of charge state machine context. + */ +#define EC_CMD_CHARGE_DUMP 0xa0 + +/* + * Set maximum battery charging current. + */ +#define EC_CMD_CHARGE_CURRENT_LIMIT 0xa1 + +struct ec_params_current_limit { + uint32_t limit; +} __packed; + +/*****************************************************************************/ +/* System commands */ + +/* + * TODO: this is a confusing name, since it doesn't necessarily reboot the EC. + * Rename to "set image" or something similar. + */ +#define EC_CMD_REBOOT_EC 0xd2 + +/* Command */ +enum ec_reboot_cmd { + EC_REBOOT_CANCEL = 0, /* Cancel a pending reboot */ + EC_REBOOT_JUMP_RO = 1, /* Jump to RO without rebooting */ + EC_REBOOT_JUMP_RW = 2, /* Jump to RW without rebooting */ + /* (command 3 was jump to RW-B) */ + EC_REBOOT_COLD = 4, /* Cold-reboot */ + EC_REBOOT_DISABLE_JUMP = 5, /* Disable jump until next reboot */ + EC_REBOOT_HIBERNATE = 6 /* Hibernate EC */ +}; + +/* Flags for ec_params_reboot_ec.reboot_flags */ +#define EC_REBOOT_FLAG_RESERVED0 (1 << 0) /* Was recovery request */ +#define EC_REBOOT_FLAG_ON_AP_SHUTDOWN (1 << 1) /* Reboot after AP shutdown */ + +struct ec_params_reboot_ec { + uint8_t cmd; /* enum ec_reboot_cmd */ + uint8_t flags; /* See EC_REBOOT_FLAG_* */ +} __packed; + +/* + * Get information on last EC panic. + * + * Returns variable-length platform-dependent panic information. See panic.h + * for details. + */ +#define EC_CMD_GET_PANIC_INFO 0xd3 + +/*****************************************************************************/ +/* + * ACPI commands + * + * These are valid ONLY on the ACPI command/data port. + */ + +/* + * ACPI Read Embedded Controller + * + * This reads from ACPI memory space on the EC (EC_ACPI_MEM_*). + * + * Use the following sequence: + * + * - Write EC_CMD_ACPI_READ to EC_LPC_ADDR_ACPI_CMD + * - Wait for EC_LPC_CMDR_PENDING bit to clear + * - Write address to EC_LPC_ADDR_ACPI_DATA + * - Wait for EC_LPC_CMDR_DATA bit to set + * - Read value from EC_LPC_ADDR_ACPI_DATA + */ +#define EC_CMD_ACPI_READ 0x80 + +/* + * ACPI Write Embedded Controller + * + * This reads from ACPI memory space on the EC (EC_ACPI_MEM_*). + * + * Use the following sequence: + * + * - Write EC_CMD_ACPI_WRITE to EC_LPC_ADDR_ACPI_CMD + * - Wait for EC_LPC_CMDR_PENDING bit to clear + * - Write address to EC_LPC_ADDR_ACPI_DATA + * - Wait for EC_LPC_CMDR_PENDING bit to clear + * - Write value to EC_LPC_ADDR_ACPI_DATA + */ +#define EC_CMD_ACPI_WRITE 0x81 + +/* + * ACPI Query Embedded Controller + * + * This clears the lowest-order bit in the currently pending host events, and + * sets the result code to the 1-based index of the bit (event 0x00000001 = 1, + * event 0x80000000 = 32), or 0 if no event was pending. + */ +#define EC_CMD_ACPI_QUERY_EVENT 0x84 + +/* Valid addresses in ACPI memory space, for read/write commands */ +/* Memory space version; set to EC_ACPI_MEM_VERSION_CURRENT */ +#define EC_ACPI_MEM_VERSION 0x00 +/* + * Test location; writing value here updates test compliment byte to (0xff - + * value). + */ +#define EC_ACPI_MEM_TEST 0x01 +/* Test compliment; writes here are ignored. */ +#define EC_ACPI_MEM_TEST_COMPLIMENT 0x02 +/* Keyboard backlight brightness percent (0 - 100) */ +#define EC_ACPI_MEM_KEYBOARD_BACKLIGHT 0x03 + +/* Current version of ACPI memory address space */ +#define EC_ACPI_MEM_VERSION_CURRENT 1 + + +/*****************************************************************************/ +/* + * Special commands + * + * These do not follow the normal rules for commands. See each command for + * details. + */ + +/* + * Reboot NOW + * + * This command will work even when the EC LPC interface is busy, because the + * reboot command is processed at interrupt level. Note that when the EC + * reboots, the host will reboot too, so there is no response to this command. + * + * Use EC_CMD_REBOOT_EC to reboot the EC more politely. + */ +#define EC_CMD_REBOOT 0xd1 /* Think "die" */ + +/* + * Resend last response (not supported on LPC). + * + * Returns EC_RES_UNAVAILABLE if there is no response available - for example, + * there was no previous command, or the previous command's response was too + * big to save. + */ +#define EC_CMD_RESEND_RESPONSE 0xdb + +/* + * This header byte on a command indicate version 0. Any header byte less + * than this means that we are talking to an old EC which doesn't support + * versioning. In that case, we assume version 0. + * + * Header bytes greater than this indicate a later version. For example, + * EC_CMD_VERSION0 + 1 means we are using version 1. + * + * The old EC interface must not use commands 0dc or higher. + */ +#define EC_CMD_VERSION0 0xdc + +#endif /* !__ACPI__ */ + +#endif /* __CROS_EC_COMMANDS_H */ -- cgit v1.2.3 From 4ab6174e8cdb007cf500e484bdf454b8d14d524a Mon Sep 17 00:00:00 2001 From: Simon Glass Date: Mon, 25 Feb 2013 14:08:37 -0800 Subject: mfd: Add ChromeOS EC implementation This is the base EC implementation, which provides a high level interface to the EC for use by the rest of the kernel. The actual communcations is dealt with by a separate protocol driver which registers itself with this interface. Interrupts are passed on through a notifier. A simple message structure is used to pass messages to the protocol driver. Signed-off-by: Simon Glass Signed-off-by: Che-Liang Chiou Signed-off-by: Jonathan Kliegman Signed-off-by: Luigi Semenzato Signed-off-by: Olof Johansson Signed-off-by: Vincent Palatin Signed-off-by: Samuel Ortiz --- include/linux/mfd/cros_ec.h | 170 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 170 insertions(+) create mode 100644 include/linux/mfd/cros_ec.h (limited to 'include') diff --git a/include/linux/mfd/cros_ec.h b/include/linux/mfd/cros_ec.h new file mode 100644 index 000000000000..032af7fc5b2e --- /dev/null +++ b/include/linux/mfd/cros_ec.h @@ -0,0 +1,170 @@ +/* + * ChromeOS EC multi-function device + * + * Copyright (C) 2012 Google, Inc + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef __LINUX_MFD_CROS_EC_H +#define __LINUX_MFD_CROS_EC_H + +#include + +/* + * Command interface between EC and AP, for LPC, I2C and SPI interfaces. + */ +enum { + EC_MSG_TX_HEADER_BYTES = 3, + EC_MSG_TX_TRAILER_BYTES = 1, + EC_MSG_TX_PROTO_BYTES = EC_MSG_TX_HEADER_BYTES + + EC_MSG_TX_TRAILER_BYTES, + EC_MSG_RX_PROTO_BYTES = 3, + + /* Max length of messages */ + EC_MSG_BYTES = EC_HOST_PARAM_SIZE + EC_MSG_TX_PROTO_BYTES, + +}; + +/** + * struct cros_ec_msg - A message sent to the EC, and its reply + * + * @version: Command version number (often 0) + * @cmd: Command to send (EC_CMD_...) + * @out_buf: Outgoing payload (to EC) + * @outlen: Outgoing length + * @in_buf: Incoming payload (from EC) + * @in_len: Incoming length + */ +struct cros_ec_msg { + u8 version; + u8 cmd; + uint8_t *out_buf; + int out_len; + uint8_t *in_buf; + int in_len; +}; + +/** + * struct cros_ec_device - Information about a ChromeOS EC device + * + * @name: Name of this EC interface + * @priv: Private data + * @irq: Interrupt to use + * @din: input buffer (from EC) + * @dout: output buffer (to EC) + * \note + * These two buffers will always be dword-aligned and include enough + * space for up to 7 word-alignment bytes also, so we can ensure that + * the body of the message is always dword-aligned (64-bit). + * + * We use this alignment to keep ARM and x86 happy. Probably word + * alignment would be OK, there might be a small performance advantage + * to using dword. + * @din_size: size of din buffer + * @dout_size: size of dout buffer + * @command_send: send a command + * @command_recv: receive a command + * @ec_name: name of EC device (e.g. 'chromeos-ec') + * @phys_name: name of physical comms layer (e.g. 'i2c-4') + * @parent: pointer to parent device (e.g. i2c or spi device) + * @dev: Device pointer + * dev_lock: Lock to prevent concurrent access + * @wake_enabled: true if this device can wake the system from sleep + * @was_wake_device: true if this device was set to wake the system from + * sleep at the last suspend + * @event_notifier: interrupt event notifier for transport devices + */ +struct cros_ec_device { + const char *name; + void *priv; + int irq; + uint8_t *din; + uint8_t *dout; + int din_size; + int dout_size; + int (*command_send)(struct cros_ec_device *ec, + uint16_t cmd, void *out_buf, int out_len); + int (*command_recv)(struct cros_ec_device *ec, + uint16_t cmd, void *in_buf, int in_len); + int (*command_sendrecv)(struct cros_ec_device *ec, + uint16_t cmd, void *out_buf, int out_len, + void *in_buf, int in_len); + int (*command_xfer)(struct cros_ec_device *ec, + struct cros_ec_msg *msg); + + const char *ec_name; + const char *phys_name; + struct device *parent; + + /* These are --private-- fields - do not assign */ + struct device *dev; + struct mutex dev_lock; + bool wake_enabled; + bool was_wake_device; + struct blocking_notifier_head event_notifier; +}; + +/** + * cros_ec_suspend - Handle a suspend operation for the ChromeOS EC device + * + * This can be called by drivers to handle a suspend event. + * + * ec_dev: Device to suspend + * @return 0 if ok, -ve on error + */ +int cros_ec_suspend(struct cros_ec_device *ec_dev); + +/** + * cros_ec_resume - Handle a resume operation for the ChromeOS EC device + * + * This can be called by drivers to handle a resume event. + * + * @ec_dev: Device to resume + * @return 0 if ok, -ve on error + */ +int cros_ec_resume(struct cros_ec_device *ec_dev); + +/** + * cros_ec_prepare_tx - Prepare an outgoing message in the output buffer + * + * This is intended to be used by all ChromeOS EC drivers, but at present + * only SPI uses it. Once LPC uses the same protocol it can start using it. + * I2C could use it now, with a refactor of the existing code. + * + * @ec_dev: Device to register + * @msg: Message to write + */ +int cros_ec_prepare_tx(struct cros_ec_device *ec_dev, + struct cros_ec_msg *msg); + +/** + * cros_ec_remove - Remove a ChromeOS EC + * + * Call this to deregister a ChromeOS EC. After this you should call + * cros_ec_free(). + * + * @ec_dev: Device to register + * @return 0 if ok, -ve on error + */ +int cros_ec_remove(struct cros_ec_device *ec_dev); + +/** + * cros_ec_register - Register a new ChromeOS EC, using the provided info + * + * Before calling this, allocate a pointer to a new device and then fill + * in all the fields up to the --private-- marker. + * + * @ec_dev: Device to register + * @return 0 if ok, -ve on error + */ +int cros_ec_register(struct cros_ec_device *ec_dev); + +#endif /* __LINUX_MFD_CROS_EC_H */ -- cgit v1.2.3 From 43840415339f1600f281211cfb5400fab696536e Mon Sep 17 00:00:00 2001 From: Simon Glass Date: Mon, 25 Feb 2013 14:08:40 -0800 Subject: input: matrix-keymap: Add function to read the new DT binding We now have a binding which adds two parameters to the matrix keypad DT node. This is separate from the GPIO-driven matrix keypad binding, and unfortunately incompatible, since that uses row-gpios/col-gpios for the row and column counts. So the easiest option here is to provide a function for non-GPIO drivers to use to decode the binding. Note: We could in fact create an entirely separate structure to hold these two fields, but it does not seem worth it, yet. If we have more parameters then we can add this, and then refactor each driver to hold such a structure. Signed-off-by: Simon Glass Acked-by: Dmitry Torokhov Tested-by: Sourav Poddar (v2) Signed-off-by: Samuel Ortiz --- include/linux/input/matrix_keypad.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include') diff --git a/include/linux/input/matrix_keypad.h b/include/linux/input/matrix_keypad.h index 5f3aa6b11bfa..27e06acc509a 100644 --- a/include/linux/input/matrix_keypad.h +++ b/include/linux/input/matrix_keypad.h @@ -81,4 +81,23 @@ int matrix_keypad_build_keymap(const struct matrix_keymap_data *keymap_data, unsigned short *keymap, struct input_dev *input_dev); +#ifdef CONFIG_OF +/** + * matrix_keypad_parse_of_params() - Read parameters from matrix-keypad node + * + * @dev: Device containing of_node + * @rows: Returns number of matrix rows + * @cols: Returns number of matrix columns + * @return 0 if OK, <0 on error + */ +int matrix_keypad_parse_of_params(struct device *dev, + unsigned int *rows, unsigned int *cols); +#else +static inline int matrix_keypad_parse_of_params(struct device *dev, + unsigned int *rows, unsigned int *cols) +{ + return -ENOSYS; +} +#endif /* CONFIG_OF */ + #endif /* _MATRIX_KEYPAD_H */ -- cgit v1.2.3 From 14c6578683367b1e7af0c3c09e872b45a45183a7 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Mon, 4 Mar 2013 14:21:34 +0200 Subject: mtd: nand: remove AG-AND support We have only one AG-AND driver and it was not touched since 2005. It looks like AG-AND was not really make it to mass-production and can be considered a dead technology. Along with the AG-AND support, this patch removes the BBT_AUTO_REFRESH feature, because the only user of this feature is AG-AND. And even though it is implemented as a generic feature, I prefer to remove it because NAND flashes do not really need it in this form. Signed-off-by: Artem Bityutskiy Acked-by: Brian Norris Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 16 ---------------- 1 file changed, 16 deletions(-) (limited to 'include') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index ef52d9c91459..7cc299436f94 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -171,22 +171,6 @@ typedef enum { #define NAND_CACHEPRG 0x00000008 /* Chip has copy back function */ #define NAND_COPYBACK 0x00000010 -/* - * AND Chip which has 4 banks and a confusing page / block - * assignment. See Renesas datasheet for further information. - */ -#define NAND_IS_AND 0x00000020 -/* - * Chip has a array of 4 pages which can be read without - * additional ready /busy waits. - */ -#define NAND_4PAGE_ARRAY 0x00000040 -/* - * Chip requires that BBT is periodically rewritten to prevent - * bits from adjacent blocks from 'leaking' in altering data. - * This happens with the Renesas AG-AND chips, possibly others. - */ -#define BBT_AUTO_REFRESH 0x00000080 /* * Chip requires ready check on read (for auto-incremented sequential read). * True only for small page devices; large page devices do not support -- cgit v1.2.3 From 0be718e5525a73557e76ea1c05b8001dde507049 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Mon, 4 Mar 2013 14:35:56 +0200 Subject: mtd: nand: remove a bunch of unused commands Signed-off-by: Artem Bityutskiy Acked-by: Brian Norris Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 20 -------------------- 1 file changed, 20 deletions(-) (limited to 'include') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 7cc299436f94..e5d6160a4511 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -86,7 +86,6 @@ extern int nand_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len); #define NAND_CMD_READOOB 0x50 #define NAND_CMD_ERASE1 0x60 #define NAND_CMD_STATUS 0x70 -#define NAND_CMD_STATUS_MULTI 0x71 #define NAND_CMD_SEQIN 0x80 #define NAND_CMD_RNDIN 0x85 #define NAND_CMD_READID 0x90 @@ -105,25 +104,6 @@ extern int nand_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len); #define NAND_CMD_RNDOUTSTART 0xE0 #define NAND_CMD_CACHEDPROG 0x15 -/* Extended commands for AG-AND device */ -/* - * Note: the command for NAND_CMD_DEPLETE1 is really 0x00 but - * there is no way to distinguish that from NAND_CMD_READ0 - * until the remaining sequence of commands has been completed - * so add a high order bit and mask it off in the command. - */ -#define NAND_CMD_DEPLETE1 0x100 -#define NAND_CMD_DEPLETE2 0x38 -#define NAND_CMD_STATUS_MULTI 0x71 -#define NAND_CMD_STATUS_ERROR 0x72 -/* multi-bank error status (banks 0-3) */ -#define NAND_CMD_STATUS_ERROR0 0x73 -#define NAND_CMD_STATUS_ERROR1 0x74 -#define NAND_CMD_STATUS_ERROR2 0x75 -#define NAND_CMD_STATUS_ERROR3 0x76 -#define NAND_CMD_STATUS_RESET 0x7f -#define NAND_CMD_STATUS_CLEAR 0xff - #define NAND_CMD_NONE -1 /* Status bits */ -- cgit v1.2.3 From 96dca4c29c5e4fc158f8f31513994408c90c6818 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Mon, 4 Mar 2013 14:50:43 +0200 Subject: mtd: nand: remove NAND_NO_PADDING macro It is not used anywhere. Signed-off-by: Artem Bityutskiy Acked-by: Brian Norris Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index e5d6160a4511..10fd7df07b5e 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -145,8 +145,6 @@ typedef enum { */ /* Buswidth is 16 bit */ #define NAND_BUSWIDTH_16 0x00000002 -/* Device supports partial programming without padding */ -#define NAND_NO_PADDING 0x00000004 /* Chip has cache program function */ #define NAND_CACHEPRG 0x00000008 /* Chip has copy back function */ @@ -171,11 +169,9 @@ typedef enum { #define NAND_SUBPAGE_READ 0x00001000 /* Options valid for Samsung large page devices */ -#define NAND_SAMSUNG_LP_OPTIONS \ - (NAND_NO_PADDING | NAND_CACHEPRG | NAND_COPYBACK) +#define NAND_SAMSUNG_LP_OPTIONS (NAND_CACHEPRG | NAND_COPYBACK) /* Macros to identify the above */ -#define NAND_MUST_PAD(chip) (!(chip->options & NAND_NO_PADDING)) #define NAND_HAS_CACHEPROG(chip) ((chip->options & NAND_CACHEPRG)) #define NAND_HAS_COPYBACK(chip) ((chip->options & NAND_COPYBACK)) #define NAND_HAS_SUBPAGE_READ(chip) ((chip->options & NAND_SUBPAGE_READ)) -- cgit v1.2.3 From 88ad4b162adb3821815d0098987040fca26c7d80 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Mon, 4 Mar 2013 14:52:25 +0200 Subject: mtd: nand: remove NAND_COPYBACK macro It is unused. Signed-off-by: Artem Bityutskiy Acked-by: Brian Norris Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 10fd7df07b5e..ec0a74877714 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -147,8 +147,6 @@ typedef enum { #define NAND_BUSWIDTH_16 0x00000002 /* Chip has cache program function */ #define NAND_CACHEPRG 0x00000008 -/* Chip has copy back function */ -#define NAND_COPYBACK 0x00000010 /* * Chip requires ready check on read (for auto-incremented sequential read). * True only for small page devices; large page devices do not support @@ -169,11 +167,10 @@ typedef enum { #define NAND_SUBPAGE_READ 0x00001000 /* Options valid for Samsung large page devices */ -#define NAND_SAMSUNG_LP_OPTIONS (NAND_CACHEPRG | NAND_COPYBACK) +#define NAND_SAMSUNG_LP_OPTIONS (NAND_CACHEPRG) /* Macros to identify the above */ #define NAND_HAS_CACHEPROG(chip) ((chip->options & NAND_CACHEPRG)) -#define NAND_HAS_COPYBACK(chip) ((chip->options & NAND_COPYBACK)) #define NAND_HAS_SUBPAGE_READ(chip) ((chip->options & NAND_SUBPAGE_READ)) /* Non chip related options */ -- cgit v1.2.3 From 3239a6cdef0be60ec2dadc501cf385dc419d7452 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Mon, 4 Mar 2013 14:56:18 +0200 Subject: mtd: nand: use NAND_HAS_CACHEPROG We have this unused macro, let's use it and justify its existence. Signed-off-by: Artem Bityutskiy Acked-by: Brian Norris Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index ec0a74877714..07d7a3dc5582 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -167,7 +167,7 @@ typedef enum { #define NAND_SUBPAGE_READ 0x00001000 /* Options valid for Samsung large page devices */ -#define NAND_SAMSUNG_LP_OPTIONS (NAND_CACHEPRG) +#define NAND_SAMSUNG_LP_OPTIONS NAND_CACHEPRG /* Macros to identify the above */ #define NAND_HAS_CACHEPROG(chip) ((chip->options & NAND_CACHEPRG)) -- cgit v1.2.3 From 68aa352de28235bccdcee96ddf49f7628e93ec6f Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Mon, 4 Mar 2013 16:05:00 +0200 Subject: mtd: nand: rename the id field of 'struct nand_flash_dev' The 'id' is a bit confusing name because NAND IDs are multi-byte. Re-name it to 'dev_id' to make it clear that this is the "device ID" part (the second byte). While on it, clean-up the commentary for 'struct nand_flash_dev'. Signed-off-by: Artem Bityutskiy Acked-by: Brian Norris Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 07d7a3dc5582..9aed31a49af1 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -548,19 +548,18 @@ struct nand_chip { /** * struct nand_flash_dev - NAND Flash Device ID Structure - * @name: Identify the device type - * @id: device ID code - * @pagesize: Pagesize in bytes. Either 256 or 512 or 0 - * If the pagesize is 0, then the real pagesize - * and the eraseize are determined from the - * extended id bytes in the chip - * @erasesize: Size of an erase block in the flash device. - * @chipsize: Total chipsize in Mega Bytes - * @options: Bitfield to store chip relevant options + * @name: a human-readable name of the NAND chip + * @dev_id: the device ID (the second byte of the full chip ID array) + * @pagesize: size of the NAND page in bytes; if 0, then the real page size (as + * well as the eraseblock size) is determined from the extended NAND + * chip ID array) + * @erasesize: eraseblock size in bytes (determined from the extended ID if 0) + * @chipsize: total chip size in MiB + * @options: stores various chip bit options */ struct nand_flash_dev { char *name; - int id; + int dev_id; unsigned long pagesize; unsigned long chipsize; unsigned long erasesize; -- cgit v1.2.3 From 8dbfae1ef04311ba19d6b6c9a4d8fdddbb90ab0f Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Mon, 4 Mar 2013 15:39:18 +0200 Subject: mtd: nand_ids: introduce helper macros Introduce helper macros for defining NAND chips. These macros do not really add much value in the current code-base. However, we are going to add full ID support which adds some more complexity to the table, and helper macros become useful for readability. Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 9aed31a49af1..63b319a6f98c 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -546,6 +546,30 @@ struct nand_chip { #define NAND_MFR_MACRONIX 0xc2 #define NAND_MFR_EON 0x92 +/* + * A helper for defining older NAND chips where the second ID byte fully + * defined the chip, including the geometry (chip size, eraseblock size, page + * size). + */ +#define LEGACY_ID_NAND(nm, devid, pagesz, chipsz, erasesz, opts) \ + { .name = (nm), .dev_id = (devid), .pagesize = (pagesz), \ + .chipsize = (chipsz), .erasesize = (erasesz), \ + .options = (opts) } + +/* + * A helper for defining newer chips which report their page size and + * eraseblock size via the extended ID bytes. + * + * The real difference between LEGACY_ID_NAND and EXTENDED_ID_NAND is that with + * EXTENDED_ID_NAND, manufacturers overloaded the same device ID so that the + * device ID now only represented a particular total chip size (and voltage, + * buswidth), and the page size, eraseblock size, and OOB size could vary while + * using the same device ID. + */ +#define EXTENDED_ID_NAND(nm, devid, chipsz, opts) \ + { .name = (nm), .dev_id = (devid), .chipsize = (chipsz), \ + .options = (opts) } + /** * struct nand_flash_dev - NAND Flash Device ID Structure * @name: a human-readable name of the NAND chip -- cgit v1.2.3 From 8e12b474f9a2349bcaebda65bdc38e8398ff408e Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Mon, 4 Mar 2013 16:26:56 +0200 Subject: mtd: nand: provision full ID support Up until now we identified NAND chips by the 'device ID' part of the full chip ID array, which is the second full ID array byte. However, the newest flashes use the same device ID for chips with identical page and eraseblock sizes, but different OOB sizes. And unfortunately, it is not clear if there is a "standard" way to fetch the OOB size from chip's full ID array. Here is an example: Toshiba TC58NVG2S0F: 0x98, 0xdc, 0x90, 0x26, 0x76, 0x15, 0x01, 0x08 Toshiba TC58NVG3S0F: 0x98, 0xd3, 0x90, 0x26, 0x76, 0x15, 0x02, 0x08 The first one is a 512MiB NAND chip with 4KiB NAND pages, 256KiB eraseblock size and 224 bytes OOB. The second one is a 1GiB NAND chip with the same page and eraseblock sizes, but with 232 bytes OOB. This means that we have to store full ID in our NAND flashes table in order to distinguish between these 2. This patch adds the 'id[8]' field to the 'struct nand_flash_dev' structure, and it makes it to be a part of anonymous union, where the second member is a structure containing the 'mfr_id' and 'dev_id' bytes. The union makes sure that 'mfr_id' refers the same RAM address as 'id[0]' and 'dev_id' refers the same RAM address as 'id[1]'. The only motivation for the union is an assumption that 'type->dev_id' is more readable than 'type->id[1]'. Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 23 +++++++++++++++++------ 1 file changed, 17 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 63b319a6f98c..9a1b74c85044 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -551,9 +551,9 @@ struct nand_chip { * defined the chip, including the geometry (chip size, eraseblock size, page * size). */ -#define LEGACY_ID_NAND(nm, devid, pagesz, chipsz, erasesz, opts) \ - { .name = (nm), .dev_id = (devid), .pagesize = (pagesz), \ - .chipsize = (chipsz), .erasesize = (erasesz), \ +#define LEGACY_ID_NAND(nm, devid, pagesz, chipsz, erasesz, opts) \ + { .name = (nm), {{ .dev_id = (devid) }}, .pagesize = (pagesz), \ + .chipsize = (chipsz), .erasesize = (erasesz), \ .options = (opts) } /* @@ -566,14 +566,19 @@ struct nand_chip { * buswidth), and the page size, eraseblock size, and OOB size could vary while * using the same device ID. */ -#define EXTENDED_ID_NAND(nm, devid, chipsz, opts) \ - { .name = (nm), .dev_id = (devid), .chipsize = (chipsz), \ +#define EXTENDED_ID_NAND(nm, devid, chipsz, opts) \ + { .name = (nm), {{ .dev_id = (devid) }}, .chipsize = (chipsz), \ .options = (opts) } /** * struct nand_flash_dev - NAND Flash Device ID Structure * @name: a human-readable name of the NAND chip * @dev_id: the device ID (the second byte of the full chip ID array) + * @mfr_id: manufecturer ID part of the full chip ID array (refers the same + * memory address as @id[0]) + * @dev_id: device ID part of the full chip ID array (refers the same memory + * address as @id[1]) + * @id: full device ID array * @pagesize: size of the NAND page in bytes; if 0, then the real page size (as * well as the eraseblock size) is determined from the extended NAND * chip ID array) @@ -583,7 +588,13 @@ struct nand_chip { */ struct nand_flash_dev { char *name; - int dev_id; + union { + struct { + uint8_t mfr_id; + uint8_t dev_id; + }; + uint8_t id[8]; + }; unsigned long pagesize; unsigned long chipsize; unsigned long erasesize; -- cgit v1.2.3 From ad2457894c272279bf73ca46ae5ea5de4876d2a0 Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Mon, 4 Mar 2013 00:57:20 +0100 Subject: mtd: devices: elm: check for device's presence before configuration In case the driver is not probed - due to config mismatches or errors in the DTS files - dev_get_drvdata() returns NULL, leading to an Ooops during boot. Make elm_config() return an error in such cases to propagate the error up to the user, so it can fall back to software mode. Signed-off-by: Daniel Mack Acked-by: Peter Korsgaard Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/platform_data/elm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/platform_data/elm.h b/include/linux/platform_data/elm.h index 1bd5244d1dcd..bf0a83b7ed9d 100644 --- a/include/linux/platform_data/elm.h +++ b/include/linux/platform_data/elm.h @@ -50,5 +50,5 @@ struct elm_errorvec { void elm_decode_bch_error_page(struct device *dev, u8 *ecc_calc, struct elm_errorvec *err_vec); -void elm_config(struct device *dev, enum bch_ecc bch_type); +int elm_config(struct device *dev, enum bch_ecc bch_type); #endif /* __ELM_H */ -- cgit v1.2.3 From 26a4734623e4f06752014336b05cf3ae77158892 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Mon, 11 Mar 2013 15:38:48 +0200 Subject: mtd: add 'const' qualifier to a couple of register functions 'mtd_device_parse_register()' and 'parse_mtd_partitions()' functions accept a an array of character pointers. These functions modify neither the pointers nor the characters they point to. The characters are actually names of the MTD parsers. At the moment, the argument type is 'const char **', which means that only the names of the parsers are constant. Let's turn the argument type into 'const char * const *', which means that both names and the pointers which point to them are constant. Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/mtd/mtd.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index f9ac2897b86b..a5cf4e8d6818 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -362,10 +362,10 @@ struct mtd_partition; struct mtd_part_parser_data; extern int mtd_device_parse_register(struct mtd_info *mtd, - const char **part_probe_types, - struct mtd_part_parser_data *parser_data, - const struct mtd_partition *defparts, - int defnr_parts); + const char * const *part_probe_types, + struct mtd_part_parser_data *parser_data, + const struct mtd_partition *defparts, + int defnr_parts); #define mtd_device_register(master, parts, nr_parts) \ mtd_device_parse_register(master, NULL, NULL, parts, nr_parts) extern int mtd_device_unregister(struct mtd_info *master); -- cgit v1.2.3 From d50dcb1d0e1f8ebe11db1719aad5753cd1b4c4f8 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Tue, 12 Mar 2013 10:28:31 +0200 Subject: mtd: plat-ram: add const quilifiers Be a bit stricter and add few more 'const' qualifiers. Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/mtd/plat-ram.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mtd/plat-ram.h b/include/linux/mtd/plat-ram.h index e07890aff1cf..44212d65aa97 100644 --- a/include/linux/mtd/plat-ram.h +++ b/include/linux/mtd/plat-ram.h @@ -20,8 +20,8 @@ struct platdata_mtd_ram { const char *mapname; - const char **map_probes; - const char **probes; + const char * const *map_probes; + const char * const *probes; struct mtd_partition *partitions; int nr_partitions; int bankwidth; -- cgit v1.2.3 From f39cf6c7d472349a9907955ef213db1f26618ba0 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Tue, 12 Mar 2013 10:32:52 +0200 Subject: mtd: physmap: add const qualifiers Be a bit stricter and add few more 'const' qualifiers. Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/mtd/physmap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mtd/physmap.h b/include/linux/mtd/physmap.h index d2887e76b7f6..aa6a2633c2da 100644 --- a/include/linux/mtd/physmap.h +++ b/include/linux/mtd/physmap.h @@ -30,7 +30,7 @@ struct physmap_flash_data { unsigned int pfow_base; char *probe_type; struct mtd_partition *parts; - const char **part_probe_types; + const char * const *part_probe_types; }; #endif /* __LINUX_MTD_PHYSMAP__ */ -- cgit v1.2.3 From ecb42fea59cf2d1e7160c5c7e707120e0e6714db Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Wed, 13 Mar 2013 13:45:00 +0200 Subject: mtd: nand: use more reasonable integer types Use 'unsigned int' instead of 'unsigned long' in the NAND chip description data structure, because 32-bits is more than enough for our purposes. We do not need 64-bits, which is what we end up on 64-bit architectures. We declare many instances of this data structure, so this should help saving some amount of memory. Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 9a1b74c85044..d5903c0a0fe7 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -582,8 +582,8 @@ struct nand_chip { * @pagesize: size of the NAND page in bytes; if 0, then the real page size (as * well as the eraseblock size) is determined from the extended NAND * chip ID array) - * @erasesize: eraseblock size in bytes (determined from the extended ID if 0) * @chipsize: total chip size in MiB + * @erasesize: eraseblock size in bytes (determined from the extended ID if 0) * @options: stores various chip bit options */ struct nand_flash_dev { @@ -595,10 +595,10 @@ struct nand_flash_dev { }; uint8_t id[8]; }; - unsigned long pagesize; - unsigned long chipsize; - unsigned long erasesize; - unsigned long options; + unsigned int pagesize; + unsigned int chipsize; + unsigned int erasesize; + unsigned int options; }; /** -- cgit v1.2.3 From 53552d22bfe1f83f69f18eddae2f1d96249440f3 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Thu, 14 Mar 2013 09:57:23 +0200 Subject: mtd: introduce a macro for max NAND ID sequence length Introduce a helpful macro for the maximum NAND ID sequence length instead of using the "8" magic number. Signed-off-by: Artem Bityutskiy Acked-by: Huang Shijie Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index d5903c0a0fe7..0f78d19303c5 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -546,6 +546,9 @@ struct nand_chip { #define NAND_MFR_MACRONIX 0xc2 #define NAND_MFR_EON 0x92 +/* The maximum expected count of bytes in the NAND ID sequence */ +#define NAND_MAX_ID_LEN 8 + /* * A helper for defining older NAND chips where the second ID byte fully * defined the chip, including the geometry (chip size, eraseblock size, page @@ -593,7 +596,7 @@ struct nand_flash_dev { uint8_t mfr_id; uint8_t dev_id; }; - uint8_t id[8]; + uint8_t id[NAND_MAX_ID_LEN]; }; unsigned int pagesize; unsigned int chipsize; -- cgit v1.2.3 From f22d5f638b0ea40e7cceb4639a608bd2c3eff97c Mon Sep 17 00:00:00 2001 From: Huang Shijie Date: Fri, 15 Mar 2013 11:00:59 +0800 Subject: mtd: add new fields to nand_flash_dev{} As time goes on, we begin to meet the situation that we can not get enough information from some nand chips's id data. Take some Toshiba's nand chips for example. I have 4 Toshiba's nand chips in my hand: TC58NVG2S0F, TC58NVG3S0F, TC58NVG5D2, TC58NVG6D2 When we read these chips' datasheets, we will get the geometry of these chips: TC58NVG2S0F : 4096 + 224 TC58NVG3S0F : 4096 + 232 TC58NVG5D2 : 8192 + 640 TC58NVG6D2 : 8192 + 640 But we can not parse out the correct oob size for these chips from the id data. This patch adds some new fields to the nand_flash_dev{}: @id_len: the valid length of the id data. See the comments in nand_id_has_period() @oobsize: the oob size. Signed-off-by: Huang Shijie Reviewed-by: Brian Norris Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 0f78d19303c5..13786f0ae12a 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -588,6 +588,8 @@ struct nand_chip { * @chipsize: total chip size in MiB * @erasesize: eraseblock size in bytes (determined from the extended ID if 0) * @options: stores various chip bit options + * @id_len: The valid length of the @id. + * @oobsize: OOB size */ struct nand_flash_dev { char *name; @@ -602,6 +604,8 @@ struct nand_flash_dev { unsigned int chipsize; unsigned int erasesize; unsigned int options; + uint16_t id_len; + uint16_t oobsize; }; /** -- cgit v1.2.3 From 5bfa9b71a2d6642506e2dfdf49a66620f54f1d92 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Tue, 19 Mar 2013 10:29:26 +0200 Subject: mtd: nand_ids: improve LEGACY_ID_NAND macro a bit Notice that all the flashes belonging to the "legacy ID" class have 512 bytes NAND page. This means we may simplify the 'LEGACY_ID_NAND()' macro as well as the NAND ID table a little. Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 13786f0ae12a..ebf970e11428 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -552,12 +552,11 @@ struct nand_chip { /* * A helper for defining older NAND chips where the second ID byte fully * defined the chip, including the geometry (chip size, eraseblock size, page - * size). + * size). All these chips have 512 bytes NAND page size. */ -#define LEGACY_ID_NAND(nm, devid, pagesz, chipsz, erasesz, opts) \ - { .name = (nm), {{ .dev_id = (devid) }}, .pagesize = (pagesz), \ - .chipsize = (chipsz), .erasesize = (erasesz), \ - .options = (opts) } +#define LEGACY_ID_NAND(nm, devid, chipsz, erasesz, opts) \ + { .name = (nm), {{ .dev_id = (devid) }}, .pagesize = 512, \ + .chipsize = (chipsz), .erasesize = (erasesz), .options = (opts) } /* * A helper for defining newer chips which report their page size and -- cgit v1.2.3 From 837a6ba4f3b6d23026674e6af6b6849a4634fff9 Mon Sep 17 00:00:00 2001 From: "Gupta, Pekon" Date: Fri, 15 Mar 2013 17:55:53 +0530 Subject: mtd: nand: subpage write support for hardware based ECC schemes This patch adds support for subpage (partial-page) writes when using hardware based ECC schemes. Advantages: (1) reduces storage overhead when using file-systems like UBIFS, which store LEB header at page-size granularity. (2) allows independent subpage writes, thereby increasing NAND storage efficiency for non-page aligned data. + updated cafe_nand and lpc32xx_mlc NAND drivers for change in chip->write_page interface. Signed-off-by: Gupta, Pekon Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index ebf970e11428..ab6363443ce8 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -318,6 +318,7 @@ struct nand_hw_control { * any single ECC step, 0 if bitflips uncorrectable, -EIO hw error * @read_subpage: function to read parts of the page covered by ECC; * returns same as read_page() + * @write_subpage: function to write parts of the page covered by ECC. * @write_page: function to write a page according to the ECC generator * requirements. * @write_oob_raw: function to write chip OOB data without ECC @@ -349,6 +350,9 @@ struct nand_ecc_ctrl { uint8_t *buf, int oob_required, int page); int (*read_subpage)(struct mtd_info *mtd, struct nand_chip *chip, uint32_t offs, uint32_t len, uint8_t *buf); + int (*write_subpage)(struct mtd_info *mtd, struct nand_chip *chip, + uint32_t offset, uint32_t data_len, + const uint8_t *data_buf, int oob_required); int (*write_page)(struct mtd_info *mtd, struct nand_chip *chip, const uint8_t *buf, int oob_required); int (*write_oob_raw)(struct mtd_info *mtd, struct nand_chip *chip, @@ -484,8 +488,8 @@ struct nand_chip { int (*errstat)(struct mtd_info *mtd, struct nand_chip *this, int state, int status, int page); int (*write_page)(struct mtd_info *mtd, struct nand_chip *chip, - const uint8_t *buf, int oob_required, int page, - int cached, int raw); + uint32_t offset, int data_len, const uint8_t *buf, + int oob_required, int page, int cached, int raw); int (*onfi_set_features)(struct mtd_info *mtd, struct nand_chip *chip, int feature_addr, uint8_t *subfeature_para); int (*onfi_get_features)(struct mtd_info *mtd, struct nand_chip *chip, -- cgit v1.2.3 From 5ab3a89a741fa4c331f42dec17fde59586dc59e6 Mon Sep 17 00:00:00 2001 From: Alexander Shiyan Date: Wed, 13 Mar 2013 21:34:20 +0400 Subject: mfd: syscon: Add non-DT support This patch allow using syscon driver from the platform data, i.e. possibility using driver on systems without oftree support. For search syscon device from the client drivers, "syscon_regmap_lookup_by_pdevname" function was added. Signed-off-by: Alexander Shiyan Acked-by: Arnd Bergmann Signed-off-by: Samuel Ortiz --- include/linux/mfd/syscon.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mfd/syscon.h b/include/linux/mfd/syscon.h index 6aeb6b8da64d..5c9ee6ee7960 100644 --- a/include/linux/mfd/syscon.h +++ b/include/linux/mfd/syscon.h @@ -17,6 +17,7 @@ extern struct regmap *syscon_node_to_regmap(struct device_node *np); extern struct regmap *syscon_regmap_lookup_by_compatible(const char *s); +extern struct regmap *syscon_regmap_lookup_by_pdevname(const char *s); extern struct regmap *syscon_regmap_lookup_by_phandle( struct device_node *np, const char *property); -- cgit v1.2.3 From 446411e18b2cb17d153e45f634a3c9a79ada3ac2 Mon Sep 17 00:00:00 2001 From: Andreas Larsson Date: Wed, 13 Feb 2013 14:20:25 +0100 Subject: spi: Initialize cs_gpio and cs_gpios with -ENOENT The return value from of_get_named_gpio is -ENOENT when the given index matches a hole in the "cs-gpios" property phandle list. However, the default value of cs_gpio in struct spi_device and entries of cs_gpios in struct spi_master is -EINVAL, which is documented to indicate that a GPIO line should not be used for the given spi_device. This sets the default value of cs_gpio in struct spi_device and entries of cs_gpios in struct spi_master to -ENOENT. Thus, -ENOENT is the only value used to indicate that no GPIO line should be used. Signed-off-by: Andreas Larsson Signed-off-by: Grant Likely --- include/linux/spi/spi.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 38c2b925923d..c395f32b53b3 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -57,7 +57,7 @@ extern struct bus_type spi_bus_type; * @modalias: Name of the driver to use with this device, or an alias * for that name. This appears in the sysfs "modalias" attribute * for driver coldplugging, and in uevents used for hotplugging - * @cs_gpio: gpio number of the chipselect line (optional, -EINVAL when + * @cs_gpio: gpio number of the chipselect line (optional, -ENOENT when * when not using a GPIO line) * * A @spi_device is used to interchange data between an SPI slave @@ -261,7 +261,7 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * queue so the subsystem notifies the driver that it may relax the * hardware by issuing this call * @cs_gpios: Array of GPIOs to use as chip select lines; one per CS - * number. Any individual value may be -EINVAL for CS lines that + * number. Any individual value may be -ENOENT for CS lines that * are not GPIOs (driven by the SPI controller itself). * * Each SPI master controller can communicate with one or more @spi_device -- cgit v1.2.3 From a2b950ac7b1e6442919ee9e79c4963e134698869 Mon Sep 17 00:00:00 2001 From: Ohad Ben-Cohen Date: Sun, 7 Apr 2013 14:06:07 +0300 Subject: remoteproc: perserve resource table data MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Copy resource table from first to second firmware loading. After firmware is loaded to memory, update the vdevs resource pointer to the resource table kept in device memory. Signed-off-by: Sjur Brændeland Acked-by: Ido Yariv [rebase, terminology and style changes] Signed-off-by: Ohad Ben-Cohen --- include/linux/remoteproc.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index faf33324c78f..b4cef16460f8 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -401,6 +401,9 @@ enum rproc_crash_type { * @crash_comp: completion used to sync crash handler and the rproc reload * @recovery_disabled: flag that state if recovery was disabled * @max_notifyid: largest allocated notify id. + * @table_ptr: pointer to the resource table in effect + * @cached_table: copy of the resource table + * @table_csum: checksum of the resource table */ struct rproc { struct klist_node node; @@ -429,9 +432,13 @@ struct rproc { struct completion crash_comp; bool recovery_disabled; int max_notifyid; + struct resource_table *table_ptr; + struct resource_table *cached_table; + u32 table_csum; }; /* we currently support only two vrings per rvdev */ + #define RVDEV_NUM_VRINGS 2 /** @@ -464,6 +471,7 @@ struct rproc_vring { * @vring: the vrings for this vdev * @dfeatures: virtio device features * @gfeatures: virtio guest features + * @rsc_offset: offset of the vdev's resource entry */ struct rproc_vdev { struct list_head node; @@ -472,6 +480,7 @@ struct rproc_vdev { struct rproc_vring vring[RVDEV_NUM_VRINGS]; unsigned long dfeatures; unsigned long gfeatures; + u32 rsc_offset; }; struct rproc *rproc_alloc(struct device *dev, const char *name, -- cgit v1.2.3 From 92b38f851470f8d8ea7ed638d546f83b5268bc12 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sjur=20Br=C3=A6ndeland?= Date: Thu, 21 Feb 2013 18:15:39 +0100 Subject: remoteproc: support virtio config space. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Support virtio configuration space and device status. The virtio device can now access the resource table in shared memory. Signed-off-by: Sjur Brændeland Acked-by: Ido Yariv [rebase and style changes] Signed-off-by: Ohad Ben-Cohen --- include/linux/remoteproc.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index b4cef16460f8..9e7e745dac55 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -469,8 +469,6 @@ struct rproc_vring { * @rproc: the rproc handle * @vdev: the virio device * @vring: the vrings for this vdev - * @dfeatures: virtio device features - * @gfeatures: virtio guest features * @rsc_offset: offset of the vdev's resource entry */ struct rproc_vdev { @@ -478,8 +476,6 @@ struct rproc_vdev { struct rproc *rproc; struct virtio_device vdev; struct rproc_vring vring[RVDEV_NUM_VRINGS]; - unsigned long dfeatures; - unsigned long gfeatures; u32 rsc_offset; }; -- cgit v1.2.3 From fc1b74925f87f6aca5432eb73f6a57eff30afde7 Mon Sep 17 00:00:00 2001 From: Geoff Levand Date: Fri, 5 Apr 2013 19:20:30 +0000 Subject: KVM: Move vm_list kvm_lock declarations out of x86 The variables vm_list and kvm_lock are common to all architectures, so move the declarations from arch/x86/include/asm/kvm_host.h to include/linux/kvm_host.h. Fixes sparse warnings like these when building for arm64: virt/kvm/kvm_main.c: warning: symbol 'kvm_lock' was not declared. Should it be static? virt/kvm/kvm_main.c: warning: symbol 'vm_list' was not declared. Should it be static? Signed-off-by: Geoff Levand Signed-off-by: Gleb Natapov --- include/linux/kvm_host.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 1c0be23f874d..71fed38c7200 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -135,6 +135,9 @@ struct kvm; struct kvm_vcpu; extern struct kmem_cache *kvm_vcpu_cache; +extern raw_spinlock_t kvm_lock; +extern struct list_head vm_list; + struct kvm_io_range { gpa_t addr; int len; -- cgit v1.2.3 From 8b415dcd762607379cf0a69c9dd25940da1d174e Mon Sep 17 00:00:00 2001 From: Geoff Levand Date: Fri, 5 Apr 2013 19:20:30 +0000 Subject: KVM: Move kvm_rebooting declaration out of x86 The variable kvm_rebooting is a common kvm variable, so move its declaration from arch/x86/include/asm/kvm_host.h to include/asm/kvm_host.h. Fixes this sparse warning when building on arm64: virt/kvm/kvm_main.c:warning: symbol 'kvm_rebooting' was not declared. Should it be static? Signed-off-by: Geoff Levand Signed-off-by: Gleb Natapov --- include/linux/kvm_host.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 71fed38c7200..20d77d24d764 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1061,6 +1061,8 @@ static inline bool kvm_check_request(int req, struct kvm_vcpu *vcpu) } } +extern bool kvm_rebooting; + #ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT static inline void kvm_vcpu_set_in_spin_loop(struct kvm_vcpu *vcpu, bool val) -- cgit v1.2.3 From f8a0941f1bbdbaa68441142675986501b48da8f5 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Fri, 22 Mar 2013 12:59:33 +0100 Subject: mfd: arizona: Basic support for edge triggered IRQs Allow the user to configure edge triggered IRQs, though we do not yet fully handle new interrupts occurring while an interrupt is being handled. Signed-off-by: Mark Brown Signed-off-by: Samuel Ortiz --- include/linux/mfd/arizona/pdata.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mfd/arizona/pdata.h b/include/linux/mfd/arizona/pdata.h index 455c51d22d6b..84fefede3a23 100644 --- a/include/linux/mfd/arizona/pdata.h +++ b/include/linux/mfd/arizona/pdata.h @@ -99,7 +99,8 @@ struct arizona_pdata { /** If a direct 32kHz clock is provided on an MCLK specify it here */ int clk32k_src; - bool irq_active_high; /** IRQ polarity */ + /** Mode for primary IRQ (defaults to active low) */ + unsigned int irq_flags; /* Base GPIO */ int gpio_base; -- cgit v1.2.3 From 3092f8050eccce8463afe771f0910634a433e24b Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Sun, 24 Mar 2013 23:05:58 +0000 Subject: mfd: arizona: Allow GPIO to be specified for IRQ line If a GPIO is specified for the chip IRQ line then request it. This improves support for systems that do not put pins into input mode when used as interrupts. Also use this GPIO when the primary IRQ is in edge triggered mode to detect if we have handled pending interrupts in order to improve robustness. Signed-off-by: Mark Brown Signed-off-by: Samuel Ortiz --- include/linux/mfd/arizona/pdata.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/mfd/arizona/pdata.h b/include/linux/mfd/arizona/pdata.h index 84fefede3a23..8755dd05ab78 100644 --- a/include/linux/mfd/arizona/pdata.h +++ b/include/linux/mfd/arizona/pdata.h @@ -163,6 +163,9 @@ struct arizona_pdata { /** Haptic actuator type */ unsigned int hap_act; + + /** GPIO for primary IRQ (used for edge triggered emulation) */ + int irq_gpio; }; #endif -- cgit v1.2.3 From 544c7aadd7d4309ed01fcd787d393db67eb7eaea Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 29 Jan 2013 18:44:41 +0800 Subject: mfd: arizona: Support configuring MICBIASes into bypass mode Signed-off-by: Mark Brown Signed-off-by: Samuel Ortiz --- include/linux/mfd/arizona/pdata.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mfd/arizona/pdata.h b/include/linux/mfd/arizona/pdata.h index 8755dd05ab78..554d903cdf41 100644 --- a/include/linux/mfd/arizona/pdata.h +++ b/include/linux/mfd/arizona/pdata.h @@ -78,6 +78,7 @@ struct arizona_micbias { unsigned int ext_cap:1; /** External capacitor fitted */ unsigned int discharge:1; /** Actively discharge */ unsigned int fast_start:1; /** Enable aggressive startup ramp rate */ + unsigned int bypass:1; /** Use bypass mode */ }; struct arizona_micd_config { -- cgit v1.2.3 From a5055d5d683605210f77d46614bbdb389c1e4a07 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Fri, 15 Feb 2013 23:56:49 +0100 Subject: mfd: twl4030-madc: Add support for raw value in twl4030_madc_conversion MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Driver twl4030-madc has hardcoded channel types (10 - battery current, 1 - battery temperature) and also conversation data in variable twl4030_divider_ratios. These hardcoded channels are incorrect for Nokia RX-51 board (where is channel 0 - battery temperature). For Nokia RX-51 there is rx51_battery power_supply driver which reporting battery information via twl4030_madc_conversion. But this driver needs raw values (not converted via some hardcoded functions). So this patch adding new parameter "raw" to struct twl4030_madc_request which tell twl4030-madc driver to not convert values, but rather return raw. Signed-off-by: Pali Rohár Reviewed-by: Anton Vorontsov Signed-off-by: Samuel Ortiz --- include/linux/i2c/twl4030-madc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/i2c/twl4030-madc.h b/include/linux/i2c/twl4030-madc.h index 530e11ba0738..01f595107048 100644 --- a/include/linux/i2c/twl4030-madc.h +++ b/include/linux/i2c/twl4030-madc.h @@ -39,6 +39,7 @@ struct twl4030_madc_conversion_method { * @do_avgP: sample the input channel for 4 consecutive cycles * @method: RT, SW1, SW2 * @type: Polling or interrupt based method + * @raw: Return raw value, do not convert it */ struct twl4030_madc_request { @@ -48,6 +49,7 @@ struct twl4030_madc_request { u16 type; bool active; bool result_pending; + bool raw; int rbuf[TWL4030_MADC_MAX_CHANNELS]; void (*func_cb)(int len, int channels, int *buf); }; -- cgit v1.2.3 From 654003e98213991e4d534487907baad2afd9828d Mon Sep 17 00:00:00 2001 From: Ian Lartey Date: Fri, 22 Mar 2013 14:55:12 +0000 Subject: mfd: palmas: is_palmas_charger needed by multiple drivers is_palmas_charger checks for the presence of charging functionality in the device Signed-off-by: Graeme Gregory Signed-off-by: Ian Lartey Acked-by: Laxman Dewangani Signed-off-by: Samuel Ortiz --- include/linux/mfd/palmas.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mfd/palmas.h b/include/linux/mfd/palmas.h index 3bbda22721ea..4a066d0caf44 100644 --- a/include/linux/mfd/palmas.h +++ b/include/linux/mfd/palmas.h @@ -1,9 +1,10 @@ /* * TI Palmas * - * Copyright 2011 Texas Instruments Inc. + * Copyright 2011-2013 Texas Instruments Inc. * * Author: Graeme Gregory + * Author: Ian Lartey * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License as published by the @@ -22,6 +23,15 @@ #define PALMAS_NUM_CLIENTS 3 +/* The ID_REVISION NUMBERS */ +#define PALMAS_CHIP_OLD_ID 0x0000 +#define PALMAS_CHIP_ID 0xC035 +#define PALMAS_CHIP_CHARGER_ID 0xC036 + +#define is_palmas(a) (((a) == PALMAS_CHIP_OLD_ID) || \ + ((a) == PALMAS_CHIP_ID)) +#define is_palmas_charger(a) ((a) == PALMAS_CHIP_CHARGER_ID) + struct palmas_pmic; struct palmas_gpadc; struct palmas_resource; -- cgit v1.2.3 From 751391c74f3d41a8d5c5dd5100385f723660c368 Mon Sep 17 00:00:00 2001 From: Rhyland Klein Date: Tue, 12 Mar 2013 18:08:06 -0400 Subject: mfd: tps65090: Fix enum in header file The enum is missing the definition for the first bit, which makes all the rest off by one. Add definition for the TPS65090_IRQ_INTERRUPT bit which at 0. Signed-off-by: Rhyland Klein Signed-off-by: Samuel Ortiz --- include/linux/mfd/tps65090.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mfd/tps65090.h b/include/linux/mfd/tps65090.h index 6694cf43e8b8..9ce231fda74f 100644 --- a/include/linux/mfd/tps65090.h +++ b/include/linux/mfd/tps65090.h @@ -27,6 +27,7 @@ /* TPS65090 IRQs */ enum { + TPS65090_IRQ_INTERRUPT, TPS65090_IRQ_VAC_STATUS_CHANGE, TPS65090_IRQ_VSYS_STATUS_CHANGE, TPS65090_IRQ_BAT_STATUS_CHANGE, -- cgit v1.2.3 From 57e1b48805a92304e4f50ebf5b885e627731a444 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Wed, 6 Mar 2013 14:28:13 +0800 Subject: mfd: arizona: Define additional FLL control registers Signed-off-by: Mark Brown Signed-off-by: Samuel Ortiz --- include/linux/mfd/arizona/registers.h | 40 +++++++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+) (limited to 'include') diff --git a/include/linux/mfd/arizona/registers.h b/include/linux/mfd/arizona/registers.h index 340355136069..a61ce90ecd3f 100644 --- a/include/linux/mfd/arizona/registers.h +++ b/include/linux/mfd/arizona/registers.h @@ -85,12 +85,14 @@ #define ARIZONA_FLL1_CONTROL_6 0x176 #define ARIZONA_FLL1_LOOP_FILTER_TEST_1 0x177 #define ARIZONA_FLL1_NCO_TEST_0 0x178 +#define ARIZONA_FLL1_CONTROL_7 0x179 #define ARIZONA_FLL1_SYNCHRONISER_1 0x181 #define ARIZONA_FLL1_SYNCHRONISER_2 0x182 #define ARIZONA_FLL1_SYNCHRONISER_3 0x183 #define ARIZONA_FLL1_SYNCHRONISER_4 0x184 #define ARIZONA_FLL1_SYNCHRONISER_5 0x185 #define ARIZONA_FLL1_SYNCHRONISER_6 0x186 +#define ARIZONA_FLL1_SYNCHRONISER_7 0x187 #define ARIZONA_FLL1_SPREAD_SPECTRUM 0x189 #define ARIZONA_FLL1_GPIO_CLOCK 0x18A #define ARIZONA_FLL2_CONTROL_1 0x191 @@ -101,12 +103,14 @@ #define ARIZONA_FLL2_CONTROL_6 0x196 #define ARIZONA_FLL2_LOOP_FILTER_TEST_1 0x197 #define ARIZONA_FLL2_NCO_TEST_0 0x198 +#define ARIZONA_FLL2_CONTROL_7 0x199 #define ARIZONA_FLL2_SYNCHRONISER_1 0x1A1 #define ARIZONA_FLL2_SYNCHRONISER_2 0x1A2 #define ARIZONA_FLL2_SYNCHRONISER_3 0x1A3 #define ARIZONA_FLL2_SYNCHRONISER_4 0x1A4 #define ARIZONA_FLL2_SYNCHRONISER_5 0x1A5 #define ARIZONA_FLL2_SYNCHRONISER_6 0x1A6 +#define ARIZONA_FLL2_SYNCHRONISER_7 0x1A7 #define ARIZONA_FLL2_SPREAD_SPECTRUM 0x1A9 #define ARIZONA_FLL2_GPIO_CLOCK 0x1AA #define ARIZONA_MIC_CHARGE_PUMP_1 0x200 @@ -1677,6 +1681,13 @@ #define ARIZONA_FLL1_FRC_INTEG_VAL_SHIFT 0 /* FLL1_FRC_INTEG_VAL - [11:0] */ #define ARIZONA_FLL1_FRC_INTEG_VAL_WIDTH 12 /* FLL1_FRC_INTEG_VAL - [11:0] */ +/* + * R377 (0x179) - FLL1 Control 7 + */ +#define ARIZONA_FLL1_GAIN_MASK 0x003c /* FLL1_GAIN */ +#define ARIZONA_FLL1_GAIN_SHIFT 2 /* FLL1_GAIN */ +#define ARIZONA_FLL1_GAIN_WIDTH 4 /* FLL1_GAIN */ + /* * R385 (0x181) - FLL1 Synchroniser 1 */ @@ -1723,6 +1734,17 @@ #define ARIZONA_FLL1_CLK_SYNC_SRC_SHIFT 0 /* FLL1_CLK_SYNC_SRC - [3:0] */ #define ARIZONA_FLL1_CLK_SYNC_SRC_WIDTH 4 /* FLL1_CLK_SYNC_SRC - [3:0] */ +/* + * R391 (0x187) - FLL1 Synchroniser 7 + */ +#define ARIZONA_FLL1_SYNC_GAIN_MASK 0x003c /* FLL1_SYNC_GAIN */ +#define ARIZONA_FLL1_SYNC_GAIN_SHIFT 2 /* FLL1_SYNC_GAIN */ +#define ARIZONA_FLL1_SYNC_GAIN_WIDTH 4 /* FLL1_SYNC_GAIN */ +#define ARIZONA_FLL1_SYNC_BW 0x0001 /* FLL1_SYNC_BW */ +#define ARIZONA_FLL1_SYNC_BW_MASK 0x0001 /* FLL1_SYNC_BW */ +#define ARIZONA_FLL1_SYNC_BW_SHIFT 0 /* FLL1_SYNC_BW */ +#define ARIZONA_FLL1_SYNC_BW_WIDTH 1 /* FLL1_SYNC_BW */ + /* * R393 (0x189) - FLL1 Spread Spectrum */ @@ -1815,6 +1837,13 @@ #define ARIZONA_FLL2_FRC_INTEG_VAL_SHIFT 0 /* FLL2_FRC_INTEG_VAL - [11:0] */ #define ARIZONA_FLL2_FRC_INTEG_VAL_WIDTH 12 /* FLL2_FRC_INTEG_VAL - [11:0] */ +/* + * R409 (0x199) - FLL2 Control 7 + */ +#define ARIZONA_FLL2_GAIN_MASK 0x003c /* FLL2_GAIN */ +#define ARIZONA_FLL2_GAIN_SHIFT 2 /* FLL2_GAIN */ +#define ARIZONA_FLL2_GAIN_WIDTH 4 /* FLL2_GAIN */ + /* * R417 (0x1A1) - FLL2 Synchroniser 1 */ @@ -1861,6 +1890,17 @@ #define ARIZONA_FLL2_CLK_SYNC_SRC_SHIFT 0 /* FLL2_CLK_SYNC_SRC - [3:0] */ #define ARIZONA_FLL2_CLK_SYNC_SRC_WIDTH 4 /* FLL2_CLK_SYNC_SRC - [3:0] */ +/* + * R423 (0x1A7) - FLL2 Synchroniser 7 + */ +#define ARIZONA_FLL2_SYNC_GAIN_MASK 0x003c /* FLL2_SYNC_GAIN */ +#define ARIZONA_FLL2_SYNC_GAIN_SHIFT 2 /* FLL2_SYNC_GAIN */ +#define ARIZONA_FLL2_SYNC_GAIN_WIDTH 4 /* FLL2_SYNC_GAIN */ +#define ARIZONA_FLL2_SYNC_BW_MASK 0x0001 /* FLL2_SYNC_BW */ +#define ARIZONA_FLL2_SYNC_BW_MASK 0x0001 /* FLL2_SYNC_BW */ +#define ARIZONA_FLL2_SYNC_BW_SHIFT 0 /* FLL2_SYNC_BW */ +#define ARIZONA_FLL2_SYNC_BW_WIDTH 1 /* FLL2_SYNC_BW */ + /* * R425 (0x1A9) - FLL2 Spread Spectrum */ -- cgit v1.2.3 From 5fb1c2dd8f9e9f3fd4ecbaefc75b83ab0ec40cfa Mon Sep 17 00:00:00 2001 From: Sylwester Nawrocki Date: Mon, 25 Mar 2013 17:56:23 +0100 Subject: mfd: syscon: Add missing struct device_node declaration MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit syscon.h header uses struct device_node in functions' declarations without declaring it. This causes compilation warnings like: include/linux/mfd/syscon.h:20: warning: ‘struct device_node’ declared inside parameter list include/linux/mfd/syscon.h:20: warning: its scope is only this definition or declaration, which is probably not what you want Fix it by adding a forward declaration of struct device_node. Signed-off-by: Sylwester Nawrocki Signed-off-by: Kyungmin Park Acked-by: Dong Aisheng Signed-off-by: Samuel Ortiz --- include/linux/mfd/syscon.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mfd/syscon.h b/include/linux/mfd/syscon.h index 5c9ee6ee7960..b473577f36db 100644 --- a/include/linux/mfd/syscon.h +++ b/include/linux/mfd/syscon.h @@ -15,6 +15,8 @@ #ifndef __LINUX_MFD_SYSCON_H__ #define __LINUX_MFD_SYSCON_H__ +struct device_node; + extern struct regmap *syscon_node_to_regmap(struct device_node *np); extern struct regmap *syscon_regmap_lookup_by_compatible(const char *s); extern struct regmap *syscon_regmap_lookup_by_pdevname(const char *s); -- cgit v1.2.3 From 230f13a5035fd4725a6623af83953623fd51173a Mon Sep 17 00:00:00 2001 From: Jean-Nicolas Graux Date: Tue, 9 Apr 2013 10:35:19 +0200 Subject: mfd: support stmpe1801 18 bits enhanced port expander Provides support for 1801 variant of stmpe gpio port expanders. This chip has 18 gpios configurable as GPI, GPO, keypad matrix, special key or dedicated key function. Note that special/dedicated key function is not supported yet. Signed-off-by: Jean-Nicolas Graux Acked-by: Linus Walleij Signed-off-by: Samuel Ortiz --- include/linux/mfd/stmpe.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/mfd/stmpe.h b/include/linux/mfd/stmpe.h index 383ac1512a39..48395a69a7e9 100644 --- a/include/linux/mfd/stmpe.h +++ b/include/linux/mfd/stmpe.h @@ -26,6 +26,7 @@ enum stmpe_partnum { STMPE801, STMPE811, STMPE1601, + STMPE1801, STMPE2401, STMPE2403, STMPE_NBR_PARTS @@ -39,6 +40,7 @@ enum { STMPE_IDX_CHIP_ID, STMPE_IDX_ICR_LSB, STMPE_IDX_IER_LSB, + STMPE_IDX_ISR_LSB, STMPE_IDX_ISR_MSB, STMPE_IDX_GPMR_LSB, STMPE_IDX_GPSR_LSB, @@ -49,6 +51,7 @@ enum { STMPE_IDX_GPFER_LSB, STMPE_IDX_GPAFR_U_MSB, STMPE_IDX_IEGPIOR_LSB, + STMPE_IDX_ISGPIOR_LSB, STMPE_IDX_ISGPIOR_MSB, STMPE_IDX_MAX, }; -- cgit v1.2.3 From d450f445f9a654080a6be4094376c2192d9a1f36 Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Tue, 19 Feb 2013 02:58:25 +0300 Subject: : fix compilation warnings with DT disabled MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix the following compilation warnings (in Simon Horman's renesas.git repo): In file included from arch/arm/mach-shmobile/setup-r8a7779.c:24:0: include/linux/of_platform.h:107:13: warning: ‘struct of_device_id’ declared inside parameter list [enabled by default] include/linux/of_platform.h:107:13: warning: its scope is only this definition or declaration, which is probably not what you want [enabled by default] include/linux/of_platform.h:107:13: warning: ‘struct device_node’ declared inside parameter list [enabled by default] only #include's headers with definitions of the above mentioned structures if CONFIG_OF_DEVICE=y but uses them even if not. One solution is to move some #include's out of #ifdef CONFIG_OF_DEVICE and use incomplete declarations for the rest of the structures where the #ifdef move doesn't help... Reported-by: Vladimir Barinov Signed-off-by: Sergei Shtylyov Signed-off-by: Rob Herring --- include/linux/of_platform.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h index 3863a4dbdf18..2a93b64a3869 100644 --- a/include/linux/of_platform.h +++ b/include/linux/of_platform.h @@ -11,9 +11,10 @@ * */ -#ifdef CONFIG_OF_DEVICE #include #include + +#ifdef CONFIG_OF_DEVICE #include #include #include @@ -100,7 +101,7 @@ extern int of_platform_populate(struct device_node *root, #if !defined(CONFIG_OF_ADDRESS) struct of_dev_auxdata; -struct device; +struct device_node; static inline int of_platform_populate(struct device_node *root, const struct of_device_id *matches, const struct of_dev_auxdata *lookup, -- cgit v1.2.3 From 066ec1dd44e84a911fe04556e4a9b89f1c83b0cb Mon Sep 17 00:00:00 2001 From: Alexander Shiyan Date: Tue, 9 Apr 2013 19:47:40 +0400 Subject: of: Add stub of_get_parent for non-OF builds Fixes build error on x86_64 allmodconfig, introduced by commit 5ab3a89a741f ("mfd: syscon: Add non-DT support"). drivers/regulator/anatop-regulator.c: In function 'anatop_regulator_probe': drivers/regulator/anatop-regulator.c:134:2: error: implicit declaration of function 'of_get_parent' [-Werror=implicit-function-declaration] Signed-off-by: Alexander Shiyan Acked-by: Rob Herring Signed-off-by: Samuel Ortiz --- include/linux/of.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/of.h b/include/linux/of.h index a0f129284948..9f5923fc0775 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -353,6 +353,11 @@ static inline struct device_node *of_find_node_by_name(struct device_node *from, return NULL; } +static inline struct device_node *of_get_parent(const struct device_node *node) +{ + return NULL; +} + static inline bool of_have_populated_dt(void) { return false; -- cgit v1.2.3 From cdee3904b4ce7c03d1013ed6dd704b43ae7fc2e9 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Wed, 9 Jan 2013 10:46:17 +1100 Subject: audit: Syscall rules are not applied to existing processes on non-x86 Commit b05d8447e782 (audit: inline audit_syscall_entry to reduce burden on archs) changed audit_syscall_entry to check for a dummy context before calling __audit_syscall_entry. Unfortunately the dummy context state is maintained in __audit_syscall_entry so once set it never gets cleared, even if the audit rules change. As a result, if there are no auditing rules when a process starts then it will never be subject to any rules added later. x86 doesn't see this because it has an assembly fast path that calls directly into __audit_syscall_entry. I noticed this issue when working on audit performance optimisations. I wrote a set of simple test cases available at: http://ozlabs.org/~anton/junkcode/audit_tests.tar.gz 02_new_rule.py fails without the patch and passes with it. The test case clears all rules, starts a process, adds a rule then verifies the process produces a syscall audit record. Signed-off-by: Anton Blanchard Cc: # 3.3+ Signed-off-by: Eric Paris --- include/linux/audit.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/audit.h b/include/linux/audit.h index 5a6d718adf34..37464c592c92 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -120,7 +120,7 @@ static inline void audit_syscall_entry(int arch, int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3) { - if (unlikely(!audit_dummy_context())) + if (unlikely(current->audit_context)) __audit_syscall_entry(arch, major, a0, a1, a2, a3); } static inline void audit_syscall_exit(void *pt_regs) -- cgit v1.2.3 From 2950fa9d3291b90e9b7663b6a409ea37a97a5e35 Mon Sep 17 00:00:00 2001 From: Chen Gang Date: Sun, 7 Apr 2013 16:55:23 +0800 Subject: kernel: audit: beautify code, for extern function, better to check its parameters by itself __audit_socketcall is an extern function. better to check its parameters by itself. also can return error code, when fail (find invalid parameters). also use macro instead of real hard code number also give related comments for it. Signed-off-by: Chen Gang [eparis: fix the return value when !CONFIG_AUDIT] Signed-off-by: Eric Paris --- include/linux/audit.h | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/audit.h b/include/linux/audit.h index 37464c592c92..8f92e1dea966 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -84,6 +84,9 @@ extern int audit_classify_arch(int arch); #define AUDIT_TYPE_CHILD_DELETE 3 /* a child being deleted */ #define AUDIT_TYPE_CHILD_CREATE 4 /* a child being created */ +/* maximized args number that audit_socketcall can process */ +#define AUDITSC_ARGS 6 + struct filename; #ifdef CONFIG_AUDITSYSCALL @@ -190,7 +193,7 @@ extern void audit_log_task_info(struct audit_buffer *ab, struct task_struct *tsk extern void __audit_ipc_obj(struct kern_ipc_perm *ipcp); extern void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode); extern int __audit_bprm(struct linux_binprm *bprm); -extern void __audit_socketcall(int nargs, unsigned long *args); +extern int __audit_socketcall(int nargs, unsigned long *args); extern int __audit_sockaddr(int len, void *addr); extern void __audit_fd_pair(int fd1, int fd2); extern void __audit_mq_open(int oflag, umode_t mode, struct mq_attr *attr); @@ -224,10 +227,11 @@ static inline int audit_bprm(struct linux_binprm *bprm) return __audit_bprm(bprm); return 0; } -static inline void audit_socketcall(int nargs, unsigned long *args) +static inline int audit_socketcall(int nargs, unsigned long *args) { if (unlikely(!audit_dummy_context())) - __audit_socketcall(nargs, args); + return __audit_socketcall(nargs, args); + return 0; } static inline int audit_sockaddr(int len, void *addr) { @@ -354,8 +358,10 @@ static inline int audit_bprm(struct linux_binprm *bprm) { return 0; } -static inline void audit_socketcall(int nargs, unsigned long *args) -{ } +static inline int audit_socketcall(int nargs, unsigned long *args) +{ + return 0; +} static inline void audit_fd_pair(int fd1, int fd2) { } static inline int audit_sockaddr(int len, void *addr) -- cgit v1.2.3 From 2b78f1e1389aef263071b9edf41c0980b092e601 Mon Sep 17 00:00:00 2001 From: Andreas Larsson Date: Fri, 15 Mar 2013 14:45:38 +0100 Subject: gpio: gpio-generic: Add 16 and 32 bit big endian byte order support There is no general support for 64-bit big endian accesses, so that is left unsupported. Signed-off-by: Andreas Larsson Acked-by: Anton Vorontsov Signed-off-by: Linus Walleij --- include/linux/basic_mmio_gpio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/basic_mmio_gpio.h b/include/linux/basic_mmio_gpio.h index 1c504ca5bdb3..d8a97ec0e2b8 100644 --- a/include/linux/basic_mmio_gpio.h +++ b/include/linux/basic_mmio_gpio.h @@ -72,5 +72,6 @@ int bgpio_init(struct bgpio_chip *bgc, struct device *dev, #define BGPIOF_BIG_ENDIAN BIT(0) #define BGPIOF_UNREADABLE_REG_SET BIT(1) /* reg_set is unreadable */ #define BGPIOF_UNREADABLE_REG_DIR BIT(2) /* reg_dir is unreadable */ +#define BGPIOF_BIG_ENDIAN_BYTE_ORDER BIT(3) #endif /* __BASIC_MMIO_GPIO_H */ -- cgit v1.2.3 From 7fc7acb9a0b0ff3ffdf21818fe0735ebaf4fecb8 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 9 Apr 2013 15:57:25 +0200 Subject: gpio / ACPI: Handle ACPI events in accordance with the spec Commit 0d1c28a (gpiolib-acpi: Add ACPI5 event model support to gpio.) that added support for ACPI events signalled through GPIO interrupts covered only GPIO pins whose numbers are less than or equal to 255. However, there may be GPIO pins with numbers greater than 255 and the ACPI spec (ACPI 5.0, Section 5.6.5.1) requires the _EVT method to be used for handling events corresponding to those pins. Moreover, according to the spec, _EVT is the default mechanism for handling all ACPI events signalled through GPIO interrupts, so if the _Exx/_Lxx method is not present for the given pin, _EVT should be used instead. If present, though, _Exx/_Lxx take precedence over _EVT which shouldn't be executed in that case (ACPI 5.0, Section 5.6.5.3). Modify acpi_gpiochip_request_interrupts() to follow the spec as described above and add acpi_gpiochip_free_interrupts() needed to free interrupts associated with _EVT. Signed-off-by: Rafael J. Wysocki Acked-by: Mika Westerberg Signed-off-by: Linus Walleij --- include/linux/acpi_gpio.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/acpi_gpio.h b/include/linux/acpi_gpio.h index b76ebd08ff8e..213135f44333 100644 --- a/include/linux/acpi_gpio.h +++ b/include/linux/acpi_gpio.h @@ -8,6 +8,7 @@ int acpi_get_gpio(char *path, int pin); void acpi_gpiochip_request_interrupts(struct gpio_chip *chip); +void acpi_gpiochip_free_interrupts(struct gpio_chip *chip); #else /* CONFIG_GPIO_ACPI */ @@ -17,6 +18,7 @@ static inline int acpi_get_gpio(char *path, int pin) } static inline void acpi_gpiochip_request_interrupts(struct gpio_chip *chip) { } +static inline void acpi_gpiochip_free_interrupts(struct gpio_chip *chip) { } #endif /* CONFIG_GPIO_ACPI */ -- cgit v1.2.3 From 0583fe478a7d93be2c814b7e50d6e81c287edfe8 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 10 Apr 2013 18:27:51 -0500 Subject: ARM: convert arm/arm64 arch timer to use CLKSRC_OF init This converts arm and arm64 to use CLKSRC_OF DT based initialization for the arch timer. A new function arch_timer_arch_init is added to allow for arch specific setup. This has a side effect of enabling sched_clock on omap5 and exynos5. There should not be any reason not to use the arch timers for sched_clock. Signed-off-by: Rob Herring Cc: Russell King Cc: Kukjin Kim Cc: Tony Lindgren Cc: Simon Horman Cc: Magnus Damm Cc: Catalin Marinas Cc: Will Deacon Cc: John Stultz Cc: Thomas Gleixner Cc: linux-samsung-soc@vger.kernel.org Cc: linux-omap@vger.kernel.org Cc: linux-sh@vger.kernel.org Acked-by: Santosh Shilimkar --- include/clocksource/arm_arch_timer.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/clocksource/arm_arch_timer.h b/include/clocksource/arm_arch_timer.h index 2603267b1a29..e6c9c4cc9b23 100644 --- a/include/clocksource/arm_arch_timer.h +++ b/include/clocksource/arm_arch_timer.h @@ -31,18 +31,12 @@ #ifdef CONFIG_ARM_ARCH_TIMER -extern int arch_timer_init(void); extern u32 arch_timer_get_rate(void); extern u64 (*arch_timer_read_counter)(void); extern struct timecounter *arch_timer_get_timecounter(void); #else -static inline int arch_timer_init(void) -{ - return -ENXIO; -} - static inline u32 arch_timer_get_rate(void) { return 0; -- cgit v1.2.3 From d71956960c9dafaafeb19ea010c234abe9d25f10 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 20 Mar 2013 16:56:18 -0500 Subject: OF: add empty of_device_is_available for !OF Add an empty version of of_device_is_available. Signed-off-by: Rob Herring --- include/linux/of.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/of.h b/include/linux/of.h index a0f129284948..95c8583688bd 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -379,6 +379,11 @@ static inline int of_device_is_compatible(const struct device_node *device, return 0; } +static inline int of_device_is_available(const struct device_node *device) +{ + return 0; +} + static inline struct property *of_find_property(const struct device_node *np, const char *name, int *lenp) -- cgit v1.2.3 From 12028d2d216220618f76284af5f8ed510b11da55 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Wed, 3 Apr 2013 13:56:54 +0300 Subject: gpiolib-acpi: introduce acpi_get_gpio_by_index() helper Instead of open-coding ACPI GPIO resource lookup in each driver, we provide a helper function analogous to Device Tree version that allows drivers to specify which GPIO resource they are interested (using an index to the GPIO resources). The function then finds out the correct resource, translates the ACPI GPIO number to the corresponding Linux GPIO number and returns that. Signed-off-by: Mika Westerberg Acked-by: Rafael J. Wysocki Signed-off-by: Linus Walleij --- include/linux/acpi_gpio.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include') diff --git a/include/linux/acpi_gpio.h b/include/linux/acpi_gpio.h index 213135f44333..4c120a1e0ca3 100644 --- a/include/linux/acpi_gpio.h +++ b/include/linux/acpi_gpio.h @@ -1,12 +1,23 @@ #ifndef _LINUX_ACPI_GPIO_H_ #define _LINUX_ACPI_GPIO_H_ +#include #include #include +/** + * struct acpi_gpio_info - ACPI GPIO specific information + * @gpioint: if %true this GPIO is of type GpioInt otherwise type is GpioIo + */ +struct acpi_gpio_info { + bool gpioint; +}; + #ifdef CONFIG_GPIO_ACPI int acpi_get_gpio(char *path, int pin); +int acpi_get_gpio_by_index(struct device *dev, int index, + struct acpi_gpio_info *info); void acpi_gpiochip_request_interrupts(struct gpio_chip *chip); void acpi_gpiochip_free_interrupts(struct gpio_chip *chip); @@ -17,6 +28,12 @@ static inline int acpi_get_gpio(char *path, int pin) return -ENODEV; } +static inline int acpi_get_gpio_by_index(struct device *dev, int index, + struct acpi_gpio_info *info) +{ + return -ENODEV; +} + static inline void acpi_gpiochip_request_interrupts(struct gpio_chip *chip) { } static inline void acpi_gpiochip_free_interrupts(struct gpio_chip *chip) { } -- cgit v1.2.3 From 80a26a5c22b90a82b8696cb72c1d09d525ada53e Mon Sep 17 00:00:00 2001 From: Zhang Rui Date: Tue, 26 Mar 2013 16:38:29 +0800 Subject: Thermal: build thermal governors into thermal_sys module The thermal governors are part of the thermal framework, rather than a seperate feature/module. Because the generic thermal layer can not work without thermal governors, and it must load the thermal governors during its initialization. Build them into one module in this patch. This also fix a problem that the generic thermal layer does not work when CONFIG_THERMAL=m and CONFIG_THERMAL_GOV_XXX=y. Signed-off-by: Zhang Rui Acked-by: Eduardo Valentin Acked-by: Durgadoss R --- include/linux/thermal.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 5a3b428daaab..4445b951b57e 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -187,7 +187,6 @@ struct thermal_governor { char name[THERMAL_NAME_LENGTH]; int (*throttle)(struct thermal_zone_device *tz, int trip); struct list_head governor_list; - struct module *owner; }; /* Structure that holds binding parameters for a zone */ @@ -247,9 +246,6 @@ struct thermal_instance *get_thermal_instance(struct thermal_zone_device *, void thermal_cdev_update(struct thermal_cooling_device *); void notify_thermal_framework(struct thermal_zone_device *, int); -int thermal_register_governor(struct thermal_governor *); -void thermal_unregister_governor(struct thermal_governor *); - #ifdef CONFIG_NET extern int thermal_generate_netlink_event(struct thermal_zone_device *tz, enum events event); -- cgit v1.2.3 From bbf7fc88c78f7317e2cdcf77e974c8a9a8312641 Mon Sep 17 00:00:00 2001 From: Zhang Rui Date: Tue, 26 Mar 2013 23:57:01 +0800 Subject: Thermal: build cpu_cooling code into thermal_sys module Signed-off-by: Zhang Rui Acked-by: Eduardo Valentin Acked-by: Durgadoss R --- include/linux/cpu_cooling.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/cpu_cooling.h b/include/linux/cpu_cooling.h index bc479b1e0fd9..77c87c9d0193 100644 --- a/include/linux/cpu_cooling.h +++ b/include/linux/cpu_cooling.h @@ -29,7 +29,7 @@ #define CPUFREQ_COOLING_START 0 #define CPUFREQ_COOLING_STOP 1 -#if defined(CONFIG_CPU_THERMAL) || defined(CONFIG_CPU_THERMAL_MODULE) +#ifdef CONFIG_CPU_THERMAL /** * cpufreq_cooling_register - function to create cpufreq cooling device. * @clip_cpus: cpumask of cpus where the frequency constraints will happen -- cgit v1.2.3 From 63c4d919cf66b1b3ffa7861bddb50a697914af5b Mon Sep 17 00:00:00 2001 From: Eduardo Valentin Date: Fri, 5 Apr 2013 12:32:28 +0000 Subject: thermal: introduce thermal_zone_get_zone_by_name helper function This patch adds a helper function to get a reference of a thermal zone, based on the zone type name. It will perform a zone name lookup and return a reference to a thermal zone device that matches the name requested. In case the zone is not found or when several zones match same name or if the required parameters are invalid, it will return the corresponding error code (ERR_PTR). Cc: Durgadoss R Signed-off-by: Eduardo Valentin Acked-by: Durgadoss R Signed-off-by: Zhang Rui --- include/linux/thermal.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 3bda306f7a50..9af2f3a99658 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -239,6 +239,7 @@ void thermal_zone_device_update(struct thermal_zone_device *); struct thermal_cooling_device *thermal_cooling_device_register(char *, void *, const struct thermal_cooling_device_ops *); void thermal_cooling_device_unregister(struct thermal_cooling_device *); +struct thermal_zone_device *thermal_zone_get_zone_by_name(const char *name); int get_tz_trend(struct thermal_zone_device *, int); struct thermal_instance *get_thermal_instance(struct thermal_zone_device *, -- cgit v1.2.3 From 837b26bb2e4a83d224e725f07a1d9ca824bf905c Mon Sep 17 00:00:00 2001 From: Eduardo Valentin Date: Fri, 5 Apr 2013 12:32:29 +0000 Subject: thermal: expose thermal_zone_get_temp API This patch exports the thermal_zone_get_temp API so that driver writers can fetch temperature of thermal zones managed by other drivers. Acked-by: Durgadoss R Signed-off-by: Eduardo Valentin Signed-off-by: Zhang Rui --- include/linux/thermal.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 9af2f3a99658..ec2b886f9d96 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -240,6 +240,7 @@ struct thermal_cooling_device *thermal_cooling_device_register(char *, void *, const struct thermal_cooling_device_ops *); void thermal_cooling_device_unregister(struct thermal_cooling_device *); struct thermal_zone_device *thermal_zone_get_zone_by_name(const char *name); +int thermal_zone_get_temp(struct thermal_zone_device *tz, unsigned long *temp); int get_tz_trend(struct thermal_zone_device *, int); struct thermal_instance *get_thermal_instance(struct thermal_zone_device *, -- cgit v1.2.3 From a53e28da574a40bcc9f78f5d0b0b60570182595b Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Mon, 25 Mar 2013 13:23:52 +0100 Subject: dma: Make the 'mask' parameter of __dma_request_channel const The 'mask' parameter is not modified in __dma_request_channel and really shouldn't be. Make this explicit by making the parameter const. Signed-off-by: Lars-Peter Clausen Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 91ac8da25020..dd6d21b335c8 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -967,7 +967,8 @@ enum dma_status dma_sync_wait(struct dma_chan *chan, dma_cookie_t cookie); #ifdef CONFIG_DMA_ENGINE enum dma_status dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx); void dma_issue_pending_all(void); -struct dma_chan *__dma_request_channel(dma_cap_mask_t *mask, dma_filter_fn fn, void *fn_param); +struct dma_chan *__dma_request_channel(const dma_cap_mask_t *mask, + dma_filter_fn fn, void *fn_param); struct dma_chan *dma_request_slave_channel(struct device *dev, char *name); void dma_release_channel(struct dma_chan *chan); #else @@ -978,7 +979,7 @@ static inline enum dma_status dma_wait_for_async_tx(struct dma_async_tx_descript static inline void dma_issue_pending_all(void) { } -static inline struct dma_chan *__dma_request_channel(dma_cap_mask_t *mask, +static inline struct dma_chan *__dma_request_channel(const dma_cap_mask_t *mask, dma_filter_fn fn, void *fn_param) { return NULL; @@ -1005,9 +1006,9 @@ struct dma_chan *net_dma_find_channel(void); __dma_request_slave_channel_compat(&(mask), x, y, dev, name) static inline struct dma_chan -*__dma_request_slave_channel_compat(dma_cap_mask_t *mask, dma_filter_fn fn, - void *fn_param, struct device *dev, - char *name) +*__dma_request_slave_channel_compat(const dma_cap_mask_t *mask, + dma_filter_fn fn, void *fn_param, + struct device *dev, char *name) { struct dma_chan *chan; -- cgit v1.2.3 From bef29ec508e58bf8b9ec0915de5b0739fb800c91 Mon Sep 17 00:00:00 2001 From: Markus Pargmann Date: Sun, 24 Feb 2013 16:36:09 +0100 Subject: DMA: of: Constant names No DMA of-function alters the name, so this patch changes the name arguments to be constant. Most drivers will probably request DMA channels using a constant name. Signed-off-by: Markus Pargmann Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 4 ++-- include/linux/of_dma.h | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 91ac8da25020..274071ca6f04 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -968,7 +968,7 @@ enum dma_status dma_sync_wait(struct dma_chan *chan, dma_cookie_t cookie); enum dma_status dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx); void dma_issue_pending_all(void); struct dma_chan *__dma_request_channel(dma_cap_mask_t *mask, dma_filter_fn fn, void *fn_param); -struct dma_chan *dma_request_slave_channel(struct device *dev, char *name); +struct dma_chan *dma_request_slave_channel(struct device *dev, const char *name); void dma_release_channel(struct dma_chan *chan); #else static inline enum dma_status dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx) @@ -984,7 +984,7 @@ static inline struct dma_chan *__dma_request_channel(dma_cap_mask_t *mask, return NULL; } static inline struct dma_chan *dma_request_slave_channel(struct device *dev, - char *name) + const char *name) { return NULL; } diff --git a/include/linux/of_dma.h b/include/linux/of_dma.h index d15073e080dd..ce6a8ab3d2bb 100644 --- a/include/linux/of_dma.h +++ b/include/linux/of_dma.h @@ -40,7 +40,7 @@ extern int of_dma_controller_register(struct device_node *np, void *data); extern int of_dma_controller_free(struct device_node *np); extern struct dma_chan *of_dma_request_slave_channel(struct device_node *np, - char *name); + const char *name); extern struct dma_chan *of_dma_simple_xlate(struct of_phandle_args *dma_spec, struct of_dma *ofdma); #else @@ -58,7 +58,7 @@ static inline int of_dma_controller_free(struct device_node *np) } static inline struct dma_chan *of_dma_request_slave_channel(struct device_node *np, - char *name) + const char *name) { return NULL; } -- cgit v1.2.3 From 95b80e0a9ab3c1c8b41af5f2863801708f8f7288 Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Thu, 21 Mar 2013 17:59:19 +0100 Subject: arm: mach-mv78xx0: convert to use the mvebu-mbus driver This commit convers the mach-mv78xx0 sub-architecture to use the mvebu-mbus driver. We simply have to call mvebu_mbus_init() in the ->init_early() function, and modify the PCIe code so that it uses the new functions provided by mvebu-mbus to create the needed PCIe windows. Signed-off-by: Thomas Petazzoni Acked-by: Arnd Bergmann Signed-off-by: Jason Cooper --- include/linux/mbus.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/mbus.h b/include/linux/mbus.h index 462eb9791012..dba482e31a13 100644 --- a/include/linux/mbus.h +++ b/include/linux/mbus.h @@ -43,6 +43,9 @@ struct mbus_dram_target_info */ #define MVEBU_MBUS_NO_REMAP (0xffffffff) +/* Maximum size of a mbus window name */ +#define MVEBU_MBUS_MAX_WINNAME_SZ 32 + /* * The Marvell mbus is to be found only on SOCs from the Orion family * at the moment. Provide a dummy stub for other architectures. -- cgit v1.2.3 From 1b2e98bc1e35ebe1f65c3db62c8317096ad7f2c8 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 9 Apr 2013 14:05:43 +0300 Subject: dma: acpi-dma: introduce ACPI DMA helpers There is a new generic API to get a DMA channel for a slave device (commit 9a6cecc8 "dmaengine: add helper function to request a slave DMA channel"). In similar fashion to the DT case (commit aa3da644 "of: Add generic device tree DMA helpers") we introduce helpers to the DMAC drivers which are enumerated by ACPI. The proposed extension provides the following API calls: acpi_dma_controller_register(), devm_acpi_dma_controller_register() acpi_dma_controller_free(), devm_acpi_dma_controller_free() acpi_dma_simple_xlate() acpi_dma_request_slave_chan_by_index() acpi_dma_request_slave_chan_by_name() The first two should be used, for example, at probe() and remove() of the corresponding DMAC driver. At the register stage the DMAC driver supplies a custom xlate() function to translate a struct dma_spec into struct dma_chan. Accordingly to the ACPI Fixed DMA resource specification the only two pieces of information the slave device has are the channel id and the request line (slave id). Those two are represented by struct dma_spec. The acpi_dma_request_slave_chan_by_index() provides access to the specifix FixedDMA resource by its index. Whereas dma_request_slave_channel() takes a string parameter to identify the DMA resources required by the slave device. To make a slave device driver work with both DeviceTree and ACPI enumeration a simple convention is established: "tx" corresponds to the index 0 and "rx" to the index 1. In case of robust configuration the slave device driver unfortunately needs to call acpi_dma_request_slave_chan_by_index() directly. Additionally the patch provides "managed" version of the register/free pair i.e. devm_acpi_dma_controller_register() and devm_acpi_dma_controller_free(). Usually, the driver uses only devm_acpi_dma_controller_register(). Signed-off-by: Andy Shevchenko Reviewed-by: Mika Westerberg Acked-by: Rafael J. Wysocki Signed-off-by: Vinod Koul --- include/linux/acpi_dma.h | 116 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 116 insertions(+) create mode 100644 include/linux/acpi_dma.h (limited to 'include') diff --git a/include/linux/acpi_dma.h b/include/linux/acpi_dma.h new file mode 100644 index 000000000000..d09deabc7bf6 --- /dev/null +++ b/include/linux/acpi_dma.h @@ -0,0 +1,116 @@ +/* + * ACPI helpers for DMA request / controller + * + * Based on of_dma.h + * + * Copyright (C) 2013, Intel Corporation + * Author: Andy Shevchenko + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef __LINUX_ACPI_DMA_H +#define __LINUX_ACPI_DMA_H + +#include +#include +#include + +/** + * struct acpi_dma_spec - slave device DMA resources + * @chan_id: channel unique id + * @slave_id: request line unique id + * @dev: struct device of the DMA controller to be used in the filter + * function + */ +struct acpi_dma_spec { + int chan_id; + int slave_id; + struct device *dev; +}; + +/** + * struct acpi_dma - representation of the registered DMAC + * @dma_controllers: linked list node + * @dev: struct device of this controller + * @acpi_dma_xlate: callback function to find a suitable channel + * @data: private data used by a callback function + */ +struct acpi_dma { + struct list_head dma_controllers; + struct device *dev; + struct dma_chan *(*acpi_dma_xlate) + (struct acpi_dma_spec *, struct acpi_dma *); + void *data; +}; + +/* Used with acpi_dma_simple_xlate() */ +struct acpi_dma_filter_info { + dma_cap_mask_t dma_cap; + dma_filter_fn filter_fn; +}; + +#ifdef CONFIG_DMA_ACPI + +int acpi_dma_controller_register(struct device *dev, + struct dma_chan *(*acpi_dma_xlate) + (struct acpi_dma_spec *, struct acpi_dma *), + void *data); +int acpi_dma_controller_free(struct device *dev); +int devm_acpi_dma_controller_register(struct device *dev, + struct dma_chan *(*acpi_dma_xlate) + (struct acpi_dma_spec *, struct acpi_dma *), + void *data); +void devm_acpi_dma_controller_free(struct device *dev); + +struct dma_chan *acpi_dma_request_slave_chan_by_index(struct device *dev, + size_t index); +struct dma_chan *acpi_dma_request_slave_chan_by_name(struct device *dev, + const char *name); + +struct dma_chan *acpi_dma_simple_xlate(struct acpi_dma_spec *dma_spec, + struct acpi_dma *adma); +#else + +static inline int acpi_dma_controller_register(struct device *dev, + struct dma_chan *(*acpi_dma_xlate) + (struct acpi_dma_spec *, struct acpi_dma *), + void *data) +{ + return -ENODEV; +} +static inline int acpi_dma_controller_free(struct device *dev) +{ + return -ENODEV; +} +static inline int devm_acpi_dma_controller_register(struct device *dev, + struct dma_chan *(*acpi_dma_xlate) + (struct acpi_dma_spec *, struct acpi_dma *), + void *data) +{ + return -ENODEV; +} +static inline void devm_acpi_dma_controller_free(struct device *dev) +{ +} + +static inline struct dma_chan *acpi_dma_request_slave_chan_by_index( + struct device *dev, size_t index) +{ + return NULL; +} +static inline struct dma_chan *acpi_dma_request_slave_chan_by_name( + struct device *dev, const char *name) +{ + return NULL; +} + +#define acpi_dma_simple_xlate NULL + +#endif + +#define acpi_dma_request_slave_channel acpi_dma_request_slave_chan_by_index + +#endif /* __LINUX_ACPI_DMA_H */ -- cgit v1.2.3 From aa2fbe6d44892070d78995f0df875ce930904e29 Mon Sep 17 00:00:00 2001 From: Yang Zhang Date: Thu, 11 Apr 2013 19:21:40 +0800 Subject: KVM: Let ioapic know the irq line status Userspace may deliver RTC interrupt without query the status. So we want to track RTC EOI for this case. Signed-off-by: Yang Zhang Reviewed-by: Gleb Natapov Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 20d77d24d764..4a76aca31478 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -292,7 +292,8 @@ struct kvm_kernel_irq_routing_entry { u32 gsi; u32 type; int (*set)(struct kvm_kernel_irq_routing_entry *e, - struct kvm *kvm, int irq_source_id, int level); + struct kvm *kvm, int irq_source_id, int level, + bool line_status); union { struct { unsigned irqchip; @@ -591,7 +592,8 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, int kvm_vm_ioctl_set_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem); -int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level); +int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level, + bool line_status); long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); @@ -722,10 +724,11 @@ void kvm_get_intr_delivery_bitmask(struct kvm_ioapic *ioapic, union kvm_ioapic_redirect_entry *entry, unsigned long *deliver_bitmask); #endif -int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level); +int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level, + bool line_status); int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level); int kvm_set_msi(struct kvm_kernel_irq_routing_entry *irq_entry, struct kvm *kvm, - int irq_source_id, int level); + int irq_source_id, int level, bool line_status); bool kvm_irq_has_notifier(struct kvm *kvm, unsigned irqchip, unsigned pin); void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin); void kvm_register_irq_ack_notifier(struct kvm *kvm, -- cgit v1.2.3 From 76ec9d18b8972f1b228f819f6126c9f022b3e642 Mon Sep 17 00:00:00 2001 From: Alexandre Courbot Date: Thu, 28 Mar 2013 04:34:56 -0700 Subject: Convert selectors of GENERIC_GPIO to GPIOLIB GENERIC_GPIO is now equivalent to GPIOLIB and features that depended on GENERIC_GPIO can now depend on GPIOLIB to allow removal of this option. Signed-off-by: Alexandre Courbot Acked-by: Linus Walleij Acked-by: Grant Likely --- include/linux/gpio.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/gpio.h b/include/linux/gpio.h index f6c7ae3e223b..552e3f46e4a3 100644 --- a/include/linux/gpio.h +++ b/include/linux/gpio.h @@ -39,7 +39,7 @@ struct gpio { const char *label; }; -#ifdef CONFIG_GENERIC_GPIO +#ifdef CONFIG_GPIOLIB #ifdef CONFIG_ARCH_HAVE_CUSTOM_GPIO_H #include @@ -74,7 +74,7 @@ static inline int irq_to_gpio(unsigned int irq) #endif /* ! CONFIG_ARCH_HAVE_CUSTOM_GPIO_H */ -#else /* ! CONFIG_GENERIC_GPIO */ +#else /* ! CONFIG_GPIOLIB */ #include #include @@ -226,7 +226,7 @@ gpiochip_remove_pin_ranges(struct gpio_chip *chip) WARN_ON(1); } -#endif /* ! CONFIG_GENERIC_GPIO */ +#endif /* ! CONFIG_GPIOLIB */ struct device; -- cgit v1.2.3 From 063cc6d5591ea9c0631b81ac5c7b829d99738b2f Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 27 Mar 2013 21:28:22 -0400 Subject: NVMe: Abstract out sector to block number conversion Introduce nvme_block_nr() to help convert sectors to block numbers. This fixes an integer overflow in the SCSI conversion layer, and it's slightly less typing than opencoding it. Signed-off-by: Matthew Wilcox Acked-by: Keith Busch --- include/linux/nvme.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index aa575033dbe7..09f419d4da4e 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -566,6 +566,11 @@ struct nvme_iod { struct scatterlist sg[0]; }; +static inline u64 nvme_block_nr(struct nvme_ns *ns, sector_t sector) +{ + return (sector >> (ns->lba_shift - 9)); +} + /** * nvme_free_iod - frees an nvme_iod * @dev: The device that the I/O was submitted to -- cgit v1.2.3 From 1c9b52651dad0ff1fa71fc6205c86d972f25bcc0 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 16 Apr 2013 15:21:06 -0400 Subject: NVMe: Fix endian-related problems in user I/O submission path When constructing the command, dsmgmt needs to be treated as a 32-bit value, not a 16-bit value. reftag, apptag and appmask all need to be converted from native-endian to little-endian. Again, sparse's bitwise warnings caught this problem. Thanks to Keith for pointing out the correct way to fix the reftag. Signed-off-by: Matthew Wilcox Acked-by: Keith Busch --- include/linux/nvme.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 09f419d4da4e..7ae7ecfc0947 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -207,11 +207,11 @@ struct nvme_common_command { __u8 flags; __u16 command_id; __le32 nsid; - __u32 cdw2[2]; + __le32 cdw2[2]; __le64 metadata; __le64 prp1; __le64 prp2; - __u32 cdw10[6]; + __le32 cdw10[6]; }; struct nvme_rw_command { -- cgit v1.2.3 From 3d81bc7e96d6bca0b8f8b7d1bf6ea72caa3aac57 Mon Sep 17 00:00:00 2001 From: Yang Zhang Date: Thu, 11 Apr 2013 19:25:13 +0800 Subject: KVM: Call common update function when ioapic entry changed. Both TMR and EOI exit bitmap need to be updated when ioapic changed or vcpu's id/ldr/dfr changed. So use common function instead eoi exit bitmap specific function. Signed-off-by: Yang Zhang Reviewed-by: Gleb Natapov Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 4a76aca31478..93a50054d46c 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -126,7 +126,7 @@ static inline bool is_error_page(struct page *page) #define KVM_REQ_MASTERCLOCK_UPDATE 19 #define KVM_REQ_MCLOCK_INPROGRESS 20 #define KVM_REQ_EPR_EXIT 21 -#define KVM_REQ_EOIBITMAP 22 +#define KVM_REQ_SCAN_IOAPIC 22 #define KVM_USERSPACE_IRQ_SOURCE_ID 0 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID 1 @@ -575,7 +575,7 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu); void kvm_flush_remote_tlbs(struct kvm *kvm); void kvm_reload_remote_mmus(struct kvm *kvm); void kvm_make_mclock_inprogress_request(struct kvm *kvm); -void kvm_make_update_eoibitmap_request(struct kvm *kvm); +void kvm_make_scan_ioapic_request(struct kvm *kvm); long kvm_arch_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); -- cgit v1.2.3 From 5e82e952f04681c10f35e02ee0a4a43ec027137a Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Tue, 19 Feb 2013 10:17:58 -0700 Subject: NVMe: Add a character device for each nvme device Registers a miscellaneous device for each nvme controller probed. This creates character device files as /dev/nvmeN, where N is the device instance, and supports nvme admin ioctl commands so devices without namespaces can be managed. Signed-off-by: Keith Busch Signed-off-by: Matthew Wilcox --- include/linux/nvme.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 7ae7ecfc0947..9b6fba872f47 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -507,6 +507,8 @@ struct nvme_admin_cmd { #ifdef __KERNEL__ #include +#include +#include #define NVME_IO_TIMEOUT (5 * HZ) @@ -527,6 +529,9 @@ struct nvme_dev { struct msix_entry *entry; struct nvme_bar __iomem *bar; struct list_head namespaces; + struct kref kref; + struct miscdevice miscdev; + char name[12]; char serial[20]; char model[40]; char firmware_rev[8]; -- cgit v1.2.3 From 62062cf8a3a99a933efdac549da380f230dbe982 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Tue, 16 Apr 2013 13:08:43 -0400 Subject: audit: allow checking the type of audit message in the user filter When userspace sends messages to the audit system it includes a type. We want to be able to filter messages based on that type without have to do the all or nothing option currently available on the AUDIT_FILTER_TYPE filter list. Instead we should be able to use the AUDIT_FILTER_USER filter list and just use the message type as one part of the matching decision. Signed-off-by: Eric Paris --- include/linux/audit.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/audit.h b/include/linux/audit.h index 8f92e1dea966..b26d7f121ac5 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -438,7 +438,7 @@ static inline void audit_log_secctx(struct audit_buffer *ab, u32 secid) extern int audit_update_lsm_rules(void); /* Private API (for audit.c only) */ -extern int audit_filter_user(void); +extern int audit_filter_user(int type); extern int audit_filter_type(int type); extern int audit_receive_filter(int type, int pid, int seq, void *data, size_t datasz, kuid_t loginuid, -- cgit v1.2.3 From 9f550553a470d3b05fc8bdced3a738d8ed5b8d8a Mon Sep 17 00:00:00 2001 From: Shlomo Pongratz Date: Wed, 10 Apr 2013 14:26:47 +0000 Subject: mlx4_core: Implement SRQ object lookup from srqn Expose a new API mlx4_srq_lookup() to retrive a SRQ based on its number. This API is needed in the mlx4_ib driver CQ polling logic, when a work completion is associated with a XRC TGT QP. Since a target QP may redirect to more than one XRC SRQ, the srq field in the QP has no usage and the real XRC SRQ need to be retrived using the information from the XRCETH IB header which is placed in the HW CQE. Signed-off-by: Shlomo Pongratz Signed-off-by: Or Gerlitz Signed-off-by: Roland Dreier --- include/linux/mlx4/srq.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mlx4/srq.h b/include/linux/mlx4/srq.h index 799a0697a383..192e0f7784f2 100644 --- a/include/linux/mlx4/srq.h +++ b/include/linux/mlx4/srq.h @@ -39,4 +39,6 @@ struct mlx4_wqe_srq_next_seg { u32 reserved2[3]; }; +struct mlx4_srq *mlx4_srq_lookup(struct mlx4_dev *dev, u32 srqn); + #endif /* MLX4_SRQ_H */ -- cgit v1.2.3 From 86239ceb33b0d8480b0f0ca0eec08e7f7a807374 Mon Sep 17 00:00:00 2001 From: Len Brown Date: Wed, 27 Feb 2013 13:18:50 -0500 Subject: intel_idle: initial C8, C9, C10 support Allow intel_idle and cpuidle to utilize C8, C9, C10 when they are present on... "Fourth Generation Intel(R) Core(TM) Processors", which are based on Intel(R) microarchitecture code name Haswell. Signed-off-by: Len Brown --- include/linux/cpuidle.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 480c14dc1ddd..309f7f596b4c 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -17,7 +17,7 @@ #include #include -#define CPUIDLE_STATE_MAX 8 +#define CPUIDLE_STATE_MAX 10 #define CPUIDLE_NAME_LEN 16 #define CPUIDLE_DESC_LEN 32 -- cgit v1.2.3 From 360e64d8bbe7c78784d769a60d152804f5079577 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Sun, 14 Apr 2013 20:35:48 +0200 Subject: mfd: ucb1400: Pass ucb1400-gpio data through ac97 bus Cc: Jean Delvare Cc: Guenter Roeck Cc: Grant Likely Acked-by: Linus Walleij Reviewed-by: Mark Brown Signed-off-by: Marek Vasut Signed-off-by: Samuel Ortiz --- include/linux/ucb1400.h | 18 ++++++------------ 1 file changed, 6 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/ucb1400.h b/include/linux/ucb1400.h index d21b33c4c6ca..2e9ee4d1c676 100644 --- a/include/linux/ucb1400.h +++ b/include/linux/ucb1400.h @@ -83,15 +83,12 @@ #define UCB_ID 0x7e #define UCB_ID_1400 0x4304 -struct ucb1400_gpio_data { - int gpio_offset; - int (*gpio_setup)(struct device *dev, int ngpio); - int (*gpio_teardown)(struct device *dev, int ngpio); -}; - struct ucb1400_gpio { struct gpio_chip gc; struct snd_ac97 *ac97; + int gpio_offset; + int (*gpio_setup)(struct device *dev, int ngpio); + int (*gpio_teardown)(struct device *dev, int ngpio); }; struct ucb1400_ts { @@ -110,6 +107,9 @@ struct ucb1400 { struct ucb1400_pdata { int irq; + int gpio_offset; + int (*gpio_setup)(struct device *dev, int ngpio); + int (*gpio_teardown)(struct device *dev, int ngpio); }; static inline u16 ucb1400_reg_read(struct snd_ac97 *ac97, u16 reg) @@ -162,10 +162,4 @@ static inline void ucb1400_adc_disable(struct snd_ac97 *ac97) unsigned int ucb1400_adc_read(struct snd_ac97 *ac97, u16 adc_channel, int adcsync); -#ifdef CONFIG_GPIO_UCB1400 -void __init ucb1400_gpio_set_data(struct ucb1400_gpio_data *data); -#else -static inline void ucb1400_gpio_set_data(struct ucb1400_gpio_data *data) {} -#endif - #endif -- cgit v1.2.3 From 95e50f6a2fe9ece6503e355400c171e0f5de61be Mon Sep 17 00:00:00 2001 From: Aaro Koskinen Date: Tue, 9 Apr 2013 22:51:25 +0300 Subject: mfd: retu: Add Tahvo support Tahvo is a multi-function device on Nokia 770, implementing USB transceiver and charge/battery control. It's so close to Retu that a single driver can support both. Signed-off-by: Aaro Koskinen Signed-off-by: Samuel Ortiz --- include/linux/mfd/retu.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mfd/retu.h b/include/linux/mfd/retu.h index 1e2715d5b836..65471c4a3926 100644 --- a/include/linux/mfd/retu.h +++ b/include/linux/mfd/retu.h @@ -1,5 +1,5 @@ /* - * Retu MFD driver interface + * Retu/Tahvo MFD driver interface * * This file is subject to the terms and conditions of the GNU General * Public License. See the file "COPYING" in the main directory of this @@ -19,4 +19,10 @@ int retu_write(struct retu_dev *, u8, u16); #define RETU_REG_CC1 0x0d /* Common control register 1 */ #define RETU_REG_STATUS 0x16 /* Status register */ +/* Interrupt sources */ +#define TAHVO_INT_VBUS 0 /* VBUS state */ + +/* Interrupt status */ +#define TAHVO_STAT_VBUS (1 << TAHVO_INT_VBUS) + #endif /* __LINUX_MFD_RETU_H */ -- cgit v1.2.3 From 4c4b8c105a7bbd4a8d41ab4458f01174fdf3fcbb Mon Sep 17 00:00:00 2001 From: Wei WANG Date: Thu, 11 Apr 2013 10:43:40 +0800 Subject: mfd: rtsx: Support RTS5249 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit RTS5249 supports SD UHS-II interface. In order to support SD UHS-II，the definitions of some internal registers of RTS5249 have to be modified and are different from its predecessors. So we need this patch to ensure RTS5249 can work, even SD/MMC stack doesn't support UHS-II interface. Signed-off-by: Wei WANG Signed-off-by: Samuel Ortiz --- include/linux/mfd/rtsx_pci.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'include') diff --git a/include/linux/mfd/rtsx_pci.h b/include/linux/mfd/rtsx_pci.h index 26ea7f1b7caf..86bc635f8385 100644 --- a/include/linux/mfd/rtsx_pci.h +++ b/include/linux/mfd/rtsx_pci.h @@ -500,6 +500,8 @@ #define BPP_POWER_15_PERCENT_ON 0x08 #define BPP_POWER_ON 0x00 #define BPP_POWER_MASK 0x0F +#define SD_VCC_PARTIAL_POWER_ON 0x02 +#define SD_VCC_POWER_ON 0x00 /* PWR_GATE_CTRL */ #define PWR_GATE_EN 0x01 @@ -689,6 +691,40 @@ #define IMAGE_FLAG_ADDR0 0xCE80 #define IMAGE_FLAG_ADDR1 0xCE81 +/* Phy register */ +#define PHY_PCR 0x00 +#define PHY_RCR0 0x01 +#define PHY_RCR1 0x02 +#define PHY_RCR2 0x03 +#define PHY_RTCR 0x04 +#define PHY_RDR 0x05 +#define PHY_TCR0 0x06 +#define PHY_TCR1 0x07 +#define PHY_TUNE 0x08 +#define PHY_IMR 0x09 +#define PHY_BPCR 0x0A +#define PHY_BIST 0x0B +#define PHY_RAW_L 0x0C +#define PHY_RAW_H 0x0D +#define PHY_RAW_DATA 0x0E +#define PHY_HOST_CLK_CTRL 0x0F +#define PHY_DMR 0x10 +#define PHY_BACR 0x11 +#define PHY_IER 0x12 +#define PHY_BCSR 0x13 +#define PHY_BPR 0x14 +#define PHY_BPNR2 0x15 +#define PHY_BPNR 0x16 +#define PHY_BRNR2 0x17 +#define PHY_BENR 0x18 +#define PHY_REG_REV 0x19 +#define PHY_FLD0 0x1A +#define PHY_FLD1 0x1B +#define PHY_FLD2 0x1C +#define PHY_FLD3 0x1D +#define PHY_FLD4 0x1E +#define PHY_DUM_REG 0x1F + #define rtsx_pci_init_cmd(pcr) ((pcr)->ci = 0) struct rtsx_pcr; -- cgit v1.2.3 From 9b8e1a5e4670b3b24c0e35c0884b4185f17fceab Mon Sep 17 00:00:00 2001 From: Andrey Smirnov Date: Thu, 18 Apr 2013 09:58:30 -0700 Subject: mfd: si476x: Add header files and Kbuild plumbing This patch adds all necessary header files and Kbuild plumbing for the core driver for Silicon Laboratories Si476x series of AM/FM tuner chips. The driver as a whole is implemented as an MFD device and this patch adds a core portion of it that provides all the necessary functionality to the two other drivers that represent radio and audio codec subsystems of the chip. Acked-by: Hans Verkuil Acked-by: Sam Ravnborg Signed-off-by: Andrey Smirnov Signed-off-by: Samuel Ortiz --- include/linux/mfd/si476x-core.h | 533 ++++++++++++++++++++++++++++++++++++ include/linux/mfd/si476x-platform.h | 267 ++++++++++++++++++ include/linux/mfd/si476x-reports.h | 163 +++++++++++ 3 files changed, 963 insertions(+) create mode 100644 include/linux/mfd/si476x-core.h create mode 100644 include/linux/mfd/si476x-platform.h create mode 100644 include/linux/mfd/si476x-reports.h (limited to 'include') diff --git a/include/linux/mfd/si476x-core.h b/include/linux/mfd/si476x-core.h new file mode 100644 index 000000000000..ede3022c03c4 --- /dev/null +++ b/include/linux/mfd/si476x-core.h @@ -0,0 +1,533 @@ +/* + * include/media/si476x-core.h -- Common definitions for si476x core + * device + * + * Copyright (C) 2012 Innovative Converged Devices(ICD) + * Copyright (C) 2013 Andrey Smirnov + * + * Author: Andrey Smirnov + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; version 2 of the License. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + */ + +#ifndef SI476X_CORE_H +#define SI476X_CORE_H + +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +/* Command Timeouts */ +#define SI476X_DEFAULT_TIMEOUT 100000 +#define SI476X_TIMEOUT_TUNE 700000 +#define SI476X_TIMEOUT_POWER_UP 330000 +#define SI476X_STATUS_POLL_US 0 + +/* -------------------- si476x-i2c.c ----------------------- */ + +enum si476x_freq_supported_chips { + SI476X_CHIP_SI4761 = 1, + SI476X_CHIP_SI4764, + SI476X_CHIP_SI4768, +}; + +enum si476x_part_revisions { + SI476X_REVISION_A10 = 0, + SI476X_REVISION_A20 = 1, + SI476X_REVISION_A30 = 2, +}; + +enum si476x_mfd_cells { + SI476X_RADIO_CELL = 0, + SI476X_CODEC_CELL, + SI476X_MFD_CELLS, +}; + +/** + * enum si476x_power_state - possible power state of the si476x + * device. + * + * @SI476X_POWER_DOWN: In this state all regulators are turned off + * and the reset line is pulled low. The device is completely + * inactive. + * @SI476X_POWER_UP_FULL: In this state all the power regualtors are + * turned on, reset line pulled high, IRQ line is enabled(polling is + * active for polling use scenario) and device is turned on with + * POWER_UP command. The device is ready to be used. + * @SI476X_POWER_INCONSISTENT: This state indicates that previous + * power down was inconsistent, meaning some of the regulators were + * not turned down and thus use of the device, without power-cycling + * is impossible. + */ +enum si476x_power_state { + SI476X_POWER_DOWN = 0, + SI476X_POWER_UP_FULL = 1, + SI476X_POWER_INCONSISTENT = 2, +}; + +/** + * struct si476x_core - internal data structure representing the + * underlying "core" device which all the MFD cell-devices use. + * + * @client: Actual I2C client used to transfer commands to the chip. + * @chip_id: Last digit of the chip model(E.g. "1" for SI4761) + * @cells: MFD cell devices created by this driver. + * @cmd_lock: Mutex used to serialize all the requests to the core + * device. This filed should not be used directly. Instead + * si476x_core_lock()/si476x_core_unlock() should be used to get + * exclusive access to the "core" device. + * @users: Active users counter(Used by the radio cell) + * @rds_read_queue: Wait queue used to wait for RDS data. + * @rds_fifo: FIFO in which all the RDS data received from the chip is + * placed. + * @rds_fifo_drainer: Worker that drains on-chip RDS FIFO. + * @rds_drainer_is_working: Flag used for launching only one instance + * of the @rds_fifo_drainer. + * @rds_drainer_status_lock: Lock used to guard access to the + * @rds_drainer_is_working variable. + * @command: Wait queue for wainting on the command comapletion. + * @cts: Clear To Send flag set upon receiving first status with CTS + * set. + * @tuning: Wait queue used for wainting for tune/seek comand + * completion. + * @stc: Similar to @cts, but for the STC bit of the status value. + * @power_up_parameters: Parameters used as argument for POWER_UP + * command when the device is started. + * @state: Current power state of the device. + * @supplues: Structure containing handles to all power supplies used + * by the device (NULL ones are ignored). + * @gpio_reset: GPIO pin connectet to the RSTB pin of the chip. + * @pinmux: Chip's configurable pins configuration. + * @diversity_mode: Chips role when functioning in diversity mode. + * @status_monitor: Polling worker used in polling use case scenarion + * (when IRQ is not avalible). + * @revision: Chip's running firmware revision number(Used for correct + * command set support). + */ + +struct si476x_core { + struct i2c_client *client; + struct regmap *regmap; + int chip_id; + struct mfd_cell cells[SI476X_MFD_CELLS]; + + struct mutex cmd_lock; /* for serializing fm radio operations */ + atomic_t users; + + wait_queue_head_t rds_read_queue; + struct kfifo rds_fifo; + struct work_struct rds_fifo_drainer; + bool rds_drainer_is_working; + struct mutex rds_drainer_status_lock; + + wait_queue_head_t command; + atomic_t cts; + + wait_queue_head_t tuning; + atomic_t stc; + + struct si476x_power_up_args power_up_parameters; + + enum si476x_power_state power_state; + + struct regulator_bulk_data supplies[4]; + + int gpio_reset; + + struct si476x_pinmux pinmux; + enum si476x_phase_diversity_mode diversity_mode; + + atomic_t is_alive; + + struct delayed_work status_monitor; +#define SI476X_WORK_TO_CORE(w) container_of(to_delayed_work(w), \ + struct si476x_core, \ + status_monitor) + + int revision; + + int rds_fifo_depth; +}; + +static inline struct si476x_core *i2c_mfd_cell_to_core(struct device *dev) +{ + struct i2c_client *client = to_i2c_client(dev->parent); + return i2c_get_clientdata(client); +} + + +/** + * si476x_core_lock() - lock the core device to get an exclusive access + * to it. + */ +static inline void si476x_core_lock(struct si476x_core *core) +{ + mutex_lock(&core->cmd_lock); +} + +/** + * si476x_core_unlock() - unlock the core device to relinquish an + * exclusive access to it. + */ +static inline void si476x_core_unlock(struct si476x_core *core) +{ + mutex_unlock(&core->cmd_lock); +} + +/* *_TUNE_FREQ family of commands accept frequency in multiples of + 10kHz */ +static inline u16 hz_to_si476x(struct si476x_core *core, int freq) +{ + u16 result; + + switch (core->power_up_parameters.func) { + default: + case SI476X_FUNC_FM_RECEIVER: + result = freq / 10000; + break; + case SI476X_FUNC_AM_RECEIVER: + result = freq / 1000; + break; + } + + return result; +} + +static inline int si476x_to_hz(struct si476x_core *core, u16 freq) +{ + int result; + + switch (core->power_up_parameters.func) { + default: + case SI476X_FUNC_FM_RECEIVER: + result = freq * 10000; + break; + case SI476X_FUNC_AM_RECEIVER: + result = freq * 1000; + break; + } + + return result; +} + +/* Since the V4L2_TUNER_CAP_LOW flag is supplied, V4L2 subsystem + * mesures frequency in 62.5 Hz units */ + +static inline int hz_to_v4l2(int freq) +{ + return (freq * 10) / 625; +} + +static inline int v4l2_to_hz(int freq) +{ + return (freq * 625) / 10; +} + +static inline u16 v4l2_to_si476x(struct si476x_core *core, int freq) +{ + return hz_to_si476x(core, v4l2_to_hz(freq)); +} + +static inline int si476x_to_v4l2(struct si476x_core *core, u16 freq) +{ + return hz_to_v4l2(si476x_to_hz(core, freq)); +} + + + +/** + * struct si476x_func_info - structure containing result of the + * FUNC_INFO command. + * + * @firmware.major: Firmware major number. + * @firmware.minor[...]: Firmware minor numbers. + * @patch_id: + * @func: Mode tuner is working in. + */ +struct si476x_func_info { + struct { + u8 major, minor[2]; + } firmware; + u16 patch_id; + enum si476x_func func; +}; + +/** + * struct si476x_power_down_args - structure used to pass parameters + * to POWER_DOWN command + * + * @xosc: true - Power down, but leav oscillator running. + * false - Full power down. + */ +struct si476x_power_down_args { + bool xosc; +}; + +/** + * enum si476x_tunemode - enum representing possible tune modes for + * the chip. + * @SI476X_TM_VALIDATED_NORMAL_TUNE: Unconditionally stay on the new + * channel after tune, tune status is valid. + * @SI476X_TM_INVALIDATED_FAST_TUNE: Unconditionally stay in the new + * channel after tune, tune status invalid. + * @SI476X_TM_VALIDATED_AF_TUNE: Jump back to previous channel if + * metric thresholds are not met. + * @SI476X_TM_VALIDATED_AF_CHECK: Unconditionally jump back to the + * previous channel. + */ +enum si476x_tunemode { + SI476X_TM_VALIDATED_NORMAL_TUNE = 0, + SI476X_TM_INVALIDATED_FAST_TUNE = 1, + SI476X_TM_VALIDATED_AF_TUNE = 2, + SI476X_TM_VALIDATED_AF_CHECK = 3, +}; + +/** + * enum si476x_smoothmetrics - enum containing the possible setting fo + * audio transitioning of the chip + * @SI476X_SM_INITIALIZE_AUDIO: Initialize audio state to match this + * new channel + * @SI476X_SM_TRANSITION_AUDIO: Transition audio state from previous + * channel values to the new values + */ +enum si476x_smoothmetrics { + SI476X_SM_INITIALIZE_AUDIO = 0, + SI476X_SM_TRANSITION_AUDIO = 1, +}; + +/** + * struct si476x_rds_status_report - the structure representing the + * response to 'FM_RD_STATUS' command + * @rdstpptyint: Traffic program flag(TP) and/or program type(PTY) + * code has changed. + * @rdspiint: Program indentifiaction(PI) code has changed. + * @rdssyncint: RDS synchronization has changed. + * @rdsfifoint: RDS was received and the RDS FIFO has at least + * 'FM_RDS_INTERRUPT_FIFO_COUNT' elements in it. + * @tpptyvalid: TP flag and PTY code are valid falg. + * @pivalid: PI code is valid flag. + * @rdssync: RDS is currently synchronized. + * @rdsfifolost: On or more RDS groups have been lost/discarded flag. + * @tp: Current channel's TP flag. + * @pty: Current channel's PTY code. + * @pi: Current channel's PI code. + * @rdsfifoused: Number of blocks remaining in the RDS FIFO (0 if + * empty). + */ +struct si476x_rds_status_report { + bool rdstpptyint, rdspiint, rdssyncint, rdsfifoint; + bool tpptyvalid, pivalid, rdssync, rdsfifolost; + bool tp; + + u8 pty; + u16 pi; + + u8 rdsfifoused; + u8 ble[4]; + + struct v4l2_rds_data rds[4]; +}; + +struct si476x_rsq_status_args { + bool primary; + bool rsqack; + bool attune; + bool cancel; + bool stcack; +}; + +enum si476x_injside { + SI476X_INJSIDE_AUTO = 0, + SI476X_INJSIDE_LOW = 1, + SI476X_INJSIDE_HIGH = 2, +}; + +struct si476x_tune_freq_args { + bool zifsr; + bool hd; + enum si476x_injside injside; + int freq; + enum si476x_tunemode tunemode; + enum si476x_smoothmetrics smoothmetrics; + int antcap; +}; + +int si476x_core_stop(struct si476x_core *, bool); +int si476x_core_start(struct si476x_core *, bool); +int si476x_core_set_power_state(struct si476x_core *, enum si476x_power_state); +bool si476x_core_has_am(struct si476x_core *); +bool si476x_core_has_diversity(struct si476x_core *); +bool si476x_core_is_a_secondary_tuner(struct si476x_core *); +bool si476x_core_is_a_primary_tuner(struct si476x_core *); +bool si476x_core_is_in_am_receiver_mode(struct si476x_core *core); +bool si476x_core_is_powered_up(struct si476x_core *core); + +enum si476x_i2c_type { + SI476X_I2C_SEND, + SI476X_I2C_RECV +}; + +int si476x_core_i2c_xfer(struct si476x_core *, + enum si476x_i2c_type, + char *, int); + + +/* -------------------- si476x-cmd.c ----------------------- */ + +int si476x_core_cmd_func_info(struct si476x_core *, struct si476x_func_info *); +int si476x_core_cmd_set_property(struct si476x_core *, u16, u16); +int si476x_core_cmd_get_property(struct si476x_core *, u16); +int si476x_core_cmd_dig_audio_pin_cfg(struct si476x_core *, + enum si476x_dclk_config, + enum si476x_dfs_config, + enum si476x_dout_config, + enum si476x_xout_config); +int si476x_core_cmd_zif_pin_cfg(struct si476x_core *, + enum si476x_iqclk_config, + enum si476x_iqfs_config, + enum si476x_iout_config, + enum si476x_qout_config); +int si476x_core_cmd_ic_link_gpo_ctl_pin_cfg(struct si476x_core *, + enum si476x_icin_config, + enum si476x_icip_config, + enum si476x_icon_config, + enum si476x_icop_config); +int si476x_core_cmd_ana_audio_pin_cfg(struct si476x_core *, + enum si476x_lrout_config); +int si476x_core_cmd_intb_pin_cfg(struct si476x_core *, enum si476x_intb_config, + enum si476x_a1_config); +int si476x_core_cmd_fm_seek_start(struct si476x_core *, bool, bool); +int si476x_core_cmd_am_seek_start(struct si476x_core *, bool, bool); +int si476x_core_cmd_fm_rds_status(struct si476x_core *, bool, bool, bool, + struct si476x_rds_status_report *); +int si476x_core_cmd_fm_rds_blockcount(struct si476x_core *, bool, + struct si476x_rds_blockcount_report *); +int si476x_core_cmd_fm_tune_freq(struct si476x_core *, + struct si476x_tune_freq_args *); +int si476x_core_cmd_am_tune_freq(struct si476x_core *, + struct si476x_tune_freq_args *); +int si476x_core_cmd_am_rsq_status(struct si476x_core *, + struct si476x_rsq_status_args *, + struct si476x_rsq_status_report *); +int si476x_core_cmd_fm_rsq_status(struct si476x_core *, + struct si476x_rsq_status_args *, + struct si476x_rsq_status_report *); +int si476x_core_cmd_power_up(struct si476x_core *, + struct si476x_power_up_args *); +int si476x_core_cmd_power_down(struct si476x_core *, + struct si476x_power_down_args *); +int si476x_core_cmd_fm_phase_div_status(struct si476x_core *); +int si476x_core_cmd_fm_phase_diversity(struct si476x_core *, + enum si476x_phase_diversity_mode); + +int si476x_core_cmd_fm_acf_status(struct si476x_core *, + struct si476x_acf_status_report *); +int si476x_core_cmd_am_acf_status(struct si476x_core *, + struct si476x_acf_status_report *); +int si476x_core_cmd_agc_status(struct si476x_core *, + struct si476x_agc_status_report *); + +enum si476x_power_grid_type { + SI476X_POWER_GRID_50HZ = 0, + SI476X_POWER_GRID_60HZ, +}; + +/* Properties */ + +enum si476x_interrupt_flags { + SI476X_STCIEN = (1 << 0), + SI476X_ACFIEN = (1 << 1), + SI476X_RDSIEN = (1 << 2), + SI476X_RSQIEN = (1 << 3), + + SI476X_ERRIEN = (1 << 6), + SI476X_CTSIEN = (1 << 7), + + SI476X_STCREP = (1 << 8), + SI476X_ACFREP = (1 << 9), + SI476X_RDSREP = (1 << 10), + SI476X_RSQREP = (1 << 11), +}; + +enum si476x_rdsint_sources { + SI476X_RDSTPPTY = (1 << 4), + SI476X_RDSPI = (1 << 3), + SI476X_RDSSYNC = (1 << 1), + SI476X_RDSRECV = (1 << 0), +}; + +enum si476x_status_response_bits { + SI476X_CTS = (1 << 7), + SI476X_ERR = (1 << 6), + /* Status response for WB receiver */ + SI476X_WB_ASQ_INT = (1 << 4), + SI476X_RSQ_INT = (1 << 3), + /* Status response for FM receiver */ + SI476X_FM_RDS_INT = (1 << 2), + SI476X_ACF_INT = (1 << 1), + SI476X_STC_INT = (1 << 0), +}; + +/* -------------------- si476x-prop.c ----------------------- */ + +enum si476x_common_receiver_properties { + SI476X_PROP_INT_CTL_ENABLE = 0x0000, + SI476X_PROP_DIGITAL_IO_INPUT_SAMPLE_RATE = 0x0200, + SI476X_PROP_DIGITAL_IO_INPUT_FORMAT = 0x0201, + SI476X_PROP_DIGITAL_IO_OUTPUT_SAMPLE_RATE = 0x0202, + SI476X_PROP_DIGITAL_IO_OUTPUT_FORMAT = 0x0203, + + SI476X_PROP_SEEK_BAND_BOTTOM = 0x1100, + SI476X_PROP_SEEK_BAND_TOP = 0x1101, + SI476X_PROP_SEEK_FREQUENCY_SPACING = 0x1102, + + SI476X_PROP_VALID_MAX_TUNE_ERROR = 0x2000, + SI476X_PROP_VALID_SNR_THRESHOLD = 0x2003, + SI476X_PROP_VALID_RSSI_THRESHOLD = 0x2004, +}; + +enum si476x_am_receiver_properties { + SI476X_PROP_AUDIO_PWR_LINE_FILTER = 0x0303, +}; + +enum si476x_fm_receiver_properties { + SI476X_PROP_AUDIO_DEEMPHASIS = 0x0302, + + SI476X_PROP_FM_RDS_INTERRUPT_SOURCE = 0x4000, + SI476X_PROP_FM_RDS_INTERRUPT_FIFO_COUNT = 0x4001, + SI476X_PROP_FM_RDS_CONFIG = 0x4002, +}; + +enum si476x_prop_audio_pwr_line_filter_bits { + SI476X_PROP_PWR_HARMONICS_MASK = 0b0000000000011111, + SI476X_PROP_PWR_GRID_MASK = 0b0000000100000000, + SI476X_PROP_PWR_ENABLE_MASK = 0b0000001000000000, + SI476X_PROP_PWR_GRID_50HZ = 0b0000000000000000, + SI476X_PROP_PWR_GRID_60HZ = 0b0000000100000000, +}; + +enum si476x_prop_fm_rds_config_bits { + SI476X_PROP_RDSEN_MASK = 0x1, + SI476X_PROP_RDSEN = 0x1, +}; + + +struct regmap *devm_regmap_init_si476x(struct si476x_core *); + +#endif /* SI476X_CORE_H */ diff --git a/include/linux/mfd/si476x-platform.h b/include/linux/mfd/si476x-platform.h new file mode 100644 index 000000000000..88bb93b7a9d5 --- /dev/null +++ b/include/linux/mfd/si476x-platform.h @@ -0,0 +1,267 @@ +/* + * include/media/si476x-platform.h -- Platform data specific definitions + * + * Copyright (C) 2013 Andrey Smirnov + * + * Author: Andrey Smirnov + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; version 2 of the License. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + */ + +#ifndef __SI476X_PLATFORM_H__ +#define __SI476X_PLATFORM_H__ + +/* It is possible to select one of the four adresses using pins A0 + * and A1 on SI476x */ +#define SI476X_I2C_ADDR_1 0x60 +#define SI476X_I2C_ADDR_2 0x61 +#define SI476X_I2C_ADDR_3 0x62 +#define SI476X_I2C_ADDR_4 0x63 + +enum si476x_iqclk_config { + SI476X_IQCLK_NOOP = 0, + SI476X_IQCLK_TRISTATE = 1, + SI476X_IQCLK_IQ = 21, +}; +enum si476x_iqfs_config { + SI476X_IQFS_NOOP = 0, + SI476X_IQFS_TRISTATE = 1, + SI476X_IQFS_IQ = 21, +}; +enum si476x_iout_config { + SI476X_IOUT_NOOP = 0, + SI476X_IOUT_TRISTATE = 1, + SI476X_IOUT_OUTPUT = 22, +}; +enum si476x_qout_config { + SI476X_QOUT_NOOP = 0, + SI476X_QOUT_TRISTATE = 1, + SI476X_QOUT_OUTPUT = 22, +}; + +enum si476x_dclk_config { + SI476X_DCLK_NOOP = 0, + SI476X_DCLK_TRISTATE = 1, + SI476X_DCLK_DAUDIO = 10, +}; + +enum si476x_dfs_config { + SI476X_DFS_NOOP = 0, + SI476X_DFS_TRISTATE = 1, + SI476X_DFS_DAUDIO = 10, +}; + +enum si476x_dout_config { + SI476X_DOUT_NOOP = 0, + SI476X_DOUT_TRISTATE = 1, + SI476X_DOUT_I2S_OUTPUT = 12, + SI476X_DOUT_I2S_INPUT = 13, +}; + +enum si476x_xout_config { + SI476X_XOUT_NOOP = 0, + SI476X_XOUT_TRISTATE = 1, + SI476X_XOUT_I2S_INPUT = 13, + SI476X_XOUT_MODE_SELECT = 23, +}; + +enum si476x_icin_config { + SI476X_ICIN_NOOP = 0, + SI476X_ICIN_TRISTATE = 1, + SI476X_ICIN_GPO1_HIGH = 2, + SI476X_ICIN_GPO1_LOW = 3, + SI476X_ICIN_IC_LINK = 30, +}; + +enum si476x_icip_config { + SI476X_ICIP_NOOP = 0, + SI476X_ICIP_TRISTATE = 1, + SI476X_ICIP_GPO2_HIGH = 2, + SI476X_ICIP_GPO2_LOW = 3, + SI476X_ICIP_IC_LINK = 30, +}; + +enum si476x_icon_config { + SI476X_ICON_NOOP = 0, + SI476X_ICON_TRISTATE = 1, + SI476X_ICON_I2S = 10, + SI476X_ICON_IC_LINK = 30, +}; + +enum si476x_icop_config { + SI476X_ICOP_NOOP = 0, + SI476X_ICOP_TRISTATE = 1, + SI476X_ICOP_I2S = 10, + SI476X_ICOP_IC_LINK = 30, +}; + + +enum si476x_lrout_config { + SI476X_LROUT_NOOP = 0, + SI476X_LROUT_TRISTATE = 1, + SI476X_LROUT_AUDIO = 2, + SI476X_LROUT_MPX = 3, +}; + + +enum si476x_intb_config { + SI476X_INTB_NOOP = 0, + SI476X_INTB_TRISTATE = 1, + SI476X_INTB_DAUDIO = 10, + SI476X_INTB_IRQ = 40, +}; + +enum si476x_a1_config { + SI476X_A1_NOOP = 0, + SI476X_A1_TRISTATE = 1, + SI476X_A1_IRQ = 40, +}; + + +struct si476x_pinmux { + enum si476x_dclk_config dclk; + enum si476x_dfs_config dfs; + enum si476x_dout_config dout; + enum si476x_xout_config xout; + + enum si476x_iqclk_config iqclk; + enum si476x_iqfs_config iqfs; + enum si476x_iout_config iout; + enum si476x_qout_config qout; + + enum si476x_icin_config icin; + enum si476x_icip_config icip; + enum si476x_icon_config icon; + enum si476x_icop_config icop; + + enum si476x_lrout_config lrout; + + enum si476x_intb_config intb; + enum si476x_a1_config a1; +}; + +enum si476x_ibias6x { + SI476X_IBIAS6X_OTHER = 0, + SI476X_IBIAS6X_RCVR1_NON_4MHZ_CLK = 1, +}; + +enum si476x_xstart { + SI476X_XSTART_MULTIPLE_TUNER = 0x11, + SI476X_XSTART_NORMAL = 0x77, +}; + +enum si476x_freq { + SI476X_FREQ_4_MHZ = 0, + SI476X_FREQ_37P209375_MHZ = 1, + SI476X_FREQ_36P4_MHZ = 2, + SI476X_FREQ_37P8_MHZ = 3, +}; + +enum si476x_xmode { + SI476X_XMODE_CRYSTAL_RCVR1 = 1, + SI476X_XMODE_EXT_CLOCK = 2, + SI476X_XMODE_CRYSTAL_RCVR2_3 = 3, +}; + +enum si476x_xbiashc { + SI476X_XBIASHC_SINGLE_RECEIVER = 0, + SI476X_XBIASHC_MULTIPLE_RECEIVER = 1, +}; + +enum si476x_xbias { + SI476X_XBIAS_RCVR2_3 = 0, + SI476X_XBIAS_4MHZ_RCVR1 = 3, + SI476X_XBIAS_RCVR1 = 7, +}; + +enum si476x_func { + SI476X_FUNC_BOOTLOADER = 0, + SI476X_FUNC_FM_RECEIVER = 1, + SI476X_FUNC_AM_RECEIVER = 2, + SI476X_FUNC_WB_RECEIVER = 3, +}; + + +/** + * @xcload: Selects the amount of additional on-chip capacitance to + * be connected between XTAL1 and gnd and between XTAL2 and + * GND. One half of the capacitance value shown here is the + * additional load capacitance presented to the xtal. The + * minimum step size is 0.277 pF. Recommended value is 0x28 + * but it will be layout dependent. Range is 0–0x3F i.e. + * (0–16.33 pF) + * @ctsien: enable CTSINT(interrupt request when CTS condition + * arises) when set + * @intsel: when set A1 pin becomes the interrupt pin; otherwise, + * INTB is the interrupt pin + * @func: selects the boot function of the device. I.e. + * SI476X_BOOTLOADER - Boot loader + * SI476X_FM_RECEIVER - FM receiver + * SI476X_AM_RECEIVER - AM receiver + * SI476X_WB_RECEIVER - Weatherband receiver + * @freq: oscillator's crystal frequency: + * SI476X_XTAL_37P209375_MHZ - 37.209375 Mhz + * SI476X_XTAL_36P4_MHZ - 36.4 Mhz + * SI476X_XTAL_37P8_MHZ - 37.8 Mhz + */ +struct si476x_power_up_args { + enum si476x_ibias6x ibias6x; + enum si476x_xstart xstart; + u8 xcload; + bool fastboot; + enum si476x_xbiashc xbiashc; + enum si476x_xbias xbias; + enum si476x_func func; + enum si476x_freq freq; + enum si476x_xmode xmode; +}; + + +/** + * enum si476x_phase_diversity_mode - possbile phase diversity modes + * for SI4764/5/6/7 chips. + * + * @SI476X_PHDIV_DISABLED: Phase diversity feature is + * disabled. + * @SI476X_PHDIV_PRIMARY_COMBINING: Tuner works as a primary tuner + * in combination with a + * secondary one. + * @SI476X_PHDIV_PRIMARY_ANTENNA: Tuner works as a primary tuner + * using only its own antenna. + * @SI476X_PHDIV_SECONDARY_ANTENNA: Tuner works as a primary tuner + * usning seconary tuner's antenna. + * @SI476X_PHDIV_SECONDARY_COMBINING: Tuner works as a secondary + * tuner in combination with the + * primary one. + */ +enum si476x_phase_diversity_mode { + SI476X_PHDIV_DISABLED = 0, + SI476X_PHDIV_PRIMARY_COMBINING = 1, + SI476X_PHDIV_PRIMARY_ANTENNA = 2, + SI476X_PHDIV_SECONDARY_ANTENNA = 3, + SI476X_PHDIV_SECONDARY_COMBINING = 5, +}; + + +/* + * Platform dependent definition + */ +struct si476x_platform_data { + int gpio_reset; /* < 0 if not used */ + + struct si476x_power_up_args power_up_parameters; + enum si476x_phase_diversity_mode diversity_mode; + + struct si476x_pinmux pinmux; +}; + + +#endif /* __SI476X_PLATFORM_H__ */ diff --git a/include/linux/mfd/si476x-reports.h b/include/linux/mfd/si476x-reports.h new file mode 100644 index 000000000000..e0b9455a79c0 --- /dev/null +++ b/include/linux/mfd/si476x-reports.h @@ -0,0 +1,163 @@ +/* + * include/media/si476x-platform.h -- Definitions of the data formats + * returned by debugfs hooks + * + * Copyright (C) 2013 Andrey Smirnov + * + * Author: Andrey Smirnov + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; version 2 of the License. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + */ + +#ifndef __SI476X_REPORTS_H__ +#define __SI476X_REPORTS_H__ + +/** + * struct si476x_rsq_status - structure containing received signal + * quality + * @multhint: Multipath Detect High. + * true - Indicatedes that the value is below + * FM_RSQ_MULTIPATH_HIGH_THRESHOLD + * false - Indicatedes that the value is above + * FM_RSQ_MULTIPATH_HIGH_THRESHOLD + * @multlint: Multipath Detect Low. + * true - Indicatedes that the value is below + * FM_RSQ_MULTIPATH_LOW_THRESHOLD + * false - Indicatedes that the value is above + * FM_RSQ_MULTIPATH_LOW_THRESHOLD + * @snrhint: SNR Detect High. + * true - Indicatedes that the value is below + * FM_RSQ_SNR_HIGH_THRESHOLD + * false - Indicatedes that the value is above + * FM_RSQ_SNR_HIGH_THRESHOLD + * @snrlint: SNR Detect Low. + * true - Indicatedes that the value is below + * FM_RSQ_SNR_LOW_THRESHOLD + * false - Indicatedes that the value is above + * FM_RSQ_SNR_LOW_THRESHOLD + * @rssihint: RSSI Detect High. + * true - Indicatedes that the value is below + * FM_RSQ_RSSI_HIGH_THRESHOLD + * false - Indicatedes that the value is above + * FM_RSQ_RSSI_HIGH_THRESHOLD + * @rssilint: RSSI Detect Low. + * true - Indicatedes that the value is below + * FM_RSQ_RSSI_LOW_THRESHOLD + * false - Indicatedes that the value is above + * FM_RSQ_RSSI_LOW_THRESHOLD + * @bltf: Band Limit. + * Set if seek command hits the band limit or wrapped to + * the original frequency. + * @snr_ready: SNR measurement in progress. + * @rssiready: RSSI measurement in progress. + * @afcrl: Set if FREQOFF >= MAX_TUNE_ERROR + * @valid: Set if the channel is valid + * rssi < FM_VALID_RSSI_THRESHOLD + * snr < FM_VALID_SNR_THRESHOLD + * tune_error < FM_VALID_MAX_TUNE_ERROR + * @readfreq: Current tuned frequency. + * @freqoff: Signed frequency offset. + * @rssi: Received Signal Strength Indicator(dBuV). + * @snr: RF SNR Indicator(dB). + * @lassi: + * @hassi: Low/High side Adjacent(100 kHz) Channel Strength Indicator + * @mult: Multipath indicator + * @dev: Who knows? But values may vary. + * @readantcap: Antenna tuning capacity value. + * @assi: Adjacent Channel(+/- 200kHz) Strength Indicator + * @usn: Ultrasonic Noise Inticator in -DBFS + */ +struct si476x_rsq_status_report { + __u8 multhint, multlint; + __u8 snrhint, snrlint; + __u8 rssihint, rssilint; + __u8 bltf; + __u8 snr_ready; + __u8 rssiready; + __u8 injside; + __u8 afcrl; + __u8 valid; + + __u16 readfreq; + __s8 freqoff; + __s8 rssi; + __s8 snr; + __s8 issi; + __s8 lassi, hassi; + __s8 mult; + __u8 dev; + __u16 readantcap; + __s8 assi; + __s8 usn; + + __u8 pilotdev; + __u8 rdsdev; + __u8 assidev; + __u8 strongdev; + __u16 rdspi; +} __packed; + +/** + * si476x_acf_status_report - ACF report results + * + * @blend_int: If set, indicates that stereo separation has crossed + * below the blend threshold as set by FM_ACF_BLEND_THRESHOLD + * @hblend_int: If set, indicates that HiBlend cutoff frequency is + * lower than threshold as set by FM_ACF_HBLEND_THRESHOLD + * @hicut_int: If set, indicates that HiCut cutoff frequency is lower + * than the threshold set by ACF_ + + */ +struct si476x_acf_status_report { + __u8 blend_int; + __u8 hblend_int; + __u8 hicut_int; + __u8 chbw_int; + __u8 softmute_int; + __u8 smute; + __u8 smattn; + __u8 chbw; + __u8 hicut; + __u8 hiblend; + __u8 pilot; + __u8 stblend; +} __packed; + +enum si476x_fmagc { + SI476X_FMAGC_10K_OHM = 0, + SI476X_FMAGC_800_OHM = 1, + SI476X_FMAGC_400_OHM = 2, + SI476X_FMAGC_200_OHM = 4, + SI476X_FMAGC_100_OHM = 8, + SI476X_FMAGC_50_OHM = 16, + SI476X_FMAGC_25_OHM = 32, + SI476X_FMAGC_12P5_OHM = 64, + SI476X_FMAGC_6P25_OHM = 128, +}; + +struct si476x_agc_status_report { + __u8 mxhi; + __u8 mxlo; + __u8 lnahi; + __u8 lnalo; + __u8 fmagc1; + __u8 fmagc2; + __u8 pgagain; + __u8 fmwblang; +} __packed; + +struct si476x_rds_blockcount_report { + __u16 expected; + __u16 received; + __u16 uncorrectable; +} __packed; + +#endif /* __SI476X_REPORTS_H__ */ -- cgit v1.2.3 From 9a08d3766874835f4eba1b3d66938326c069d817 Mon Sep 17 00:00:00 2001 From: Wang YanQing Date: Fri, 19 Apr 2013 09:38:04 +0800 Subject: iommu: Include linux/err.h The linux/iommu.h header uses ERR_PTR defined in linux/err.h but doesn't include it. Cc:joro@8bytes.org Reviewed-by: Alex Williamson Signed-off-by: Wang YanQing Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index ba3b8a98a049..6a027dc8dbfe 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -20,6 +20,7 @@ #define __LINUX_IOMMU_H #include +#include #include #define IOMMU_READ (1) -- cgit v1.2.3 From e34d3865ee4a71195f91b23fd09e2619a5f727d3 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 28 Jan 2013 17:42:24 +0000 Subject: ata: arasan: remove the need for platform_data This adds a complete DT binding for the arasan device driver. There is currently only one user, which is the spear13xx platform, so we don't actually have to parse all the properties until another user comes in, but this does use the generic DMA binding to find the DMA channel. The patch is untested so far and is part of a series to convert the spear platform over to use the generic DMA binding, so it should stay with the rest of the series. Signed-off-by: Arnd Bergmann Acked-by: Viresh Kumar Cc: Vinod Koul Cc: Jeff Garzik Cc: devicetree-discuss@lists.ozlabs.org --- include/linux/pata_arasan_cf_data.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/pata_arasan_cf_data.h b/include/linux/pata_arasan_cf_data.h index a7b4fc386e63..3cc21c9cc1e8 100644 --- a/include/linux/pata_arasan_cf_data.h +++ b/include/linux/pata_arasan_cf_data.h @@ -37,8 +37,6 @@ struct arasan_cf_pdata { #define CF_BROKEN_PIO (1) #define CF_BROKEN_MWDMA (1 << 1) #define CF_BROKEN_UDMA (1 << 2) - /* This is platform specific data for the DMA controller */ - void *dma_priv; }; static inline void -- cgit v1.2.3 From f11899894c0a683c754ca71b45f7c9c3d35a3a1c Mon Sep 17 00:00:00 2001 From: Tomasz Figa Date: Sat, 20 Apr 2013 23:22:13 +0200 Subject: clocksource: add samsung pwm timer driver This adds a new clocksource driver for the PWM timer that is present in most Samsung SoCs, based on the existing driver in arch/arm/plat-samsung/samsung-time.c and many changes implemented by Tomasz Figa. Originally, the conversion of all Samsung machines to the new driver was planned for 3.10, but that work ended up being too late and too invasive just before the merge window. Unfortunately, other changes in the Exynos platform resulted in some Exynos4 setups, particularly the Universal C210 board to be broken. In order to fix that with minimum risk, so we now leave the existing pwm clocksource driver in place for all older platforms and use the new driver only for device tree enabled boards. This way, we can get the broken machines running again using DT descriptions. All clocksource changes were implemented by Tomasz, while the DT registration was rewritten by Arnd. Signed-off-by: Arnd Bergmann Cc: Tomasz Figa Cc: Kyungmin Park Cc: Kukjin Kim Cc: Ben Dooks Cc: John Stultz Cc: Thomas Gleixner --- include/clocksource/samsung_pwm.h | 41 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) create mode 100644 include/clocksource/samsung_pwm.h (limited to 'include') diff --git a/include/clocksource/samsung_pwm.h b/include/clocksource/samsung_pwm.h new file mode 100644 index 000000000000..eff8668da252 --- /dev/null +++ b/include/clocksource/samsung_pwm.h @@ -0,0 +1,41 @@ +/* + * Copyright (C) 2013 Samsung Electronics Co., Ltd. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see . + */ +#ifndef __CLOCKSOURCE_SAMSUNG_PWM_H +#define __CLOCKSOURCE_SAMSUNG_PWM_H + +#include + +#define SAMSUNG_PWM_NUM 5 + +struct platform_device; +struct device_node; + +struct samsung_pwm_variant { + u8 bits; + u8 div_base; + u8 tclk_mask; + u8 output_mask; + bool has_tint_cstat; +}; + +struct samsung_pwm { + struct samsung_pwm_variant variant; + spinlock_t slock; + void __iomem *base; + int irq[SAMSUNG_PWM_NUM]; +}; + +#endif /* __CLOCKSOURCE_SAMSUNG_PWM_H */ -- cgit v1.2.3 From a2a4a7e4abb27c833d4e09ac1d434ab48a64062c Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sat, 20 Apr 2013 01:28:40 +0900 Subject: f2fs: add tracepoints for sync & inode operations Add tracepoints in f2fs for tracing the syncing operations like filesystem sync, file sync enter/exit. It will helf to trace the code under debugging scenarios. Also add tracepoints for tracing the various inode operations like building inode, eviction of inode, link/unlike of inodes. Signed-off-by: Namjae Jeon Signed-off-by: Pankaj Kumar Acked-by: Steven Rostedt [Jaegeuk: combine and modify the tracepoint structures] Signed-off-by: Jaegeuk Kim --- include/trace/events/f2fs.h | 195 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 195 insertions(+) create mode 100644 include/trace/events/f2fs.h (limited to 'include') diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h new file mode 100644 index 000000000000..03bb0dbf468d --- /dev/null +++ b/include/trace/events/f2fs.h @@ -0,0 +1,195 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM f2fs + +#if !defined(_TRACE_F2FS_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_F2FS_H + +#include + +#define show_dev(entry) MAJOR(entry->dev), MINOR(entry->dev) +#define show_dev_ino(entry) show_dev(entry), (unsigned long)entry->ino + +DECLARE_EVENT_CLASS(f2fs__inode, + + TP_PROTO(struct inode *inode), + + TP_ARGS(inode), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(ino_t, pino) + __field(umode_t, mode) + __field(loff_t, size) + __field(unsigned int, nlink) + __field(blkcnt_t, blocks) + __field(__u8, advise) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->pino = F2FS_I(inode)->i_pino; + __entry->mode = inode->i_mode; + __entry->nlink = inode->i_nlink; + __entry->size = inode->i_size; + __entry->blocks = inode->i_blocks; + __entry->advise = F2FS_I(inode)->i_advise; + ), + + TP_printk("dev = (%d,%d), ino = %lu, pino = %lu, i_mode = 0x%hx, " + "i_size = %lld, i_nlink = %u, i_blocks = %llu, i_advise = 0x%x", + show_dev_ino(__entry), + (unsigned long)__entry->pino, + __entry->mode, + __entry->size, + (unsigned int)__entry->nlink, + (unsigned long long)__entry->blocks, + (unsigned char)__entry->advise) +); + +DECLARE_EVENT_CLASS(f2fs__inode_exit, + + TP_PROTO(struct inode *inode, int ret), + + TP_ARGS(inode, ret), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(int, ret) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->ret = ret; + ), + + TP_printk("dev = (%d,%d), ino = %lu, ret = %d", + show_dev_ino(__entry), + __entry->ret) +); + +DEFINE_EVENT(f2fs__inode, f2fs_sync_file_enter, + + TP_PROTO(struct inode *inode), + + TP_ARGS(inode) +); + +TRACE_EVENT(f2fs_sync_file_exit, + + TP_PROTO(struct inode *inode, bool need_cp, int datasync, int ret), + + TP_ARGS(inode, need_cp, datasync, ret), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(bool, need_cp) + __field(int, datasync) + __field(int, ret) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->need_cp = need_cp; + __entry->datasync = datasync; + __entry->ret = ret; + ), + + TP_printk("dev = (%d,%d), ino = %lu, checkpoint is %s, " + "datasync = %d, ret = %d", + show_dev_ino(__entry), + __entry->need_cp ? "needed" : "not needed", + __entry->datasync, + __entry->ret) +); + +TRACE_EVENT(f2fs_sync_fs, + + TP_PROTO(struct super_block *sb, int wait), + + TP_ARGS(sb, wait), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(int, dirty) + __field(int, wait) + ), + + TP_fast_assign( + __entry->dev = sb->s_dev; + __entry->dirty = F2FS_SB(sb)->s_dirty; + __entry->wait = wait; + ), + + TP_printk("dev = (%d,%d), superblock is %s, wait = %d", + show_dev(__entry), + __entry->dirty ? "dirty" : "not dirty", + __entry->wait) +); + +DEFINE_EVENT(f2fs__inode, f2fs_iget, + + TP_PROTO(struct inode *inode), + + TP_ARGS(inode) +); + +DEFINE_EVENT(f2fs__inode_exit, f2fs_iget_exit, + + TP_PROTO(struct inode *inode, int ret), + + TP_ARGS(inode, ret) +); + +DEFINE_EVENT(f2fs__inode, f2fs_evict_inode, + + TP_PROTO(struct inode *inode), + + TP_ARGS(inode) +); + +TRACE_EVENT(f2fs_unlink_enter, + + TP_PROTO(struct inode *dir, struct dentry *dentry), + + TP_ARGS(dir, dentry), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(loff_t, size) + __field(blkcnt_t, blocks) + __field(const char *, name) + ), + + TP_fast_assign( + __entry->dev = dir->i_sb->s_dev; + __entry->ino = dir->i_ino; + __entry->size = dir->i_size; + __entry->blocks = dir->i_blocks; + __entry->name = dentry->d_name.name; + ), + + TP_printk("dev = (%d,%d), dir ino = %lu, i_size = %lld, " + "i_blocks = %llu, name = %s", + show_dev_ino(__entry), + __entry->size, + (unsigned long long)__entry->blocks, + __entry->name) +); + +DEFINE_EVENT(f2fs__inode_exit, f2fs_unlink_exit, + + TP_PROTO(struct inode *inode, int ret), + + TP_ARGS(inode, ret) +); +#endif /* _TRACE_F2FS_H */ + + /* This part must be outside protection */ +#include -- cgit v1.2.3 From 51dd62493477923723c797c6da60121ed39900ed Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sat, 20 Apr 2013 01:28:52 +0900 Subject: f2fs: add tracepoints for truncate operation add tracepoints for tracing the truncate operations like truncate node/data blocks, f2fs_truncate etc. Tracepoints are added at entry and exit of operation to trace the success & failure of operation. Signed-off-by: Namjae Jeon Signed-off-by: Pankaj Kumar Acked-by: Steven Rostedt [Jaegeuk: combine and modify the tracepoint structures] Signed-off-by: Jaegeuk Kim --- include/trace/events/f2fs.h | 176 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 176 insertions(+) (limited to 'include') diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index 03bb0dbf468d..4bbd19f79d27 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -189,6 +189,182 @@ DEFINE_EVENT(f2fs__inode_exit, f2fs_unlink_exit, TP_ARGS(inode, ret) ); + +DEFINE_EVENT(f2fs__inode, f2fs_truncate, + + TP_PROTO(struct inode *inode), + + TP_ARGS(inode) +); + +TRACE_EVENT(f2fs_truncate_data_blocks_range, + + TP_PROTO(struct inode *inode, nid_t nid, unsigned int ofs, int free), + + TP_ARGS(inode, nid, ofs, free), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(nid_t, nid) + __field(unsigned int, ofs) + __field(int, free) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->nid = nid; + __entry->ofs = ofs; + __entry->free = free; + ), + + TP_printk("dev = (%d,%d), ino = %lu, nid = %u, offset = %u, freed = %d", + show_dev_ino(__entry), + (unsigned int)__entry->nid, + __entry->ofs, + __entry->free) +); + +DECLARE_EVENT_CLASS(f2fs__truncate_op, + + TP_PROTO(struct inode *inode, u64 from), + + TP_ARGS(inode, from), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(loff_t, size) + __field(blkcnt_t, blocks) + __field(u64, from) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->size = inode->i_size; + __entry->blocks = inode->i_blocks; + __entry->from = from; + ), + + TP_printk("dev = (%d,%d), ino = %lu, i_size = %lld, i_blocks = %llu, " + "start file offset = %llu", + show_dev_ino(__entry), + __entry->size, + (unsigned long long)__entry->blocks, + (unsigned long long)__entry->from) +); + +DEFINE_EVENT(f2fs__truncate_op, f2fs_truncate_blocks_enter, + + TP_PROTO(struct inode *inode, u64 from), + + TP_ARGS(inode, from) +); + +DEFINE_EVENT(f2fs__inode_exit, f2fs_truncate_blocks_exit, + + TP_PROTO(struct inode *inode, int ret), + + TP_ARGS(inode, ret) +); + +DEFINE_EVENT(f2fs__truncate_op, f2fs_truncate_inode_blocks_enter, + + TP_PROTO(struct inode *inode, u64 from), + + TP_ARGS(inode, from) +); + +DEFINE_EVENT(f2fs__inode_exit, f2fs_truncate_inode_blocks_exit, + + TP_PROTO(struct inode *inode, int ret), + + TP_ARGS(inode, ret) +); + +DECLARE_EVENT_CLASS(f2fs__truncate_node, + + TP_PROTO(struct inode *inode, nid_t nid, block_t blk_addr), + + TP_ARGS(inode, nid, blk_addr), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(nid_t, nid) + __field(block_t, blk_addr) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->nid = nid; + __entry->blk_addr = blk_addr; + ), + + TP_printk("dev = (%d,%d), ino = %lu, nid = %u, block_address = 0x%llx", + show_dev_ino(__entry), + (unsigned int)__entry->nid, + (unsigned long long)__entry->blk_addr) +); + +DEFINE_EVENT(f2fs__truncate_node, f2fs_truncate_nodes_enter, + + TP_PROTO(struct inode *inode, nid_t nid, block_t blk_addr), + + TP_ARGS(inode, nid, blk_addr) +); + +DEFINE_EVENT(f2fs__inode_exit, f2fs_truncate_nodes_exit, + + TP_PROTO(struct inode *inode, int ret), + + TP_ARGS(inode, ret) +); + +DEFINE_EVENT(f2fs__truncate_node, f2fs_truncate_node, + + TP_PROTO(struct inode *inode, nid_t nid, block_t blk_addr), + + TP_ARGS(inode, nid, blk_addr) +); + +TRACE_EVENT(f2fs_truncate_partial_nodes, + + TP_PROTO(struct inode *inode, nid_t nid[], int depth, int err), + + TP_ARGS(inode, nid, depth, err), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(nid_t, nid[3]) + __field(int, depth) + __field(int, err) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->nid[0] = nid[0]; + __entry->nid[1] = nid[1]; + __entry->nid[2] = nid[2]; + __entry->depth = depth; + __entry->err = err; + ), + + TP_printk("dev = (%d,%d), ino = %lu, " + "nid[0] = %u, nid[1] = %u, nid[2] = %u, depth = %d, err = %d", + show_dev_ino(__entry), + (unsigned int)__entry->nid[0], + (unsigned int)__entry->nid[1], + (unsigned int)__entry->nid[2], + __entry->depth, + __entry->err) +); + #endif /* _TRACE_F2FS_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 848753aa3b19a6513315ca54f22ba1e2732ea94a Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Tue, 23 Apr 2013 16:38:02 +0900 Subject: f2fs: add tracepoint for tracing the page i/o Add tracepoints for page i/o operations and block allocation tracing during page read operation. Signed-off-by: Namjae Jeon Signed-off-by: Pankaj Kumar Acked-by: Steven Rostedt [Jaegeuk: combine and modify the tracepoint structures] Signed-off-by: Jaegeuk Kim --- include/trace/events/f2fs.h | 74 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 74 insertions(+) (limited to 'include') diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index 4bbd19f79d27..924e69aa984f 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -8,6 +8,15 @@ #define show_dev(entry) MAJOR(entry->dev), MINOR(entry->dev) #define show_dev_ino(entry) show_dev(entry), (unsigned long)entry->ino +#define show_bio_type(type) \ + __print_symbolic(type, \ + { READ, "READ" }, \ + { READA, "READAHEAD" }, \ + { READ_SYNC, "READ_SYNC" }, \ + { WRITE, "WRITE" }, \ + { WRITE_SYNC, "WRITE_SYNC" }, \ + { WRITE_FLUSH, "WRITE_FLUSH" }, \ + { WRITE_FUA, "WRITE_FUA" }) DECLARE_EVENT_CLASS(f2fs__inode, @@ -365,6 +374,71 @@ TRACE_EVENT(f2fs_truncate_partial_nodes, __entry->err) ); +TRACE_EVENT_CONDITION(f2fs_readpage, + + TP_PROTO(struct page *page, sector_t blkaddr, int type), + + TP_ARGS(page, blkaddr, type), + + TP_CONDITION(page->mapping), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(pgoff_t, index) + __field(sector_t, blkaddr) + __field(int, type) + ), + + TP_fast_assign( + __entry->dev = page->mapping->host->i_sb->s_dev; + __entry->ino = page->mapping->host->i_ino; + __entry->index = page->index; + __entry->blkaddr = blkaddr; + __entry->type = type; + ), + + TP_printk("dev = (%d,%d), ino = %lu, page_index = 0x%lx, " + "blkaddr = 0x%llx, bio_type = %s", + show_dev_ino(__entry), + (unsigned long)__entry->index, + (unsigned long long)__entry->blkaddr, + show_bio_type(__entry->type)) +); + +TRACE_EVENT(f2fs_get_data_block, + TP_PROTO(struct inode *inode, sector_t iblock, + struct buffer_head *bh, int ret), + + TP_ARGS(inode, iblock, bh, ret), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(sector_t, iblock) + __field(sector_t, bh_start) + __field(size_t, bh_size) + __field(int, ret) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->iblock = iblock; + __entry->bh_start = bh->b_blocknr; + __entry->bh_size = bh->b_size; + __entry->ret = ret; + ), + + TP_printk("dev = (%d,%d), ino = %lu, file offset = %llu, " + "start blkaddr = 0x%llx, len = 0x%llx bytes, err = %d", + show_dev_ino(__entry), + (unsigned long long)__entry->iblock, + (unsigned long long)__entry->bh_start, + (unsigned long long)__entry->bh_size, + __entry->ret) +); + #endif /* _TRACE_F2FS_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 8e46b3ed11b750a740fec0a313ad9118059fc37b Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Tue, 23 Apr 2013 16:42:53 +0900 Subject: f2fs: add tracepoints for GC threads Add tracepoints for tracing the garbage collector threads in f2fs with status of collection & type. Signed-off-by: Namjae Jeon Signed-off-by: Pankaj Kumar Acked-by: Steven Rostedt [Jaegeuk: modify slightly to show information] Signed-off-by: Jaegeuk Kim --- include/trace/events/f2fs.h | 75 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 75 insertions(+) (limited to 'include') diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index 924e69aa984f..6f7cf7af8899 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -18,6 +18,33 @@ { WRITE_FLUSH, "WRITE_FLUSH" }, \ { WRITE_FUA, "WRITE_FUA" }) +#define show_data_type(type) \ + __print_symbolic(type, \ + { CURSEG_HOT_DATA, "Hot DATA" }, \ + { CURSEG_WARM_DATA, "Warm DATA" }, \ + { CURSEG_COLD_DATA, "Cold DATA" }, \ + { CURSEG_HOT_NODE, "Hot NODE" }, \ + { CURSEG_WARM_NODE, "Warm NODE" }, \ + { CURSEG_COLD_NODE, "Cold NODE" }, \ + { NO_CHECK_TYPE, "No TYPE" }) + +#define show_gc_type(type) \ + __print_symbolic(type, \ + { FG_GC, "Foreground GC" }, \ + { BG_GC, "Background GC" }) + +#define show_alloc_mode(type) \ + __print_symbolic(type, \ + { LFS, "LFS-mode" }, \ + { SSR, "SSR-mode" }) + +#define show_victim_policy(type) \ + __print_symbolic(type, \ + { GC_GREEDY, "Greedy" }, \ + { GC_CB, "Cost-Benefit" }) + +struct victim_sel_policy; + DECLARE_EVENT_CLASS(f2fs__inode, TP_PROTO(struct inode *inode), @@ -439,6 +466,54 @@ TRACE_EVENT(f2fs_get_data_block, __entry->ret) ); +TRACE_EVENT(f2fs_get_victim, + + TP_PROTO(struct super_block *sb, int type, int gc_type, + struct victim_sel_policy *p, unsigned int pre_victim, + unsigned int prefree, unsigned int free), + + TP_ARGS(sb, type, gc_type, p, pre_victim, prefree, free), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(int, type) + __field(int, gc_type) + __field(int, alloc_mode) + __field(int, gc_mode) + __field(unsigned int, victim) + __field(unsigned int, ofs_unit) + __field(unsigned int, pre_victim) + __field(unsigned int, prefree) + __field(unsigned int, free) + ), + + TP_fast_assign( + __entry->dev = sb->s_dev; + __entry->type = type; + __entry->gc_type = gc_type; + __entry->alloc_mode = p->alloc_mode; + __entry->gc_mode = p->gc_mode; + __entry->victim = p->min_segno; + __entry->ofs_unit = p->ofs_unit; + __entry->pre_victim = pre_victim; + __entry->prefree = prefree; + __entry->free = free; + ), + + TP_printk("dev = (%d,%d), type = %s, policy = (%s, %s, %s), victim = %u " + "ofs_unit = %u, pre_victim_secno = %d, prefree = %u, free = %u", + show_dev(__entry), + show_data_type(__entry->type), + show_gc_type(__entry->gc_type), + show_alloc_mode(__entry->alloc_mode), + show_victim_policy(__entry->gc_mode), + __entry->victim, + __entry->ofs_unit, + (int)__entry->pre_victim, + __entry->prefree, + __entry->free) +); + #endif /* _TRACE_F2FS_H */ /* This part must be outside protection */ -- cgit v1.2.3 From c01e285324793a86c2c90c8451ed6feb04b3d310 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Tue, 23 Apr 2013 17:00:52 +0900 Subject: f2fs: add tracepoints to debug the block allocation Add tracepoints to debug the block allocation & fallocate. Signed-off-by: Namjae Jeon Signed-off-by: Pankaj Kumar Acked-by: Steven Rostedt [Jaegeuk: enhance information] Signed-off-by: Jaegeuk Kim --- include/trace/events/f2fs.h | 64 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 64 insertions(+) (limited to 'include') diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index 6f7cf7af8899..56b6240e6c01 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -514,6 +514,70 @@ TRACE_EVENT(f2fs_get_victim, __entry->free) ); +TRACE_EVENT(f2fs_fallocate, + + TP_PROTO(struct inode *inode, int mode, + loff_t offset, loff_t len, int ret), + + TP_ARGS(inode, mode, offset, len, ret), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(int, mode) + __field(loff_t, offset) + __field(loff_t, len) + __field(loff_t, size) + __field(blkcnt_t, blocks) + __field(int, ret) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->mode = mode; + __entry->offset = offset; + __entry->len = len; + __entry->size = inode->i_size; + __entry->blocks = inode->i_blocks; + __entry->ret = ret; + ), + + TP_printk("dev = (%d,%d), ino = %lu, mode = %x, offset = %lld, " + "len = %lld, i_size = %lld, i_blocks = %llu, ret = %d", + show_dev_ino(__entry), + __entry->mode, + (unsigned long long)__entry->offset, + (unsigned long long)__entry->len, + (unsigned long long)__entry->size, + (unsigned long long)__entry->blocks, + __entry->ret) +); + +TRACE_EVENT(f2fs_reserve_new_block, + + TP_PROTO(struct inode *inode, nid_t nid, unsigned int ofs_in_node), + + TP_ARGS(inode, nid, ofs_in_node), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(nid_t, nid) + __field(unsigned int, ofs_in_node) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->nid = nid; + __entry->ofs_in_node = ofs_in_node; + ), + + TP_printk("dev = (%d,%d), nid = %u, ofs_in_node = %u", + show_dev(__entry), + (unsigned int)__entry->nid, + __entry->ofs_in_node) +); + #endif /* _TRACE_F2FS_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 6ec178dac6768204a6edf70f4a53d40b691c12b4 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Tue, 23 Apr 2013 17:51:43 +0900 Subject: f2fs: add tracepoints for write page operations Add tracepoints to debug the various page write operation like data pages, meta pages. Signed-off-by: Namjae Jeon Signed-off-by: Pankaj Kumar Acked-by: Steven Rostedt [Jaegeuk: remove unnecessary tracepoints] Signed-off-by: Jaegeuk Kim --- include/trace/events/f2fs.h | 67 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 67 insertions(+) (limited to 'include') diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index 56b6240e6c01..ae2da92e0768 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -8,6 +8,14 @@ #define show_dev(entry) MAJOR(entry->dev), MINOR(entry->dev) #define show_dev_ino(entry) show_dev(entry), (unsigned long)entry->ino + +#define show_block_type(type) \ + __print_symbolic(type, \ + { NODE, "NODE" }, \ + { DATA, "DATA" }, \ + { META, "META" }, \ + { META_FLUSH, "META_FLUSH" }) + #define show_bio_type(type) \ __print_symbolic(type, \ { READ, "READ" }, \ @@ -578,6 +586,65 @@ TRACE_EVENT(f2fs_reserve_new_block, __entry->ofs_in_node) ); +TRACE_EVENT(f2fs_do_submit_bio, + + TP_PROTO(struct super_block *sb, int btype, bool sync, struct bio *bio), + + TP_ARGS(sb, btype, sync, bio), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(int, btype) + __field(bool, sync) + __field(sector_t, sector) + __field(unsigned int, size) + ), + + TP_fast_assign( + __entry->dev = sb->s_dev; + __entry->btype = btype; + __entry->sync = sync; + __entry->sector = bio->bi_sector; + __entry->size = bio->bi_size; + ), + + TP_printk("dev = (%d,%d), type = %s, io = %s, sector = %lld, size = %u", + show_dev(__entry), + show_block_type(__entry->btype), + __entry->sync ? "sync" : "no sync", + (unsigned long long)__entry->sector, + __entry->size) +); + +TRACE_EVENT(f2fs_submit_write_page, + + TP_PROTO(struct page *page, block_t blk_addr, int type), + + TP_ARGS(page, blk_addr, type), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(int, type) + __field(pgoff_t, index) + __field(block_t, block) + ), + + TP_fast_assign( + __entry->dev = page->mapping->host->i_sb->s_dev; + __entry->ino = page->mapping->host->i_ino; + __entry->type = type; + __entry->index = page->index; + __entry->block = blk_addr; + ), + + TP_printk("dev = (%d,%d), ino = %lu, %s, index = %lu, blkaddr = 0x%llx", + show_dev_ino(__entry), + show_block_type(__entry->type), + (unsigned long)__entry->index, + (unsigned long long)__entry->block) +); + #endif /* _TRACE_F2FS_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 2af4bd6ca556d690ee166200abd16fdbe749782e Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Tue, 23 Apr 2013 18:26:54 +0900 Subject: f2fs: add tracepoints to debug checkpoint request Add tracepoints to debug checkpoint request. Signed-off-by: Namjae Jeon Signed-off-by: Pankaj Kumar Acked-by: Steven Rostedt [Jaegeuk: change expressions] Signed-off-by: Jaegeuk Kim --- include/trace/events/f2fs.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include') diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index ae2da92e0768..b2b2f72a023d 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -645,6 +645,30 @@ TRACE_EVENT(f2fs_submit_write_page, (unsigned long long)__entry->block) ); +TRACE_EVENT(f2fs_write_checkpoint, + + TP_PROTO(struct super_block *sb, bool is_umount, char *msg), + + TP_ARGS(sb, is_umount, msg), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(bool, is_umount) + __field(char *, msg) + ), + + TP_fast_assign( + __entry->dev = sb->s_dev; + __entry->is_umount = is_umount; + __entry->msg = msg; + ), + + TP_printk("dev = (%d,%d), checkpoint for %s, state = %s", + show_dev(__entry), + __entry->is_umount ? "clean umount" : "consistency", + __entry->msg) +); + #endif /* _TRACE_F2FS_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 871dd9286e25330c8a581e5dacfa8b1dfe1dd641 Mon Sep 17 00:00:00 2001 From: James Bottomley Date: Wed, 24 Apr 2013 08:52:50 -0600 Subject: block: fix max discard sectors limit linux-v3.8-rc1 and later support for plug for blkdev_issue_discard with commit 0cfbcafcae8b7364b5fa96c2b26ccde7a3a296a9 (block: add plug for blkdev_issue_discard ) For example, 1) DISCARD rq-1 with size size 4GB 2) DISCARD rq-2 with size size 1GB If these 2 discard requests get merged, final request size will be 5GB. In this case, request's __data_len field may overflow as it can store max 4GB(unsigned int). This issue was observed while doing mkfs.f2fs on 5GB SD card: https://lkml.org/lkml/2013/4/1/292 Info: sector size = 512 Info: total sectors = 11370496 (in 512bytes) Info: zone aligned segment0 blkaddr: 512 [ 257.789764] blk_update_request: bio idx 0 >= vcnt 0 mkfs process gets stuck in D state and I see the following in the dmesg: [ 257.789733] __end_that: dev mmcblk0: type=1, flags=122c8081 [ 257.789764] sector 4194304, nr/cnr 2981888/4294959104 [ 257.789764] bio df3840c0, biotail df3848c0, buffer (null), len 1526726656 [ 257.789764] blk_update_request: bio idx 0 >= vcnt 0 [ 257.794921] request botched: dev mmcblk0: type=1, flags=122c8081 [ 257.794921] sector 4194304, nr/cnr 2981888/4294959104 [ 257.794921] bio df3840c0, biotail df3848c0, buffer (null), len 1526726656 This patch fixes this issue. Reported-by: Max Filippov Signed-off-by: James Bottomley Signed-off-by: Namjae Jeon Tested-by: Max Filippov Cc: Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 89d89c7162aa..6189bf26b53d 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -844,7 +844,7 @@ static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q, unsigned int cmd_flags) { if (unlikely(cmd_flags & REQ_DISCARD)) - return q->limits.max_discard_sectors; + return min(q->limits.max_discard_sectors, UINT_MAX >> 9); if (unlikely(cmd_flags & REQ_WRITE_SAME)) return q->limits.max_write_same_sectors; -- cgit v1.2.3 From 198f38f7fb2d0956cc3394655d03cdb7054b0dcd Mon Sep 17 00:00:00 2001 From: Eduardo Valentin Date: Wed, 24 Apr 2013 23:10:28 +0800 Subject: thermal: cpu_cooling: add needed header for cpu_cooling.h Update header list for cpu_cooling.h. Missing definition of cpumask. Signed-off-by: Eduardo Valentin Acked-by: Amit Daniel Kachhap Signed-off-by: Zhang Rui --- include/linux/cpu_cooling.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpu_cooling.h b/include/linux/cpu_cooling.h index 77c87c9d0193..75ef931fc4fc 100644 --- a/include/linux/cpu_cooling.h +++ b/include/linux/cpu_cooling.h @@ -25,6 +25,7 @@ #define __CPU_COOLING_H__ #include +#include #define CPUFREQ_COOLING_START 0 #define CPUFREQ_COOLING_STOP 1 -- cgit v1.2.3 From e44dec77be9e032ff9c2f95f17f7df3a55b58f60 Mon Sep 17 00:00:00 2001 From: Eduardo Valentin Date: Wed, 17 Apr 2013 17:12:22 +0000 Subject: thermal: cpu_cooling: remove unused symbols on cpu_cooling.h Remove defines that are not in used. Signed-off-by: Eduardo Valentin Acked-by: Amit Daniel Kachhap Signed-off-by: Zhang Rui --- include/linux/cpu_cooling.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/cpu_cooling.h b/include/linux/cpu_cooling.h index 75ef931fc4fc..f48f6fbcd3be 100644 --- a/include/linux/cpu_cooling.h +++ b/include/linux/cpu_cooling.h @@ -27,9 +27,6 @@ #include #include -#define CPUFREQ_COOLING_START 0 -#define CPUFREQ_COOLING_STOP 1 - #ifdef CONFIG_CPU_THERMAL /** * cpufreq_cooling_register - function to create cpufreq cooling device. -- cgit v1.2.3 From 7b73c993776b9f7d833dde7d09fd861508c54777 Mon Sep 17 00:00:00 2001 From: Eduardo Valentin Date: Tue, 23 Apr 2013 21:48:14 +0000 Subject: thermal: rename notify_thermal_framework to thermal_notify_framework To follow the prefix names used by the thermal functions, this patch renames notify_thermal_framework to thermal_notify_framework. Signed-off-by: Eduardo Valentin Signed-off-by: Zhang Rui --- include/linux/thermal.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index ec2b886f9d96..d7272ab20ebc 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -246,7 +246,7 @@ int get_tz_trend(struct thermal_zone_device *, int); struct thermal_instance *get_thermal_instance(struct thermal_zone_device *, struct thermal_cooling_device *, int); void thermal_cdev_update(struct thermal_cooling_device *); -void notify_thermal_framework(struct thermal_zone_device *, int); +void thermal_notify_framework(struct thermal_zone_device *, int); #ifdef CONFIG_NET extern int thermal_generate_netlink_event(struct thermal_zone_device *tz, -- cgit v1.2.3 From aa16bea929aed6ea854b55d2be8306a9fb40e694 Mon Sep 17 00:00:00 2001 From: Alexey Kardashevskiy Date: Mon, 25 Mar 2013 10:23:49 +1100 Subject: iommu: Add a function to find an iommu group by id As IOMMU groups are exposed to the user space by their numbers, the user space can use them in various kernel APIs so the kernel might need an API to find a group by its ID. As an example, QEMU VFIO on PPC64 platform needs it to associate a logical bus number (LIOBN) with a specific IOMMU group in order to support in-kernel handling of DMA map/unmap requests. The patch adds the iommu_group_get_by_id(id) function which performs such search. v2: fixed reference counting. Signed-off-by: Alexey Kardashevskiy Acked-by: Alex Williamson Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 6a027dc8dbfe..8e1b5be72b02 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -126,6 +126,7 @@ struct iommu_ops { extern int bus_set_iommu(struct bus_type *bus, struct iommu_ops *ops); extern bool iommu_present(struct bus_type *bus); extern struct iommu_domain *iommu_domain_alloc(struct bus_type *bus); +extern struct iommu_group *iommu_group_get_by_id(int id); extern void iommu_domain_free(struct iommu_domain *domain); extern int iommu_attach_device(struct iommu_domain *domain, struct device *dev); -- cgit v1.2.3 From 3cd0e1789ad39c3b7ed006ce53a83328bdadbee8 Mon Sep 17 00:00:00 2001 From: Hadar Hen Zion Date: Wed, 24 Apr 2013 13:58:44 +0000 Subject: mlx4_core: Move DMFS HW structs to common header file Move flow steering HW structures to be on the public mlx4 include directory, as a pre-step for the mlx4 IB driver to use them too. Signed-off-by: Hadar Hen Zion Signed-off-by: Or Gerlitz Signed-off-by: Roland Dreier --- include/linux/mlx4/device.h | 79 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 79 insertions(+) (limited to 'include') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 811f91cf5e8c..9fbf416fa694 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -962,6 +962,85 @@ struct mlx4_net_trans_rule { u32 qpn; }; +struct mlx4_net_trans_rule_hw_ctrl { + __be32 ctrl; + u8 rsvd1; + u8 funcid; + u8 vep; + u8 port; + __be32 qpn; + __be32 rsvd2; +}; + +struct mlx4_net_trans_rule_hw_ib { + u8 size; + u8 rsvd1; + __be16 id; + u32 rsvd2; + __be32 qpn; + __be32 qpn_mask; + u8 dst_gid[16]; + u8 dst_gid_msk[16]; +} __packed; + +struct mlx4_net_trans_rule_hw_eth { + u8 size; + u8 rsvd; + __be16 id; + u8 rsvd1[6]; + u8 dst_mac[6]; + u16 rsvd2; + u8 dst_mac_msk[6]; + u16 rsvd3; + u8 src_mac[6]; + u16 rsvd4; + u8 src_mac_msk[6]; + u8 rsvd5; + u8 ether_type_enable; + __be16 ether_type; + __be16 vlan_id_msk; + __be16 vlan_id; +} __packed; + +struct mlx4_net_trans_rule_hw_tcp_udp { + u8 size; + u8 rsvd; + __be16 id; + __be16 rsvd1[3]; + __be16 dst_port; + __be16 rsvd2; + __be16 dst_port_msk; + __be16 rsvd3; + __be16 src_port; + __be16 rsvd4; + __be16 src_port_msk; +} __packed; + +struct mlx4_net_trans_rule_hw_ipv4 { + u8 size; + u8 rsvd; + __be16 id; + __be32 rsvd1; + __be32 dst_ip; + __be32 dst_ip_msk; + __be32 src_ip; + __be32 src_ip_msk; +} __packed; + +struct _rule_hw { + union { + struct { + u8 size; + u8 rsvd; + __be16 id; + }; + struct mlx4_net_trans_rule_hw_eth eth; + struct mlx4_net_trans_rule_hw_ib ib; + struct mlx4_net_trans_rule_hw_ipv4 ipv4; + struct mlx4_net_trans_rule_hw_tcp_udp tcp_udp; + }; +}; + int mlx4_flow_steer_promisc_add(struct mlx4_dev *dev, u8 port, u32 qpn, enum mlx4_net_trans_promisc_mode mode); int mlx4_flow_steer_promisc_remove(struct mlx4_dev *dev, u8 port, -- cgit v1.2.3 From f91625398a2e6e03f0155861b630021ceddb42e7 Mon Sep 17 00:00:00 2001 From: Hadar Hen Zion Date: Wed, 24 Apr 2013 13:58:45 +0000 Subject: mlx4: Match DMFS promiscuous field names to firmware spec Align the names used by enum mlx4_net_trans_promisc_mode with the actual firmware specification. The patch doesn't introduce any functional change or API change towards the firmware. Remove MLX4_FS_PROMISC_FUNCTION_PORT which isn't of use. Add new enums MLX4_FS_{UC/MC}_SNIFFER as a preparation step for sniffer support. Signed-off-by: Hadar Hen Zion Signed-off-by: Or Gerlitz Signed-off-by: Roland Dreier --- include/linux/mlx4/device.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 9fbf416fa694..b2fe59d199f8 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -896,11 +896,12 @@ static inline int map_hw_to_sw_id(u16 header_id) } enum mlx4_net_trans_promisc_mode { - MLX4_FS_PROMISC_NONE = 0, - MLX4_FS_PROMISC_UPLINK, - /* For future use. Not implemented yet */ - MLX4_FS_PROMISC_FUNCTION_PORT, - MLX4_FS_PROMISC_ALL_MULTI, + MLX4_FS_REGULAR = 1, + MLX4_FS_ALL_DEFAULT, + MLX4_FS_MC_DEFAULT, + MLX4_FS_UC_SNIFFER, + MLX4_FS_MC_SNIFFER, + }; struct mlx4_spec_eth { -- cgit v1.2.3 From ba60a3560ccf8e4253da9c0e8d1292375fd51796 Mon Sep 17 00:00:00 2001 From: Hadar Hen Zion Date: Wed, 24 Apr 2013 13:58:46 +0000 Subject: mlx4_core: Change a few DMFS fields names to match firmare spec Change struct mlx4_net_trans_rule_hw_eth :: vlan_id name to vlan_tag Change struct mlx4_net_trans_rule_hw_ib :: r_u_qpn name to l3_qpn The patch doesn't introduce any functional change or API change towards the firmware. Signed-off-by: Hadar Hen Zion Signed-off-by: Or Gerlitz Signed-off-by: Roland Dreier --- include/linux/mlx4/device.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index b2fe59d199f8..a69bda77c1d1 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -930,7 +930,7 @@ struct mlx4_spec_ipv4 { }; struct mlx4_spec_ib { - __be32 r_qpn; + __be32 l3_qpn; __be32 qpn_msk; u8 dst_gid[16]; u8 dst_gid_msk[16]; @@ -978,7 +978,7 @@ struct mlx4_net_trans_rule_hw_ib { u8 rsvd1; __be16 id; u32 rsvd2; - __be32 qpn; + __be32 l3_qpn; __be32 qpn_mask; u8 dst_gid[16]; u8 dst_gid_msk[16]; @@ -999,8 +999,8 @@ struct mlx4_net_trans_rule_hw_eth { u8 rsvd5; u8 ether_type_enable; __be16 ether_type; - __be16 vlan_id_msk; - __be16 vlan_id; + __be16 vlan_tag_msk; + __be16 vlan_tag; } __packed; struct mlx4_net_trans_rule_hw_tcp_udp { -- cgit v1.2.3 From bcf372971d471f6cb4070adb7bfc987d8b3d21f2 Mon Sep 17 00:00:00 2001 From: Hadar Hen Zion Date: Wed, 24 Apr 2013 13:58:47 +0000 Subject: mlx4_core: Directly expose fields of DMFS HW rule control segment Some of struct mlx4_net_trans_rule_hw_ctrl fields were packed into u32 and accessed through bit field operations. Expose and access them directly as u8 or u16. Signed-off-by: Hadar Hen Zion Signed-off-by: Or Gerlitz Signed-off-by: Roland Dreier --- include/linux/mlx4/device.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index a69bda77c1d1..08e5bc1387e1 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -964,7 +964,9 @@ struct mlx4_net_trans_rule { }; struct mlx4_net_trans_rule_hw_ctrl { - __be32 ctrl; + __be16 prio; + u8 type; + u8 flags; u8 rsvd1; u8 funcid; u8 vep; -- cgit v1.2.3 From c2c19dc3c9a1585e58804041e5a328cde425403a Mon Sep 17 00:00:00 2001 From: Hadar Hen Zion Date: Wed, 24 Apr 2013 13:58:48 +0000 Subject: mlx4_core: Expose a few helpers to fill DMFS HW strucutures Re-arrange some of code which fills DMFS HW structures so we can use it from within the core driver and from the IB driver too, e.g when verbs DMFS structures are transformed into mlx4 hardware structs. Also, add struct mlx4_flow_handle struct which will be of use by the DMFS verbs flow in the IB driver. Signed-off-by: Hadar Hen Zion Signed-off-by: Or Gerlitz Signed-off-by: Roland Dreier --- include/linux/mlx4/device.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 08e5bc1387e1..ad4a53fbdddf 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -901,7 +901,7 @@ enum mlx4_net_trans_promisc_mode { MLX4_FS_MC_DEFAULT, MLX4_FS_UC_SNIFFER, MLX4_FS_MC_SNIFFER, - + MLX4_FS_MODE_NUM, /* should be last */ }; struct mlx4_spec_eth { @@ -1044,6 +1044,11 @@ struct _rule_hw { }; }; +/* translating DMFS verbs sniffer rule to the FW API would need two reg IDs */ +struct mlx4_flow_handle { + u64 reg_id[2]; +}; + int mlx4_flow_steer_promisc_add(struct mlx4_dev *dev, u8 port, u32 qpn, enum mlx4_net_trans_promisc_mode mode); int mlx4_flow_steer_promisc_remove(struct mlx4_dev *dev, u8 port, @@ -1093,6 +1098,11 @@ void mlx4_counter_free(struct mlx4_dev *dev, u32 idx); int mlx4_flow_attach(struct mlx4_dev *dev, struct mlx4_net_trans_rule *rule, u64 *reg_id); int mlx4_flow_detach(struct mlx4_dev *dev, u64 reg_id); +int mlx4_map_sw_to_hw_steering_mode(struct mlx4_dev *dev, + enum mlx4_net_trans_promisc_mode flow_type); +int mlx4_map_sw_to_hw_steering_id(struct mlx4_dev *dev, + enum mlx4_net_trans_rule_id id); +int mlx4_hw_rule_sz(struct mlx4_dev *dev, enum mlx4_net_trans_rule_id id); void mlx4_sync_pkey_table(struct mlx4_dev *dev, int slave, int port, int i, int val); -- cgit v1.2.3 From 99f4c6b66a9ae362d21e6df95d04bc74e04d285e Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Fri, 26 Apr 2013 17:23:26 +0200 Subject: mfd: si476x: Don't use 0bNNN This doesn't compile with sparc64 gcc-3.4.5. Cc: Hans Verkuil Cc: Sam Ravnborg Cc: Andrey Smirnov Signed-off-by: Andrew Morton Signed-off-by: Samuel Ortiz --- include/linux/mfd/si476x-core.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/mfd/si476x-core.h b/include/linux/mfd/si476x-core.h index ede3022c03c4..ba89b94e4a56 100644 --- a/include/linux/mfd/si476x-core.h +++ b/include/linux/mfd/si476x-core.h @@ -515,11 +515,11 @@ enum si476x_fm_receiver_properties { }; enum si476x_prop_audio_pwr_line_filter_bits { - SI476X_PROP_PWR_HARMONICS_MASK = 0b0000000000011111, - SI476X_PROP_PWR_GRID_MASK = 0b0000000100000000, - SI476X_PROP_PWR_ENABLE_MASK = 0b0000001000000000, - SI476X_PROP_PWR_GRID_50HZ = 0b0000000000000000, - SI476X_PROP_PWR_GRID_60HZ = 0b0000000100000000, + SI476X_PROP_PWR_HARMONICS_MASK = 0x001f, + SI476X_PROP_PWR_GRID_MASK = 0x0100, + SI476X_PROP_PWR_ENABLE_MASK = 0x0200, + SI476X_PROP_PWR_GRID_50HZ = 0x0000, + SI476X_PROP_PWR_GRID_60HZ = 0x0100, }; enum si476x_prop_fm_rds_config_bits { -- cgit v1.2.3 From 8175e5b79c38a1d85225da516fa1a0ecbf2fdbca Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Mon, 15 Apr 2013 10:42:33 +0200 Subject: KVM: Add KVM_IRQCHIP_NUM_PINS in addition to KVM_IOAPIC_NUM_PINS The concept of routing interrupt lines to an irqchip is nothing that is IOAPIC specific. Every irqchip has a maximum number of pins that can be linked to irq lines. So let's add a new define that allows us to reuse generic code for non-IOAPIC platforms. Signed-off-by: Alexander Graf Acked-by: Michael S. Tsirkin --- include/linux/kvm_host.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 93a50054d46c..bf3b1dcb8b3d 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -307,7 +307,7 @@ struct kvm_kernel_irq_routing_entry { #ifdef __KVM_HAVE_IOAPIC struct kvm_irq_routing_table { - int chip[KVM_NR_IRQCHIPS][KVM_IOAPIC_NUM_PINS]; + int chip[KVM_NR_IRQCHIPS][KVM_IRQCHIP_NUM_PINS]; struct kvm_kernel_irq_routing_entry *rt_entries; u32 nr_rt_entries; /* -- cgit v1.2.3 From a725d56a02ec3582bb5b9756f261fdc6962c79ee Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Wed, 17 Apr 2013 13:29:30 +0200 Subject: KVM: Introduce CONFIG_HAVE_KVM_IRQ_ROUTING Quite a bit of code in KVM has been conditionalized on availability of IOAPIC emulation. However, most of it is generically applicable to platforms that don't have an IOPIC, but a different type of irq chip. Make code that only relies on IRQ routing, not an APIC itself, on CONFIG_HAVE_KVM_IRQ_ROUTING, so that we can reuse it later. Signed-off-by: Alexander Graf Acked-by: Michael S. Tsirkin --- include/linux/kvm_host.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index bf3b1dcb8b3d..4215d4f3d86f 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -304,7 +304,7 @@ struct kvm_kernel_irq_routing_entry { struct hlist_node link; }; -#ifdef __KVM_HAVE_IOAPIC +#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING struct kvm_irq_routing_table { int chip[KVM_NR_IRQCHIPS][KVM_IRQCHIP_NUM_PINS]; @@ -432,7 +432,7 @@ void kvm_vcpu_uninit(struct kvm_vcpu *vcpu); int __must_check vcpu_load(struct kvm_vcpu *vcpu); void vcpu_put(struct kvm_vcpu *vcpu); -#ifdef __KVM_HAVE_IOAPIC +#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING int kvm_irqfd_init(void); void kvm_irqfd_exit(void); #else @@ -957,7 +957,7 @@ static inline int mmu_notifier_retry(struct kvm *kvm, unsigned long mmu_seq) } #endif -#ifdef KVM_CAP_IRQ_ROUTING +#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING #define KVM_MAX_IRQ_ROUTES 1024 -- cgit v1.2.3 From 948a902c842aaef49af9e48b00469229b04a43a9 Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Mon, 15 Apr 2013 10:49:31 +0200 Subject: KVM: Drop __KVM_HAVE_IOAPIC condition on irq routing We have a capability enquire system that allows user space to ask kvm whether a feature is available. The point behind this system is that we can have different kernel configurations with different capabilities and user space can adjust accordingly. Because features can always be non existent, we can drop any #ifdefs on CAP defines that could be used generically, like the irq routing bits. These can be easily reused for non-IOAPIC systems as well. Signed-off-by: Alexander Graf Acked-by: Michael S. Tsirkin --- include/uapi/linux/kvm.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 74d0ff3dfd66..c741902c9e0b 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -579,9 +579,7 @@ struct kvm_ppc_smmu_info { #ifdef __KVM_HAVE_PIT #define KVM_CAP_REINJECT_CONTROL 24 #endif -#ifdef __KVM_HAVE_IOAPIC #define KVM_CAP_IRQ_ROUTING 25 -#endif #define KVM_CAP_IRQ_INJECT_STATUS 26 #ifdef __KVM_HAVE_DEVICE_ASSIGNMENT #define KVM_CAP_DEVICE_DEASSIGNMENT 27 -- cgit v1.2.3 From 7eee2efdc6978aa70ab4046394128c1a10bc2d80 Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Mon, 15 Apr 2013 10:50:54 +0200 Subject: KVM: Remove kvm_get_intr_delivery_bitmask The prototype has been stale for a while, I can't spot any real function define behind it. Let's just remove it. Signed-off-by: Alexander Graf Acked-by: Michael S. Tsirkin --- include/linux/kvm_host.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 4215d4f3d86f..a7bfe9d3aa5e 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -719,11 +719,6 @@ void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq, void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin, bool mask); -#ifdef __KVM_HAVE_IOAPIC -void kvm_get_intr_delivery_bitmask(struct kvm_ioapic *ioapic, - union kvm_ioapic_redirect_entry *entry, - unsigned long *deliver_bitmask); -#endif int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level, bool line_status); int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level); -- cgit v1.2.3 From 1c9f8520bda73c07fed9bcdb307854b45a3a60c4 Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Mon, 15 Apr 2013 23:04:10 +0200 Subject: KVM: Extract generic irqchip logic into irqchip.c The current irq_comm.c file contains pieces of code that are generic across different irqchip implementations, as well as code that is fully IOAPIC specific. Split the generic bits out into irqchip.c. Signed-off-by: Alexander Graf Acked-by: Michael S. Tsirkin --- include/trace/events/kvm.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h index 19911dddaeb7..7005d1109ec9 100644 --- a/include/trace/events/kvm.h +++ b/include/trace/events/kvm.h @@ -37,7 +37,7 @@ TRACE_EVENT(kvm_userspace_exit, __entry->errno < 0 ? -__entry->errno : __entry->reason) ); -#if defined(__KVM_HAVE_IRQ_LINE) +#if defined(CONFIG_HAVE_KVM_IRQCHIP) TRACE_EVENT(kvm_set_irq, TP_PROTO(unsigned int gsi, int level, int irq_source_id), TP_ARGS(gsi, level, irq_source_id), @@ -122,6 +122,10 @@ TRACE_EVENT(kvm_msi_set_irq, {KVM_IRQCHIP_PIC_SLAVE, "PIC slave"}, \ {KVM_IRQCHIP_IOAPIC, "IOAPIC"} +#endif /* defined(__KVM_HAVE_IOAPIC) */ + +#if defined(CONFIG_HAVE_KVM_IRQCHIP) + TRACE_EVENT(kvm_ack_irq, TP_PROTO(unsigned int irqchip, unsigned int pin), TP_ARGS(irqchip, pin), @@ -136,14 +140,18 @@ TRACE_EVENT(kvm_ack_irq, __entry->pin = pin; ), +#ifdef kvm_irqchips TP_printk("irqchip %s pin %u", __print_symbolic(__entry->irqchip, kvm_irqchips), __entry->pin) +#else + TP_printk("irqchip %d pin %u", __entry->irqchip, __entry->pin) +#endif ); +#endif /* defined(CONFIG_HAVE_KVM_IRQCHIP) */ -#endif /* defined(__KVM_HAVE_IOAPIC) */ #define KVM_TRACE_MMIO_READ_UNSATISFIED 0 #define KVM_TRACE_MMIO_READ 1 -- cgit v1.2.3 From e8cde0939d8ebe9c8ebe5a4bdf71af51a0d56053 Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Mon, 15 Apr 2013 23:23:21 +0200 Subject: KVM: Move irq routing setup to irqchip.c Setting up IRQ routes is nothing IOAPIC specific. Extract everything that really is generic code into irqchip.c and only leave the ioapic specific bits to irq_comm.c. Signed-off-by: Alexander Graf Acked-by: Michael S. Tsirkin --- include/linux/kvm_host.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index a7bfe9d3aa5e..dcef724f4ba6 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -961,6 +961,9 @@ int kvm_set_irq_routing(struct kvm *kvm, const struct kvm_irq_routing_entry *entries, unsigned nr, unsigned flags); +int kvm_set_routing_entry(struct kvm_irq_routing_table *rt, + struct kvm_kernel_irq_routing_entry *e, + const struct kvm_irq_routing_entry *ue); void kvm_free_irq_routing(struct kvm *kvm); int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi); -- cgit v1.2.3 From 852b6d57dc7fa378019786fa84727036e56839ea Mon Sep 17 00:00:00 2001 From: Scott Wood Date: Fri, 12 Apr 2013 14:08:42 +0000 Subject: kvm: add device control API Currently, devices that are emulated inside KVM are configured in a hardcoded manner based on an assumption that any given architecture only has one way to do it. If there's any need to access device state, it is done through inflexible one-purpose-only IOCTLs (e.g. KVM_GET/SET_LAPIC). Defining new IOCTLs for every little thing is cumbersome and depletes a limited numberspace. This API provides a mechanism to instantiate a device of a certain type, returning an ID that can be used to set/get attributes of the device. Attributes may include configuration parameters (e.g. register base address), device state, operational commands, etc. It is similar to the ONE_REG API, except that it acts on devices rather than vcpus. Both device types and individual attributes can be tested without having to create the device or get/set the attribute, without the need for separately managing enumerated capabilities. Signed-off-by: Scott Wood Signed-off-by: Alexander Graf --- include/linux/kvm_host.h | 35 +++++++++++++++++++++++++++++++++++ include/uapi/linux/kvm.h | 27 +++++++++++++++++++++++++++ 2 files changed, 62 insertions(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index dcef724f4ba6..6dab6b5b3e3b 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1064,6 +1064,41 @@ static inline bool kvm_check_request(int req, struct kvm_vcpu *vcpu) extern bool kvm_rebooting; +struct kvm_device_ops; + +struct kvm_device { + struct kvm_device_ops *ops; + struct kvm *kvm; + atomic_t users; + void *private; +}; + +/* create, destroy, and name are mandatory */ +struct kvm_device_ops { + const char *name; + int (*create)(struct kvm_device *dev, u32 type); + + /* + * Destroy is responsible for freeing dev. + * + * Destroy may be called before or after destructors are called + * on emulated I/O regions, depending on whether a reference is + * held by a vcpu or other kvm component that gets destroyed + * after the emulated I/O. + */ + void (*destroy)(struct kvm_device *dev); + + int (*set_attr)(struct kvm_device *dev, struct kvm_device_attr *attr); + int (*get_attr)(struct kvm_device *dev, struct kvm_device_attr *attr); + int (*has_attr)(struct kvm_device *dev, struct kvm_device_attr *attr); + long (*ioctl)(struct kvm_device *dev, unsigned int ioctl, + unsigned long arg); +}; + +void kvm_device_get(struct kvm_device *dev); +void kvm_device_put(struct kvm_device *dev); +struct kvm_device *kvm_device_from_filp(struct file *filp); + #ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT static inline void kvm_vcpu_set_in_spin_loop(struct kvm_vcpu *vcpu, bool val) diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index c741902c9e0b..38a0be0c199f 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -666,6 +666,7 @@ struct kvm_ppc_smmu_info { #define KVM_CAP_PPC_EPR 86 #define KVM_CAP_ARM_PSCI 87 #define KVM_CAP_ARM_SET_DEVICE_ADDR 88 +#define KVM_CAP_DEVICE_CTRL 89 #ifdef KVM_CAP_IRQ_ROUTING @@ -818,6 +819,24 @@ struct kvm_arm_device_addr { __u64 addr; }; +/* + * Device control API, available with KVM_CAP_DEVICE_CTRL + */ +#define KVM_CREATE_DEVICE_TEST 1 + +struct kvm_create_device { + __u32 type; /* in: KVM_DEV_TYPE_xxx */ + __u32 fd; /* out: device handle */ + __u32 flags; /* in: KVM_CREATE_DEVICE_xxx */ +}; + +struct kvm_device_attr { + __u32 flags; /* no flags currently defined */ + __u32 group; /* device-defined */ + __u64 attr; /* group-defined */ + __u64 addr; /* userspace address of attr data */ +}; + /* * ioctls for VM fds */ @@ -906,6 +925,14 @@ struct kvm_s390_ucas_mapping { /* Available with KVM_CAP_ARM_SET_DEVICE_ADDR */ #define KVM_ARM_SET_DEVICE_ADDR _IOW(KVMIO, 0xab, struct kvm_arm_device_addr) +/* ioctl for vm fd */ +#define KVM_CREATE_DEVICE _IOWR(KVMIO, 0xe0, struct kvm_create_device) + +/* ioctls for fds returned by KVM_CREATE_DEVICE */ +#define KVM_SET_DEVICE_ATTR _IOW(KVMIO, 0xe1, struct kvm_device_attr) +#define KVM_GET_DEVICE_ATTR _IOW(KVMIO, 0xe2, struct kvm_device_attr) +#define KVM_HAS_DEVICE_ATTR _IOW(KVMIO, 0xe3, struct kvm_device_attr) + /* * ioctls for vcpu fds */ -- cgit v1.2.3 From 5df554ad5b7522ea62b0ff9d5be35183494efc21 Mon Sep 17 00:00:00 2001 From: Scott Wood Date: Fri, 12 Apr 2013 14:08:46 +0000 Subject: kvm/ppc/mpic: in-kernel MPIC emulation Hook the MPIC code up to the KVM interfaces, add locking, etc. Signed-off-by: Scott Wood [agraf: add stub function for kvmppc_mpic_set_epr, non-booke, 64bit] Signed-off-by: Alexander Graf --- include/linux/kvm_host.h | 2 ++ include/uapi/linux/kvm.h | 3 +++ 2 files changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 6dab6b5b3e3b..feffbdaf8986 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1099,6 +1099,8 @@ void kvm_device_get(struct kvm_device *dev); void kvm_device_put(struct kvm_device *dev); struct kvm_device *kvm_device_from_filp(struct file *filp); +extern struct kvm_device_ops kvm_mpic_ops; + #ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT static inline void kvm_vcpu_set_in_spin_loop(struct kvm_vcpu *vcpu, bool val) diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 38a0be0c199f..4148becdc93f 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -837,6 +837,9 @@ struct kvm_device_attr { __u64 addr; /* userspace address of attr data */ }; +#define KVM_DEV_TYPE_FSL_MPIC_20 1 +#define KVM_DEV_TYPE_FSL_MPIC_42 2 + /* * ioctls for VM fds */ -- cgit v1.2.3 From eb1e4f43e0f47f2655372c7d32c43db9711c278e Mon Sep 17 00:00:00 2001 From: Scott Wood Date: Fri, 12 Apr 2013 14:08:47 +0000 Subject: kvm/ppc/mpic: add KVM_CAP_IRQ_MPIC Enabling this capability connects the vcpu to the designated in-kernel MPIC. Using explicit connections between vcpus and irqchips allows for flexibility, but the main benefit at the moment is that it simplifies the code -- KVM doesn't need vm-global state to remember which MPIC object is associated with this vm, and it doesn't need to care about ordering between irqchip creation and vcpu creation. Signed-off-by: Scott Wood [agraf: add stub functions for kvmppc_mpic_{dis,}connect_vcpu] Signed-off-by: Alexander Graf --- include/uapi/linux/kvm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 4148becdc93f..0ebf59b50ed0 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -667,6 +667,7 @@ struct kvm_ppc_smmu_info { #define KVM_CAP_ARM_PSCI 87 #define KVM_CAP_ARM_SET_DEVICE_ADDR 88 #define KVM_CAP_DEVICE_CTRL 89 +#define KVM_CAP_IRQ_MPIC 90 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From 07f0a7bdec5c4039cfb9b836482c45004d4c21cc Mon Sep 17 00:00:00 2001 From: Scott Wood Date: Thu, 25 Apr 2013 14:11:23 +0000 Subject: kvm: destroy emulated devices on VM exit The hassle of getting refcounting right was greater than the hassle of keeping a list of devices to destroy on VM exit. Signed-off-by: Scott Wood Signed-off-by: Alexander Graf --- include/linux/kvm_host.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index feffbdaf8986..36c977694741 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -393,6 +393,7 @@ struct kvm { long mmu_notifier_count; #endif long tlbs_dirty; + struct list_head devices; }; #define kvm_err(fmt, ...) \ @@ -1069,8 +1070,8 @@ struct kvm_device_ops; struct kvm_device { struct kvm_device_ops *ops; struct kvm *kvm; - atomic_t users; void *private; + struct list_head vm_node; }; /* create, destroy, and name are mandatory */ -- cgit v1.2.3 From 8e591cb7204739efa8e15967ea334eb367039dde Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Wed, 17 Apr 2013 20:30:00 +0000 Subject: KVM: PPC: Book3S: Add infrastructure to implement kernel-side RTAS calls For pseries machine emulation, in order to move the interrupt controller code to the kernel, we need to intercept some RTAS calls in the kernel itself. This adds an infrastructure to allow in-kernel handlers to be registered for RTAS services by name. A new ioctl, KVM_PPC_RTAS_DEFINE_TOKEN, then allows userspace to associate token values with those service names. Then, when the guest requests an RTAS service with one of those token values, it will be handled by the relevant in-kernel handler rather than being passed up to userspace as at present. Signed-off-by: Michael Ellerman Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras [agraf: fix warning] Signed-off-by: Alexander Graf --- include/uapi/linux/kvm.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 0ebf59b50ed0..d4005192ad6e 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -668,6 +668,7 @@ struct kvm_ppc_smmu_info { #define KVM_CAP_ARM_SET_DEVICE_ADDR 88 #define KVM_CAP_DEVICE_CTRL 89 #define KVM_CAP_IRQ_MPIC 90 +#define KVM_CAP_PPC_RTAS 91 #ifdef KVM_CAP_IRQ_ROUTING @@ -928,6 +929,8 @@ struct kvm_s390_ucas_mapping { #define KVM_PPC_GET_HTAB_FD _IOW(KVMIO, 0xaa, struct kvm_get_htab_fd) /* Available with KVM_CAP_ARM_SET_DEVICE_ADDR */ #define KVM_ARM_SET_DEVICE_ADDR _IOW(KVMIO, 0xab, struct kvm_arm_device_addr) +/* Available with KVM_CAP_PPC_RTAS */ +#define KVM_PPC_RTAS_DEFINE_TOKEN _IOW(KVMIO, 0xac, struct kvm_rtas_token_args) /* ioctl for vm fd */ #define KVM_CREATE_DEVICE _IOWR(KVMIO, 0xe0, struct kvm_create_device) -- cgit v1.2.3 From d44ada516277f5d58b9bda2ea0a2c9503b316bbf Mon Sep 17 00:00:00 2001 From: Eduardo Valentin Date: Wed, 17 Apr 2013 17:12:23 +0000 Subject: thermal: cpu_cooling: improve line breaking To improve code readiness, change the way the lines are broken in this file. Signed-off-by: Eduardo Valentin Signed-off-by: Zhang Rui --- include/linux/cpu_cooling.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/cpu_cooling.h b/include/linux/cpu_cooling.h index f48f6fbcd3be..282e27028418 100644 --- a/include/linux/cpu_cooling.h +++ b/include/linux/cpu_cooling.h @@ -32,8 +32,8 @@ * cpufreq_cooling_register - function to create cpufreq cooling device. * @clip_cpus: cpumask of cpus where the frequency constraints will happen */ -struct thermal_cooling_device *cpufreq_cooling_register( - const struct cpumask *clip_cpus); +struct thermal_cooling_device * +cpufreq_cooling_register(const struct cpumask *clip_cpus); /** * cpufreq_cooling_unregister - function to remove cpufreq cooling device. @@ -43,18 +43,18 @@ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev); unsigned long cpufreq_cooling_get_level(unsigned int, unsigned int); #else /* !CONFIG_CPU_THERMAL */ -static inline struct thermal_cooling_device *cpufreq_cooling_register( - const struct cpumask *clip_cpus) +static inline struct thermal_cooling_device * +cpufreq_cooling_register(const struct cpumask *clip_cpus) { return NULL; } -static inline void cpufreq_cooling_unregister( - struct thermal_cooling_device *cdev) +static inline +void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev) { return; } -static inline unsigned long cpufreq_cooling_get_level(unsigned int, - unsigned int) +static inline +unsigned long cpufreq_cooling_get_level(unsigned int, unsigned int) { return THERMAL_CSTATE_INVALID; } -- cgit v1.2.3 From 730dca42c1d363c939da18c1499c7327c66e2b37 Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Sun, 28 Apr 2013 10:50:52 +0200 Subject: KVM: x86: Rework request for immediate exit The VMX implementation of enable_irq_window raised KVM_REQ_IMMEDIATE_EXIT after we checked it in vcpu_enter_guest. This caused infinite loops on vmentry. Fix it by letting enable_irq_window signal the need for an immediate exit via its return value and drop KVM_REQ_IMMEDIATE_EXIT. This issue only affects nested VMX scenarios. Signed-off-by: Jan Kiszka Signed-off-by: Gleb Natapov --- include/linux/kvm_host.h | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 93a50054d46c..7bde42470e37 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -119,14 +119,13 @@ static inline bool is_error_page(struct page *page) #define KVM_REQ_APF_HALT 12 #define KVM_REQ_STEAL_UPDATE 13 #define KVM_REQ_NMI 14 -#define KVM_REQ_IMMEDIATE_EXIT 15 -#define KVM_REQ_PMU 16 -#define KVM_REQ_PMI 17 -#define KVM_REQ_WATCHDOG 18 -#define KVM_REQ_MASTERCLOCK_UPDATE 19 -#define KVM_REQ_MCLOCK_INPROGRESS 20 -#define KVM_REQ_EPR_EXIT 21 -#define KVM_REQ_SCAN_IOAPIC 22 +#define KVM_REQ_PMU 15 +#define KVM_REQ_PMI 16 +#define KVM_REQ_WATCHDOG 17 +#define KVM_REQ_MASTERCLOCK_UPDATE 18 +#define KVM_REQ_MCLOCK_INPROGRESS 19 +#define KVM_REQ_EPR_EXIT 20 +#define KVM_REQ_SCAN_IOAPIC 21 #define KVM_USERSPACE_IRQ_SOURCE_ID 0 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID 1 -- cgit v1.2.3 From 2a5bab1004729f3302c776e53ee7c895b98bb1ce Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Tue, 16 Apr 2013 13:49:18 -0600 Subject: kvm: Allow build-time configuration of KVM device assignment We hope to at some point deprecate KVM legacy device assignment in favor of VFIO-based assignment. Towards that end, allow legacy device assignment to be deconfigured. Signed-off-by: Alex Williamson Reviewed-by: Alexander Graf Acked-by: Michael S. Tsirkin Signed-off-by: Gleb Natapov --- include/linux/kvm_host.h | 30 ++++++++---------------------- include/uapi/linux/kvm.h | 4 ---- 2 files changed, 8 insertions(+), 26 deletions(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 309774715897..996661eb8e99 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -667,7 +667,6 @@ static inline wait_queue_head_t *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu) int kvm_arch_init_vm(struct kvm *kvm, unsigned long type); void kvm_arch_destroy_vm(struct kvm *kvm); -void kvm_free_all_assigned_devices(struct kvm *kvm); void kvm_arch_sync_events(struct kvm *kvm); int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu); @@ -736,7 +735,7 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id); /* For vcpu->arch.iommu_flags */ #define KVM_IOMMU_CACHE_COHERENCY 0x1 -#ifdef CONFIG_IOMMU_API +#ifdef CONFIG_KVM_DEVICE_ASSIGNMENT int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot); void kvm_iommu_unmap_pages(struct kvm *kvm, struct kvm_memory_slot *slot); int kvm_iommu_map_guest(struct kvm *kvm); @@ -745,7 +744,7 @@ int kvm_assign_device(struct kvm *kvm, struct kvm_assigned_dev_kernel *assigned_dev); int kvm_deassign_device(struct kvm *kvm, struct kvm_assigned_dev_kernel *assigned_dev); -#else /* CONFIG_IOMMU_API */ +#else static inline int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot) { @@ -757,28 +756,11 @@ static inline void kvm_iommu_unmap_pages(struct kvm *kvm, { } -static inline int kvm_iommu_map_guest(struct kvm *kvm) -{ - return -ENODEV; -} - static inline int kvm_iommu_unmap_guest(struct kvm *kvm) { return 0; } - -static inline int kvm_assign_device(struct kvm *kvm, - struct kvm_assigned_dev_kernel *assigned_dev) -{ - return 0; -} - -static inline int kvm_deassign_device(struct kvm *kvm, - struct kvm_assigned_dev_kernel *assigned_dev) -{ - return 0; -} -#endif /* CONFIG_IOMMU_API */ +#endif static inline void __guest_enter(void) { @@ -1032,11 +1014,13 @@ static inline bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu) { return true; } #endif -#ifdef __KVM_HAVE_DEVICE_ASSIGNMENT +#ifdef CONFIG_KVM_DEVICE_ASSIGNMENT long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl, unsigned long arg); +void kvm_free_all_assigned_devices(struct kvm *kvm); + #else static inline long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl, @@ -1045,6 +1029,8 @@ static inline long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl, return -ENOTTY; } +static inline void kvm_free_all_assigned_devices(struct kvm *kvm) {} + #endif static inline void kvm_make_request(int req, struct kvm_vcpu *vcpu) diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index d4005192ad6e..965e5b52dee0 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -561,9 +561,7 @@ struct kvm_ppc_smmu_info { #define KVM_CAP_MP_STATE 14 #define KVM_CAP_COALESCED_MMIO 15 #define KVM_CAP_SYNC_MMU 16 /* Changes to host mmap are reflected in guest */ -#ifdef __KVM_HAVE_DEVICE_ASSIGNMENT #define KVM_CAP_DEVICE_ASSIGNMENT 17 -#endif #define KVM_CAP_IOMMU 18 #ifdef __KVM_HAVE_MSI #define KVM_CAP_DEVICE_MSI 20 @@ -581,9 +579,7 @@ struct kvm_ppc_smmu_info { #endif #define KVM_CAP_IRQ_ROUTING 25 #define KVM_CAP_IRQ_INJECT_STATUS 26 -#ifdef __KVM_HAVE_DEVICE_ASSIGNMENT #define KVM_CAP_DEVICE_DEASSIGNMENT 27 -#endif #ifdef __KVM_HAVE_MSIX #define KVM_CAP_DEVICE_MSIX 28 #endif -- cgit v1.2.3 From 7aac482e6290ab7ad21809e0c7327be959a2203e Mon Sep 17 00:00:00 2001 From: Tomasz Figa Date: Tue, 23 Apr 2013 17:46:24 +0200 Subject: clocksource: samsung_pwm_timer: Make PWM spinlock global This patch makes the PWM spinlock global and exports it to allow using it in Samsung PWM driver (will be reworked to use proper synchronization in further patches). Signed-off-by: Tomasz Figa Signed-off-by: Kyungmin Park Reviewed-by: Arnd Bergmann Acked-by: Kukjin Kim Signed-off-by: Olof Johansson --- include/clocksource/samsung_pwm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/clocksource/samsung_pwm.h b/include/clocksource/samsung_pwm.h index eff8668da252..399d2414734f 100644 --- a/include/clocksource/samsung_pwm.h +++ b/include/clocksource/samsung_pwm.h @@ -23,6 +23,8 @@ struct platform_device; struct device_node; +extern spinlock_t samsung_pwm_lock; + struct samsung_pwm_variant { u8 bits; u8 div_base; -- cgit v1.2.3 From 09d718a78c79ddc270dccbfa1b1070b20b9a9ae1 Mon Sep 17 00:00:00 2001 From: Tomasz Figa Date: Tue, 23 Apr 2013 17:46:26 +0200 Subject: clocksource: samsung_pwm_timer: Drop unused samsung_pwm struct This patch removes the unused samsung_pwm struct from public header. Signed-off-by: Tomasz Figa Signed-off-by: Kyungmin Park Reviewed-by: Arnd Bergmann Acked-by: Kukjin Kim Signed-off-by: Olof Johansson --- include/clocksource/samsung_pwm.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include') diff --git a/include/clocksource/samsung_pwm.h b/include/clocksource/samsung_pwm.h index 399d2414734f..b1d8fe706f1a 100644 --- a/include/clocksource/samsung_pwm.h +++ b/include/clocksource/samsung_pwm.h @@ -20,9 +20,6 @@ #define SAMSUNG_PWM_NUM 5 -struct platform_device; -struct device_node; - extern spinlock_t samsung_pwm_lock; struct samsung_pwm_variant { @@ -33,11 +30,4 @@ struct samsung_pwm_variant { bool has_tint_cstat; }; -struct samsung_pwm { - struct samsung_pwm_variant variant; - spinlock_t slock; - void __iomem *base; - int irq[SAMSUNG_PWM_NUM]; -}; - #endif /* __CLOCKSOURCE_SAMSUNG_PWM_H */ -- cgit v1.2.3 From f9bb48a2c25a96757d13795ba7cc52687f94446f Mon Sep 17 00:00:00 2001 From: Tomasz Figa Date: Tue, 23 Apr 2013 17:46:27 +0200 Subject: clocksource: samsung_pwm_timer: Add support for non-DT platforms This patch extends the driver to support platforms that still use legacy ATAGS-based boot, without device tree, by providing an exported function that can be used from platform code to initialize the clocksource. Signed-off-by: Tomasz Figa Signed-off-by: Kyungmin Park Reviewed-by: Arnd Bergmann Acked-by: Kukjin Kim Signed-off-by: Olof Johansson --- include/clocksource/samsung_pwm.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/clocksource/samsung_pwm.h b/include/clocksource/samsung_pwm.h index b1d8fe706f1a..5c449c8199e9 100644 --- a/include/clocksource/samsung_pwm.h +++ b/include/clocksource/samsung_pwm.h @@ -30,4 +30,7 @@ struct samsung_pwm_variant { bool has_tint_cstat; }; +void samsung_pwm_clocksource_init(void __iomem *base, + unsigned int *irqs, struct samsung_pwm_variant *variant); + #endif /* __CLOCKSOURCE_SAMSUNG_PWM_H */ -- cgit v1.2.3 From d70b4f53b950676228297f0b204f2e1512c1ff6c Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Thu, 25 Apr 2013 13:24:33 +0900 Subject: f2fs: add a tracepoint on f2fs_new_inode This can help when debugging the free nid allocation flows. Reviewed-by: Namjae Jeon Signed-off-by: Jaegeuk Kim --- include/trace/events/f2fs.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index b2b2f72a023d..52ae54828eda 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -197,6 +197,13 @@ DEFINE_EVENT(f2fs__inode, f2fs_evict_inode, TP_ARGS(inode) ); +DEFINE_EVENT(f2fs__inode_exit, f2fs_new_inode, + + TP_PROTO(struct inode *inode, int ret), + + TP_ARGS(inode, ret) +); + TRACE_EVENT(f2fs_unlink_enter, TP_PROTO(struct inode *dir, struct dentry *dentry), -- cgit v1.2.3 From 18a1053f7b85acdda2428c9f694101070cb8e62a Mon Sep 17 00:00:00 2001 From: "Shimoda, Yoshihiro" Date: Tue, 23 Apr 2013 20:00:12 +0900 Subject: sudmac: add support for SUDMAC Some Renesas USB modules have SUDMAC. This patch supports it using the shdma-base driver. Signed-off-by: Yoshihiro Shimoda Reviewed-by: Guennadi Liakhovetski Acked-by: Kuninori Morimoto Signed-off-by: Vinod Koul --- include/linux/sudmac.h | 52 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 52 insertions(+) create mode 100644 include/linux/sudmac.h (limited to 'include') diff --git a/include/linux/sudmac.h b/include/linux/sudmac.h new file mode 100644 index 000000000000..377b8a5788fa --- /dev/null +++ b/include/linux/sudmac.h @@ -0,0 +1,52 @@ +/* + * Header for the SUDMAC driver + * + * Copyright (C) 2013 Renesas Solutions Corp. + * + * This is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + */ +#ifndef SUDMAC_H +#define SUDMAC_H + +#include +#include +#include + +/* Used by slave DMA clients to request DMA to/from a specific peripheral */ +struct sudmac_slave { + struct shdma_slave shdma_slave; /* Set by the platform */ +}; + +/* + * Supplied by platforms to specify, how a DMA channel has to be configured for + * a certain peripheral + */ +struct sudmac_slave_config { + int slave_id; +}; + +struct sudmac_channel { + unsigned long offset; + unsigned long config; + unsigned long wait; /* The configuable range is 0 to 3 */ + unsigned long dint_end_bit; +}; + +struct sudmac_pdata { + const struct sudmac_slave_config *slave; + int slave_num; + const struct sudmac_channel *channel; + int channel_num; +}; + +/* Definitions for the sudmac_channel.config */ +#define SUDMAC_TX_BUFFER_MODE BIT(0) +#define SUDMAC_RX_END_MODE BIT(1) + +/* Definitions for the sudmac_channel.dint_end_bit */ +#define SUDMAC_DMA_BIT_CH0 BIT(0) +#define SUDMAC_DMA_BIT_CH1 BIT(1) + +#endif -- cgit v1.2.3 From dc9eb698f441889f2d7926b1cc6f1e14f0787f00 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Fri, 19 Apr 2013 13:23:09 -0400 Subject: audit: stop pushing loginid, uid, sessionid as arguments We always use current. Stop pulling this when the skb comes in and pushing it around as arguments. Just get it at the end when you need it. Signed-off-by: Eric Paris --- include/linux/audit.h | 3 +-- include/linux/tty.h | 6 ++---- 2 files changed, 3 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/audit.h b/include/linux/audit.h index b26d7f121ac5..a3a50cca1efb 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -441,8 +441,7 @@ extern int audit_update_lsm_rules(void); extern int audit_filter_user(int type); extern int audit_filter_type(int type); extern int audit_receive_filter(int type, int pid, int seq, - void *data, size_t datasz, kuid_t loginuid, - u32 sessionid, u32 sid); + void *data, size_t datasz); extern int audit_enabled; #else /* CONFIG_AUDIT */ static inline __printf(4, 5) diff --git a/include/linux/tty.h b/include/linux/tty.h index 8db1b569c37a..78e378b3971c 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -517,8 +517,7 @@ extern void tty_audit_exit(void); extern void tty_audit_fork(struct signal_struct *sig); extern void tty_audit_tiocsti(struct tty_struct *tty, char ch); extern void tty_audit_push(struct tty_struct *tty); -extern int tty_audit_push_task(struct task_struct *tsk, - kuid_t loginuid, u32 sessionid); +extern int tty_audit_push_task(struct task_struct *tsk); #else static inline void tty_audit_add_data(struct tty_struct *tty, unsigned char *data, size_t size, unsigned icanon) @@ -536,8 +535,7 @@ static inline void tty_audit_fork(struct signal_struct *sig) static inline void tty_audit_push(struct tty_struct *tty) { } -static inline int tty_audit_push_task(struct task_struct *tsk, - kuid_t loginuid, u32 sessionid) +static inline int tty_audit_push_task(struct task_struct *tsk) { return 0; } -- cgit v1.2.3 From 152f497b9b5940f81de3205465840a5eb316458e Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Fri, 19 Apr 2013 13:56:11 -0400 Subject: audit: push loginuid and sessionid processing down Since we are always current, we can push a lot of this stuff to the bottom and get rid of useless interfaces and arguments. Signed-off-by: Eric Paris --- include/linux/tty.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/tty.h b/include/linux/tty.h index 78e378b3971c..96d640b32cd8 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -517,7 +517,7 @@ extern void tty_audit_exit(void); extern void tty_audit_fork(struct signal_struct *sig); extern void tty_audit_tiocsti(struct tty_struct *tty, char ch); extern void tty_audit_push(struct tty_struct *tty); -extern int tty_audit_push_task(struct task_struct *tsk); +extern int tty_audit_push_current(void); #else static inline void tty_audit_add_data(struct tty_struct *tty, unsigned char *data, size_t size, unsigned icanon) @@ -535,7 +535,7 @@ static inline void tty_audit_fork(struct signal_struct *sig) static inline void tty_audit_push(struct tty_struct *tty) { } -static inline int tty_audit_push_task(struct task_struct *tsk) +static inline int tty_audit_push_current(void) { return 0; } -- cgit v1.2.3 From b122c3767c1d89763b4babca062c3171a71ed97c Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Fri, 19 Apr 2013 15:00:33 -0400 Subject: audit: use a consistent audit helper to log lsm information We have a number of places we were reimplementing the same code to write out lsm labels. Just do it one darn place. Signed-off-by: Eric Paris --- include/linux/audit.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/audit.h b/include/linux/audit.h index a3a50cca1efb..e2dd9c124140 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -188,7 +188,7 @@ static inline int audit_get_sessionid(struct task_struct *tsk) return tsk->sessionid; } -extern void audit_log_task_context(struct audit_buffer *ab); +extern int audit_log_task_context(struct audit_buffer *ab); extern void audit_log_task_info(struct audit_buffer *ab, struct task_struct *tsk); extern void __audit_ipc_obj(struct kern_ipc_perm *ipcp); extern void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode); @@ -344,8 +344,10 @@ static inline int audit_get_sessionid(struct task_struct *tsk) { return -1; } -static inline void audit_log_task_context(struct audit_buffer *ab) -{ } +static int void audit_log_task_context(struct audit_buffer *ab) +{ + return 0; +} static inline void audit_log_task_info(struct audit_buffer *ab, struct task_struct *tsk) { } -- cgit v1.2.3 From 4d3fb709b285ac885c40950a837edbfc90029c5f Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Tue, 30 Apr 2013 09:53:34 -0400 Subject: helper for some session id stuff --- include/linux/audit.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/audit.h b/include/linux/audit.h index e2dd9c124140..b76bfc8efc25 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -89,6 +89,8 @@ extern int audit_classify_arch(int arch); struct filename; +extern void audit_log_session_info(struct audit_buffer *ab); + #ifdef CONFIG_AUDITSYSCALL /* These are defined in auditsc.c */ /* Public API */ -- cgit v1.2.3 From 46e959ea2969cc1668d09b0dc55226946cf781f1 Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Fri, 3 May 2013 14:03:50 -0400 Subject: audit: add an option to control logging of passwords with pam_tty_audit Most commands are entered one line at a time and processed as complete lines in non-canonical mode. Commands that interactively require a password, enter canonical mode to do this while shutting off echo. This pair of features (icanon and !echo) can be used to avoid logging passwords by audit while still logging the rest of the command. Adding a member (log_passwd) to the struct audit_tty_status passed in by pam_tty_audit allows control of canonical mode without echo per task. Signed-off-by: Richard Guy Briggs Signed-off-by: Eric Paris --- include/linux/sched.h | 1 + include/uapi/linux/audit.h | 3 ++- 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index d2112477ff5e..c4689fe92864 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -641,6 +641,7 @@ struct signal_struct { #endif #ifdef CONFIG_AUDIT unsigned audit_tty; + unsigned audit_tty_log_passwd; struct tty_audit_buf *tty_audit_buf; #endif #ifdef CONFIG_CGROUPS diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h index 9f096f1c0907..c058c24b97ac 100644 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@ -369,7 +369,8 @@ struct audit_status { }; struct audit_tty_status { - __u32 enabled; /* 1 = enabled, 0 = disabled */ + __u32 enabled; /* 1 = enabled, 0 = disabled */ + __u32 log_passwd; /* 1 = enabled, 0 = disabled */ }; /* audit_rule_data supports filter rules with both integer and string -- cgit v1.2.3 From b24a30a7305418ff138ff51776fc555ec57c011a Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Tue, 30 Apr 2013 15:30:32 -0400 Subject: audit: fix event coverage of AUDIT_ANOM_LINK The userspace audit tools didn't like the existing formatting of the AUDIT_ANOM_LINK event. It needed to be expanded to emit an AUDIT_PATH event as well, so this implements the change. The bulk of the patch is moving code out of auditsc.c into audit.c and audit.h for general use. It expands audit_log_name to include an optional "struct path" argument for the simple case of just needing to report a pathname. This also makes audit_log_task_info available when syscall auditing is not enabled, since it is needed in either case for process details. Signed-off-by: Kees Cook Reported-by: Steve Grubb --- include/linux/audit.h | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/audit.h b/include/linux/audit.h index b76bfc8efc25..469d11755e46 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -190,8 +190,6 @@ static inline int audit_get_sessionid(struct task_struct *tsk) return tsk->sessionid; } -extern int audit_log_task_context(struct audit_buffer *ab); -extern void audit_log_task_info(struct audit_buffer *ab, struct task_struct *tsk); extern void __audit_ipc_obj(struct kern_ipc_perm *ipcp); extern void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode); extern int __audit_bprm(struct linux_binprm *bprm); @@ -346,13 +344,6 @@ static inline int audit_get_sessionid(struct task_struct *tsk) { return -1; } -static int void audit_log_task_context(struct audit_buffer *ab) -{ - return 0; -} -static inline void audit_log_task_info(struct audit_buffer *ab, - struct task_struct *tsk) -{ } static inline void audit_ipc_obj(struct kern_ipc_perm *ipcp) { } static inline void audit_ipc_set_perm(unsigned long qbytes, uid_t uid, @@ -439,6 +430,10 @@ static inline void audit_log_secctx(struct audit_buffer *ab, u32 secid) { } #endif +extern int audit_log_task_context(struct audit_buffer *ab); +extern void audit_log_task_info(struct audit_buffer *ab, + struct task_struct *tsk); + extern int audit_update_lsm_rules(void); /* Private API (for audit.c only) */ @@ -485,6 +480,13 @@ static inline void audit_log_link_denied(const char *string, { } static inline void audit_log_secctx(struct audit_buffer *ab, u32 secid) { } +static inline int audit_log_task_context(struct audit_buffer *ab) +{ + return 0; +} +static inline void audit_log_task_info(struct audit_buffer *ab, + struct task_struct *tsk) +{ } #define audit_enabled 0 #endif /* CONFIG_AUDIT */ static inline void audit_log_string(struct audit_buffer *ab, const char *buf) -- cgit v1.2.3 From 60b9df7a54804a965850db00beec4d3a2c002536 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Wed, 1 May 2013 14:37:21 +0200 Subject: fuse: add flag to turn on async direct IO Without async DIO write requests to a single file were always serialized. With async DIO that's no longer the case. So don't turn on async DIO by default for fear of breaking backward compatibility. Signed-off-by: Miklos Szeredi --- include/uapi/linux/fuse.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index 706d035fa748..60bb2f9f7b74 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -90,6 +90,9 @@ * 7.21 * - add FUSE_READDIRPLUS * - send the requested events in POLL request + * + * 7.22 + * - add FUSE_ASYNC_DIO */ #ifndef _LINUX_FUSE_H @@ -125,7 +128,7 @@ #define FUSE_KERNEL_VERSION 7 /** Minor version number of this interface */ -#define FUSE_KERNEL_MINOR_VERSION 21 +#define FUSE_KERNEL_MINOR_VERSION 22 /** The node ID of the root inode */ #define FUSE_ROOT_ID 1 @@ -215,6 +218,7 @@ struct fuse_file_lock { * FUSE_AUTO_INVAL_DATA: automatically invalidate cached pages * FUSE_DO_READDIRPLUS: do READDIRPLUS (READDIR+LOOKUP in one) * FUSE_READDIRPLUS_AUTO: adaptive readdirplus + * FUSE_ASYNC_DIO: asynchronous direct I/O submission */ #define FUSE_ASYNC_READ (1 << 0) #define FUSE_POSIX_LOCKS (1 << 1) @@ -231,6 +235,7 @@ struct fuse_file_lock { #define FUSE_AUTO_INVAL_DATA (1 << 12) #define FUSE_DO_READDIRPLUS (1 << 13) #define FUSE_READDIRPLUS_AUTO (1 << 14) +#define FUSE_ASYNC_DIO (1 << 15) /** * CUSE INIT request/reply flags -- cgit v1.2.3 From 07c09b725543ff2958c11522d583f90f7fdba735 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 15 Feb 2013 22:10:17 -0600 Subject: libceph: make ceph_msg->bio_seg be unsigned The bio_seg field is used by the ceph messenger in iterating through a bio. It should never have a negative value, so make it an unsigned. (I contemplated making it unsigned short to match the struct bio definition, but it offered no benefit.) Change variables used to hold bio_seg values to all be unsigned as well. Change two variable names in init_bio_iter() to match the convention used everywhere else. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 60903e0f665c..8297288a66e0 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -86,7 +86,7 @@ struct ceph_msg { #ifdef CONFIG_BLOCK struct bio *bio; /* instead of pages/pagelist */ struct bio *bio_iter; /* bio iterator */ - int bio_seg; /* current bio segment */ + unsigned int bio_seg; /* current bio segment */ #endif /* CONFIG_BLOCK */ struct ceph_pagelist *trail; /* the trailing part of the data */ bool front_is_vmalloc; -- cgit v1.2.3 From d4b515fa10dd52a2aef88df7299e9f3a8ab0957a Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Mon, 25 Feb 2013 17:35:46 -0600 Subject: libceph: distinguish page array and pagelist count Use distinct fields for tracking the number of pages in a message's page array and in a message's page list. Currently only one or the other is used at a time, but that will be changing soon. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 8297288a66e0..1b08349a413c 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -75,9 +75,10 @@ struct ceph_msg { struct kvec front; /* unaligned blobs of message */ struct ceph_buffer *middle; struct page **pages; /* data payload. NOT OWNER. */ - unsigned nr_pages; /* size of page array */ + unsigned page_count; /* size of page array */ unsigned page_alignment; /* io offset in first page */ struct ceph_pagelist *pagelist; /* instead of pages */ + unsigned int pagelist_count; /* number of pages in pagelist */ struct ceph_connection *con; struct list_head list_head; -- cgit v1.2.3 From 0d5af1643535508f82d6bcc2b9b93b180e8c3f4b Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Wed, 27 Feb 2013 10:26:25 -0600 Subject: libceph: complete lingering requests only once An osd request marked to linger will be re-submitted in the event a connection to the target osd gets dropped. Currently, if there is a callback function associated with a request it will be called each time a request is submitted--which for lingering requests can be more than once. Change it so a request--including lingering ones--will get completed (from the perspective of the user of the osd client) exactly once. This resolves: http://tracker.ceph.com/issues/3967 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 1dd5d466b6f9..a79f833bba4a 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -85,6 +85,7 @@ struct ceph_osd_request { s32 r_reply_op_result[CEPH_OSD_MAX_OP]; int r_got_reply; int r_linger; + int r_completed; struct ceph_osd_client *r_osdc; struct kref r_kref; -- cgit v1.2.3 From 2a24d1f4bd7995de133c857bfdc77ac82c842300 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 1 Mar 2013 18:00:15 -0600 Subject: libceph: use (void *) for untyped data in osd ops Two of the fields defining osd operations are defined using (char *) while the data they represent are really untyped, not character strings. Change them to have type (void *). Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index a79f833bba4a..ec33588194ef 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -184,7 +184,7 @@ struct ceph_osd_req_op { } extent; struct { const char *name; - const char *val; + const void *val; u32 name_len; u32 value_len; __u8 cmp_op; /* CEPH_OSD_CMPXATTR_OP_* */ @@ -193,7 +193,7 @@ struct ceph_osd_req_op { struct { const char *class_name; const char *method_name; - const char *indata; + const void *indata; u32 indata_len; __u8 class_len; __u8 method_len; -- cgit v1.2.3 From ec02a2f2ffae13e038453ae89592a8c6210f7f4d Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 1 Mar 2013 18:00:15 -0600 Subject: libceph: kill ceph_msg->pagelist_count The pagelist_count field is never actually used, so get rid of it. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 1b08349a413c..6c118748a7f8 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -78,7 +78,6 @@ struct ceph_msg { unsigned page_count; /* size of page array */ unsigned page_alignment; /* io offset in first page */ struct ceph_pagelist *pagelist; /* instead of pages */ - unsigned int pagelist_count; /* number of pages in pagelist */ struct ceph_connection *con; struct list_head list_head; -- cgit v1.2.3 From 41766f87f54cc8bef023b4b0550f48753959345a Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 1 Mar 2013 18:00:15 -0600 Subject: libceph: rename ceph_calc_object_layout() The purpose of ceph_calc_object_layout() is to fill in the pool number and seed for a ceph_pg structure provided, based on a given osd map and target object id. Currently that function takes a file layout parameter, but the only thing used out of that is its pool number. Change the function so it takes a pool number rather than the full file layout structure. Only update the ceph_pg if the pool is found in the osd map. Get rid of few useless lines of code from the function while there. Since the function now very clearly just fills in the ceph_pg structure it's provided, rename it ceph_calc_ceph_pg(). Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osdmap.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h index c819190d1642..167daf60c4e8 100644 --- a/include/linux/ceph/osdmap.h +++ b/include/linux/ceph/osdmap.h @@ -131,10 +131,8 @@ extern int ceph_calc_file_object_mapping(struct ceph_file_layout *layout, u64 *bno, u64 *oxoff, u64 *oxlen); /* calculate mapping of object to a placement group */ -extern int ceph_calc_object_layout(struct ceph_pg *pg, - const char *oid, - struct ceph_file_layout *fl, - struct ceph_osdmap *osdmap); +extern int ceph_calc_ceph_pg(struct ceph_pg *pg, const char *oid, + struct ceph_osdmap *osdmap, uint64_t pool); extern int ceph_calc_pg_acting(struct ceph_osdmap *osdmap, struct ceph_pg pgid, int *acting); -- cgit v1.2.3 From 153e5167e0e237faaefb7adf82db5748c1452d73 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 1 Mar 2013 18:00:15 -0600 Subject: libceph: don't assign page info in ceph_osdc_new_request() Currently ceph_osdc_new_request() assigns an osd request's r_num_pages and r_alignment fields. The only thing it does after that is call ceph_osdc_build_request(), and that doesn't need those fields to be assigned. Move the assignment of those fields out of ceph_osdc_new_request() and into its caller. As a result, the page_align parameter is no longer used, so get rid of it. Note that in ceph_sync_write(), the value for req->r_num_pages had already been calculated earlier (as num_pages, and fortunately it was computed the same way). So don't bother recomputing it, but because it's not needed earlier, move that calculation after the call to ceph_osdc_new_request(). Hold off making the assignment to r_alignment, doing it instead r_pages and r_num_pages are getting set. Similarly, in start_read(), nr_pages already holds the number of pages in the array (and is calculated the same way), so there's no need to recompute it. Move the assignment of the page alignment down with the others there as well. This and the next few patches are preparation work for: http://tracker.ceph.com/issues/4127 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index ec33588194ef..803a9db0b475 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -247,7 +247,7 @@ extern struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *, int do_sync, u32 truncate_seq, u64 truncate_size, struct timespec *mtime, - bool use_mempool, int page_align); + bool use_mempool); extern void ceph_osdc_set_request_linger(struct ceph_osd_client *osdc, struct ceph_osd_request *req); -- cgit v1.2.3 From 2794a82a11cfeae0890741b18b0049ddb55ce646 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Thu, 14 Feb 2013 12:16:43 -0600 Subject: libceph: separate osd request data info Pull the fields in an osd request structure that define the data for the request out into a separate structure. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 24 ++++++++++++++++-------- 1 file changed, 16 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 803a9db0b475..600b8278d11e 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -50,6 +50,21 @@ struct ceph_osd { #define CEPH_OSD_MAX_OP 10 +struct ceph_osd_data { + struct { + struct { + struct page **pages; + u32 num_pages; + u32 alignment; + bool pages_from_pool; + bool own_pages; + }; +#ifdef CONFIG_BLOCK + struct bio *bio; +#endif /* CONFIG_BLOCK */ + }; +}; + /* an in-flight request */ struct ceph_osd_request { u64 r_tid; /* unique for this client */ @@ -105,15 +120,8 @@ struct ceph_osd_request { struct ceph_file_layout r_file_layout; struct ceph_snap_context *r_snapc; /* snap context for writes */ - unsigned r_num_pages; /* size of page array (follows) */ - unsigned r_page_alignment; /* io offset in first page */ - struct page **r_pages; /* pages for data payload */ - int r_pages_from_pool; - int r_own_pages; /* if true, i own page list */ -#ifdef CONFIG_BLOCK - struct bio *r_bio; /* instead of pages */ -#endif + struct ceph_osd_data r_data; struct ceph_pagelist r_trail; /* trailing part of the data */ }; -- cgit v1.2.3 From 2ac2b7a6d4976bd6b5dc0751aa77d12d48d3ac4c Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Thu, 14 Feb 2013 12:16:43 -0600 Subject: libceph: distinguish page and bio requests An osd request uses either pages or a bio list for its data. Use a union to record information about the two, and add a data type tag to select between them. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 600b8278d11e..56604b33dc3c 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -50,8 +50,17 @@ struct ceph_osd { #define CEPH_OSD_MAX_OP 10 +enum ceph_osd_data_type { + CEPH_OSD_DATA_TYPE_NONE, + CEPH_OSD_DATA_TYPE_PAGES, +#ifdef CONFIG_BLOCK + CEPH_OSD_DATA_TYPE_BIO, +#endif /* CONFIG_BLOCK */ +}; + struct ceph_osd_data { - struct { + enum ceph_osd_data_type type; + union { struct { struct page **pages; u32 num_pages; -- cgit v1.2.3 From 0fff87ec798abdb4a99f01cbb0197266bb68c5dc Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Thu, 14 Feb 2013 12:16:43 -0600 Subject: libceph: separate read and write data An osd request defines information about where data to be read should be placed as well as where data to write comes from. Currently these are represented by common fields. Keep information about data for writing separate from data to be read by splitting these into data_in and data_out fields. This is the key patch in this whole series, in that it actually identifies which osd requests generate outgoing data and which generate incoming data. It's less obvious (currently) that an osd CALL op generates both outgoing and incoming data; that's the focus of some upcoming work. This resolves: http://tracker.ceph.com/issues/4127 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 56604b33dc3c..40e02603723d 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -130,8 +130,9 @@ struct ceph_osd_request { struct ceph_file_layout r_file_layout; struct ceph_snap_context *r_snapc; /* snap context for writes */ - struct ceph_osd_data r_data; - struct ceph_pagelist r_trail; /* trailing part of the data */ + struct ceph_osd_data r_data_in; + struct ceph_osd_data r_data_out; + struct ceph_pagelist r_trail; /* trailing part of data out */ }; struct ceph_osd_event { -- cgit v1.2.3 From 7b11ba37585595034a91df8869414f732466b800 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 8 Mar 2013 18:51:03 -0600 Subject: libceph: define CEPH_MSG_MAX_MIDDLE_LEN This is probably unnecessary but the code read as if it were wrong in read_partial_message(). Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/libceph.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 29818fc3fa49..5493d7b86423 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -66,6 +66,7 @@ struct ceph_options { #define CEPH_OSD_IDLE_TTL_DEFAULT 60 #define CEPH_MSG_MAX_FRONT_LEN (16*1024*1024) +#define CEPH_MSG_MAX_MIDDLE_LEN (16*1024*1024) #define CEPH_MSG_MAX_DATA_LEN (16*1024*1024) #define CEPH_AUTH_NAME_DEFAULT "guest" -- cgit v1.2.3 From e0c594878e3211b09208c779df5f996f0b831d9e Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Thu, 7 Mar 2013 15:38:25 -0600 Subject: libceph: record byte count not page count Record the byte count for an osd request rather than the page count. The number of pages can always be derived from the byte count (and alignment/offset) but the reverse is not true. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 40e02603723d..a8016dfbfdba 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -63,7 +63,7 @@ struct ceph_osd_data { union { struct { struct page **pages; - u32 num_pages; + u64 length; u32 alignment; bool pages_from_pool; bool own_pages; -- cgit v1.2.3 From 02afca6ca00b7972887c5cc77068356f33bdfc18 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Thu, 14 Feb 2013 12:16:43 -0600 Subject: libceph: isolate message page field manipulation Define a function ceph_msg_data_set_pages(), which more clearly abstracts the assignment page-related fields for data in a ceph message structure. Use this new function in the osd client and mds client. Ideally, these fields would never be set more than once (with BUG_ON() calls to guarantee that). At the moment though the osd client sets these every time it receives a message, and in the event of a communication problem this can happen more than once. (This will be resolved shortly, but setting up these helpers first makes it all a bit easier to work with.) Rearrange the field order in a ceph_msg structure to group those that are used to define the possible data payloads. This partially resolves: http://tracker.ceph.com/issues/4263 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 22 +++++++++++++--------- 1 file changed, 13 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 6c118748a7f8..aa463b9b30af 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -74,21 +74,22 @@ struct ceph_msg { struct ceph_msg_footer footer; /* footer */ struct kvec front; /* unaligned blobs of message */ struct ceph_buffer *middle; - struct page **pages; /* data payload. NOT OWNER. */ - unsigned page_count; /* size of page array */ - unsigned page_alignment; /* io offset in first page */ - struct ceph_pagelist *pagelist; /* instead of pages */ - - struct ceph_connection *con; - struct list_head list_head; - struct kref kref; + struct page **pages; /* data payload. NOT OWNER. */ + unsigned int page_alignment; /* io offset in first page */ + unsigned int page_count; /* # pages in array or list */ + struct ceph_pagelist *pagelist; /* instead of pages */ #ifdef CONFIG_BLOCK + unsigned int bio_seg; /* current bio segment */ struct bio *bio; /* instead of pages/pagelist */ struct bio *bio_iter; /* bio iterator */ - unsigned int bio_seg; /* current bio segment */ #endif /* CONFIG_BLOCK */ struct ceph_pagelist *trail; /* the trailing part of the data */ + + struct ceph_connection *con; + struct list_head list_head; /* links for connection lists */ + + struct kref kref; bool front_is_vmalloc; bool more_to_follow; bool needs_out_seq; @@ -218,6 +219,9 @@ extern void ceph_msg_revoke_incoming(struct ceph_msg *msg); extern void ceph_con_keepalive(struct ceph_connection *con); +extern void ceph_msg_data_set_pages(struct ceph_msg *msg, struct page **pages, + unsigned int page_count, size_t alignment); + extern struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags, bool can_fail); extern void ceph_msg_kfree(struct ceph_msg *m); -- cgit v1.2.3 From f1baeb2b9fc1c2c87ec02f1bf8cb88e108d4fbce Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Thu, 7 Mar 2013 15:38:26 -0600 Subject: libceph: set page info with byte length When setting page array information for message data, provide the byte length rather than the page count ceph_msg_data_set_pages(). Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index aa463b9b30af..e6d20e892a88 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -220,7 +220,7 @@ extern void ceph_msg_revoke_incoming(struct ceph_msg *msg); extern void ceph_con_keepalive(struct ceph_connection *con); extern void ceph_msg_data_set_pages(struct ceph_msg *msg, struct page **pages, - unsigned int page_count, size_t alignment); + size_t length, size_t alignment); extern struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags, bool can_fail); -- cgit v1.2.3 From 27fa83852ba275361eaa1a1283cf6704fa8191a6 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Thu, 14 Feb 2013 12:16:43 -0600 Subject: libceph: isolate other message data fields Define ceph_msg_data_set_pagelist(), ceph_msg_data_set_bio(), and ceph_msg_data_set_trail() to clearly abstract the assignment of the remaining data-related fields in a ceph message structure. Use the new functions in the osd client and mds client. This partially resolves: http://tracker.ceph.com/issues/4263 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index e6d20e892a88..9d9be4682ac3 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -221,6 +221,11 @@ extern void ceph_con_keepalive(struct ceph_connection *con); extern void ceph_msg_data_set_pages(struct ceph_msg *msg, struct page **pages, size_t length, size_t alignment); +extern void ceph_msg_data_set_pagelist(struct ceph_msg *msg, + struct ceph_pagelist *pagelist); +extern void ceph_msg_data_set_bio(struct ceph_msg *msg, struct bio *bio); +extern void ceph_msg_data_set_trail(struct ceph_msg *msg, + struct ceph_pagelist *trail); extern struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags, bool can_fail); -- cgit v1.2.3 From 4a73ef27ad04f1b8ea23eb55e50b20fcc0530a6f Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Thu, 7 Mar 2013 15:38:26 -0600 Subject: libceph: record message data byte length Record the number of bytes of data in a page array rather than the number of pages in the array. It can be assumed that the page array is of sufficient size to hold the number of bytes indicated (and offset by the indicated alignment). Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 9d9be4682ac3..1991a6f9dc90 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -77,7 +77,7 @@ struct ceph_msg { struct page **pages; /* data payload. NOT OWNER. */ unsigned int page_alignment; /* io offset in first page */ - unsigned int page_count; /* # pages in array or list */ + size_t length; /* # data bytes in array or list */ struct ceph_pagelist *pagelist; /* instead of pages */ #ifdef CONFIG_BLOCK unsigned int bio_seg; /* current bio segment */ -- cgit v1.2.3 From 97fb1c7f6637ee61c90b8bc186d464cfd426b063 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 1 Mar 2013 18:00:16 -0600 Subject: libceph: define ceph_msg_has_*() data macros Define and use macros ceph_msg_has_*() to determine whether to operate on the pages, pagelist, bio, and trail fields of a message. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 1991a6f9dc90..889fe4720133 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -64,6 +64,13 @@ struct ceph_messenger { u32 required_features; }; +#define ceph_msg_has_pages(m) ((m)->pages != NULL) +#define ceph_msg_has_pagelist(m) ((m)->pagelist != NULL) +#ifdef CONFIG_BLOCK +#define ceph_msg_has_bio(m) ((m)->bio != NULL) +#endif /* CONFIG_BLOCK */ +#define ceph_msg_has_trail(m) ((m)->trail != NULL) + /* * a single message. it contains a header (src, dest, message type, etc.), * footer (crc values, mainly), a "front" message body, and possibly a -- cgit v1.2.3 From f9e15777afd87585f2222dfd446c2e52deb65eba Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 1 Mar 2013 18:00:16 -0600 Subject: libceph: be explicit about message data representation A ceph message has a data payload portion. The memory for that data (either the source of data to send or the location to place data that is received) is specified in several ways. The ceph_msg structure includes fields for all of those ways, but this mispresents the fact that not all of them are used at a time. Specifically, the data in a message can be in: - an array of pages - a list of pages - a list of Linux bios - a second list of pages (the "trail") (The two page lists are currently only ever used for outgoing data.) Impose more structure on the ceph message, making the grouping of some of these fields explicit. Shorten the name of the "page_alignment" field. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 33 +++++++++++++++++++++------------ 1 file changed, 21 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 889fe4720133..fb2b18a20c13 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -64,12 +64,12 @@ struct ceph_messenger { u32 required_features; }; -#define ceph_msg_has_pages(m) ((m)->pages != NULL) -#define ceph_msg_has_pagelist(m) ((m)->pagelist != NULL) +#define ceph_msg_has_pages(m) ((m)->p.pages != NULL) +#define ceph_msg_has_pagelist(m) ((m)->l.pagelist != NULL) #ifdef CONFIG_BLOCK -#define ceph_msg_has_bio(m) ((m)->bio != NULL) +#define ceph_msg_has_bio(m) ((m)->b.bio != NULL) #endif /* CONFIG_BLOCK */ -#define ceph_msg_has_trail(m) ((m)->trail != NULL) +#define ceph_msg_has_trail(m) ((m)->t.trail != NULL) /* * a single message. it contains a header (src, dest, message type, etc.), @@ -82,16 +82,25 @@ struct ceph_msg { struct kvec front; /* unaligned blobs of message */ struct ceph_buffer *middle; - struct page **pages; /* data payload. NOT OWNER. */ - unsigned int page_alignment; /* io offset in first page */ - size_t length; /* # data bytes in array or list */ - struct ceph_pagelist *pagelist; /* instead of pages */ + /* data payload */ + struct { + struct page **pages; /* NOT OWNER. */ + size_t length; /* # data bytes in array */ + unsigned int alignment; /* first page */ + } p; + struct { + struct ceph_pagelist *pagelist; + } l; #ifdef CONFIG_BLOCK - unsigned int bio_seg; /* current bio segment */ - struct bio *bio; /* instead of pages/pagelist */ - struct bio *bio_iter; /* bio iterator */ + struct { + struct bio *bio_iter; /* iterator */ + struct bio *bio; + unsigned int bio_seg; /* current seg in bio */ + } b; #endif /* CONFIG_BLOCK */ - struct ceph_pagelist *trail; /* the trailing part of the data */ + struct { + struct ceph_pagelist *trail; /* trailing part of data */ + } t; struct ceph_connection *con; struct list_head list_head; /* links for connection lists */ -- cgit v1.2.3 From 437945094fed0deb1810e8da95465c8f26bc6f80 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 1 Mar 2013 18:00:16 -0600 Subject: libceph: abstract message data Group the types of message data into an abstract structure with a type indicator and a union containing fields appropriate to the type of data it represents. Use this to represent the pages, pagelist, bio, and trail in a ceph message. Verify message data is of type NONE in ceph_msg_data_set_*() routines. Since information about message data of type NONE really should not be interpreted, get rid of the other assertions in those functions. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 71 ++++++++++++++++++++++++++++++------------ 1 file changed, 51 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index fb2b18a20c13..5860dd0c2caf 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -64,12 +64,55 @@ struct ceph_messenger { u32 required_features; }; -#define ceph_msg_has_pages(m) ((m)->p.pages != NULL) -#define ceph_msg_has_pagelist(m) ((m)->l.pagelist != NULL) +#define ceph_msg_has_pages(m) ((m)->p.type == CEPH_MSG_DATA_PAGES) +#define ceph_msg_has_pagelist(m) ((m)->l.type == CEPH_MSG_DATA_PAGELIST) #ifdef CONFIG_BLOCK -#define ceph_msg_has_bio(m) ((m)->b.bio != NULL) +#define ceph_msg_has_bio(m) ((m)->b.type == CEPH_MSG_DATA_BIO) #endif /* CONFIG_BLOCK */ -#define ceph_msg_has_trail(m) ((m)->t.trail != NULL) +#define ceph_msg_has_trail(m) ((m)->t.type == CEPH_MSG_DATA_PAGELIST) + +enum ceph_msg_data_type { + CEPH_MSG_DATA_NONE, /* message contains no data payload */ + CEPH_MSG_DATA_PAGES, /* data source/destination is a page array */ + CEPH_MSG_DATA_PAGELIST, /* data source/destination is a pagelist */ +#ifdef CONFIG_BLOCK + CEPH_MSG_DATA_BIO, /* data source/destination is a bio list */ +#endif /* CONFIG_BLOCK */ +}; + +static __inline__ bool ceph_msg_data_type_valid(enum ceph_msg_data_type type) +{ + switch (type) { + case CEPH_MSG_DATA_NONE: + case CEPH_MSG_DATA_PAGES: + case CEPH_MSG_DATA_PAGELIST: +#ifdef CONFIG_BLOCK + case CEPH_MSG_DATA_BIO: +#endif /* CONFIG_BLOCK */ + return true; + default: + return false; + } +} + +struct ceph_msg_data { + enum ceph_msg_data_type type; + union { +#ifdef CONFIG_BLOCK + struct { + struct bio *bio_iter; /* iterator */ + struct bio *bio; + unsigned int bio_seg; /* current seg in bio */ + }; +#endif /* CONFIG_BLOCK */ + struct { + struct page **pages; /* NOT OWNER. */ + size_t length; /* total # bytes */ + unsigned int alignment; /* first page */ + }; + struct ceph_pagelist *pagelist; + }; +}; /* * a single message. it contains a header (src, dest, message type, etc.), @@ -83,24 +126,12 @@ struct ceph_msg { struct ceph_buffer *middle; /* data payload */ - struct { - struct page **pages; /* NOT OWNER. */ - size_t length; /* # data bytes in array */ - unsigned int alignment; /* first page */ - } p; - struct { - struct ceph_pagelist *pagelist; - } l; + struct ceph_msg_data p; /* pages */ + struct ceph_msg_data l; /* pagelist */ #ifdef CONFIG_BLOCK - struct { - struct bio *bio_iter; /* iterator */ - struct bio *bio; - unsigned int bio_seg; /* current seg in bio */ - } b; + struct ceph_msg_data b; /* bio */ #endif /* CONFIG_BLOCK */ - struct { - struct ceph_pagelist *trail; /* trailing part of data */ - } t; + struct ceph_msg_data t; /* trail */ struct ceph_connection *con; struct list_head list_head; /* links for connection lists */ -- cgit v1.2.3 From fe38a2b67bc6b3a60da82a23e9082256a30e39d9 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Wed, 6 Mar 2013 23:39:39 -0600 Subject: libceph: start defining message data cursor This patch lays out the foundation for using generic routines to manage processing items of message data. For simplicity, we'll start with just the trail portion of a message, because it stands alone and is only present for outgoing data. First some basic concepts. We'll use the term "data item" to represent one of the ceph_msg_data structures associated with a message. There are currently four of those, with single-letter field names p, l, b, and t. A data item is further broken into "pieces" which always lie in a single page. A data item will include a "cursor" that will track state as the memory defined by the item is consumed by sending data from or receiving data into it. We define three routines to manipulate a data item's cursor: the "init" routine; the "next" routine; and the "advance" routine. The "init" routine initializes the cursor so it points at the beginning of the first piece in the item. The "next" routine returns the page, page offset, and length (limited by both the page and item size) of the next unconsumed piece in the item. It also indicates to the caller whether the piece being returned is the last one in the data item. The "advance" routine consumes the requested number of bytes in the item (advancing the cursor). This is used to record the number of bytes from the current piece that were actually sent or received by the network code. It returns an indication of whether the result means the current piece has been fully consumed. This is used by the message send code to determine whether it should calculate the CRC for the next piece processed. The trail of a message is implemented as a ceph pagelist. The routines defined for it will be usable for non-trail pagelist data as well. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 5860dd0c2caf..14862438faff 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -95,6 +95,12 @@ static __inline__ bool ceph_msg_data_type_valid(enum ceph_msg_data_type type) } } +struct ceph_msg_data_cursor { + bool last_piece; /* now at last piece of data item */ + struct page *page; /* current page in pagelist */ + size_t offset; /* pagelist bytes consumed */ +}; + struct ceph_msg_data { enum ceph_msg_data_type type; union { @@ -112,6 +118,7 @@ struct ceph_msg_data { }; struct ceph_pagelist *pagelist; }; + struct ceph_msg_data_cursor cursor; /* pagelist only */ }; /* -- cgit v1.2.3 From dd236fcb65d7b6b80c408cb5f66aab55f4594284 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Wed, 6 Mar 2013 23:39:39 -0600 Subject: libceph: prepare for other message data item types This just inserts some infrastructure in preparation for handling other types of ceph message data items. No functional changes, just trying to simplify review by separating out some noise. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 14862438faff..716c3fdeb257 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -97,8 +97,12 @@ static __inline__ bool ceph_msg_data_type_valid(enum ceph_msg_data_type type) struct ceph_msg_data_cursor { bool last_piece; /* now at last piece of data item */ - struct page *page; /* current page in pagelist */ - size_t offset; /* pagelist bytes consumed */ + union { + struct { /* pagelist */ + struct page *page; /* page from list */ + size_t offset; /* bytes from list */ + }; + }; }; struct ceph_msg_data { -- cgit v1.2.3 From 6aaa4511deb4b0fd776d1153dc63a89cdc024fb8 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Wed, 6 Mar 2013 23:39:39 -0600 Subject: libceph: implement bio message data item cursor Implement and use cursor routines for bio message data items for outbound message data. (See the previous commit for reasoning in support of the changes in out_msg_pos_next().) Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 716c3fdeb257..76b4645e2dff 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -98,6 +98,13 @@ static __inline__ bool ceph_msg_data_type_valid(enum ceph_msg_data_type type) struct ceph_msg_data_cursor { bool last_piece; /* now at last piece of data item */ union { +#ifdef CONFIG_BLOCK + struct { /* bio */ + struct bio *bio; /* bio from list */ + unsigned int vector_index; /* vector from bio */ + unsigned int vector_offset; /* bytes from vector */ + }; +#endif /* CONFIG_BLOCK */ struct { /* pagelist */ struct page *page; /* page from list */ size_t offset; /* bytes from list */ -- cgit v1.2.3 From e766d7b55e10f93c7bab298135a4e90dcc46620d Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Thu, 7 Mar 2013 15:38:28 -0600 Subject: libceph: implement pages array cursor Implement and use cursor routines for page array message data items for outbound message data. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 76b4645e2dff..b53b9ef65009 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -105,6 +105,12 @@ struct ceph_msg_data_cursor { unsigned int vector_offset; /* bytes from vector */ }; #endif /* CONFIG_BLOCK */ + struct { /* pages */ + size_t resid; /* bytes from array */ + unsigned int page_offset; /* offset in page */ + unsigned short page_index; /* index in array */ + unsigned short page_count; /* pages in array */ + }; struct { /* pagelist */ struct page *page; /* page from list */ size_t offset; /* bytes from list */ -- cgit v1.2.3 From 175face2ba31025b0dcd6da4e711fca7764287fa Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 8 Mar 2013 13:35:36 -0600 Subject: libceph: let osd ops determine request data length The length of outgoing data in an osd request is dependent on the osd ops that are embedded in that request. Each op is encoded into a request message using osd_req_encode_op(), so that should be used to determine the amount of outgoing data implied by the op as it is encoded. Have osd_req_encode_op() return the number of bytes of outgoing data implied by the op being encoded, and accumulate and use that in ceph_osdc_build_request(). As a result, ceph_osdc_build_request() no longer requires its "len" parameter, so get rid of it. Using the sum of the op lengths rather than the length provided is a valid change because: - The only callers of osd ceph_osdc_build_request() are rbd and the osd client (in ceph_osdc_new_request() on behalf of the file system). - When rbd calls it, the length provided is only non-zero for write requests, and in that case the single op has the same length value as what was passed here. - When called from ceph_osdc_new_request(), (it's not all that easy to see, but) the length passed is also always the same as the extent length encoded in its (single) write op if present. This resolves: http://tracker.ceph.com/issues/4406 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index a8016dfbfdba..bcf3f72ec3f8 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -249,8 +249,7 @@ extern struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client * bool use_mempool, gfp_t gfp_flags); -extern void ceph_osdc_build_request(struct ceph_osd_request *req, - u64 off, u64 len, +extern void ceph_osdc_build_request(struct ceph_osd_request *req, u64 off, unsigned int num_op, struct ceph_osd_req_op *src_ops, struct ceph_snap_context *snapc, -- cgit v1.2.3 From 9a5e6d09ddd0cd68ce64c3aa54095e4a0e85b089 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 8 Mar 2013 13:35:36 -0600 Subject: libceph: have osd requests support pagelist data Add support for recording a ceph pagelist as data associated with an osd request. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index bcf3f72ec3f8..cf0ba93426da 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -53,6 +53,7 @@ struct ceph_osd { enum ceph_osd_data_type { CEPH_OSD_DATA_TYPE_NONE, CEPH_OSD_DATA_TYPE_PAGES, + CEPH_OSD_DATA_TYPE_PAGELIST, #ifdef CONFIG_BLOCK CEPH_OSD_DATA_TYPE_BIO, #endif /* CONFIG_BLOCK */ @@ -68,8 +69,9 @@ struct ceph_osd_data { bool pages_from_pool; bool own_pages; }; + struct ceph_pagelist *pagelist; #ifdef CONFIG_BLOCK - struct bio *bio; + struct bio *bio; #endif /* CONFIG_BLOCK */ }; }; -- cgit v1.2.3 From 95e072eb38f99c724739d91a1f12bb8bfe1619b5 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 8 Mar 2013 13:35:36 -0600 Subject: libceph: kill osd request r_trail The osd trail is a pagelist, used only for a CALL osd operation to hold the class and method names, along with any input data for the call. It is only currently used by the rbd client, and when it's used it is the only bit of outbound data in the osd request. Since we already support (non-trail) pagelist data in a message, we can just save this outbound CALL data in the "normal" pagelist rather than the trail, and get rid of the trail entirely. The existing pagelist support depends on the pagelist being dynamically allocated, and ownership of it is passed to the messenger once it's been attached to a message. (That is to say, the messenger releases and frees the pagelist when it's done with it). That means we need to dynamically allocate the pagelist also. Note that we simply assert that the allocation of a pagelist structure succeeds. Appending to a pagelist might require a dynamic allocation, so we're already assuming we won't run into trouble doing so (we're just ignore any failures--and that should be fixed at some point). This resolves: http://tracker.ceph.com/issues/4407 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index cf0ba93426da..1dab291b2dc6 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -134,7 +134,6 @@ struct ceph_osd_request { struct ceph_osd_data r_data_in; struct ceph_osd_data r_data_out; - struct ceph_pagelist r_trail; /* trailing part of data out */ }; struct ceph_osd_event { -- cgit v1.2.3 From 9d2a06c2750177dca5f8d0e89884c1d409d64bbc Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 8 Mar 2013 13:35:36 -0600 Subject: libceph: kill message trail The wart that is the ceph message trail can now be removed, because its only user was the osd client, and the previous patch made that no longer the case. The result allows write_partial_msg_pages() to be simplified considerably. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index b53b9ef65009..0e4536cc46f0 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -69,7 +69,6 @@ struct ceph_messenger { #ifdef CONFIG_BLOCK #define ceph_msg_has_bio(m) ((m)->b.type == CEPH_MSG_DATA_BIO) #endif /* CONFIG_BLOCK */ -#define ceph_msg_has_trail(m) ((m)->t.type == CEPH_MSG_DATA_PAGELIST) enum ceph_msg_data_type { CEPH_MSG_DATA_NONE, /* message contains no data payload */ @@ -155,7 +154,6 @@ struct ceph_msg { #ifdef CONFIG_BLOCK struct ceph_msg_data b; /* bio */ #endif /* CONFIG_BLOCK */ - struct ceph_msg_data t; /* trail */ struct ceph_connection *con; struct list_head list_head; /* links for connection lists */ @@ -295,8 +293,6 @@ extern void ceph_msg_data_set_pages(struct ceph_msg *msg, struct page **pages, extern void ceph_msg_data_set_pagelist(struct ceph_msg *msg, struct ceph_pagelist *pagelist); extern void ceph_msg_data_set_bio(struct ceph_msg *msg, struct bio *bio); -extern void ceph_msg_data_set_trail(struct ceph_msg *msg, - struct ceph_pagelist *trail); extern struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags, bool can_fail); -- cgit v1.2.3 From 3a23083bda56850a1dc0e1c6d270b1f5dc789f07 Mon Sep 17 00:00:00 2001 From: Sage Weil Date: Mon, 25 Mar 2013 08:47:40 -0700 Subject: libceph: implement RECONNECT_SEQ feature This is an old protocol extension that allows the client and server to avoid resending old messages after a reconnect (following a socket error). Instead, the exchange their sequence numbers during the handshake. This avoids sending a bunch of useless data over the socket. It has been supported in the server code since v0.22 (Sep 2010). Signed-off-by: Sage Weil Reviewed-by: Alex Elder --- include/linux/ceph/ceph_features.h | 2 ++ include/linux/ceph/msgr.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index 76554cecaab2..4c42080347af 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -41,6 +41,7 @@ */ #define CEPH_FEATURES_SUPPORTED_DEFAULT \ (CEPH_FEATURE_NOSRCADDR | \ + CEPH_FEATURE_RECONNECT_SEQ | \ CEPH_FEATURE_PGID64 | \ CEPH_FEATURE_PGPOOL3 | \ CEPH_FEATURE_OSDENC | \ @@ -51,6 +52,7 @@ #define CEPH_FEATURES_REQUIRED_DEFAULT \ (CEPH_FEATURE_NOSRCADDR | \ + CEPH_FEATURE_RECONNECT_SEQ | \ CEPH_FEATURE_PGID64 | \ CEPH_FEATURE_PGPOOL3 | \ CEPH_FEATURE_OSDENC) diff --git a/include/linux/ceph/msgr.h b/include/linux/ceph/msgr.h index 680d3d648cac..3d94a73b5f30 100644 --- a/include/linux/ceph/msgr.h +++ b/include/linux/ceph/msgr.h @@ -87,6 +87,7 @@ struct ceph_entity_inst { #define CEPH_MSGR_TAG_BADPROTOVER 10 /* bad protocol version */ #define CEPH_MSGR_TAG_BADAUTHORIZER 11 /* bad authorizer */ #define CEPH_MSGR_TAG_FEATURES 12 /* insufficient features */ +#define CEPH_MSGR_TAG_SEQ 13 /* 64-bit int follows with seen seq number */ /* -- cgit v1.2.3 From 0bed9b5c523d577378b6f83eab5835fe30c27208 Mon Sep 17 00:00:00 2001 From: Sage Weil Date: Mon, 25 Mar 2013 10:26:01 -0700 Subject: libceph: add update_authorizer auth method Currently the messenger calls out to a get_authorizer con op, which will create a new authorizer if it doesn't yet have one. In the meantime, when we rotate our service keys, the authorizer doesn't get updated. Eventually it will be rejected by the server on a new connection attempt and get invalidated, and we will then rebuild a new authorizer, but this is not ideal. Instead, if we do have an authorizer, call a new update_authorizer op that will verify that the current authorizer is using the latest secret. If it is not, we will build a new one that does. This avoids the transient failure. This fixes one of the sorry sequence of events for bug http://tracker.ceph.com/issues/4282 Signed-off-by: Sage Weil Reviewed-by: Alex Elder --- include/linux/ceph/auth.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/ceph/auth.h b/include/linux/ceph/auth.h index d4080f309b56..73e973e70026 100644 --- a/include/linux/ceph/auth.h +++ b/include/linux/ceph/auth.h @@ -52,6 +52,9 @@ struct ceph_auth_client_ops { */ int (*create_authorizer)(struct ceph_auth_client *ac, int peer_type, struct ceph_auth_handshake *auth); + /* ensure that an existing authorizer is up to date */ + int (*update_authorizer)(struct ceph_auth_client *ac, int peer_type, + struct ceph_auth_handshake *auth); int (*verify_authorizer_reply)(struct ceph_auth_client *ac, struct ceph_authorizer *a, size_t len); void (*destroy_authorizer)(struct ceph_auth_client *ac, -- cgit v1.2.3 From 27859f9773e4a0b2042435b13400ee2c891a61f4 Mon Sep 17 00:00:00 2001 From: Sage Weil Date: Mon, 25 Mar 2013 10:26:14 -0700 Subject: libceph: wrap auth ops in wrapper functions Use wrapper functions that check whether the auth op exists so that callers do not need a bunch of conditional checks. Simplifies the external interface. Signed-off-by: Sage Weil Reviewed-by: Alex Elder --- include/linux/ceph/auth.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include') diff --git a/include/linux/ceph/auth.h b/include/linux/ceph/auth.h index 73e973e70026..c9c3b3abe4a3 100644 --- a/include/linux/ceph/auth.h +++ b/include/linux/ceph/auth.h @@ -97,5 +97,18 @@ extern int ceph_build_auth(struct ceph_auth_client *ac, void *msg_buf, size_t msg_len); extern int ceph_auth_is_authenticated(struct ceph_auth_client *ac); +extern int ceph_auth_create_authorizer(struct ceph_auth_client *ac, + int peer_type, + struct ceph_auth_handshake *auth); +extern void ceph_auth_destroy_authorizer(struct ceph_auth_client *ac, + struct ceph_authorizer *a); +extern int ceph_auth_update_authorizer(struct ceph_auth_client *ac, + int peer_type, + struct ceph_auth_handshake *a); +extern int ceph_auth_verify_authorizer_reply(struct ceph_auth_client *ac, + struct ceph_authorizer *a, + size_t len); +extern void ceph_auth_invalidate_authorizer(struct ceph_auth_client *ac, + int peer_type); #endif -- cgit v1.2.3 From e9966076cdd952e19f2dd4854cd719be0d7cbebc Mon Sep 17 00:00:00 2001 From: Sage Weil Date: Mon, 25 Mar 2013 10:26:30 -0700 Subject: libceph: wrap auth methods in a mutex The auth code is called from a variety of contexts, include the mon_client (protected by the monc's mutex) and the messenger callbacks (currently protected by nothing). Avoid chaos by protecting all auth state with a mutex. Nothing is blocking, so this should be simple and lightweight. Signed-off-by: Sage Weil Reviewed-by: Alex Elder --- include/linux/ceph/auth.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/ceph/auth.h b/include/linux/ceph/auth.h index c9c3b3abe4a3..5f3386844134 100644 --- a/include/linux/ceph/auth.h +++ b/include/linux/ceph/auth.h @@ -78,6 +78,8 @@ struct ceph_auth_client { u64 global_id; /* our unique id in system */ const struct ceph_crypto_key *key; /* our secret key */ unsigned want_keys; /* which services we want */ + + struct mutex mutex; }; extern struct ceph_auth_client *ceph_auth_init(const char *name, -- cgit v1.2.3 From 25aff7c559c8b54a810bc094d59fe037cfed6b18 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Mon, 11 Mar 2013 23:34:22 -0500 Subject: libceph: record residual bytes for all message data types All of the data types can use this, not just the page array. Until now, only the bio type doesn't have it available, and only the initiator of the request (the rbd client) is able to supply the length of the full request without re-scanning the bio list. Change the cursor init routines so the length is supplied based on the message header "data_len" field, and use that length to intiialize the "resid" field of the cursor. In addition, change the way "last_piece" is defined so it is based on the residual number of bytes in the original request. This is necessary (at least for bio messages) because it is possible for a read request to succeed without consuming all of the space available in the data buffer. This resolves: http://tracker.ceph.com/issues/4427 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 0e4536cc46f0..459e55280bf8 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -95,6 +95,7 @@ static __inline__ bool ceph_msg_data_type_valid(enum ceph_msg_data_type type) } struct ceph_msg_data_cursor { + size_t resid; /* bytes not yet consumed */ bool last_piece; /* now at last piece of data item */ union { #ifdef CONFIG_BLOCK @@ -105,7 +106,6 @@ struct ceph_msg_data_cursor { }; #endif /* CONFIG_BLOCK */ struct { /* pages */ - size_t resid; /* bytes from array */ unsigned int page_offset; /* offset in page */ unsigned short page_index; /* index in array */ unsigned short page_count; /* pages in array */ -- cgit v1.2.3 From 6518be47f910f62a98cb6044dbb457af55241f95 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Mon, 11 Mar 2013 23:34:23 -0500 Subject: libceph: kill ceph message bio_iter, bio_seg The bio_iter and bio_seg fields in a message are no longer used, we use the cursor instead. So get rid of them and the functions that operate on them them. This is related to: http://tracker.ceph.com/issues/4428 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 459e55280bf8..252e01b7f7de 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -121,11 +121,7 @@ struct ceph_msg_data { enum ceph_msg_data_type type; union { #ifdef CONFIG_BLOCK - struct { - struct bio *bio_iter; /* iterator */ - struct bio *bio; - unsigned int bio_seg; /* current seg in bio */ - }; + struct bio *bio; #endif /* CONFIG_BLOCK */ struct { struct page **pages; /* NOT OWNER. */ -- cgit v1.2.3 From 4c59b4a278f9b7a418ad8af933fd7b341df64393 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Mon, 11 Mar 2013 23:34:23 -0500 Subject: libceph: collapse all data items into one It turns out that only one of the data item types is ever used at any one time in a single message (currently). - A page array is used by the osd client (on behalf of the file system) and by rbd. Only one osd op (and therefore at most one data item) is ever used at a time by rbd. And the only time the file system sends two, the second op contains no data. - A bio is only used by the rbd client (and again, only one data item per message) - A page list is used by the file system and by rbd for outgoing data, but only one op (and one data item) at a time. We can therefore collapse all three of our data item fields into a single field "data", and depend on the messenger code to properly handle it based on its type. This allows us to eliminate quite a bit of duplicated code. This is related to: http://tracker.ceph.com/issues/4429 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 12 ++---------- 1 file changed, 2 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 252e01b7f7de..af786b29f7a4 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -64,11 +64,7 @@ struct ceph_messenger { u32 required_features; }; -#define ceph_msg_has_pages(m) ((m)->p.type == CEPH_MSG_DATA_PAGES) -#define ceph_msg_has_pagelist(m) ((m)->l.type == CEPH_MSG_DATA_PAGELIST) -#ifdef CONFIG_BLOCK -#define ceph_msg_has_bio(m) ((m)->b.type == CEPH_MSG_DATA_BIO) -#endif /* CONFIG_BLOCK */ +#define ceph_msg_has_data(m) ((m)->data.type != CEPH_MSG_DATA_NONE) enum ceph_msg_data_type { CEPH_MSG_DATA_NONE, /* message contains no data payload */ @@ -145,11 +141,7 @@ struct ceph_msg { struct ceph_buffer *middle; /* data payload */ - struct ceph_msg_data p; /* pages */ - struct ceph_msg_data l; /* pagelist */ -#ifdef CONFIG_BLOCK - struct ceph_msg_data b; /* bio */ -#endif /* CONFIG_BLOCK */ + struct ceph_msg_data data; struct ceph_connection *con; struct list_head list_head; /* links for connection lists */ -- cgit v1.2.3 From 859a35d5523e8e6a5c3568c12febe2e1270bc3a1 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Mon, 11 Mar 2013 23:34:23 -0500 Subject: libceph: kill most of ceph_msg_pos All but one of the fields in the ceph_msg_pos structure are now never used (only assigned), so get rid of them. This allows several small blocks of code to go away. This is cleanup of old code related to: http://tracker.ceph.com/issues/4428 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index af786b29f7a4..c76b228cb524 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -157,8 +157,6 @@ struct ceph_msg { }; struct ceph_msg_pos { - int page, page_pos; /* which page; offset in page */ - int data_pos; /* offset in data payload */ bool did_page_crc; /* true if we've calculated crc for current page */ }; -- cgit v1.2.3 From f5db90bcf2c69d099f9d828a8104796f41de6bc5 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Mon, 11 Mar 2013 23:34:23 -0500 Subject: libceph: kill last of ceph_msg_pos The only remaining field in the ceph_msg_pos structure is did_page_crc. In the new cursor model of things that flag (or something like it) belongs in the cursor. Define a new field "need_crc" in the cursor (which applies to all types of data) and initialize it to true whenever a cursor is initialized. In write_partial_message_data(), the data CRC still will be computed as before, but it will check the cursor->need_crc field to determine whether it's needed. Any time the cursor is advanced to a new piece of a data item, need_crc will be set, and this will cause the crc for that entire piece to be accumulated into the data crc. In write_partial_message_data() the intermediate crc value is now held in a local variable so it doesn't have to be byte-swapped so many times. In read_partial_msg_data() we do something similar (but mainly for consistency there). With that, the ceph_msg_pos structure can go away, and it no longer needs to be passed as an argument to prepare_message_data(). This cleanup is related to: http://tracker.ceph.com/issues/4428 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index c76b228cb524..686df5bfa717 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -93,6 +93,7 @@ static __inline__ bool ceph_msg_data_type_valid(enum ceph_msg_data_type type) struct ceph_msg_data_cursor { size_t resid; /* bytes not yet consumed */ bool last_piece; /* now at last piece of data item */ + bool need_crc; /* new piece; crc update needed */ union { #ifdef CONFIG_BLOCK struct { /* bio */ @@ -156,10 +157,6 @@ struct ceph_msg { struct ceph_msgpool *pool; }; -struct ceph_msg_pos { - bool did_page_crc; /* true if we've calculated crc for current page */ -}; - /* ceph connection fault delay defaults, for exponential backoff */ #define BASE_DELAY_INTERVAL (HZ/2) #define MAX_DELAY_INTERVAL (5 * 60 * HZ) @@ -217,7 +214,6 @@ struct ceph_connection { struct ceph_msg *out_msg; /* sending message (== tail of out_sent) */ bool out_msg_done; - struct ceph_msg_pos out_msg_pos; struct kvec out_kvec[8], /* sending header/footer data */ *out_kvec_cur; @@ -231,7 +227,6 @@ struct ceph_connection { /* message in temps */ struct ceph_msg_header in_hdr; struct ceph_msg *in_msg; - struct ceph_msg_pos in_msg_pos; u32 in_front_crc, in_middle_crc, in_data_crc; /* calculated crc */ char in_tag; /* protocol control byte */ -- cgit v1.2.3 From 6644ed7b7e04f8e588aebdaa58cededb9416ab95 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Mon, 11 Mar 2013 23:34:24 -0500 Subject: libceph: make message data be a pointer Begin the transition from a single message data item to a list of them by replacing the "data" structure in a message with a pointer to a ceph_msg_data structure. A null pointer will indicate the message has no data; replace the use of ceph_msg_has_data() with a simple check for a null pointer. Create functions ceph_msg_data_create() and ceph_msg_data_destroy() to dynamically allocate and free a data item structure of a given type. When a message has its data item "set," allocate one of these to hold the data description, and free it when the last reference to the message is dropped. This partially resolves: http://tracker.ceph.com/issues/4429 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 686df5bfa717..3181321bed6d 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -64,8 +64,6 @@ struct ceph_messenger { u32 required_features; }; -#define ceph_msg_has_data(m) ((m)->data.type != CEPH_MSG_DATA_NONE) - enum ceph_msg_data_type { CEPH_MSG_DATA_NONE, /* message contains no data payload */ CEPH_MSG_DATA_PAGES, /* data source/destination is a page array */ @@ -141,8 +139,7 @@ struct ceph_msg { struct kvec front; /* unaligned blobs of message */ struct ceph_buffer *middle; - /* data payload */ - struct ceph_msg_data data; + struct ceph_msg_data *data; /* data payload */ struct ceph_connection *con; struct list_head list_head; /* links for connection lists */ -- cgit v1.2.3 From adfe695a25e92e3a4597807fbc7f9a8105218776 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Wed, 13 Mar 2013 20:50:00 -0500 Subject: ceph: move max constant definitions Move some definitions for max integer values out of the rbd code and into the more central "decode.h" header file. These really belong in a Linux (or libc) header somewhere, but I haven't gotten around to proposing that yet. This is in preparation for moving some code out of rbd.c and into the osd client. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/decode.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/ceph/decode.h b/include/linux/ceph/decode.h index 360d9d08ca9e..689f1df37bff 100644 --- a/include/linux/ceph/decode.h +++ b/include/linux/ceph/decode.h @@ -8,6 +8,13 @@ #include +/* This seemed to be the easiest place to define these */ + +#define U8_MAX ((u8) (~0U)) +#define U16_MAX ((u16) (~0U)) +#define U32_MAX ((u32) (~0U)) +#define U64_MAX ((u64) (~0ULL)) + /* * in all cases, * void **p pointer to position pointer -- cgit v1.2.3 From 33803f3300265661b5c5d20a9811c6a2a157d545 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Wed, 13 Mar 2013 20:50:00 -0500 Subject: libceph: define source request op functions The rbd code has a function that allocates and populates a ceph_osd_req_op structure (the in-core version of an osd request operation). When reviewed, Josh suggested two things: that the big varargs function might be better split into type-specific functions; and that this functionality really belongs in the osd client rather than rbd. This patch implements both of Josh's suggestions. It breaks up the rbd function into separate functions and defines them in the osd client module as exported interfaces. Unlike the rbd version, however, the functions don't allocate an osd_req_op structure; they are provided the address of one and that is initialized instead. The rbd function has been eliminated and calls to it have been replaced by calls to the new routines. The rbd code now now use a stack (struct) variable to hold the op rather than allocating and freeing it each time. For now only the capabilities used by rbd are implemented. Implementing all the other osd op types, and making the rest of the code use it will be done separately, in the next few patches. Note that only the extent, cls, and watch portions of the ceph_osd_req_op structure are currently used. Delete the others (xattr, pgls, and snap) from its definition so nobody thinks it's actually implemented or needed. We can add it back again later if needed, when we know it's been tested. This (and a few follow-on patches) resolves: http://tracker.ceph.com/issues/3861 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 26 +++++++++++--------------- 1 file changed, 11 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 1dab291b2dc6..5fd2cbfcfd91 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -201,14 +201,6 @@ struct ceph_osd_req_op { u64 truncate_size; u32 truncate_seq; } extent; - struct { - const char *name; - const void *val; - u32 name_len; - u32 value_len; - __u8 cmp_op; /* CEPH_OSD_CMPXATTR_OP_* */ - __u8 cmp_mode; /* CEPH_OSD_CMPXATTR_MODE_* */ - } xattr; struct { const char *class_name; const char *method_name; @@ -218,13 +210,6 @@ struct ceph_osd_req_op { __u8 method_len; __u8 argc; } cls; - struct { - u64 cookie; - u64 count; - } pgls; - struct { - u64 snapid; - } snap; struct { u64 cookie; u64 ver; @@ -244,6 +229,17 @@ extern void ceph_osdc_handle_reply(struct ceph_osd_client *osdc, extern void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg); +extern void osd_req_op_init(struct ceph_osd_req_op *op, u16 opcode); +extern void osd_req_op_extent_init(struct ceph_osd_req_op *op, u16 opcode, + u64 offset, u64 length, + u64 truncate_size, u32 truncate_seq); +extern void osd_req_op_cls_init(struct ceph_osd_req_op *op, u16 opcode, + const char *class, const char *method, + const void *request_data, + size_t request_data_size); +extern void osd_req_op_watch_init(struct ceph_osd_req_op *op, u16 opcode, + u64 cookie, u64 version, int flag); + extern struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, struct ceph_snap_context *snapc, unsigned int num_op, -- cgit v1.2.3 From ef4859d6479d19bcc65c3156cf3b7dd747355c29 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Mon, 1 Apr 2013 18:58:26 -0500 Subject: libceph: define ceph_decode_pgid() only once There are two basically identical definitions of __decode_pgid() in libceph, one in "net/ceph/osdmap.c" and the other in "net/ceph/osd_client.c". Get rid of both, and instead define a single inline version in "include/linux/ceph/osdmap.h". Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osdmap.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include') diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h index 167daf60c4e8..d05cc4451af6 100644 --- a/include/linux/ceph/osdmap.h +++ b/include/linux/ceph/osdmap.h @@ -3,6 +3,7 @@ #include #include +#include #include #include @@ -119,6 +120,29 @@ static inline struct ceph_entity_addr *ceph_osd_addr(struct ceph_osdmap *map, return &map->osd_addr[osd]; } +static inline int ceph_decode_pgid(void **p, void *end, struct ceph_pg *pgid) +{ + __u8 version; + + if (!ceph_has_room(p, end, 1 + 8 + 4 + 4)) { + pr_warning("incomplete pg encoding"); + + return -EINVAL; + } + version = ceph_decode_8(p); + if (version > 1) { + pr_warning("do not understand pg encoding %d > 1", + (int)version); + return -EINVAL; + } + + pgid->pool = ceph_decode_64(p); + pgid->seed = ceph_decode_32(p); + *p += 4; /* skip deprecated preferred value */ + + return 0; +} + extern struct ceph_osdmap *osdmap_decode(void **p, void *end); extern struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, struct ceph_osdmap *map, -- cgit v1.2.3 From ace6d3a96f00c271b3f337adcde8e8cbe39c3820 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Mon, 1 Apr 2013 16:12:14 -0500 Subject: libceph: drop ceph_osd_request->r_con_filling_msg A field in an osd request keeps track of whether a connection is currently filling the request's reply message. This patch gets rid of that field. An osd request includes two messages--a request and a reply--and they're both associated with the connection that existed to its the target osd at the time the request was created. An osd request can be dropped early, even when it's in flight. And at that time both messages are released. It's possible the reply message has been supplied to its connection to receive an incoming response message at the time the osd request gets dropped. So ceph_osdc_release_request() revokes that message from the connection before releasing it so things get cleaned up properly. Previously this may have caused a problem, because the connection that a message was associated with might have gone away before the revoke request. And to avoid any problems using that connection, the osd client held a reference to it when it supplies its response message. However since this commit: 38941f80 libceph: have messages point to their connection all messages hold a reference to the connection they are associated with whenever the connection is actively operating on the message (i.e. while the message is queued to send or sending, and when it data is being received into it). And if a message has no connection associated with it, ceph_msg_revoke_incoming() won't do anything when asked to revoke it. As a result, there is no need to keep an additional reference to the connection associated with a message when we hand the message to the messenger when it calls our alloc_msg() method to receive something. If the connection *were* operating on it, it would have its own reference, and if not, there's no work to be done when we need to revoke it. So get rid of the osd request's r_con_filling_msg field. This resolves: http://tracker.ceph.com/issues/4647 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 5fd2cbfcfd91..3b5ba31c2cbd 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -89,8 +89,6 @@ struct ceph_osd_request { int r_pg_osds[CEPH_PG_MAX_SIZE]; int r_num_pg_osds; - struct ceph_connection *r_con_filling_msg; - struct ceph_msg *r_request, *r_reply; int r_flags; /* any additional flags for the osd */ u32 r_sent; /* >0 if r_request is sending/sent */ -- cgit v1.2.3 From fdce58ccb5df621695b079378c619046acabc778 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Thu, 14 Mar 2013 14:09:06 -0500 Subject: libceph: record length of bio list with bio When assigning a bio pointer to an osd request, we don't have an efficient way of knowing the total length bytes in the bio list. That information is available at the point it's set up by the rbd code, so record it with the osd data when it's set. This and the next patch are related to maintaining the length of a message's data independent of the message header, as described here: http://tracker.ceph.com/issues/4589 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 3b5ba31c2cbd..fdda93ebbb4c 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -71,7 +71,10 @@ struct ceph_osd_data { }; struct ceph_pagelist *pagelist; #ifdef CONFIG_BLOCK - struct bio *bio; + struct { + struct bio *bio; /* list of bios */ + size_t bio_length; /* total in list */ + }; #endif /* CONFIG_BLOCK */ }; }; -- cgit v1.2.3 From a19308048182d5f9e16b03b1d1c038d9346c7589 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Thu, 14 Mar 2013 14:09:06 -0500 Subject: libceph: record message data length Keep track of the length of the data portion for a message in a separate field in the ceph_msg structure. This information has been maintained in wire byte order in the message header, but that's going to change soon. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 3181321bed6d..b832c0ce899a 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -139,6 +139,7 @@ struct ceph_msg { struct kvec front; /* unaligned blobs of message */ struct ceph_buffer *middle; + size_t data_length; struct ceph_msg_data *data; /* data payload */ struct ceph_connection *con; @@ -270,7 +271,8 @@ extern void ceph_msg_data_set_pages(struct ceph_msg *msg, struct page **pages, size_t length, size_t alignment); extern void ceph_msg_data_set_pagelist(struct ceph_msg *msg, struct ceph_pagelist *pagelist); -extern void ceph_msg_data_set_bio(struct ceph_msg *msg, struct bio *bio); +extern void ceph_msg_data_set_bio(struct ceph_msg *msg, struct bio *bio, + size_t length); extern struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags, bool can_fail); -- cgit v1.2.3 From acead002b200569273bed331c93c4a91d25e10b8 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Thu, 14 Mar 2013 14:09:05 -0500 Subject: libceph: don't build request in ceph_osdc_new_request() This patch moves the call to ceph_osdc_build_request() out of ceph_osdc_new_request() and into its caller. This is in order to defer formatting osd operation information into the request message until just before request is started. The only unusual (ab)user of ceph_osdc_build_request() is ceph_writepages_start(), where the final length of write request may change (downward) based on the current inode size or the oldest snapshot context with dirty data for the inode. The remaining callers don't change anything in the request after has been built. This means the ops array is now supplied by the caller. It also means there is no need to pass the mtime to ceph_osdc_new_request() (it gets provided to ceph_osdc_build_request()). And rather than passing a do_sync flag, have the number of ops in the ops array supplied imply adding a second STARTSYNC operation after the READ or WRITE requested. This and some of the patches that follow are related to having the messenger (only) be responsible for filling the content of the message header, as described here: http://tracker.ceph.com/issues/4589 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index fdda93ebbb4c..ffaf9076fdc4 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -243,12 +243,12 @@ extern void osd_req_op_watch_init(struct ceph_osd_req_op *op, u16 opcode, extern struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, struct ceph_snap_context *snapc, - unsigned int num_op, + unsigned int num_ops, bool use_mempool, gfp_t gfp_flags); extern void ceph_osdc_build_request(struct ceph_osd_request *req, u64 off, - unsigned int num_op, + unsigned int num_ops, struct ceph_osd_req_op *src_ops, struct ceph_snap_context *snapc, u64 snap_id, @@ -257,11 +257,11 @@ extern void ceph_osdc_build_request(struct ceph_osd_request *req, u64 off, extern struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *, struct ceph_file_layout *layout, struct ceph_vino vino, - u64 offset, u64 *len, int op, int flags, + u64 offset, u64 *len, + int num_ops, struct ceph_osd_req_op *ops, + int opcode, int flags, struct ceph_snap_context *snapc, - int do_sync, u32 truncate_seq, - u64 truncate_size, - struct timespec *mtime, + u32 truncate_seq, u64 truncate_size, bool use_mempool); extern void ceph_osdc_set_request_linger(struct ceph_osd_client *osdc, -- cgit v1.2.3 From e5975c7c8eb6aeab8d2f76a98c368081082795e0 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Thu, 14 Mar 2013 14:09:05 -0500 Subject: ceph: build osd request message later for writepages Hold off building the osd request message in ceph_writepages_start() until just before it will be submitted to the osd client for execution. We'll still create the request and allocate the page pointer array after we learn we have at least one page to write. A local variable will be used to keep track of the allocated array of pages. Wait until just before submitting the request for assigning that page array pointer to the request message. Create ands use a new function osd_req_op_extent_update() whose purpose is to serve this one spot where the length value supplied when an osd request's op was initially formatted might need to get changed (reduced, never increased) before submitting the request. Previously, ceph_writepages_start() assigned the message header's data length because of this update. That's no longer necessary, because ceph_osdc_build_request() will recalculate the right value to use based on the content of the ops in the request. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index ffaf9076fdc4..5ee1a3776b4b 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -234,6 +234,7 @@ extern void osd_req_op_init(struct ceph_osd_req_op *op, u16 opcode); extern void osd_req_op_extent_init(struct ceph_osd_req_op *op, u16 opcode, u64 offset, u64 length, u64 truncate_size, u32 truncate_seq); +extern void osd_req_op_extent_update(struct ceph_osd_req_op *op, u64 length); extern void osd_req_op_cls_init(struct ceph_osd_req_op *op, u16 opcode, const char *class, const char *method, const void *request_data, -- cgit v1.2.3 From 43bfe5de9fa78e07248b70992ce50321efec622c Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Wed, 3 Apr 2013 01:28:57 -0500 Subject: libceph: define osd data initialization helpers Define and use functions that encapsulate the initializion of a ceph_osd_data structure. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 5ee1a3776b4b..af60dac1f9c0 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -280,6 +280,17 @@ static inline void ceph_osdc_put_request(struct ceph_osd_request *req) kref_put(&req->r_kref, ceph_osdc_release_request); } +extern void ceph_osd_data_pages_init(struct ceph_osd_data *osd_data, + struct page **pages, u64 length, + u32 alignment, bool pages_from_pool, + bool own_pages); +extern void ceph_osd_data_pagelist_init(struct ceph_osd_data *osd_data, + struct ceph_pagelist *pagelist); +#ifdef CONFIG_BLOCK +extern void ceph_osd_data_bio_init(struct ceph_osd_data *osd_data, + struct bio *bio, size_t bio_length); +#endif /* CONFIG_BLOCK */ + extern int ceph_osdc_start_request(struct ceph_osd_client *osdc, struct ceph_osd_request *req, bool nofail); -- cgit v1.2.3 From 79528734f3ae4699a2886f62f55e18fb34fb3651 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Wed, 3 Apr 2013 21:32:51 -0500 Subject: libceph: keep source rather than message osd op array An osd request keeps a pointer to the osd operations (ops) array that it builds in its request message. In order to allow each op in the array to have its own distinct data, we will need to keep track of each op's data, and that information does not go over the wire. As long as we're tracking the data we might as well just track the entire (source) op definition for each of the ops. And if we're doing that, we'll have no more need to keep a pointer to the wire-encoded version. This patch makes the array of source ops be kept with the osd request structure, and uses that instead of the version encoded in the message in places where that was previously used. The array will be embedded in the request structure, and the maximum number of ops we ever actually use is currently 2. So reduce CEPH_OSD_MAX_OP to 2 to reduce the size of the structure. The result of doing this sort of ripples back up, and as a result various function parameters and local variables become unnecessary. Make r_num_ops be unsigned, and move the definition of struct ceph_osd_req_op earlier to ensure it's defined where needed. It does not yet add per-op data, that's coming soon. This resolves: http://tracker.ceph.com/issues/4656 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 70 ++++++++++++++++++++--------------------- 1 file changed, 34 insertions(+), 36 deletions(-) (limited to 'include') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index af60dac1f9c0..f4c1a2a22a14 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -48,7 +48,7 @@ struct ceph_osd { }; -#define CEPH_OSD_MAX_OP 10 +#define CEPH_OSD_MAX_OP 2 enum ceph_osd_data_type { CEPH_OSD_DATA_TYPE_NONE, @@ -79,6 +79,34 @@ struct ceph_osd_data { }; }; +struct ceph_osd_req_op { + u16 op; /* CEPH_OSD_OP_* */ + u32 payload_len; + union { + struct { + u64 offset, length; + u64 truncate_size; + u32 truncate_seq; + } extent; + struct { + const char *class_name; + const char *method_name; + const void *indata; + u32 indata_len; + __u8 class_len; + __u8 method_len; + __u8 argc; + } cls; + struct { + u64 cookie; + u64 ver; + u32 prot_ver; + u32 timeout; + __u8 flag; + } watch; + }; +}; + /* an in-flight request */ struct ceph_osd_request { u64 r_tid; /* unique for this client */ @@ -95,10 +123,11 @@ struct ceph_osd_request { struct ceph_msg *r_request, *r_reply; int r_flags; /* any additional flags for the osd */ u32 r_sent; /* >0 if r_request is sending/sent */ - int r_num_ops; - /* encoded message content */ - struct ceph_osd_op *r_request_ops; + /* request osd ops array */ + unsigned int r_num_ops; + struct ceph_osd_req_op r_ops[CEPH_OSD_MAX_OP]; + /* these are updated on each send */ __le32 *r_request_osdmap_epoch; __le32 *r_request_flags; @@ -193,34 +222,6 @@ struct ceph_osd_client { struct workqueue_struct *notify_wq; }; -struct ceph_osd_req_op { - u16 op; /* CEPH_OSD_OP_* */ - u32 payload_len; - union { - struct { - u64 offset, length; - u64 truncate_size; - u32 truncate_seq; - } extent; - struct { - const char *class_name; - const char *method_name; - const void *indata; - u32 indata_len; - __u8 class_len; - __u8 method_len; - __u8 argc; - } cls; - struct { - u64 cookie; - u64 ver; - u32 prot_ver; - u32 timeout; - __u8 flag; - } watch; - }; -}; - extern int ceph_osdc_init(struct ceph_osd_client *osdc, struct ceph_client *client); extern void ceph_osdc_stop(struct ceph_osd_client *osdc); @@ -249,8 +250,6 @@ extern struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client * gfp_t gfp_flags); extern void ceph_osdc_build_request(struct ceph_osd_request *req, u64 off, - unsigned int num_ops, - struct ceph_osd_req_op *src_ops, struct ceph_snap_context *snapc, u64 snap_id, struct timespec *mtime); @@ -259,8 +258,7 @@ extern struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *, struct ceph_file_layout *layout, struct ceph_vino vino, u64 offset, u64 *len, - int num_ops, struct ceph_osd_req_op *ops, - int opcode, int flags, + int num_ops, int opcode, int flags, struct ceph_snap_context *snapc, u32 truncate_seq, u64 truncate_size, bool use_mempool); -- cgit v1.2.3 From 54d5064912649e296552f298e6472ffd37cd8f90 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Wed, 3 Apr 2013 01:28:58 -0500 Subject: libceph: rename data out field in osd request op There are fields "indata" and "indata_len" defined the ceph osd request op structure. The "in" part is with from the point of view of the osd server, but is a little confusing here on the client side. Change their names to use "request" instead of "in" to indicate that it defines data provided with the request (as opposed the data returned in the response). Rename the local variable in osd_req_encode_op() to match. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index f4c1a2a22a14..a9c4089894c8 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -91,8 +91,8 @@ struct ceph_osd_req_op { struct { const char *class_name; const char *method_name; - const void *indata; - u32 indata_len; + const void *request_data; + u32 request_data_len; __u8 class_len; __u8 method_len; __u8 argc; -- cgit v1.2.3 From 8c042b0df99cd06ef8473ef6e204b87b3dc80158 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Wed, 3 Apr 2013 01:28:58 -0500 Subject: libceph: add data pointers in osd op structures An extent type osd operation currently implies that there will be corresponding data supplied in the data portion of the request (for write) or response (for read) message. Similarly, an osd class method operation implies a data item will be supplied to receive the response data from the operation. Add a ceph_osd_data pointer to each of those structures, and assign it to point to eithre the incoming or the outgoing data structure in the osd message. The data is not always available when an op is initially set up, so add two new functions to allow setting them after the op has been initialized. Begin to make use of the data item pointer available in the osd operation rather than the request data in or out structure in places where it's convenient. Add some assertions to verify pointers are always set the way they're expected to be. This is a sort of stepping stone toward really moving the data into the osd request ops, to allow for some validation before making that jump. This is the first in a series of patches that resolve: http://tracker.ceph.com/issues/4657 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index a9c4089894c8..ae5193550fbf 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -87,12 +87,14 @@ struct ceph_osd_req_op { u64 offset, length; u64 truncate_size; u32 truncate_seq; + struct ceph_osd_data *osd_data; } extent; struct { const char *class_name; const char *method_name; const void *request_data; u32 request_data_len; + struct ceph_osd_data *response_data; __u8 class_len; __u8 method_len; __u8 argc; @@ -236,10 +238,14 @@ extern void osd_req_op_extent_init(struct ceph_osd_req_op *op, u16 opcode, u64 offset, u64 length, u64 truncate_size, u32 truncate_seq); extern void osd_req_op_extent_update(struct ceph_osd_req_op *op, u64 length); +extern void osd_req_op_extent_osd_data(struct ceph_osd_req_op *op, + struct ceph_osd_data *osd_data); extern void osd_req_op_cls_init(struct ceph_osd_req_op *op, u16 opcode, const char *class, const char *method, const void *request_data, size_t request_data_size); +extern void osd_req_op_cls_response_data(struct ceph_osd_req_op *op, + struct ceph_osd_data *response_data); extern void osd_req_op_watch_init(struct ceph_osd_req_op *op, u16 opcode, u64 cookie, u64 version, int flag); -- cgit v1.2.3 From c99d2d4abb6c405ef52e9bc1da87b382b8f41739 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 5 Apr 2013 01:27:11 -0500 Subject: libceph: specify osd op by index in request An osd request now holds all of its source op structures, and every place that initializes one of these is in fact initializing one of the entries in the the osd request's array. So rather than supplying the address of the op to initialize, have caller specify the osd request and an indication of which op it would like to initialize. This better hides the details the op structure (and faciltates moving the data pointers they use). Since osd_req_op_init() is a common routine, and it's not used outside the osd client code, give it static scope. Also make it return the address of the specified op (so all the other init routines don't have to repeat that code). Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index ae5193550fbf..144d57cbef9e 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -233,20 +233,25 @@ extern void ceph_osdc_handle_reply(struct ceph_osd_client *osdc, extern void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg); -extern void osd_req_op_init(struct ceph_osd_req_op *op, u16 opcode); -extern void osd_req_op_extent_init(struct ceph_osd_req_op *op, u16 opcode, +extern void osd_req_op_extent_init(struct ceph_osd_request *osd_req, + unsigned int which, u16 opcode, u64 offset, u64 length, u64 truncate_size, u32 truncate_seq); -extern void osd_req_op_extent_update(struct ceph_osd_req_op *op, u64 length); -extern void osd_req_op_extent_osd_data(struct ceph_osd_req_op *op, +extern void osd_req_op_extent_update(struct ceph_osd_request *osd_req, + unsigned int which, u64 length); +extern void osd_req_op_extent_osd_data(struct ceph_osd_request *osd_req, + unsigned int which, struct ceph_osd_data *osd_data); -extern void osd_req_op_cls_init(struct ceph_osd_req_op *op, u16 opcode, +extern void osd_req_op_cls_init(struct ceph_osd_request *osd_req, + unsigned int which, u16 opcode, const char *class, const char *method, const void *request_data, size_t request_data_size); -extern void osd_req_op_cls_response_data(struct ceph_osd_req_op *op, +extern void osd_req_op_cls_response_data(struct ceph_osd_request *osd_req, + unsigned int which, struct ceph_osd_data *response_data); -extern void osd_req_op_watch_init(struct ceph_osd_req_op *op, u16 opcode, +extern void osd_req_op_watch_init(struct ceph_osd_request *osd_req, + unsigned int which, u16 opcode, u64 cookie, u64 version, int flag); extern struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, -- cgit v1.2.3 From 5f562df5f59340eae4272501b974903f48d2ad92 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 5 Apr 2013 01:27:12 -0500 Subject: libceph: format class info at init time An object class method is formatted using a pagelist which contains the class name, the method name, and the data concatenated into an osd request's outbound data. Currently when a class op is initialized in osd_req_op_cls_init(), the lengths of and pointers to these three items are recorded. Later, when the op is getting formatted into the request message, a new pagelist is created and that is when these items get copied into the pagelist. This patch makes it so the pagelist to hold these items is created when the op is initialized instead. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 144d57cbef9e..71c41575646d 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -93,8 +93,9 @@ struct ceph_osd_req_op { const char *class_name; const char *method_name; const void *request_data; - u32 request_data_len; + struct ceph_osd_data *request_info; struct ceph_osd_data *response_data; + u32 request_data_len; __u8 class_len; __u8 method_len; __u8 argc; -- cgit v1.2.3 From a4ce40a9a7c1053ac2a41cf64255e44e356e5522 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 5 Apr 2013 01:27:12 -0500 Subject: libceph: combine initializing and setting osd data This ends up being a rather large patch but what it's doing is somewhat straightforward. Basically, this is replacing two calls with one. The first of the two calls is initializing a struct ceph_osd_data with data (either a page array, a page list, or a bio list); the second is setting an osd request op so it associates that data with one of the op's parameters. In place of those two will be a single function that initializes the op directly. That means we sort of fan out a set of the needed functions: - extent ops with pages data - extent ops with pagelist data - extent ops with bio list data and - class ops with page data for receiving a response We also have define another one, but it's only used internally: - class ops with pagelist data for request parameters Note that we *still* haven't gotten rid of the osd request's r_data_in and r_data_out fields. All the osd ops refer to them for their data. For now, these data fields are pointers assigned to the appropriate r_data_* field when these new functions are called. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 43 ++++++++++++++++++++++++++--------------- 1 file changed, 27 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 71c41575646d..f8a00b48e550 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -240,17 +240,39 @@ extern void osd_req_op_extent_init(struct ceph_osd_request *osd_req, u64 truncate_size, u32 truncate_seq); extern void osd_req_op_extent_update(struct ceph_osd_request *osd_req, unsigned int which, u64 length); -extern void osd_req_op_extent_osd_data(struct ceph_osd_request *osd_req, + +extern struct ceph_osd_data *osd_req_op_extent_osd_data( + struct ceph_osd_request *osd_req, + unsigned int which, bool write_request); +extern struct ceph_osd_data *osd_req_op_cls_response_data( + struct ceph_osd_request *osd_req, + unsigned int which); + +extern void osd_req_op_extent_osd_data_pages(struct ceph_osd_request *, + unsigned int which, bool write_request, + struct page **pages, u64 length, + u32 alignment, bool pages_from_pool, + bool own_pages); +extern void osd_req_op_extent_osd_data_pagelist(struct ceph_osd_request *, + unsigned int which, bool write_request, + struct ceph_pagelist *pagelist); +#ifdef CONFIG_BLOCK +extern void osd_req_op_extent_osd_data_bio(struct ceph_osd_request *, + unsigned int which, bool write_request, + struct bio *bio, size_t bio_length); +#endif /* CONFIG_BLOCK */ + +extern void osd_req_op_cls_response_data_pages(struct ceph_osd_request *, unsigned int which, - struct ceph_osd_data *osd_data); + struct page **pages, u64 length, + u32 alignment, bool pages_from_pool, + bool own_pages); + extern void osd_req_op_cls_init(struct ceph_osd_request *osd_req, unsigned int which, u16 opcode, const char *class, const char *method, const void *request_data, size_t request_data_size); -extern void osd_req_op_cls_response_data(struct ceph_osd_request *osd_req, - unsigned int which, - struct ceph_osd_data *response_data); extern void osd_req_op_watch_init(struct ceph_osd_request *osd_req, unsigned int which, u16 opcode, u64 cookie, u64 version, int flag); @@ -290,17 +312,6 @@ static inline void ceph_osdc_put_request(struct ceph_osd_request *req) kref_put(&req->r_kref, ceph_osdc_release_request); } -extern void ceph_osd_data_pages_init(struct ceph_osd_data *osd_data, - struct page **pages, u64 length, - u32 alignment, bool pages_from_pool, - bool own_pages); -extern void ceph_osd_data_pagelist_init(struct ceph_osd_data *osd_data, - struct ceph_pagelist *pagelist); -#ifdef CONFIG_BLOCK -extern void ceph_osd_data_bio_init(struct ceph_osd_data *osd_data, - struct bio *bio, size_t bio_length); -#endif /* CONFIG_BLOCK */ - extern int ceph_osdc_start_request(struct ceph_osd_client *osdc, struct ceph_osd_request *req, bool nofail); -- cgit v1.2.3 From ec9123c56787fa7fb2608f05b19d21c5e1912d87 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 5 Apr 2013 01:27:12 -0500 Subject: libceph: set the data pointers when encoding ops Still using the osd request r_data_in and r_data_out pointer, but we're basically only referring to it via the data pointers in the osd ops. And we're transferring that information to the request or reply message only when the op indicates it's needed, in osd_req_encode_op(). To avoid a forward reference, ceph_osdc_msg_data_set() was moved up in the file. Don't bother calling ceph_osd_data_init(), in ceph_osd_alloc(), because the ops array will already be zeroed anyway. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index f8a00b48e550..dd4ca4ba8cab 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -51,7 +51,7 @@ struct ceph_osd { #define CEPH_OSD_MAX_OP 2 enum ceph_osd_data_type { - CEPH_OSD_DATA_TYPE_NONE, + CEPH_OSD_DATA_TYPE_NONE = 0, CEPH_OSD_DATA_TYPE_PAGES, CEPH_OSD_DATA_TYPE_PAGELIST, #ifdef CONFIG_BLOCK -- cgit v1.2.3 From 5476492fba9fd0b4118aacf5b924dd29b8cca56c Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 5 Apr 2013 01:27:12 -0500 Subject: libceph: kill off osd request r_data_in and r_data_out Finally! Convert the osd op data pointers into real structures, and make the switch over to using them instead of having all ops share the in and/or out data structures in the osd request. Set up a new function to traverse the set of ops and release any data associated with them (pages). This and the patches leading up to it resolve: http://tracker.ceph.com/issues/4657 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index dd4ca4ba8cab..4ec46c0ceaf7 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -87,14 +87,14 @@ struct ceph_osd_req_op { u64 offset, length; u64 truncate_size; u32 truncate_seq; - struct ceph_osd_data *osd_data; + struct ceph_osd_data osd_data; } extent; struct { const char *class_name; const char *method_name; const void *request_data; - struct ceph_osd_data *request_info; - struct ceph_osd_data *response_data; + struct ceph_osd_data request_info; + struct ceph_osd_data response_data; u32 request_data_len; __u8 class_len; __u8 method_len; @@ -164,9 +164,6 @@ struct ceph_osd_request { struct ceph_file_layout r_file_layout; struct ceph_snap_context *r_snapc; /* snap context for writes */ - - struct ceph_osd_data r_data_in; - struct ceph_osd_data r_data_out; }; struct ceph_osd_event { -- cgit v1.2.3 From ea96571f7b865edaf1acd472e6f2cddc9fb67892 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 5 Apr 2013 14:46:01 -0500 Subject: libceph: fix possible CONFIG_BLOCK build problem This patch: 15a0d7b libceph: record message data length did not enclose some bio-specific code inside CONFIG_BLOCK as it should have. Fix that. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index b832c0ce899a..cdeebae03e0d 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -271,8 +271,10 @@ extern void ceph_msg_data_set_pages(struct ceph_msg *msg, struct page **pages, size_t length, size_t alignment); extern void ceph_msg_data_set_pagelist(struct ceph_msg *msg, struct ceph_pagelist *pagelist); +#ifdef CONFIG_BLOCK extern void ceph_msg_data_set_bio(struct ceph_msg *msg, struct bio *bio, size_t length); +#endif /* CONFIG_BLOCK */ extern struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags, bool can_fail); -- cgit v1.2.3 From c851c49591ebf000c610711e39eea7da5ff05b21 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 5 Apr 2013 14:46:01 -0500 Subject: libceph: record bio length The bio is the only data item type that doesn't record its full length. Fix that. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index cdeebae03e0d..4fb870a5b5fc 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -116,7 +116,10 @@ struct ceph_msg_data { enum ceph_msg_data_type type; union { #ifdef CONFIG_BLOCK - struct bio *bio; + struct { + struct bio *bio; + size_t bio_length; + }; #endif /* CONFIG_BLOCK */ struct { struct page **pages; /* NOT OWNER. */ -- cgit v1.2.3 From 36153ec9dd6287d7cedf6afb51453c445d946cee Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Thu, 14 Mar 2013 14:09:06 -0500 Subject: libceph: move cursor into message A message will only be processing a single data item at a time, so there's no need for each data item to have its own cursor. Move the cursor embedded in the message data structure into the message itself. To minimize the impact, keep the data->cursor field, but make it be a pointer to the cursor in the message. Move the definition of ceph_msg_data above ceph_msg_data_cursor so the cursor can point to the data without a forward definition rather than vice-versa. This and the upcoming patches are part of: http://tracker.ceph.com/issues/3761 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 43 +++++++++++++++++++++--------------------- 1 file changed, 22 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 4fb870a5b5fc..e7557242817c 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -88,6 +88,25 @@ static __inline__ bool ceph_msg_data_type_valid(enum ceph_msg_data_type type) } } +struct ceph_msg_data { + enum ceph_msg_data_type type; + union { +#ifdef CONFIG_BLOCK + struct { + struct bio *bio; + size_t bio_length; + }; +#endif /* CONFIG_BLOCK */ + struct { + struct page **pages; /* NOT OWNER. */ + size_t length; /* total # bytes */ + unsigned int alignment; /* first page */ + }; + struct ceph_pagelist *pagelist; + }; + struct ceph_msg_data_cursor *cursor; +}; + struct ceph_msg_data_cursor { size_t resid; /* bytes not yet consumed */ bool last_piece; /* now at last piece of data item */ @@ -112,25 +131,6 @@ struct ceph_msg_data_cursor { }; }; -struct ceph_msg_data { - enum ceph_msg_data_type type; - union { -#ifdef CONFIG_BLOCK - struct { - struct bio *bio; - size_t bio_length; - }; -#endif /* CONFIG_BLOCK */ - struct { - struct page **pages; /* NOT OWNER. */ - size_t length; /* total # bytes */ - unsigned int alignment; /* first page */ - }; - struct ceph_pagelist *pagelist; - }; - struct ceph_msg_data_cursor cursor; /* pagelist only */ -}; - /* * a single message. it contains a header (src, dest, message type, etc.), * footer (crc values, mainly), a "front" message body, and possibly a @@ -142,8 +142,9 @@ struct ceph_msg { struct kvec front; /* unaligned blobs of message */ struct ceph_buffer *middle; - size_t data_length; - struct ceph_msg_data *data; /* data payload */ + size_t data_length; + struct ceph_msg_data *data; + struct ceph_msg_data_cursor cursor; struct ceph_connection *con; struct list_head list_head; /* links for connection lists */ -- cgit v1.2.3 From 8ae4f4f5c056150d5480710ab356801e84d01a3d Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Thu, 14 Mar 2013 14:09:06 -0500 Subject: libceph: have cursor point to data Rather than having a ceph message data item point to the cursor it's associated with, have the cursor point to a data item. This will allow a message cursor to be used for more than one data item. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index e7557242817c..8846ff610502 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -104,13 +104,13 @@ struct ceph_msg_data { }; struct ceph_pagelist *pagelist; }; - struct ceph_msg_data_cursor *cursor; }; struct ceph_msg_data_cursor { - size_t resid; /* bytes not yet consumed */ - bool last_piece; /* now at last piece of data item */ - bool need_crc; /* new piece; crc update needed */ + struct ceph_msg_data *data; /* data item this describes */ + size_t resid; /* bytes not yet consumed */ + bool last_piece; /* current is last piece */ + bool need_crc; /* crc update needed */ union { #ifdef CONFIG_BLOCK struct { /* bio */ -- cgit v1.2.3 From 5240d9f95dfe0f0701b35fbff1cb5b70825ad23f Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Thu, 14 Mar 2013 14:09:06 -0500 Subject: libceph: replace message data pointer with list In place of the message data pointer, use a list head which links through message data items. For now we only support a single entry on that list. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 8846ff610502..318da0170a1e 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -89,6 +89,7 @@ static __inline__ bool ceph_msg_data_type_valid(enum ceph_msg_data_type type) } struct ceph_msg_data { + struct list_head links; /* ceph_msg->data */ enum ceph_msg_data_type type; union { #ifdef CONFIG_BLOCK @@ -143,7 +144,7 @@ struct ceph_msg { struct ceph_buffer *middle; size_t data_length; - struct ceph_msg_data *data; + struct list_head data; struct ceph_msg_data_cursor cursor; struct ceph_connection *con; -- cgit v1.2.3 From ca8b3a69174b04376722672d7dd6b666a7f17c50 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 5 Apr 2013 14:46:01 -0500 Subject: libceph: implement multiple data items in a message This patch adds support to the messenger for more than one data item in its data list. A message data cursor has two more fields to support this: - a count of the number of bytes left to be consumed across all data items in the list, "total_resid" - a pointer to the head of the list (for validation only) The cursor initialization routine has been split into two parts: the outer one, which initializes the cursor for traversing the entire list of data items; and the inner one, which initializes the cursor to start processing a single data item. When a message cursor is first initialized, the outer initialization routine sets total_resid to the length provided. The data pointer is initialized to the first data item on the list. From there, the inner initialization routine finishes by setting up to process the data item the cursor points to. Advancing the cursor consumes bytes in total_resid. If the resid field reaches zero, it means the current data item is fully consumed. If total_resid indicates there is more data, the cursor is advanced to point to the next data item, and then the inner initialization routine prepares for using that. (A check is made at this point to make sure we don't wrap around the front of the list.) The type-specific init routines are modified so they can be given a length that's larger than what the data item can support. The resid field is initialized to the smaller of the provided length and the length of the entire data item. When total_resid reaches zero, we're done. This resolves: http://tracker.ceph.com/issues/3761 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 318da0170a1e..de1d2e1ecce2 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -108,7 +108,10 @@ struct ceph_msg_data { }; struct ceph_msg_data_cursor { - struct ceph_msg_data *data; /* data item this describes */ + size_t total_resid; /* across all data items */ + struct list_head *data_head; /* = &ceph_msg->data */ + + struct ceph_msg_data *data; /* current data item */ size_t resid; /* bytes not yet consumed */ bool last_piece; /* current is last piece */ bool need_crc; /* crc update needed */ -- cgit v1.2.3 From 90af36022aecdeeb1b9c0755461187de717c86dd Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 5 Apr 2013 14:46:01 -0500 Subject: libceph: add, don't set data for a message Change the names of the functions that put data on a pagelist to reflect that we're adding to whatever's already there rather than just setting it to the one thing. Currently only one data item is ever added to a message, but that's about to change. This resolves: http://tracker.ceph.com/issues/2770 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index de1d2e1ecce2..7c1420bb1dce 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -275,12 +275,12 @@ extern void ceph_msg_revoke_incoming(struct ceph_msg *msg); extern void ceph_con_keepalive(struct ceph_connection *con); -extern void ceph_msg_data_set_pages(struct ceph_msg *msg, struct page **pages, +extern void ceph_msg_data_add_pages(struct ceph_msg *msg, struct page **pages, size_t length, size_t alignment); -extern void ceph_msg_data_set_pagelist(struct ceph_msg *msg, +extern void ceph_msg_data_add_pagelist(struct ceph_msg *msg, struct ceph_pagelist *pagelist); #ifdef CONFIG_BLOCK -extern void ceph_msg_data_set_bio(struct ceph_msg *msg, struct bio *bio, +extern void ceph_msg_data_add_bio(struct ceph_msg *msg, struct bio *bio, size_t length); #endif /* CONFIG_BLOCK */ -- cgit v1.2.3 From 04017e29bbcf0673d8a6af616c56e395d05f5971 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 5 Apr 2013 14:46:02 -0500 Subject: libceph: make method call data be a separate data item Right now the data for a method call is specified via a pointer and length, and it's copied--along with the class and method name--into a pagelist data item to be sent to the osd. Instead, encode the data in a data item separate from the class and method names. This will allow large amounts of data to be supplied to methods without copying. Only rbd uses the class functionality right now, and when it really needs this it will probably need to use a page array rather than a page list. But this simple implementation demonstrates the functionality on the osd client, and that's enough for now. This resolves: http://tracker.ceph.com/issues/4104 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 4ec46c0ceaf7..2a68a7465c18 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -92,10 +92,9 @@ struct ceph_osd_req_op { struct { const char *class_name; const char *method_name; - const void *request_data; struct ceph_osd_data request_info; + struct ceph_osd_data request_data; struct ceph_osd_data response_data; - u32 request_data_len; __u8 class_len; __u8 method_len; __u8 argc; @@ -259,6 +258,9 @@ extern void osd_req_op_extent_osd_data_bio(struct ceph_osd_request *, struct bio *bio, size_t bio_length); #endif /* CONFIG_BLOCK */ +extern void osd_req_op_cls_request_data_pagelist(struct ceph_osd_request *, + unsigned int which, + struct ceph_pagelist *pagelist); extern void osd_req_op_cls_response_data_pages(struct ceph_osd_request *, unsigned int which, struct page **pages, u64 length, @@ -267,9 +269,7 @@ extern void osd_req_op_cls_response_data_pages(struct ceph_osd_request *, extern void osd_req_op_cls_init(struct ceph_osd_request *osd_req, unsigned int which, u16 opcode, - const char *class, const char *method, - const void *request_data, - size_t request_data_size); + const char *class, const char *method); extern void osd_req_op_watch_init(struct ceph_osd_request *osd_req, unsigned int which, u16 opcode, u64 cookie, u64 version, int flag); -- cgit v1.2.3 From 26be88087ae8a04a5b576aa2f490597b649fc132 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Mon, 15 Apr 2013 11:20:42 -0500 Subject: libceph: change how "safe" callback is used An osd request currently has two callbacks. They inform the initiator of the request when we've received confirmation for the target osd that a request was received, and when the osd indicates all changes described by the request are durable. The only time the second callback is used is in the ceph file system for a synchronous write. There's a race that makes some handling of this case unsafe. This patch addresses this problem. The error handling for this callback is also kind of gross, and this patch changes that as well. In ceph_sync_write(), if a safe callback is requested we want to add the request on the ceph inode's unsafe items list. Because items on this list must have their tid set (by ceph_osd_start_request()), the request added *after* the call to that function returns. The problem with this is that there's a race between starting the request and adding it to the unsafe items list; the request may already be complete before ceph_sync_write() even begins to put it on the list. To address this, we change the way the "safe" callback is used. Rather than just calling it when the request is "safe", we use it to notify the initiator the bounds (start and end) of the period during which the request is *unsafe*. So the initiator gets notified just before the request gets sent to the osd (when it is "unsafe"), and again when it's known the results are durable (it's no longer unsafe). The first call will get made in __send_request(), just before the request message gets sent to the messenger for the first time. That function is only called by __send_queued(), which is always called with the osd client's request mutex held. We then have this callback function insert the request on the ceph inode's unsafe list when we're told the request is unsafe. This will avoid the race because this call will be made under protection of the osd client's request mutex. It also nicely groups the setup and cleanup of the state associated with managing unsafe requests. The name of the "safe" callback field is changed to "unsafe" to better reflect its new purpose. It has a Boolean "unsafe" parameter to indicate whether the request is becoming unsafe or is now safe. Because the "msg" parameter wasn't used, we drop that. This resolves the original problem reportedin: http://tracker.ceph.com/issues/4706 Reported-by: Yan, Zheng Signed-off-by: Alex Elder Reviewed-by: Yan, Zheng Reviewed-by: Sage Weil --- include/linux/ceph/osd_client.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 2a68a7465c18..0d3358ef5285 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -29,6 +29,7 @@ struct ceph_authorizer; */ typedef void (*ceph_osdc_callback_t)(struct ceph_osd_request *, struct ceph_msg *); +typedef void (*ceph_osdc_unsafe_callback_t)(struct ceph_osd_request *, bool); /* a given osd we're communicating with */ struct ceph_osd { @@ -149,7 +150,8 @@ struct ceph_osd_request { struct kref r_kref; bool r_mempool; struct completion r_completion, r_safe_completion; - ceph_osdc_callback_t r_callback, r_safe_callback; + ceph_osdc_callback_t r_callback; + ceph_osdc_unsafe_callback_t r_unsafe_callback; struct ceph_eversion r_reassert_version; struct list_head r_unsafe_item; -- cgit v1.2.3 From 406e2c9f9286fc93ae2191a7abf477dea05aadc9 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Mon, 15 Apr 2013 14:50:36 -0500 Subject: libceph: kill off osd data write_request parameters In the incremental move toward supporting distinct data items in an osd request some of the functions had "write_request" parameters to indicate, basically, whether the data belonged to in_data or the out_data. Now that we maintain the data fields in the op structure there is no need to indicate the direction, so get rid of the "write_request" parameters. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 0d3358ef5285..0e406934a551 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -241,22 +241,22 @@ extern void osd_req_op_extent_update(struct ceph_osd_request *osd_req, extern struct ceph_osd_data *osd_req_op_extent_osd_data( struct ceph_osd_request *osd_req, - unsigned int which, bool write_request); + unsigned int which); extern struct ceph_osd_data *osd_req_op_cls_response_data( struct ceph_osd_request *osd_req, unsigned int which); extern void osd_req_op_extent_osd_data_pages(struct ceph_osd_request *, - unsigned int which, bool write_request, + unsigned int which, struct page **pages, u64 length, u32 alignment, bool pages_from_pool, bool own_pages); extern void osd_req_op_extent_osd_data_pagelist(struct ceph_osd_request *, - unsigned int which, bool write_request, + unsigned int which, struct ceph_pagelist *pagelist); #ifdef CONFIG_BLOCK extern void osd_req_op_extent_osd_data_bio(struct ceph_osd_request *, - unsigned int which, bool write_request, + unsigned int which, struct bio *bio, size_t bio_length); #endif /* CONFIG_BLOCK */ -- cgit v1.2.3 From 49719778bfa5371ec9b5a7d989bb29000e3ac5df Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Mon, 11 Feb 2013 12:33:24 -0600 Subject: libceph: support raw data requests Allow osd request ops that aren't otherwise structured (not class, extent, or watch ops) to specify "raw" data to be used to hold incoming data for the op. Make use of this capability for the osd STAT op. Prefix the name of the private function osd_req_op_init() with "_", and expose a new function by that (earlier) name whose purpose is to initialize osd ops with (only) implied data. For now we'll just support the use of a page array for an osd op with incoming raw data. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 0e406934a551..4d84a2b44f18 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -84,6 +84,7 @@ struct ceph_osd_req_op { u16 op; /* CEPH_OSD_OP_* */ u32 payload_len; union { + struct ceph_osd_data raw_data_in; struct { u64 offset, length; u64 truncate_size; @@ -232,6 +233,15 @@ extern void ceph_osdc_handle_reply(struct ceph_osd_client *osdc, extern void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg); +extern void osd_req_op_init(struct ceph_osd_request *osd_req, + unsigned int which, u16 opcode); + +extern void osd_req_op_raw_data_in_pages(struct ceph_osd_request *, + unsigned int which, + struct page **pages, u64 length, + u32 alignment, bool pages_from_pool, + bool own_pages); + extern void osd_req_op_extent_init(struct ceph_osd_request *osd_req, unsigned int which, u16 opcode, u64 offset, u64 length, -- cgit v1.2.3 From 6c57b5545d46e276381a15a59283c984cf3f94e3 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 19 Apr 2013 15:34:49 -0500 Subject: libceph: support pages for class request data Add the ability to provide an array of pages as outbound request data for object class method calls. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 4d84a2b44f18..4191cd2c55e5 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -273,6 +273,11 @@ extern void osd_req_op_extent_osd_data_bio(struct ceph_osd_request *, extern void osd_req_op_cls_request_data_pagelist(struct ceph_osd_request *, unsigned int which, struct ceph_pagelist *pagelist); +extern void osd_req_op_cls_request_data_pages(struct ceph_osd_request *, + unsigned int which, + struct page **pages, u64 length, + u32 alignment, bool pages_from_pool, + bool own_pages); extern void osd_req_op_cls_response_data_pages(struct ceph_osd_request *, unsigned int which, struct page **pages, u64 length, -- cgit v1.2.3 From b587398a4ff6520753f9a58da294c80ee22443a5 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 19 Apr 2013 15:34:50 -0500 Subject: libceph: add signed type limits Flesh out the limits defined in to include the maximum and minimum values for signed type S8, S16, S32, and S64. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/decode.h | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/ceph/decode.h b/include/linux/ceph/decode.h index 689f1df37bff..9575a52e011f 100644 --- a/include/linux/ceph/decode.h +++ b/include/linux/ceph/decode.h @@ -10,10 +10,20 @@ /* This seemed to be the easiest place to define these */ -#define U8_MAX ((u8) (~0U)) -#define U16_MAX ((u16) (~0U)) -#define U32_MAX ((u32) (~0U)) -#define U64_MAX ((u64) (~0ULL)) +#define U8_MAX ((u8)(~0U)) +#define U16_MAX ((u16)(~0U)) +#define U32_MAX ((u32)(~0U)) +#define U64_MAX ((u64)(~0ULL)) + +#define S8_MAX ((s8)(U8_MAX >> 1)) +#define S16_MAX ((s16)(U16_MAX >> 1)) +#define S32_MAX ((s32)(U32_MAX >> 1)) +#define S64_MAX ((s64)(U64_MAX >> 1LL)) + +#define S8_MIN ((s8)(-S8_MAX - 1)) +#define S16_MIN ((s16)(-S16_MAX - 1)) +#define S32_MIN ((s32)(-S32_MAX - 1)) +#define S64_MIN ((s64)(-S64_MAX - 1LL)) /* * in all cases, -- cgit v1.2.3 From c3f56102f28d90946171ae51753bd417b003fd42 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 19 Apr 2013 15:34:50 -0500 Subject: libceph: validate timespec conversions A ceph timespec contains 32-bit unsigned values for its seconds and nanoseconds components. For a standard timespec, both fields are signed, and the seconds field is almost surely 64 bits. Add some explicit casts so the fact that this conversion is taking place is obvious. Also trip a bug if we ever try to put out of range (negative or too big) values into a ceph timespec. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/decode.h | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/ceph/decode.h b/include/linux/ceph/decode.h index 9575a52e011f..379f71508995 100644 --- a/include/linux/ceph/decode.h +++ b/include/linux/ceph/decode.h @@ -154,14 +154,19 @@ bad: static inline void ceph_decode_timespec(struct timespec *ts, const struct ceph_timespec *tv) { - ts->tv_sec = le32_to_cpu(tv->tv_sec); - ts->tv_nsec = le32_to_cpu(tv->tv_nsec); + ts->tv_sec = (__kernel_time_t)le32_to_cpu(tv->tv_sec); + ts->tv_nsec = (long)le32_to_cpu(tv->tv_nsec); } static inline void ceph_encode_timespec(struct ceph_timespec *tv, const struct timespec *ts) { - tv->tv_sec = cpu_to_le32(ts->tv_sec); - tv->tv_nsec = cpu_to_le32(ts->tv_nsec); + BUG_ON(ts->tv_sec < 0); + BUG_ON(ts->tv_sec > (__kernel_time_t)U32_MAX); + BUG_ON(ts->tv_nsec < 0); + BUG_ON(ts->tv_nsec > (long)U32_MAX); + + tv->tv_sec = cpu_to_le32((u32)ts->tv_sec); + tv->tv_nsec = cpu_to_le32((u32)ts->tv_nsec); } /* -- cgit v1.2.3 From 4f0dcb10cf1454a1c38aeaa04cb2757535e4905e Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Tue, 30 Apr 2013 00:44:32 -0500 Subject: libceph: create source file "net/ceph/snapshot.c" This creates a new source file "net/ceph/snapshot.c" to contain utility routines related to ceph snapshot contexts. The main motivation was to define ceph_create_snap_context() as a common way to create these structures, but I've moved the definitions of ceph_get_snap_context() and ceph_put_snap_context() there too. (The benefit of inlining those is very small, and I'd rather keep this collection of functions together.) Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/libceph.h | 30 +++++------------------------- 1 file changed, 5 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 5493d7b86423..2e3024881a5e 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -157,31 +157,11 @@ struct ceph_snap_context { u64 snaps[]; }; -static inline struct ceph_snap_context * -ceph_get_snap_context(struct ceph_snap_context *sc) -{ - /* - printk("get_snap_context %p %d -> %d\n", sc, atomic_read(&sc->nref), - atomic_read(&sc->nref)+1); - */ - if (sc) - atomic_inc(&sc->nref); - return sc; -} - -static inline void ceph_put_snap_context(struct ceph_snap_context *sc) -{ - if (!sc) - return; - /* - printk("put_snap_context %p %d -> %d\n", sc, atomic_read(&sc->nref), - atomic_read(&sc->nref)-1); - */ - if (atomic_dec_and_test(&sc->nref)) { - /*printk(" deleting snap_context %p\n", sc);*/ - kfree(sc); - } -} +extern struct ceph_snap_context *ceph_create_snap_context(u32 snap_count, + gfp_t gfp_flags); +extern struct ceph_snap_context *ceph_get_snap_context( + struct ceph_snap_context *sc); +extern void ceph_put_snap_context(struct ceph_snap_context *sc); /* * calculate the number of pages a given length and offset map onto, -- cgit v1.2.3 From 5975a2e0950291a6bfe9fd5880e7952ff87764be Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Sat, 27 Apr 2013 00:28:37 +0000 Subject: KVM: PPC: Book3S: Add API for in-kernel XICS emulation This adds the API for userspace to instantiate an XICS device in a VM and connect VCPUs to it. The API consists of a new device type for the KVM_CREATE_DEVICE ioctl, a new capability KVM_CAP_IRQ_XICS, which functions similarly to KVM_CAP_IRQ_MPIC, and the KVM_IRQ_LINE ioctl, which is used to assert and deassert interrupt inputs of the XICS. The XICS device has one attribute group, KVM_DEV_XICS_GRP_SOURCES. Each attribute within this group corresponds to the state of one interrupt source. The attribute number is the same as the interrupt source number. This does not support irq routing or irqfd yet. Signed-off-by: Paul Mackerras Acked-by: David Gibson Signed-off-by: Alexander Graf --- include/linux/kvm_host.h | 1 + include/uapi/linux/kvm.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 996661eb8e99..7823b6369c5e 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1086,6 +1086,7 @@ void kvm_device_put(struct kvm_device *dev); struct kvm_device *kvm_device_from_filp(struct file *filp); extern struct kvm_device_ops kvm_mpic_ops; +extern struct kvm_device_ops kvm_xics_ops; #ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 965e5b52dee0..a5c86fc34a37 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -665,6 +665,7 @@ struct kvm_ppc_smmu_info { #define KVM_CAP_DEVICE_CTRL 89 #define KVM_CAP_IRQ_MPIC 90 #define KVM_CAP_PPC_RTAS 91 +#define KVM_CAP_IRQ_XICS 92 #ifdef KVM_CAP_IRQ_ROUTING @@ -837,6 +838,7 @@ struct kvm_device_attr { #define KVM_DEV_TYPE_FSL_MPIC_20 1 #define KVM_DEV_TYPE_FSL_MPIC_42 2 +#define KVM_DEV_TYPE_XICS 3 /* * ioctls for VM fds -- cgit v1.2.3 From c13d2b6d3640d1ef180e40191178b4f1271982c1 Mon Sep 17 00:00:00 2001 From: Bhanu Prakash Gollapudi Date: Fri, 8 Mar 2013 13:28:51 -0800 Subject: [SCSI] bnx2fc: Include chip number in the symbolic name [jejb: move PCI_DEVICE_ID definitions to include/pci_ids.h] Signed-off-by: Bhanu Prakash Gollapudi Signed-off-by: James Bottomley --- include/linux/pci_ids.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 2b85c521f737..c12916248469 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2147,11 +2147,13 @@ #define PCI_DEVICE_ID_TIGON3_5705M_2 0x165e #define PCI_DEVICE_ID_NX2_57712 0x1662 #define PCI_DEVICE_ID_NX2_57712E 0x1663 +#define PCI_DEVICE_ID_NX2_57712_MF 0x1663 #define PCI_DEVICE_ID_TIGON3_5714 0x1668 #define PCI_DEVICE_ID_TIGON3_5714S 0x1669 #define PCI_DEVICE_ID_TIGON3_5780 0x166a #define PCI_DEVICE_ID_TIGON3_5780S 0x166b #define PCI_DEVICE_ID_TIGON3_5705F 0x166e +#define PCI_DEVICE_ID_NX2_57712_VF 0x166f #define PCI_DEVICE_ID_TIGON3_5754M 0x1672 #define PCI_DEVICE_ID_TIGON3_5755M 0x1673 #define PCI_DEVICE_ID_TIGON3_5756 0x1674 @@ -2177,13 +2179,15 @@ #define PCI_DEVICE_ID_TIGON3_5787 0x169b #define PCI_DEVICE_ID_TIGON3_5788 0x169c #define PCI_DEVICE_ID_TIGON3_5789 0x169d +#define PCI_DEVICE_ID_NX2_57840_4_10 0x16a1 +#define PCI_DEVICE_ID_NX2_57840_2_20 0x16a2 +#define PCI_DEVICE_ID_NX2_57840_MF 0x16a4 #define PCI_DEVICE_ID_NX2_57800_MF 0x16a5 #define PCI_DEVICE_ID_TIGON3_5702X 0x16a6 #define PCI_DEVICE_ID_TIGON3_5703X 0x16a7 #define PCI_DEVICE_ID_TIGON3_5704S 0x16a8 #define PCI_DEVICE_ID_NX2_57800_VF 0x16a9 #define PCI_DEVICE_ID_NX2_5706S 0x16aa -#define PCI_DEVICE_ID_NX2_57840_MF 0x16a4 #define PCI_DEVICE_ID_NX2_5708S 0x16ac #define PCI_DEVICE_ID_NX2_57840_VF 0x16ad #define PCI_DEVICE_ID_NX2_57810_MF 0x16ae -- cgit v1.2.3 From de61608acf89779c8831aaa1428b6975d49d98c0 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Fri, 19 Apr 2013 11:42:14 +0200 Subject: dma:of: Use a mutex to protect the of_dma_list Currently the OF DMA code uses a spin lock to protect the of_dma_list from concurrent access and a per controller reference count to protect the controller from being freed while a request operation is in progress. If of_dma_controller_free() is called for a controller who's reference count is not zero it will return -EBUSY and not remove the controller. This is fine up until here, but leaves the question what the caller of of_dma_controller_free() is supposed to do if the controller couldn't be freed. The only viable solution for the caller is to spin on of_dma_controller_free() until it returns success. E.g. do { ret = of_dma_controller_free(dev->of_node) } while (ret != -EBUSY); This is rather ugly and unnecessary and none of the current users of of_dma_controller_free() check it's return value anyway. Instead protect the list by a mutex. The mutex will be held as long as a request operation is in progress. So if of_dma_controller_free() is called while a request operation is in progress it will be put to sleep and only wake up once the request operation has finished. This means that it is no longer possible to register or unregister OF DMA controllers from a context where it's not possible to sleep. But I doubt that we'll ever need this. Also rename of_dma_get_controller back to of_dma_find_controller. Signed-off-by: Lars-Peter Clausen Acked-by: Arnd Bergmann Signed-off-by: Vinod Koul --- include/linux/of_dma.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/of_dma.h b/include/linux/of_dma.h index ce6a8ab3d2bb..364dda734877 100644 --- a/include/linux/of_dma.h +++ b/include/linux/of_dma.h @@ -25,7 +25,6 @@ struct of_dma { struct dma_chan *(*of_dma_xlate) (struct of_phandle_args *, struct of_dma *); void *of_dma_data; - int use_count; }; struct of_dma_filter_info { @@ -38,7 +37,7 @@ extern int of_dma_controller_register(struct device_node *np, struct dma_chan *(*of_dma_xlate) (struct of_phandle_args *, struct of_dma *), void *data); -extern int of_dma_controller_free(struct device_node *np); +extern void of_dma_controller_free(struct device_node *np); extern struct dma_chan *of_dma_request_slave_channel(struct device_node *np, const char *name); extern struct dma_chan *of_dma_simple_xlate(struct of_phandle_args *dma_spec, @@ -52,9 +51,8 @@ static inline int of_dma_controller_register(struct device_node *np, return -ENODEV; } -static inline int of_dma_controller_free(struct device_node *np) +static inline void of_dma_controller_free(struct device_node *np) { - return -ENODEV; } static inline struct dma_chan *of_dma_request_slave_channel(struct device_node *np, -- cgit v1.2.3 From 5522ae0b68421e2645303ff010e27afc5292e0ab Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Wed, 1 May 2013 12:43:04 -0500 Subject: libceph: use slab cache for osd client requests Create a slab cache to manage allocation of ceph_osdc_request structures. This resolves: http://tracker.ceph.com/issues/3926 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 4191cd2c55e5..186db0bf4951 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -224,6 +224,9 @@ struct ceph_osd_client { struct workqueue_struct *notify_wq; }; +extern int ceph_osdc_setup(void); +extern void ceph_osdc_cleanup(void); + extern int ceph_osdc_init(struct ceph_osd_client *osdc, struct ceph_client *client); extern void ceph_osdc_stop(struct ceph_osd_client *osdc); -- cgit v1.2.3 From 159b67d7aefe3902df91075be5d80943c1570aa8 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Tue, 9 Apr 2013 17:13:20 -0600 Subject: NVMe: Device specific stripe size handling We have an nvme device that has a concept of a stripe size. IO requests that do not transfer data crossing a stripe boundary has greater performance compared to IO that does cross it. This patch sets the stripe size for the device if the device and vendor ids match one with this feature and splits IO requests that cross the stripe boundary. Signed-off-by: Keith Busch Signed-off-by: Matthew Wilcox --- include/linux/nvme.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 9b6fba872f47..af29b0e0b092 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -536,6 +536,7 @@ struct nvme_dev { char model[40]; char firmware_rev[8]; u32 max_hw_sectors; + u32 stripe_size; u16 oncs; }; -- cgit v1.2.3 From 631d706e684e6187dbbc3cce3ee301d5b53648a8 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 17 Apr 2013 10:19:05 +0300 Subject: [SCSI] libosd: remover duplicate __bitwise annotation __be32 is already a __bitwise type so we don't need the second __bitwise here. It causes a Sparse error: include/scsi/osd_protocol.h:110:26: error: invalid modifier Signed-off-by: Dan Carpenter Acked-by: Benny Halevy Signed-off-by: James Bottomley --- include/scsi/osd_protocol.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/scsi/osd_protocol.h b/include/scsi/osd_protocol.h index a6026da25f3e..25ac6283b9c7 100644 --- a/include/scsi/osd_protocol.h +++ b/include/scsi/osd_protocol.h @@ -107,7 +107,7 @@ enum osd_attributes_mode { * int exponent: 04; * } */ -typedef __be32 __bitwise osd_cdb_offset; +typedef __be32 osd_cdb_offset; enum { OSD_OFFSET_UNUSED = 0xFFFFFFFF, -- cgit v1.2.3 From f410c680b5344f1cb63ff011c6ae3d4963f45c30 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Tue, 23 Apr 2013 17:23:59 -0600 Subject: NVMe: Meta-data support in NVME_IOCTL_SUBMIT_IO This adds support for namespaces with separate meta-data formats in the submit io ioctl. The meta-data buffer has to be a contiguous, so such a buffer is allocated and the mapped user pages are copied to/from this buffer for write/read commands. Signed-off-by: Keith Busch Signed-off-by: Matthew Wilcox --- include/linux/nvme.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index af29b0e0b092..971ef086ed63 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -552,6 +552,7 @@ struct nvme_ns { int ns_id; int lba_shift; + int ms; u64 mode_select_num_blocks; u32 mode_select_block_len; }; -- cgit v1.2.3 From e30b5dca15dea86aa697f9d58ff646294fe80d3d Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Fri, 3 May 2013 02:15:52 -0400 Subject: ext4: fix fio regression We (Linux Kernel Performance project) found a regression introduced by commit: f7fec032aa ext4: track all extent status in extent status tree The commit causes about 20% performance decrease in fio random write test. Profiler shows that rb_next() uses a lot of CPU time. The call stack is: rb_next ext4_es_find_delayed_extent ext4_map_blocks _ext4_get_block ext4_get_block_write __blockdev_direct_IO ext4_direct_IO generic_file_direct_write __generic_file_aio_write ext4_file_write aio_rw_vect_retry aio_run_iocb do_io_submit sys_io_submit system_call_fastpath io_submit td_io_getevents io_u_queued_complete thread_main main __libc_start_main The cause is that ext4_es_find_delayed_extent() doesn't have an upper bound, it keeps searching until a delayed extent is found. When there are a lots of non-delayed entries in the extent state tree, ext4_es_find_delayed_extent() may uses a lot of CPU time. Reported-by: LKP project Signed-off-by: Yan, Zheng Signed-off-by: Zheng Liu Cc: "Theodore Ts'o" --- include/trace/events/ext4.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index d0e686402df8..8ee15b97cd38 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -2139,7 +2139,7 @@ TRACE_EVENT(ext4_es_remove_extent, __entry->lblk, __entry->len) ); -TRACE_EVENT(ext4_es_find_delayed_extent_enter, +TRACE_EVENT(ext4_es_find_delayed_extent_range_enter, TP_PROTO(struct inode *inode, ext4_lblk_t lblk), TP_ARGS(inode, lblk), @@ -2161,7 +2161,7 @@ TRACE_EVENT(ext4_es_find_delayed_extent_enter, (unsigned long) __entry->ino, __entry->lblk) ); -TRACE_EVENT(ext4_es_find_delayed_extent_exit, +TRACE_EVENT(ext4_es_find_delayed_extent_range_exit, TP_PROTO(struct inode *inode, struct extent_status *es), TP_ARGS(inode, es), -- cgit v1.2.3 From 2acd09f3232825a0e95134703ec59bc327ef9967 Mon Sep 17 00:00:00 2001 From: Andy Grover Date: Thu, 25 Apr 2013 15:04:02 -0700 Subject: target: Remove unused struct members in se_dev_entry Some were incremented, but never used anywhere from what I could tell. Signed-off-by: Andy Grover Signed-off-by: Nicholas Bellinger --- include/target/target_core_base.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index c4af592f7057..136b7b2f7b32 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -572,12 +572,8 @@ struct se_dev_entry { bool def_pr_registered; /* See transport_lunflags_table */ u32 lun_flags; - u32 deve_cmds; u32 mapped_lun; - u32 average_bytes; - u32 last_byte_count; u32 total_cmds; - u32 total_bytes; u64 pr_res_key; u64 creation_time; u32 attach_count; -- cgit v1.2.3 From 77d21f23a1e4db8639e3916547c903a3b3c7a07c Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Fri, 3 May 2013 14:49:41 +0000 Subject: virtio: don't expose u16 in userspace api Programs using virtio headers outside of kernel will no longer build because u16 type does not exist in userspace. All user ABI must use __u16 typedef instead. Bug introduce by: commit 986a4f4d452dec004697f667439d27c3fda9c928 Author: Jason Wang Date: Fri Dec 7 07:04:56 2012 +0000 virtio_net: multiqueue support Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/uapi/linux/virtio_net.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h index a5a8c88753b9..c520203fac2f 100644 --- a/include/uapi/linux/virtio_net.h +++ b/include/uapi/linux/virtio_net.h @@ -191,7 +191,7 @@ struct virtio_net_ctrl_mac { * specified. */ struct virtio_net_ctrl_mq { - u16 virtqueue_pairs; + __u16 virtqueue_pairs; }; #define VIRTIO_NET_CTRL_MQ 4 -- cgit v1.2.3 From a8ca889ed9585894d53fd8919d80cbe8baff09e7 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 5 May 2013 21:31:22 -0400 Subject: mtd_blktrans_ops->release() should return void Both existing instances always return 0 and even if they didn't, the value would be lost on the way out. Just don't bother... Signed-off-by: Al Viro --- include/linux/mtd/blktrans.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mtd/blktrans.h b/include/linux/mtd/blktrans.h index 4eb0a50d0c55..e93837f647de 100644 --- a/include/linux/mtd/blktrans.h +++ b/include/linux/mtd/blktrans.h @@ -74,7 +74,7 @@ struct mtd_blktrans_ops { /* Called with mtd_table_mutex held; no race with add/remove */ int (*open)(struct mtd_blktrans_dev *dev); - int (*release)(struct mtd_blktrans_dev *dev); + void (*release)(struct mtd_blktrans_dev *dev); /* Called on {de,}registration and on subsequent addition/removal of devices, with mtd_table_mutex held. */ -- cgit v1.2.3 From 6286ae97d10ea2b5cd90532163797ab217bfdbdf Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Fri, 3 May 2013 15:43:18 +0000 Subject: slab: Return NULL for oversized allocations The inline path seems to have changed the SLAB behavior for very large kmalloc allocations with commit e3366016 ("slab: Use common kmalloc_index/kmalloc_size functions"). This patch restores the old behavior but also adds diagnostics so that we can figure where in the code these large allocations occur. Reported-and-tested-by: Tetsuo Handa Signed-off-by: Christoph Lameter Link: http://lkml.kernel.org/r/201305040348.CIF81716.OStQOHFJMFLOVF@I-love.SAKURA.ne.jp [ penberg@kernel.org: use WARN_ON_ONCE ] Signed-off-by: Pekka Enberg --- include/linux/slab_def.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index 113ec080313f..cd401580bdd3 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -126,6 +126,9 @@ static __always_inline void *kmalloc(size_t size, gfp_t flags) if (!size) return ZERO_SIZE_PTR; + if (WARN_ON_ONCE(size > KMALLOC_MAX_SIZE)) + return NULL; + i = kmalloc_index(size); #ifdef CONFIG_ZONE_DMA @@ -172,6 +175,9 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) if (!size) return ZERO_SIZE_PTR; + if (WARN_ON_ONCE(size > KMALLOC_MAX_SIZE)) + return NULL; + i = kmalloc_index(size); #ifdef CONFIG_ZONE_DMA -- cgit v1.2.3 From 1deb9d341d475ff84262e927d6c0e36fecb9942e Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Mon, 6 May 2013 13:05:50 +0200 Subject: HID: debug: fix RCU preemption issue Commit 2353f2bea ("HID: protect hid_debug_list") introduced mutex locking around debug_list access to prevent SMP races when debugfs nodes are being operated upon by multiple userspace processess. mutex is not a proper synchronization primitive though, as the hid-debug callbacks are being called from atomic contexts. We also have to be careful about disabling IRQs when taking the lock to prevent deadlock against IRQ handlers. Benjamin reports this has also been reported in RH bugzilla as bug #958935. =============================== [ INFO: suspicious RCU usage. ] 3.9.0+ #94 Not tainted ------------------------------- include/linux/rcupdate.h:476 Illegal context switch in RCU read-side critical section! other info that might help us debug this: rcu_scheduler_active = 1, debug_locks = 0 4 locks held by Xorg/5502: #0: (&evdev->mutex){+.+...}, at: [] evdev_write+0x6d/0x160 #1: (&(&dev->event_lock)->rlock#2){-.-...}, at: [] input_inject_event+0x5b/0x230 #2: (rcu_read_lock){.+.+..}, at: [] input_inject_event+0x42/0x230 #3: (&(&usbhid->lock)->rlock){-.....}, at: [] usb_hidinput_input_event+0x89/0x120 stack backtrace: CPU: 0 PID: 5502 Comm: Xorg Not tainted 3.9.0+ #94 Hardware name: Dell Inc. OptiPlex 390/0M5DCD, BIOS A09 07/24/2012 0000000000000001 ffff8800689c7c38 ffffffff816f249f ffff8800689c7c68 ffffffff810acb1d 0000000000000000 ffffffff81a03ac7 000000000000019d 0000000000000000 ffff8800689c7c90 ffffffff8107cda7 0000000000000000 Call Trace: [] dump_stack+0x19/0x1b [] lockdep_rcu_suspicious+0xfd/0x130 [] __might_sleep+0xc7/0x230 [] mutex_lock_nested+0x40/0x3a0 [] ? vsnprintf+0x354/0x640 [] hid_debug_event+0x34/0x100 [] hid_dump_input+0x67/0xa0 [] hid_set_field+0x50/0x120 [] usb_hidinput_input_event+0x9a/0x120 [] input_handle_event+0x8e/0x530 [] input_inject_event+0x1d0/0x230 [] ? input_inject_event+0x42/0x230 [] evdev_write+0xde/0x160 [] vfs_write+0xc8/0x1f0 [] SyS_write+0x55/0xa0 [] system_call_fastpath+0x16/0x1b BUG: sleeping function called from invalid context at kernel/mutex.c:413 in_atomic(): 1, irqs_disabled(): 1, pid: 5502, name: Xorg INFO: lockdep is turned off. irq event stamp: 1098574 hardirqs last enabled at (1098573): [] _raw_spin_unlock_irqrestore+0x3f/0x70 hardirqs last disabled at (1098574): [] _raw_spin_lock_irqsave+0x25/0xa0 softirqs last enabled at (1098306): [] __do_softirq+0x18f/0x3c0 softirqs last disabled at (1097867): [] irq_exit+0xa5/0xb0 CPU: 0 PID: 5502 Comm: Xorg Not tainted 3.9.0+ #94 Hardware name: Dell Inc. OptiPlex 390/0M5DCD, BIOS A09 07/24/2012 ffffffff81a03ac7 ffff8800689c7c68 ffffffff816f249f ffff8800689c7c90 ffffffff8107ce60 0000000000000000 ffff8800689c7fd8 ffff88006a62c800 ffff8800689c7d10 ffffffff816f7770 ffff8800689c7d00 ffffffff81312ac4 Call Trace: [] dump_stack+0x19/0x1b [] __might_sleep+0x180/0x230 [] mutex_lock_nested+0x40/0x3a0 [] ? vsnprintf+0x354/0x640 [] hid_debug_event+0x34/0x100 [] hid_dump_input+0x67/0xa0 [] hid_set_field+0x50/0x120 [] usb_hidinput_input_event+0x9a/0x120 [] input_handle_event+0x8e/0x530 [] input_inject_event+0x1d0/0x230 [] ? input_inject_event+0x42/0x230 [] evdev_write+0xde/0x160 [] vfs_write+0xc8/0x1f0 [] SyS_write+0x55/0xa0 [] system_call_fastpath+0x16/0x1b Reported-by: majianpeng Reported-by: Benjamin Tissoires Reviewed-by: Dmitry Torokhov Signed-off-by: Jiri Kosina --- include/linux/hid.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/hid.h b/include/linux/hid.h index af1b86d46f6e..0c48991b0402 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -515,7 +515,7 @@ struct hid_device { /* device report descriptor */ struct dentry *debug_rdesc; struct dentry *debug_events; struct list_head debug_list; - struct mutex debug_list_lock; + spinlock_t debug_list_lock; wait_queue_head_t debug_wait; }; -- cgit v1.2.3 From b56141ab34e2c3e2d7960cea12c20c99530c0c76 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Sun, 5 May 2013 04:56:22 +0000 Subject: net: frag, fix race conditions in LRU list maintenance This patch fixes race between inet_frag_lru_move() and inet_frag_lru_add() which was introduced in commit 3ef0eb0db4bf92c6d2510fe5c4dc51852746f206 ("net: frag, move LRU list maintenance outside of rwlock") One cpu already added new fragment queue into hash but not into LRU. Other cpu found it in hash and tries to move it to the end of LRU. This leads to NULL pointer dereference inside of list_move_tail(). Another possible race condition is between inet_frag_lru_move() and inet_frag_lru_del(): move can happens after deletion. This patch initializes LRU list head before adding fragment into hash and inet_frag_lru_move() doesn't touches it if it's empty. I saw this kernel oops two times in a couple of days. [119482.128853] BUG: unable to handle kernel NULL pointer dereference at (null) [119482.132693] IP: [] __list_del_entry+0x29/0xd0 [119482.136456] PGD 2148f6067 PUD 215ab9067 PMD 0 [119482.140221] Oops: 0000 [#1] SMP [119482.144008] Modules linked in: vfat msdos fat 8021q fuse nfsd auth_rpcgss nfs_acl nfs lockd sunrpc ppp_async ppp_generic bridge slhc stp llc w83627ehf hwmon_vid snd_hda_codec_hdmi snd_hda_codec_realtek kvm_amd k10temp kvm snd_hda_intel snd_hda_codec edac_core radeon snd_hwdep ath9k snd_pcm ath9k_common snd_page_alloc ath9k_hw snd_timer snd soundcore drm_kms_helper ath ttm r8169 mii [119482.152692] CPU 3 [119482.152721] Pid: 20, comm: ksoftirqd/3 Not tainted 3.9.0-zurg-00001-g9f95269 #132 To Be Filled By O.E.M. To Be Filled By O.E.M./RS880D [119482.161478] RIP: 0010:[] [] __list_del_entry+0x29/0xd0 [119482.166004] RSP: 0018:ffff880216d5db58 EFLAGS: 00010207 [119482.170568] RAX: 0000000000000000 RBX: ffff88020882b9c0 RCX: dead000000200200 [119482.175189] RDX: 0000000000000000 RSI: 0000000000000880 RDI: ffff88020882ba00 [119482.179860] RBP: ffff880216d5db58 R08: ffffffff8155c7f0 R09: 0000000000000014 [119482.184570] R10: 0000000000000000 R11: 0000000000000000 R12: ffff88020882ba00 [119482.189337] R13: ffffffff81c8d780 R14: ffff880204357f00 R15: 00000000000005a0 [119482.194140] FS: 00007f58124dc700(0000) GS:ffff88021fcc0000(0000) knlGS:0000000000000000 [119482.198928] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b [119482.203711] CR2: 0000000000000000 CR3: 00000002155f0000 CR4: 00000000000007e0 [119482.208533] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [119482.213371] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [119482.218221] Process ksoftirqd/3 (pid: 20, threadinfo ffff880216d5c000, task ffff880216d3a9a0) [119482.223113] Stack: [119482.228004] ffff880216d5dbd8 ffffffff8155dcda 0000000000000000 ffff000200000001 [119482.233038] ffff8802153c1f00 ffff880000289440 ffff880200000014 ffff88007bc72000 [119482.238083] 00000000000079d5 ffff88007bc72f44 ffffffff00000002 ffff880204357f00 [119482.243090] Call Trace: [119482.248009] [] ip_defrag+0x8fa/0xd10 [119482.252921] [] ipv4_conntrack_defrag+0x83/0xe0 [119482.257803] [] nf_iterate+0x8b/0xa0 [119482.262658] [] ? inet_del_offload+0x40/0x40 [119482.267527] [] nf_hook_slow+0x74/0x130 [119482.272412] [] ? inet_del_offload+0x40/0x40 [119482.277302] [] ip_rcv+0x268/0x320 [119482.282147] [] __netif_receive_skb_core+0x612/0x7e0 [119482.286998] [] __netif_receive_skb+0x18/0x60 [119482.291826] [] process_backlog+0xa0/0x160 [119482.296648] [] net_rx_action+0x139/0x220 [119482.301403] [] __do_softirq+0xe7/0x220 [119482.306103] [] run_ksoftirqd+0x28/0x40 [119482.310809] [] smpboot_thread_fn+0xff/0x1a0 [119482.315515] [] ? lg_local_lock_cpu+0x40/0x40 [119482.320219] [] kthread+0xc0/0xd0 [119482.324858] [] ? insert_kthread_work+0x40/0x40 [119482.329460] [] ret_from_fork+0x7c/0xb0 [119482.334057] [] ? insert_kthread_work+0x40/0x40 [119482.338661] Code: 00 00 55 48 8b 17 48 b9 00 01 10 00 00 00 ad de 48 8b 47 08 48 89 e5 48 39 ca 74 29 48 b9 00 02 20 00 00 00 ad de 48 39 c8 74 7a <4c> 8b 00 4c 39 c7 75 53 4c 8b 42 08 4c 39 c7 75 2b 48 89 42 08 [119482.343787] RIP [] __list_del_entry+0x29/0xd0 [119482.348675] RSP [119482.353493] CR2: 0000000000000000 Oops happened on this path: ip_defrag() -> ip_frag_queue() -> inet_frag_lru_move() -> list_move_tail() -> __list_del_entry() Signed-off-by: Konstantin Khlebnikov Cc: Jesper Dangaard Brouer Cc: Florian Westphal Cc: Eric Dumazet Cc: David S. Miller Acked-by: Florian Westphal Signed-off-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- include/net/inet_frag.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index 4182c9be8bb5..bfcbc0017950 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -141,14 +141,15 @@ static inline int sum_frag_mem_limit(struct netns_frags *nf) static inline void inet_frag_lru_move(struct inet_frag_queue *q) { spin_lock(&q->net->lru_lock); - list_move_tail(&q->lru_list, &q->net->lru_list); + if (!list_empty(&q->lru_list)) + list_move_tail(&q->lru_list, &q->net->lru_list); spin_unlock(&q->net->lru_lock); } static inline void inet_frag_lru_del(struct inet_frag_queue *q) { spin_lock(&q->net->lru_lock); - list_del(&q->lru_list); + list_del_init(&q->lru_list); q->net->nqueues--; spin_unlock(&q->net->lru_lock); } -- cgit v1.2.3 From 243198d09f535f5cd74114f1b779c3da25bc70c8 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 5 May 2013 16:05:55 +0000 Subject: rps_dev_flow_table_release(): no need to delay vfree() The same story as with fib_trie patch - vfree() from RCU callbacks is legitimate now. Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index f8898a435dc5..a94a5a0ab122 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -593,7 +593,6 @@ struct rps_dev_flow { struct rps_dev_flow_table { unsigned int mask; struct rcu_head rcu; - struct work_struct free_work; struct rps_dev_flow flows[0]; }; #define RPS_DEV_FLOW_TABLE_SIZE(_num) (sizeof(struct rps_dev_flow_table) + \ -- cgit v1.2.3 From 9b21493c4520970f8f404e0265f48e37f9cffaf5 Mon Sep 17 00:00:00 2001 From: Lin Ming Date: Sat, 23 Mar 2013 11:42:25 +0800 Subject: [SCSI] sd: use REQ_PM in sd's runtime suspend operation With the introduction of REQ_PM, modify sd's runtime suspend operation functions to use that flag so that the operations to put the device into runtime suspended state(i.e. sync cache and stop device) will not affect its runtime PM status. Signed-off-by: Lin Ming Signed-off-by: Aaron Lu Acked-by: Alan Stern Signed-off-by: James Bottomley --- include/scsi/scsi_device.h | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index a7f9cba275e9..cc645876d147 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -394,10 +394,18 @@ extern int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd, int data_direction, void *buffer, unsigned bufflen, unsigned char *sense, int timeout, int retries, int flag, int *resid); -extern int scsi_execute_req(struct scsi_device *sdev, const unsigned char *cmd, - int data_direction, void *buffer, unsigned bufflen, - struct scsi_sense_hdr *, int timeout, int retries, - int *resid); +extern int scsi_execute_req_flags(struct scsi_device *sdev, + const unsigned char *cmd, int data_direction, void *buffer, + unsigned bufflen, struct scsi_sense_hdr *sshdr, int timeout, + int retries, int *resid, int flags); +static inline int scsi_execute_req(struct scsi_device *sdev, + const unsigned char *cmd, int data_direction, void *buffer, + unsigned bufflen, struct scsi_sense_hdr *sshdr, int timeout, + int retries, int *resid) +{ + return scsi_execute_req_flags(sdev, cmd, data_direction, buffer, + bufflen, sshdr, timeout, retries, resid, 0); +} extern void sdev_disable_disk_events(struct scsi_device *sdev); extern void sdev_enable_disk_events(struct scsi_device *sdev); -- cgit v1.2.3 From c2c71324ecb471c932bc1ff59e46ffcf82f274fc Mon Sep 17 00:00:00 2001 From: Stefan Behrens Date: Wed, 10 Apr 2013 17:10:52 +0000 Subject: Btrfs: allow omitting stream header and end-cmd for btrfs send Two new flags are added to allow omitting the stream header and the end command for btrfs send streams. This is used in cases where you send multiple snapshots back-to-back in one stream. This used to be encoded like this (with 2 snapshots in this example): + + + + + + EOF The new format (if the two new flags are used) is this one: + + + Note that the currently existing receivers treat only as an indication that a new is following. This means, you can just skip the sequence without loosing compatibility. As long as an EOF is following, the currently existing receivers handle the new format (if the two new flags are used) exactly as the old one. So what is the benefit of this change? The goal is to be able to use a single stream (one TCP connection) to multiplex a request/response handshake plus Btrfs send streams, all in the same stream. In this case you cannot evaluate an EOF condition as an end of the Btrfs send stream. You need something else, and the is just perfect for this purpose. The summary is: The format change is driven by the need to send several Btrfs send streams over a single TCP connections, with the ability for a repeated request/response handshake in the middle. And this format change does not break any existing tool, it is completely compatible. You could compare the old behaviour of the Btrfs send stream to the one of ftp where you need a seperate request/response channel and newly opened data transfer channels for each file, while the new behaviour is more like http using a single stream for everything. Signed-off-by: Stefan Behrens Signed-off-by: Josef Bacik --- include/uapi/linux/btrfs.h | 20 +++++++++++++++++++- 1 file changed, 19 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index fa3a5f9338fc..5e39e859a848 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -412,7 +412,25 @@ struct btrfs_ioctl_received_subvol_args { * search of clone sources doesn't find an extent. UPDATE_EXTENT * commands will be sent instead of WRITE commands. */ -#define BTRFS_SEND_FLAG_NO_FILE_DATA 0x1 +#define BTRFS_SEND_FLAG_NO_FILE_DATA 0x1 + +/* + * Do not add the leading stream header. Used when multiple snapshots + * are sent back to back. + */ +#define BTRFS_SEND_FLAG_OMIT_STREAM_HEADER 0x2 + +/* + * Omit the command at the end of the stream that indicated the end + * of the stream. This option is used when multiple snapshots are + * sent back to back. + */ +#define BTRFS_SEND_FLAG_OMIT_END_CMD 0x4 + +#define BTRFS_SEND_FLAG_MASK \ + (BTRFS_SEND_FLAG_NO_FILE_DATA | \ + BTRFS_SEND_FLAG_OMIT_STREAM_HEADER | \ + BTRFS_SEND_FLAG_OMIT_END_CMD) struct btrfs_ioctl_send_args { __s64 send_fd; /* in */ -- cgit v1.2.3 From 2f2320360b0c35b86938bfc561124474f0dac6e4 Mon Sep 17 00:00:00 2001 From: Jan Schmidt Date: Thu, 25 Apr 2013 16:04:51 +0000 Subject: Btrfs: rescan for qgroups If qgroup tracking is out of sync, a rescan operation can be started. It iterates the complete extent tree and recalculates all qgroup tracking data. This is an expensive operation and should not be used unless required. A filesystem under rescan can still be umounted. The rescan continues on the next mount. Status information is provided with a separate ioctl while a rescan operation is in progress. Signed-off-by: Jan Schmidt Signed-off-by: Josef Bacik --- include/uapi/linux/btrfs.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index 5e39e859a848..5ef0df545a2a 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -376,12 +376,18 @@ struct btrfs_ioctl_get_dev_stats { #define BTRFS_QUOTA_CTL_ENABLE 1 #define BTRFS_QUOTA_CTL_DISABLE 2 -#define BTRFS_QUOTA_CTL_RESCAN 3 +#define BTRFS_QUOTA_CTL_RESCAN__NOTUSED 3 struct btrfs_ioctl_quota_ctl_args { __u64 cmd; __u64 status; }; +struct btrfs_ioctl_quota_rescan_args { + __u64 flags; + __u64 progress; + __u64 reserved[6]; +}; + struct btrfs_ioctl_qgroup_assign_args { __u64 assign; __u64 src; @@ -520,6 +526,10 @@ struct btrfs_ioctl_send_args { struct btrfs_ioctl_qgroup_create_args) #define BTRFS_IOC_QGROUP_LIMIT _IOR(BTRFS_IOCTL_MAGIC, 43, \ struct btrfs_ioctl_qgroup_limit_args) +#define BTRFS_IOC_QUOTA_RESCAN _IOW(BTRFS_IOCTL_MAGIC, 44, \ + struct btrfs_ioctl_quota_rescan_args) +#define BTRFS_IOC_QUOTA_RESCAN_STATUS _IOR(BTRFS_IOCTL_MAGIC, 45, \ + struct btrfs_ioctl_quota_rescan_args) #define BTRFS_IOC_GET_FSLABEL _IOR(BTRFS_IOCTL_MAGIC, 49, \ char[BTRFS_LABEL_SIZE]) #define BTRFS_IOC_SET_FSLABEL _IOW(BTRFS_IOCTL_MAGIC, 50, \ -- cgit v1.2.3 From 7c1d5fae4a87d3cf3e9ffd68bcdbaf6529013009 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 3 May 2013 14:40:01 -0400 Subject: NFSv4: Convert nfs41_free_stateid to use an asynchronous RPC call The main reason for doing this is will be to allow for an asynchronous RPC mode that we can use for freeing lock stateids as per section 8.2.4 of RFC5661. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 766c5bc9d441..104b62f23ee0 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1176,7 +1176,7 @@ struct nfs41_test_stateid_res { struct nfs41_free_stateid_args { struct nfs4_sequence_args seq_args; - nfs4_stateid *stateid; + nfs4_stateid stateid; }; struct nfs41_free_stateid_res { -- cgit v1.2.3 From db2a144bedd58b3dcf19950c2f476c58c9f39d18 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 5 May 2013 21:52:57 -0400 Subject: block_device_operations->release() should return void The value passed is 0 in all but "it can never happen" cases (and those only in a couple of drivers) *and* it would've been lost on the way out anyway, even if something tried to pass something meaningful. Just don't bother. Signed-off-by: Al Viro --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 78feda9bbae2..e38cfe77f7f0 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1484,7 +1484,7 @@ static inline bool blk_integrity_is_initialized(struct gendisk *g) struct block_device_operations { int (*open) (struct block_device *, fmode_t); - int (*release) (struct gendisk *, fmode_t); + void (*release) (struct gendisk *, fmode_t); int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); int (*direct_access) (struct block_device *, sector_t, -- cgit v1.2.3 From 4385bab128911df14ab25f0b5ae1a48d7b53dd94 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 5 May 2013 22:11:03 -0400 Subject: make blkdev_put() return void same story as with the previous patches - note that return value of blkdev_close() is lost, since there's nowhere the caller (__fput()) could return it to. Signed-off-by: Al Viro --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index b5a24ba83b6f..43db02e9c9fa 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2091,7 +2091,7 @@ extern struct block_device *blkdev_get_by_path(const char *path, fmode_t mode, void *holder); extern struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder); -extern int blkdev_put(struct block_device *bdev, fmode_t mode); +extern void blkdev_put(struct block_device *bdev, fmode_t mode); #ifdef CONFIG_SYSFS extern int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk); extern void bd_unlink_disk_holder(struct block_device *bdev, -- cgit v1.2.3 From 2d864e41710f1d2ba406fb62018ab0487152e6f2 Mon Sep 17 00:00:00 2001 From: Anatol Pomozov Date: Tue, 7 May 2013 15:37:48 -0700 Subject: kref: minor cleanup - make warning smp-safe - result of atomic _unless_zero functions should be checked by caller to avoid use-after-free error - trivial whitespace fix. Link: https://lkml.org/lkml/2013/4/12/391 Tested: compile x86, boot machine and run xfstests Signed-off-by: Anatol Pomozov [ Removed line-break, changed to use WARN_ON_ONCE() - Linus ] Signed-off-by: Linus Torvalds --- include/linux/kref.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/kref.h b/include/linux/kref.h index 4972e6e9ca93..e15828fd71f1 100644 --- a/include/linux/kref.h +++ b/include/linux/kref.h @@ -39,8 +39,11 @@ static inline void kref_init(struct kref *kref) */ static inline void kref_get(struct kref *kref) { - WARN_ON(!atomic_read(&kref->refcount)); - atomic_inc(&kref->refcount); + /* If refcount was 0 before incrementing then we have a race + * condition when this kref is freeing by some other thread right now. + * In this case one should use kref_get_unless_zero() + */ + WARN_ON_ONCE(atomic_inc_return(&kref->refcount) < 2); } /** @@ -100,7 +103,7 @@ static inline int kref_put_mutex(struct kref *kref, struct mutex *lock) { WARN_ON(release == NULL); - if (unlikely(!atomic_add_unless(&kref->refcount, -1, 1))) { + if (unlikely(!atomic_add_unless(&kref->refcount, -1, 1))) { mutex_lock(lock); if (unlikely(!atomic_dec_and_test(&kref->refcount))) { mutex_unlock(lock); -- cgit v1.2.3 From 0f157a5b58d0d2890f0ae20da9fe66aa19a91a4d Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Tue, 7 May 2013 16:18:10 -0700 Subject: include/linux/mm.h: complete the mm_walk definition That nameless-function-arguments thing drives me batty. Fix. Cc: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 1a7f19e7f1a0..e0c8528a41a4 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -951,13 +951,19 @@ void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma, * (see walk_page_range for more details) */ struct mm_walk { - int (*pgd_entry)(pgd_t *, unsigned long, unsigned long, struct mm_walk *); - int (*pud_entry)(pud_t *, unsigned long, unsigned long, struct mm_walk *); - int (*pmd_entry)(pmd_t *, unsigned long, unsigned long, struct mm_walk *); - int (*pte_entry)(pte_t *, unsigned long, unsigned long, struct mm_walk *); - int (*pte_hole)(unsigned long, unsigned long, struct mm_walk *); - int (*hugetlb_entry)(pte_t *, unsigned long, - unsigned long, unsigned long, struct mm_walk *); + int (*pgd_entry)(pgd_t *pgd, unsigned long addr, + unsigned long next, struct mm_walk *walk); + int (*pud_entry)(pud_t *pud, unsigned long addr, + unsigned long next, struct mm_walk *walk); + int (*pmd_entry)(pmd_t *pmd, unsigned long addr, + unsigned long next, struct mm_walk *walk); + int (*pte_entry)(pte_t *pte, unsigned long addr, + unsigned long next, struct mm_walk *walk); + int (*pte_hole)(unsigned long addr, unsigned long next, + struct mm_walk *walk); + int (*hugetlb_entry)(pte_t *pte, unsigned long hmask, + unsigned long addr, unsigned long next, + struct mm_walk *walk); struct mm_struct *mm; void *private; }; -- cgit v1.2.3 From af73e4d9506d3b797509f3c030e7dcd554f7d9c4 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Tue, 7 May 2013 16:18:13 -0700 Subject: hugetlbfs: fix mmap failure in unaligned size request The current kernel returns -EINVAL unless a given mmap length is "almost" hugepage aligned. This is because in sys_mmap_pgoff() the given length is passed to vm_mmap_pgoff() as it is without being aligned with hugepage boundary. This is a regression introduced in commit 40716e29243d ("hugetlbfs: fix alignment of huge page requests"), where alignment code is pushed into hugetlb_file_setup() and the variable len in caller side is not changed. To fix this, this patch partially reverts that commit, and adds alignment code in caller side. And it also introduces hstate_sizelog() in order to get proper hstate to specified hugepage size. Addresses https://bugzilla.kernel.org/show_bug.cgi?id=56881 [akpm@linux-foundation.org: fix warning when CONFIG_HUGETLB_PAGE=n] Signed-off-by: Naoya Horiguchi Signed-off-by: Johannes Weiner Reported-by: Cc: Steven Truelove Cc: Jianguo Wu Cc: Hugh Dickins Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 19 +++++++++++++------ 1 file changed, 13 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 3a62df310f2e..6b4890fa57e7 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -189,8 +189,7 @@ static inline struct hugetlbfs_sb_info *HUGETLBFS_SB(struct super_block *sb) extern const struct file_operations hugetlbfs_file_operations; extern const struct vm_operations_struct hugetlb_vm_ops; -struct file *hugetlb_file_setup(const char *name, unsigned long addr, - size_t size, vm_flags_t acct, +struct file *hugetlb_file_setup(const char *name, size_t size, vm_flags_t acct, struct user_struct **user, int creat_flags, int page_size_log); @@ -209,8 +208,8 @@ static inline int is_file_hugepages(struct file *file) #define is_file_hugepages(file) 0 static inline struct file * -hugetlb_file_setup(const char *name, unsigned long addr, size_t size, - vm_flags_t acctflag, struct user_struct **user, int creat_flags, +hugetlb_file_setup(const char *name, size_t size, vm_flags_t acctflag, + struct user_struct **user, int creat_flags, int page_size_log) { return ERR_PTR(-ENOSYS); @@ -288,6 +287,13 @@ static inline struct hstate *hstate_file(struct file *f) return hstate_inode(file_inode(f)); } +static inline struct hstate *hstate_sizelog(int page_size_log) +{ + if (!page_size_log) + return &default_hstate; + return size_to_hstate(1 << page_size_log); +} + static inline struct hstate *hstate_vma(struct vm_area_struct *vma) { return hstate_file(vma->vm_file); @@ -352,11 +358,12 @@ static inline int hstate_index(struct hstate *h) return h - hstates; } -#else +#else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; #define alloc_huge_page_node(h, nid) NULL #define alloc_bootmem_huge_page(h) NULL #define hstate_file(f) NULL +#define hstate_sizelog(s) NULL #define hstate_vma(v) NULL #define hstate_inode(i) NULL #define huge_page_size(h) PAGE_SIZE @@ -371,6 +378,6 @@ static inline unsigned int pages_per_huge_page(struct hstate *h) } #define hstate_index_to_shift(index) 0 #define hstate_index(h) 0 -#endif +#endif /* CONFIG_HUGETLB_PAGE */ #endif /* _LINUX_HUGETLB_H */ -- cgit v1.2.3 From 22ea9c070350b824d6c3b65bce06ee7c6cc87b99 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Tue, 7 May 2013 16:18:17 -0700 Subject: remove unused random32() and srandom32() After finishing a naming transition, remove unused backward compatibility wrapper macros Signed-off-by: Akinobu Mita Cc: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/random.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include') diff --git a/include/linux/random.h b/include/linux/random.h index 347ce553a306..3b9377d6b7a5 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -29,13 +29,6 @@ u32 prandom_u32(void); void prandom_bytes(void *buf, int nbytes); void prandom_seed(u32 seed); -/* - * These macros are preserved for backward compatibility and should be - * removed as soon as a transition is finished. - */ -#define random32() prandom_u32() -#define srandom32(seed) prandom_seed(seed) - u32 prandom_u32_state(struct rnd_state *); void prandom_bytes_state(struct rnd_state *state, void *buf, int nbytes); -- cgit v1.2.3 From 4b49bb8ad6d6e6e564017e2fad2357c3024683eb Mon Sep 17 00:00:00 2001 From: Zach Brown Date: Tue, 7 May 2013 16:18:21 -0700 Subject: aio: remove dead code from aio.h Signed-off-by: Zach Brown Signed-off-by: Kent Overstreet Cc: Felipe Balbi Cc: Greg Kroah-Hartman Cc: Mark Fasheh Cc: Joel Becker Cc: Rusty Russell Cc: Jens Axboe Cc: Asai Thambi S P Cc: Selvan Mani Cc: Sam Bradshaw Acked-by: Jeff Moyer Cc: Al Viro Cc: Benjamin LaHaise Reviewed-by: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/aio.h | 24 ------------------------ 1 file changed, 24 deletions(-) (limited to 'include') diff --git a/include/linux/aio.h b/include/linux/aio.h index 31ff6dba4872..b46a09f73f1d 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -9,44 +9,22 @@ #include -#define AIO_MAXSEGS 4 -#define AIO_KIOGRP_NR_ATOMIC 8 - struct kioctx; -/* Notes on cancelling a kiocb: - * If a kiocb is cancelled, aio_complete may return 0 to indicate - * that cancel has not yet disposed of the kiocb. All cancel - * operations *must* call aio_put_req to dispose of the kiocb - * to guard against races with the completion code. - */ -#define KIOCB_C_CANCELLED 0x01 -#define KIOCB_C_COMPLETE 0x02 - #define KIOCB_SYNC_KEY (~0U) /* ki_flags bits */ -/* - * This may be used for cancel/retry serialization in the future, but - * for now it's unused and we probably don't want modules to even - * think they can use it. - */ -/* #define KIF_LOCKED 0 */ #define KIF_KICKED 1 #define KIF_CANCELLED 2 -#define kiocbTryLock(iocb) test_and_set_bit(KIF_LOCKED, &(iocb)->ki_flags) #define kiocbTryKick(iocb) test_and_set_bit(KIF_KICKED, &(iocb)->ki_flags) -#define kiocbSetLocked(iocb) set_bit(KIF_LOCKED, &(iocb)->ki_flags) #define kiocbSetKicked(iocb) set_bit(KIF_KICKED, &(iocb)->ki_flags) #define kiocbSetCancelled(iocb) set_bit(KIF_CANCELLED, &(iocb)->ki_flags) -#define kiocbClearLocked(iocb) clear_bit(KIF_LOCKED, &(iocb)->ki_flags) #define kiocbClearKicked(iocb) clear_bit(KIF_KICKED, &(iocb)->ki_flags) #define kiocbClearCancelled(iocb) clear_bit(KIF_CANCELLED, &(iocb)->ki_flags) -#define kiocbIsLocked(iocb) test_bit(KIF_LOCKED, &(iocb)->ki_flags) #define kiocbIsKicked(iocb) test_bit(KIF_KICKED, &(iocb)->ki_flags) #define kiocbIsCancelled(iocb) test_bit(KIF_CANCELLED, &(iocb)->ki_flags) @@ -207,8 +185,6 @@ struct kioctx { }; /* prototypes */ -extern unsigned aio_max_size; - #ifdef CONFIG_AIO extern ssize_t wait_on_sync_kiocb(struct kiocb *iocb); extern int aio_put_req(struct kiocb *iocb); -- cgit v1.2.3 From 41003a7bcfed1255032e1e7c7b487e505b22e298 Mon Sep 17 00:00:00 2001 From: Zach Brown Date: Tue, 7 May 2013 16:18:25 -0700 Subject: aio: remove retry-based AIO This removes the retry-based AIO infrastructure now that nothing in tree is using it. We want to remove retry-based AIO because it is fundemantally unsafe. It retries IO submission from a kernel thread that has only assumed the mm of the submitting task. All other task_struct references in the IO submission path will see the kernel thread, not the submitting task. This design flaw means that nothing of any meaningful complexity can use retry-based AIO. This removes all the code and data associated with the retry machinery. The most significant benefit of this is the removal of the locking around the unused run list in the submission path. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Kent Overstreet Signed-off-by: Zach Brown Cc: Zach Brown Cc: Felipe Balbi Cc: Greg Kroah-Hartman Cc: Mark Fasheh Cc: Joel Becker Cc: Rusty Russell Cc: Jens Axboe Cc: Asai Thambi S P Cc: Selvan Mani Cc: Sam Bradshaw Acked-by: Jeff Moyer Cc: Al Viro Cc: Benjamin LaHaise Reviewed-by: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/aio.h | 22 ---------------------- include/linux/errno.h | 1 - 2 files changed, 23 deletions(-) (limited to 'include') diff --git a/include/linux/aio.h b/include/linux/aio.h index b46a09f73f1d..019204e46c11 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -14,18 +14,12 @@ struct kioctx; #define KIOCB_SYNC_KEY (~0U) /* ki_flags bits */ -#define KIF_KICKED 1 #define KIF_CANCELLED 2 -#define kiocbTryKick(iocb) test_and_set_bit(KIF_KICKED, &(iocb)->ki_flags) - -#define kiocbSetKicked(iocb) set_bit(KIF_KICKED, &(iocb)->ki_flags) #define kiocbSetCancelled(iocb) set_bit(KIF_CANCELLED, &(iocb)->ki_flags) -#define kiocbClearKicked(iocb) clear_bit(KIF_KICKED, &(iocb)->ki_flags) #define kiocbClearCancelled(iocb) clear_bit(KIF_CANCELLED, &(iocb)->ki_flags) -#define kiocbIsKicked(iocb) test_bit(KIF_KICKED, &(iocb)->ki_flags) #define kiocbIsCancelled(iocb) test_bit(KIF_CANCELLED, &(iocb)->ki_flags) /* is there a better place to document function pointer methods? */ @@ -52,18 +46,8 @@ struct kioctx; * not ask the method again -- ki_retry must ensure forward progress. * aio_complete() must be called once and only once in the future, multiple * calls may result in undefined behaviour. - * - * If ki_retry returns -EIOCBRETRY it has made a promise that kick_iocb() - * will be called on the kiocb pointer in the future. This may happen - * through generic helpers that associate kiocb->ki_wait with a wait - * queue head that ki_retry uses via current->io_wait. It can also happen - * with custom tracking and manual calls to kick_iocb(), though that is - * discouraged. In either case, kick_iocb() must be called once and only - * once. ki_retry must ensure forward progress, the AIO core will wait - * indefinitely for kick_iocb() to be called. */ struct kiocb { - struct list_head ki_run_list; unsigned long ki_flags; int ki_users; unsigned ki_key; /* id of this request */ @@ -160,7 +144,6 @@ static inline unsigned aio_ring_avail(struct aio_ring_info *info, struct kioctx { atomic_t users; int dead; - struct mm_struct *mm; /* This needs improving */ unsigned long user_id; @@ -172,15 +155,12 @@ struct kioctx { int reqs_active; struct list_head active_reqs; /* used for cancellation */ - struct list_head run_list; /* used for kicked reqs */ /* sys_io_setup currently limits this to an unsigned int */ unsigned max_reqs; struct aio_ring_info ring_info; - struct delayed_work wq; - struct rcu_head rcu_head; }; @@ -188,7 +168,6 @@ struct kioctx { #ifdef CONFIG_AIO extern ssize_t wait_on_sync_kiocb(struct kiocb *iocb); extern int aio_put_req(struct kiocb *iocb); -extern void kick_iocb(struct kiocb *iocb); extern int aio_complete(struct kiocb *iocb, long res, long res2); struct mm_struct; extern void exit_aio(struct mm_struct *mm); @@ -197,7 +176,6 @@ extern long do_io_submit(aio_context_t ctx_id, long nr, #else static inline ssize_t wait_on_sync_kiocb(struct kiocb *iocb) { return 0; } static inline int aio_put_req(struct kiocb *iocb) { return 0; } -static inline void kick_iocb(struct kiocb *iocb) { } static inline int aio_complete(struct kiocb *iocb, long res, long res2) { return 0; } struct mm_struct; static inline void exit_aio(struct mm_struct *mm) { } diff --git a/include/linux/errno.h b/include/linux/errno.h index f6bf082d4d4f..89627b9187f9 100644 --- a/include/linux/errno.h +++ b/include/linux/errno.h @@ -28,6 +28,5 @@ #define EBADTYPE 527 /* Type not supported by server */ #define EJUKEBOX 528 /* Request initiated, but will not complete before timeout */ #define EIOCBQUEUED 529 /* iocb queued, will get completion event */ -#define EIOCBRETRY 530 /* iocb queued, will trigger a retry */ #endif -- cgit v1.2.3 From 2d68449e86168744513ca4f13477f081ce167130 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Tue, 7 May 2013 16:18:29 -0700 Subject: aio: kill return value of aio_complete() Nothing used the return value, and it probably wasn't possible to use it safely for the locked versions (aio_complete(), aio_put_req()). Just kill it. Signed-off-by: Kent Overstreet Acked-by: Zach Brown Cc: Felipe Balbi Cc: Greg Kroah-Hartman Cc: Mark Fasheh Cc: Joel Becker Cc: Rusty Russell Cc: Jens Axboe Cc: Asai Thambi S P Cc: Selvan Mani Cc: Sam Bradshaw Acked-by: Jeff Moyer Cc: Al Viro Cc: Benjamin LaHaise Reviewed-by: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/aio.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/aio.h b/include/linux/aio.h index 019204e46c11..615d55a5d0be 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -167,16 +167,16 @@ struct kioctx { /* prototypes */ #ifdef CONFIG_AIO extern ssize_t wait_on_sync_kiocb(struct kiocb *iocb); -extern int aio_put_req(struct kiocb *iocb); -extern int aio_complete(struct kiocb *iocb, long res, long res2); +extern void aio_put_req(struct kiocb *iocb); +extern void aio_complete(struct kiocb *iocb, long res, long res2); struct mm_struct; extern void exit_aio(struct mm_struct *mm); extern long do_io_submit(aio_context_t ctx_id, long nr, struct iocb __user *__user *iocbpp, bool compat); #else static inline ssize_t wait_on_sync_kiocb(struct kiocb *iocb) { return 0; } -static inline int aio_put_req(struct kiocb *iocb) { return 0; } -static inline int aio_complete(struct kiocb *iocb, long res, long res2) { return 0; } +static inline void aio_put_req(struct kiocb *iocb) { } +static inline void aio_complete(struct kiocb *iocb, long res, long res2) { } struct mm_struct; static inline void exit_aio(struct mm_struct *mm) { } static inline long do_io_submit(aio_context_t ctx_id, long nr, -- cgit v1.2.3 From 4e179bca6718693148c7445c236bc3e0e0013ffd Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Tue, 7 May 2013 16:18:33 -0700 Subject: aio: move private stuff out of aio.h Signed-off-by: Kent Overstreet Cc: Zach Brown Cc: Felipe Balbi Cc: Greg Kroah-Hartman Cc: Mark Fasheh Cc: Joel Becker Cc: Rusty Russell Cc: Jens Axboe Cc: Asai Thambi S P Cc: Selvan Mani Cc: Sam Bradshaw Acked-by: Jeff Moyer Cc: Al Viro Cc: Benjamin LaHaise Cc: Theodore Ts'o Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/aio.h | 61 ----------------------------------------------------- 1 file changed, 61 deletions(-) (limited to 'include') diff --git a/include/linux/aio.h b/include/linux/aio.h index 615d55a5d0be..7b1eb234e0ab 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -103,67 +103,6 @@ static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) }; } -#define AIO_RING_MAGIC 0xa10a10a1 -#define AIO_RING_COMPAT_FEATURES 1 -#define AIO_RING_INCOMPAT_FEATURES 0 -struct aio_ring { - unsigned id; /* kernel internal index number */ - unsigned nr; /* number of io_events */ - unsigned head; - unsigned tail; - - unsigned magic; - unsigned compat_features; - unsigned incompat_features; - unsigned header_length; /* size of aio_ring */ - - - struct io_event io_events[0]; -}; /* 128 bytes + ring size */ - -#define AIO_RING_PAGES 8 -struct aio_ring_info { - unsigned long mmap_base; - unsigned long mmap_size; - - struct page **ring_pages; - spinlock_t ring_lock; - long nr_pages; - - unsigned nr, tail; - - struct page *internal_pages[AIO_RING_PAGES]; -}; - -static inline unsigned aio_ring_avail(struct aio_ring_info *info, - struct aio_ring *ring) -{ - return (ring->head + info->nr - 1 - ring->tail) % info->nr; -} - -struct kioctx { - atomic_t users; - int dead; - - /* This needs improving */ - unsigned long user_id; - struct hlist_node list; - - wait_queue_head_t wait; - - spinlock_t ctx_lock; - - int reqs_active; - struct list_head active_reqs; /* used for cancellation */ - - /* sys_io_setup currently limits this to an unsigned int */ - unsigned max_reqs; - - struct aio_ring_info ring_info; - - struct rcu_head rcu_head; -}; - /* prototypes */ #ifdef CONFIG_AIO extern ssize_t wait_on_sync_kiocb(struct kiocb *iocb); -- cgit v1.2.3 From 11599ebac4a249ab3c8b9a535c21db7a51458c0a Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Tue, 7 May 2013 16:18:39 -0700 Subject: aio: make aio_put_req() lockless Freeing a kiocb needed to touch the kioctx for three things: * Pull it off the reqs_active list * Decrementing reqs_active * Issuing a wakeup, if the kioctx was in the process of being freed. This patch moves these to aio_complete(), for a couple reasons: * aio_complete() already has to issue the wakeup, so if we drop the kioctx refcount before aio_complete does its wakeup we don't have to do it twice. * aio_complete currently has to take the kioctx lock, so it makes sense for it to pull the kiocb off the reqs_active list too. * A later patch is going to change reqs_active to include unreaped completions - this will mean allocating a kiocb doesn't have to look at the ringbuffer. So taking the decrement of reqs_active out of kiocb_free() is useful prep work for that patch. This doesn't really affect cancellation, since existing (usb) code that implements a cancel function still calls aio_complete() - we just have to make sure that aio_complete does the necessary teardown for cancelled kiocbs. It does affect code paths where we free kiocbs that were never submitted; they need to decrement reqs_active and pull the kiocb off the reqs_active list. This occurs in two places: kiocb_batch_free(), which is going away in a later patch, and the error path in io_submit_one. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Kent Overstreet Cc: Zach Brown Cc: Felipe Balbi Cc: Greg Kroah-Hartman Cc: Mark Fasheh Cc: Joel Becker Cc: Rusty Russell Cc: Jens Axboe Cc: Asai Thambi S P Cc: Selvan Mani Cc: Sam Bradshaw Acked-by: Jeff Moyer Cc: Al Viro Cc: Benjamin LaHaise Reviewed-by: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/aio.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/aio.h b/include/linux/aio.h index 7b1eb234e0ab..1e728f0086f8 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -49,7 +49,7 @@ struct kioctx; */ struct kiocb { unsigned long ki_flags; - int ki_users; + atomic_t ki_users; unsigned ki_key; /* id of this request */ struct file *ki_filp; @@ -96,7 +96,7 @@ static inline bool is_sync_kiocb(struct kiocb *kiocb) static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) { *kiocb = (struct kiocb) { - .ki_users = 1, + .ki_users = ATOMIC_INIT(1), .ki_key = KIOCB_SYNC_KEY, .ki_filp = filp, .ki_obj.tsk = current, -- cgit v1.2.3 From 774a08b3548f3f4f36c1a4f2a29a1b3710a2c939 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Tue, 7 May 2013 16:18:43 -0700 Subject: wait: add wait_event_hrtimeout() Analagous to wait_event_timeout() and friends, this adds wait_event_hrtimeout() and wait_event_interruptible_hrtimeout(). Note that unlike the versions that use regular timers, these don't return the amount of time remaining when they return - instead, they return 0 or -ETIME if they timed out. because I was uncomfortable with the semantics of doing it the other way (that I could get it right, anyways). If the timer expires, there's no real guarantee that expire_time - current_time would be <= 0 - due to timer slack certainly, and I'm not sure I want to know the implications of the different clock bases in hrtimers. If the timer does expire and the code calculates that the time remaining is nonnegative, that could be even worse if the calling code then reuses that timeout. Probably safer to just return 0 then, but I could imagine weird bugs or at least unintended behaviour arising from that too. I came to the conclusion that if other users end up actually needing the amount of time remaining, the sanest thing to do would be to create a version that uses absolute timeouts instead of relative. [akpm@linux-foundation.org: fix description of `timeout' arg] Signed-off-by: Kent Overstreet Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Zach Brown Cc: Felipe Balbi Cc: Greg Kroah-Hartman Cc: Mark Fasheh Cc: Joel Becker Cc: Rusty Russell Cc: Jens Axboe Cc: Asai Thambi S P Cc: Selvan Mani Cc: Sam Bradshaw Cc: Jeff Moyer Cc: Al Viro Cc: Benjamin LaHaise Reviewed-by: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/wait.h | 86 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 86 insertions(+) (limited to 'include') diff --git a/include/linux/wait.h b/include/linux/wait.h index 7cb64d4b499d..ac38be2692d8 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -330,6 +330,92 @@ do { \ __ret; \ }) +#define __wait_event_hrtimeout(wq, condition, timeout, state) \ +({ \ + int __ret = 0; \ + DEFINE_WAIT(__wait); \ + struct hrtimer_sleeper __t; \ + \ + hrtimer_init_on_stack(&__t.timer, CLOCK_MONOTONIC, \ + HRTIMER_MODE_REL); \ + hrtimer_init_sleeper(&__t, current); \ + if ((timeout).tv64 != KTIME_MAX) \ + hrtimer_start_range_ns(&__t.timer, timeout, \ + current->timer_slack_ns, \ + HRTIMER_MODE_REL); \ + \ + for (;;) { \ + prepare_to_wait(&wq, &__wait, state); \ + if (condition) \ + break; \ + if (state == TASK_INTERRUPTIBLE && \ + signal_pending(current)) { \ + __ret = -ERESTARTSYS; \ + break; \ + } \ + if (!__t.task) { \ + __ret = -ETIME; \ + break; \ + } \ + schedule(); \ + } \ + \ + hrtimer_cancel(&__t.timer); \ + destroy_hrtimer_on_stack(&__t.timer); \ + finish_wait(&wq, &__wait); \ + __ret; \ +}) + +/** + * wait_event_hrtimeout - sleep until a condition gets true or a timeout elapses + * @wq: the waitqueue to wait on + * @condition: a C expression for the event to wait for + * @timeout: timeout, as a ktime_t + * + * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the + * @condition evaluates to true or a signal is received. + * The @condition is checked each time the waitqueue @wq is woken up. + * + * wake_up() has to be called after changing any variable that could + * change the result of the wait condition. + * + * The function returns 0 if @condition became true, or -ETIME if the timeout + * elapsed. + */ +#define wait_event_hrtimeout(wq, condition, timeout) \ +({ \ + int __ret = 0; \ + if (!(condition)) \ + __ret = __wait_event_hrtimeout(wq, condition, timeout, \ + TASK_UNINTERRUPTIBLE); \ + __ret; \ +}) + +/** + * wait_event_interruptible_hrtimeout - sleep until a condition gets true or a timeout elapses + * @wq: the waitqueue to wait on + * @condition: a C expression for the event to wait for + * @timeout: timeout, as a ktime_t + * + * The process is put to sleep (TASK_INTERRUPTIBLE) until the + * @condition evaluates to true or a signal is received. + * The @condition is checked each time the waitqueue @wq is woken up. + * + * wake_up() has to be called after changing any variable that could + * change the result of the wait condition. + * + * The function returns 0 if @condition became true, -ERESTARTSYS if it was + * interrupted by a signal, or -ETIME if the timeout elapsed. + */ +#define wait_event_interruptible_hrtimeout(wq, condition, timeout) \ +({ \ + long __ret = 0; \ + if (!(condition)) \ + __ret = __wait_event_hrtimeout(wq, condition, timeout, \ + TASK_INTERRUPTIBLE); \ + __ret; \ +}) + #define __wait_event_interruptible_exclusive(wq, condition, ret) \ do { \ DEFINE_WAIT(__wait); \ -- cgit v1.2.3 From 0460fef2a9215680f7f85415b57731b7e0fdf673 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Tue, 7 May 2013 16:18:49 -0700 Subject: aio: use cancellation list lazily Cancelling kiocbs requires adding them to a per kioctx linked list, which is one of the few things we need to take the kioctx lock for in the fast path. But most kiocbs can't be cancelled - so if we just do this lazily, we can avoid quite a bit of locking overhead. While we're at it, instead of using a flag bit switch to using ki_cancel itself to indicate that a kiocb has been cancelled/completed. This lets us get rid of ki_flags entirely. [akpm@linux-foundation.org: remove buggy BUG()] Signed-off-by: Kent Overstreet Cc: Zach Brown Cc: Felipe Balbi Cc: Greg Kroah-Hartman Cc: Mark Fasheh Cc: Joel Becker Cc: Rusty Russell Cc: Jens Axboe Cc: Asai Thambi S P Cc: Selvan Mani Cc: Sam Bradshaw Cc: Jeff Moyer Cc: Al Viro Cc: Benjamin LaHaise Reviewed-by: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/aio.h | 27 ++++++++++++++++++--------- 1 file changed, 18 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/aio.h b/include/linux/aio.h index 1e728f0086f8..d2a00038ec77 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -10,17 +10,24 @@ #include struct kioctx; +struct kiocb; #define KIOCB_SYNC_KEY (~0U) -/* ki_flags bits */ -#define KIF_CANCELLED 2 - -#define kiocbSetCancelled(iocb) set_bit(KIF_CANCELLED, &(iocb)->ki_flags) - -#define kiocbClearCancelled(iocb) clear_bit(KIF_CANCELLED, &(iocb)->ki_flags) +/* + * We use ki_cancel == KIOCB_CANCELLED to indicate that a kiocb has been either + * cancelled or completed (this makes a certain amount of sense because + * successful cancellation - io_cancel() - does deliver the completion to + * userspace). + * + * And since most things don't implement kiocb cancellation and we'd really like + * kiocb completion to be lockless when possible, we use ki_cancel to + * synchronize cancellation and completion - we only set it to KIOCB_CANCELLED + * with xchg() or cmpxchg(), see batch_complete_aio() and kiocb_cancel(). + */ +#define KIOCB_CANCELLED ((void *) (~0ULL)) -#define kiocbIsCancelled(iocb) test_bit(KIF_CANCELLED, &(iocb)->ki_flags) +typedef int (kiocb_cancel_fn)(struct kiocb *, struct io_event *); /* is there a better place to document function pointer methods? */ /** @@ -48,13 +55,12 @@ struct kioctx; * calls may result in undefined behaviour. */ struct kiocb { - unsigned long ki_flags; atomic_t ki_users; unsigned ki_key; /* id of this request */ struct file *ki_filp; struct kioctx *ki_ctx; /* may be NULL for sync ops */ - int (*ki_cancel)(struct kiocb *, struct io_event *); + kiocb_cancel_fn *ki_cancel; ssize_t (*ki_retry)(struct kiocb *); void (*ki_dtor)(struct kiocb *); @@ -112,6 +118,7 @@ struct mm_struct; extern void exit_aio(struct mm_struct *mm); extern long do_io_submit(aio_context_t ctx_id, long nr, struct iocb __user *__user *iocbpp, bool compat); +void kiocb_set_cancel_fn(struct kiocb *req, kiocb_cancel_fn *cancel); #else static inline ssize_t wait_on_sync_kiocb(struct kiocb *iocb) { return 0; } static inline void aio_put_req(struct kiocb *iocb) { } @@ -121,6 +128,8 @@ static inline void exit_aio(struct mm_struct *mm) { } static inline long do_io_submit(aio_context_t ctx_id, long nr, struct iocb __user * __user *iocbpp, bool compat) { return 0; } +static inline void kiocb_set_cancel_fn(struct kiocb *req, + kiocb_cancel_fn *cancel) { } #endif /* CONFIG_AIO */ static inline struct kiocb *list_kiocb(struct list_head *h) -- cgit v1.2.3 From a1c8eae75ea3b0168fca93788db1b5aef2424921 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Tue, 7 May 2013 16:18:53 -0700 Subject: aio: kill batch allocation Previously, allocating a kiocb required touching quite a few global (well, per kioctx) cachelines... so batching up allocation to amortize those was worthwhile. But we've gotten rid of some of those, and in another couple of patches kiocb allocation won't require writing to any shared cachelines, so that means we can just rip this code out. Signed-off-by: Kent Overstreet Cc: Zach Brown Cc: Felipe Balbi Cc: Greg Kroah-Hartman Cc: Mark Fasheh Cc: Joel Becker Cc: Rusty Russell Cc: Jens Axboe Cc: Asai Thambi S P Cc: Selvan Mani Cc: Sam Bradshaw Cc: Jeff Moyer Cc: Al Viro Cc: Benjamin LaHaise Reviewed-by: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/aio.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/aio.h b/include/linux/aio.h index d2a00038ec77..f0a8481af99b 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -85,7 +85,6 @@ struct kiocb { struct list_head ki_list; /* the aio core uses this * for cancellation */ - struct list_head ki_batch; /* batch allocation */ /* * If the aio_resfd field of the userspace iocb is not zero, -- cgit v1.2.3 From 780a7654cee8d61819512385e778e4827db4bfbc Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 9 Apr 2013 02:22:10 -0700 Subject: audit: Make testing for a valid loginuid explicit. audit rule additions containing "-F auid!=4294967295" were failing with EINVAL because of a regression caused by e1760bd. Apparently some userland audit rule sets want to know if loginuid uid has been set and are using a test for auid != 4294967295 to determine that. In practice that is a horrible way to ask if a value has been set, because it relies on subtle implementation details and will break every time the uid implementation in the kernel changes. So add a clean way to test if the audit loginuid has been set, and silently convert the old idiom to the cleaner and more comprehensible new idiom. Cc: # 3.7 Reported-By: Richard Guy Briggs Signed-off-by: "Eric W. Biederman" Tested-by: Richard Guy Briggs Signed-off-by: Eric Paris --- include/linux/audit.h | 5 +++++ include/uapi/linux/audit.h | 1 + 2 files changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/audit.h b/include/linux/audit.h index 469d11755e46..b20b03852f21 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -391,6 +391,11 @@ static inline void audit_ptrace(struct task_struct *t) #define audit_signals 0 #endif /* CONFIG_AUDITSYSCALL */ +static inline bool audit_loginuid_set(struct task_struct *tsk) +{ + return uid_valid(audit_get_loginuid(tsk)); +} + #ifdef CONFIG_AUDIT /* These are defined in audit.c */ /* Public API */ diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h index c058c24b97ac..75cef3fd97ad 100644 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@ -246,6 +246,7 @@ #define AUDIT_OBJ_TYPE 21 #define AUDIT_OBJ_LEV_LOW 22 #define AUDIT_OBJ_LEV_HIGH 23 +#define AUDIT_LOGINUID_SET 24 /* These are ONLY useful when checking * at syscall exit time (AUDIT_AT_EXIT). */ -- cgit v1.2.3 From 8a6608907cf165b3ae658c9de2efe6af4be68bff Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Tue, 7 May 2013 16:19:10 -0700 Subject: aio: kill ki_key ki_key wasn't actually used for anything previously - it was always 0. Drop it to trim struct kiocb a bit. Signed-off-by: Kent Overstreet Cc: Zach Brown Cc: Felipe Balbi Cc: Greg Kroah-Hartman Cc: Mark Fasheh Cc: Joel Becker Cc: Rusty Russell Cc: Jens Axboe Cc: Asai Thambi S P Cc: Selvan Mani Cc: Sam Bradshaw Cc: Jeff Moyer Cc: Al Viro Cc: Benjamin LaHaise Reviewed-by: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/aio.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/aio.h b/include/linux/aio.h index f0a8481af99b..7308836dd045 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -12,7 +12,7 @@ struct kioctx; struct kiocb; -#define KIOCB_SYNC_KEY (~0U) +#define KIOCB_KEY 0 /* * We use ki_cancel == KIOCB_CANCELLED to indicate that a kiocb has been either @@ -56,10 +56,9 @@ typedef int (kiocb_cancel_fn)(struct kiocb *, struct io_event *); */ struct kiocb { atomic_t ki_users; - unsigned ki_key; /* id of this request */ struct file *ki_filp; - struct kioctx *ki_ctx; /* may be NULL for sync ops */ + struct kioctx *ki_ctx; /* NULL for sync ops */ kiocb_cancel_fn *ki_cancel; ssize_t (*ki_retry)(struct kiocb *); void (*ki_dtor)(struct kiocb *); @@ -95,14 +94,14 @@ struct kiocb { static inline bool is_sync_kiocb(struct kiocb *kiocb) { - return kiocb->ki_key == KIOCB_SYNC_KEY; + return kiocb->ki_ctx == NULL; } static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) { *kiocb = (struct kiocb) { .ki_users = ATOMIC_INIT(1), - .ki_key = KIOCB_SYNC_KEY, + .ki_ctx = NULL, .ki_filp = filp, .ki_obj.tsk = current, }; -- cgit v1.2.3 From 41ef4eb8eef8d06bc1399e7b00c940d771554711 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Tue, 7 May 2013 16:19:11 -0700 Subject: aio: kill ki_retry Thanks to Zach Brown's work to rip out the retry infrastructure, we don't need this anymore - ki_retry was only called right after the kiocb was initialized. This also refactors and trims some duplicated code, as well as cleaning up the refcounting/error handling a bit. [akpm@linux-foundation.org: use fmode_t in aio_run_iocb()] [akpm@linux-foundation.org: fix file_start_write/file_end_write tests] [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Kent Overstreet Cc: Zach Brown Cc: Felipe Balbi Cc: Greg Kroah-Hartman Cc: Mark Fasheh Cc: Joel Becker Cc: Rusty Russell Cc: Jens Axboe Cc: Asai Thambi S P Cc: Selvan Mani Cc: Sam Bradshaw Cc: Jeff Moyer Cc: Al Viro Cc: Benjamin LaHaise Reviewed-by: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/aio.h | 26 -------------------------- 1 file changed, 26 deletions(-) (limited to 'include') diff --git a/include/linux/aio.h b/include/linux/aio.h index 7308836dd045..1bdf965339f9 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -29,38 +29,12 @@ struct kiocb; typedef int (kiocb_cancel_fn)(struct kiocb *, struct io_event *); -/* is there a better place to document function pointer methods? */ -/** - * ki_retry - iocb forward progress callback - * @kiocb: The kiocb struct to advance by performing an operation. - * - * This callback is called when the AIO core wants a given AIO operation - * to make forward progress. The kiocb argument describes the operation - * that is to be performed. As the operation proceeds, perhaps partially, - * ki_retry is expected to update the kiocb with progress made. Typically - * ki_retry is set in the AIO core and it itself calls file_operations - * helpers. - * - * ki_retry's return value determines when the AIO operation is completed - * and an event is generated in the AIO event ring. Except the special - * return values described below, the value that is returned from ki_retry - * is transferred directly into the completion ring as the operation's - * resulting status. Once this has happened ki_retry *MUST NOT* reference - * the kiocb pointer again. - * - * If ki_retry returns -EIOCBQUEUED it has made a promise that aio_complete() - * will be called on the kiocb pointer in the future. The AIO core will - * not ask the method again -- ki_retry must ensure forward progress. - * aio_complete() must be called once and only once in the future, multiple - * calls may result in undefined behaviour. - */ struct kiocb { atomic_t ki_users; struct file *ki_filp; struct kioctx *ki_ctx; /* NULL for sync ops */ kiocb_cancel_fn *ki_cancel; - ssize_t (*ki_retry)(struct kiocb *); void (*ki_dtor)(struct kiocb *); union { -- cgit v1.2.3 From a27bb332c04cec8c4afd7912df0dc7890db27560 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Tue, 7 May 2013 16:19:08 -0700 Subject: aio: don't include aio.h in sched.h Faster kernel compiles by way of fewer unnecessary includes. [akpm@linux-foundation.org: fix fallout] [akpm@linux-foundation.org: fix build] Signed-off-by: Kent Overstreet Cc: Zach Brown Cc: Felipe Balbi Cc: Greg Kroah-Hartman Cc: Mark Fasheh Cc: Joel Becker Cc: Rusty Russell Cc: Jens Axboe Cc: Asai Thambi S P Cc: Selvan Mani Cc: Sam Bradshaw Cc: Jeff Moyer Cc: Al Viro Cc: Benjamin LaHaise Reviewed-by: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cgroup.h | 1 + include/linux/pid_namespace.h | 1 + include/linux/sched.h | 2 -- include/linux/writeback.h | 1 + 4 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 3bff9ce09cf7..5047355b9a0f 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -28,6 +28,7 @@ struct cgroup_subsys; struct inode; struct cgroup; struct css_id; +struct eventfd_ctx; extern int cgroup_init_early(void); extern int cgroup_init(void); diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index 731e4ecee3bd..e2772666f004 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -4,6 +4,7 @@ #include #include #include +#include #include #include #include diff --git a/include/linux/sched.h b/include/linux/sched.h index 4800e9d1864c..022c085ac3c5 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -313,8 +313,6 @@ extern void schedule_preempt_disabled(void); struct nsproxy; struct user_namespace; -#include - #ifdef CONFIG_MMU extern void arch_pick_mmap_layout(struct mm_struct *mm); extern unsigned long diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 9a9367c0c076..579a5007c696 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -5,6 +5,7 @@ #define WRITEBACK_H #include +#include #include DECLARE_PER_CPU(int, dirty_throttle_leaks); -- cgit v1.2.3 From d24f5a9ad9febffa53b1d3fcdf36c9a2283d848e Mon Sep 17 00:00:00 2001 From: David Henningsson Date: Wed, 8 May 2013 15:33:11 +0200 Subject: ALSA: Add comment for control TLV API Userspace is not meant to have to handle all strange dB ranges, so add a specification comment. Signed-off-by: David Henningsson Signed-off-by: Takashi Iwai --- include/sound/tlv.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/sound/tlv.h b/include/sound/tlv.h index 28c65e1ada21..e11e179420a1 100644 --- a/include/sound/tlv.h +++ b/include/sound/tlv.h @@ -74,7 +74,11 @@ #define DECLARE_TLV_DB_LINEAR(name, min_dB, max_dB) \ unsigned int name[] = { TLV_DB_LINEAR_ITEM(min_dB, max_dB) } -/* dB range container */ +/* dB range container: + * Items in dB range container must be ordered by their values and by their + * dB values. This implies that larger values must correspond with larger + * dB values (which is also required for all other mixer controls). + */ /* Each item is: */ #define TLV_DB_RANGE_ITEM(...) \ TLV_ITEM(SNDRV_CTL_TLVT_DB_RANGE, __VA_ARGS__) -- cgit v1.2.3 From ab3ea5bf37e7189e843e19e500e7af50e802b5f6 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 6 May 2013 08:22:18 -0400 Subject: NVMe: Simplify Firmware Activate code slightly Add definitions for the three Firmware Activate actions, and change the SCSI translation code to construct the command into a temporary variable instead of translating the endianness back-and-forth. Signed-off-by: Matthew Wilcox Reviewed-by: Vishal Verma --- include/linux/nvme.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 971ef086ed63..f451c8d6e231 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -316,6 +316,9 @@ enum { NVME_FEAT_WRITE_ATOMIC = 0x0a, NVME_FEAT_ASYNC_EVENT = 0x0b, NVME_FEAT_SW_PROGRESS = 0x0c, + NVME_FWACT_REPL = (0 << 3), + NVME_FWACT_REPL_ACTV = (1 << 3), + NVME_FWACT_ACTV = (2 << 3), }; struct nvme_identify { -- cgit v1.2.3 From 6eecdc5f95a393cb558503123eae9a9a6642e835 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 6 May 2013 11:29:23 +0000 Subject: usbnet: allow status interrupt URB to always be active Some drivers (sierra_net) need the status interrupt URB active even when the device is closed, because they receive custom indications from firmware. Add functions to refcount the status interrupt URB submit/kill operation so that sub-drivers and the generic driver don't fight over whether the status interrupt URB is active or not. A sub-driver can call usbnet_status_start() at any time, but the URB is only submitted the first time the function is called. Likewise, when the sub-driver is done with the URB, it calls usbnet_status_stop() but the URB is only killed when all users have stopped it. The URB is still killed and re-submitted for suspend/resume, as before, with the same refcount it had at suspend. Signed-off-by: Dan Williams Acked-by: Oliver Neukum Signed-off-by: David S. Miller --- include/linux/usb/usbnet.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index da46327fca17..f18d64129f99 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -56,6 +56,8 @@ struct usbnet { struct sk_buff_head done; struct sk_buff_head rxq_pause; struct urb *interrupt; + unsigned interrupt_count; + struct mutex interrupt_mutex; struct usb_anchor deferred; struct tasklet_struct bh; @@ -248,4 +250,7 @@ extern int usbnet_nway_reset(struct net_device *net); extern int usbnet_manage_power(struct usbnet *, int); extern void usbnet_link_change(struct usbnet *, bool, bool); +extern int usbnet_status_start(struct usbnet *dev, gfp_t mem_flags); +extern void usbnet_status_stop(struct usbnet *dev); + #endif /* __LINUX_USB_USBNET_H */ -- cgit v1.2.3 From 4f924b2aa4d3cb30f07e57d6b608838edcbc0d88 Mon Sep 17 00:00:00 2001 From: Josh Boyer Date: Wed, 8 May 2013 09:45:47 +0000 Subject: if_cablemodem.h: Add parenthesis around ioctl macros Protect the SIOCGCM* ioctl macros with parenthesis. Reported-by: Paul Wouters Signed-off-by: Josh Boyer Signed-off-by: David S. Miller --- include/uapi/linux/if_cablemodem.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/if_cablemodem.h b/include/uapi/linux/if_cablemodem.h index 9ca1007edd93..ee6b3c442baf 100644 --- a/include/uapi/linux/if_cablemodem.h +++ b/include/uapi/linux/if_cablemodem.h @@ -12,11 +12,11 @@ */ /* some useful defines for sb1000.c e cmconfig.c - fv */ -#define SIOCGCMSTATS SIOCDEVPRIVATE+0 /* get cable modem stats */ -#define SIOCGCMFIRMWARE SIOCDEVPRIVATE+1 /* get cm firmware version */ -#define SIOCGCMFREQUENCY SIOCDEVPRIVATE+2 /* get cable modem frequency */ -#define SIOCSCMFREQUENCY SIOCDEVPRIVATE+3 /* set cable modem frequency */ -#define SIOCGCMPIDS SIOCDEVPRIVATE+4 /* get cable modem PIDs */ -#define SIOCSCMPIDS SIOCDEVPRIVATE+5 /* set cable modem PIDs */ +#define SIOCGCMSTATS (SIOCDEVPRIVATE+0) /* get cable modem stats */ +#define SIOCGCMFIRMWARE (SIOCDEVPRIVATE+1) /* get cm firmware version */ +#define SIOCGCMFREQUENCY (SIOCDEVPRIVATE+2) /* get cable modem frequency */ +#define SIOCSCMFREQUENCY (SIOCDEVPRIVATE+3) /* set cable modem frequency */ +#define SIOCGCMPIDS (SIOCDEVPRIVATE+4) /* get cable modem PIDs */ +#define SIOCSCMPIDS (SIOCDEVPRIVATE+5) /* set cable modem PIDs */ #endif -- cgit v1.2.3 From 91c2e0bcae72a3086c698b5de2b950b885abb0e6 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 5 Mar 2013 20:10:59 -0500 Subject: unify compat fanotify_mark(2), switch to COMPAT_SYSCALL_DEFINE Signed-off-by: Al Viro --- include/linux/compat.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/compat.h b/include/linux/compat.h index d53c35352ea9..7f0c1dd09079 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -673,6 +673,8 @@ int __compat_save_altstack(compat_stack_t __user *, unsigned long); asmlinkage long compat_sys_sched_rr_get_interval(compat_pid_t pid, struct compat_timespec __user *interval); +asmlinkage long compat_sys_fanotify_mark(int, unsigned int, __u32, __u32, + int, const char __user *); #else #define is_compat_task() (0) -- cgit v1.2.3 From 60371952e1dd0d507039b2654c22083b32c38398 Mon Sep 17 00:00:00 2001 From: Fabio Estevam Date: Wed, 8 May 2013 21:05:54 +0800 Subject: ARM: imx: Select GENERIC_ALLOCATOR Since commit 657eee7 (media: coda: use genalloc API) the following build error happens with imx_v4_v5_defconfig: drivers/built-in.o: In function 'coda_remove': clk-composite.c:(.text+0x112180): undefined reference to 'gen_pool_free' drivers/built-in.o: In function 'coda_probe': clk-composite.c:(.text+0x112310): undefined reference to 'of_get_named_gen_pool' clk-composite.c:(.text+0x1123f4): undefined reference to 'gen_pool_alloc' clk-composite.c:(.text+0x11240c): undefined reference to 'gen_pool_virt_to_phys' clk-composite.c:(.text+0x112458): undefined reference to 'dev_get_gen_pool' Select GENERIC_ALLOCATOR and get rid of the custom IRAM_ALLOC. Signed-off-by: Fabio Estevam Signed-off-by: Shawn Guo Signed-off-by: Olof Johansson --- include/linux/platform_data/imx-iram.h | 41 ---------------------------------- 1 file changed, 41 deletions(-) delete mode 100644 include/linux/platform_data/imx-iram.h (limited to 'include') diff --git a/include/linux/platform_data/imx-iram.h b/include/linux/platform_data/imx-iram.h deleted file mode 100644 index 022690c33702..000000000000 --- a/include/linux/platform_data/imx-iram.h +++ /dev/null @@ -1,41 +0,0 @@ -/* - * Copyright (C) 2010 Freescale Semiconductor, Inc. All Rights Reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2 - * of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, - * MA 02110-1301, USA. - */ -#include - -#ifdef CONFIG_IRAM_ALLOC - -int __init iram_init(unsigned long base, unsigned long size); -void __iomem *iram_alloc(unsigned int size, unsigned long *dma_addr); -void iram_free(unsigned long dma_addr, unsigned int size); - -#else - -static inline int __init iram_init(unsigned long base, unsigned long size) -{ - return -ENOMEM; -} - -static inline void __iomem *iram_alloc(unsigned int size, unsigned long *dma_addr) -{ - return NULL; -} - -static inline void iram_free(unsigned long base, unsigned long size) {} - -#endif -- cgit v1.2.3 From f04f24fb7e48d446bd89a01c6056571f25972511 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 9 May 2013 14:44:17 +0900 Subject: ftrace, kprobes: Fix a deadlock on ftrace_regex_lock Fix a deadlock on ftrace_regex_lock which happens when setting an enable_event trigger on dynamic kprobe event as below. ---- sh-2.05b# echo p vfs_symlink > kprobe_events sh-2.05b# echo vfs_symlink:enable_event:kprobes:p_vfs_symlink_0 > set_ftrace_filter ============================================= [ INFO: possible recursive locking detected ] 3.9.0+ #35 Not tainted --------------------------------------------- sh/72 is trying to acquire lock: (ftrace_regex_lock){+.+.+.}, at: [] ftrace_set_hash+0x81/0x1f0 but task is already holding lock: (ftrace_regex_lock){+.+.+.}, at: [] ftrace_regex_write.isra.29.part.30+0x3d/0x220 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(ftrace_regex_lock); lock(ftrace_regex_lock); *** DEADLOCK *** ---- To fix that, this introduces a finer regex_lock for each ftrace_ops. ftrace_regex_lock is too big of a lock which protects all filter/notrace_hash operations, but it doesn't need to be a global lock after supporting multiple ftrace_ops because each ftrace_ops has its own filter/notrace_hash. Link: http://lkml.kernel.org/r/20130509054417.30398.84254.stgit@mhiramat-M0-7522 Cc: Srikar Dronamraju Cc: Oleg Nesterov Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Tom Zanussi Signed-off-by: Masami Hiramatsu [ Added initialization flag and automate mutex initialization for non ftrace.c ftrace_probes. ] Signed-off-by: Steven Rostedt --- include/linux/ftrace.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index f83e17a40e8b..99d0fbcbaf79 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -90,6 +90,8 @@ typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip, * not set this, then the ftrace infrastructure will add recursion * protection for the caller. * STUB - The ftrace_ops is just a place holder. + * INITIALIZED - The ftrace_ops has already been initialized (first use time + * register_ftrace_function() is called, it will initialized the ops) */ enum { FTRACE_OPS_FL_ENABLED = 1 << 0, @@ -100,6 +102,7 @@ enum { FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED = 1 << 5, FTRACE_OPS_FL_RECURSION_SAFE = 1 << 6, FTRACE_OPS_FL_STUB = 1 << 7, + FTRACE_OPS_FL_INITIALIZED = 1 << 8, }; struct ftrace_ops { @@ -110,6 +113,7 @@ struct ftrace_ops { #ifdef CONFIG_DYNAMIC_FTRACE struct ftrace_hash *notrace_hash; struct ftrace_hash *filter_hash; + struct mutex regex_lock; #endif }; -- cgit v1.2.3 From 1cf4c0732db3cd3c49cadbc60ff6bda08604e6fa Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 9 May 2013 14:44:29 +0900 Subject: tracing: Modify soft-mode only if there's no other referrer Modify soft-mode flag only if no other soft-mode referrer (currently only the ftrace triggers) by using a reference counter in each ftrace_event_file. Without this fix, adding and removing several different enable/disable_event triggers on the same event clear soft-mode bit from the ftrace_event_file. This also happens with a typo of glob on setting triggers. e.g. # echo vfs_symlink:enable_event:net:netif_rx > set_ftrace_filter # cat events/net/netif_rx/enable 0* # echo typo_func:enable_event:net:netif_rx > set_ftrace_filter # cat events/net/netif_rx/enable 0 # cat set_ftrace_filter #### all functions enabled #### vfs_symlink:enable_event:net:netif_rx:unlimited As above, we still have a trigger, but soft-mode is gone. Link: http://lkml.kernel.org/r/20130509054429.30398.7464.stgit@mhiramat-M0-7522 Cc: Srikar Dronamraju Cc: Oleg Nesterov Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: David Sharp Cc: Hiraku Toyooka Cc: Tom Zanussi Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 34e00fb49bec..4372658c73ae 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -293,6 +293,7 @@ struct ftrace_event_file { * caching and such. Which is mostly OK ;-) */ unsigned long flags; + atomic_t sm_ref; /* soft-mode reference counter */ }; #define __TRACE_EVENT_FLAGS(name, value) \ -- cgit v1.2.3 From 54afc1214133deddd49162b101971af5711f1b3a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Wed, 8 May 2013 16:38:33 +0300 Subject: drm: Add kernel-doc for drm_fb_helper_funcs->initial_config MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Ville Syrjälä Signed-off-by: Dave Airlie --- include/drm/drm_fb_helper.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/drm/drm_fb_helper.h b/include/drm/drm_fb_helper.h index 8230b46fdd73..61ebd51f6112 100644 --- a/include/drm/drm_fb_helper.h +++ b/include/drm/drm_fb_helper.h @@ -57,6 +57,7 @@ struct drm_fb_helper_surface_size { * @fb_probe: - Driver callback to allocate and initialize the fbdev info * structure. Futhermore it also needs to allocate the drm * framebuffer used to back the fbdev. + * @initial_config: - Setup an initial fbdev display configuration * * Driver callbacks used by the fbdev emulation helper library. */ -- cgit v1.2.3 From 7b97936f298af7991ca4717a4c23610d9ecd8927 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Wed, 8 May 2013 16:38:34 +0300 Subject: drm: Remove pointless '-' characters from drm_fb_helper documentation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Ville Syrjälä Signed-off-by: Dave Airlie --- include/drm/drm_fb_helper.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/drm/drm_fb_helper.h b/include/drm/drm_fb_helper.h index 61ebd51f6112..471f276ce8f7 100644 --- a/include/drm/drm_fb_helper.h +++ b/include/drm/drm_fb_helper.h @@ -50,14 +50,14 @@ struct drm_fb_helper_surface_size { /** * struct drm_fb_helper_funcs - driver callbacks for the fbdev emulation library - * @gamma_set: - Set the given gamma lut register on the given crtc. - * @gamma_get: - Read the given gamma lut register on the given crtc, used to - * save the current lut when force-restoring the fbdev for e.g. - * kdbg. - * @fb_probe: - Driver callback to allocate and initialize the fbdev info - * structure. Futhermore it also needs to allocate the drm - * framebuffer used to back the fbdev. - * @initial_config: - Setup an initial fbdev display configuration + * @gamma_set: Set the given gamma lut register on the given crtc. + * @gamma_get: Read the given gamma lut register on the given crtc, used to + * save the current lut when force-restoring the fbdev for e.g. + * kdbg. + * @fb_probe: Driver callback to allocate and initialize the fbdev info + * structure. Futhermore it also needs to allocate the drm + * framebuffer used to back the fbdev. + * @initial_config: Setup an initial fbdev display configuration * * Driver callbacks used by the fbdev emulation helper library. */ -- cgit v1.2.3 From b9434d0f162c351e02e0e8f66ca6b75a67595537 Mon Sep 17 00:00:00 2001 From: Chris Cummins Date: Thu, 9 May 2013 14:20:40 +0100 Subject: drm: Use names of ioctls in debug traces MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The intention here is to make the output of dmesg with full verbosity a bit easier for a human to parse. This commit transforms: [drm:drm_ioctl], pid=699, cmd=0x6458, nr=0x58, dev 0xe200, auth=1 [drm:drm_ioctl], pid=699, cmd=0xc010645b, nr=0x5b, dev 0xe200, auth=1 [drm:drm_ioctl], pid=699, cmd=0xc0106461, nr=0x61, dev 0xe200, auth=1 [drm:drm_ioctl], pid=699, cmd=0xc01c64ae, nr=0xae, dev 0xe200, auth=1 [drm:drm_mode_addfb], [FB:32] [drm:drm_ioctl], pid=699, cmd=0xc0106464, nr=0x64, dev 0xe200, auth=1 [drm:drm_vm_open_locked], 0x7fd9302fe000,0x00a00000 [drm:drm_ioctl], pid=699, cmd=0x400c645f, nr=0x5f, dev 0xe200, auth=1 [drm:drm_ioctl], pid=699, cmd=0xc00464af, nr=0xaf, dev 0xe200, auth=1 [drm:intel_crtc_set_config], [CRTC:3] [NOFB] into: [drm:drm_ioctl], pid=699, dev=0xe200, auth=1, I915_GEM_THROTTLE [drm:drm_ioctl], pid=699, dev=0xe200, auth=1, I915_GEM_CREATE [drm:drm_ioctl], pid=699, dev=0xe200, auth=1, I915_GEM_SET_TILING [drm:drm_ioctl], pid=699, dev=0xe200, auth=1, IOCTL_MODE_ADDFB [drm:drm_mode_addfb], [FB:32] [drm:drm_ioctl], pid=699, dev=0xe200, auth=1, I915_GEM_MMAP_GTT [drm:drm_vm_open_locked], 0x7fd9302fe000,0x00a00000 [drm:drm_ioctl], pid=699, dev=0xe200, auth=1, I915_GEM_SET_DOMAIN [drm:drm_ioctl], pid=699, dev=0xe200, auth=1, DRM_IOCTL_MODE_RMFB [drm:intel_crtc_set_config], [CRTC:3] [NOFB] v2: drm_ioctls is now a constant (Ville Syrjälä) Signed-off-by: Chris Cummins Signed-off-by: Dave Airlie --- include/drm/drmP.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/drmP.h b/include/drm/drmP.h index f1ce786736e4..b092b5bcf227 100644 --- a/include/drm/drmP.h +++ b/include/drm/drmP.h @@ -316,6 +316,7 @@ struct drm_ioctl_desc { int flags; drm_ioctl_t *func; unsigned int cmd_drv; + const char *name; }; /** @@ -324,7 +325,7 @@ struct drm_ioctl_desc { */ #define DRM_IOCTL_DEF_DRV(ioctl, _func, _flags) \ - [DRM_IOCTL_NR(DRM_##ioctl)] = {.cmd = DRM_##ioctl, .func = _func, .flags = _flags, .cmd_drv = DRM_IOCTL_##ioctl} + [DRM_IOCTL_NR(DRM_##ioctl)] = {.cmd = DRM_##ioctl, .func = _func, .flags = _flags, .cmd_drv = DRM_IOCTL_##ioctl, .name = #ioctl} struct drm_magic_entry { struct list_head head; -- cgit v1.2.3 From 058ce5ca8155a4c8eeac9b9e8a70e6664996337b Mon Sep 17 00:00:00 2001 From: Alasdair G Kergon Date: Fri, 10 May 2013 14:37:17 +0100 Subject: dm: document iterate_devices Document iterate_devices in device-mapper.h. Signed-off-by: Alasdair G Kergon --- include/linux/device-mapper.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 1e483fa7afb4..3cd32478f2fd 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -79,11 +79,26 @@ typedef int (*dm_ioctl_fn) (struct dm_target *ti, unsigned int cmd, typedef int (*dm_merge_fn) (struct dm_target *ti, struct bvec_merge_data *bvm, struct bio_vec *biovec, int max_size); +/* + * These iteration functions are typically used to check (and combine) + * properties of underlying devices. + * E.g. Does at least one underlying device support flush? + * Does any underlying device not support WRITE_SAME? + * + * The callout function is called once for each contiguous section of + * an underlying device. State can be maintained in *data. + * Return non-zero to stop iterating through any further devices. + */ typedef int (*iterate_devices_callout_fn) (struct dm_target *ti, struct dm_dev *dev, sector_t start, sector_t len, void *data); +/* + * This function must iterate through each section of device used by the + * target until it encounters a non-zero return code, which it then returns. + * Returns zero if no callout returned non-zero. + */ typedef int (*dm_iterate_devices_fn) (struct dm_target *ti, iterate_devices_callout_fn fn, void *data); -- cgit v1.2.3 From aa9f8328fc51460e15da129caf622b6560fa8c99 Mon Sep 17 00:00:00 2001 From: James Bottomley Date: Tue, 7 May 2013 14:44:06 -0700 Subject: [SCSI] sas: unify the pointlessly separated enums sas_dev_type and sas_device_type These enums have been separate since the dawn of SAS, mainly because the latter is a procotol only enum and the former includes additional state for libsas. The dichotomy causes endless confusion about which one you should use where and leads to pointless warnings like this: drivers/scsi/mvsas/mv_sas.c: In function 'mvs_update_phyinfo': drivers/scsi/mvsas/mv_sas.c:1162:34: warning: comparison between 'enum sas_device_type' and 'enum sas_dev_type' [-Wenum-compare] Fix by eliminating one of them. The one kept is effectively the sas.h one, but call it sas_device_type and make sure the enums are all properly namespaced with the SAS_ prefix. Signed-off-by: James Bottomley --- include/scsi/libsas.h | 4 ++-- include/scsi/sas.h | 22 ++++++++++++---------- include/scsi/sas_ata.h | 4 ++-- include/scsi/scsi_transport_sas.h | 7 ------- 4 files changed, 16 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h index ef937b56f9b5..e2c1e66d58ae 100644 --- a/include/scsi/libsas.h +++ b/include/scsi/libsas.h @@ -118,7 +118,7 @@ struct ex_phy { enum ex_phy_state phy_state; - enum sas_dev_type attached_dev_type; + enum sas_device_type attached_dev_type; enum sas_linkrate linkrate; u8 attached_sata_host:1; @@ -195,7 +195,7 @@ enum { struct domain_device { spinlock_t done_lock; - enum sas_dev_type dev_type; + enum sas_device_type dev_type; enum sas_linkrate linkrate; enum sas_linkrate min_linkrate; diff --git a/include/scsi/sas.h b/include/scsi/sas.h index be3eb0bf1ac0..0d2607d12387 100644 --- a/include/scsi/sas.h +++ b/include/scsi/sas.h @@ -90,16 +90,18 @@ enum sas_oob_mode { }; /* See sas_discover.c if you plan on changing these */ -enum sas_dev_type { - NO_DEVICE = 0, /* protocol */ - SAS_END_DEV = 1, /* protocol */ - EDGE_DEV = 2, /* protocol */ - FANOUT_DEV = 3, /* protocol */ - SAS_HA = 4, - SATA_DEV = 5, - SATA_PM = 7, - SATA_PM_PORT= 8, - SATA_PENDING = 9, +enum sas_device_type { + /* these are SAS protocol defined (attached device type field) */ + SAS_PHY_UNUSED = 0, + SAS_END_DEVICE = 1, + SAS_EDGE_EXPANDER_DEVICE = 2, + SAS_FANOUT_EXPANDER_DEVICE = 3, + /* these are internal to libsas */ + SAS_HA = 4, + SAS_SATA_DEV = 5, + SAS_SATA_PM = 7, + SAS_SATA_PM_PORT = 8, + SAS_SATA_PENDING = 9, }; enum sas_protocol { diff --git a/include/scsi/sas_ata.h b/include/scsi/sas_ata.h index ff71a5654684..00f41aeeecf5 100644 --- a/include/scsi/sas_ata.h +++ b/include/scsi/sas_ata.h @@ -32,8 +32,8 @@ static inline int dev_is_sata(struct domain_device *dev) { - return dev->dev_type == SATA_DEV || dev->dev_type == SATA_PM || - dev->dev_type == SATA_PM_PORT || dev->dev_type == SATA_PENDING; + return dev->dev_type == SAS_SATA_DEV || dev->dev_type == SAS_SATA_PM || + dev->dev_type == SAS_SATA_PM_PORT || dev->dev_type == SAS_SATA_PENDING; } int sas_get_ata_info(struct domain_device *dev, struct ex_phy *phy); diff --git a/include/scsi/scsi_transport_sas.h b/include/scsi/scsi_transport_sas.h index 9b8e08879cfc..0bd71e2702e3 100644 --- a/include/scsi/scsi_transport_sas.h +++ b/include/scsi/scsi_transport_sas.h @@ -10,13 +10,6 @@ struct scsi_transport_template; struct sas_rphy; struct request; -enum sas_device_type { - SAS_PHY_UNUSED = 0, - SAS_END_DEVICE = 1, - SAS_EDGE_EXPANDER_DEVICE = 2, - SAS_FANOUT_EXPANDER_DEVICE = 3, -}; - static inline int sas_protocol_ata(enum sas_protocol proto) { return ((proto & SAS_PROTOCOL_SATA) || -- cgit v1.2.3 From 8526cb114f771851d84425d85d8735a6e0816ba2 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Mon, 6 May 2013 12:06:56 -0500 Subject: [SCSI] iscsi class, qla4xxx: fix sess/conn refcounting when find fns are used This fixes a bug where the iscsi class/driver did not do a put_device when a sess/conn device was found. This also simplifies the interface by not having to pass in some arguments that were duplicated and did not need to be exported. Reported-by: Zhao Hongjiang Signed-off-by: Mike Christie Acked-by: Vikas Chaudhary Signed-off-by: James Bottomley --- include/scsi/scsi_transport_iscsi.h | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/scsi/scsi_transport_iscsi.h b/include/scsi/scsi_transport_iscsi.h index 4a58cca2ecc1..d0f1602985e7 100644 --- a/include/scsi/scsi_transport_iscsi.h +++ b/include/scsi/scsi_transport_iscsi.h @@ -471,14 +471,10 @@ iscsi_destroy_flashnode_sess(struct iscsi_bus_flash_session *fnode_sess); extern void iscsi_destroy_all_flashnode(struct Scsi_Host *shost); extern int iscsi_flashnode_bus_match(struct device *dev, struct device_driver *drv); -extern int iscsi_is_flashnode_conn_dev(struct device *dev, void *data); - extern struct device * iscsi_find_flashnode_sess(struct Scsi_Host *shost, void *data, int (*fn)(struct device *dev, void *data)); - extern struct device * -iscsi_find_flashnode_conn(struct iscsi_bus_flash_session *fnode_sess, - void *data, - int (*fn)(struct device *dev, void *data)); +iscsi_find_flashnode_conn(struct iscsi_bus_flash_session *fnode_sess); + #endif -- cgit v1.2.3 From 7677fc965fba41d1386fa3b76a1f00303f02bb2d Mon Sep 17 00:00:00 2001 From: Rony Efraim Date: Wed, 8 May 2013 22:22:35 +0000 Subject: net/mlx4: Strengthen VLAN tags/priorities enforcement in VST mode Make sure that the following steps are taken: - drop packets sent by the VF with vlan tag - block packets with vlan tag which are steered to the VF - drop/block tagged packets when the policy is priority-tagged - make sure VLAN stripping for received packets is set - make sure force UP bit for the VF QP is set Use enum values for all the above instead of numerical bit offsets. Signed-off-by: Rony Efraim Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/qp.h | 29 +++++++++++++++++++++++++++-- 1 file changed, 27 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h index 67f46ad6920a..352eec9df1b8 100644 --- a/include/linux/mlx4/qp.h +++ b/include/linux/mlx4/qp.h @@ -126,7 +126,7 @@ struct mlx4_rss_context { struct mlx4_qp_path { u8 fl; - u8 reserved1[1]; + u8 vlan_control; u8 disable_pkey_check; u8 pkey_index; u8 counter_index; @@ -141,11 +141,32 @@ struct mlx4_qp_path { u8 sched_queue; u8 vlan_index; u8 feup; - u8 reserved3; + u8 fvl_rx; u8 reserved4[2]; u8 dmac[6]; }; +enum { /* fl */ + MLX4_FL_CV = 1 << 6, + MLX4_FL_ETH_HIDE_CQE_VLAN = 1 << 2 +}; +enum { /* vlan_control */ + MLX4_VLAN_CTRL_ETH_TX_BLOCK_TAGGED = 1 << 6, + MLX4_VLAN_CTRL_ETH_RX_BLOCK_TAGGED = 1 << 2, + MLX4_VLAN_CTRL_ETH_RX_BLOCK_PRIO_TAGGED = 1 << 1, /* 802.1p priority tag */ + MLX4_VLAN_CTRL_ETH_RX_BLOCK_UNTAGGED = 1 << 0 +}; + +enum { /* feup */ + MLX4_FEUP_FORCE_ETH_UP = 1 << 6, /* force Eth UP */ + MLX4_FSM_FORCE_ETH_SRC_MAC = 1 << 5, /* force Source MAC */ + MLX4_FVL_FORCE_ETH_VLAN = 1 << 3 /* force Eth vlan */ +}; + +enum { /* fvl_rx */ + MLX4_FVL_RX_FORCE_ETH_VLAN = 1 << 0 /* enforce Eth rx vlan */ +}; + struct mlx4_qp_context { __be32 flags; __be32 pd; @@ -185,6 +206,10 @@ struct mlx4_qp_context { u32 reserved5[10]; }; +enum { /* param3 */ + MLX4_STRIP_VLAN = 1 << 30 +}; + /* Which firmware version adds support for NEC (NoErrorCompletion) bit */ #define MLX4_FW_VER_WQE_CTRL_NEC mlx4_fw_ver(2, 2, 232) -- cgit v1.2.3 From f77d602124d865c38705df7fa25c03de9c284ad2 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 9 May 2013 10:28:16 +0000 Subject: ipv6: do not clear pinet6 field We have seen multiple NULL dereferences in __inet6_lookup_established() After analysis, I found that inet6_sk() could be NULL while the check for sk_family == AF_INET6 was true. Bug was added in linux-2.6.29 when RCU lookups were introduced in UDP and TCP stacks. Once an IPv6 socket, using SLAB_DESTROY_BY_RCU is inserted in a hash table, we no longer can clear pinet6 field. This patch extends logic used in commit fcbdf09d9652c891 ("net: fix nulls list corruptions in sk_prot_alloc") TCP/UDP/UDPLite IPv6 protocols provide their own .clear_sk() method to make sure we do not clear pinet6 field. At socket clone phase, we do not really care, as cloning the parent (non NULL) pinet6 is not adding a fatal race. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/sock.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index 5c97b0fc5623..66772cf8c3c5 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -866,6 +866,18 @@ struct inet_hashinfo; struct raw_hashinfo; struct module; +/* + * caches using SLAB_DESTROY_BY_RCU should let .next pointer from nulls nodes + * un-modified. Special care is taken when initializing object to zero. + */ +static inline void sk_prot_clear_nulls(struct sock *sk, int size) +{ + if (offsetof(struct sock, sk_node.next) != 0) + memset(sk, 0, offsetof(struct sock, sk_node.next)); + memset(&sk->sk_node.pprev, 0, + size - offsetof(struct sock, sk_node.pprev)); +} + /* Networking protocol blocks we attach to sockets. * socket layer -> transport layer interface * transport -> network interface is defined by struct inet_proto -- cgit v1.2.3 From 0a3b15ac3cc3ddc791901e12bdc930b5fa11a30a Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 2 May 2013 21:54:37 +0200 Subject: ACPI / PM: Move processor suspend/resume to syscore_ops The system suspend routine of the ACPI processor driver saves the BUS_MASTER_RLD register and its resume routine restores it. However, there can be only one such register in the system and it really should be saved after non-boot CPUs have been offlined and restored before they are put back online during resume. For this reason, move the saving and restoration of BUS_MASTER_RLD to syscore suspend and syscore resume, respectively, and drop the no longer necessary suspend/resume callbacks from the ACPI processor driver. Signed-off-by: Rafael J. Wysocki --- include/acpi/processor.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/acpi/processor.h b/include/acpi/processor.h index b327b5a9296d..ea69367fdd3b 100644 --- a/include/acpi/processor.h +++ b/include/acpi/processor.h @@ -329,10 +329,16 @@ int acpi_processor_power_init(struct acpi_processor *pr); int acpi_processor_power_exit(struct acpi_processor *pr); int acpi_processor_cst_has_changed(struct acpi_processor *pr); int acpi_processor_hotplug(struct acpi_processor *pr); -int acpi_processor_suspend(struct device *dev); -int acpi_processor_resume(struct device *dev); extern struct cpuidle_driver acpi_idle_driver; +#ifdef CONFIG_PM_SLEEP +void acpi_processor_syscore_init(void); +void acpi_processor_syscore_exit(void); +#else +static inline void acpi_processor_syscore_init(void) {} +static inline void acpi_processor_syscore_exit(void) {} +#endif + /* in processor_thermal.c */ int acpi_processor_get_limit_info(struct acpi_processor *pr); extern const struct thermal_cooling_device_ops processor_cooling_ops; -- cgit v1.2.3 From 36200af867e2cf5adc1ff77214b2524f6111736f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jan-Simon=20M=C3=B6ller?= Date: Tue, 30 Apr 2013 09:39:04 +0000 Subject: ACPI: Fix section to __init. Align with usage in acpixf.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fixes warning during compilation with clang. [rjw: Subject and changelog] Signed-off-by: Jan-Simon Möller Signed-off-by: Rafael J. Wysocki --- include/acpi/acpiosxf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/acpi/acpiosxf.h b/include/acpi/acpiosxf.h index 5b3d2bd4813a..64b8c7639520 100644 --- a/include/acpi/acpiosxf.h +++ b/include/acpi/acpiosxf.h @@ -77,7 +77,7 @@ struct acpi_signal_fatal_info { /* * OSL Initialization and shutdown primitives */ -acpi_status __initdata acpi_os_initialize(void); +acpi_status __init acpi_os_initialize(void); acpi_status acpi_os_terminate(void); -- cgit v1.2.3 From 95643359f8b31e74b35901f4e36cd069cd67fd48 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Mon, 13 May 2013 15:23:49 +1000 Subject: drm: remove unused wrapper macros We don't use these anymore so nuke them. Signed-off-by: Dave Airlie --- include/drm/drm_os_linux.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include') diff --git a/include/drm/drm_os_linux.h b/include/drm/drm_os_linux.h index 393369147a2d..675ddf4b441f 100644 --- a/include/drm/drm_os_linux.h +++ b/include/drm/drm_os_linux.h @@ -87,15 +87,6 @@ static __inline__ int mtrr_del(int reg, unsigned long base, unsigned long size) /** Other copying of data from kernel space */ #define DRM_COPY_TO_USER(arg1, arg2, arg3) \ copy_to_user(arg1, arg2, arg3) -/* Macros for copyfrom user, but checking readability only once */ -#define DRM_VERIFYAREA_READ( uaddr, size ) \ - (access_ok( VERIFY_READ, uaddr, size ) ? 0 : -EFAULT) -#define DRM_COPY_FROM_USER_UNCHECKED(arg1, arg2, arg3) \ - __copy_from_user(arg1, arg2, arg3) -#define DRM_COPY_TO_USER_UNCHECKED(arg1, arg2, arg3) \ - __copy_to_user(arg1, arg2, arg3) -#define DRM_GET_USER_UNCHECKED(val, uaddr) \ - __get_user(val, uaddr) #define DRM_HZ HZ -- cgit v1.2.3 From e2555fde4159467fb579e6ae3c0a8fc33015d0f5 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 13 May 2013 09:45:01 -0400 Subject: jbd,jbd2: fix oops in jbd2_journal_put_journal_head() Commit ae4647fb (jbd2: reduce journal_head size) introduced a regression where we occasionally hit panic in jbd2_journal_put_journal_head() because of wrong b_jcount. The bug is caused by gcc making 64-bit access to 32-bit bitfield and thus clobbering b_jcount. At least for now, those 8 bytes saved in struct journal_head are not worth the trouble with gcc bitfield handling so revert that part of the patch. Reported-by: EUNBONG SONG Reported-by: Tony Luck Signed-off-by: Jan Kara Signed-off-by: "Theodore Ts'o" --- include/linux/journal-head.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/journal-head.h b/include/linux/journal-head.h index 13a3da25ff07..98cd41bb39c8 100644 --- a/include/linux/journal-head.h +++ b/include/linux/journal-head.h @@ -30,15 +30,19 @@ struct journal_head { /* * Journalling list for this buffer [jbd_lock_bh_state()] + * NOTE: We *cannot* combine this with b_modified into a bitfield + * as gcc would then (which the C standard allows but which is + * very unuseful) make 64-bit accesses to the bitfield and clobber + * b_jcount if its update races with bitfield modification. */ - unsigned b_jlist:4; + unsigned b_jlist; /* * This flag signals the buffer has been modified by * the currently running transaction * [jbd_lock_bh_state()] */ - unsigned b_modified:1; + unsigned b_modified; /* * Copy of the buffer data frozen for writing to the log. -- cgit v1.2.3 From ee8209fd026b074bb8eb75bece516a338a281b1b Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 8 May 2013 11:55:48 +0300 Subject: dma: acpi-dma: parse CSRT to extract additional resources Since we have CSRT only to get additional DMA controller resources, let's get rid of drivers/acpi/csrt.c and move its logic inside ACPI DMA helpers code. Signed-off-by: Andy Shevchenko Signed-off-by: Mika Westerberg Acked-by: Rafael J. Wysocki Signed-off-by: Vinod Koul --- include/linux/acpi_dma.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/acpi_dma.h b/include/linux/acpi_dma.h index d09deabc7bf6..fb0298082916 100644 --- a/include/linux/acpi_dma.h +++ b/include/linux/acpi_dma.h @@ -37,6 +37,8 @@ struct acpi_dma_spec { * @dev: struct device of this controller * @acpi_dma_xlate: callback function to find a suitable channel * @data: private data used by a callback function + * @base_request_line: first supported request line (CSRT) + * @end_request_line: last supported request line (CSRT) */ struct acpi_dma { struct list_head dma_controllers; @@ -44,6 +46,8 @@ struct acpi_dma { struct dma_chan *(*acpi_dma_xlate) (struct acpi_dma_spec *, struct acpi_dma *); void *data; + unsigned short base_request_line; + unsigned short end_request_line; }; /* Used with acpi_dma_simple_xlate() */ -- cgit v1.2.3 From b59cc200ac025aca597fb21862c1c9e667f2eff2 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 8 May 2013 11:55:49 +0300 Subject: ACPI / LPSS: register clock device for Lynxpoint DMA properly The DMA controller in Lynxpoint is enumerated as a regular ACPI device now. To work properly it is using the LPSS root clock as a functional clock. That's why we have to register the clock device accordingly to the ACPI ID of the DMA controller. The acpi_lpss.c module is responsible to do the job. This patch also removes hardcoded name of the DMA device in clk-lpt.c and the name of the root clock in acpi_lpss.c. Signed-off-by: Rafael J. Wysocki Signed-off-by: Andy Shevchenko Signed-off-by: Vinod Koul --- include/linux/platform_data/clk-lpss.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/platform_data/clk-lpss.h b/include/linux/platform_data/clk-lpss.h index 528e73ce46d2..23901992b9dd 100644 --- a/include/linux/platform_data/clk-lpss.h +++ b/include/linux/platform_data/clk-lpss.h @@ -13,6 +13,11 @@ #ifndef __CLK_LPSS_H #define __CLK_LPSS_H +struct lpss_clk_data { + const char *name; + struct clk *clk; +}; + extern int lpt_clk_init(void); #endif /* __CLK_LPSS_H */ -- cgit v1.2.3 From 63ad9cbff5896dadfee510f631ffcb0176984722 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Tue, 23 Apr 2013 15:28:38 +0200 Subject: pinctrl: generic: Fix typos and clarify comments Drive strength controls both sink and source currents, clarify the description accordingly. Signed-off-by: Laurent Pinchart Signed-off-by: Linus Walleij --- include/linux/pinctrl/pinconf-generic.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/pinctrl/pinconf-generic.h b/include/linux/pinctrl/pinconf-generic.h index 72474e18f1e0..6aa238096622 100644 --- a/include/linux/pinctrl/pinconf-generic.h +++ b/include/linux/pinctrl/pinconf-generic.h @@ -37,17 +37,17 @@ * if it is 0, pull-down is disabled. * @PIN_CONFIG_DRIVE_PUSH_PULL: the pin will be driven actively high and * low, this is the most typical case and is typically achieved with two - * active transistors on the output. Sending this config will enabale + * active transistors on the output. Setting this config will enable * push-pull mode, the argument is ignored. * @PIN_CONFIG_DRIVE_OPEN_DRAIN: the pin will be driven with open drain (open * collector) which means it is usually wired with other output ports - * which are then pulled up with an external resistor. Sending this - * config will enabale open drain mode, the argument is ignored. + * which are then pulled up with an external resistor. Setting this + * config will enable open drain mode, the argument is ignored. * @PIN_CONFIG_DRIVE_OPEN_SOURCE: the pin will be driven with open source - * (open emitter). Sending this config will enabale open drain mode, the + * (open emitter). Setting this config will enable open drain mode, the * argument is ignored. - * @PIN_CONFIG_DRIVE_STRENGTH: the pin will output the current passed as - * argument. The argument is in mA. + * @PIN_CONFIG_DRIVE_STRENGTH: the pin will sink or source at most the current + * passed as argument. The argument is in mA. * @PIN_CONFIG_INPUT_SCHMITT_ENABLE: control schmitt-trigger mode on the pin. * If the argument != 0, schmitt-trigger mode is enabled. If it's 0, * schmitt-trigger mode is disabled. -- cgit v1.2.3 From b4f711ee03d28f776fd2324fd0bd999cc428e4d2 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Wed, 24 Apr 2013 11:32:56 -0700 Subject: time: Revert ALWAYS_USE_PERSISTENT_CLOCK compile time optimizaitons Kay Sievers noted that the ALWAYS_USE_PERSISTENT_CLOCK config, which enables some minor compile time optimization to avoid uncessary code in mostly the suspend/resume path could cause problems for userland. In particular, the dependency for RTC_HCTOSYS on !ALWAYS_USE_PERSISTENT_CLOCK, which avoids setting the time twice and simplifies suspend/resume, has the side effect of causing the /sys/class/rtc/rtcN/hctosys flag to always be zero, and this flag is commonly used by udev to setup the /dev/rtc symlink to /dev/rtcN, which can cause pain for older applications. While the udev rules could use some work to be less fragile, breaking userland should strongly be avoided. Additionally the compile time optimizations are fairly minor, and the code being optimized is likely to be reworked in the future, so lets revert this change. Reported-by: Kay Sievers Signed-off-by: John Stultz Cc: stable #3.9 Cc: Feng Tang Cc: Jason Gunthorpe Link: http://lkml.kernel.org/r/1366828376-18124-1-git-send-email-john.stultz@linaro.org Signed-off-by: Thomas Gleixner --- include/linux/time.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/time.h b/include/linux/time.h index 22d81b3c955b..d5d229b2e5af 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -117,14 +117,10 @@ static inline bool timespec_valid_strict(const struct timespec *ts) extern bool persistent_clock_exist; -#ifdef ALWAYS_USE_PERSISTENT_CLOCK -#define has_persistent_clock() true -#else static inline bool has_persistent_clock(void) { return persistent_clock_exist; } -#endif extern void read_persistent_clock(struct timespec *ts); extern void read_boot_clock(struct timespec *ts); -- cgit v1.2.3 From a1321ddd27e65c6ada5b9a12cae4ee2612d76893 Mon Sep 17 00:00:00 2001 From: Joern Engel Date: Mon, 13 May 2013 16:30:05 -0400 Subject: target: removed unused transport_state flag Signed-off-by: Joern Engel Signed-off-by: Nicholas Bellinger --- include/target/target_core_base.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index 136b7b2f7b32..e773dfa5f98f 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -463,7 +463,6 @@ struct se_cmd { #define CMD_T_ABORTED (1 << 0) #define CMD_T_ACTIVE (1 << 1) #define CMD_T_COMPLETE (1 << 2) -#define CMD_T_QUEUED (1 << 3) #define CMD_T_SENT (1 << 4) #define CMD_T_STOP (1 << 5) #define CMD_T_FAILED (1 << 6) -- cgit v1.2.3 From ccf5ae83a6cf3d9cfe9a7038bfe7cd38ab03d5e1 Mon Sep 17 00:00:00 2001 From: Joern Engel Date: Mon, 13 May 2013 16:30:06 -0400 Subject: target: close target_put_sess_cmd() vs. core_tmr_abort_task() race It is possible for one thread to to take se_sess->sess_cmd_lock in core_tmr_abort_task() before taking a reference count on se_cmd->cmd_kref, while another thread in target_put_sess_cmd() drops se_cmd->cmd_kref before taking se_sess->sess_cmd_lock. This introduces kref_put_spinlock_irqsave() and uses it in target_put_sess_cmd() to close the race window. Signed-off-by: Joern Engel Acked-by: Greg Kroah-Hartman Cc: Signed-off-by: Nicholas Bellinger --- include/linux/kref.h | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) (limited to 'include') diff --git a/include/linux/kref.h b/include/linux/kref.h index 4972e6e9ca93..7419c02085d7 100644 --- a/include/linux/kref.h +++ b/include/linux/kref.h @@ -19,6 +19,7 @@ #include #include #include +#include struct kref { atomic_t refcount; @@ -95,6 +96,38 @@ static inline int kref_put(struct kref *kref, void (*release)(struct kref *kref) return kref_sub(kref, 1, release); } +/** + * kref_put_spinlock_irqsave - decrement refcount for object. + * @kref: object. + * @release: pointer to the function that will clean up the object when the + * last reference to the object is released. + * This pointer is required, and it is not acceptable to pass kfree + * in as this function. + * @lock: lock to take in release case + * + * Behaves identical to kref_put with one exception. If the reference count + * drops to zero, the lock will be taken atomically wrt dropping the reference + * count. The release function has to call spin_unlock() without _irqrestore. + */ +static inline int kref_put_spinlock_irqsave(struct kref *kref, + void (*release)(struct kref *kref), + spinlock_t *lock) +{ + unsigned long flags; + + WARN_ON(release == NULL); + if (atomic_add_unless(&kref->refcount, -1, 1)) + return 0; + spin_lock_irqsave(lock, flags); + if (atomic_dec_and_test(&kref->refcount)) { + release(kref); + local_irq_restore(flags); + return 1; + } + spin_unlock_irqrestore(lock, flags); + return 0; +} + static inline int kref_put_mutex(struct kref *kref, void (*release)(struct kref *kref), struct mutex *lock) -- cgit v1.2.3 From 8cdb46da06ea94543a3b2e53e3e92736421d1093 Mon Sep 17 00:00:00 2001 From: Hans Schillstrom Date: Wed, 15 May 2013 01:23:45 +0000 Subject: netfilter: log: netns NULL ptr bug when calling from conntrack Since (69b34fb netfilter: xt_LOG: add net namespace support for xt_LOG), we hit this: [ 4224.708977] BUG: unable to handle kernel NULL pointer dereference at 0000000000000388 [ 4224.709074] IP: [] ipt_log_packet+0x29/0x270 when callling log functions from conntrack both in and out are NULL i.e. the net pointer is invalid. Adding struct net *net in call to nf_logfn() will secure that there always is a vaild net ptr. Reported as netfilter's bugzilla bug 818: https://bugzilla.netfilter.org/show_bug.cgi?id=818 Reported-by: Ronald Signed-off-by: Hans Schillstrom Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_log.h | 3 ++- include/net/netfilter/nfnetlink_log.h | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_log.h b/include/net/netfilter/nf_log.h index 31f1fb9eb784..99eac12d040b 100644 --- a/include/net/netfilter/nf_log.h +++ b/include/net/netfilter/nf_log.h @@ -30,7 +30,8 @@ struct nf_loginfo { } u; }; -typedef void nf_logfn(u_int8_t pf, +typedef void nf_logfn(struct net *net, + u_int8_t pf, unsigned int hooknum, const struct sk_buff *skb, const struct net_device *in, diff --git a/include/net/netfilter/nfnetlink_log.h b/include/net/netfilter/nfnetlink_log.h index e2dec42c2db2..5ca3f14f0998 100644 --- a/include/net/netfilter/nfnetlink_log.h +++ b/include/net/netfilter/nfnetlink_log.h @@ -2,7 +2,8 @@ #define _KER_NFNETLINK_LOG_H void -nfulnl_log_packet(u_int8_t pf, +nfulnl_log_packet(struct net *net, + u_int8_t pf, unsigned int hooknum, const struct sk_buff *skb, const struct net_device *in, -- cgit v1.2.3 From de97f250394996f5acb07ba9e6dbdfc15ee4316c Mon Sep 17 00:00:00 2001 From: "Robert P. J. Day" Date: Thu, 2 May 2013 09:51:44 -0400 Subject: Correct typo "supperspeed" to "superspeed". Tidy up kernel-doc content for USB GADGET. No functional change. Signed-off-by: Robert P. J. Day Signed-off-by: Felipe Balbi --- include/linux/usb/gadget.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index c454a88abf2e..f1b0dca60f12 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -563,9 +563,8 @@ static inline int gadget_is_dualspeed(struct usb_gadget *g) } /** - * gadget_is_superspeed() - return true if the hardware handles - * supperspeed - * @g: controller that might support supper speed + * gadget_is_superspeed() - return true if the hardware handles superspeed + * @g: controller that might support superspeed */ static inline int gadget_is_superspeed(struct usb_gadget *g) { -- cgit v1.2.3 From 755ccb9d577b95b43537cfeb36da59140412f858 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Wed, 15 May 2013 08:00:25 +0000 Subject: broadcom: add include guards to include/linux/brcmphy.h include/linux/brcmphy.h is currently not protected against double inclusion, add ifdefs guard to fix that. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/brcmphy.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index b840a4960282..677b4f01b2d0 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -1,3 +1,6 @@ +#ifndef _LINUX_BRCMPHY_H +#define _LINUX_BRCMPHY_H + #define PHY_ID_BCM50610 0x0143bd60 #define PHY_ID_BCM50610M 0x0143bd70 #define PHY_ID_BCM5241 0x0143bc30 @@ -29,3 +32,5 @@ #define PHY_BRCM_CLEAR_RGMII_MODE 0x00004000 #define PHY_BRCM_DIS_TXCRXC_NOENRGY 0x00008000 #define PHY_BCM_FLAGS_VALID 0x80000000 + +#endif /* _LINUX_BRCMPHY_H */ -- cgit v1.2.3 From f6b3d85f7f6d66f890862d763b2ed092c5dd4322 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Fri, 3 May 2013 10:01:03 +0200 Subject: mac80211: fix spurious RCU warning and update documentation Document rx vs tx status concurrency requirements. Signed-off-by: Felix Fietkau Signed-off-by: Johannes Berg --- include/net/mac80211.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 04c2d4670dc6..885898a40d13 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -3043,7 +3043,8 @@ void ieee80211_napi_complete(struct ieee80211_hw *hw); * This function may not be called in IRQ context. Calls to this function * for a single hardware must be synchronized against each other. Calls to * this function, ieee80211_rx_ni() and ieee80211_rx_irqsafe() may not be - * mixed for a single hardware. + * mixed for a single hardware. Must not run concurrently with + * ieee80211_tx_status() or ieee80211_tx_status_ni(). * * In process context use instead ieee80211_rx_ni(). * @@ -3059,7 +3060,8 @@ void ieee80211_rx(struct ieee80211_hw *hw, struct sk_buff *skb); * (internally defers to a tasklet.) * * Calls to this function, ieee80211_rx() or ieee80211_rx_ni() may not - * be mixed for a single hardware. + * be mixed for a single hardware.Must not run concurrently with + * ieee80211_tx_status() or ieee80211_tx_status_ni(). * * @hw: the hardware this frame came in on * @skb: the buffer to receive, owned by mac80211 after this call @@ -3073,7 +3075,8 @@ void ieee80211_rx_irqsafe(struct ieee80211_hw *hw, struct sk_buff *skb); * (internally disables bottom halves). * * Calls to this function, ieee80211_rx() and ieee80211_rx_irqsafe() may - * not be mixed for a single hardware. + * not be mixed for a single hardware. Must not run concurrently with + * ieee80211_tx_status() or ieee80211_tx_status_ni(). * * @hw: the hardware this frame came in on * @skb: the buffer to receive, owned by mac80211 after this call @@ -3196,7 +3199,8 @@ void ieee80211_get_tx_rates(struct ieee80211_vif *vif, * This function may not be called in IRQ context. Calls to this function * for a single hardware must be synchronized against each other. Calls * to this function, ieee80211_tx_status_ni() and ieee80211_tx_status_irqsafe() - * may not be mixed for a single hardware. + * may not be mixed for a single hardware. Must not run concurrently with + * ieee80211_rx() or ieee80211_rx_ni(). * * @hw: the hardware the frame was transmitted by * @skb: the frame that was transmitted, owned by mac80211 after this call -- cgit v1.2.3 From b0ce3508b25ea6fa10ae3ca254de1d695b521702 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 16 May 2013 07:34:53 +0000 Subject: bonding: allow TSO being set on bonding master MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In some situations, we need to disable TSO on bonding slaves. bonding device automatically unset TSO in bond_fix_features(), and performance is not good because : 1) We consume more cpu cycles. 2) GSO segmentation has some bugs leading to out of order TCP packets if this segmentation is done before virtual device. This particular problem will be addressed in a separate patch. This patch allows TSO being set/unset on the bonding master, so that GSO segmentation is done after bonding layer. Signed-off-by: Eric Dumazet Cc: Michał Mirosław Cc: Jay Vosburgh Cc: Andy Gospodarek Cc: Maciej Żenczykowski Cc: Tom Herbert Cc: Neal Cardwell Cc: Yuchung Cheng Signed-off-by: David S. Miller --- include/linux/netdevice.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index a94a5a0ab122..60584b185a0c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2733,6 +2733,17 @@ static inline netdev_features_t netdev_get_wanted_features( } netdev_features_t netdev_increment_features(netdev_features_t all, netdev_features_t one, netdev_features_t mask); + +/* Allow TSO being used on stacked device : + * Performing the GSO segmentation before last device + * is a performance improvement. + */ +static inline netdev_features_t netdev_add_tso_features(netdev_features_t features, + netdev_features_t mask) +{ + return netdev_increment_features(features, NETIF_F_ALL_TSO, mask); +} + int __netdev_update_features(struct net_device *dev); void netdev_update_features(struct net_device *dev); void netdev_change_features(struct net_device *dev); -- cgit v1.2.3 From 0b8ebdb18888c55588b932f4f564b9c9529de627 Mon Sep 17 00:00:00 2001 From: Fabio Baltieri Date: Thu, 9 May 2013 13:08:08 +0200 Subject: mfd: ab8500-sysctrl: Always enable pm_power_off handler AB8500 sysctrl driver implements a pm_power_off handler, but that is currently not registered until a specific platform data field is enabled. This patch drops the platform data field and always registers ab8500_power_off if no other pm_power_off handler was defined before, and also introduces the necessary cleanup code in the driver's remove function. Acked-by: Linus Walleij Signed-off-by: Fabio Baltieri Signed-off-by: Lee Jones Signed-off-by: Samuel Ortiz --- include/linux/mfd/abx500/ab8500.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/mfd/abx500/ab8500.h b/include/linux/mfd/abx500/ab8500.h index fb1bf7d6a410..0390d5943ed6 100644 --- a/include/linux/mfd/abx500/ab8500.h +++ b/include/linux/mfd/abx500/ab8500.h @@ -373,13 +373,11 @@ struct ab8500_sysctrl_platform_data; /** * struct ab8500_platform_data - AB8500 platform data * @irq_base: start of AB8500 IRQs, AB8500_NR_IRQS will be used - * @pm_power_off: Should machine pm power off hook be registered or not * @init: board-specific initialization after detection of ab8500 * @regulator: machine-specific constraints for regulators */ struct ab8500_platform_data { int irq_base; - bool pm_power_off; void (*init) (struct ab8500 *); struct ab8500_regulator_platform_data *regulator; struct abx500_gpio_platform_data *gpio; -- cgit v1.2.3 From 0693196fe7bbb5e6cafd255dfce91ff6d10bc18f Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Sun, 5 May 2013 20:32:27 +0200 Subject: USB: serial: add wait_until_sent operation Add wait_until_sent operation which can be used to wait for hardware buffers to drain. Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/serial.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h index b9b0f7b4e43b..afbb7eeaac5f 100644 --- a/include/linux/usb/serial.h +++ b/include/linux/usb/serial.h @@ -268,6 +268,7 @@ struct usb_serial_driver { struct usb_serial_port *port, struct ktermios *old); void (*break_ctl)(struct tty_struct *tty, int break_state); int (*chars_in_buffer)(struct tty_struct *tty); + void (*wait_until_sent)(struct tty_struct *tty, long timeout); void (*throttle)(struct tty_struct *tty); void (*unthrottle)(struct tty_struct *tty); int (*tiocmget)(struct tty_struct *tty); -- cgit v1.2.3 From dcf0105039660e951dfea348d317043d17988dfc Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 8 May 2013 17:51:43 +0200 Subject: USB: serial: add generic wait_until_sent implementation Add generic wait_until_sent implementation which polls for empty hardware buffers using the new port-operation tx_empty. The generic implementation will be used for all sub-drivers that implement tx_empty but does not define wait_until_sent. Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/serial.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h index afbb7eeaac5f..302ddf55d2da 100644 --- a/include/linux/usb/serial.h +++ b/include/linux/usb/serial.h @@ -269,6 +269,7 @@ struct usb_serial_driver { void (*break_ctl)(struct tty_struct *tty, int break_state); int (*chars_in_buffer)(struct tty_struct *tty); void (*wait_until_sent)(struct tty_struct *tty, long timeout); + bool (*tx_empty)(struct usb_serial_port *port); void (*throttle)(struct tty_struct *tty); void (*unthrottle)(struct tty_struct *tty); int (*tiocmget)(struct tty_struct *tty); @@ -328,6 +329,8 @@ extern void usb_serial_generic_close(struct usb_serial_port *port); extern int usb_serial_generic_resume(struct usb_serial *serial); extern int usb_serial_generic_write_room(struct tty_struct *tty); extern int usb_serial_generic_chars_in_buffer(struct tty_struct *tty); +extern void usb_serial_generic_wait_until_sent(struct tty_struct *tty, + long timeout); extern void usb_serial_generic_read_bulk_callback(struct urb *urb); extern void usb_serial_generic_write_bulk_callback(struct urb *urb); extern void usb_serial_generic_throttle(struct tty_struct *tty); -- cgit v1.2.3 From d4988d4c733ba0b61cb372edd3d1992d26dd10d3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Thu, 9 May 2013 21:24:24 +0200 Subject: bcma: add more core IDs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit PCIe and ARM CR4 cores were found on 14e4:43b1 AKA BCM4352. Reported-by: Gabriel Thörnblad Signed-off-by: Rafał Miłecki Signed-off-by: John W. Linville --- include/linux/bcma/bcma.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h index f14a98a79c9d..2e34db82a643 100644 --- a/include/linux/bcma/bcma.h +++ b/include/linux/bcma/bcma.h @@ -134,7 +134,10 @@ struct bcma_host_ops { #define BCMA_CORE_I2S 0x834 #define BCMA_CORE_SDR_DDR1_MEM_CTL 0x835 /* SDR/DDR1 memory controller core */ #define BCMA_CORE_SHIM 0x837 /* SHIM component in ubus/6362 */ -#define BCMA_CORE_ARM_CR4 0x83e +#define BCMA_CORE_PHY_AC 0x83B +#define BCMA_CORE_PCIE2 0x83C /* PCI Express Gen2 */ +#define BCMA_CORE_USB30_DEV 0x83D +#define BCMA_CORE_ARM_CR4 0x83E #define BCMA_CORE_DEFAULT 0xFFF #define BCMA_MAX_NR_CORES 16 -- cgit v1.2.3 From 3f327e39b4b8f760c331bb2836735be6d83fbf53 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Tue, 7 May 2013 11:06:03 -0600 Subject: PCI: acpiphp: Re-enumerate devices when host bridge receives Bus Check When a PCI host bridge device receives a Bus Check notification, we must re-enumerate starting with the bridge to discover changes (devices that have been added or removed). Prior to 668192b678 ("PCI: acpiphp: Move host bridge hotplug to pci_root.c"), this happened in _handle_hotplug_event_bridge(). After that commit, _handle_hotplug_event_bridge() is not installed for host bridges, and the host bridge notify handler, _handle_hotplug_event_root() did not re-enumerate. This patch adds re-enumeration to _handle_hotplug_event_root(). This fixes cases where we don't notice the addition or removal of PCI devices, e.g., the PCI-to-USB ExpressCard in the bugzilla below. [bhelgaas: changelog, references] Reference: https://lkml.kernel.org/r/CAAh6nkmbKR3HTqm5ommevsBwhL_u0N8Rk7Wsms_LfP=nBgKNew@mail.gmail.com Reference: https://bugzilla.kernel.org/show_bug.cgi?id=57961 Reported-by: Gavin Guo Tested-by: Gavin Guo Signed-off-by: Yinghai Lu Signed-off-by: Bjorn Helgaas Reviewed-by: Jiang Liu Acked-by: Rafael J. Wysocki CC: stable@vger.kernel.org # v3.9+ --- include/linux/pci-acpi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/pci-acpi.h b/include/linux/pci-acpi.h index 81b31613eb25..170447977278 100644 --- a/include/linux/pci-acpi.h +++ b/include/linux/pci-acpi.h @@ -60,11 +60,13 @@ static inline void acpi_pci_slot_remove(struct pci_bus *bus) { } void acpiphp_init(void); void acpiphp_enumerate_slots(struct pci_bus *bus, acpi_handle handle); void acpiphp_remove_slots(struct pci_bus *bus); +void acpiphp_check_host_bridge(acpi_handle handle); #else static inline void acpiphp_init(void) { } static inline void acpiphp_enumerate_slots(struct pci_bus *bus, acpi_handle handle) { } static inline void acpiphp_remove_slots(struct pci_bus *bus) { } +static inline void acpiphp_check_host_bridge(acpi_handle handle) { } #endif #else /* CONFIG_ACPI */ -- cgit v1.2.3 From 7f18d05a1af75142d4856a91ffd2f1d8eb553c12 Mon Sep 17 00:00:00 2001 From: Santosh Shilimkar Date: Wed, 15 May 2013 20:18:41 +0530 Subject: SERIAL: OMAP: Remove the slave idle handling from the driver UART IP slave idle handling now taken care by runtime pm backend(hwmod layer) so remove the hackery from the driver. As discussed on the list, in future if dma mode needs to be brought back to this driver, UART sysc handling needs to be updated in framework such a way that no-idle/force idle profile can be supported. Given the broken dma mode for OMAP uarts, its very unlikely. Acked-by: Greg Kroah-Hartman Tested-by: Vaibhav Bedia Tested-by: Sourav Poddar Signed-off-by: Rajendra nayak Signed-off-by: Santosh Shilimkar Reviewed-by: Kevin Hilman Tested-by: Kevin Hilman # OMAP4/Panda Signed-off-by: Paul Walmsley --- include/linux/platform_data/serial-omap.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/platform_data/serial-omap.h b/include/linux/platform_data/serial-omap.h index ff9b0aab5281..c860c1b314c0 100644 --- a/include/linux/platform_data/serial-omap.h +++ b/include/linux/platform_data/serial-omap.h @@ -43,8 +43,6 @@ struct omap_uart_port_info { int DTR_present; int (*get_context_loss_count)(struct device *); - void (*set_forceidle)(struct device *); - void (*set_noidle)(struct device *); void (*enable_wakeup)(struct device *, bool); }; -- cgit v1.2.3 From d2f83e9078b8114e3b9d09082856c1aac299aa37 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Fri, 17 May 2013 09:05:21 +0930 Subject: Hoist memcpy_fromiovec/memcpy_toiovec into lib/ ERROR: "memcpy_fromiovec" [drivers/vhost/vhost_scsi.ko] undefined! That function is only present with CONFIG_NET. Turns out that crypto/algif_skcipher.c also uses that outside net, but it actually needs sockets anyway. In addition, commit 6d4f0139d642c45411a47879325891ce2a7c164a added CONFIG_NET dependency to CONFIG_VMCI for memcpy_toiovec, so hoist that function and revert that commit too. socket.h already includes uio.h, so no callers need updating; trying only broke things fo x86_64 randconfig (thanks Fengguang!). Reported-by: Randy Dunlap Acked-by: David S. Miller Acked-by: Michael S. Tsirkin Signed-off-by: Rusty Russell --- include/linux/socket.h | 2 -- include/linux/uio.h | 3 +++ 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/socket.h b/include/linux/socket.h index 428c37a1f95c..33bf2dfab19d 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -305,7 +305,6 @@ struct ucred { extern void cred_to_ucred(struct pid *pid, const struct cred *cred, struct ucred *ucred); -extern int memcpy_fromiovec(unsigned char *kdata, struct iovec *iov, int len); extern int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov, int offset, int len); extern int csum_partial_copy_fromiovecend(unsigned char *kdata, @@ -314,7 +313,6 @@ extern int csum_partial_copy_fromiovecend(unsigned char *kdata, unsigned int len, __wsum *csump); extern int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr_storage *address, int mode); -extern int memcpy_toiovec(struct iovec *v, unsigned char *kdata, int len); extern int memcpy_toiovecend(const struct iovec *v, unsigned char *kdata, int offset, int len); extern int move_addr_to_kernel(void __user *uaddr, int ulen, struct sockaddr_storage *kaddr); diff --git a/include/linux/uio.h b/include/linux/uio.h index 629aaf51f30b..c55ce243cc09 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -35,4 +35,7 @@ static inline size_t iov_length(const struct iovec *iov, unsigned long nr_segs) } unsigned long iov_shorten(struct iovec *iov, unsigned long nr_segs, size_t to); + +int memcpy_fromiovec(unsigned char *kdata, struct iovec *iov, int len); +int memcpy_toiovec(struct iovec *iov, unsigned char *kdata, int len); #endif -- cgit v1.2.3 From 6407d75afd08545f2252bb39806ffd3f10c7faac Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 17 May 2013 10:44:15 +0930 Subject: virtio_console: fix uapi header uapi should use __u32 not u32. Fix a macro in virtio_console.h which uses u32. Signed-off-by: Michael S. Tsirkin Signed-off-by: Rusty Russell Cc: stable@kernel.org --- include/uapi/linux/virtio_console.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/virtio_console.h b/include/uapi/linux/virtio_console.h index ee13ab6c3614..c312f16bc4e7 100644 --- a/include/uapi/linux/virtio_console.h +++ b/include/uapi/linux/virtio_console.h @@ -39,7 +39,7 @@ #define VIRTIO_CONSOLE_F_SIZE 0 /* Does host provide console size? */ #define VIRTIO_CONSOLE_F_MULTIPORT 1 /* Does host provide multiple ports? */ -#define VIRTIO_CONSOLE_BAD_ID (~(u32)0) +#define VIRTIO_CONSOLE_BAD_ID (~(__u32)0) struct virtio_console_config { /* colums of the screens */ -- cgit v1.2.3 From 2a0f90551a76a626fd6a606877c8635f52f066e6 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Fri, 27 Jul 2012 18:48:52 -0400 Subject: drm/radeon: add Hainan pci ids MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Alex Deucher Reviewed-by: Christian König --- include/drm/drm_pciids.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h index c2af598f701d..bb1bc485390b 100644 --- a/include/drm/drm_pciids.h +++ b/include/drm/drm_pciids.h @@ -152,6 +152,12 @@ {0x1002, 0x6621, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6623, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6631, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6660, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_HAINAN|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6663, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_HAINAN|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6664, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_HAINAN|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6665, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_HAINAN|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6667, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_HAINAN|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x666F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_HAINAN|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6700, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAYMAN|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6701, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAYMAN|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6702, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAYMAN|RADEON_NEW_MEMMAP}, \ -- cgit v1.2.3 From 421b40a6286ee343d77d5e51f5ee6d04d7a2a90f Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Fri, 17 May 2013 12:41:03 -0400 Subject: tty/vt: Fix vc_deallocate() lock order Now that the tty port owns the flip buffers and i/o is allowed from the driver even when no tty is attached, the destruction of the tty port (and the flip buffers) must ensure that no outstanding work is pending. Unfortunately, this creates a lock order problem with the console_lock (see attached lockdep report [1] below). For single console deallocation, drop the console_lock prior to port destruction. When multiple console deallocation, defer port destruction until the consoles have been deallocated. tty_port_destroy() is not required if the port has not been used; remove from vc_allocate() failure path. [1] lockdep report from Dave Jones ====================================================== [ INFO: possible circular locking dependency detected ] 3.9.0+ #16 Not tainted ------------------------------------------------------- (agetty)/26163 is trying to acquire lock: blocked: ((&buf->work)){+.+...}, instance: ffff88011c8b0020, at: [] flush_work+0x5/0x2e0 but task is already holding lock: blocked: (console_lock){+.+.+.}, instance: ffffffff81c2fde0, at: [] vt_ioctl+0xb61/0x1230 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (console_lock){+.+.+.}: [] lock_acquire+0xa4/0x210 [] console_lock+0x77/0x80 [] con_flush_chars+0x2d/0x50 [] n_tty_receive_buf+0x122/0x14d0 [] flush_to_ldisc+0x119/0x170 [] process_one_work+0x211/0x700 [] worker_thread+0x11b/0x3a0 [] kthread+0xed/0x100 [] ret_from_fork+0x7c/0xb0 -> #0 ((&buf->work)){+.+...}: [] __lock_acquire+0x193a/0x1c00 [] lock_acquire+0xa4/0x210 [] flush_work+0x4e/0x2e0 [] __cancel_work_timer+0x95/0x130 [] cancel_work_sync+0x10/0x20 [] tty_port_destroy+0x12/0x20 [] vc_deallocate+0xf8/0x110 [] vt_ioctl+0xb6c/0x1230 [] tty_ioctl+0x285/0xd50 [] do_vfs_ioctl+0x305/0x530 [] sys_ioctl+0x81/0xa0 [] system_call_fastpath+0x16/0x1b other info that might help us debug this: [ 6760.076175] Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(console_lock); lock((&buf->work)); lock(console_lock); lock((&buf->work)); *** DEADLOCK *** 1 lock on stack by (agetty)/26163: #0: blocked: (console_lock){+.+.+.}, instance: ffffffff81c2fde0, at: [] vt_ioctl+0xb61/0x1230 stack backtrace: Pid: 26163, comm: (agetty) Not tainted 3.9.0+ #16 Call Trace: [] print_circular_bug+0x200/0x20e [] __lock_acquire+0x193a/0x1c00 [] ? sched_clock+0x9/0x10 [] ? sched_clock+0x9/0x10 [] ? native_sched_clock+0x20/0x80 [] lock_acquire+0xa4/0x210 [] ? flush_work+0x5/0x2e0 [] flush_work+0x4e/0x2e0 [] ? flush_work+0x5/0x2e0 [] ? mark_held_locks+0xbb/0x140 [] ? __free_pages_ok.part.57+0x93/0xc0 [] ? mark_held_locks+0xbb/0x140 [] ? __cancel_work_timer+0x82/0x130 [] __cancel_work_timer+0x95/0x130 [] cancel_work_sync+0x10/0x20 [] tty_port_destroy+0x12/0x20 [] vc_deallocate+0xf8/0x110 [] vt_ioctl+0xb6c/0x1230 [] ? lock_release_holdtime.part.30+0xa1/0x170 [] tty_ioctl+0x285/0xd50 [] ? inode_has_perm.isra.46.constprop.61+0x56/0x80 [] do_vfs_ioctl+0x305/0x530 [] ? selinux_file_ioctl+0x5b/0x110 [] sys_ioctl+0x81/0xa0 [] system_call_fastpath+0x16/0x1b Cc: Dave Jones Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/vt_kern.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/vt_kern.h b/include/linux/vt_kern.h index e8d65718560b..0d33fca48774 100644 --- a/include/linux/vt_kern.h +++ b/include/linux/vt_kern.h @@ -36,7 +36,7 @@ extern int fg_console, last_console, want_console; int vc_allocate(unsigned int console); int vc_cons_allocated(unsigned int console); int vc_resize(struct vc_data *vc, unsigned int cols, unsigned int lines); -void vc_deallocate(unsigned int console); +struct vc_data *vc_deallocate(unsigned int console); void reset_palette(struct vc_data *vc); void do_blank_screen(int entering_gfx); void do_unblank_screen(int leaving_gfx); -- cgit v1.2.3 From ec4602a9588a196fa1a9af46bfdd37cbf5792db4 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 16 May 2013 22:29:28 +0200 Subject: ACPI / PM: Allow device power states to be used for CONFIG_PM unset Currently, drivers/acpi/device_pm.c depends on CONFIG_PM and all of the functions defined in there are replaced with static inline stubs if that option is unset. However, CONFIG_PM means, roughly, "runtime PM or suspend/hibernation support" and some of those functions are useful regardless of that. For example, they are used by the ACPI fan driver for controlling fans and acpi_device_set_power() is called during device removal. Moreover, device initialization may depend on setting device power states properly. For these reasons, make the routines manipulating ACPI device power states defined in drivers/acpi/device_pm.c available for CONFIG_PM unset too. Reported-by: Zhang Rui Reported-and-tested-by: Michel Lespinasse Signed-off-by: Rafael J. Wysocki Cc: 3.9+ --- include/acpi/acpi_bus.h | 40 +++++----------------------------------- 1 file changed, 5 insertions(+), 35 deletions(-) (limited to 'include') diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index 98db31d9f9b4..636c59f2003a 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -377,7 +377,6 @@ acpi_status acpi_bus_get_status_handle(acpi_handle handle, unsigned long long *sta); int acpi_bus_get_status(struct acpi_device *device); -#ifdef CONFIG_PM int acpi_bus_set_power(acpi_handle handle, int state); const char *acpi_power_state_string(int state); int acpi_device_get_power(struct acpi_device *device, int *state); @@ -385,41 +384,12 @@ int acpi_device_set_power(struct acpi_device *device, int state); int acpi_bus_init_power(struct acpi_device *device); int acpi_bus_update_power(acpi_handle handle, int *state_p); bool acpi_bus_power_manageable(acpi_handle handle); + +#ifdef CONFIG_PM bool acpi_bus_can_wakeup(acpi_handle handle); -#else /* !CONFIG_PM */ -static inline int acpi_bus_set_power(acpi_handle handle, int state) -{ - return 0; -} -static inline const char *acpi_power_state_string(int state) -{ - return "D0"; -} -static inline int acpi_device_get_power(struct acpi_device *device, int *state) -{ - return 0; -} -static inline int acpi_device_set_power(struct acpi_device *device, int state) -{ - return 0; -} -static inline int acpi_bus_init_power(struct acpi_device *device) -{ - return 0; -} -static inline int acpi_bus_update_power(acpi_handle handle, int *state_p) -{ - return 0; -} -static inline bool acpi_bus_power_manageable(acpi_handle handle) -{ - return false; -} -static inline bool acpi_bus_can_wakeup(acpi_handle handle) -{ - return false; -} -#endif /* !CONFIG_PM */ +#else +static inline bool acpi_bus_can_wakeup(acpi_handle handle) { return false; } +#endif #ifdef CONFIG_ACPI_PROC_EVENT int acpi_bus_generate_proc_event(struct acpi_device *device, u8 type, int data); -- cgit v1.2.3 From 154c2670087bd7f54688274aca627433e4a7c181 Mon Sep 17 00:00:00 2001 From: Ralf Baechle Date: Tue, 21 May 2013 10:51:10 +0200 Subject: Add include dependencies to . MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If has not been included before , a build error like the below one will result: CC arch/mips/kernel/idle.o In file included from arch/mips/kernel/idle.c:17:0: include/linux/printk.h:109:1: error: data definition has no type or storage class [-Werror] include/linux/printk.h:109:1: error: type defaults to ‘int’ in declaration of ‘asmlinkage’ [-Werror=implicit-int] include/linux/printk.h:110:1: error: ‘format’ attribute only applies to function types [-Werror=attributes] include/linux/printk.h:110:1: error: expected ‘,’ or ‘;’ before ‘int’ include/linux/printk.h:114:1: error: data definition has no type or storage class [-Werror] include/linux/printk.h:114:1: error: type defaults to ‘int’ in declaration of ‘asmlinkage’ [-Werror=implicit-int] include/linux/printk.h:115:1: error: ‘format’ attribute only applies to function types [-Werror=attributes] include/linux/printk.h:115:1: error: expected ‘,’ or ‘;’ before ‘int’ include/linux/printk.h:117:1: error: data definition has no type or storage class [-Werror] include/linux/printk.h:117:1: error: type defaults to ‘int’ in declaration of ‘asmlinkage’ [-Werror=implicit-int] include/linux/printk.h:118:1: error: ‘format’ attribute only applies to function types [-Werror=attributes] include/linux/printk.h:118:1: error: ‘__cold__’ attribute ignored [-Werror=attributes] include/linux/printk.h:118:1: error: expected ‘,’ or ‘;’ before ‘asmlinkage’ include/linux/printk.h:122:1: error: data definition has no type or storage class [-Werror] include/linux/printk.h:122:1: error: type defaults to ‘int’ in declaration of ‘asmlinkage’ [-Werror=implicit-int] include/linux/printk.h:123:1: error: ‘format’ attribute only applies to function types [-Werror=attributes] include/linux/printk.h:123:1: error: ‘__cold__’ attribute ignored [-Werror=attributes] include/linux/printk.h:123:1: error: expected ‘,’ or ‘;’ before ‘int’ In file included from include/linux/kernel.h:14:0, from include/linux/sched.h:15, from arch/mips/kernel/idle.c:18: include/linux/dynamic_debug.h: In function ‘ddebug_dyndbg_module_param_cb’: include/linux/dynamic_debug.h:124:3: error: implicit declaration of function ‘printk’ [-Werror=implicit-function-declaration] Fixed by including . Signed-off-by: Ralf Baechle --- include/linux/printk.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/printk.h b/include/linux/printk.h index 6af944ab38f0..22c7052e9372 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -4,6 +4,7 @@ #include #include #include +#include extern const char linux_banner[]; extern const char linux_proc_banner[]; -- cgit v1.2.3 From a11650e11093ed57dca78bf16e7836517c599098 Mon Sep 17 00:00:00 2001 From: Alexandre Bounine Date: Fri, 24 May 2013 15:55:05 -0700 Subject: rapidio: make enumeration/discovery configurable Systems that use RapidIO fabric may need to implement their own enumeration and discovery methods which are better suitable for needs of a target application. The following set of patches is intended to simplify process of introduction of new RapidIO fabric enumeration/discovery methods. The first patch offers ability to add new RapidIO enumeration/discovery methods using kernel configuration options. This new configuration option mechanism allows to select statically linked or modular enumeration/discovery method(s) from the list of existing methods or use external module(s). This patch also updates the currently existing enumeration/discovery code to be used as a statically linked or modular method. The corresponding configuration option is named "Basic enumeration/discovery" method. This is the only one configuration option available today but new methods are expected to be introduced after adoption of provided patches. The second patch address a long time complaint of RapidIO subsystem users regarding fabric enumeration/discovery start sequence. Existing implementation offers only a boot-time enumeration/discovery start which requires synchronized boot of all endpoints in RapidIO network. While it works for small closed configurations with limited number of endpoints, using this approach in systems with large number of endpoints is quite challenging. To eliminate requirement for synchronized start the second patch introduces RapidIO enumeration/discovery start from user space. For compatibility with the existing RapidIO subsystem implementation, automatic boot time enumeration/discovery start can be configured in by specifying "rio-scan.scan=1" command line parameter if statically linked basic enumeration method is selected. This patch: Rework to implement RapidIO enumeration/discovery method selection combined with ability to use enumeration/discovery as a kernel module. This patch adds ability to introduce new RapidIO enumeration/discovery methods using kernel configuration options. Configuration option mechanism allows to select statically linked or modular enumeration/discovery method from the list of existing methods or use external modules. If a modular enumeration/discovery is selected each RapidIO mport device can have its own method attached to it. The existing enumeration/discovery code was updated to be used as statically linked or modular method. This configuration option is named "Basic enumeration/discovery" method. Several common routines have been moved from rio-scan.c to make them available to other enumeration methods and reduce number of exported symbols. Signed-off-by: Alexandre Bounine Cc: Matt Porter Cc: Li Yang Cc: Kumar Gala Cc: Andre van Herk Cc: Micha Nelissen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rio.h | 13 ++++++++++++- include/linux/rio_drv.h | 1 + 2 files changed, 13 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/rio.h b/include/linux/rio.h index a3e784278667..cd3796ee7410 100644 --- a/include/linux/rio.h +++ b/include/linux/rio.h @@ -83,7 +83,6 @@ extern struct bus_type rio_bus_type; extern struct device rio_bus; -extern struct list_head rio_devices; /* list of all devices */ struct rio_mport; struct rio_dev; @@ -237,6 +236,7 @@ enum rio_phy_type { * @name: Port name string * @priv: Master port private data * @dma: DMA device associated with mport + * @nscan: RapidIO network enumeration/discovery operations */ struct rio_mport { struct list_head dbells; /* list of doorbell events */ @@ -262,6 +262,7 @@ struct rio_mport { #ifdef CONFIG_RAPIDIO_DMA_ENGINE struct dma_device dma; #endif + struct rio_scan *nscan; }; struct rio_id_table { @@ -460,6 +461,16 @@ static inline struct rio_mport *dma_to_mport(struct dma_device *ddev) } #endif /* CONFIG_RAPIDIO_DMA_ENGINE */ +/** + * struct rio_scan - RIO enumeration and discovery operations + * @enumerate: Callback to perform RapidIO fabric enumeration. + * @discover: Callback to perform RapidIO fabric discovery. + */ +struct rio_scan { + int (*enumerate)(struct rio_mport *mport); + int (*discover)(struct rio_mport *mport); +}; + /* Architecture and hardware-specific functions */ extern int rio_register_mport(struct rio_mport *); extern int rio_open_inb_mbox(struct rio_mport *, void *, int, int); diff --git a/include/linux/rio_drv.h b/include/linux/rio_drv.h index b75c05920ab5..5059994fe297 100644 --- a/include/linux/rio_drv.h +++ b/include/linux/rio_drv.h @@ -433,5 +433,6 @@ extern u16 rio_local_get_device_id(struct rio_mport *port); extern struct rio_dev *rio_get_device(u16 vid, u16 did, struct rio_dev *from); extern struct rio_dev *rio_get_asm(u16 vid, u16 did, u16 asm_vid, u16 asm_did, struct rio_dev *from); +extern int rio_init_mports(void); #endif /* LINUX_RIO_DRV_H */ -- cgit v1.2.3 From bc8fcfea18249640f2728c46d70999dcb7e4dc49 Mon Sep 17 00:00:00 2001 From: Alexandre Bounine Date: Fri, 24 May 2013 15:55:06 -0700 Subject: rapidio: add enumeration/discovery start from user space Add RapidIO enumeration/discovery start from user space. User space start allows to defer RapidIO fabric scan until the moment when all participating endpoints are initialized avoiding mandatory synchronized start of all endpoints (which may be challenging in systems with large number of RapidIO endpoints). Signed-off-by: Alexandre Bounine Cc: Matt Porter Cc: Li Yang Cc: Kumar Gala Cc: Andre van Herk Cc: Micha Nelissen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rio.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/rio.h b/include/linux/rio.h index cd3796ee7410..18e099342e6f 100644 --- a/include/linux/rio.h +++ b/include/linux/rio.h @@ -265,6 +265,11 @@ struct rio_mport { struct rio_scan *nscan; }; +/* + * Enumeration/discovery control flags + */ +#define RIO_SCAN_ENUM_NO_WAIT 0x00000001 /* Do not wait for enum completed */ + struct rio_id_table { u16 start; /* logical minimal id */ u32 max; /* max number of IDs in table */ @@ -467,8 +472,8 @@ static inline struct rio_mport *dma_to_mport(struct dma_device *ddev) * @discover: Callback to perform RapidIO fabric discovery. */ struct rio_scan { - int (*enumerate)(struct rio_mport *mport); - int (*discover)(struct rio_mport *mport); + int (*enumerate)(struct rio_mport *mport, u32 flags); + int (*discover)(struct rio_mport *mport, u32 flags); }; /* Architecture and hardware-specific functions */ -- cgit v1.2.3 From 4c663cfc523a88d97a8309b04a089c27dc57fd7e Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Fri, 24 May 2013 15:55:09 -0700 Subject: wait: fix false timeouts when using wait_event_timeout() Many callers of the wait_event_timeout() and wait_event_interruptible_timeout() expect that the return value will be positive if the specified condition becomes true before the timeout elapses. However, at the moment this isn't guaranteed. If the wake-up handler is delayed enough, the time remaining until timeout will be calculated as 0 - and passed back as a return value - even if the condition became true before the timeout has passed. Fix this by returning at least 1 if the condition becomes true. This semantic is in line with what wait_for_condition_timeout() does; see commit bb10ed09 ("sched: fix wait_for_completion_timeout() spurious failure under heavy load"). Daniel said "We have 3 instances of this bug in drm/i915. One case even where we switch between the interruptible and not interruptible wait_event_timeout variants, foolishly presuming they have the same semantics. I very much like this." One such bug is reported at https://bugs.freedesktop.org/show_bug.cgi?id=64133 Signed-off-by: Imre Deak Acked-by: Daniel Vetter Acked-by: David Howells Acked-by: Jens Axboe Cc: "Paul E. McKenney" Cc: Dave Jones Cc: Lukas Czerner Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/wait.h | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/wait.h b/include/linux/wait.h index ac38be2692d8..1133695eb067 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -217,6 +217,8 @@ do { \ if (!ret) \ break; \ } \ + if (!ret && (condition)) \ + ret = 1; \ finish_wait(&wq, &__wait); \ } while (0) @@ -233,8 +235,9 @@ do { \ * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * - * The function returns 0 if the @timeout elapsed, and the remaining - * jiffies if the condition evaluated to true before the timeout elapsed. + * The function returns 0 if the @timeout elapsed, or the remaining + * jiffies (at least 1) if the @condition evaluated to %true before + * the @timeout elapsed. */ #define wait_event_timeout(wq, condition, timeout) \ ({ \ @@ -302,6 +305,8 @@ do { \ ret = -ERESTARTSYS; \ break; \ } \ + if (!ret && (condition)) \ + ret = 1; \ finish_wait(&wq, &__wait); \ } while (0) @@ -318,9 +323,10 @@ do { \ * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * - * The function returns 0 if the @timeout elapsed, -ERESTARTSYS if it - * was interrupted by a signal, and the remaining jiffies otherwise - * if the condition evaluated to true before the timeout elapsed. + * Returns: + * 0 if the @timeout elapsed, -%ERESTARTSYS if it was interrupted by + * a signal, or the remaining jiffies (at least 1) if the @condition + * evaluated to %true before the @timeout elapsed. */ #define wait_event_interruptible_timeout(wq, condition, timeout) \ ({ \ -- cgit v1.2.3 From 7450231fb35492951e78a91b833fd935171f4e66 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 24 May 2013 15:55:20 -0700 Subject: linux/kernel.h: fix kernel-doc warning Fix kernel-doc warning in : Warning(include/linux/kernel.h:590): No description found for parameter 'ip' scripts/kernel-doc cannot handle macros, functions, or function prototypes between the function or macro that is being documented and its definition, so move these prototypes above the function that is being documented. Signed-off-by: Randy Dunlap Cc: Steven Rostedt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index e96329ceb28c..e9ef6d6b51d5 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -562,6 +562,9 @@ int __trace_bprintk(unsigned long ip, const char *fmt, ...); extern __printf(2, 3) int __trace_printk(unsigned long ip, const char *fmt, ...); +extern int __trace_bputs(unsigned long ip, const char *str); +extern int __trace_puts(unsigned long ip, const char *str, int size); + /** * trace_puts - write a string into the ftrace buffer * @str: the string to record @@ -587,8 +590,6 @@ int __trace_printk(unsigned long ip, const char *fmt, ...); * (1 when __trace_bputs is used, strlen(str) when __trace_puts is used) */ -extern int __trace_bputs(unsigned long ip, const char *str); -extern int __trace_puts(unsigned long ip, const char *str, int size); #define trace_puts(str) ({ \ static const char *trace_printk_fmt \ __attribute__((section("__trace_printk_fmt"))) = \ -- cgit v1.2.3 From 29bb9e5a75684106a37593ad75ec75ff8312731b Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 24 May 2013 15:23:40 -0400 Subject: tracing/context-tracking: Add preempt_schedule_context() for tracing Dave Jones hit the following bug report: =============================== [ INFO: suspicious RCU usage. ] 3.10.0-rc2+ #1 Not tainted ------------------------------- include/linux/rcupdate.h:771 rcu_read_lock() used illegally while idle! other info that might help us debug this: RCU used illegally from idle CPU! rcu_scheduler_active = 1, debug_locks = 0 RCU used illegally from extended quiescent state! 2 locks held by cc1/63645: #0: (&rq->lock){-.-.-.}, at: [] __schedule+0xed/0x9b0 #1: (rcu_read_lock){.+.+..}, at: [] cpuacct_charge+0x5/0x1f0 CPU: 1 PID: 63645 Comm: cc1 Not tainted 3.10.0-rc2+ #1 [loadavg: 40.57 27.55 13.39 25/277 64369] Hardware name: Gigabyte Technology Co., Ltd. GA-MA78GM-S2H/GA-MA78GM-S2H, BIOS F12a 04/23/2010 0000000000000000 ffff88010f78fcf8 ffffffff816ae383 ffff88010f78fd28 ffffffff810b698d ffff88011c092548 000000000023d073 ffff88011c092500 0000000000000001 ffff88010f78fd60 ffffffff8109d7c5 ffffffff8109d645 Call Trace: [] dump_stack+0x19/0x1b [] lockdep_rcu_suspicious+0xfd/0x130 [] cpuacct_charge+0x185/0x1f0 [] ? cpuacct_charge+0x5/0x1f0 [] update_curr+0xec/0x240 [] put_prev_task_fair+0x228/0x480 [] __schedule+0x161/0x9b0 [] preempt_schedule+0x51/0x80 [] ? __cond_resched_softirq+0x60/0x60 [] ? retint_careful+0x12/0x2e [] ftrace_ops_control_func+0x1dc/0x210 [] ftrace_call+0x5/0x2f [] ? retint_careful+0xb/0x2e [] ? schedule_user+0x5/0x70 [] ? schedule_user+0x5/0x70 [] ? retint_careful+0x12/0x2e ------------[ cut here ]------------ What happened was that the function tracer traced the schedule_user() code that tells RCU that the system is coming back from userspace, and to add the CPU back to the RCU monitoring. Because the function tracer does a preempt_disable/enable_notrace() calls the preempt_enable_notrace() checks the NEED_RESCHED flag. If it is set, then preempt_schedule() is called. But this is called before the user_exit() function can inform the kernel that the CPU is no longer in user mode and needs to be accounted for by RCU. The fix is to create a new preempt_schedule_context() that checks if the kernel is still in user mode and if so to switch it to kernel mode before calling schedule. It also switches back to user mode coming back from schedule in need be. The only user of this currently is the preempt_enable_notrace(), which is only used by the tracing subsystem. Signed-off-by: Steven Rostedt Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1369423420.6828.226.camel@gandalf.local.home Signed-off-by: Ingo Molnar --- include/linux/preempt.h | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/preempt.h b/include/linux/preempt.h index 87a03c746f17..f5d4723cdb3d 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -33,9 +33,25 @@ do { \ preempt_schedule(); \ } while (0) +#ifdef CONFIG_CONTEXT_TRACKING + +void preempt_schedule_context(void); + +#define preempt_check_resched_context() \ +do { \ + if (unlikely(test_thread_flag(TIF_NEED_RESCHED))) \ + preempt_schedule_context(); \ +} while (0) +#else + +#define preempt_check_resched_context() preempt_check_resched() + +#endif /* CONFIG_CONTEXT_TRACKING */ + #else /* !CONFIG_PREEMPT */ #define preempt_check_resched() do { } while (0) +#define preempt_check_resched_context() do { } while (0) #endif /* CONFIG_PREEMPT */ @@ -88,7 +104,7 @@ do { \ do { \ preempt_enable_no_resched_notrace(); \ barrier(); \ - preempt_check_resched(); \ + preempt_check_resched_context(); \ } while (0) #else /* !CONFIG_PREEMPT_COUNT */ -- cgit v1.2.3