From 07a723097cd31e9c2def69ac4d42834a16f79219 Mon Sep 17 00:00:00 2001 From: Clemens Ladisch Date: Mon, 31 Oct 2011 17:06:28 -0700 Subject: dma-mapping: fix sync_single_range_* DMA debugging Commit 5fd75a7850b5 (dma-mapping: remove unnecessary sync_single_range_* in dma_map_ops) unified not only the dma_map_ops but also the corresponding debug_dma_sync_* calls. This led to spurious WARN()ings like the following because the DMA debug code was no longer able to detect the DMA buffer base address without the separate offset parameter: WARNING: at lib/dma-debug.c:911 check_sync+0xce/0x446() firewire_ohci 0000:04:00.0: DMA-API: device driver tries to sync DMA memory it has not allocated [device address=0x00000000cedaa400] [size=1024 bytes] Call Trace: ... [] check_sync+0xce/0x446 [] debug_dma_sync_single_for_device+0x39/0x3b [] ohci_queue_iso+0x4f3/0x77d [firewire_ohci] ... To fix this, unshare the sync_single_* and sync_single_range_* implementations so that we are able to call the correct debug_dma_sync_* functions. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Clemens Ladisch Cc: FUJITA Tomonori Cc: Konrad Rzeszutek Wilk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/dma-mapping-common.h | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/asm-generic/dma-mapping-common.h b/include/asm-generic/dma-mapping-common.h index 0c80bb38773..9fa3f96e38c 100644 --- a/include/asm-generic/dma-mapping-common.h +++ b/include/asm-generic/dma-mapping-common.h @@ -123,7 +123,12 @@ static inline void dma_sync_single_range_for_cpu(struct device *dev, size_t size, enum dma_data_direction dir) { - dma_sync_single_for_cpu(dev, addr + offset, size, dir); + const struct dma_map_ops *ops = get_dma_ops(dev); + + BUG_ON(!valid_dma_direction(dir)); + if (ops->sync_single_for_cpu) + ops->sync_single_for_cpu(dev, addr + offset, size, dir); + debug_dma_sync_single_range_for_cpu(dev, addr, offset, size, dir); } static inline void dma_sync_single_range_for_device(struct device *dev, @@ -132,7 +137,12 @@ static inline void dma_sync_single_range_for_device(struct device *dev, size_t size, enum dma_data_direction dir) { - dma_sync_single_for_device(dev, addr + offset, size, dir); + const struct dma_map_ops *ops = get_dma_ops(dev); + + BUG_ON(!valid_dma_direction(dir)); + if (ops->sync_single_for_device) + ops->sync_single_for_device(dev, addr + offset, size, dir); + debug_dma_sync_single_range_for_device(dev, addr, offset, size, dir); } static inline void -- cgit v1.2.3 From 6eea69dd8befeabd3d0f217400f54b157dd91fe9 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Mon, 31 Oct 2011 17:06:29 -0700 Subject: include/linux/dmar.h: forward-declare struct acpi_dmar_header x86_64 allnoconfig: In file included from arch/x86/kernel/pci-dma.c:3: include/linux/dmar.h:248: warning: 'struct acpi_dmar_header' declared inside parameter list include/linux/dmar.h:248: warning: its scope is only this definition or declaration, which is probably not what you want Cc: Suresh Siddha Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/dmar.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/dmar.h b/include/linux/dmar.h index a8b1a847c10..731a6097510 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -26,6 +26,8 @@ #include #include +struct acpi_dmar_header; + /* DMAR Flags */ #define DMAR_INTR_REMAP 0x1 #define DMAR_X2APIC_OPT_OUT 0x2 -- cgit v1.2.3 From fcf634098c00dd9cd247447368495f0b79be12d1 Mon Sep 17 00:00:00 2001 From: Christopher Yeoh Date: Mon, 31 Oct 2011 17:06:39 -0700 Subject: Cross Memory Attach The basic idea behind cross memory attach is to allow MPI programs doing intra-node communication to do a single copy of the message rather than a double copy of the message via shared memory. The following patch attempts to achieve this by allowing a destination process, given an address and size from a source process, to copy memory directly from the source process into its own address space via a system call. There is also a symmetrical ability to copy from the current process's address space into a destination process's address space. - Use of /proc/pid/mem has been considered, but there are issues with using it: - Does not allow for specifying iovecs for both src and dest, assuming preadv or pwritev was implemented either the area read from or written to would need to be contiguous. - Currently mem_read allows only processes who are currently ptrace'ing the target and are still able to ptrace the target to read from the target. This check could possibly be moved to the open call, but its not clear exactly what race this restriction is stopping (reason appears to have been lost) - Having to send the fd of /proc/self/mem via SCM_RIGHTS on unix domain socket is a bit ugly from a userspace point of view, especially when you may have hundreds if not (eventually) thousands of processes that all need to do this with each other - Doesn't allow for some future use of the interface we would like to consider adding in the future (see below) - Interestingly reading from /proc/pid/mem currently actually involves two copies! (But this could be fixed pretty easily) As mentioned previously use of vmsplice instead was considered, but has problems. Since you need the reader and writer working co-operatively if the pipe is not drained then you block. Which requires some wrapping to do non blocking on the send side or polling on the receive. In all to all communication it requires ordering otherwise you can deadlock. And in the example of many MPI tasks writing to one MPI task vmsplice serialises the copying. There are some cases of MPI collectives where even a single copy interface does not get us the performance gain we could. For example in an MPI_Reduce rather than copy the data from the source we would like to instead use it directly in a mathops (say the reduce is doing a sum) as this would save us doing a copy. We don't need to keep a copy of the data from the source. I haven't implemented this, but I think this interface could in the future do all this through the use of the flags - eg could specify the math operation and type and the kernel rather than just copying the data would apply the specified operation between the source and destination and store it in the destination. Although we don't have a "second user" of the interface (though I've had some nibbles from people who may be interested in using it for intra process messaging which is not MPI). This interface is something which hardware vendors are already doing for their custom drivers to implement fast local communication. And so in addition to this being useful for OpenMPI it would mean the driver maintainers don't have to fix things up when the mm changes. There was some discussion about how much faster a true zero copy would go. Here's a link back to the email with some testing I did on that: http://marc.info/?l=linux-mm&m=130105930902915&w=2 There is a basic man page for the proposed interface here: http://ozlabs.org/~cyeoh/cma/process_vm_readv.txt This has been implemented for x86 and powerpc, other architecture should mainly (I think) just need to add syscall numbers for the process_vm_readv and process_vm_writev. There are 32 bit compatibility versions for 64-bit kernels. For arch maintainers there are some simple tests to be able to quickly verify that the syscalls are working correctly here: http://ozlabs.org/~cyeoh/cma/cma-test-20110718.tgz Signed-off-by: Chris Yeoh Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Thomas Gleixner Cc: Arnd Bergmann Cc: Paul Mackerras Cc: Benjamin Herrenschmidt Cc: David Howells Cc: James Morris Cc: Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compat.h | 3 ++- include/linux/fs.h | 7 ++++--- include/linux/syscalls.h | 13 +++++++++++++ 3 files changed, 19 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/compat.h b/include/linux/compat.h index c6e7523bf76..154bf568301 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -547,7 +547,8 @@ extern ssize_t compat_rw_copy_check_uvector(int type, const struct compat_iovec __user *uvector, unsigned long nr_segs, unsigned long fast_segs, struct iovec *fast_pointer, - struct iovec **ret_pointer); + struct iovec **ret_pointer, + int check_access); extern void __user *compat_alloc_user_space(unsigned long len); diff --git a/include/linux/fs.h b/include/linux/fs.h index 14493a2d5a0..87b4c6b9692 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1633,9 +1633,10 @@ struct inode_operations { struct seq_file; ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector, - unsigned long nr_segs, unsigned long fast_segs, - struct iovec *fast_pointer, - struct iovec **ret_pointer); + unsigned long nr_segs, unsigned long fast_segs, + struct iovec *fast_pointer, + struct iovec **ret_pointer, + int check_access); extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *); extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 1ff0ec2a5e8..86a24b1166d 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -844,4 +844,17 @@ asmlinkage long sys_open_by_handle_at(int mountdirfd, struct file_handle __user *handle, int flags); asmlinkage long sys_setns(int fd, int nstype); +asmlinkage long sys_process_vm_readv(pid_t pid, + const struct iovec __user *lvec, + unsigned long liovcnt, + const struct iovec __user *rvec, + unsigned long riovcnt, + unsigned long flags); +asmlinkage long sys_process_vm_writev(pid_t pid, + const struct iovec __user *lvec, + unsigned long liovcnt, + const struct iovec __user *rvec, + unsigned long riovcnt, + unsigned long flags); + #endif -- cgit v1.2.3 From 4356f21d09283dc6d39a6f7287a65ddab61e2808 Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Mon, 31 Oct 2011 17:06:47 -0700 Subject: mm: change isolate mode from #define to bitwise type Change ISOLATE_XXX macro with bitwise isolate_mode_t type. Normally, macro isn't recommended as it's type-unsafe and making debugging harder as symbol cannot be passed throught to the debugger. Quote from Johannes " Hmm, it would probably be cleaner to fully convert the isolation mode into independent flags. INACTIVE, ACTIVE, BOTH is currently a tri-state among flags, which is a bit ugly." This patch moves isolate mode from swap.h to mmzone.h by memcontrol.h Signed-off-by: Minchan Kim Cc: Johannes Weiner Cc: KAMEZAWA Hiroyuki Cc: KOSAKI Motohiro Cc: Mel Gorman Cc: Rik van Riel Cc: Michal Hocko Cc: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 3 ++- include/linux/mmzone.h | 8 ++++++++ include/linux/swap.h | 7 +------ include/trace/events/vmscan.h | 8 ++++---- 4 files changed, 15 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 343bd7661f2..ac797fa03ef 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -35,7 +35,8 @@ enum mem_cgroup_page_stat_item { extern unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan, struct list_head *dst, unsigned long *scanned, int order, - int mode, struct zone *z, + isolate_mode_t mode, + struct zone *z, struct mem_cgroup *mem_cont, int active, int file); diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index be1ac8d7789..436ce6e7a44 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -164,6 +164,14 @@ static inline int is_unevictable_lru(enum lru_list l) #define LRU_ALL_EVICTABLE (LRU_ALL_FILE | LRU_ALL_ANON) #define LRU_ALL ((1 << NR_LRU_LISTS) - 1) +/* Isolate inactive pages */ +#define ISOLATE_INACTIVE ((__force isolate_mode_t)0x1) +/* Isolate active pages */ +#define ISOLATE_ACTIVE ((__force isolate_mode_t)0x2) + +/* LRU Isolation modes. */ +typedef unsigned __bitwise__ isolate_mode_t; + enum zone_watermarks { WMARK_MIN, WMARK_LOW, diff --git a/include/linux/swap.h b/include/linux/swap.h index c71f84bb62e..1e22e126d2a 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -243,15 +243,10 @@ static inline void lru_cache_add_file(struct page *page) __lru_cache_add(page, LRU_INACTIVE_FILE); } -/* LRU Isolation modes. */ -#define ISOLATE_INACTIVE 0 /* Isolate inactive pages. */ -#define ISOLATE_ACTIVE 1 /* Isolate active pages. */ -#define ISOLATE_BOTH 2 /* Isolate both active and inactive pages. */ - /* linux/mm/vmscan.c */ extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask); -extern int __isolate_lru_page(struct page *page, int mode, int file); +extern int __isolate_lru_page(struct page *page, isolate_mode_t mode, int file); extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem, gfp_t gfp_mask, bool noswap); extern unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem, diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index 36851f7f13d..edc4b3d25a2 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -266,7 +266,7 @@ DECLARE_EVENT_CLASS(mm_vmscan_lru_isolate_template, unsigned long nr_lumpy_taken, unsigned long nr_lumpy_dirty, unsigned long nr_lumpy_failed, - int isolate_mode), + isolate_mode_t isolate_mode), TP_ARGS(order, nr_requested, nr_scanned, nr_taken, nr_lumpy_taken, nr_lumpy_dirty, nr_lumpy_failed, isolate_mode), @@ -278,7 +278,7 @@ DECLARE_EVENT_CLASS(mm_vmscan_lru_isolate_template, __field(unsigned long, nr_lumpy_taken) __field(unsigned long, nr_lumpy_dirty) __field(unsigned long, nr_lumpy_failed) - __field(int, isolate_mode) + __field(isolate_mode_t, isolate_mode) ), TP_fast_assign( @@ -312,7 +312,7 @@ DEFINE_EVENT(mm_vmscan_lru_isolate_template, mm_vmscan_lru_isolate, unsigned long nr_lumpy_taken, unsigned long nr_lumpy_dirty, unsigned long nr_lumpy_failed, - int isolate_mode), + isolate_mode_t isolate_mode), TP_ARGS(order, nr_requested, nr_scanned, nr_taken, nr_lumpy_taken, nr_lumpy_dirty, nr_lumpy_failed, isolate_mode) @@ -327,7 +327,7 @@ DEFINE_EVENT(mm_vmscan_lru_isolate_template, mm_vmscan_memcg_isolate, unsigned long nr_lumpy_taken, unsigned long nr_lumpy_dirty, unsigned long nr_lumpy_failed, - int isolate_mode), + isolate_mode_t isolate_mode), TP_ARGS(order, nr_requested, nr_scanned, nr_taken, nr_lumpy_taken, nr_lumpy_dirty, nr_lumpy_failed, isolate_mode) -- cgit v1.2.3 From 39deaf8585152f1a35c1676d3d7dc6ae0fb65967 Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Mon, 31 Oct 2011 17:06:51 -0700 Subject: mm: compaction: make isolate_lru_page() filter-aware In async mode, compaction doesn't migrate dirty or writeback pages. So, it's meaningless to pick the page and re-add it to lru list. Of course, when we isolate the page in compaction, the page might be dirty or writeback but when we try to migrate the page, the page would be not dirty, writeback. So it could be migrated. But it's very unlikely as isolate and migration cycle is much faster than writeout. So, this patch helps cpu overhead and prevent unnecessary LRU churning. Signed-off-by: Minchan Kim Acked-by: Johannes Weiner Reviewed-by: KAMEZAWA Hiroyuki Reviewed-by: KOSAKI Motohiro Acked-by: Mel Gorman Acked-by: Rik van Riel Reviewed-by: Michal Hocko Cc: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 436ce6e7a44..80da968798e 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -168,6 +168,8 @@ static inline int is_unevictable_lru(enum lru_list l) #define ISOLATE_INACTIVE ((__force isolate_mode_t)0x1) /* Isolate active pages */ #define ISOLATE_ACTIVE ((__force isolate_mode_t)0x2) +/* Isolate clean file */ +#define ISOLATE_CLEAN ((__force isolate_mode_t)0x4) /* LRU Isolation modes. */ typedef unsigned __bitwise__ isolate_mode_t; -- cgit v1.2.3 From f80c0673610e36ae29d63e3297175e22f70dde5f Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Mon, 31 Oct 2011 17:06:55 -0700 Subject: mm: zone_reclaim: make isolate_lru_page() filter-aware In __zone_reclaim case, we don't want to shrink mapped page. Nonetheless, we have isolated mapped page and re-add it into LRU's head. It's unnecessary CPU overhead and makes LRU churning. Of course, when we isolate the page, the page might be mapped but when we try to migrate the page, the page would be not mapped. So it could be migrated. But race is rare and although it happens, it's no big deal. Signed-off-by: Minchan Kim Acked-by: Johannes Weiner Reviewed-by: KAMEZAWA Hiroyuki Reviewed-by: KOSAKI Motohiro Reviewed-by: Michal Hocko Cc: Mel Gorman Cc: Rik van Riel Cc: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 80da968798e..ec57779c5a5 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -170,6 +170,8 @@ static inline int is_unevictable_lru(enum lru_list l) #define ISOLATE_ACTIVE ((__force isolate_mode_t)0x2) /* Isolate clean file */ #define ISOLATE_CLEAN ((__force isolate_mode_t)0x4) +/* Isolate unmapped file */ +#define ISOLATE_UNMAPPED ((__force isolate_mode_t)0x8) /* LRU Isolation modes. */ typedef unsigned __bitwise__ isolate_mode_t; -- cgit v1.2.3 From c9f01245b6a7d77d17deaa71af10f6aca14fa24e Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Mon, 31 Oct 2011 17:07:15 -0700 Subject: oom: remove oom_disable_count This removes mm->oom_disable_count entirely since it's unnecessary and currently buggy. The counter was intended to be per-process but it's currently decremented in the exit path for each thread that exits, causing it to underflow. The count was originally intended to prevent oom killing threads that share memory with threads that cannot be killed since it doesn't lead to future memory freeing. The counter could be fixed to represent all threads sharing the same mm, but it's better to remove the count since: - it is possible that the OOM_DISABLE thread sharing memory with the victim is waiting on that thread to exit and will actually cause future memory freeing, and - there is no guarantee that a thread is disabled from oom killing just because another thread sharing its mm is oom disabled. Signed-off-by: David Rientjes Reported-by: Oleg Nesterov Reviewed-by: Oleg Nesterov Cc: Ying Han Cc: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index c93d00a6e95..6456624aa96 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -336,9 +336,6 @@ struct mm_struct { unsigned int token_priority; unsigned int last_interval; - /* How many tasks sharing this mm are OOM_DISABLE */ - atomic_t oom_disable_count; - unsigned long flags; /* Must use atomic bitops to access the bits */ struct core_state *core_state; /* coredumping support */ -- cgit v1.2.3 From 43362a4977e37db46f86f7e6ab935f0006956632 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Mon, 31 Oct 2011 17:07:18 -0700 Subject: oom: fix race while temporarily setting current's oom_score_adj test_set_oom_score_adj() was introduced in 72788c385604 ("oom: replace PF_OOM_ORIGIN with toggling oom_score_adj") to temporarily elevate current's oom_score_adj for ksm and swapoff without requiring an additional per-process flag. Using that function to both set oom_score_adj to OOM_SCORE_ADJ_MAX and then reinstate the previous value is racy since it's possible that userspace can set the value to something else itself before the old value is reinstated. That results in userspace setting current's oom_score_adj to a different value and then the kernel immediately setting it back to its previous value without notification. To fix this, a new compare_swap_oom_score_adj() function is introduced with the same semantics as the compare and swap CAS instruction, or CMPXCHG on x86. It is used to reinstate the previous value of oom_score_adj if and only if the present value is the same as the old value. Signed-off-by: David Rientjes Cc: Oleg Nesterov Cc: Ying Han Cc: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/oom.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/oom.h b/include/linux/oom.h index 13b7b02e599..6f9d04a8533 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -40,6 +40,7 @@ enum oom_constraint { CONSTRAINT_MEMCG, }; +extern void compare_swap_oom_score_adj(int old_val, int new_val); extern int test_set_oom_score_adj(int new_val); extern unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem, -- cgit v1.2.3 From bc3e53f682d93df677dbd5006a404722b3adfe18 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Mon, 31 Oct 2011 17:07:30 -0700 Subject: mm: distinguish between mlocked and pinned pages Some kernel components pin user space memory (infiniband and perf) (by increasing the page count) and account that memory as "mlocked". The difference between mlocking and pinning is: A. mlocked pages are marked with PG_mlocked and are exempt from swapping. Page migration may move them around though. They are kept on a special LRU list. B. Pinned pages cannot be moved because something needs to directly access physical memory. They may not be on any LRU list. I recently saw an mlockalled process where mm->locked_vm became bigger than the virtual size of the process (!) because some memory was accounted for twice: Once when the page was mlocked and once when the Infiniband layer increased the refcount because it needt to pin the RDMA memory. This patch introduces a separate counter for pinned pages and accounts them seperately. Signed-off-by: Christoph Lameter Cc: Mike Marciniszyn Cc: Roland Dreier Cc: Sean Hefty Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 6456624aa96..f3175830cc7 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -304,7 +304,7 @@ struct mm_struct { unsigned long hiwater_rss; /* High-watermark of RSS usage */ unsigned long hiwater_vm; /* High-water virtual memory usage */ - unsigned long total_vm, locked_vm, shared_vm, exec_vm; + unsigned long total_vm, locked_vm, pinned_vm, shared_vm, exec_vm; unsigned long stack_vm, reserved_vm, def_flags, nr_ptes; unsigned long start_code, end_code, start_data, end_data; unsigned long start_brk, brk, start_stack; -- cgit v1.2.3 From e10d59f2c3decaf22cc5d3de7040eba202bc2df3 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Mon, 31 Oct 2011 17:07:34 -0700 Subject: mm: add comments to explain mm_struct fields Add comments to explain the page statistics field in the mm_struct. [akpm@linux-foundation.org: add missing ;] Signed-off-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index f3175830cc7..3e01a19a91e 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -304,8 +304,15 @@ struct mm_struct { unsigned long hiwater_rss; /* High-watermark of RSS usage */ unsigned long hiwater_vm; /* High-water virtual memory usage */ - unsigned long total_vm, locked_vm, pinned_vm, shared_vm, exec_vm; - unsigned long stack_vm, reserved_vm, def_flags, nr_ptes; + unsigned long total_vm; /* Total pages mapped */ + unsigned long locked_vm; /* Pages that have PG_mlocked set */ + unsigned long pinned_vm; /* Refcount permanently increased */ + unsigned long shared_vm; /* Shared pages (files) */ + unsigned long exec_vm; /* VM_EXEC & ~VM_WRITE */ + unsigned long stack_vm; /* VM_GROWSUP/DOWN */ + unsigned long reserved_vm; /* VM_RESERVED|VM_IO pages */ + unsigned long def_flags; + unsigned long nr_ptes; /* Page table pages */ unsigned long start_code, end_code, start_data, end_data; unsigned long start_brk, brk, start_stack; unsigned long arg_start, arg_end, env_start, env_end; -- cgit v1.2.3 From ee72886d8ed5d9de3fa0ed3b99a7ca7702576a96 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 31 Oct 2011 17:07:38 -0700 Subject: mm: vmscan: do not writeback filesystem pages in direct reclaim Testing from the XFS folk revealed that there is still too much I/O from the end of the LRU in kswapd. Previously it was considered acceptable by VM people for a small number of pages to be written back from reclaim with testing generally showing about 0.3% of pages reclaimed were written back (higher if memory was low). That writing back a small number of pages is ok has been heavily disputed for quite some time and Dave Chinner explained it well; It doesn't have to be a very high number to be a problem. IO is orders of magnitude slower than the CPU time it takes to flush a page, so the cost of making a bad flush decision is very high. And single page writeback from the LRU is almost always a bad flush decision. To complicate matters, filesystems respond very differently to requests from reclaim according to Christoph Hellwig; xfs tries to write it back if the requester is kswapd ext4 ignores the request if it's a delayed allocation btrfs ignores the request As a result, each filesystem has different performance characteristics when under memory pressure and there are many pages being dirtied. In some cases, the request is ignored entirely so the VM cannot depend on the IO being dispatched. The objective of this series is to reduce writing of filesystem-backed pages from reclaim, play nicely with writeback that is already in progress and throttle reclaim appropriately when writeback pages are encountered. The assumption is that the flushers will always write pages faster than if reclaim issues the IO. A secondary goal is to avoid the problem whereby direct reclaim splices two potentially deep call stacks together. There is a potential new problem as reclaim has less control over how long before a page in a particularly zone or container is cleaned and direct reclaimers depend on kswapd or flusher threads to do the necessary work. However, as filesystems sometimes ignore direct reclaim requests already, it is not expected to be a serious issue. Patch 1 disables writeback of filesystem pages from direct reclaim entirely. Anonymous pages are still written. Patch 2 removes dead code in lumpy reclaim as it is no longer able to synchronously write pages. This hurts lumpy reclaim but there is an expectation that compaction is used for hugepage allocations these days and lumpy reclaim's days are numbered. Patches 3-4 add warnings to XFS and ext4 if called from direct reclaim. With patch 1, this "never happens" and is intended to catch regressions in this logic in the future. Patch 5 disables writeback of filesystem pages from kswapd unless the priority is raised to the point where kswapd is considered to be in trouble. Patch 6 throttles reclaimers if too many dirty pages are being encountered and the zones or backing devices are congested. Patch 7 invalidates dirty pages found at the end of the LRU so they are reclaimed quickly after being written back rather than waiting for a reclaimer to find them I consider this series to be orthogonal to the writeback work but it is worth noting that the writeback work affects the viability of patch 8 in particular. I tested this on ext4 and xfs using fs_mark, a simple writeback test based on dd and a micro benchmark that does a streaming write to a large mapping (exercises use-once LRU logic) followed by streaming writes to a mix of anonymous and file-backed mappings. The command line for fs_mark when botted with 512M looked something like ./fs_mark -d /tmp/fsmark-2676 -D 100 -N 150 -n 150 -L 25 -t 1 -S0 -s 10485760 The number of files was adjusted depending on the amount of available memory so that the files created was about 3xRAM. For multiple threads, the -d switch is specified multiple times. The test machine is x86-64 with an older generation of AMD processor with 4 cores. The underlying storage was 4 disks configured as RAID-0 as this was the best configuration of storage I had available. Swap is on a separate disk. Dirty ratio was tuned to 40% instead of the default of 20%. Testing was run with and without monitors to both verify that the patches were operating as expected and that any performance gain was real and not due to interference from monitors. Here is a summary of results based on testing XFS. 512M1P-xfs Files/s mean 32.69 ( 0.00%) 34.44 ( 5.08%) 512M1P-xfs Elapsed Time fsmark 51.41 48.29 512M1P-xfs Elapsed Time simple-wb 114.09 108.61 512M1P-xfs Elapsed Time mmap-strm 113.46 109.34 512M1P-xfs Kswapd efficiency fsmark 62% 63% 512M1P-xfs Kswapd efficiency simple-wb 56% 61% 512M1P-xfs Kswapd efficiency mmap-strm 44% 42% 512M-xfs Files/s mean 30.78 ( 0.00%) 35.94 (14.36%) 512M-xfs Elapsed Time fsmark 56.08 48.90 512M-xfs Elapsed Time simple-wb 112.22 98.13 512M-xfs Elapsed Time mmap-strm 219.15 196.67 512M-xfs Kswapd efficiency fsmark 54% 56% 512M-xfs Kswapd efficiency simple-wb 54% 55% 512M-xfs Kswapd efficiency mmap-strm 45% 44% 512M-4X-xfs Files/s mean 30.31 ( 0.00%) 33.33 ( 9.06%) 512M-4X-xfs Elapsed Time fsmark 63.26 55.88 512M-4X-xfs Elapsed Time simple-wb 100.90 90.25 512M-4X-xfs Elapsed Time mmap-strm 261.73 255.38 512M-4X-xfs Kswapd efficiency fsmark 49% 50% 512M-4X-xfs Kswapd efficiency simple-wb 54% 56% 512M-4X-xfs Kswapd efficiency mmap-strm 37% 36% 512M-16X-xfs Files/s mean 60.89 ( 0.00%) 65.22 ( 6.64%) 512M-16X-xfs Elapsed Time fsmark 67.47 58.25 512M-16X-xfs Elapsed Time simple-wb 103.22 90.89 512M-16X-xfs Elapsed Time mmap-strm 237.09 198.82 512M-16X-xfs Kswapd efficiency fsmark 45% 46% 512M-16X-xfs Kswapd efficiency simple-wb 53% 55% 512M-16X-xfs Kswapd efficiency mmap-strm 33% 33% Up until 512-4X, the FSmark improvements were statistically significant. For the 4X and 16X tests the results were within standard deviations but just barely. The time to completion for all tests is improved which is an important result. In general, kswapd efficiency is not affected by skipping dirty pages. 1024M1P-xfs Files/s mean 39.09 ( 0.00%) 41.15 ( 5.01%) 1024M1P-xfs Elapsed Time fsmark 84.14 80.41 1024M1P-xfs Elapsed Time simple-wb 210.77 184.78 1024M1P-xfs Elapsed Time mmap-strm 162.00 160.34 1024M1P-xfs Kswapd efficiency fsmark 69% 75% 1024M1P-xfs Kswapd efficiency simple-wb 71% 77% 1024M1P-xfs Kswapd efficiency mmap-strm 43% 44% 1024M-xfs Files/s mean 35.45 ( 0.00%) 37.00 ( 4.19%) 1024M-xfs Elapsed Time fsmark 94.59 91.00 1024M-xfs Elapsed Time simple-wb 229.84 195.08 1024M-xfs Elapsed Time mmap-strm 405.38 440.29 1024M-xfs Kswapd efficiency fsmark 79% 71% 1024M-xfs Kswapd efficiency simple-wb 74% 74% 1024M-xfs Kswapd efficiency mmap-strm 39% 42% 1024M-4X-xfs Files/s mean 32.63 ( 0.00%) 35.05 ( 6.90%) 1024M-4X-xfs Elapsed Time fsmark 103.33 97.74 1024M-4X-xfs Elapsed Time simple-wb 204.48 178.57 1024M-4X-xfs Elapsed Time mmap-strm 528.38 511.88 1024M-4X-xfs Kswapd efficiency fsmark 81% 70% 1024M-4X-xfs Kswapd efficiency simple-wb 73% 72% 1024M-4X-xfs Kswapd efficiency mmap-strm 39% 38% 1024M-16X-xfs Files/s mean 42.65 ( 0.00%) 42.97 ( 0.74%) 1024M-16X-xfs Elapsed Time fsmark 103.11 99.11 1024M-16X-xfs Elapsed Time simple-wb 200.83 178.24 1024M-16X-xfs Elapsed Time mmap-strm 397.35 459.82 1024M-16X-xfs Kswapd efficiency fsmark 84% 69% 1024M-16X-xfs Kswapd efficiency simple-wb 74% 73% 1024M-16X-xfs Kswapd efficiency mmap-strm 39% 40% All FSMark tests up to 16X had statistically significant improvements. For the most part, tests are completing faster with the exception of the streaming writes to a mixture of anonymous and file-backed mappings which were slower in two cases In the cases where the mmap-strm tests were slower, there was more swapping due to dirty pages being skipped. The number of additional pages swapped is almost identical to the fewer number of pages written from reclaim. In other words, roughly the same number of pages were reclaimed but swapping was slower. As the test is a bit unrealistic and stresses memory heavily, the small shift is acceptable. 4608M1P-xfs Files/s mean 29.75 ( 0.00%) 30.96 ( 3.91%) 4608M1P-xfs Elapsed Time fsmark 512.01 492.15 4608M1P-xfs Elapsed Time simple-wb 618.18 566.24 4608M1P-xfs Elapsed Time mmap-strm 488.05 465.07 4608M1P-xfs Kswapd efficiency fsmark 93% 86% 4608M1P-xfs Kswapd efficiency simple-wb 88% 84% 4608M1P-xfs Kswapd efficiency mmap-strm 46% 45% 4608M-xfs Files/s mean 27.60 ( 0.00%) 28.85 ( 4.33%) 4608M-xfs Elapsed Time fsmark 555.96 532.34 4608M-xfs Elapsed Time simple-wb 659.72 571.85 4608M-xfs Elapsed Time mmap-strm 1082.57 1146.38 4608M-xfs Kswapd efficiency fsmark 89% 91% 4608M-xfs Kswapd efficiency simple-wb 88% 82% 4608M-xfs Kswapd efficiency mmap-strm 48% 46% 4608M-4X-xfs Files/s mean 26.00 ( 0.00%) 27.47 ( 5.35%) 4608M-4X-xfs Elapsed Time fsmark 592.91 564.00 4608M-4X-xfs Elapsed Time simple-wb 616.65 575.07 4608M-4X-xfs Elapsed Time mmap-strm 1773.02 1631.53 4608M-4X-xfs Kswapd efficiency fsmark 90% 94% 4608M-4X-xfs Kswapd efficiency simple-wb 87% 82% 4608M-4X-xfs Kswapd efficiency mmap-strm 43% 43% 4608M-16X-xfs Files/s mean 26.07 ( 0.00%) 26.42 ( 1.32%) 4608M-16X-xfs Elapsed Time fsmark 602.69 585.78 4608M-16X-xfs Elapsed Time simple-wb 606.60 573.81 4608M-16X-xfs Elapsed Time mmap-strm 1549.75 1441.86 4608M-16X-xfs Kswapd efficiency fsmark 98% 98% 4608M-16X-xfs Kswapd efficiency simple-wb 88% 82% 4608M-16X-xfs Kswapd efficiency mmap-strm 44% 42% Unlike the other tests, the fsmark results are not statistically significant but the min and max times are both improved and for the most part, tests completed faster. There are other indications that this is an improvement as well. For example, in the vast majority of cases, there were fewer pages scanned by direct reclaim implying in many cases that stalls due to direct reclaim are reduced. KSwapd is scanning more due to skipping dirty pages which is unfortunate but the CPU usage is still acceptable In an earlier set of tests, I used blktrace and in almost all cases throughput throughout the entire test was higher. However, I ended up discarding those results as recording blktrace data was too heavy for my liking. On a laptop, I plugged in a USB stick and ran a similar tests of tests using it as backing storage. A desktop environment was running and for the entire duration of the tests, firefox and gnome terminal were launching and exiting to vaguely simulate a user. 1024M-xfs Files/s mean 0.41 ( 0.00%) 0.44 ( 6.82%) 1024M-xfs Elapsed Time fsmark 2053.52 1641.03 1024M-xfs Elapsed Time simple-wb 1229.53 768.05 1024M-xfs Elapsed Time mmap-strm 4126.44 4597.03 1024M-xfs Kswapd efficiency fsmark 84% 85% 1024M-xfs Kswapd efficiency simple-wb 92% 81% 1024M-xfs Kswapd efficiency mmap-strm 60% 51% 1024M-xfs Avg wait ms fsmark 5404.53 4473.87 1024M-xfs Avg wait ms simple-wb 2541.35 1453.54 1024M-xfs Avg wait ms mmap-strm 3400.25 3852.53 The mmap-strm results were hurt because firefox launching had a tendency to push the test out of memory. On the postive side, firefox launched marginally faster with the patches applied. Time to completion for many tests was faster but more importantly - the "Avg wait" time as measured by iostat was far lower implying the system would be more responsive. It was also the case that "Avg wait ms" on the root filesystem was lower. I tested it manually and while the system felt slightly more responsive while copying data to a USB stick, it was marginal enough that it could be my imagination. This patch: do not writeback filesystem pages in direct reclaim. When kswapd is failing to keep zones above the min watermark, a process will enter direct reclaim in the same manner kswapd does. If a dirty page is encountered during the scan, this page is written to backing storage using mapping->writepage. This causes two problems. First, it can result in very deep call stacks, particularly if the target storage or filesystem are complex. Some filesystems ignore write requests from direct reclaim as a result. The second is that a single-page flush is inefficient in terms of IO. While there is an expectation that the elevator will merge requests, this does not always happen. Quoting Christoph Hellwig; The elevator has a relatively small window it can operate on, and can never fix up a bad large scale writeback pattern. This patch prevents direct reclaim writing back filesystem pages by checking if current is kswapd. Anonymous pages are still written to swap as there is not the equivalent of a flusher thread for anonymous pages. If the dirty pages cannot be written back, they are placed back on the LRU lists. There is now a direct dependency on dirty page balancing to prevent too many pages in the system being dirtied which would prevent reclaim making forward progress. Signed-off-by: Mel Gorman Reviewed-by: Minchan Kim Cc: Dave Chinner Cc: Christoph Hellwig Cc: Johannes Weiner Cc: Wu Fengguang Cc: Jan Kara Cc: Rik van Riel Cc: Mel Gorman Cc: Alex Elder Cc: Theodore Ts'o Cc: Chris Mason Cc: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index ec57779c5a5..2c41b2c1943 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -100,6 +100,7 @@ enum zone_stat_item { NR_UNSTABLE_NFS, /* NFS unstable pages */ NR_BOUNCE, NR_VMSCAN_WRITE, + NR_VMSCAN_WRITE_SKIP, NR_WRITEBACK_TEMP, /* Writeback using temporary buffers */ NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */ NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */ -- cgit v1.2.3 From 49ea7eb65e7c5060807fb9312b1ad4c3eab82e2c Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 31 Oct 2011 17:07:59 -0700 Subject: mm: vmscan: immediately reclaim end-of-LRU dirty pages when writeback completes When direct reclaim encounters a dirty page, it gets recycled around the LRU for another cycle. This patch marks the page PageReclaim similar to deactivate_page() so that the page gets reclaimed almost immediately after the page gets cleaned. This is to avoid reclaiming clean pages that are younger than a dirty page encountered at the end of the LRU that might have been something like a use-once page. Signed-off-by: Mel Gorman Acked-by: Johannes Weiner Cc: Dave Chinner Cc: Christoph Hellwig Cc: Wu Fengguang Cc: Jan Kara Cc: Minchan Kim Cc: Rik van Riel Cc: Mel Gorman Cc: Alex Elder Cc: Theodore Ts'o Cc: Chris Mason Cc: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 2c41b2c1943..188cb2ffe8d 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -100,7 +100,7 @@ enum zone_stat_item { NR_UNSTABLE_NFS, /* NFS unstable pages */ NR_BOUNCE, NR_VMSCAN_WRITE, - NR_VMSCAN_WRITE_SKIP, + NR_VMSCAN_IMMEDIATE, /* Prioritise for reclaim when writeback ends */ NR_WRITEBACK_TEMP, /* Writeback using temporary buffers */ NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */ NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */ -- cgit v1.2.3 From 798248206b59acc6e1238c778281419c041891a7 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Mon, 31 Oct 2011 17:08:07 -0700 Subject: lib/string.c: introduce memchr_inv() memchr_inv() is mainly used to check whether the whole buffer is filled with just a specified byte. The function name and prototype are stolen from logfs and the implementation is from SLUB. Signed-off-by: Akinobu Mita Acked-by: Christoph Lameter Acked-by: Pekka Enberg Cc: Matt Mackall Acked-by: Joern Engel Cc: Marcin Slusarz Cc: Eric Dumazet Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/string.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/string.h b/include/linux/string.h index a176db2f2c8..e033564f10b 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -114,6 +114,7 @@ extern int memcmp(const void *,const void *,__kernel_size_t); #ifndef __HAVE_ARCH_MEMCHR extern void * memchr(const void *,int,__kernel_size_t); #endif +void *memchr_inv(const void *s, int c, size_t n); extern char *kstrdup(const char *s, gfp_t gfp); extern char *kstrndup(const char *s, size_t len, gfp_t gfp); -- cgit v1.2.3 From f5252e009d5b87071a919221e4f6624184005368 Mon Sep 17 00:00:00 2001 From: Mitsuo Hayasaka Date: Mon, 31 Oct 2011 17:08:13 -0700 Subject: mm: avoid null pointer access in vm_struct via /proc/vmallocinfo The /proc/vmallocinfo shows information about vmalloc allocations in vmlist that is a linklist of vm_struct. It, however, may access pages field of vm_struct where a page was not allocated. This results in a null pointer access and leads to a kernel panic. Why this happens: In __vmalloc_node_range() called from vmalloc(), newly allocated vm_struct is added to vmlist at __get_vm_area_node() and then, some fields of vm_struct such as nr_pages and pages are set at __vmalloc_area_node(). In other words, it is added to vmlist before it is fully initialized. At the same time, when the /proc/vmallocinfo is read, it accesses the pages field of vm_struct according to the nr_pages field at show_numa_info(). Thus, a null pointer access happens. The patch adds the newly allocated vm_struct to the vmlist *after* it is fully initialized. So, it can avoid accessing the pages field with unallocated page when show_numa_info() is called. Signed-off-by: Mitsuo Hayasaka Cc: Andrew Morton Cc: David Rientjes Cc: Namhyung Kim Cc: "Paul E. McKenney" Cc: Jeremy Fitzhardinge Cc: Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 9332e52ea8c..687fb11e201 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -13,6 +13,7 @@ struct vm_area_struct; /* vma defining user mapping in mm_types.h */ #define VM_MAP 0x00000004 /* vmap()ed pages */ #define VM_USERMAP 0x00000008 /* suitable for remap_vmalloc_range */ #define VM_VPAGES 0x00000010 /* buffer for pages was vmalloc'ed */ +#define VM_UNLIST 0x00000020 /* vm_struct is not listed in vmlist */ /* bits [20..32] reserved for arch specific ioremap internals */ /* -- cgit v1.2.3 From 0a93ebef698b08ed04af0d7d913bab8aedfdc253 Mon Sep 17 00:00:00 2001 From: Sam Ravnborg Date: Mon, 31 Oct 2011 17:08:16 -0700 Subject: memblock: add memblock_start_of_DRAM() SPARC32 require access to the start address. Add a new helper memblock_start_of_DRAM() to give access to the address of the first memblock - which contains the lowest address. The awkward name was chosen to match the already present memblock_end_of_DRAM(). Signed-off-by: Sam Ravnborg Cc: "David S. Miller" Cc: Yinghai Lu Acked-by: Tejun Heo Cc: "H. Peter Anvin" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 7525e38c434..e6b843e16e8 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -80,6 +80,7 @@ extern phys_addr_t __memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr); extern phys_addr_t memblock_phys_mem_size(void); +extern phys_addr_t memblock_start_of_DRAM(void); extern phys_addr_t memblock_end_of_DRAM(void); extern void memblock_enforce_memory_limit(phys_addr_t memory_limit); extern int memblock_is_memory(phys_addr_t addr); -- cgit v1.2.3 From 37a1c49a91ad55f917a399ef2174b5ebda4283f9 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Mon, 31 Oct 2011 17:08:30 -0700 Subject: thp: mremap support and TLB optimization This adds THP support to mremap (decreases the number of split_huge_page() calls). Here are also some benchmarks with a proggy like this: === #define _GNU_SOURCE #include #include #include #include #include #define SIZE (5UL*1024*1024*1024) int main() { static struct timeval oldstamp, newstamp; long diffsec; char *p, *p2, *p3, *p4; if (posix_memalign((void **)&p, 2*1024*1024, SIZE)) perror("memalign"), exit(1); if (posix_memalign((void **)&p2, 2*1024*1024, SIZE)) perror("memalign"), exit(1); if (posix_memalign((void **)&p3, 2*1024*1024, 4096)) perror("memalign"), exit(1); memset(p, 0xff, SIZE); memset(p2, 0xff, SIZE); memset(p3, 0x77, 4096); gettimeofday(&oldstamp, NULL); p4 = mremap(p, SIZE, SIZE, MREMAP_FIXED|MREMAP_MAYMOVE, p3); gettimeofday(&newstamp, NULL); diffsec = newstamp.tv_sec - oldstamp.tv_sec; diffsec = newstamp.tv_usec - oldstamp.tv_usec + 1000000 * diffsec; printf("usec %ld\n", diffsec); if (p == MAP_FAILED || p4 != p3) //if (p == MAP_FAILED) perror("mremap"), exit(1); if (memcmp(p4, p2, SIZE)) printf("mremap bug\n"), exit(1); printf("ok\n"); return 0; } === THP on Performance counter stats for './largepage13' (3 runs): 69195836 dTLB-loads ( +- 3.546% ) (scaled from 50.30%) 60708 dTLB-load-misses ( +- 11.776% ) (scaled from 52.62%) 676266476 dTLB-stores ( +- 5.654% ) (scaled from 69.54%) 29856 dTLB-store-misses ( +- 4.081% ) (scaled from 89.22%) 1055848782 iTLB-loads ( +- 4.526% ) (scaled from 80.18%) 8689 iTLB-load-misses ( +- 2.987% ) (scaled from 58.20%) 7.314454164 seconds time elapsed ( +- 0.023% ) THP off Performance counter stats for './largepage13' (3 runs): 1967379311 dTLB-loads ( +- 0.506% ) (scaled from 60.59%) 9238687 dTLB-load-misses ( +- 22.547% ) (scaled from 61.87%) 2014239444 dTLB-stores ( +- 0.692% ) (scaled from 60.40%) 3312335 dTLB-store-misses ( +- 7.304% ) (scaled from 67.60%) 6764372065 iTLB-loads ( +- 0.925% ) (scaled from 79.00%) 8202 iTLB-load-misses ( +- 0.475% ) (scaled from 70.55%) 9.693655243 seconds time elapsed ( +- 0.069% ) grep thp /proc/vmstat thp_fault_alloc 35849 thp_fault_fallback 0 thp_collapse_alloc 3 thp_collapse_alloc_failed 0 thp_split 0 thp_split 0 confirms no thp split despite plenty of hugepages allocated. The measurement of only the mremap time (so excluding the 3 long memset and final long 10GB memory accessing memcmp): THP on usec 14824 usec 14862 usec 14859 THP off usec 256416 usec 255981 usec 255847 With an older kernel without the mremap optimizations (the below patch optimizes the non THP version too). THP on usec 392107 usec 390237 usec 404124 THP off usec 444294 usec 445237 usec 445820 I guess with a threaded program that sends more IPI on large SMP it'd create an even larger difference. All debug options are off except DEBUG_VM to avoid skewing the results. The only problem for native 2M mremap like it happens above both the source and destination address must be 2M aligned or the hugepmd can't be moved without a split but that is an hardware limitation. [akpm@linux-foundation.org: coding-style nitpicking] Signed-off-by: Andrea Arcangeli Acked-by: Johannes Weiner Acked-by: Mel Gorman Acked-by: Rik van Riel Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 48c32ebf65a..a9ace9c3250 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -22,6 +22,11 @@ extern int zap_huge_pmd(struct mmu_gather *tlb, extern int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, unsigned char *vec); +extern int move_huge_pmd(struct vm_area_struct *vma, + struct vm_area_struct *new_vma, + unsigned long old_addr, + unsigned long new_addr, unsigned long old_end, + pmd_t *old_pmd, pmd_t *new_pmd); extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, pgprot_t newprot); -- cgit v1.2.3 From 06d5e032adcbc7d50c606a1396f00e2474e4213e Mon Sep 17 00:00:00 2001 From: Sonic Zhang Date: Mon, 31 Oct 2011 17:08:31 -0700 Subject: include/asm-generic/page.h: calculate virt_to_page and page_to_virt via predefined macro On NOMMU architectures, if physical memory doesn't start from 0, ARCH_PFN_OFFSET is defined to generate page index in mem_map array. Because virtual address is equal to physical address, PAGE_OFFSET is always 0. virt_to_page and page_to_virt should not index page by PAGE_OFFSET directly. Signed-off-by: Sonic Zhang Cc: Greg Ungerer Cc: Geert Uytterhoeven Cc: David Howells Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/page.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/asm-generic/page.h b/include/asm-generic/page.h index 75fec18cdc5..351889d1de1 100644 --- a/include/asm-generic/page.h +++ b/include/asm-generic/page.h @@ -79,8 +79,8 @@ extern unsigned long memory_end; #define virt_to_pfn(kaddr) (__pa(kaddr) >> PAGE_SHIFT) #define pfn_to_virt(pfn) __va((pfn) << PAGE_SHIFT) -#define virt_to_page(addr) (mem_map + (((unsigned long)(addr)-PAGE_OFFSET) >> PAGE_SHIFT)) -#define page_to_virt(page) ((((page) - mem_map) << PAGE_SHIFT) + PAGE_OFFSET) +#define virt_to_page(addr) pfn_to_page(virt_to_pfn(addr)) +#define page_to_virt(page) pfn_to_virt(page_to_pfn(page)) #ifndef page_to_phys #define page_to_phys(page) ((dma_addr_t)page_to_pfn(page) << PAGE_SHIFT) -- cgit v1.2.3 From 3ee9a4f086716d792219c021e8509f91165a4128 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Mon, 31 Oct 2011 17:08:35 -0700 Subject: mm: neaten warn_alloc_failed Add __attribute__((format (printf...) to the function to validate format and arguments. Use vsprintf extension %pV to avoid any possible message interleaving. Coalesce format string. Convert printks/pr_warning to pr_warn. [akpm@linux-foundation.org: use the __printf() macro] Signed-off-by: Joe Perches Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 7438071b44a..3b3e3b8bb70 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1334,7 +1334,8 @@ extern void si_meminfo(struct sysinfo * val); extern void si_meminfo_node(struct sysinfo *val, int nid); extern int after_bootmem; -extern void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...); +extern __printf(3, 4) +void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...); extern void setup_per_cpu_pageset(void); -- cgit v1.2.3 From 09f363c7363eb10cfb4b82094bd7064e5608258b Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Mon, 31 Oct 2011 17:08:57 -0700 Subject: vmscan: fix shrinker callback bug in fs/super.c The callback must not return -1 when nr_to_scan is zero. Fix the bug in fs/super.c and add this requirement to the callback specification. Signed-off-by: Mikulas Patocka Cc: Dave Chinner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/shrinker.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h index 790651b4e5b..a83833a1f7a 100644 --- a/include/linux/shrinker.h +++ b/include/linux/shrinker.h @@ -20,6 +20,7 @@ struct shrink_control { * 'nr_to_scan' entries and attempt to free them up. It should return * the number of objects which remain in the cache. If it returns -1, it means * it cannot do any scanning at this time (eg. there is a risk of deadlock). + * The callback must not return -1 if nr_to_scan is zero. * * The 'gfpmask' refers to the allocation we are currently trying to * fulfil. -- cgit v1.2.3 From d43a87e68e9e71d2987a29cc239acec4e8f410c9 Mon Sep 17 00:00:00 2001 From: Kyungmin Park Date: Mon, 31 Oct 2011 17:09:08 -0700 Subject: mm: compaction: make compact_zone_order() static There's no compact_zone_order() user outside file scope, so make it static. Signed-off-by: Kyungmin Park Acked-by: David Rientjes Reviewed-by: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index cc9f7a42864..bb2bbdbe546 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -24,8 +24,6 @@ extern unsigned long try_to_compact_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask, bool sync); extern unsigned long compaction_suitable(struct zone *zone, int order); -extern unsigned long compact_zone_order(struct zone *zone, int order, - gfp_t gfp_mask, bool sync); /* Do not skip compaction more than 64 times */ #define COMPACT_MAX_DEFER_SHIFT 6 @@ -69,12 +67,6 @@ static inline unsigned long compaction_suitable(struct zone *zone, int order) return COMPACT_SKIPPED; } -static inline unsigned long compact_zone_order(struct zone *zone, int order, - gfp_t gfp_mask, bool sync) -{ - return COMPACT_CONTINUE; -} - static inline void defer_compaction(struct zone *zone) { } -- cgit v1.2.3 From ec400c9fab99d16a491cea17d27d0c6a5780b97c Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 31 Oct 2011 17:11:07 -0700 Subject: lis3lv02d: make regulator API usage unconditional MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The regulator API contains a range of features for stubbing itself out when not in use and for transparently restricting the actual effect of regulator API calls where they can't be supported on a particular system so that drivers don't need to individually implement this. Simplify the driver slightly by making use of this idiom. The only in tree user is ecovec24 which does not use the regulator API. Signed-off-by: Mark Brown Cc: Éric Piel Cc: Ilkka Koskinen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/lis3lv02d.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/lis3lv02d.h b/include/linux/lis3lv02d.h index d4292c8431e..f1664c636af 100644 --- a/include/linux/lis3lv02d.h +++ b/include/linux/lis3lv02d.h @@ -113,7 +113,6 @@ struct lis3lv02d_platform_data { s8 axis_x; s8 axis_y; s8 axis_z; -#define LIS3_USE_REGULATOR_CTRL 0x01 #define LIS3_USE_BLOCK_READ 0x02 u16 driver_features; int default_rate; -- cgit v1.2.3 From b9075fa968a0a4347aef35e235e2995c0e57dddd Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Mon, 31 Oct 2011 17:11:33 -0700 Subject: treewide: use __printf not __attribute__((format(printf,...))) Standardize the style for compiler based printf format verification. Standardized the location of __printf too. Done via script and a little typing. $ grep -rPl --include=*.[ch] -w "__attribute__" * | \ grep -vP "^(tools|scripts|include/linux/compiler-gcc.h)" | \ xargs perl -n -i -e 'local $/; while (<>) { s/\b__attribute__\s*\(\s*\(\s*format\s*\(\s*printf\s*,\s*(.+)\s*,\s*(.+)\s*\)\s*\)\s*\)/__printf($1, $2)/g ; print; }' [akpm@linux-foundation.org: revert arch bits] Signed-off-by: Joe Perches Cc: "Kirill A. Shutemov" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/bug.h | 11 ++-- include/drm/drmP.h | 10 ++-- include/linux/audit.h | 11 ++-- include/linux/blktrace_api.h | 2 +- include/linux/device.h | 110 ++++++++++++++++++-------------------- include/linux/dynamic_debug.h | 19 ++++--- include/linux/ext3_fs.h | 16 +++--- include/linux/fs.h | 4 +- include/linux/fscache-cache.h | 8 +-- include/linux/gameport.h | 8 +-- include/linux/kallsyms.h | 5 +- include/linux/kdb.h | 9 ++-- include/linux/kernel.h | 44 +++++++-------- include/linux/kexec.h | 4 +- include/linux/kmod.h | 4 +- include/linux/kobject.h | 26 +++++---- include/linux/kthread.h | 4 +- include/linux/libata.h | 18 +++---- include/linux/mmiotrace.h | 8 +-- include/linux/netdevice.h | 34 ++++++------ include/linux/printk.h | 12 ++--- include/linux/quotaops.h | 2 +- include/linux/seq_file.h | 3 +- include/linux/trace_seq.h | 8 +-- include/net/bluetooth/bluetooth.h | 2 +- include/net/netfilter/nf_log.h | 3 +- include/net/sock.h | 4 +- include/sound/core.h | 4 +- include/sound/info.h | 4 +- include/sound/seq_kernel.h | 4 +- include/xen/hvc-console.h | 4 +- include/xen/xenbus.h | 12 ++--- 32 files changed, 197 insertions(+), 220 deletions(-) (limited to 'include') diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h index dfb0ec666c9..84458b0c38d 100644 --- a/include/asm-generic/bug.h +++ b/include/asm-generic/bug.h @@ -61,11 +61,12 @@ struct bug_entry { */ #ifndef __WARN_TAINT #ifndef __ASSEMBLY__ -extern void warn_slowpath_fmt(const char *file, const int line, - const char *fmt, ...) __attribute__((format(printf, 3, 4))); -extern void warn_slowpath_fmt_taint(const char *file, const int line, - unsigned taint, const char *fmt, ...) - __attribute__((format(printf, 4, 5))); +extern __printf(3, 4) +void warn_slowpath_fmt(const char *file, const int line, + const char *fmt, ...); +extern __printf(4, 5) +void warn_slowpath_fmt_taint(const char *file, const int line, unsigned taint, + const char *fmt, ...); extern void warn_slowpath_null(const char *file, const int line); #define WANT_WARN_ON_SLOWPATH #endif diff --git a/include/drm/drmP.h b/include/drm/drmP.h index 43538b64356..cf3b446139e 100644 --- a/include/drm/drmP.h +++ b/include/drm/drmP.h @@ -122,12 +122,12 @@ struct drm_device; * using the DRM_DEBUG_KMS and DRM_DEBUG. */ -extern __attribute__((format (printf, 4, 5))) +extern __printf(4, 5) void drm_ut_debug_printk(unsigned int request_level, - const char *prefix, - const char *function_name, - const char *format, ...); -extern __attribute__((format (printf, 2, 3))) + const char *prefix, + const char *function_name, + const char *format, ...); +extern __printf(2, 3) int drm_err(const char *func, const char *format, ...); /***********************************************************************/ diff --git a/include/linux/audit.h b/include/linux/audit.h index 0c8006129fb..2f81c6f3b63 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -584,14 +584,13 @@ extern int audit_signals; #ifdef CONFIG_AUDIT /* These are defined in audit.c */ /* Public API */ -extern void audit_log(struct audit_context *ctx, gfp_t gfp_mask, - int type, const char *fmt, ...) - __attribute__((format(printf,4,5))); +extern __printf(4, 5) +void audit_log(struct audit_context *ctx, gfp_t gfp_mask, int type, + const char *fmt, ...); extern struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, int type); -extern void audit_log_format(struct audit_buffer *ab, - const char *fmt, ...) - __attribute__((format(printf,2,3))); +extern __printf(2, 3) +void audit_log_format(struct audit_buffer *ab, const char *fmt, ...); extern void audit_log_end(struct audit_buffer *ab); extern int audit_string_contains_control(const char *string, size_t len); diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 8e9e4bc6d73..4d1a0748eaf 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -170,7 +170,7 @@ extern void blk_trace_shutdown(struct request_queue *); extern int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, struct block_device *bdev, struct blk_user_trace_setup *buts); -extern __attribute__((format(printf, 2, 3))) +extern __printf(2, 3) void __trace_note_message(struct blk_trace *, const char *fmt, ...); /** diff --git a/include/linux/device.h b/include/linux/device.h index 85e78fc7d7f..e88abeecfad 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -622,8 +622,8 @@ static inline const char *dev_name(const struct device *dev) return kobject_name(&dev->kobj); } -extern int dev_set_name(struct device *dev, const char *name, ...) - __attribute__((format(printf, 2, 3))); +extern __printf(2, 3) +int dev_set_name(struct device *dev, const char *name, ...); #ifdef CONFIG_NUMA static inline int dev_to_node(struct device *dev) @@ -753,10 +753,10 @@ extern struct device *device_create_vargs(struct class *cls, void *drvdata, const char *fmt, va_list vargs); -extern struct device *device_create(struct class *cls, struct device *parent, - dev_t devt, void *drvdata, - const char *fmt, ...) - __attribute__((format(printf, 5, 6))); +extern __printf(5, 6) +struct device *device_create(struct class *cls, struct device *parent, + dev_t devt, void *drvdata, + const char *fmt, ...); extern void device_destroy(struct class *cls, dev_t devt); /* @@ -800,64 +800,56 @@ extern const char *dev_driver_string(const struct device *dev); extern int __dev_printk(const char *level, const struct device *dev, struct va_format *vaf); -extern int dev_printk(const char *level, const struct device *dev, - const char *fmt, ...) - __attribute__ ((format (printf, 3, 4))); -extern int dev_emerg(const struct device *dev, const char *fmt, ...) - __attribute__ ((format (printf, 2, 3))); -extern int dev_alert(const struct device *dev, const char *fmt, ...) - __attribute__ ((format (printf, 2, 3))); -extern int dev_crit(const struct device *dev, const char *fmt, ...) - __attribute__ ((format (printf, 2, 3))); -extern int dev_err(const struct device *dev, const char *fmt, ...) - __attribute__ ((format (printf, 2, 3))); -extern int dev_warn(const struct device *dev, const char *fmt, ...) - __attribute__ ((format (printf, 2, 3))); -extern int dev_notice(const struct device *dev, const char *fmt, ...) - __attribute__ ((format (printf, 2, 3))); -extern int _dev_info(const struct device *dev, const char *fmt, ...) - __attribute__ ((format (printf, 2, 3))); +extern __printf(3, 4) +int dev_printk(const char *level, const struct device *dev, + const char *fmt, ...) + ; +extern __printf(2, 3) +int dev_emerg(const struct device *dev, const char *fmt, ...); +extern __printf(2, 3) +int dev_alert(const struct device *dev, const char *fmt, ...); +extern __printf(2, 3) +int dev_crit(const struct device *dev, const char *fmt, ...); +extern __printf(2, 3) +int dev_err(const struct device *dev, const char *fmt, ...); +extern __printf(2, 3) +int dev_warn(const struct device *dev, const char *fmt, ...); +extern __printf(2, 3) +int dev_notice(const struct device *dev, const char *fmt, ...); +extern __printf(2, 3) +int _dev_info(const struct device *dev, const char *fmt, ...); #else static inline int __dev_printk(const char *level, const struct device *dev, struct va_format *vaf) - { return 0; } -static inline int dev_printk(const char *level, const struct device *dev, - const char *fmt, ...) - __attribute__ ((format (printf, 3, 4))); -static inline int dev_printk(const char *level, const struct device *dev, - const char *fmt, ...) - { return 0; } - -static inline int dev_emerg(const struct device *dev, const char *fmt, ...) - __attribute__ ((format (printf, 2, 3))); -static inline int dev_emerg(const struct device *dev, const char *fmt, ...) - { return 0; } -static inline int dev_crit(const struct device *dev, const char *fmt, ...) - __attribute__ ((format (printf, 2, 3))); -static inline int dev_crit(const struct device *dev, const char *fmt, ...) - { return 0; } -static inline int dev_alert(const struct device *dev, const char *fmt, ...) - __attribute__ ((format (printf, 2, 3))); -static inline int dev_alert(const struct device *dev, const char *fmt, ...) - { return 0; } -static inline int dev_err(const struct device *dev, const char *fmt, ...) - __attribute__ ((format (printf, 2, 3))); -static inline int dev_err(const struct device *dev, const char *fmt, ...) - { return 0; } -static inline int dev_warn(const struct device *dev, const char *fmt, ...) - __attribute__ ((format (printf, 2, 3))); -static inline int dev_warn(const struct device *dev, const char *fmt, ...) - { return 0; } -static inline int dev_notice(const struct device *dev, const char *fmt, ...) - __attribute__ ((format (printf, 2, 3))); -static inline int dev_notice(const struct device *dev, const char *fmt, ...) - { return 0; } -static inline int _dev_info(const struct device *dev, const char *fmt, ...) - __attribute__ ((format (printf, 2, 3))); -static inline int _dev_info(const struct device *dev, const char *fmt, ...) - { return 0; } +{ return 0; } +static inline __printf(3, 4) +int dev_printk(const char *level, const struct device *dev, + const char *fmt, ...) +{ return 0; } + +static inline __printf(2, 3) +int dev_emerg(const struct device *dev, const char *fmt, ...) +{ return 0; } +static inline __printf(2, 3) +int dev_crit(const struct device *dev, const char *fmt, ...) +{ return 0; } +static inline __printf(2, 3) +int dev_alert(const struct device *dev, const char *fmt, ...) +{ return 0; } +static inline __printf(2, 3) +int dev_err(const struct device *dev, const char *fmt, ...) +{ return 0; } +static inline __printf(2, 3) +int dev_warn(const struct device *dev, const char *fmt, ...) +{ return 0; } +static inline __printf(2, 3) +int dev_notice(const struct device *dev, const char *fmt, ...) +{ return 0; } +static inline __printf(2, 3) +int _dev_info(const struct device *dev, const char *fmt, ...) +{ return 0; } #endif diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h index 13aae8087b5..0564e3c3988 100644 --- a/include/linux/dynamic_debug.h +++ b/include/linux/dynamic_debug.h @@ -37,22 +37,21 @@ int ddebug_add_module(struct _ddebug *tab, unsigned int n, #if defined(CONFIG_DYNAMIC_DEBUG) extern int ddebug_remove_module(const char *mod_name); -extern int __dynamic_pr_debug(struct _ddebug *descriptor, const char *fmt, ...) - __attribute__ ((format (printf, 2, 3))); +extern __printf(2, 3) +int __dynamic_pr_debug(struct _ddebug *descriptor, const char *fmt, ...); struct device; -extern int __dynamic_dev_dbg(struct _ddebug *descriptor, - const struct device *dev, - const char *fmt, ...) - __attribute__ ((format (printf, 3, 4))); +extern __printf(3, 4) +int __dynamic_dev_dbg(struct _ddebug *descriptor, const struct device *dev, + const char *fmt, ...); struct net_device; -extern int __dynamic_netdev_dbg(struct _ddebug *descriptor, - const struct net_device *dev, - const char *fmt, ...) - __attribute__ ((format (printf, 3, 4))); +extern __printf(3, 4) +int __dynamic_netdev_dbg(struct _ddebug *descriptor, + const struct net_device *dev, + const char *fmt, ...); #define DEFINE_DYNAMIC_DEBUG_METADATA(name, fmt) \ static struct _ddebug __used __aligned(8) \ diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h index 67a803aee61..81965cce6bf 100644 --- a/include/linux/ext3_fs.h +++ b/include/linux/ext3_fs.h @@ -937,15 +937,15 @@ extern int ext3_group_extend(struct super_block *sb, ext3_fsblk_t n_blocks_count); /* super.c */ -extern void ext3_error (struct super_block *, const char *, const char *, ...) - __attribute__ ((format (printf, 3, 4))); +extern __printf(3, 4) +void ext3_error(struct super_block *, const char *, const char *, ...); extern void __ext3_std_error (struct super_block *, const char *, int); -extern void ext3_abort (struct super_block *, const char *, const char *, ...) - __attribute__ ((format (printf, 3, 4))); -extern void ext3_warning (struct super_block *, const char *, const char *, ...) - __attribute__ ((format (printf, 3, 4))); -extern void ext3_msg(struct super_block *, const char *, const char *, ...) - __attribute__ ((format (printf, 3, 4))); +extern __printf(3, 4) +void ext3_abort(struct super_block *, const char *, const char *, ...); +extern __printf(3, 4) +void ext3_warning(struct super_block *, const char *, const char *, ...); +extern __printf(3, 4) +void ext3_msg(struct super_block *, const char *, const char *, ...); extern void ext3_update_dynamic_rev (struct super_block *sb); #define ext3_std_error(sb, errno) \ diff --git a/include/linux/fs.h b/include/linux/fs.h index 87b4c6b9692..7a049fd2aa4 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2635,8 +2635,8 @@ static const struct file_operations __fops = { \ .llseek = generic_file_llseek, \ }; -static inline void __attribute__((format(printf, 1, 2))) -__simple_attr_check_format(const char *fmt, ...) +static inline __printf(1, 2) +void __simple_attr_check_format(const char *fmt, ...) { /* don't do anything, just let the compiler check the arguments; */ } diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index af095b54502..ce31408b1e4 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -492,10 +492,10 @@ static inline void fscache_end_io(struct fscache_retrieval *op, /* * out-of-line cache backend functions */ -extern void fscache_init_cache(struct fscache_cache *cache, - const struct fscache_cache_ops *ops, - const char *idfmt, - ...) __attribute__ ((format (printf, 3, 4))); +extern __printf(3, 4) +void fscache_init_cache(struct fscache_cache *cache, + const struct fscache_cache_ops *ops, + const char *idfmt, ...); extern int fscache_add_cache(struct fscache_cache *cache, struct fscache_object *fsdef, diff --git a/include/linux/gameport.h b/include/linux/gameport.h index b65a6f47277..069ee413910 100644 --- a/include/linux/gameport.h +++ b/include/linux/gameport.h @@ -78,8 +78,8 @@ static inline void gameport_register_port(struct gameport *gameport) void gameport_unregister_port(struct gameport *gameport); -void gameport_set_phys(struct gameport *gameport, const char *fmt, ...) - __attribute__ ((format (printf, 2, 3))); +__printf(2, 3) +void gameport_set_phys(struct gameport *gameport, const char *fmt, ...); #else @@ -93,8 +93,8 @@ static inline void gameport_unregister_port(struct gameport *gameport) return; } -static inline void gameport_set_phys(struct gameport *gameport, - const char *fmt, ...) +static inline __printf(2, 3) +void gameport_set_phys(struct gameport *gameport, const char *fmt, ...) { return; } diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h index 0df513b7a9f..387571959dd 100644 --- a/include/linux/kallsyms.h +++ b/include/linux/kallsyms.h @@ -101,9 +101,8 @@ static inline int lookup_symbol_attrs(unsigned long addr, unsigned long *size, u #endif /*CONFIG_KALLSYMS*/ /* This macro allows us to keep printk typechecking */ -static void __check_printsym_format(const char *fmt, ...) -__attribute__((format(printf,1,2))); -static inline void __check_printsym_format(const char *fmt, ...) +static __printf(1, 2) +void __check_printsym_format(const char *fmt, ...) { } diff --git a/include/linux/kdb.h b/include/linux/kdb.h index 529d9a0c75a..064725854db 100644 --- a/include/linux/kdb.h +++ b/include/linux/kdb.h @@ -114,12 +114,9 @@ typedef enum { } kdb_reason_t; extern int kdb_trap_printk; -extern int vkdb_printf(const char *fmt, va_list args) - __attribute__ ((format (printf, 1, 0))); -extern int kdb_printf(const char *, ...) - __attribute__ ((format (printf, 1, 2))); -typedef int (*kdb_printf_t)(const char *, ...) - __attribute__ ((format (printf, 1, 2))); +extern __printf(1, 0) int vkdb_printf(const char *fmt, va_list args); +extern __printf(1, 2) int kdb_printf(const char *, ...); +typedef __printf(1, 2) int (*kdb_printf_t)(const char *, ...); extern void kdb_init(int level); diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 8eefcf7e95e..e40c950e1d6 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -296,20 +296,18 @@ extern long long simple_strtoll(const char *,char **,unsigned int); #define strict_strtoull kstrtoull #define strict_strtoll kstrtoll -extern int sprintf(char * buf, const char * fmt, ...) - __attribute__ ((format (printf, 2, 3))); -extern int vsprintf(char *buf, const char *, va_list) - __attribute__ ((format (printf, 2, 0))); -extern int snprintf(char * buf, size_t size, const char * fmt, ...) - __attribute__ ((format (printf, 3, 4))); -extern int vsnprintf(char *buf, size_t size, const char *fmt, va_list args) - __attribute__ ((format (printf, 3, 0))); -extern int scnprintf(char * buf, size_t size, const char * fmt, ...) - __attribute__ ((format (printf, 3, 4))); -extern int vscnprintf(char *buf, size_t size, const char *fmt, va_list args) - __attribute__ ((format (printf, 3, 0))); -extern char *kasprintf(gfp_t gfp, const char *fmt, ...) - __attribute__ ((format (printf, 2, 3))); +extern __printf(2, 3) int sprintf(char *buf, const char * fmt, ...); +extern __printf(2, 0) int vsprintf(char *buf, const char *, va_list); +extern __printf(3, 4) +int snprintf(char *buf, size_t size, const char *fmt, ...); +extern __printf(3, 0) +int vsnprintf(char *buf, size_t size, const char *fmt, va_list args); +extern __printf(3, 4) +int scnprintf(char *buf, size_t size, const char *fmt, ...); +extern __printf(3, 0) +int vscnprintf(char *buf, size_t size, const char *fmt, va_list args); +extern __printf(2, 3) +char *kasprintf(gfp_t gfp, const char *fmt, ...); extern char *kvasprintf(gfp_t gfp, const char *fmt, va_list args); extern int sscanf(const char *, const char *, ...) @@ -427,8 +425,8 @@ extern void tracing_start(void); extern void tracing_stop(void); extern void ftrace_off_permanent(void); -static inline void __attribute__ ((format (printf, 1, 2))) -____trace_printk_check_format(const char *fmt, ...) +static inline __printf(1, 2) +void ____trace_printk_check_format(const char *fmt, ...) { } #define __trace_printk_check_format(fmt, args...) \ @@ -467,13 +465,11 @@ do { \ __trace_printk(_THIS_IP_, fmt, ##args); \ } while (0) -extern int -__trace_bprintk(unsigned long ip, const char *fmt, ...) - __attribute__ ((format (printf, 2, 3))); +extern __printf(2, 3) +int __trace_bprintk(unsigned long ip, const char *fmt, ...); -extern int -__trace_printk(unsigned long ip, const char *fmt, ...) - __attribute__ ((format (printf, 2, 3))); +extern __printf(2, 3) +int __trace_printk(unsigned long ip, const char *fmt, ...); extern void trace_dump_stack(void); @@ -502,8 +498,8 @@ __ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap); extern void ftrace_dump(enum ftrace_dump_mode oops_dump_mode); #else -static inline int -trace_printk(const char *fmt, ...) __attribute__ ((format (printf, 1, 2))); +static inline __printf(1, 2) +int trace_printk(const char *fmt, ...); static inline void tracing_start(void) { } static inline void tracing_stop(void) { } diff --git a/include/linux/kexec.h b/include/linux/kexec.h index c2478a342cd..8944ebe7963 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -130,8 +130,8 @@ int kexec_should_crash(struct task_struct *); void crash_save_cpu(struct pt_regs *regs, int cpu); void crash_save_vmcoreinfo(void); void arch_crash_save_vmcoreinfo(void); -void vmcoreinfo_append_str(const char *fmt, ...) - __attribute__ ((format (printf, 1, 2))); +__printf(1, 2) +void vmcoreinfo_append_str(const char *fmt, ...); unsigned long paddr_vmcoreinfo_note(void); #define VMCOREINFO_OSRELEASE(value) \ diff --git a/include/linux/kmod.h b/include/linux/kmod.h index 0da38cf7db7..b16f6539073 100644 --- a/include/linux/kmod.h +++ b/include/linux/kmod.h @@ -32,8 +32,8 @@ extern char modprobe_path[]; /* for sysctl */ /* modprobe exit status on success, -ve on error. Return value * usually useless though. */ -extern int __request_module(bool wait, const char *name, ...) \ - __attribute__((format(printf, 2, 3))); +extern __printf(2, 3) +int __request_module(bool wait, const char *name, ...); #define request_module(mod...) __request_module(true, mod) #define request_module_nowait(mod...) __request_module(false, mod) #define try_then_request_module(x, mod...) \ diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 668729cc0fe..ad81e1c5148 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -72,8 +72,8 @@ struct kobject { unsigned int uevent_suppress:1; }; -extern int kobject_set_name(struct kobject *kobj, const char *name, ...) - __attribute__((format(printf, 2, 3))); +extern __printf(2, 3) +int kobject_set_name(struct kobject *kobj, const char *name, ...); extern int kobject_set_name_vargs(struct kobject *kobj, const char *fmt, va_list vargs); @@ -83,15 +83,13 @@ static inline const char *kobject_name(const struct kobject *kobj) } extern void kobject_init(struct kobject *kobj, struct kobj_type *ktype); -extern int __must_check kobject_add(struct kobject *kobj, - struct kobject *parent, - const char *fmt, ...) - __attribute__((format(printf, 3, 4))); -extern int __must_check kobject_init_and_add(struct kobject *kobj, - struct kobj_type *ktype, - struct kobject *parent, - const char *fmt, ...) - __attribute__((format(printf, 4, 5))); +extern __printf(3, 4) __must_check +int kobject_add(struct kobject *kobj, struct kobject *parent, + const char *fmt, ...); +extern __printf(4, 5) __must_check +int kobject_init_and_add(struct kobject *kobj, + struct kobj_type *ktype, struct kobject *parent, + const char *fmt, ...); extern void kobject_del(struct kobject *kobj); @@ -212,8 +210,8 @@ int kobject_uevent(struct kobject *kobj, enum kobject_action action); int kobject_uevent_env(struct kobject *kobj, enum kobject_action action, char *envp[]); -int add_uevent_var(struct kobj_uevent_env *env, const char *format, ...) - __attribute__((format (printf, 2, 3))); +__printf(2, 3) +int add_uevent_var(struct kobj_uevent_env *env, const char *format, ...); int kobject_action_type(const char *buf, size_t count, enum kobject_action *type); @@ -226,7 +224,7 @@ static inline int kobject_uevent_env(struct kobject *kobj, char *envp[]) { return 0; } -static inline __attribute__((format(printf, 2, 3))) +static inline __printf(2, 3) int add_uevent_var(struct kobj_uevent_env *env, const char *format, ...) { return 0; } diff --git a/include/linux/kthread.h b/include/linux/kthread.h index 1e923e5e88e..5cac19b3a26 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -4,11 +4,11 @@ #include #include +__printf(4, 5) struct task_struct *kthread_create_on_node(int (*threadfn)(void *data), void *data, int node, - const char namefmt[], ...) - __attribute__((format(printf, 4, 5))); + const char namefmt[], ...); #define kthread_create(threadfn, data, namefmt, arg...) \ kthread_create_on_node(threadfn, data, -1, namefmt, ##arg) diff --git a/include/linux/libata.h b/include/linux/libata.h index 23fa829bf7a..cafc09a64fe 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1256,13 +1256,13 @@ static inline int sata_srst_pmp(struct ata_link *link) /* * printk helpers */ -__attribute__((format (printf, 3, 4))) +__printf(3, 4) int ata_port_printk(const struct ata_port *ap, const char *level, const char *fmt, ...); -__attribute__((format (printf, 3, 4))) +__printf(3, 4) int ata_link_printk(const struct ata_link *link, const char *level, const char *fmt, ...); -__attribute__((format (printf, 3, 4))) +__printf(3, 4) int ata_dev_printk(const struct ata_device *dev, const char *level, const char *fmt, ...); @@ -1304,10 +1304,10 @@ void ata_print_version(const struct device *dev, const char *version); /* * ata_eh_info helpers */ -extern void __ata_ehi_push_desc(struct ata_eh_info *ehi, const char *fmt, ...) - __attribute__ ((format (printf, 2, 3))); -extern void ata_ehi_push_desc(struct ata_eh_info *ehi, const char *fmt, ...) - __attribute__ ((format (printf, 2, 3))); +extern __printf(2, 3) +void __ata_ehi_push_desc(struct ata_eh_info *ehi, const char *fmt, ...); +extern __printf(2, 3) +void ata_ehi_push_desc(struct ata_eh_info *ehi, const char *fmt, ...); extern void ata_ehi_clear_desc(struct ata_eh_info *ehi); static inline void ata_ehi_hotplugged(struct ata_eh_info *ehi) @@ -1321,8 +1321,8 @@ static inline void ata_ehi_hotplugged(struct ata_eh_info *ehi) /* * port description helpers */ -extern void ata_port_desc(struct ata_port *ap, const char *fmt, ...) - __attribute__ ((format (printf, 2, 3))); +extern __printf(2, 3) +void ata_port_desc(struct ata_port *ap, const char *fmt, ...); #ifdef CONFIG_PCI extern void ata_port_pbar_desc(struct ata_port *ap, int bar, ssize_t offset, const char *name); diff --git a/include/linux/mmiotrace.h b/include/linux/mmiotrace.h index 97491f78b08..c5d52780d6a 100644 --- a/include/linux/mmiotrace.h +++ b/include/linux/mmiotrace.h @@ -49,8 +49,7 @@ extern void mmiotrace_ioremap(resource_size_t offset, unsigned long size, extern void mmiotrace_iounmap(volatile void __iomem *addr); /* For anyone to insert markers. Remember trailing newline. */ -extern int mmiotrace_printk(const char *fmt, ...) - __attribute__ ((format (printf, 1, 2))); +extern __printf(1, 2) int mmiotrace_printk(const char *fmt, ...); #else /* !CONFIG_MMIOTRACE: */ static inline int is_kmmio_active(void) { @@ -71,10 +70,7 @@ static inline void mmiotrace_iounmap(volatile void __iomem *addr) { } -static inline int mmiotrace_printk(const char *fmt, ...) - __attribute__ ((format (printf, 1, 0))); - -static inline int mmiotrace_printk(const char *fmt, ...) +static inline __printf(1, 2) int mmiotrace_printk(const char *fmt, ...) { return 0; } diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index df1c836e694..cbeb5867cff 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2622,23 +2622,23 @@ static inline const char *netdev_name(const struct net_device *dev) extern int __netdev_printk(const char *level, const struct net_device *dev, struct va_format *vaf); -extern int netdev_printk(const char *level, const struct net_device *dev, - const char *format, ...) - __attribute__ ((format (printf, 3, 4))); -extern int netdev_emerg(const struct net_device *dev, const char *format, ...) - __attribute__ ((format (printf, 2, 3))); -extern int netdev_alert(const struct net_device *dev, const char *format, ...) - __attribute__ ((format (printf, 2, 3))); -extern int netdev_crit(const struct net_device *dev, const char *format, ...) - __attribute__ ((format (printf, 2, 3))); -extern int netdev_err(const struct net_device *dev, const char *format, ...) - __attribute__ ((format (printf, 2, 3))); -extern int netdev_warn(const struct net_device *dev, const char *format, ...) - __attribute__ ((format (printf, 2, 3))); -extern int netdev_notice(const struct net_device *dev, const char *format, ...) - __attribute__ ((format (printf, 2, 3))); -extern int netdev_info(const struct net_device *dev, const char *format, ...) - __attribute__ ((format (printf, 2, 3))); +extern __printf(3, 4) +int netdev_printk(const char *level, const struct net_device *dev, + const char *format, ...); +extern __printf(2, 3) +int netdev_emerg(const struct net_device *dev, const char *format, ...); +extern __printf(2, 3) +int netdev_alert(const struct net_device *dev, const char *format, ...); +extern __printf(2, 3) +int netdev_crit(const struct net_device *dev, const char *format, ...); +extern __printf(2, 3) +int netdev_err(const struct net_device *dev, const char *format, ...); +extern __printf(2, 3) +int netdev_warn(const struct net_device *dev, const char *format, ...); +extern __printf(2, 3) +int netdev_notice(const struct net_device *dev, const char *format, ...); +extern __printf(2, 3) +int netdev_info(const struct net_device *dev, const char *format, ...); #define MODULE_ALIAS_NETDEV(device) \ MODULE_ALIAS("netdev-" device) diff --git a/include/linux/printk.h b/include/linux/printk.h index 0101d55d965..f0e22f75143 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -82,22 +82,22 @@ struct va_format { * Dummy printk for disabled debugging statements to use whilst maintaining * gcc's format and side-effect checking. */ -static inline __attribute__ ((format (printf, 1, 2))) +static inline __printf(1, 2) int no_printk(const char *fmt, ...) { return 0; } -extern asmlinkage __attribute__ ((format (printf, 1, 2))) +extern asmlinkage __printf(1, 2) void early_printk(const char *fmt, ...); extern int printk_needs_cpu(int cpu); extern void printk_tick(void); #ifdef CONFIG_PRINTK -asmlinkage __attribute__ ((format (printf, 1, 0))) +asmlinkage __printf(1, 0) int vprintk(const char *fmt, va_list args); -asmlinkage __attribute__ ((format (printf, 1, 2))) __cold +asmlinkage __printf(1, 2) __cold int printk(const char *fmt, ...); /* @@ -117,12 +117,12 @@ extern int kptr_restrict; void log_buf_kexec_setup(void); void __init setup_log_buf(int early); #else -static inline __attribute__ ((format (printf, 1, 0))) +static inline __printf(1, 0) int vprintk(const char *s, va_list args) { return 0; } -static inline __attribute__ ((format (printf, 1, 2))) __cold +static inline __printf(1, 2) __cold int printk(const char *s, ...) { return 0; diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index 26f9e3612e0..d93f95e6177 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -31,7 +31,7 @@ static inline bool is_quota_modification(struct inode *inode, struct iattr *ia) #define quota_error(sb, fmt, args...) \ __quota_error((sb), __func__, fmt , ## args) -extern __attribute__((format (printf, 3, 4))) +extern __printf(3, 4) void __quota_error(struct super_block *sb, const char *func, const char *fmt, ...); diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index be720cd2038..0b69a468421 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -84,8 +84,7 @@ int seq_putc(struct seq_file *m, char c); int seq_puts(struct seq_file *m, const char *s); int seq_write(struct seq_file *seq, const void *data, size_t len); -int seq_printf(struct seq_file *, const char *, ...) - __attribute__ ((format (printf,2,3))); +__printf(2, 3) int seq_printf(struct seq_file *, const char *, ...); int seq_path(struct seq_file *, struct path *, char *); int seq_dentry(struct seq_file *, struct dentry *, char *); diff --git a/include/linux/trace_seq.h b/include/linux/trace_seq.h index 5cf397ceb72..7dadc3df0c7 100644 --- a/include/linux/trace_seq.h +++ b/include/linux/trace_seq.h @@ -29,10 +29,10 @@ trace_seq_init(struct trace_seq *s) * Currently only defined when tracing is enabled. */ #ifdef CONFIG_TRACING -extern int trace_seq_printf(struct trace_seq *s, const char *fmt, ...) - __attribute__ ((format (printf, 2, 3))); -extern int trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args) - __attribute__ ((format (printf, 2, 0))); +extern __printf(2, 3) +int trace_seq_printf(struct trace_seq *s, const char *fmt, ...); +extern __printf(2, 0) +int trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args); extern int trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary); extern int trace_print_seq(struct seq_file *m, struct trace_seq *s); diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index e727555d4ee..e86af08293a 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -77,7 +77,7 @@ struct bt_power { #define BT_POWER_FORCE_ACTIVE_OFF 0 #define BT_POWER_FORCE_ACTIVE_ON 1 -__attribute__((format (printf, 2, 3))) +__printf(2, 3) int bt_printk(const char *level, const char *fmt, ...); #define BT_INFO(fmt, arg...) bt_printk(KERN_INFO, pr_fmt(fmt), ##arg) diff --git a/include/net/netfilter/nf_log.h b/include/net/netfilter/nf_log.h index 920997f1aff..e991bd0a27a 100644 --- a/include/net/netfilter/nf_log.h +++ b/include/net/netfilter/nf_log.h @@ -53,12 +53,13 @@ int nf_log_bind_pf(u_int8_t pf, const struct nf_logger *logger); void nf_log_unbind_pf(u_int8_t pf); /* Calls the registered backend logging function */ +__printf(7, 8) void nf_log_packet(u_int8_t pf, unsigned int hooknum, const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, const struct nf_loginfo *li, - const char *fmt, ...) __attribute__ ((format(printf,7,8))); + const char *fmt, ...); #endif /* _NF_LOG_H */ diff --git a/include/net/sock.h b/include/net/sock.h index 5ac682f73d6..c6658bef7f3 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -76,8 +76,8 @@ printk(KERN_DEBUG msg); } while (0) #else /* Validate arguments and do nothing */ -static inline void __attribute__ ((format (printf, 2, 3))) -SOCK_DEBUG(struct sock *sk, const char *msg, ...) +static inline __printf(2, 3) +void SOCK_DEBUG(struct sock *sk, const char *msg, ...) { } #endif diff --git a/include/sound/core.h b/include/sound/core.h index 1fa2407c966..91d513879a7 100644 --- a/include/sound/core.h +++ b/include/sound/core.h @@ -326,9 +326,9 @@ void release_and_free_resource(struct resource *res); /* --- */ #if defined(CONFIG_SND_DEBUG) || defined(CONFIG_SND_VERBOSE_PRINTK) +__printf(4, 5) void __snd_printk(unsigned int level, const char *file, int line, - const char *format, ...) - __attribute__ ((format (printf, 4, 5))); + const char *format, ...); #else #define __snd_printk(level, file, line, format, args...) \ printk(format, ##args) diff --git a/include/sound/info.h b/include/sound/info.h index 4e94cf1ff76..5492cc40dc5 100644 --- a/include/sound/info.h +++ b/include/sound/info.h @@ -110,8 +110,8 @@ void snd_card_info_read_oss(struct snd_info_buffer *buffer); static inline void snd_card_info_read_oss(struct snd_info_buffer *buffer) {} #endif -int snd_iprintf(struct snd_info_buffer *buffer, const char *fmt, ...) \ - __attribute__ ((format (printf, 2, 3))); +__printf(2, 3) +int snd_iprintf(struct snd_info_buffer *buffer, const char *fmt, ...); int snd_info_init(void); int snd_info_done(void); diff --git a/include/sound/seq_kernel.h b/include/sound/seq_kernel.h index 3d9afb6a8c9..f352a98ce4f 100644 --- a/include/sound/seq_kernel.h +++ b/include/sound/seq_kernel.h @@ -75,9 +75,9 @@ struct snd_seq_port_callback { }; /* interface for kernel client */ +__printf(3, 4) int snd_seq_create_kernel_client(struct snd_card *card, int client_index, - const char *name_fmt, ...) - __attribute__ ((format (printf, 3, 4))); + const char *name_fmt, ...); int snd_seq_delete_kernel_client(int client); int snd_seq_kernel_client_enqueue(int client, struct snd_seq_event *ev, int atomic, int hop); int snd_seq_kernel_client_dispatch(int client, struct snd_seq_event *ev, int atomic, int hop); diff --git a/include/xen/hvc-console.h b/include/xen/hvc-console.h index 901724dc528..b62dfef15f6 100644 --- a/include/xen/hvc-console.h +++ b/include/xen/hvc-console.h @@ -6,12 +6,12 @@ extern struct console xenboot_console; #ifdef CONFIG_HVC_XEN void xen_console_resume(void); void xen_raw_console_write(const char *str); -__attribute__((format(printf, 1, 2))) +__printf(1, 2) void xen_raw_printk(const char *fmt, ...); #else static inline void xen_console_resume(void) { } static inline void xen_raw_console_write(const char *str) { } -static inline __attribute__((format(printf, 1, 2))) +static inline __printf(1, 2) void xen_raw_printk(const char *fmt, ...) { } #endif diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h index aceeca799fd..b9f9fb5af0d 100644 --- a/include/xen/xenbus.h +++ b/include/xen/xenbus.h @@ -156,9 +156,9 @@ int xenbus_scanf(struct xenbus_transaction t, __attribute__((format(scanf, 4, 5))); /* Single printf and write: returns -errno or 0. */ +__printf(4, 5) int xenbus_printf(struct xenbus_transaction t, - const char *dir, const char *node, const char *fmt, ...) - __attribute__((format(printf, 4, 5))); + const char *dir, const char *node, const char *fmt, ...); /* Generic read function: NULL-terminated triples of name, * sprintf-style type string, and pointer. Returns 0 or errno.*/ @@ -200,11 +200,11 @@ int xenbus_watch_path(struct xenbus_device *dev, const char *path, struct xenbus_watch *watch, void (*callback)(struct xenbus_watch *, const char **, unsigned int)); +__printf(4, 5) int xenbus_watch_pathfmt(struct xenbus_device *dev, struct xenbus_watch *watch, void (*callback)(struct xenbus_watch *, const char **, unsigned int), - const char *pathfmt, ...) - __attribute__ ((format (printf, 4, 5))); + const char *pathfmt, ...); int xenbus_switch_state(struct xenbus_device *dev, enum xenbus_state new_state); int xenbus_grant_ring(struct xenbus_device *dev, unsigned long ring_mfn); @@ -223,9 +223,9 @@ int xenbus_free_evtchn(struct xenbus_device *dev, int port); enum xenbus_state xenbus_read_driver_state(const char *path); -__attribute__((format(printf, 3, 4))) +__printf(3, 4) void xenbus_dev_error(struct xenbus_device *dev, int err, const char *fmt, ...); -__attribute__((format(printf, 3, 4))) +__printf(3, 4) void xenbus_dev_fatal(struct xenbus_device *dev, int err, const char *fmt, ...); const char *xenbus_strstate(enum xenbus_state state); -- cgit v1.2.3 From 0556dc340e5159cdff925a5ab7f3a72f49745661 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 31 Oct 2011 17:11:48 -0700 Subject: backlight: fix broken regulator API usage in l4f00242t03 The regulator support in the l4f00242t03 is very non-idiomatic. Rather than requesting the regulators based on the device name and the supply names used by the device the driver requires boards to pass system specific supply names around through platform data. The driver also conditionally requests the regulators based on this platform data, adding unneeded conditional code to the driver. Fix this by removing the platform data and converting to the standard idiom, also updating all in tree users of the driver. As no datasheet appears to be available for the LCD I'm guessing the names for the supplies based on the existing users and I've no ability to do anything more than compile test. The use of regulator_set_voltage() in the driver is also problematic, since fixed voltages are required the expectation would be that the voltages would be fixed in the constraints set by the machines rather than manually configured by the driver, but is less problematic. Signed-off-by: Mark Brown Tested-by: Fabio Estevam Cc: Richard Purdie Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/spi/l4f00242t03.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/spi/l4f00242t03.h b/include/linux/spi/l4f00242t03.h index aee1dbda4ed..bc8677c8eba 100644 --- a/include/linux/spi/l4f00242t03.h +++ b/include/linux/spi/l4f00242t03.h @@ -24,8 +24,6 @@ struct l4f00242t03_pdata { unsigned int reset_gpio; unsigned int data_enable_gpio; - const char *io_supply; /* will be set to 1.8 V */ - const char *core_supply; /* will be set to 2.8 V */ }; #endif /* _INCLUDE_LINUX_SPI_L4F00242T03_H_ */ -- cgit v1.2.3 From f59b6f9f323ff1b4567a69f9063cdd8bb57805e6 Mon Sep 17 00:00:00 2001 From: Magnus Damm Date: Mon, 31 Oct 2011 17:11:55 -0700 Subject: leds: Renesas TPU LED driver Add V2 of the LED driver for a single timer channel for the TPU hardware block commonly found in Renesas SoCs. The driver has been written with optimal Power Management in mind, so to save power the LED is driven as a regular GPIO pin in case of maximum brightness and power off which allows the TPU hardware to be idle and which in turn allows the clocks to be stopped and the power domain to be turned off transparently. Any other brightness level requires use of the TPU hardware in PWM mode. TPU hardware device clocks and power are managed through Runtime PM. System suspend and resume is known to be working - during suspend the LED is set to off by the generic LED code. The TPU hardware timer is equipeed with a 16-bit counter together with an up-to-divide-by-64 prescaler which makes the hardware suitable for brightness control. Hardware blink is unsupported. The LED PWM waveform has been verified with a Fluke 123 Scope meter on a sh7372 Mackerel board. Tested with experimental sh7372 A3SP power domain patches. Platform device bind/unbind tested ok. V2 has been tested on the DS2 LED of the sh73a0-based AG5EVM. [axel.lin@gmail.com: include linux/module.h] Signed-off-by: Magnus Damm Cc: Paul Mundt Cc: Richard Purdie Cc: Grant Likely Signed-off-by: Axel Lin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/leds-renesas-tpu.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) create mode 100644 include/linux/leds-renesas-tpu.h (limited to 'include') diff --git a/include/linux/leds-renesas-tpu.h b/include/linux/leds-renesas-tpu.h new file mode 100644 index 00000000000..055387086fc --- /dev/null +++ b/include/linux/leds-renesas-tpu.h @@ -0,0 +1,14 @@ +#ifndef __LEDS_RENESAS_TPU_H__ +#define __LEDS_RENESAS_TPU_H__ + +struct led_renesas_tpu_config { + char *name; + unsigned pin_gpio_fn; + unsigned pin_gpio; + unsigned int channel_offset; + unsigned int timer_bit; + unsigned int max_brightness; + unsigned int refresh_rate; +}; + +#endif /* __LEDS_RENESAS_TPU_H__ */ -- cgit v1.2.3 From 2b67c95b74f17c13c7b3a990540c9dd9b4a8480d Mon Sep 17 00:00:00 2001 From: Magnus Damm Date: Mon, 31 Oct 2011 17:12:09 -0700 Subject: drivers/leds/leds-renesas-tpu.c: move Renesas TPU LED driver platform data Use the platform_data include directory for the TPU LED driver, as suggested by Paul Mundt. Signed-off-by: Magnus Damm Cc: Paul Mundt Cc: Richard Purdie Cc: Grant Likely Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/leds-renesas-tpu.h | 14 -------------- include/linux/platform_data/leds-renesas-tpu.h | 14 ++++++++++++++ 2 files changed, 14 insertions(+), 14 deletions(-) delete mode 100644 include/linux/leds-renesas-tpu.h create mode 100644 include/linux/platform_data/leds-renesas-tpu.h (limited to 'include') diff --git a/include/linux/leds-renesas-tpu.h b/include/linux/leds-renesas-tpu.h deleted file mode 100644 index 055387086fc..00000000000 --- a/include/linux/leds-renesas-tpu.h +++ /dev/null @@ -1,14 +0,0 @@ -#ifndef __LEDS_RENESAS_TPU_H__ -#define __LEDS_RENESAS_TPU_H__ - -struct led_renesas_tpu_config { - char *name; - unsigned pin_gpio_fn; - unsigned pin_gpio; - unsigned int channel_offset; - unsigned int timer_bit; - unsigned int max_brightness; - unsigned int refresh_rate; -}; - -#endif /* __LEDS_RENESAS_TPU_H__ */ diff --git a/include/linux/platform_data/leds-renesas-tpu.h b/include/linux/platform_data/leds-renesas-tpu.h new file mode 100644 index 00000000000..055387086fc --- /dev/null +++ b/include/linux/platform_data/leds-renesas-tpu.h @@ -0,0 +1,14 @@ +#ifndef __LEDS_RENESAS_TPU_H__ +#define __LEDS_RENESAS_TPU_H__ + +struct led_renesas_tpu_config { + char *name; + unsigned pin_gpio_fn; + unsigned pin_gpio; + unsigned int channel_offset; + unsigned int timer_bit; + unsigned int max_brightness; + unsigned int refresh_rate; +}; + +#endif /* __LEDS_RENESAS_TPU_H__ */ -- cgit v1.2.3 From 55036ba76b2d2fd53b5c00993fcec5ed56e83922 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 31 Oct 2011 17:12:41 -0700 Subject: lib: rename pack_hex_byte() to hex_byte_pack() As suggested by Andrew Morton in [1] there is better to have most significant part first in the function name. [1] https://lkml.org/lkml/2011/9/20/22 There is no functional change. Signed-off-by: Andy Shevchenko Cc: Jesper Nilsson Cc: David Howells Cc: Koichi Yasutake Cc: Jason Wessel Cc: Mimi Zohar Cc: James Morris Cc: OGAWA Hirofumi Cc: "John W. Linville" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index e40c950e1d6..4824f26a0dc 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -372,13 +372,18 @@ extern const char hex_asc[]; #define hex_asc_lo(x) hex_asc[((x) & 0x0f)] #define hex_asc_hi(x) hex_asc[((x) & 0xf0) >> 4] -static inline char *pack_hex_byte(char *buf, u8 byte) +static inline char *hex_byte_pack(char *buf, u8 byte) { *buf++ = hex_asc_hi(byte); *buf++ = hex_asc_lo(byte); return buf; } +static inline char * __deprecated pack_hex_byte(char *buf, u8 byte) +{ + return hex_byte_pack(buf, byte); +} + extern int hex_to_bin(char ch); extern int __must_check hex2bin(u8 *dst, const char *src, size_t count); -- cgit v1.2.3 From fc23af34b00ef444eec088f744983b9ca6c7f5d1 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Mon, 31 Oct 2011 17:13:08 -0700 Subject: llist-return-whether-list-is-empty-before-adding-in-llist_add-fix clarify comment Cc: Huang Ying Cc: Mathieu Desnoyers Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/llist.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/llist.h b/include/linux/llist.h index 7287734e08d..801b44b07aa 100644 --- a/include/linux/llist.h +++ b/include/linux/llist.h @@ -148,7 +148,7 @@ static inline struct llist_node *llist_next(struct llist_node *node) * @new: new entry to be added * @head: the head for your lock-less list * - * Return whether list is empty before adding. + * Returns true if the list was empty prior to adding this entry. */ static inline bool llist_add(struct llist_node *new, struct llist_head *head) { -- cgit v1.2.3 From 67d0a0754455f89ef3946946159d8ec9e45ce33a Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Mon, 31 Oct 2011 17:13:10 -0700 Subject: kernel.h/checkpatch: mark strict_strto and simple_strto as obsolete Mark obsolete/deprecated strict_strto and simple_strto functions and macros as obsolete. Update checkpatch to warn about their use. Signed-off-by: Joe Perches Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 4824f26a0dc..4c0d3b2fd5f 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -287,6 +287,8 @@ static inline int __must_check kstrtos32_from_user(const char __user *s, size_t return kstrtoint_from_user(s, count, base, res); } +/* Obsolete, do not use. Use kstrto instead */ + extern unsigned long simple_strtoul(const char *,char **,unsigned int); extern long simple_strtol(const char *,char **,unsigned int); extern unsigned long long simple_strtoull(const char *,char **,unsigned int); @@ -296,6 +298,8 @@ extern long long simple_strtoll(const char *,char **,unsigned int); #define strict_strtoull kstrtoull #define strict_strtoll kstrtoll +/* lib/printf utilities */ + extern __printf(2, 3) int sprintf(char *buf, const char * fmt, ...); extern __printf(2, 0) int vsprintf(char *buf, const char *, va_list); extern __printf(3, 4) -- cgit v1.2.3