From 6a46079cf57a7f7758e8b926980a4f852f89b34d Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 16 Sep 2009 11:50:15 +0200 Subject: HWPOISON: The high level memory error handler in the VM v7 Add the high level memory handler that poisons pages that got corrupted by hardware (typically by a two bit flip in a DIMM or a cache) on the Linux level. The goal is to prevent everyone from accessing these pages in the future. This done at the VM level by marking a page hwpoisoned and doing the appropriate action based on the type of page it is. The code that does this is portable and lives in mm/memory-failure.c To quote the overview comment: High level machine check handler. Handles pages reported by the hardware as being corrupted usually due to a 2bit ECC memory or cache failure. This focuses on pages detected as corrupted in the background. When the current CPU tries to consume corruption the currently running process can just be killed directly instead. This implies that if the error cannot be handled for some reason it's safe to just ignore it because no corruption has been consumed yet. Instead when that happens another machine check will happen. Handles page cache pages in various states. The tricky part here is that we can access any page asynchronous to other VM users, because memory failures could happen anytime and anywhere, possibly violating some of their assumptions. This is why this code has to be extremely careful. Generally it tries to use normal locking rules, as in get the standard locks, even if that means the error handling takes potentially a long time. Some of the operations here are somewhat inefficient and have non linear algorithmic complexity, because the data structures have not been optimized for this case. This is in particular the case for the mapping from a vma to a process. Since this case is expected to be rare we hope we can get away with this. There are in principle two strategies to kill processes on poison: - just unmap the data and wait for an actual reference before killing - kill as soon as corruption is detected. Both have advantages and disadvantages and should be used in different situations. Right now both are implemented and can be switched with a new sysctl vm.memory_failure_early_kill The default is early kill. The patch does some rmap data structure walking on its own to collect processes to kill. This is unusual because normally all rmap data structure knowledge is in rmap.c only. I put it here for now to keep everything together and rmap knowledge has been seeping out anyways Includes contributions from Johannes Weiner, Chris Mason, Fengguang Wu, Nick Piggin (who did a lot of great work) and others. Cc: npiggin@suse.de Cc: riel@redhat.com Signed-off-by: Andi Kleen Acked-by: Rik van Riel Reviewed-by: Hidehiro Kawai --- fs/proc/meminfo.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'fs/proc') diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index d5c410d47fa..78faedcb0a8 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -95,7 +95,11 @@ static int meminfo_proc_show(struct seq_file *m, void *v) "Committed_AS: %8lu kB\n" "VmallocTotal: %8lu kB\n" "VmallocUsed: %8lu kB\n" - "VmallocChunk: %8lu kB\n", + "VmallocChunk: %8lu kB\n" +#ifdef CONFIG_MEMORY_FAILURE + "HardwareCorrupted: %8lu kB\n" +#endif + , K(i.totalram), K(i.freeram), K(i.bufferram), @@ -140,6 +144,9 @@ static int meminfo_proc_show(struct seq_file *m, void *v) (unsigned long)VMALLOC_TOTAL >> 10, vmi.used >> 10, vmi.largest_chunk >> 10 +#ifdef CONFIG_MEMORY_FAILURE + ,atomic_long_read(&mce_bad_pages) << (PAGE_SHIFT - 10) +#endif ); hugetlb_report_meminfo(m); -- cgit v1.2.3 From c6a7f5728a1db45d30df55a01adc130b4ab0327c Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Mon, 21 Sep 2009 17:01:32 -0700 Subject: mm: oom analysis: Show kernel stack usage in /proc/meminfo and OOM log output The amount of memory allocated to kernel stacks can become significant and cause OOM conditions. However, we do not display the amount of memory consumed by stacks. Add code to display the amount of memory used for stacks in /proc/meminfo. Signed-off-by: KOSAKI Motohiro Reviewed-by: Christoph Lameter Reviewed-by: Minchan Kim Reviewed-by: Rik van Riel Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/node.c | 3 +++ fs/proc/meminfo.c | 2 ++ include/linux/mmzone.h | 3 ++- kernel/fork.c | 11 +++++++++++ mm/page_alloc.c | 3 +++ mm/vmstat.c | 1 + 6 files changed, 22 insertions(+), 1 deletion(-) (limited to 'fs/proc') diff --git a/drivers/base/node.c b/drivers/base/node.c index 91d4087b403..b560c17f6d4 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -85,6 +85,7 @@ static ssize_t node_read_meminfo(struct sys_device * dev, "Node %d FilePages: %8lu kB\n" "Node %d Mapped: %8lu kB\n" "Node %d AnonPages: %8lu kB\n" + "Node %d KernelStack: %8lu kB\n" "Node %d PageTables: %8lu kB\n" "Node %d NFS_Unstable: %8lu kB\n" "Node %d Bounce: %8lu kB\n" @@ -116,6 +117,8 @@ static ssize_t node_read_meminfo(struct sys_device * dev, nid, K(node_page_state(nid, NR_FILE_PAGES)), nid, K(node_page_state(nid, NR_FILE_MAPPED)), nid, K(node_page_state(nid, NR_ANON_PAGES)), + nid, node_page_state(nid, NR_KERNEL_STACK) * + THREAD_SIZE / 1024, nid, K(node_page_state(nid, NR_PAGETABLE)), nid, K(node_page_state(nid, NR_UNSTABLE_NFS)), nid, K(node_page_state(nid, NR_BOUNCE)), diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index d5c410d47fa..1fc588f430e 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -84,6 +84,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v) "Slab: %8lu kB\n" "SReclaimable: %8lu kB\n" "SUnreclaim: %8lu kB\n" + "KernelStack: %8lu kB\n" "PageTables: %8lu kB\n" #ifdef CONFIG_QUICKLIST "Quicklists: %8lu kB\n" @@ -128,6 +129,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v) global_page_state(NR_SLAB_UNRECLAIMABLE)), K(global_page_state(NR_SLAB_RECLAIMABLE)), K(global_page_state(NR_SLAB_UNRECLAIMABLE)), + global_page_state(NR_KERNEL_STACK) * THREAD_SIZE / 1024, K(global_page_state(NR_PAGETABLE)), #ifdef CONFIG_QUICKLIST K(quicklist_total_size()), diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 88959853737..d9335b8de84 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -94,10 +94,11 @@ enum zone_stat_item { NR_SLAB_RECLAIMABLE, NR_SLAB_UNRECLAIMABLE, NR_PAGETABLE, /* used for pagetables */ + NR_KERNEL_STACK, + /* Second 128 byte cacheline */ NR_UNSTABLE_NFS, /* NFS unstable pages */ NR_BOUNCE, NR_VMSCAN_WRITE, - /* Second 128 byte cacheline */ NR_WRITEBACK_TEMP, /* Writeback using temporary buffers */ #ifdef CONFIG_NUMA NUMA_HIT, /* allocated in intended node */ diff --git a/kernel/fork.c b/kernel/fork.c index 2cebfb23b0b..d4638c8cc19 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -136,9 +136,17 @@ struct kmem_cache *vm_area_cachep; /* SLAB cache for mm_struct structures (tsk->mm) */ static struct kmem_cache *mm_cachep; +static void account_kernel_stack(struct thread_info *ti, int account) +{ + struct zone *zone = page_zone(virt_to_page(ti)); + + mod_zone_page_state(zone, NR_KERNEL_STACK, account); +} + void free_task(struct task_struct *tsk) { prop_local_destroy_single(&tsk->dirties); + account_kernel_stack(tsk->stack, -1); free_thread_info(tsk->stack); rt_mutex_debug_task_free(tsk); ftrace_graph_exit_task(tsk); @@ -253,6 +261,9 @@ static struct task_struct *dup_task_struct(struct task_struct *orig) tsk->btrace_seq = 0; #endif tsk->splice_pipe = NULL; + + account_kernel_stack(ti, 1); + return tsk; out: diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 494c09196c3..4e050f325eb 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2177,6 +2177,7 @@ void show_free_areas(void) " mapped:%lukB" " slab_reclaimable:%lukB" " slab_unreclaimable:%lukB" + " kernel_stack:%lukB" " pagetables:%lukB" " unstable:%lukB" " bounce:%lukB" @@ -2201,6 +2202,8 @@ void show_free_areas(void) K(zone_page_state(zone, NR_FILE_MAPPED)), K(zone_page_state(zone, NR_SLAB_RECLAIMABLE)), K(zone_page_state(zone, NR_SLAB_UNRECLAIMABLE)), + zone_page_state(zone, NR_KERNEL_STACK) * + THREAD_SIZE / 1024, K(zone_page_state(zone, NR_PAGETABLE)), K(zone_page_state(zone, NR_UNSTABLE_NFS)), K(zone_page_state(zone, NR_BOUNCE)), diff --git a/mm/vmstat.c b/mm/vmstat.c index 138bed53706..ceda39b63d7 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -639,6 +639,7 @@ static const char * const vmstat_text[] = { "nr_slab_reclaimable", "nr_slab_unreclaimable", "nr_page_table_pages", + "nr_kernel_stack", "nr_unstable", "nr_bounce", "nr_vmscan_write", -- cgit v1.2.3 From 4b02108ac1b3354a22b0d83c684797692efdc395 Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Mon, 21 Sep 2009 17:01:33 -0700 Subject: mm: oom analysis: add shmem vmstat Recently we encountered OOM problems due to memory use of the GEM cache. Generally a large amuont of Shmem/Tmpfs pages tend to create a memory shortage problem. We often use the following calculation to determine the amount of shmem pages: shmem = NR_ACTIVE_ANON + NR_INACTIVE_ANON - NR_ANON_PAGES however the expression does not consider isolated and mlocked pages. This patch adds explicit accounting for pages used by shmem and tmpfs. Signed-off-by: KOSAKI Motohiro Acked-by: Rik van Riel Reviewed-by: Christoph Lameter Acked-by: Wu Fengguang Cc: David Rientjes Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/node.c | 2 ++ fs/proc/meminfo.c | 2 ++ include/linux/mmzone.h | 1 + mm/filemap.c | 4 ++++ mm/migrate.c | 5 ++++- mm/page_alloc.c | 5 ++++- mm/vmstat.c | 2 +- 7 files changed, 18 insertions(+), 3 deletions(-) (limited to 'fs/proc') diff --git a/drivers/base/node.c b/drivers/base/node.c index b560c17f6d4..1fe5536d404 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -85,6 +85,7 @@ static ssize_t node_read_meminfo(struct sys_device * dev, "Node %d FilePages: %8lu kB\n" "Node %d Mapped: %8lu kB\n" "Node %d AnonPages: %8lu kB\n" + "Node %d Shmem: %8lu kB\n" "Node %d KernelStack: %8lu kB\n" "Node %d PageTables: %8lu kB\n" "Node %d NFS_Unstable: %8lu kB\n" @@ -117,6 +118,7 @@ static ssize_t node_read_meminfo(struct sys_device * dev, nid, K(node_page_state(nid, NR_FILE_PAGES)), nid, K(node_page_state(nid, NR_FILE_MAPPED)), nid, K(node_page_state(nid, NR_ANON_PAGES)), + nid, K(node_page_state(nid, NR_SHMEM)), nid, node_page_state(nid, NR_KERNEL_STACK) * THREAD_SIZE / 1024, nid, K(node_page_state(nid, NR_PAGETABLE)), diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index 1fc588f430e..171e052c07b 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -81,6 +81,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v) "Writeback: %8lu kB\n" "AnonPages: %8lu kB\n" "Mapped: %8lu kB\n" + "Shmem: %8lu kB\n" "Slab: %8lu kB\n" "SReclaimable: %8lu kB\n" "SUnreclaim: %8lu kB\n" @@ -125,6 +126,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v) K(global_page_state(NR_WRITEBACK)), K(global_page_state(NR_ANON_PAGES)), K(global_page_state(NR_FILE_MAPPED)), + K(global_page_state(NR_SHMEM)), K(global_page_state(NR_SLAB_RECLAIMABLE) + global_page_state(NR_SLAB_UNRECLAIMABLE)), K(global_page_state(NR_SLAB_RECLAIMABLE)), diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index d9335b8de84..b3583b93b77 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -100,6 +100,7 @@ enum zone_stat_item { NR_BOUNCE, NR_VMSCAN_WRITE, NR_WRITEBACK_TEMP, /* Writeback using temporary buffers */ + NR_SHMEM, /* shmem pages (included tmpfs/GEM pages) */ #ifdef CONFIG_NUMA NUMA_HIT, /* allocated in intended node */ NUMA_MISS, /* allocated in non intended node */ diff --git a/mm/filemap.c b/mm/filemap.c index dd51c68e2b8..bcc7372aebb 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -119,6 +119,8 @@ void __remove_from_page_cache(struct page *page) page->mapping = NULL; mapping->nrpages--; __dec_zone_page_state(page, NR_FILE_PAGES); + if (PageSwapBacked(page)) + __dec_zone_page_state(page, NR_SHMEM); BUG_ON(page_mapped(page)); /* @@ -431,6 +433,8 @@ int add_to_page_cache_locked(struct page *page, struct address_space *mapping, if (likely(!error)) { mapping->nrpages++; __inc_zone_page_state(page, NR_FILE_PAGES); + if (PageSwapBacked(page)) + __inc_zone_page_state(page, NR_SHMEM); spin_unlock_irq(&mapping->tree_lock); } else { page->mapping = NULL; diff --git a/mm/migrate.c b/mm/migrate.c index 0edeac91348..37143b92448 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -312,7 +312,10 @@ static int migrate_page_move_mapping(struct address_space *mapping, */ __dec_zone_page_state(page, NR_FILE_PAGES); __inc_zone_page_state(newpage, NR_FILE_PAGES); - + if (PageSwapBacked(page)) { + __dec_zone_page_state(page, NR_SHMEM); + __inc_zone_page_state(newpage, NR_SHMEM); + } spin_unlock_irq(&mapping->tree_lock); return 0; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 4e050f325eb..e50c22545b8 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2139,7 +2139,7 @@ void show_free_areas(void) " unevictable:%lu" " dirty:%lu writeback:%lu unstable:%lu buffer:%lu\n" " free:%lu slab_reclaimable:%lu slab_unreclaimable:%lu\n" - " mapped:%lu pagetables:%lu bounce:%lu\n", + " mapped:%lu shmem:%lu pagetables:%lu bounce:%lu\n", global_page_state(NR_ACTIVE_ANON), global_page_state(NR_ACTIVE_FILE), global_page_state(NR_INACTIVE_ANON), @@ -2153,6 +2153,7 @@ void show_free_areas(void) global_page_state(NR_SLAB_RECLAIMABLE), global_page_state(NR_SLAB_UNRECLAIMABLE), global_page_state(NR_FILE_MAPPED), + global_page_state(NR_SHMEM), global_page_state(NR_PAGETABLE), global_page_state(NR_BOUNCE)); @@ -2175,6 +2176,7 @@ void show_free_areas(void) " dirty:%lukB" " writeback:%lukB" " mapped:%lukB" + " shmem:%lukB" " slab_reclaimable:%lukB" " slab_unreclaimable:%lukB" " kernel_stack:%lukB" @@ -2200,6 +2202,7 @@ void show_free_areas(void) K(zone_page_state(zone, NR_FILE_DIRTY)), K(zone_page_state(zone, NR_WRITEBACK)), K(zone_page_state(zone, NR_FILE_MAPPED)), + K(zone_page_state(zone, NR_SHMEM)), K(zone_page_state(zone, NR_SLAB_RECLAIMABLE)), K(zone_page_state(zone, NR_SLAB_UNRECLAIMABLE)), zone_page_state(zone, NR_KERNEL_STACK) * diff --git a/mm/vmstat.c b/mm/vmstat.c index ceda39b63d7..7214a451125 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -644,7 +644,7 @@ static const char * const vmstat_text[] = { "nr_bounce", "nr_vmscan_write", "nr_writeback_temp", - + "nr_shmem", #ifdef CONFIG_NUMA "numa_hit", "numa_miss", -- cgit v1.2.3 From 9a840895147b12de5cdd633c600b38686840ee53 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Mon, 21 Sep 2009 17:02:01 -0700 Subject: ksm: identify PageKsm pages KSM will need to identify its kernel merged pages unambiguously, and /proc/kpageflags will probably like to do so too. Since KSM will only be substituting anonymous pages, statistics are best preserved by making a PageKsm page a special PageAnon page: one with no anon_vma. But KSM then needs its own page_add_ksm_rmap() - keep it in ksm.h near PageKsm; and do_wp_page() must COW them, unlike singly mapped PageAnons. Signed-off-by: Hugh Dickins Signed-off-by: Chris Wright Signed-off-by: Izik Eidus Cc: Wu Fengguang Cc: Andrea Arcangeli Cc: Rik van Riel Cc: Wu Fengguang Cc: Balbir Singh Cc: Hugh Dickins Cc: KAMEZAWA Hiroyuki Cc: Lee Schermerhorn Cc: Avi Kivity Cc: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/page.c | 5 +++++ include/linux/ksm.h | 29 +++++++++++++++++++++++++++++ mm/memory.c | 3 ++- 3 files changed, 36 insertions(+), 1 deletion(-) (limited to 'fs/proc') diff --git a/fs/proc/page.c b/fs/proc/page.c index 2707c6c7a20..2281c2cbfe2 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -2,6 +2,7 @@ #include #include #include +#include #include #include #include @@ -95,6 +96,8 @@ static const struct file_operations proc_kpagecount_operations = { #define KPF_UNEVICTABLE 18 #define KPF_NOPAGE 20 +#define KPF_KSM 21 + /* kernel hacking assistances * WARNING: subject to change, never rely on them! */ @@ -137,6 +140,8 @@ static u64 get_uflags(struct page *page) u |= 1 << KPF_MMAP; if (PageAnon(page)) u |= 1 << KPF_ANON; + if (PageKsm(page)) + u |= 1 << KPF_KSM; /* * compound pages: export both head/tail info diff --git a/include/linux/ksm.h b/include/linux/ksm.h index eb2a448981e..a485c14ecd5 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -10,6 +10,7 @@ #include #include #include +#include #ifdef CONFIG_KSM int ksm_madvise(struct vm_area_struct *vma, unsigned long start, @@ -29,6 +30,27 @@ static inline void ksm_exit(struct mm_struct *mm) if (test_bit(MMF_VM_MERGEABLE, &mm->flags)) __ksm_exit(mm); } + +/* + * A KSM page is one of those write-protected "shared pages" or "merged pages" + * which KSM maps into multiple mms, wherever identical anonymous page content + * is found in VM_MERGEABLE vmas. It's a PageAnon page, with NULL anon_vma. + */ +static inline int PageKsm(struct page *page) +{ + return ((unsigned long)page->mapping == PAGE_MAPPING_ANON); +} + +/* + * But we have to avoid the checking which page_add_anon_rmap() performs. + */ +static inline void page_add_ksm_rmap(struct page *page) +{ + if (atomic_inc_and_test(&page->_mapcount)) { + page->mapping = (void *) PAGE_MAPPING_ANON; + __inc_zone_page_state(page, NR_ANON_PAGES); + } +} #else /* !CONFIG_KSM */ static inline int ksm_madvise(struct vm_area_struct *vma, unsigned long start, @@ -45,6 +67,13 @@ static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) static inline void ksm_exit(struct mm_struct *mm) { } + +static inline int PageKsm(struct page *page) +{ + return 0; +} + +/* No stub required for page_add_ksm_rmap(page) */ #endif /* !CONFIG_KSM */ #endif diff --git a/mm/memory.c b/mm/memory.c index 7a61a11f186..1a435b81876 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -45,6 +45,7 @@ #include #include #include +#include #include #include #include @@ -1974,7 +1975,7 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, * Take out anonymous pages first, anonymous shared vmas are * not dirty accountable. */ - if (PageAnon(old_page)) { + if (PageAnon(old_page) && !PageKsm(old_page)) { if (!trylock_page(old_page)) { page_cache_get(old_page); pte_unmap_unlock(page_table, ptl); -- cgit v1.2.3 From 398499d5f3613c47f2143b8c54a04efb5d7a6da9 Mon Sep 17 00:00:00 2001 From: "Moussa A. Ba" Date: Mon, 21 Sep 2009 17:02:29 -0700 Subject: pagemap clear_refs: modify to specify anon or mapped vma clearing The patch makes the clear_refs more versatile in adding the option to select anonymous pages or file backed pages for clearing. This addition has a measurable impact on user space application performance as it decreases the number of pagewalks in scenarios where one is only interested in a specific type of page (anonymous or file mapped). The patch adds anonymous and file backed filters to the clear_refs interface. echo 1 > /proc/PID/clear_refs resets the bits on all pages echo 2 > /proc/PID/clear_refs resets the bits on anonymous pages only echo 3 > /proc/PID/clear_refs resets the bits on file backed pages only Any other value is ignored Signed-off-by: Moussa A. Ba Signed-off-by: Jared E. Hulbert Acked-by: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/filesystems/proc.txt | 13 +++++++++++++ fs/proc/task_mmu.c | 28 ++++++++++++++++++++++++---- 2 files changed, 37 insertions(+), 4 deletions(-) (limited to 'fs/proc') diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index 1c96cb6c797..ae7f8bb1b7b 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -375,6 +375,19 @@ of memory currently marked as referenced or accessed. This file is only present if the CONFIG_MMU kernel configuration option is enabled. +The /proc/PID/clear_refs is used to reset the PG_Referenced and ACCESSED/YOUNG +bits on both physical and virtual pages associated with a process. +To clear the bits for all the pages associated with the process + > echo 1 > /proc/PID/clear_refs + +To clear the bits for the anonymous pages associated with the process + > echo 2 > /proc/PID/clear_refs + +To clear the bits for the file mapped pages associated with the process + > echo 3 > /proc/PID/clear_refs +Any other value written to /proc/PID/clear_refs will have no effect. + + 1.2 Kernel data --------------- diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 9bd8be1d235..59e98fea34a 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -465,6 +465,10 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr, return 0; } +#define CLEAR_REFS_ALL 1 +#define CLEAR_REFS_ANON 2 +#define CLEAR_REFS_MAPPED 3 + static ssize_t clear_refs_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { @@ -472,13 +476,15 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, char buffer[PROC_NUMBUF], *end; struct mm_struct *mm; struct vm_area_struct *vma; + int type; memset(buffer, 0, sizeof(buffer)); if (count > sizeof(buffer) - 1) count = sizeof(buffer) - 1; if (copy_from_user(buffer, buf, count)) return -EFAULT; - if (!simple_strtol(buffer, &end, 0)) + type = simple_strtol(buffer, &end, 0); + if (type < CLEAR_REFS_ALL || type > CLEAR_REFS_MAPPED) return -EINVAL; if (*end == '\n') end++; @@ -494,9 +500,23 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, down_read(&mm->mmap_sem); for (vma = mm->mmap; vma; vma = vma->vm_next) { clear_refs_walk.private = vma; - if (!is_vm_hugetlb_page(vma)) - walk_page_range(vma->vm_start, vma->vm_end, - &clear_refs_walk); + if (is_vm_hugetlb_page(vma)) + continue; + /* + * Writing 1 to /proc/pid/clear_refs affects all pages. + * + * Writing 2 to /proc/pid/clear_refs only affects + * Anonymous pages. + * + * Writing 3 to /proc/pid/clear_refs only affects file + * mapped pages. + */ + if (type == CLEAR_REFS_ANON && vma->vm_file) + continue; + if (type == CLEAR_REFS_MAPPED && !vma->vm_file) + continue; + walk_page_range(vma->vm_start, vma->vm_end, + &clear_refs_walk); } flush_tlb_mm(mm); up_read(&mm->mmap_sem); -- cgit v1.2.3 From 73d7c33e81aed92ac185950a20407c1a2ea65a83 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Mon, 21 Sep 2009 17:02:35 -0700 Subject: kcore: /proc/kcore should use vread /proc/kcore has its own routine to access vmallc area. It can be replaced with vread(). And by this, /proc/kcore can do safe access to vmalloc area. Signed-off-by: KAMEZAWA Hiroyuki Cc: WANG Cong Cc: Mike Smith Cc: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/kcore.c | 35 ++--------------------------------- 1 file changed, 2 insertions(+), 33 deletions(-) (limited to 'fs/proc') diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index 59b43a06887..f06f45b4218 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -328,43 +328,12 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) return -EFAULT; } else if (is_vmalloc_addr((void *)start)) { char * elf_buf; - struct vm_struct *m; - unsigned long curstart = start; - unsigned long cursize = tsz; elf_buf = kzalloc(tsz, GFP_KERNEL); if (!elf_buf) return -ENOMEM; - - read_lock(&vmlist_lock); - for (m=vmlist; m && cursize; m=m->next) { - unsigned long vmstart; - unsigned long vmsize; - unsigned long msize = m->size - PAGE_SIZE; - - if (((unsigned long)m->addr + msize) < - curstart) - continue; - if ((unsigned long)m->addr > (curstart + - cursize)) - break; - vmstart = (curstart < (unsigned long)m->addr ? - (unsigned long)m->addr : curstart); - if (((unsigned long)m->addr + msize) > - (curstart + cursize)) - vmsize = curstart + cursize - vmstart; - else - vmsize = (unsigned long)m->addr + - msize - vmstart; - curstart = vmstart + vmsize; - cursize -= vmsize; - /* don't dump ioremap'd stuff! (TA) */ - if (m->flags & VM_IOREMAP) - continue; - memcpy(elf_buf + (vmstart - start), - (char *)vmstart, vmsize); - } - read_unlock(&vmlist_lock); + vread(elf_buf, (char *)start, tsz); + /* we have to zero-fill user buffer even if no read */ if (copy_to_user(buffer, elf_buf, tsz)) { kfree(elf_buf); return -EFAULT; -- cgit v1.2.3 From 28b83c5193e7ab951e402252278f2cc79dc4d298 Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Mon, 21 Sep 2009 17:03:13 -0700 Subject: oom: move oom_adj value from task_struct to signal_struct Currently, OOM logic callflow is here. __out_of_memory() select_bad_process() for each task badness() calculate badness of one task oom_kill_process() search child oom_kill_task() kill target task and mm shared tasks with it example, process-A have two thread, thread-A and thread-B and it have very fat memory and each thread have following oom_adj and oom_score. thread-A: oom_adj = OOM_DISABLE, oom_score = 0 thread-B: oom_adj = 0, oom_score = very-high Then, select_bad_process() select thread-B, but oom_kill_task() refuse kill the task because thread-A have OOM_DISABLE. Thus __out_of_memory() call select_bad_process() again. but select_bad_process() select the same task. It mean kernel fall in livelock. The fact is, select_bad_process() must select killable task. otherwise OOM logic go into livelock. And root cause is, oom_adj shouldn't be per-thread value. it should be per-process value because OOM-killer kill a process, not thread. Thus This patch moves oomkilladj (now more appropriately named oom_adj) from struct task_struct to struct signal_struct. it naturally prevent select_bad_process() choose wrong task. Signed-off-by: KOSAKI Motohiro Cc: Paul Menage Cc: David Rientjes Cc: KAMEZAWA Hiroyuki Cc: Rik van Riel Cc: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/base.c | 24 ++++++++++++++++++++---- include/linux/sched.h | 3 ++- kernel/fork.c | 2 ++ mm/oom_kill.c | 34 +++++++++++++++------------------- 4 files changed, 39 insertions(+), 24 deletions(-) (limited to 'fs/proc') diff --git a/fs/proc/base.c b/fs/proc/base.c index 6f742f6658a..81cfff82875 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -999,11 +999,17 @@ static ssize_t oom_adjust_read(struct file *file, char __user *buf, struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode); char buffer[PROC_NUMBUF]; size_t len; - int oom_adjust; + int oom_adjust = OOM_DISABLE; + unsigned long flags; if (!task) return -ESRCH; - oom_adjust = task->oomkilladj; + + if (lock_task_sighand(task, &flags)) { + oom_adjust = task->signal->oom_adj; + unlock_task_sighand(task, &flags); + } + put_task_struct(task); len = snprintf(buffer, sizeof(buffer), "%i\n", oom_adjust); @@ -1017,6 +1023,7 @@ static ssize_t oom_adjust_write(struct file *file, const char __user *buf, struct task_struct *task; char buffer[PROC_NUMBUF], *end; int oom_adjust; + unsigned long flags; memset(buffer, 0, sizeof(buffer)); if (count > sizeof(buffer) - 1) @@ -1032,11 +1039,20 @@ static ssize_t oom_adjust_write(struct file *file, const char __user *buf, task = get_proc_task(file->f_path.dentry->d_inode); if (!task) return -ESRCH; - if (oom_adjust < task->oomkilladj && !capable(CAP_SYS_RESOURCE)) { + if (!lock_task_sighand(task, &flags)) { + put_task_struct(task); + return -ESRCH; + } + + if (oom_adjust < task->signal->oom_adj && !capable(CAP_SYS_RESOURCE)) { + unlock_task_sighand(task, &flags); put_task_struct(task); return -EACCES; } - task->oomkilladj = oom_adjust; + + task->signal->oom_adj = oom_adjust; + + unlock_task_sighand(task, &flags); put_task_struct(task); if (end - buffer == 0) return -EIO; diff --git a/include/linux/sched.h b/include/linux/sched.h index 899d7304d59..17e9a8e9a51 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -639,6 +639,8 @@ struct signal_struct { unsigned audit_tty; struct tty_audit_buf *tty_audit_buf; #endif + + int oom_adj; /* OOM kill score adjustment (bit shift) */ }; /* Context switch must be unlocked if interrupts are to be enabled */ @@ -1221,7 +1223,6 @@ struct task_struct { * a short time */ unsigned char fpu_counter; - s8 oomkilladj; /* OOM kill score adjustment (bit shift). */ #ifdef CONFIG_BLK_DEV_IO_TRACE unsigned int btrace_seq; #endif diff --git a/kernel/fork.c b/kernel/fork.c index 73a442b7be6..1020977b57c 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -880,6 +880,8 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) tty_audit_fork(sig); + sig->oom_adj = current->signal->oom_adj; + return 0; } diff --git a/mm/oom_kill.c b/mm/oom_kill.c index da4c342f264..630b77fe862 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -58,6 +58,10 @@ unsigned long badness(struct task_struct *p, unsigned long uptime) unsigned long points, cpu_time, run_time; struct mm_struct *mm; struct task_struct *child; + int oom_adj = p->signal->oom_adj; + + if (oom_adj == OOM_DISABLE) + return 0; task_lock(p); mm = p->mm; @@ -148,15 +152,15 @@ unsigned long badness(struct task_struct *p, unsigned long uptime) points /= 8; /* - * Adjust the score by oomkilladj. + * Adjust the score by oom_adj. */ - if (p->oomkilladj) { - if (p->oomkilladj > 0) { + if (oom_adj) { + if (oom_adj > 0) { if (!points) points = 1; - points <<= p->oomkilladj; + points <<= oom_adj; } else - points >>= -(p->oomkilladj); + points >>= -(oom_adj); } #ifdef DEBUG @@ -251,7 +255,7 @@ static struct task_struct *select_bad_process(unsigned long *ppoints, *ppoints = ULONG_MAX; } - if (p->oomkilladj == OOM_DISABLE) + if (p->signal->oom_adj == OOM_DISABLE) continue; points = badness(p, uptime.tv_sec); @@ -304,7 +308,7 @@ static void dump_tasks(const struct mem_cgroup *mem) } printk(KERN_INFO "[%5d] %5d %5d %8lu %8lu %3d %3d %s\n", p->pid, __task_cred(p)->uid, p->tgid, mm->total_vm, - get_mm_rss(mm), (int)task_cpu(p), p->oomkilladj, + get_mm_rss(mm), (int)task_cpu(p), p->signal->oom_adj, p->comm); task_unlock(p); } while_each_thread(g, p); @@ -359,18 +363,9 @@ static int oom_kill_task(struct task_struct *p) * change to NULL at any time since we do not hold task_lock(p). * However, this is of no concern to us. */ - - if (mm == NULL) + if (!mm || p->signal->oom_adj == OOM_DISABLE) return 1; - /* - * Don't kill the process if any threads are set to OOM_DISABLE - */ - do_each_thread(g, q) { - if (q->mm == mm && q->oomkilladj == OOM_DISABLE) - return 1; - } while_each_thread(g, q); - __oom_kill_task(p, 1); /* @@ -394,8 +389,9 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, if (printk_ratelimit()) { printk(KERN_WARNING "%s invoked oom-killer: " - "gfp_mask=0x%x, order=%d, oomkilladj=%d\n", - current->comm, gfp_mask, order, current->oomkilladj); + "gfp_mask=0x%x, order=%d, oom_adj=%d\n", + current->comm, gfp_mask, order, + current->signal->oom_adj); task_lock(current); cpuset_print_task_mems_allowed(current); task_unlock(current); -- cgit v1.2.3 From 495789a51a91cb8c015d8d77fecbac1caf20b186 Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Mon, 21 Sep 2009 17:03:14 -0700 Subject: oom: make oom_score to per-process value oom-killer kills a process, not task. Then oom_score should be calculated as per-process too. it makes consistency more and makes speed up select_bad_process(). Signed-off-by: KOSAKI Motohiro Cc: Paul Menage Cc: David Rientjes Cc: KAMEZAWA Hiroyuki Cc: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/filesystems/proc.txt | 2 +- fs/proc/base.c | 2 +- mm/oom_kill.c | 35 +++++++++++++++++++++++++++++------ 3 files changed, 31 insertions(+), 8 deletions(-) (limited to 'fs/proc') diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index ae7f8bb1b7b..75988ba26a5 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -1205,7 +1205,7 @@ The following heuristics are then applied: * if the task was reniced, its score doubles * superuser or direct hardware access tasks (CAP_SYS_ADMIN, CAP_SYS_RESOURCE or CAP_SYS_RAWIO) have their score divided by 4 - * if oom condition happened in one cpuset and checked task does not belong + * if oom condition happened in one cpuset and checked process does not belong to it, its score is divided by 8 * the resulting score is multiplied by two to the power of oom_adj, i.e. points <<= oom_adj when it is positive and diff --git a/fs/proc/base.c b/fs/proc/base.c index 81cfff82875..71a34253dcb 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -447,7 +447,7 @@ static int proc_oom_score(struct task_struct *task, char *buffer) do_posix_clock_monotonic_gettime(&uptime); read_lock(&tasklist_lock); - points = badness(task, uptime.tv_sec); + points = badness(task->group_leader, uptime.tv_sec); read_unlock(&tasklist_lock); return sprintf(buffer, "%lu\n", points); } diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 630b77fe862..37269229484 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -34,6 +34,23 @@ int sysctl_oom_dump_tasks; static DEFINE_SPINLOCK(zone_scan_lock); /* #define DEBUG */ +/* + * Is all threads of the target process nodes overlap ours? + */ +static int has_intersects_mems_allowed(struct task_struct *tsk) +{ + struct task_struct *t; + + t = tsk; + do { + if (cpuset_mems_allowed_intersects(current, t)) + return 1; + t = next_thread(t); + } while (t != tsk); + + return 0; +} + /** * badness - calculate a numeric value for how bad this task has been * @p: task struct of which task we should calculate @@ -59,6 +76,9 @@ unsigned long badness(struct task_struct *p, unsigned long uptime) struct mm_struct *mm; struct task_struct *child; int oom_adj = p->signal->oom_adj; + struct task_cputime task_time; + unsigned long utime; + unsigned long stime; if (oom_adj == OOM_DISABLE) return 0; @@ -106,8 +126,11 @@ unsigned long badness(struct task_struct *p, unsigned long uptime) * of seconds. There is no particular reason for this other than * that it turned out to work very well in practice. */ - cpu_time = (cputime_to_jiffies(p->utime) + cputime_to_jiffies(p->stime)) - >> (SHIFT_HZ + 3); + thread_group_cputime(p, &task_time); + utime = cputime_to_jiffies(task_time.utime); + stime = cputime_to_jiffies(task_time.stime); + cpu_time = (utime + stime) >> (SHIFT_HZ + 3); + if (uptime >= p->start_time.tv_sec) run_time = (uptime - p->start_time.tv_sec) >> 10; @@ -148,7 +171,7 @@ unsigned long badness(struct task_struct *p, unsigned long uptime) * because p may have allocated or otherwise mapped memory on * this node before. However it will be less likely. */ - if (!cpuset_mems_allowed_intersects(current, p)) + if (!has_intersects_mems_allowed(p)) points /= 8; /* @@ -204,13 +227,13 @@ static inline enum oom_constraint constrained_alloc(struct zonelist *zonelist, static struct task_struct *select_bad_process(unsigned long *ppoints, struct mem_cgroup *mem) { - struct task_struct *g, *p; + struct task_struct *p; struct task_struct *chosen = NULL; struct timespec uptime; *ppoints = 0; do_posix_clock_monotonic_gettime(&uptime); - do_each_thread(g, p) { + for_each_process(p) { unsigned long points; /* @@ -263,7 +286,7 @@ static struct task_struct *select_bad_process(unsigned long *ppoints, chosen = p; *ppoints = points; } - } while_each_thread(g, p); + } return chosen; } -- cgit v1.2.3 From 5d863b89688e5811cd9e5bd0082cb38abe03adf3 Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Mon, 21 Sep 2009 17:03:16 -0700 Subject: oom: fix oom_adjust_write() input sanity check Andrew Morton pointed out oom_adjust_write() has very strange EIO and new line handling. this patch fixes it. Signed-off-by: KOSAKI Motohiro Cc: Paul Menage Cc: David Rientjes Cc: KAMEZAWA Hiroyuki Cc: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/base.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) (limited to 'fs/proc') diff --git a/fs/proc/base.c b/fs/proc/base.c index 71a34253dcb..55c4c805a75 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1021,21 +1021,24 @@ static ssize_t oom_adjust_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct task_struct *task; - char buffer[PROC_NUMBUF], *end; - int oom_adjust; + char buffer[PROC_NUMBUF]; + long oom_adjust; unsigned long flags; + int err; memset(buffer, 0, sizeof(buffer)); if (count > sizeof(buffer) - 1) count = sizeof(buffer) - 1; if (copy_from_user(buffer, buf, count)) return -EFAULT; - oom_adjust = simple_strtol(buffer, &end, 0); + + err = strict_strtol(strstrip(buffer), 0, &oom_adjust); + if (err) + return -EINVAL; if ((oom_adjust < OOM_ADJUST_MIN || oom_adjust > OOM_ADJUST_MAX) && oom_adjust != OOM_DISABLE) return -EINVAL; - if (*end == '\n') - end++; + task = get_proc_task(file->f_path.dentry->d_inode); if (!task) return -ESRCH; @@ -1054,9 +1057,8 @@ static ssize_t oom_adjust_write(struct file *file, const char __user *buf, unlock_task_sighand(task, &flags); put_task_struct(task); - if (end - buffer == 0) - return -EIO; - return end - buffer; + + return count; } static const struct file_operations proc_oom_adjust_operations = { -- cgit v1.2.3 From 88e9d34c727883d7d6f02cf1475b3ec98b8480c7 Mon Sep 17 00:00:00 2001 From: James Morris Date: Tue, 22 Sep 2009 16:43:43 -0700 Subject: seq_file: constify seq_operations Make all seq_operations structs const, to help mitigate against revectoring user-triggerable function pointers. This is derived from the grsecurity patch, although generated from scratch because it's simpler than extracting the changes from there. Signed-off-by: James Morris Acked-by: Serge Hallyn Acked-by: Casey Schaufler Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/mn10300/kernel/setup.c | 2 +- arch/powerpc/kernel/setup-common.c | 2 +- arch/powerpc/platforms/pseries/hvCall_inst.c | 2 +- drivers/block/cciss.c | 2 +- drivers/char/misc.c | 2 +- drivers/char/tpm/tpm_bios.c | 4 ++-- drivers/isdn/capi/kcapi_proc.c | 10 +++++----- drivers/scsi/sg.c | 6 +++--- fs/afs/proc.c | 8 ++++---- fs/dlm/debug_fs.c | 12 ++++++------ fs/jbd2/journal.c | 4 ++-- fs/nfs/client.c | 4 ++-- fs/nfsd/export.c | 2 +- fs/ocfs2/cluster/netdebug.c | 4 ++-- fs/ocfs2/dlm/dlmdebug.c | 2 +- fs/proc/nommu.c | 2 +- include/linux/nfsd/nfsd.h | 2 +- ipc/util.c | 2 +- kernel/cgroup.c | 2 +- kernel/kprobes.c | 2 +- kernel/lockdep_proc.c | 2 +- kernel/trace/ftrace.c | 4 ++-- kernel/trace/trace.c | 4 ++-- net/ipv6/ip6mr.c | 2 +- security/integrity/ima/ima_fs.c | 4 ++-- security/smack/smackfs.c | 6 +++--- 26 files changed, 49 insertions(+), 49 deletions(-) (limited to 'fs/proc') diff --git a/arch/mn10300/kernel/setup.c b/arch/mn10300/kernel/setup.c index 79890edfd67..3f24c298a3a 100644 --- a/arch/mn10300/kernel/setup.c +++ b/arch/mn10300/kernel/setup.c @@ -285,7 +285,7 @@ static void c_stop(struct seq_file *m, void *v) { } -struct seq_operations cpuinfo_op = { +const struct seq_operations cpuinfo_op = { .start = c_start, .next = c_next, .stop = c_stop, diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 02fed27af7f..1d5570a1e45 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -328,7 +328,7 @@ static void c_stop(struct seq_file *m, void *v) { } -struct seq_operations cpuinfo_op = { +const struct seq_operations cpuinfo_op = { .start =c_start, .next = c_next, .stop = c_stop, diff --git a/arch/powerpc/platforms/pseries/hvCall_inst.c b/arch/powerpc/platforms/pseries/hvCall_inst.c index eae51ef9af2..3631a4f277e 100644 --- a/arch/powerpc/platforms/pseries/hvCall_inst.c +++ b/arch/powerpc/platforms/pseries/hvCall_inst.c @@ -71,7 +71,7 @@ static int hc_show(struct seq_file *m, void *p) return 0; } -static struct seq_operations hcall_inst_seq_ops = { +static const struct seq_operations hcall_inst_seq_ops = { .start = hc_start, .next = hc_next, .stop = hc_stop, diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c index 4f19105f755..24c3e21ab26 100644 --- a/drivers/block/cciss.c +++ b/drivers/block/cciss.c @@ -363,7 +363,7 @@ static void cciss_seq_stop(struct seq_file *seq, void *v) h->busy_configuring = 0; } -static struct seq_operations cciss_seq_ops = { +static const struct seq_operations cciss_seq_ops = { .start = cciss_seq_start, .show = cciss_seq_show, .next = cciss_seq_next, diff --git a/drivers/char/misc.c b/drivers/char/misc.c index 1ee27cc2342..07fa612a58d 100644 --- a/drivers/char/misc.c +++ b/drivers/char/misc.c @@ -91,7 +91,7 @@ static int misc_seq_show(struct seq_file *seq, void *v) } -static struct seq_operations misc_seq_ops = { +static const struct seq_operations misc_seq_ops = { .start = misc_seq_start, .next = misc_seq_next, .stop = misc_seq_stop, diff --git a/drivers/char/tpm/tpm_bios.c b/drivers/char/tpm/tpm_bios.c index 0c2f55a38b9..bf2170fb1cd 100644 --- a/drivers/char/tpm/tpm_bios.c +++ b/drivers/char/tpm/tpm_bios.c @@ -343,14 +343,14 @@ static int tpm_ascii_bios_measurements_show(struct seq_file *m, void *v) return 0; } -static struct seq_operations tpm_ascii_b_measurments_seqops = { +static const struct seq_operations tpm_ascii_b_measurments_seqops = { .start = tpm_bios_measurements_start, .next = tpm_bios_measurements_next, .stop = tpm_bios_measurements_stop, .show = tpm_ascii_bios_measurements_show, }; -static struct seq_operations tpm_binary_b_measurments_seqops = { +static const struct seq_operations tpm_binary_b_measurments_seqops = { .start = tpm_bios_measurements_start, .next = tpm_bios_measurements_next, .stop = tpm_bios_measurements_stop, diff --git a/drivers/isdn/capi/kcapi_proc.c b/drivers/isdn/capi/kcapi_proc.c index 50ed778f63f..09d4db764d2 100644 --- a/drivers/isdn/capi/kcapi_proc.c +++ b/drivers/isdn/capi/kcapi_proc.c @@ -89,14 +89,14 @@ static int contrstats_show(struct seq_file *seq, void *v) return 0; } -static struct seq_operations seq_controller_ops = { +static const struct seq_operations seq_controller_ops = { .start = controller_start, .next = controller_next, .stop = controller_stop, .show = controller_show, }; -static struct seq_operations seq_contrstats_ops = { +static const struct seq_operations seq_contrstats_ops = { .start = controller_start, .next = controller_next, .stop = controller_stop, @@ -194,14 +194,14 @@ applstats_show(struct seq_file *seq, void *v) return 0; } -static struct seq_operations seq_applications_ops = { +static const struct seq_operations seq_applications_ops = { .start = applications_start, .next = applications_next, .stop = applications_stop, .show = applications_show, }; -static struct seq_operations seq_applstats_ops = { +static const struct seq_operations seq_applstats_ops = { .start = applications_start, .next = applications_next, .stop = applications_stop, @@ -264,7 +264,7 @@ static int capi_driver_show(struct seq_file *seq, void *v) return 0; } -static struct seq_operations seq_capi_driver_ops = { +static const struct seq_operations seq_capi_driver_ops = { .start = capi_driver_start, .next = capi_driver_next, .stop = capi_driver_stop, diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 4968c4ced38..848b5946685 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -2233,7 +2233,7 @@ static struct file_operations dev_fops = { .open = sg_proc_open_dev, .release = seq_release, }; -static struct seq_operations dev_seq_ops = { +static const struct seq_operations dev_seq_ops = { .start = dev_seq_start, .next = dev_seq_next, .stop = dev_seq_stop, @@ -2246,7 +2246,7 @@ static struct file_operations devstrs_fops = { .open = sg_proc_open_devstrs, .release = seq_release, }; -static struct seq_operations devstrs_seq_ops = { +static const struct seq_operations devstrs_seq_ops = { .start = dev_seq_start, .next = dev_seq_next, .stop = dev_seq_stop, @@ -2259,7 +2259,7 @@ static struct file_operations debug_fops = { .open = sg_proc_open_debug, .release = seq_release, }; -static struct seq_operations debug_seq_ops = { +static const struct seq_operations debug_seq_ops = { .start = dev_seq_start, .next = dev_seq_next, .stop = dev_seq_stop, diff --git a/fs/afs/proc.c b/fs/afs/proc.c index 8630615e57f..852739d262a 100644 --- a/fs/afs/proc.c +++ b/fs/afs/proc.c @@ -28,7 +28,7 @@ static int afs_proc_cells_show(struct seq_file *m, void *v); static ssize_t afs_proc_cells_write(struct file *file, const char __user *buf, size_t size, loff_t *_pos); -static struct seq_operations afs_proc_cells_ops = { +static const struct seq_operations afs_proc_cells_ops = { .start = afs_proc_cells_start, .next = afs_proc_cells_next, .stop = afs_proc_cells_stop, @@ -70,7 +70,7 @@ static void *afs_proc_cell_volumes_next(struct seq_file *p, void *v, static void afs_proc_cell_volumes_stop(struct seq_file *p, void *v); static int afs_proc_cell_volumes_show(struct seq_file *m, void *v); -static struct seq_operations afs_proc_cell_volumes_ops = { +static const struct seq_operations afs_proc_cell_volumes_ops = { .start = afs_proc_cell_volumes_start, .next = afs_proc_cell_volumes_next, .stop = afs_proc_cell_volumes_stop, @@ -95,7 +95,7 @@ static void *afs_proc_cell_vlservers_next(struct seq_file *p, void *v, static void afs_proc_cell_vlservers_stop(struct seq_file *p, void *v); static int afs_proc_cell_vlservers_show(struct seq_file *m, void *v); -static struct seq_operations afs_proc_cell_vlservers_ops = { +static const struct seq_operations afs_proc_cell_vlservers_ops = { .start = afs_proc_cell_vlservers_start, .next = afs_proc_cell_vlservers_next, .stop = afs_proc_cell_vlservers_stop, @@ -119,7 +119,7 @@ static void *afs_proc_cell_servers_next(struct seq_file *p, void *v, static void afs_proc_cell_servers_stop(struct seq_file *p, void *v); static int afs_proc_cell_servers_show(struct seq_file *m, void *v); -static struct seq_operations afs_proc_cell_servers_ops = { +static const struct seq_operations afs_proc_cell_servers_ops = { .start = afs_proc_cell_servers_start, .next = afs_proc_cell_servers_next, .stop = afs_proc_cell_servers_stop, diff --git a/fs/dlm/debug_fs.c b/fs/dlm/debug_fs.c index 1d1d2744223..1c8bb8c3a82 100644 --- a/fs/dlm/debug_fs.c +++ b/fs/dlm/debug_fs.c @@ -386,9 +386,9 @@ static int table_seq_show(struct seq_file *seq, void *iter_ptr) return rv; } -static struct seq_operations format1_seq_ops; -static struct seq_operations format2_seq_ops; -static struct seq_operations format3_seq_ops; +static const struct seq_operations format1_seq_ops; +static const struct seq_operations format2_seq_ops; +static const struct seq_operations format3_seq_ops; static void *table_seq_start(struct seq_file *seq, loff_t *pos) { @@ -534,21 +534,21 @@ static void table_seq_stop(struct seq_file *seq, void *iter_ptr) } } -static struct seq_operations format1_seq_ops = { +static const struct seq_operations format1_seq_ops = { .start = table_seq_start, .next = table_seq_next, .stop = table_seq_stop, .show = table_seq_show, }; -static struct seq_operations format2_seq_ops = { +static const struct seq_operations format2_seq_ops = { .start = table_seq_start, .next = table_seq_next, .stop = table_seq_stop, .show = table_seq_show, }; -static struct seq_operations format3_seq_ops = { +static const struct seq_operations format3_seq_ops = { .start = table_seq_start, .next = table_seq_next, .stop = table_seq_stop, diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index a8a358bc0f2..53b86e16e5f 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -768,7 +768,7 @@ static void jbd2_seq_history_stop(struct seq_file *seq, void *v) { } -static struct seq_operations jbd2_seq_history_ops = { +static const struct seq_operations jbd2_seq_history_ops = { .start = jbd2_seq_history_start, .next = jbd2_seq_history_next, .stop = jbd2_seq_history_stop, @@ -872,7 +872,7 @@ static void jbd2_seq_info_stop(struct seq_file *seq, void *v) { } -static struct seq_operations jbd2_seq_info_ops = { +static const struct seq_operations jbd2_seq_info_ops = { .start = jbd2_seq_info_start, .next = jbd2_seq_info_next, .stop = jbd2_seq_info_stop, diff --git a/fs/nfs/client.c b/fs/nfs/client.c index a7ce15d3c24..152025358da 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -1531,7 +1531,7 @@ static void *nfs_server_list_next(struct seq_file *p, void *v, loff_t *pos); static void nfs_server_list_stop(struct seq_file *p, void *v); static int nfs_server_list_show(struct seq_file *m, void *v); -static struct seq_operations nfs_server_list_ops = { +static const struct seq_operations nfs_server_list_ops = { .start = nfs_server_list_start, .next = nfs_server_list_next, .stop = nfs_server_list_stop, @@ -1552,7 +1552,7 @@ static void *nfs_volume_list_next(struct seq_file *p, void *v, loff_t *pos); static void nfs_volume_list_stop(struct seq_file *p, void *v); static int nfs_volume_list_show(struct seq_file *m, void *v); -static struct seq_operations nfs_volume_list_ops = { +static const struct seq_operations nfs_volume_list_ops = { .start = nfs_volume_list_start, .next = nfs_volume_list_next, .stop = nfs_volume_list_stop, diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index 984a5ebcc1d..c1c9e035d4a 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -1517,7 +1517,7 @@ static int e_show(struct seq_file *m, void *p) return svc_export_show(m, &svc_export_cache, cp); } -struct seq_operations nfs_exports_op = { +const struct seq_operations nfs_exports_op = { .start = e_start, .next = e_next, .stop = e_stop, diff --git a/fs/ocfs2/cluster/netdebug.c b/fs/ocfs2/cluster/netdebug.c index f8424874fa0..cfb2be708ab 100644 --- a/fs/ocfs2/cluster/netdebug.c +++ b/fs/ocfs2/cluster/netdebug.c @@ -163,7 +163,7 @@ static void nst_seq_stop(struct seq_file *seq, void *v) { } -static struct seq_operations nst_seq_ops = { +static const struct seq_operations nst_seq_ops = { .start = nst_seq_start, .next = nst_seq_next, .stop = nst_seq_stop, @@ -344,7 +344,7 @@ static void sc_seq_stop(struct seq_file *seq, void *v) { } -static struct seq_operations sc_seq_ops = { +static const struct seq_operations sc_seq_ops = { .start = sc_seq_start, .next = sc_seq_next, .stop = sc_seq_stop, diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c index df52f706f66..c5c88124096 100644 --- a/fs/ocfs2/dlm/dlmdebug.c +++ b/fs/ocfs2/dlm/dlmdebug.c @@ -683,7 +683,7 @@ static int lockres_seq_show(struct seq_file *s, void *v) return 0; } -static struct seq_operations debug_lockres_ops = { +static const struct seq_operations debug_lockres_ops = { .start = lockres_seq_start, .stop = lockres_seq_stop, .next = lockres_seq_next, diff --git a/fs/proc/nommu.c b/fs/proc/nommu.c index 7e14d1a0400..9fe7d7ebe11 100644 --- a/fs/proc/nommu.c +++ b/fs/proc/nommu.c @@ -109,7 +109,7 @@ static void *nommu_region_list_next(struct seq_file *m, void *v, loff_t *pos) return rb_next((struct rb_node *) v); } -static struct seq_operations proc_nommu_region_list_seqop = { +static const struct seq_operations proc_nommu_region_list_seqop = { .start = nommu_region_list_start, .next = nommu_region_list_next, .stop = nommu_region_list_stop, diff --git a/include/linux/nfsd/nfsd.h b/include/linux/nfsd/nfsd.h index 03bbe903910..510ffdd5020 100644 --- a/include/linux/nfsd/nfsd.h +++ b/include/linux/nfsd/nfsd.h @@ -60,7 +60,7 @@ extern spinlock_t nfsd_drc_lock; extern unsigned int nfsd_drc_max_mem; extern unsigned int nfsd_drc_mem_used; -extern struct seq_operations nfs_exports_op; +extern const struct seq_operations nfs_exports_op; /* * Function prototypes. diff --git a/ipc/util.c b/ipc/util.c index b8e4ba92f6d..79ce84e890f 100644 --- a/ipc/util.c +++ b/ipc/util.c @@ -942,7 +942,7 @@ static int sysvipc_proc_show(struct seq_file *s, void *it) return iface->show(s, it); } -static struct seq_operations sysvipc_proc_seqops = { +static const struct seq_operations sysvipc_proc_seqops = { .start = sysvipc_proc_start, .stop = sysvipc_proc_stop, .next = sysvipc_proc_next, diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 213b7f92fcd..cd83d9933b6 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -2314,7 +2314,7 @@ static int cgroup_tasks_show(struct seq_file *s, void *v) return seq_printf(s, "%d\n", *(int *)v); } -static struct seq_operations cgroup_tasks_seq_operations = { +static const struct seq_operations cgroup_tasks_seq_operations = { .start = cgroup_tasks_start, .stop = cgroup_tasks_stop, .next = cgroup_tasks_next, diff --git a/kernel/kprobes.c b/kernel/kprobes.c index ef177d653b2..cfadc1291d0 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1321,7 +1321,7 @@ static int __kprobes show_kprobe_addr(struct seq_file *pi, void *v) return 0; } -static struct seq_operations kprobes_seq_ops = { +static const struct seq_operations kprobes_seq_ops = { .start = kprobe_seq_start, .next = kprobe_seq_next, .stop = kprobe_seq_stop, diff --git a/kernel/lockdep_proc.c b/kernel/lockdep_proc.c index d4b3dbc79fd..d4aba4f3584 100644 --- a/kernel/lockdep_proc.c +++ b/kernel/lockdep_proc.c @@ -594,7 +594,7 @@ static int ls_show(struct seq_file *m, void *v) return 0; } -static struct seq_operations lockstat_ops = { +static const struct seq_operations lockstat_ops = { .start = ls_start, .next = ls_next, .stop = ls_stop, diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index c71e91bf737..23df7771c93 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1520,7 +1520,7 @@ static int t_show(struct seq_file *m, void *v) return 0; } -static struct seq_operations show_ftrace_seq_ops = { +static const struct seq_operations show_ftrace_seq_ops = { .start = t_start, .next = t_next, .stop = t_stop, @@ -2459,7 +2459,7 @@ static int g_show(struct seq_file *m, void *v) return 0; } -static struct seq_operations ftrace_graph_seq_ops = { +static const struct seq_operations ftrace_graph_seq_ops = { .start = g_start, .next = g_next, .stop = g_stop, diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index a35925d222b..6c0f6a8a22e 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1949,7 +1949,7 @@ static int s_show(struct seq_file *m, void *v) return 0; } -static struct seq_operations tracer_seq_ops = { +static const struct seq_operations tracer_seq_ops = { .start = s_start, .next = s_next, .stop = s_stop, @@ -2163,7 +2163,7 @@ static int t_show(struct seq_file *m, void *v) return 0; } -static struct seq_operations show_traces_seq_ops = { +static const struct seq_operations show_traces_seq_ops = { .start = t_start, .next = t_next, .stop = t_stop, diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 3907510c2ce..090675e269e 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -324,7 +324,7 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) return 0; } -static struct seq_operations ipmr_mfc_seq_ops = { +static const struct seq_operations ipmr_mfc_seq_ops = { .start = ipmr_mfc_seq_start, .next = ipmr_mfc_seq_next, .stop = ipmr_mfc_seq_stop, diff --git a/security/integrity/ima/ima_fs.c b/security/integrity/ima/ima_fs.c index 6bfc7eaebfd..8e9777b7640 100644 --- a/security/integrity/ima/ima_fs.c +++ b/security/integrity/ima/ima_fs.c @@ -146,7 +146,7 @@ static int ima_measurements_show(struct seq_file *m, void *v) return 0; } -static struct seq_operations ima_measurments_seqops = { +static const struct seq_operations ima_measurments_seqops = { .start = ima_measurements_start, .next = ima_measurements_next, .stop = ima_measurements_stop, @@ -221,7 +221,7 @@ static int ima_ascii_measurements_show(struct seq_file *m, void *v) return 0; } -static struct seq_operations ima_ascii_measurements_seqops = { +static const struct seq_operations ima_ascii_measurements_seqops = { .start = ima_measurements_start, .next = ima_measurements_next, .stop = ima_measurements_stop, diff --git a/security/smack/smackfs.c b/security/smack/smackfs.c index f83a8098072..aeead758509 100644 --- a/security/smack/smackfs.c +++ b/security/smack/smackfs.c @@ -187,7 +187,7 @@ static void load_seq_stop(struct seq_file *s, void *v) /* No-op */ } -static struct seq_operations load_seq_ops = { +static const struct seq_operations load_seq_ops = { .start = load_seq_start, .next = load_seq_next, .show = load_seq_show, @@ -503,7 +503,7 @@ static void cipso_seq_stop(struct seq_file *s, void *v) /* No-op */ } -static struct seq_operations cipso_seq_ops = { +static const struct seq_operations cipso_seq_ops = { .start = cipso_seq_start, .stop = cipso_seq_stop, .next = cipso_seq_next, @@ -697,7 +697,7 @@ static void netlbladdr_seq_stop(struct seq_file *s, void *v) /* No-op */ } -static struct seq_operations netlbladdr_seq_ops = { +static const struct seq_operations netlbladdr_seq_ops = { .start = netlbladdr_seq_start, .stop = netlbladdr_seq_stop, .next = netlbladdr_seq_next, -- cgit v1.2.3 From cff4edb591c153a779a27a3fd8e7bc1217f2f6b8 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 22 Sep 2009 16:45:32 -0700 Subject: proc: fix reported unit for RLIMIT_CPU /proc/$pid/limits should show RLIMIT_CPU as seconds, which is the unit used in kernel/posix-cpu-timers.c: unsigned long psecs = cputime_to_secs(ptime); ... if (psecs >= sig->rlim[RLIMIT_CPU].rlim_max) { ... __group_send_sig_info(SIGKILL, SEND_SIG_PRIV, tsk); Signed-off-by: Kees Cook Acked-by: WANG Cong Acked-by: Neil Horman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/base.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/proc') diff --git a/fs/proc/base.c b/fs/proc/base.c index 55c4c805a75..69bb70351b9 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -458,7 +458,7 @@ struct limit_names { }; static const struct limit_names lnames[RLIM_NLIMITS] = { - [RLIMIT_CPU] = {"Max cpu time", "ms"}, + [RLIMIT_CPU] = {"Max cpu time", "seconds"}, [RLIMIT_FSIZE] = {"Max file size", "bytes"}, [RLIMIT_DATA] = {"Max data size", "bytes"}, [RLIMIT_STACK] = {"Max stack size", "bytes"}, -- cgit v1.2.3 From 9b4d1cbef8f41aff2b3e4ca31f566c071fe601de Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 22 Sep 2009 16:45:34 -0700 Subject: proc_flush_task: flush /proc/tid/task/pid when a sub-thread exits The exiting sub-thread flushes /proc/pid only, but this doesn't buy too much: ps and friends mostly use /proc/tid/task/pid. Remove "if (thread_group_leader())" checks from proc_flush_task() path, this means we always remove /proc/tid/task/pid dentry on exit, and this actually matches the comment above proc_flush_task(). The test-case: static void* tfunc(void *arg) { char name[256]; sprintf(name, "/proc/%d/task/%ld/status", getpid(), gettid()); close(open(name, O_RDONLY)); return NULL; } int main(void) { pthread_t t; for (;;) { if (!pthread_create(&t, NULL, &tfunc, NULL)) pthread_join(t, NULL); } } slabtop shows that pid/proc_inode_cache/etc grow quickly and "indefinitely" until the task is killed or shrink_slab() is called, not good. And the main thread needs a lot of time to exit. The same can happen if something like "ps -efL" runs continuously, while some application spawns short-living threads. Reported-by: "James M. Leddy" Signed-off-by: Oleg Nesterov Cc: Alexey Dobriyan Cc: "Eric W. Biederman" Cc: Dominic Duval Cc: Frank Hirtz Cc: "Fuller, Johnray" Cc: Larry Woodman Cc: Paul Batkowski Cc: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/base.c | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-) (limited to 'fs/proc') diff --git a/fs/proc/base.c b/fs/proc/base.c index 69bb70351b9..5bc587049b3 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -2604,9 +2604,6 @@ static void proc_flush_task_mnt(struct vfsmount *mnt, pid_t pid, pid_t tgid) dput(dentry); } - if (tgid == 0) - goto out; - name.name = buf; name.len = snprintf(buf, sizeof(buf), "%d", tgid); leader = d_hash_and_lookup(mnt->mnt_root, &name); @@ -2663,17 +2660,16 @@ out: void proc_flush_task(struct task_struct *task) { int i; - struct pid *pid, *tgid = NULL; + struct pid *pid, *tgid; struct upid *upid; pid = task_pid(task); - if (thread_group_leader(task)) - tgid = task_tgid(task); + tgid = task_tgid(task); for (i = 0; i <= pid->level; i++) { upid = &pid->numbers[i]; proc_flush_task_mnt(upid->ns->proc_mnt, upid->nr, - tgid ? tgid->numbers[i].nr : 0); + tgid->numbers[i].nr); } upid = &pid->numbers[pid->level]; -- cgit v1.2.3 From acef82b873b6899d80e639317228f2104dae79a2 Mon Sep 17 00:00:00 2001 From: Amerigo Wang Date: Tue, 22 Sep 2009 16:45:35 -0700 Subject: kcore: fix /proc/kcore's stat.st_size In 9063c61fd5cbd ("x86, 64-bit: Clean up user address masking") Linus fixed the wrong size of /proc/kcore problem. But its size still looks insane, since it never equals the size of physical memory. Signed-off-by: WANG Cong Cc: "Eric W. Biederman" Cc: Tao Ma Cc: Acked-by: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/kcore.c | 3 --- 1 file changed, 3 deletions(-) (limited to 'fs/proc') diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index f06f45b4218..0cf8a24cf6c 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -374,9 +374,6 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) static int __init proc_kcore_init(void) { proc_root_kcore = proc_create("kcore", S_IRUSR, NULL, &proc_kcore_operations); - if (proc_root_kcore) - proc_root_kcore->size = - (size_t)high_memory - PAGE_OFFSET + PAGE_SIZE; return 0; } module_init(proc_kcore_init); -- cgit v1.2.3 From fb92a4b068be96799da3748c11cbd69760e44d7b Mon Sep 17 00:00:00 2001 From: Vincent Li Date: Tue, 22 Sep 2009 16:45:36 -0700 Subject: fs/proc/task_mmu.c v1: fix clear_refs_write() input sanity check Andrew Morton pointed out similar string hacking and obfuscated check for zero-length input at the end of the function, David Rientjes suggested to use strict_strtol to replace simple_strtol, this patch cover above suggestions, add removing of leading and trailing whitespace from user input. It does not change function behavious. Signed-off-by: Vincent Li Acked-by: David Rientjes Cc: Matt Mackall Cc: Amerigo Wang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/task_mmu.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) (limited to 'fs/proc') diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 59e98fea34a..366b1017a4f 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -473,21 +473,20 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct task_struct *task; - char buffer[PROC_NUMBUF], *end; + char buffer[PROC_NUMBUF]; struct mm_struct *mm; struct vm_area_struct *vma; - int type; + long type; memset(buffer, 0, sizeof(buffer)); if (count > sizeof(buffer) - 1) count = sizeof(buffer) - 1; if (copy_from_user(buffer, buf, count)) return -EFAULT; - type = simple_strtol(buffer, &end, 0); + if (strict_strtol(strstrip(buffer), 10, &type)) + return -EINVAL; if (type < CLEAR_REFS_ALL || type > CLEAR_REFS_MAPPED) return -EINVAL; - if (*end == '\n') - end++; task = get_proc_task(file->f_path.dentry->d_inode); if (!task) return -ESRCH; @@ -523,9 +522,8 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, mmput(mm); } put_task_struct(task); - if (end - buffer == 0) - return -EIO; - return end - buffer; + + return count; } const struct file_operations proc_clear_refs_operations = { -- cgit v1.2.3 From cba8aafe1e07dfc8bae5ba78be8e02883bd34d31 Mon Sep 17 00:00:00 2001 From: Vincent Li Date: Tue, 22 Sep 2009 16:45:38 -0700 Subject: fs/proc/base.c: fix proc_fault_inject_write() input sanity check Remove obfuscated zero-length input check and return -EINVAL instead of -EIO error to make the error message clear to user. Add whitespace stripping. No functionality changes. The old code: echo 1 > /proc/pid/make-it-fail (ok) echo 1foo > /proc/pid/make-it-fail (-bash: echo: write error: Input/output error) The new code: echo 1 > /proc/pid/make-it-fail (ok) echo 1foo > /proc/pid/make-it-fail (-bash: echo: write error: Invalid argument) This patch is conservative in changes to not breaking existing scripts/applications. Signed-off-by: Vincent Li Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/base.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'fs/proc') diff --git a/fs/proc/base.c b/fs/proc/base.c index 5bc587049b3..837469a9659 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1187,17 +1187,16 @@ static ssize_t proc_fault_inject_write(struct file * file, count = sizeof(buffer) - 1; if (copy_from_user(buffer, buf, count)) return -EFAULT; - make_it_fail = simple_strtol(buffer, &end, 0); - if (*end == '\n') - end++; + make_it_fail = simple_strtol(strstrip(buffer), &end, 0); + if (*end) + return -EINVAL; task = get_proc_task(file->f_dentry->d_inode); if (!task) return -ESRCH; task->make_it_fail = make_it_fail; put_task_struct(task); - if (end - buffer == 0) - return -EIO; - return end - buffer; + + return count; } static const struct file_operations proc_fault_inject_operations = { -- cgit v1.2.3 From d899bf7b55f503ba7d3d07ed27c3a37e270fa7db Mon Sep 17 00:00:00 2001 From: Stefani Seibold Date: Tue, 22 Sep 2009 16:45:40 -0700 Subject: procfs: provide stack information for threads A patch to give a better overview of the userland application stack usage, especially for embedded linux. Currently you are only able to dump the main process/thread stack usage which is showed in /proc/pid/status by the "VmStk" Value. But you get no information about the consumed stack memory of the the threads. There is an enhancement in the /proc//{task/*,}/*maps and which marks the vm mapping where the thread stack pointer reside with "[thread stack xxxxxxxx]". xxxxxxxx is the maximum size of stack. This is a value information, because libpthread doesn't set the start of the stack to the top of the mapped area, depending of the pthread usage. A sample output of /proc//task//maps looks like: 08048000-08049000 r-xp 00000000 03:00 8312 /opt/z 08049000-0804a000 rw-p 00001000 03:00 8312 /opt/z 0804a000-0806b000 rw-p 00000000 00:00 0 [heap] a7d12000-a7d13000 ---p 00000000 00:00 0 a7d13000-a7f13000 rw-p 00000000 00:00 0 [thread stack: 001ff4b4] a7f13000-a7f14000 ---p 00000000 00:00 0 a7f14000-a7f36000 rw-p 00000000 00:00 0 a7f36000-a8069000 r-xp 00000000 03:00 4222 /lib/libc.so.6 a8069000-a806b000 r--p 00133000 03:00 4222 /lib/libc.so.6 a806b000-a806c000 rw-p 00135000 03:00 4222 /lib/libc.so.6 a806c000-a806f000 rw-p 00000000 00:00 0 a806f000-a8083000 r-xp 00000000 03:00 14462 /lib/libpthread.so.0 a8083000-a8084000 r--p 00013000 03:00 14462 /lib/libpthread.so.0 a8084000-a8085000 rw-p 00014000 03:00 14462 /lib/libpthread.so.0 a8085000-a8088000 rw-p 00000000 00:00 0 a8088000-a80a4000 r-xp 00000000 03:00 8317 /lib/ld-linux.so.2 a80a4000-a80a5000 r--p 0001b000 03:00 8317 /lib/ld-linux.so.2 a80a5000-a80a6000 rw-p 0001c000 03:00 8317 /lib/ld-linux.so.2 afaf5000-afb0a000 rw-p 00000000 00:00 0 [stack] ffffe000-fffff000 r-xp 00000000 00:00 0 [vdso] Also there is a new entry "stack usage" in /proc//{task/*,}/status which will you give the current stack usage in kb. A sample output of /proc/self/status looks like: Name: cat State: R (running) Tgid: 507 Pid: 507 . . . CapBnd: fffffffffffffeff voluntary_ctxt_switches: 0 nonvoluntary_ctxt_switches: 0 Stack usage: 12 kB I also fixed stack base address in /proc//{task/*,}/stat to the base address of the associated thread stack and not the one of the main process. This makes more sense. [akpm@linux-foundation.org: fs/proc/array.c now needs walk_page_range()] Signed-off-by: Stefani Seibold Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Alexey Dobriyan Cc: "Eric W. Biederman" Cc: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/filesystems/proc.txt | 5 ++- fs/exec.c | 2 + fs/proc/array.c | 85 +++++++++++++++++++++++++++++++++++++- fs/proc/task_mmu.c | 19 +++++++++ include/linux/sched.h | 1 + kernel/fork.c | 2 + mm/Makefile | 4 +- 7 files changed, 114 insertions(+), 4 deletions(-) (limited to 'fs/proc') diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index 75988ba26a5..b5aee7838a0 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -176,6 +176,7 @@ read the file /proc/PID/status: CapBnd: ffffffffffffffff voluntary_ctxt_switches: 0 nonvoluntary_ctxt_switches: 1 + Stack usage: 12 kB This shows you nearly the same information you would get if you viewed it with the ps command. In fact, ps uses the proc file system to obtain its @@ -229,6 +230,7 @@ Table 1-2: Contents of the statm files (as of 2.6.30-rc7) Mems_allowed_list Same as previous, but in "list format" voluntary_ctxt_switches number of voluntary context switches nonvoluntary_ctxt_switches number of non voluntary context switches + Stack usage: stack usage high water mark (round up to page size) .............................................................................. Table 1-3: Contents of the statm files (as of 2.6.8-rc3) @@ -307,7 +309,7 @@ address perms offset dev inode pathname 08049000-0804a000 rw-p 00001000 03:00 8312 /opt/test 0804a000-0806b000 rw-p 00000000 00:00 0 [heap] a7cb1000-a7cb2000 ---p 00000000 00:00 0 -a7cb2000-a7eb2000 rw-p 00000000 00:00 0 +a7cb2000-a7eb2000 rw-p 00000000 00:00 0 [threadstack:001ff4b4] a7eb2000-a7eb3000 ---p 00000000 00:00 0 a7eb3000-a7ed5000 rw-p 00000000 00:00 0 a7ed5000-a8008000 r-xp 00000000 03:00 4222 /lib/libc.so.6 @@ -343,6 +345,7 @@ is not associated with a file: [stack] = the stack of the main process [vdso] = the "virtual dynamic shared object", the kernel system call handler + [threadstack:xxxxxxxx] = the stack of the thread, xxxxxxxx is the stack size or if empty, the mapping is anonymous. diff --git a/fs/exec.c b/fs/exec.c index 69bb9d89979..5c833c18d0d 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1357,6 +1357,8 @@ int do_execve(char * filename, if (retval < 0) goto out; + current->stack_start = current->mm->start_stack; + /* execve succeeded */ current->fs->in_exec = 0; current->in_execve = 0; diff --git a/fs/proc/array.c b/fs/proc/array.c index 725a650bbbb..0c6bc602e6c 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -82,6 +82,7 @@ #include #include #include +#include #include #include @@ -321,6 +322,87 @@ static inline void task_context_switch_counts(struct seq_file *m, p->nivcsw); } +struct stack_stats { + struct vm_area_struct *vma; + unsigned long startpage; + unsigned long usage; +}; + +static int stack_usage_pte_range(pmd_t *pmd, unsigned long addr, + unsigned long end, struct mm_walk *walk) +{ + struct stack_stats *ss = walk->private; + struct vm_area_struct *vma = ss->vma; + pte_t *pte, ptent; + spinlock_t *ptl; + int ret = 0; + + pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); + for (; addr != end; pte++, addr += PAGE_SIZE) { + ptent = *pte; + +#ifdef CONFIG_STACK_GROWSUP + if (pte_present(ptent) || is_swap_pte(ptent)) + ss->usage = addr - ss->startpage + PAGE_SIZE; +#else + if (pte_present(ptent) || is_swap_pte(ptent)) { + ss->usage = ss->startpage - addr + PAGE_SIZE; + pte++; + ret = 1; + break; + } +#endif + } + pte_unmap_unlock(pte - 1, ptl); + cond_resched(); + return ret; +} + +static inline unsigned long get_stack_usage_in_bytes(struct vm_area_struct *vma, + struct task_struct *task) +{ + struct stack_stats ss; + struct mm_walk stack_walk = { + .pmd_entry = stack_usage_pte_range, + .mm = vma->vm_mm, + .private = &ss, + }; + + if (!vma->vm_mm || is_vm_hugetlb_page(vma)) + return 0; + + ss.vma = vma; + ss.startpage = task->stack_start & PAGE_MASK; + ss.usage = 0; + +#ifdef CONFIG_STACK_GROWSUP + walk_page_range(KSTK_ESP(task) & PAGE_MASK, vma->vm_end, + &stack_walk); +#else + walk_page_range(vma->vm_start, (KSTK_ESP(task) & PAGE_MASK) + PAGE_SIZE, + &stack_walk); +#endif + return ss.usage; +} + +static inline void task_show_stack_usage(struct seq_file *m, + struct task_struct *task) +{ + struct vm_area_struct *vma; + struct mm_struct *mm = get_task_mm(task); + + if (mm) { + down_read(&mm->mmap_sem); + vma = find_vma(mm, task->stack_start); + if (vma) + seq_printf(m, "Stack usage:\t%lu kB\n", + get_stack_usage_in_bytes(vma, task) >> 10); + + up_read(&mm->mmap_sem); + mmput(mm); + } +} + int proc_pid_status(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { @@ -340,6 +422,7 @@ int proc_pid_status(struct seq_file *m, struct pid_namespace *ns, task_show_regs(m, task); #endif task_context_switch_counts(m, task); + task_show_stack_usage(m, task); return 0; } @@ -481,7 +564,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, rsslim, mm ? mm->start_code : 0, mm ? mm->end_code : 0, - (permitted && mm) ? mm->start_stack : 0, + (permitted) ? task->stack_start : 0, esp, eip, /* The signal information here is obsolete. diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 366b1017a4f..2a1bef9203c 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -243,6 +243,25 @@ static void show_map_vma(struct seq_file *m, struct vm_area_struct *vma) } else if (vma->vm_start <= mm->start_stack && vma->vm_end >= mm->start_stack) { name = "[stack]"; + } else { + unsigned long stack_start; + struct proc_maps_private *pmp; + + pmp = m->private; + stack_start = pmp->task->stack_start; + + if (vma->vm_start <= stack_start && + vma->vm_end >= stack_start) { + pad_len_spaces(m, len); + seq_printf(m, + "[threadstack:%08lx]", +#ifdef CONFIG_STACK_GROWSUP + vma->vm_end - stack_start +#else + stack_start - vma->vm_start +#endif + ); + } } } else { name = "[vdso]"; diff --git a/include/linux/sched.h b/include/linux/sched.h index 6448bbc6406..3cbc6c0be66 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1529,6 +1529,7 @@ struct task_struct { /* bitmask of trace recursion */ unsigned long trace_recursion; #endif /* CONFIG_TRACING */ + unsigned long stack_start; }; /* Future-safe accessor for struct task_struct's cpus_allowed. */ diff --git a/kernel/fork.c b/kernel/fork.c index 7cf45812ce8..8f45b0ebdda 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1095,6 +1095,8 @@ static struct task_struct *copy_process(unsigned long clone_flags, p->bts = NULL; + p->stack_start = stack_start; + /* Perform scheduler related setup. Assign this task to a CPU. */ sched_fork(p, clone_flags); diff --git a/mm/Makefile b/mm/Makefile index 728a9fde49d..88193d73cd1 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -11,10 +11,10 @@ obj-y := bootmem.o filemap.o mempool.o oom_kill.o fadvise.o \ maccess.o page_alloc.o page-writeback.o \ readahead.o swap.o truncate.o vmscan.o shmem.o \ prio_tree.o util.o mmzone.o vmstat.o backing-dev.o \ - page_isolation.o mm_init.o mmu_context.o $(mmu-y) + page_isolation.o mm_init.o mmu_context.o \ + pagewalk.o $(mmu-y) obj-y += init-mm.o -obj-$(CONFIG_PROC_PAGE_MONITOR) += pagewalk.o obj-$(CONFIG_BOUNCE) += bounce.o obj-$(CONFIG_SWAP) += page_io.o swap_state.o swapfile.o thrash.o obj-$(CONFIG_HAS_DMA) += dmapool.o -- cgit v1.2.3 From 2ef43ec772551e975a6ea7cf22b59c84955aadf9 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Tue, 22 Sep 2009 16:45:41 -0700 Subject: kcore: use usual list for kclist This patchset is for /proc/kcore. With this, - many per-arch hooks are removed. - /proc/kcore will know really valid physical memory area. - /proc/kcore will be aware of memory hotplug. - /proc/kcore will be architecture independent i.e. if an arch supports CONFIG_MMU, it can use /proc/kcore. (if the arch uses usual memory layout.) This patch: /proc/kcore uses its own list handling codes. It's better to use generic list codes. No changes in logic. just clean up. Signed-off-by: KAMEZAWA Hiroyuki Cc: Ralf Baechle Cc: Benjamin Herrenschmidt Cc: WANG Cong Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/kcore.c | 12 ++++++------ include/linux/proc_fs.h | 2 +- 2 files changed, 7 insertions(+), 7 deletions(-) (limited to 'fs/proc') diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index 0cf8a24cf6c..f9327e51ce9 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -20,6 +20,7 @@ #include #include #include +#include #define CORE_STR "CORE" @@ -57,7 +58,7 @@ struct memelfnote void *data; }; -static struct kcore_list *kclist; +static LIST_HEAD(kclist_head); static DEFINE_RWLOCK(kclist_lock); void @@ -67,8 +68,7 @@ kclist_add(struct kcore_list *new, void *addr, size_t size) new->size = size; write_lock(&kclist_lock); - new->next = kclist; - kclist = new; + list_add_tail(&new->list, &kclist_head); write_unlock(&kclist_lock); } @@ -80,7 +80,7 @@ static size_t get_kcore_size(int *nphdr, size_t *elf_buflen) *nphdr = 1; /* PT_NOTE */ size = 0; - for (m=kclist; m; m=m->next) { + list_for_each_entry(m, &kclist_head, list) { try = kc_vaddr_to_offset((size_t)m->addr + m->size); if (try > size) size = try; @@ -192,7 +192,7 @@ static void elf_kcore_store_hdr(char *bufp, int nphdr, int dataoff) nhdr->p_align = 0; /* setup ELF PT_LOAD program header for every area */ - for (m=kclist; m; m=m->next) { + list_for_each_entry(m, &kclist_head, list) { phdr = (struct elf_phdr *) bufp; bufp += sizeof(struct elf_phdr); offset += sizeof(struct elf_phdr); @@ -317,7 +317,7 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) struct kcore_list *m; read_lock(&kclist_lock); - for (m=kclist; m; m=m->next) { + list_for_each_entry(m, &kclist_head, list) { if (start >= m->addr && start < (m->addr+m->size)) break; } diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index e6e77d31c41..0aff2a62eba 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -79,7 +79,7 @@ struct proc_dir_entry { }; struct kcore_list { - struct kcore_list *next; + struct list_head list; unsigned long addr; size_t size; }; -- cgit v1.2.3 From c30bb2a25fcfde6157e6154a32c14686fb0bedbe Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Tue, 22 Sep 2009 16:45:43 -0700 Subject: kcore: add kclist types Presently, kclist_add() only eats start address and size as its arguments. Considering to make kclist dynamically reconfigulable, it's necessary to know which kclists are for System RAM and which are not. This patch add kclist types as KCORE_RAM KCORE_VMALLOC KCORE_TEXT KCORE_OTHER This "type" is used in a patch following this for detecting KCORE_RAM. Signed-off-by: KAMEZAWA Hiroyuki Cc: Ralf Baechle Cc: Benjamin Herrenschmidt Cc: WANG Cong Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/mm/init.c | 7 ++++--- arch/mips/mm/init.c | 7 ++++--- arch/powerpc/mm/init_32.c | 4 ++-- arch/powerpc/mm/init_64.c | 5 +++-- arch/sh/mm/init.c | 4 ++-- arch/x86/mm/init_32.c | 4 ++-- arch/x86/mm/init_64.c | 11 ++++++----- fs/proc/kcore.c | 3 ++- include/linux/proc_fs.h | 13 +++++++++++-- 9 files changed, 36 insertions(+), 22 deletions(-) (limited to 'fs/proc') diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index 1d286244a56..f6a3c21a282 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -639,9 +639,10 @@ mem_init (void) high_memory = __va(max_low_pfn * PAGE_SIZE); - kclist_add(&kcore_mem, __va(0), max_low_pfn * PAGE_SIZE); - kclist_add(&kcore_vmem, (void *)VMALLOC_START, VMALLOC_END-VMALLOC_START); - kclist_add(&kcore_kernel, _stext, _end - _stext); + kclist_add(&kcore_mem, __va(0), max_low_pfn * PAGE_SIZE, KCORE_RAM); + kclist_add(&kcore_vmem, (void *)VMALLOC_START, + VMALLOC_END-VMALLOC_START, KCORE_VMALLOC); + kclist_add(&kcore_kernel, _stext, _end - _stext, KCORE_TEXT); for_each_online_pgdat(pgdat) if (pgdat->bdata->node_bootmem_map) diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index 1f4ee4797a6..f8661985bff 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -409,11 +409,12 @@ void __init mem_init(void) if ((unsigned long) &_text > (unsigned long) CKSEG0) /* The -4 is a hack so that user tools don't have to handle the overflow. */ - kclist_add(&kcore_kseg0, (void *) CKSEG0, 0x80000000 - 4); + kclist_add(&kcore_kseg0, (void *) CKSEG0, + 0x80000000 - 4, KCORE_TEXT); #endif - kclist_add(&kcore_mem, __va(0), max_low_pfn << PAGE_SHIFT); + kclist_add(&kcore_mem, __va(0), max_low_pfn << PAGE_SHIFT, KCORE_RAM); kclist_add(&kcore_vmalloc, (void *)VMALLOC_START, - VMALLOC_END-VMALLOC_START); + VMALLOC_END-VMALLOC_START, KCORE_VMALLOC); printk(KERN_INFO "Memory: %luk/%luk available (%ldk kernel code, " "%ldk reserved, %ldk data, %ldk init, %ldk highmem)\n", diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c index 3ef5084b90c..e91add90ec5 100644 --- a/arch/powerpc/mm/init_32.c +++ b/arch/powerpc/mm/init_32.c @@ -268,11 +268,11 @@ static int __init setup_kcore(void) size); } - kclist_add(kcore_mem, __va(base), size); + kclist_add(kcore_mem, __va(base), size, KCORE_RAM); } kclist_add(&kcore_vmem, (void *)VMALLOC_START, - VMALLOC_END-VMALLOC_START); + VMALLOC_END-VMALLOC_START, KCORE_VMALLOC); return 0; } diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index 31582329cd6..9ee563101b5 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -128,10 +128,11 @@ static int __init setup_kcore(void) if (!kcore_mem) panic("%s: kmalloc failed\n", __func__); - kclist_add(kcore_mem, __va(base), size); + kclist_add(kcore_mem, __va(base), size, KCORE_RAM); } - kclist_add(&kcore_vmem, (void *)VMALLOC_START, VMALLOC_END-VMALLOC_START); + kclist_add(&kcore_vmem, (void *)VMALLOC_START, + VMALLOC_END-VMALLOC_START, KCORE_VMALLOC); return 0; } diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c index fabb7c6f48d..ef56c9f9d7b 100644 --- a/arch/sh/mm/init.c +++ b/arch/sh/mm/init.c @@ -226,9 +226,9 @@ void __init mem_init(void) datasize = (unsigned long) &_edata - (unsigned long) &_etext; initsize = (unsigned long) &__init_end - (unsigned long) &__init_begin; - kclist_add(&kcore_mem, __va(0), max_low_pfn << PAGE_SHIFT); + kclist_add(&kcore_mem, __va(0), max_low_pfn << PAGE_SHIFT, KCORE_RAM); kclist_add(&kcore_vmalloc, (void *)VMALLOC_START, - VMALLOC_END - VMALLOC_START); + VMALLOC_END - VMALLOC_START, KCORE_VMALLOC); printk(KERN_INFO "Memory: %luk/%luk available (%dk kernel code, " "%dk data, %dk init)\n", diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index b49b4f67453..2cbc4011293 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -886,9 +886,9 @@ void __init mem_init(void) datasize = (unsigned long) &_edata - (unsigned long) &_etext; initsize = (unsigned long) &__init_end - (unsigned long) &__init_begin; - kclist_add(&kcore_mem, __va(0), max_low_pfn << PAGE_SHIFT); + kclist_add(&kcore_mem, __va(0), max_low_pfn << PAGE_SHIFT, KCORE_RAM); kclist_add(&kcore_vmalloc, (void *)VMALLOC_START, - VMALLOC_END-VMALLOC_START); + VMALLOC_END-VMALLOC_START, KCORE_VMALLOC); printk(KERN_INFO "Memory: %luk/%luk available (%dk kernel code, " "%dk reserved, %dk data, %dk init, %ldk highmem)\n", diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 810bd31e7f5..c05810b614f 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -677,13 +677,14 @@ void __init mem_init(void) initsize = (unsigned long) &__init_end - (unsigned long) &__init_begin; /* Register memory areas for /proc/kcore */ - kclist_add(&kcore_mem, __va(0), max_low_pfn << PAGE_SHIFT); + kclist_add(&kcore_mem, __va(0), max_low_pfn << PAGE_SHIFT, KCORE_RAM); kclist_add(&kcore_vmalloc, (void *)VMALLOC_START, - VMALLOC_END-VMALLOC_START); - kclist_add(&kcore_kernel, &_stext, _end - _stext); - kclist_add(&kcore_modules, (void *)MODULES_VADDR, MODULES_LEN); + VMALLOC_END-VMALLOC_START, KCORE_VMALLOC); + kclist_add(&kcore_kernel, &_stext, _end - _stext, KCORE_TEXT); + kclist_add(&kcore_modules, (void *)MODULES_VADDR, MODULES_LEN, + KCORE_OTHER); kclist_add(&kcore_vsyscall, (void *)VSYSCALL_START, - VSYSCALL_END - VSYSCALL_START); + VSYSCALL_END - VSYSCALL_START, KCORE_OTHER); printk(KERN_INFO "Memory: %luk/%luk available (%ldk kernel code, " "%ldk absent, %ldk reserved, %ldk data, %ldk init)\n", diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index f9327e51ce9..659c1635db8 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -62,10 +62,11 @@ static LIST_HEAD(kclist_head); static DEFINE_RWLOCK(kclist_lock); void -kclist_add(struct kcore_list *new, void *addr, size_t size) +kclist_add(struct kcore_list *new, void *addr, size_t size, int type) { new->addr = (unsigned long)addr; new->size = size; + new->type = type; write_lock(&kclist_lock); list_add_tail(&new->list, &kclist_head); diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 0aff2a62eba..bd7b840765a 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -78,10 +78,18 @@ struct proc_dir_entry { struct list_head pde_openers; /* who did ->open, but not ->release */ }; +enum kcore_type { + KCORE_TEXT, + KCORE_VMALLOC, + KCORE_RAM, + KCORE_OTHER, +}; + struct kcore_list { struct list_head list; unsigned long addr; size_t size; + int type; }; struct vmcore { @@ -233,11 +241,12 @@ static inline void dup_mm_exe_file(struct mm_struct *oldmm, #endif /* CONFIG_PROC_FS */ #if !defined(CONFIG_PROC_KCORE) -static inline void kclist_add(struct kcore_list *new, void *addr, size_t size) +static inline void +kclist_add(struct kcore_list *new, void *addr, size_t size, int type) { } #else -extern void kclist_add(struct kcore_list *, void *, size_t); +extern void kclist_add(struct kcore_list *, void *, size_t, int type); #endif union proc_op { -- cgit v1.2.3 From a0614da88b67ffa3dbcc0d40b817e682c7c4a0ee Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Tue, 22 Sep 2009 16:45:44 -0700 Subject: kcore: register vmalloc area in generic way For /proc/kcore, vmalloc areas are registered per arch. But, all of them registers same range of [VMALLOC_START...VMALLOC_END) This patch unifies them. By this. archs which have no kclist_add() hooks can see vmalloc area correctly. Signed-off-by: KAMEZAWA Hiroyuki Cc: Ralf Baechle Cc: Benjamin Herrenschmidt Cc: WANG Cong Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/mm/init.c | 4 +--- arch/mips/mm/init.c | 4 +--- arch/powerpc/mm/init_32.c | 4 ---- arch/powerpc/mm/init_64.c | 4 ---- arch/sh/mm/init.c | 4 +--- arch/x86/mm/init_32.c | 4 +--- arch/x86/mm/init_64.c | 4 +--- fs/proc/kcore.c | 5 +++++ 8 files changed, 10 insertions(+), 23 deletions(-) (limited to 'fs/proc') diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index f6a3c21a282..286b98aa854 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -617,7 +617,7 @@ mem_init (void) long reserved_pages, codesize, datasize, initsize; pg_data_t *pgdat; int i; - static struct kcore_list kcore_mem, kcore_vmem, kcore_kernel; + static struct kcore_list kcore_mem, kcore_kernel; BUG_ON(PTRS_PER_PGD * sizeof(pgd_t) != PAGE_SIZE); BUG_ON(PTRS_PER_PMD * sizeof(pmd_t) != PAGE_SIZE); @@ -640,8 +640,6 @@ mem_init (void) high_memory = __va(max_low_pfn * PAGE_SIZE); kclist_add(&kcore_mem, __va(0), max_low_pfn * PAGE_SIZE, KCORE_RAM); - kclist_add(&kcore_vmem, (void *)VMALLOC_START, - VMALLOC_END-VMALLOC_START, KCORE_VMALLOC); kclist_add(&kcore_kernel, _stext, _end - _stext, KCORE_TEXT); for_each_online_pgdat(pgdat) diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index f8661985bff..4a83da499e2 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -352,7 +352,7 @@ void __init paging_init(void) free_area_init_nodes(max_zone_pfns); } -static struct kcore_list kcore_mem, kcore_vmalloc; +static struct kcore_list kcore_mem; #ifdef CONFIG_64BIT static struct kcore_list kcore_kseg0; #endif @@ -413,8 +413,6 @@ void __init mem_init(void) 0x80000000 - 4, KCORE_TEXT); #endif kclist_add(&kcore_mem, __va(0), max_low_pfn << PAGE_SHIFT, KCORE_RAM); - kclist_add(&kcore_vmalloc, (void *)VMALLOC_START, - VMALLOC_END-VMALLOC_START, KCORE_VMALLOC); printk(KERN_INFO "Memory: %luk/%luk available (%ldk kernel code, " "%ldk reserved, %ldk data, %ldk init, %ldk highmem)\n", diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c index e91add90ec5..38a450d16b2 100644 --- a/arch/powerpc/mm/init_32.c +++ b/arch/powerpc/mm/init_32.c @@ -243,7 +243,6 @@ void free_initrd_mem(unsigned long start, unsigned long end) #endif #ifdef CONFIG_PROC_KCORE -static struct kcore_list kcore_vmem; static int __init setup_kcore(void) { @@ -271,9 +270,6 @@ static int __init setup_kcore(void) kclist_add(kcore_mem, __va(base), size, KCORE_RAM); } - kclist_add(&kcore_vmem, (void *)VMALLOC_START, - VMALLOC_END-VMALLOC_START, KCORE_VMALLOC); - return 0; } module_init(setup_kcore); diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index 9ee563101b5..87ef492a1a5 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -110,7 +110,6 @@ void free_initrd_mem(unsigned long start, unsigned long end) #endif #ifdef CONFIG_PROC_KCORE -static struct kcore_list kcore_vmem; static int __init setup_kcore(void) { @@ -131,9 +130,6 @@ static int __init setup_kcore(void) kclist_add(kcore_mem, __va(base), size, KCORE_RAM); } - kclist_add(&kcore_vmem, (void *)VMALLOC_START, - VMALLOC_END-VMALLOC_START, KCORE_VMALLOC); - return 0; } module_init(setup_kcore); diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c index ef56c9f9d7b..bf8bd026db5 100644 --- a/arch/sh/mm/init.c +++ b/arch/sh/mm/init.c @@ -186,7 +186,7 @@ void __init paging_init(void) set_fixmap_nocache(FIX_UNCACHED, __pa(&__uncached_start)); } -static struct kcore_list kcore_mem, kcore_vmalloc; +static struct kcore_list kcore_mem; void __init mem_init(void) { @@ -227,8 +227,6 @@ void __init mem_init(void) initsize = (unsigned long) &__init_end - (unsigned long) &__init_begin; kclist_add(&kcore_mem, __va(0), max_low_pfn << PAGE_SHIFT, KCORE_RAM); - kclist_add(&kcore_vmalloc, (void *)VMALLOC_START, - VMALLOC_END - VMALLOC_START, KCORE_VMALLOC); printk(KERN_INFO "Memory: %luk/%luk available (%dk kernel code, " "%dk data, %dk init)\n", diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 2cbc4011293..7108678ca9b 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -857,7 +857,7 @@ static void __init test_wp_bit(void) } } -static struct kcore_list kcore_mem, kcore_vmalloc; +static struct kcore_list kcore_mem; void __init mem_init(void) { @@ -887,8 +887,6 @@ void __init mem_init(void) initsize = (unsigned long) &__init_end - (unsigned long) &__init_begin; kclist_add(&kcore_mem, __va(0), max_low_pfn << PAGE_SHIFT, KCORE_RAM); - kclist_add(&kcore_vmalloc, (void *)VMALLOC_START, - VMALLOC_END-VMALLOC_START, KCORE_VMALLOC); printk(KERN_INFO "Memory: %luk/%luk available (%dk kernel code, " "%dk reserved, %dk data, %dk init, %ldk highmem)\n", diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index c05810b614f..da2cae7427a 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -647,7 +647,7 @@ EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); #endif /* CONFIG_MEMORY_HOTPLUG */ -static struct kcore_list kcore_mem, kcore_vmalloc, kcore_kernel, +static struct kcore_list kcore_mem, kcore_kernel, kcore_modules, kcore_vsyscall; void __init mem_init(void) @@ -678,8 +678,6 @@ void __init mem_init(void) /* Register memory areas for /proc/kcore */ kclist_add(&kcore_mem, __va(0), max_low_pfn << PAGE_SHIFT, KCORE_RAM); - kclist_add(&kcore_vmalloc, (void *)VMALLOC_START, - VMALLOC_END-VMALLOC_START, KCORE_VMALLOC); kclist_add(&kcore_kernel, &_stext, _end - _stext, KCORE_TEXT); kclist_add(&kcore_modules, (void *)MODULES_VADDR, MODULES_LEN, KCORE_OTHER); diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index 659c1635db8..e10d360110b 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -372,9 +372,14 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) return acc; } +static struct kcore_list kcore_vmalloc; + static int __init proc_kcore_init(void) { proc_root_kcore = proc_create("kcore", S_IRUSR, NULL, &proc_kcore_operations); + + kclist_add(&kcore_vmalloc, (void *)VMALLOC_START, + VMALLOC_END - VMALLOC_START, KCORE_VMALLOC); return 0; } module_init(proc_kcore_init); -- cgit v1.2.3 From 9492587cf35d370db33ef4b38375dfb35a105b61 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Tue, 22 Sep 2009 16:45:45 -0700 Subject: kcore: register text area in generic way Some 64bit arch has special segment for mapping kernel text. It should be entried to /proc/kcore in addtion to direct-linear-map, vmalloc area. This patch unifies KCORE_TEXT entry scattered under x86 and ia64. I'm not familiar with other archs (mips has its own even after this patch) but range of [_stext ..._end) is a valid area of text and it's not in direct-map area, defining CONFIG_ARCH_PROC_KCORE_TEXT is only a necessary thing to do. Note: I left mips as it is now. Signed-off-by: KAMEZAWA Hiroyuki Cc: Ralf Baechle Cc: Benjamin Herrenschmidt Cc: WANG Cong Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/Kconfig | 4 ++++ arch/ia64/mm/init.c | 3 +-- arch/x86/Kconfig | 4 ++++ arch/x86/mm/init_64.c | 4 +--- fs/proc/kcore.c | 19 ++++++++++++++++++- 5 files changed, 28 insertions(+), 6 deletions(-) (limited to 'fs/proc') diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 011a1cdf0eb..6851e52ed5a 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -500,6 +500,10 @@ config HAVE_ARCH_NODEDATA_EXTENSION def_bool y depends on NUMA +config ARCH_PROC_KCORE_TEXT + def_bool y + depends on PROC_KCORE + config IA32_SUPPORT bool "Support for Linux/x86 binaries" help diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index 286b98aa854..3f95ea1d6fb 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -617,7 +617,7 @@ mem_init (void) long reserved_pages, codesize, datasize, initsize; pg_data_t *pgdat; int i; - static struct kcore_list kcore_mem, kcore_kernel; + static struct kcore_list kcore_mem; BUG_ON(PTRS_PER_PGD * sizeof(pgd_t) != PAGE_SIZE); BUG_ON(PTRS_PER_PMD * sizeof(pmd_t) != PAGE_SIZE); @@ -640,7 +640,6 @@ mem_init (void) high_memory = __va(max_low_pfn * PAGE_SIZE); kclist_add(&kcore_mem, __va(0), max_low_pfn * PAGE_SIZE, KCORE_RAM); - kclist_add(&kcore_kernel, _stext, _end - _stext, KCORE_TEXT); for_each_online_pgdat(pgdat) if (pgdat->bdata->node_bootmem_map) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index e4ff5d1280c..7c7a54bed4a 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1204,6 +1204,10 @@ config ARCH_DISCONTIGMEM_DEFAULT def_bool y depends on NUMA && X86_32 +config ARCH_PROC_KCORE_TEXT + def_bool y + depends on X86_64 && PROC_KCORE + config ARCH_SPARSEMEM_DEFAULT def_bool y depends on X86_64 diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index da2cae7427a..a0c2efb10cb 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -647,8 +647,7 @@ EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); #endif /* CONFIG_MEMORY_HOTPLUG */ -static struct kcore_list kcore_mem, kcore_kernel, - kcore_modules, kcore_vsyscall; +static struct kcore_list kcore_mem, kcore_modules, kcore_vsyscall; void __init mem_init(void) { @@ -678,7 +677,6 @@ void __init mem_init(void) /* Register memory areas for /proc/kcore */ kclist_add(&kcore_mem, __va(0), max_low_pfn << PAGE_SHIFT, KCORE_RAM); - kclist_add(&kcore_kernel, &_stext, _end - _stext, KCORE_TEXT); kclist_add(&kcore_modules, (void *)MODULES_VADDR, MODULES_LEN, KCORE_OTHER); kclist_add(&kcore_vsyscall, (void *)VSYSCALL_START, diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index e10d360110b..fdde1cc7839 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -21,6 +21,7 @@ #include #include #include +#include #define CORE_STR "CORE" @@ -374,10 +375,26 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) static struct kcore_list kcore_vmalloc; +#ifdef CONFIG_ARCH_PROC_KCORE_TEXT +static struct kcore_list kcore_text; +/* + * If defined, special segment is used for mapping kernel text instead of + * direct-map area. We need to create special TEXT section. + */ +static void __init proc_kcore_text_init(void) +{ + kclist_add(&kcore_text, _stext, _end - _stext, KCORE_TEXT); +} +#else +static void __init proc_kcore_text_init(void) +{ +} +#endif + static int __init proc_kcore_init(void) { proc_root_kcore = proc_create("kcore", S_IRUSR, NULL, &proc_kcore_operations); - + proc_kcore_text_init(); kclist_add(&kcore_vmalloc, (void *)VMALLOC_START, VMALLOC_END - VMALLOC_START, KCORE_VMALLOC); return 0; -- cgit v1.2.3 From 3089aa1b0c07fb7c48f9829c619f50198307789d Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Tue, 22 Sep 2009 16:45:48 -0700 Subject: kcore: use registerd physmem information For /proc/kcore, each arch registers its memory range by kclist_add(). In usual, - range of physical memory - range of vmalloc area - text, etc... are registered but "range of physical memory" has some troubles. It doesn't updated at memory hotplug and it tend to include unnecessary memory holes. Now, /proc/iomem (kernel/resource.c) includes required physical memory range information and it's properly updated at memory hotplug. Then, it's good to avoid using its own code(duplicating information) and to rebuild kclist for physical memory based on /proc/iomem. Signed-off-by: KAMEZAWA Hiroyuki Signed-off-by: Jiri Slaby Cc: Ralf Baechle Cc: Benjamin Herrenschmidt Cc: WANG Cong Cc: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/mm/init.c | 3 - arch/mips/mm/init.c | 2 - arch/powerpc/mm/init_32.c | 32 --------- arch/powerpc/mm/init_64.c | 26 ------- arch/sh/mm/init.c | 4 -- arch/x86/mm/init_32.c | 4 -- arch/x86/mm/init_64.c | 3 +- fs/proc/kcore.c | 179 ++++++++++++++++++++++++++++++++++++++++++---- 8 files changed, 168 insertions(+), 85 deletions(-) (limited to 'fs/proc') diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index 3f95ea1d6fb..1857766a63c 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -617,7 +617,6 @@ mem_init (void) long reserved_pages, codesize, datasize, initsize; pg_data_t *pgdat; int i; - static struct kcore_list kcore_mem; BUG_ON(PTRS_PER_PGD * sizeof(pgd_t) != PAGE_SIZE); BUG_ON(PTRS_PER_PMD * sizeof(pmd_t) != PAGE_SIZE); @@ -639,8 +638,6 @@ mem_init (void) high_memory = __va(max_low_pfn * PAGE_SIZE); - kclist_add(&kcore_mem, __va(0), max_low_pfn * PAGE_SIZE, KCORE_RAM); - for_each_online_pgdat(pgdat) if (pgdat->bdata->node_bootmem_map) totalram_pages += free_all_bootmem_node(pgdat); diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index 4a83da499e2..15aa1902a78 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -352,7 +352,6 @@ void __init paging_init(void) free_area_init_nodes(max_zone_pfns); } -static struct kcore_list kcore_mem; #ifdef CONFIG_64BIT static struct kcore_list kcore_kseg0; #endif @@ -412,7 +411,6 @@ void __init mem_init(void) kclist_add(&kcore_kseg0, (void *) CKSEG0, 0x80000000 - 4, KCORE_TEXT); #endif - kclist_add(&kcore_mem, __va(0), max_low_pfn << PAGE_SHIFT, KCORE_RAM); printk(KERN_INFO "Memory: %luk/%luk available (%ldk kernel code, " "%ldk reserved, %ldk data, %ldk init, %ldk highmem)\n", diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c index 38a450d16b2..9ddcfb4dc13 100644 --- a/arch/powerpc/mm/init_32.c +++ b/arch/powerpc/mm/init_32.c @@ -242,35 +242,3 @@ void free_initrd_mem(unsigned long start, unsigned long end) } #endif -#ifdef CONFIG_PROC_KCORE - -static int __init setup_kcore(void) -{ - int i; - - for (i = 0; i < lmb.memory.cnt; i++) { - unsigned long base; - unsigned long size; - struct kcore_list *kcore_mem; - - base = lmb.memory.region[i].base; - size = lmb.memory.region[i].size; - - kcore_mem = kmalloc(sizeof(struct kcore_list), GFP_ATOMIC); - if (!kcore_mem) - panic("%s: kmalloc failed\n", __func__); - - /* must stay under 32 bits */ - if ( 0xfffffffful - (unsigned long)__va(base) < size) { - size = 0xfffffffful - (unsigned long)(__va(base)); - printk(KERN_DEBUG "setup_kcore: restrict size=%lx\n", - size); - } - - kclist_add(kcore_mem, __va(base), size, KCORE_RAM); - } - - return 0; -} -module_init(setup_kcore); -#endif diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index 87ef492a1a5..335c578b9cc 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -109,32 +109,6 @@ void free_initrd_mem(unsigned long start, unsigned long end) } #endif -#ifdef CONFIG_PROC_KCORE - -static int __init setup_kcore(void) -{ - int i; - - for (i=0; i < lmb.memory.cnt; i++) { - unsigned long base, size; - struct kcore_list *kcore_mem; - - base = lmb.memory.region[i].base; - size = lmb.memory.region[i].size; - - /* GFP_ATOMIC to avoid might_sleep warnings during boot */ - kcore_mem = kmalloc(sizeof(struct kcore_list), GFP_ATOMIC); - if (!kcore_mem) - panic("%s: kmalloc failed\n", __func__); - - kclist_add(kcore_mem, __va(base), size, KCORE_RAM); - } - - return 0; -} -module_init(setup_kcore); -#endif - static void pgd_ctor(void *addr) { memset(addr, 0, PGD_TABLE_SIZE); diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c index bf8bd026db5..8173e38afd3 100644 --- a/arch/sh/mm/init.c +++ b/arch/sh/mm/init.c @@ -186,8 +186,6 @@ void __init paging_init(void) set_fixmap_nocache(FIX_UNCACHED, __pa(&__uncached_start)); } -static struct kcore_list kcore_mem; - void __init mem_init(void) { int codesize, datasize, initsize; @@ -226,8 +224,6 @@ void __init mem_init(void) datasize = (unsigned long) &_edata - (unsigned long) &_etext; initsize = (unsigned long) &__init_end - (unsigned long) &__init_begin; - kclist_add(&kcore_mem, __va(0), max_low_pfn << PAGE_SHIFT, KCORE_RAM); - printk(KERN_INFO "Memory: %luk/%luk available (%dk kernel code, " "%dk data, %dk init)\n", nr_free_pages() << (PAGE_SHIFT-10), diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 7108678ca9b..30938c1d8d5 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -857,8 +857,6 @@ static void __init test_wp_bit(void) } } -static struct kcore_list kcore_mem; - void __init mem_init(void) { int codesize, reservedpages, datasize, initsize; @@ -886,8 +884,6 @@ void __init mem_init(void) datasize = (unsigned long) &_edata - (unsigned long) &_etext; initsize = (unsigned long) &__init_end - (unsigned long) &__init_begin; - kclist_add(&kcore_mem, __va(0), max_low_pfn << PAGE_SHIFT, KCORE_RAM); - printk(KERN_INFO "Memory: %luk/%luk available (%dk kernel code, " "%dk reserved, %dk data, %dk init, %ldk highmem)\n", nr_free_pages() << (PAGE_SHIFT-10), diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index a0c2efb10cb..d5d23cc2407 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -647,7 +647,7 @@ EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); #endif /* CONFIG_MEMORY_HOTPLUG */ -static struct kcore_list kcore_mem, kcore_modules, kcore_vsyscall; +static struct kcore_list kcore_modules, kcore_vsyscall; void __init mem_init(void) { @@ -676,7 +676,6 @@ void __init mem_init(void) initsize = (unsigned long) &__init_end - (unsigned long) &__init_begin; /* Register memory areas for /proc/kcore */ - kclist_add(&kcore_mem, __va(0), max_low_pfn << PAGE_SHIFT, KCORE_RAM); kclist_add(&kcore_modules, (void *)MODULES_VADDR, MODULES_LEN, KCORE_OTHER); kclist_add(&kcore_vsyscall, (void *)VSYSCALL_START, diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index fdde1cc7839..802de33d634 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -17,10 +17,14 @@ #include #include #include +#include #include #include #include #include +#include +#include +#include #include #define CORE_STR "CORE" @@ -31,17 +35,6 @@ static struct proc_dir_entry *proc_root_kcore; -static int open_kcore(struct inode * inode, struct file * filp) -{ - return capable(CAP_SYS_RAWIO) ? 0 : -EPERM; -} - -static ssize_t read_kcore(struct file *, char __user *, size_t, loff_t *); - -static const struct file_operations proc_kcore_operations = { - .read = read_kcore, - .open = open_kcore, -}; #ifndef kc_vaddr_to_offset #define kc_vaddr_to_offset(v) ((v) - PAGE_OFFSET) @@ -61,6 +54,7 @@ struct memelfnote static LIST_HEAD(kclist_head); static DEFINE_RWLOCK(kclist_lock); +static int kcore_need_update = 1; void kclist_add(struct kcore_list *new, void *addr, size_t size, int type) @@ -99,6 +93,126 @@ static size_t get_kcore_size(int *nphdr, size_t *elf_buflen) return size + *elf_buflen; } +static void free_kclist_ents(struct list_head *head) +{ + struct kcore_list *tmp, *pos; + + list_for_each_entry_safe(pos, tmp, head, list) { + list_del(&pos->list); + kfree(pos); + } +} +/* + * Replace all KCORE_RAM information with passed list. + */ +static void __kcore_update_ram(struct list_head *list) +{ + struct kcore_list *tmp, *pos; + LIST_HEAD(garbage); + + write_lock(&kclist_lock); + if (kcore_need_update) { + list_for_each_entry_safe(pos, tmp, &kclist_head, list) { + if (pos->type == KCORE_RAM) + list_move(&pos->list, &garbage); + } + list_splice_tail(list, &kclist_head); + } else + list_splice(list, &garbage); + kcore_need_update = 0; + write_unlock(&kclist_lock); + + free_kclist_ents(&garbage); +} + + +#ifdef CONFIG_HIGHMEM +/* + * If no highmem, we can assume [0...max_low_pfn) continuous range of memory + * because memory hole is not as big as !HIGHMEM case. + * (HIGHMEM is special because part of memory is _invisible_ from the kernel.) + */ +static int kcore_update_ram(void) +{ + LIST_HEAD(head); + struct kcore_list *ent; + int ret = 0; + + ent = kmalloc(sizeof(*ent), GFP_KERNEL); + if (!ent) + return -ENOMEM; + ent->addr = (unsigned long)__va(0); + ent->size = max_low_pfn << PAGE_SHIFT; + ent->type = KCORE_RAM; + list_add(&ent->list, &head); + __kcore_update_ram(&head); + return ret; +} + +#else /* !CONFIG_HIGHMEM */ + +static int +kclist_add_private(unsigned long pfn, unsigned long nr_pages, void *arg) +{ + struct list_head *head = (struct list_head *)arg; + struct kcore_list *ent; + + ent = kmalloc(sizeof(*ent), GFP_KERNEL); + if (!ent) + return -ENOMEM; + ent->addr = (unsigned long)__va((pfn << PAGE_SHIFT)); + ent->size = nr_pages << PAGE_SHIFT; + + /* Sanity check: Can happen in 32bit arch...maybe */ + if (ent->addr < (unsigned long) __va(0)) + goto free_out; + + /* cut not-mapped area. ....from ppc-32 code. */ + if (ULONG_MAX - ent->addr < ent->size) + ent->size = ULONG_MAX - ent->addr; + + /* cut when vmalloc() area is higher than direct-map area */ + if (VMALLOC_START > (unsigned long)__va(0)) { + if (ent->addr > VMALLOC_START) + goto free_out; + if (VMALLOC_START - ent->addr < ent->size) + ent->size = VMALLOC_START - ent->addr; + } + + ent->type = KCORE_RAM; + list_add_tail(&ent->list, head); + return 0; +free_out: + kfree(ent); + return 1; +} + +static int kcore_update_ram(void) +{ + int nid, ret; + unsigned long end_pfn; + LIST_HEAD(head); + + /* Not inialized....update now */ + /* find out "max pfn" */ + end_pfn = 0; + for_each_node_state(nid, N_HIGH_MEMORY) { + unsigned long node_end; + node_end = NODE_DATA(nid)->node_start_pfn + + NODE_DATA(nid)->node_spanned_pages; + if (end_pfn < node_end) + end_pfn = node_end; + } + /* scan 0 to max_pfn */ + ret = walk_system_ram_range(0, end_pfn, &head, kclist_add_private); + if (ret) { + free_kclist_ents(&head); + return -ENOMEM; + } + __kcore_update_ram(&head); + return ret; +} +#endif /* CONFIG_HIGHMEM */ /*****************************************************************************/ /* @@ -373,6 +487,39 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) return acc; } + +static int open_kcore(struct inode *inode, struct file *filp) +{ + if (!capable(CAP_SYS_RAWIO)) + return -EPERM; + if (kcore_need_update) + kcore_update_ram(); + return 0; +} + + +static const struct file_operations proc_kcore_operations = { + .read = read_kcore, + .open = open_kcore, +}; + +#ifdef CONFIG_MEMORY_HOTPLUG +/* just remember that we have to update kcore */ +static int __meminit kcore_callback(struct notifier_block *self, + unsigned long action, void *arg) +{ + switch (action) { + case MEM_ONLINE: + case MEM_OFFLINE: + write_lock(&kclist_lock); + kcore_need_update = 1; + write_unlock(&kclist_lock); + } + return NOTIFY_OK; +} +#endif + + static struct kcore_list kcore_vmalloc; #ifdef CONFIG_ARCH_PROC_KCORE_TEXT @@ -393,10 +540,18 @@ static void __init proc_kcore_text_init(void) static int __init proc_kcore_init(void) { - proc_root_kcore = proc_create("kcore", S_IRUSR, NULL, &proc_kcore_operations); + proc_root_kcore = proc_create("kcore", S_IRUSR, NULL, + &proc_kcore_operations); + /* Store text area if it's special */ proc_kcore_text_init(); + /* Store vmalloc area */ kclist_add(&kcore_vmalloc, (void *)VMALLOC_START, VMALLOC_END - VMALLOC_START, KCORE_VMALLOC); + /* Store direct-map area from physical memory map */ + kcore_update_ram(); + hotplug_memory_notifier(kcore_callback, 0); + /* Other special area, area-for-module etc is arch specific. */ + return 0; } module_init(proc_kcore_init); -- cgit v1.2.3 From 26562c59fa9111ae3ea7b78045889662aac9e5ac Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Tue, 22 Sep 2009 16:45:49 -0700 Subject: kcore: register vmemmap range Benjamin Herrenschmidt pointed out that vmemmap range is not included in KCORE_RAM, KCORE_VMALLOC .... This adds KCORE_VMEMMAP if SPARSEMEM_VMEMMAP is used. By this, vmemmap can be readable via /proc/kcore Because it's not vmalloc area, vread/vwrite cannot be used. But the range is static against the memory layout, this patch handles vmemmap area by the same scheme with physical memory. This patch assumes SPARSEMEM_VMEMMAP range is not in VMALLOC range. It's correct now. [akpm@linux-foundation.org: fix typo] Signed-off-by: KAMEZAWA Hiroyuki Cc: Jiri Slaby Cc: Ralf Baechle Cc: Benjamin Herrenschmidt Cc: WANG Cong Cc: Benjamin Herrenschmidt Cc: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/kcore.c | 52 +++++++++++++++++++++++++++++++++++++++++++++++-- include/linux/proc_fs.h | 1 + 2 files changed, 51 insertions(+), 2 deletions(-) (limited to 'fs/proc') diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index 802de33d634..78970e6f715 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -103,7 +103,7 @@ static void free_kclist_ents(struct list_head *head) } } /* - * Replace all KCORE_RAM information with passed list. + * Replace all KCORE_RAM/KCORE_VMEMMAP information with passed list. */ static void __kcore_update_ram(struct list_head *list) { @@ -113,7 +113,8 @@ static void __kcore_update_ram(struct list_head *list) write_lock(&kclist_lock); if (kcore_need_update) { list_for_each_entry_safe(pos, tmp, &kclist_head, list) { - if (pos->type == KCORE_RAM) + if (pos->type == KCORE_RAM + || pos->type == KCORE_VMEMMAP) list_move(&pos->list, &garbage); } list_splice_tail(list, &kclist_head); @@ -151,6 +152,47 @@ static int kcore_update_ram(void) #else /* !CONFIG_HIGHMEM */ +#ifdef CONFIG_SPARSEMEM_VMEMMAP +/* calculate vmemmap's address from given system ram pfn and register it */ +int get_sparsemem_vmemmap_info(struct kcore_list *ent, struct list_head *head) +{ + unsigned long pfn = __pa(ent->addr) >> PAGE_SHIFT; + unsigned long nr_pages = ent->size >> PAGE_SHIFT; + unsigned long start, end; + struct kcore_list *vmm, *tmp; + + + start = ((unsigned long)pfn_to_page(pfn)) & PAGE_MASK; + end = ((unsigned long)pfn_to_page(pfn + nr_pages)) - 1; + end = ALIGN(end, PAGE_SIZE); + /* overlap check (because we have to align page */ + list_for_each_entry(tmp, head, list) { + if (tmp->type != KCORE_VMEMMAP) + continue; + if (start < tmp->addr + tmp->size) + if (end > tmp->addr) + end = tmp->addr; + } + if (start < end) { + vmm = kmalloc(sizeof(*vmm), GFP_KERNEL); + if (!vmm) + return 0; + vmm->addr = start; + vmm->size = end - start; + vmm->type = KCORE_VMEMMAP; + list_add_tail(&vmm->list, head); + } + return 1; + +} +#else +int get_sparsemem_vmemmap_info(struct kcore_list *ent, struct list_head *head) +{ + return 1; +} + +#endif + static int kclist_add_private(unsigned long pfn, unsigned long nr_pages, void *arg) { @@ -181,6 +223,12 @@ kclist_add_private(unsigned long pfn, unsigned long nr_pages, void *arg) ent->type = KCORE_RAM; list_add_tail(&ent->list, head); + + if (!get_sparsemem_vmemmap_info(ent, head)) { + list_del(&ent->list); + goto free_out; + } + return 0; free_out: kfree(ent); diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index bd7b840765a..379eaed72d4 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -82,6 +82,7 @@ enum kcore_type { KCORE_TEXT, KCORE_VMALLOC, KCORE_RAM, + KCORE_VMEMMAP, KCORE_OTHER, }; -- cgit v1.2.3 From 81ac3ad9061dd9cd490ee92f0c5316a14d77ce18 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Tue, 22 Sep 2009 16:45:49 -0700 Subject: kcore: register module area in generic way Some archs define MODULED_VADDR/MODULES_END which is not in VMALLOC area. This is handled only in x86-64. This patch make it more generic. And we can use vread/vwrite to access the area. Fix it. Signed-off-by: KAMEZAWA Hiroyuki Cc: Jiri Slaby Cc: Ralf Baechle Cc: Benjamin Herrenschmidt Cc: WANG Cong Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/mm/init_64.c | 4 +--- fs/proc/kcore.c | 19 ++++++++++++++++++- include/linux/mm.h | 8 ++++++++ mm/vmalloc.c | 2 +- 4 files changed, 28 insertions(+), 5 deletions(-) (limited to 'fs/proc') diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index d5d23cc2407..5a4398a6006 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -647,7 +647,7 @@ EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); #endif /* CONFIG_MEMORY_HOTPLUG */ -static struct kcore_list kcore_modules, kcore_vsyscall; +static struct kcore_list kcore_vsyscall; void __init mem_init(void) { @@ -676,8 +676,6 @@ void __init mem_init(void) initsize = (unsigned long) &__init_end - (unsigned long) &__init_begin; /* Register memory areas for /proc/kcore */ - kclist_add(&kcore_modules, (void *)MODULES_VADDR, MODULES_LEN, - KCORE_OTHER); kclist_add(&kcore_vsyscall, (void *)VSYSCALL_START, VSYSCALL_END - VSYSCALL_START, KCORE_OTHER); diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index 78970e6f715..c6a5ec73197 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -490,7 +490,7 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) if (m == NULL) { if (clear_user(buffer, tsz)) return -EFAULT; - } else if (is_vmalloc_addr((void *)start)) { + } else if (is_vmalloc_or_module_addr((void *)start)) { char * elf_buf; elf_buf = kzalloc(tsz, GFP_KERNEL); @@ -586,6 +586,22 @@ static void __init proc_kcore_text_init(void) } #endif +#if defined(CONFIG_MODULES) && defined(MODULES_VADDR) +/* + * MODULES_VADDR has no intersection with VMALLOC_ADDR. + */ +struct kcore_list kcore_modules; +static void __init add_modules_range(void) +{ + kclist_add(&kcore_modules, (void *)MODULES_VADDR, + MODULES_END - MODULES_VADDR, KCORE_VMALLOC); +} +#else +static void __init add_modules_range(void) +{ +} +#endif + static int __init proc_kcore_init(void) { proc_root_kcore = proc_create("kcore", S_IRUSR, NULL, @@ -595,6 +611,7 @@ static int __init proc_kcore_init(void) /* Store vmalloc area */ kclist_add(&kcore_vmalloc, (void *)VMALLOC_START, VMALLOC_END - VMALLOC_START, KCORE_VMALLOC); + add_modules_range(); /* Store direct-map area from physical memory map */ kcore_update_ram(); hotplug_memory_notifier(kcore_callback, 0); diff --git a/include/linux/mm.h b/include/linux/mm.h index 5946e2ff9fe..b6eae5e3144 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -285,6 +285,14 @@ static inline int is_vmalloc_addr(const void *x) return 0; #endif } +#ifdef CONFIG_MMU +extern int is_vmalloc_or_module_addr(const void *x); +#else +static int is_vmalloc_or_module_addr(const void *x) +{ + return 0; +} +#endif static inline struct page *compound_head(struct page *page) { diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 5535da1d696..69511e66323 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -184,7 +184,7 @@ static int vmap_page_range(unsigned long start, unsigned long end, return ret; } -static inline int is_vmalloc_or_module_addr(const void *x) +int is_vmalloc_or_module_addr(const void *x) { /* * ARM, x86-64 and sparc64 put modules in a special place, -- cgit v1.2.3 From 90396f96b7da0e2305ffe0266d22b6f8221f28ba Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Tue, 22 Sep 2009 16:45:50 -0700 Subject: kcore: more fixes for init proc_kcore_init() doesn't check NULL case. fix it and remove unnecessary comments. Signed-off-by: KAMEZAWA Hiroyuki Acked-by: WANG Cong Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/kcore.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'fs/proc') diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index c6a5ec73197..70733780fdd 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -606,6 +606,10 @@ static int __init proc_kcore_init(void) { proc_root_kcore = proc_create("kcore", S_IRUSR, NULL, &proc_kcore_operations); + if (!proc_root_kcore) { + printk(KERN_ERR "couldn't create /proc/kcore\n"); + return 0; /* Always returns 0. */ + } /* Store text area if it's special */ proc_kcore_text_init(); /* Store vmalloc area */ @@ -615,7 +619,6 @@ static int __init proc_kcore_init(void) /* Store direct-map area from physical memory map */ kcore_update_ram(); hotplug_memory_notifier(kcore_callback, 0); - /* Other special area, area-for-module etc is arch specific. */ return 0; } -- cgit v1.2.3 From 678ad5d8aaf8925cb8465f84e1e47d9b1284666a Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Tue, 22 Sep 2009 16:45:51 -0700 Subject: /proc/kcore: fix stat.st_size Presently the size of /proc/kcore which can be read by 'ls -l' is 0. But it's not the correct value. On x86-64, ls -l shows ... root root 140737486266368 2009-09-17 10:29 /proc/kcore Then, 7FFFFFFE02000. This comes from vmalloc area's size. (*) This shows "core" size, not memory size. This patch shows the size by updating "size" field in struct proc_dir_entry. Later, lookup routine will create inode and fill inode->i_size based on this value. Then, this has a problem. - Once inode is cached, inode->i_size will never be updated. Then, this patch is not memory-hotplug-aware. To update inode->i_size, we have to know dentry or inode. But there is no way to lookup them by inside kernel. Hmmm.... Next patch will try it. Signed-off-by: KAMEZAWA Hiroyuki Acked-by: WANG Cong Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/kcore.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'fs/proc') diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index 70733780fdd..3d0485c361c 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -107,6 +107,8 @@ static void free_kclist_ents(struct list_head *head) */ static void __kcore_update_ram(struct list_head *list) { + int nphdr; + size_t size; struct kcore_list *tmp, *pos; LIST_HEAD(garbage); @@ -121,6 +123,7 @@ static void __kcore_update_ram(struct list_head *list) } else list_splice(list, &garbage); kcore_need_update = 0; + proc_root_kcore->size = get_kcore_size(&nphdr, &size); write_unlock(&kclist_lock); free_kclist_ents(&garbage); @@ -429,7 +432,8 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) unsigned long start; read_lock(&kclist_lock); - proc_root_kcore->size = size = get_kcore_size(&nphdr, &elf_buflen); + size = get_kcore_size(&nphdr, &elf_buflen); + if (buflen == 0 || *fpos >= size) { read_unlock(&kclist_lock); return 0; -- cgit v1.2.3 From 0d4c36a9b6ab6b15851f60956d901a3c53574ea8 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Tue, 22 Sep 2009 16:45:52 -0700 Subject: /proc/kcore: update stat.st_size after memory hotplug After memory hotplug (or other events in future), kcore size can be modified. To update inode->i_size, we have to know inode/dentry but we can't get it from inside /proc directly. But considerinyg memory hotplug, kcore image is updated only when it's opened. Then, updating inode->i_size at open() is enough. Signed-off-by: KAMEZAWA Hiroyuki Acked-by: WANG Cong Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/kcore.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'fs/proc') diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index 3d0485c361c..56013371f9f 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -546,6 +546,11 @@ static int open_kcore(struct inode *inode, struct file *filp) return -EPERM; if (kcore_need_update) kcore_update_ram(); + if (i_size_read(inode) != proc_root_kcore->size) { + mutex_lock(&inode->i_mutex); + i_size_write(inode, proc_root_kcore->size); + mutex_unlock(&inode->i_mutex); + } return 0; } -- cgit v1.2.3 From 96830a57de1197519b62af6a4c9ceea556c18c3d Mon Sep 17 00:00:00 2001 From: Michael Abbott Date: Thu, 24 Sep 2009 10:15:19 +0200 Subject: [PATCH] Fix idle time field in /proc/uptime Git commit 79741dd changes idle cputime accounting, but unfortunately the /proc/uptime file hasn't caught up. Here the idle time calculation from /proc/stat is copied over. Signed-off-by: Michael Abbott Signed-off-by: Martin Schwidefsky --- fs/proc/uptime.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'fs/proc') diff --git a/fs/proc/uptime.c b/fs/proc/uptime.c index 0c10a0b3f14..766b1d45605 100644 --- a/fs/proc/uptime.c +++ b/fs/proc/uptime.c @@ -4,13 +4,18 @@ #include #include #include +#include #include static int uptime_proc_show(struct seq_file *m, void *v) { struct timespec uptime; struct timespec idle; - cputime_t idletime = cputime_add(init_task.utime, init_task.stime); + int i; + cputime_t idletime = cputime_zero; + + for_each_possible_cpu(i) + idletime = cputime64_add(idletime, kstat_cpu(i).cpustat.idle); do_posix_clock_monotonic_gettime(&uptime); monotonic_to_bootbased(&uptime); -- cgit v1.2.3 From 8d65af789f3e2cf4cfbdbf71a0f7a61ebcd41d38 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Wed, 23 Sep 2009 15:57:19 -0700 Subject: sysctl: remove "struct file *" argument of ->proc_handler It's unused. It isn't needed -- read or write flag is already passed and sysctl shouldn't care about the rest. It _was_ used in two places at arch/frv for some reason. Signed-off-by: Alexey Dobriyan Cc: David Howells Cc: "Eric W. Biederman" Cc: Al Viro Cc: Ralf Baechle Cc: Martin Schwidefsky Cc: Ingo Molnar Cc: "David S. Miller" Cc: James Morris Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/frv/kernel/pm.c | 14 +++---- arch/mips/lasat/sysctl.c | 18 ++++----- arch/s390/appldata/appldata_base.c | 9 ++--- arch/s390/kernel/debug.c | 4 +- arch/s390/mm/cmm.c | 4 +- arch/x86/include/asm/nmi.h | 3 +- arch/x86/kernel/apic/nmi.c | 4 +- arch/x86/kernel/vsyscall_64.c | 10 +---- drivers/cdrom/cdrom.c | 8 ++-- drivers/char/random.c | 4 +- drivers/net/wireless/arlan-proc.c | 28 +++++++------- drivers/parport/procfs.c | 12 +++--- fs/coda/coda_int.h | 1 + fs/drop_caches.c | 4 +- fs/file_table.c | 6 +-- fs/proc/proc_sysctl.c | 2 +- fs/xfs/linux-2.6/xfs_sysctl.c | 3 +- include/linux/fs.h | 2 +- include/linux/ftrace.h | 4 +- include/linux/hugetlb.h | 6 +-- include/linux/mm.h | 2 +- include/linux/mmzone.h | 13 +++---- include/linux/sched.h | 8 ++-- include/linux/security.h | 2 +- include/linux/swap.h | 2 +- include/linux/sysctl.h | 19 +++++----- include/linux/writeback.h | 11 +++--- include/net/ip.h | 2 +- include/net/ndisc.h | 2 - ipc/ipc_sysctl.c | 16 ++++---- ipc/mq_sysctl.c | 8 ++-- kernel/hung_task.c | 4 +- kernel/sched.c | 4 +- kernel/sched_fair.c | 4 +- kernel/slow-work.c | 12 +++--- kernel/softlockup.c | 4 +- kernel/sysctl.c | 78 ++++++++++++++++---------------------- kernel/trace/ftrace.c | 4 +- kernel/trace/trace_stack.c | 4 +- kernel/utsname_sysctl.c | 4 +- mm/hugetlb.c | 12 +++--- mm/page-writeback.c | 20 +++++----- mm/page_alloc.c | 24 ++++++------ mm/vmscan.c | 4 +- net/bridge/br_netfilter.c | 4 +- net/decnet/dn_dev.c | 5 +-- net/decnet/sysctl_net_decnet.c | 2 - net/ipv4/devinet.c | 12 +++--- net/ipv4/route.c | 7 ++-- net/ipv4/sysctl_net_ipv4.c | 16 ++++---- net/ipv6/addrconf.c | 8 ++-- net/ipv6/ndisc.c | 8 ++-- net/ipv6/route.c | 4 +- net/irda/irsysctl.c | 8 ++-- net/netfilter/ipvs/ip_vs_ctl.c | 8 ++-- net/netfilter/nf_log.c | 4 +- net/phonet/sysctl.c | 4 +- net/sunrpc/sysctl.c | 4 +- net/sunrpc/xprtrdma/svc_rdma.c | 2 +- security/min_addr.c | 4 +- 60 files changed, 239 insertions(+), 270 deletions(-) (limited to 'fs/proc') diff --git a/arch/frv/kernel/pm.c b/arch/frv/kernel/pm.c index be722fc1acf..0d4d3e3a4cf 100644 --- a/arch/frv/kernel/pm.c +++ b/arch/frv/kernel/pm.c @@ -150,7 +150,7 @@ static int user_atoi(char __user *ubuf, size_t len) /* * Send us to sleep. */ -static int sysctl_pm_do_suspend(ctl_table *ctl, int write, struct file *filp, +static int sysctl_pm_do_suspend(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *fpos) { int retval, mode; @@ -198,13 +198,13 @@ static int try_set_cmode(int new_cmode) } -static int cmode_procctl(ctl_table *ctl, int write, struct file *filp, +static int cmode_procctl(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *fpos) { int new_cmode; if (!write) - return proc_dointvec(ctl, write, filp, buffer, lenp, fpos); + return proc_dointvec(ctl, write, buffer, lenp, fpos); new_cmode = user_atoi(buffer, *lenp); @@ -301,13 +301,13 @@ static int try_set_cm(int new_cm) return 0; } -static int p0_procctl(ctl_table *ctl, int write, struct file *filp, +static int p0_procctl(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *fpos) { int new_p0; if (!write) - return proc_dointvec(ctl, write, filp, buffer, lenp, fpos); + return proc_dointvec(ctl, write, buffer, lenp, fpos); new_p0 = user_atoi(buffer, *lenp); @@ -345,13 +345,13 @@ static int p0_sysctl(ctl_table *table, return 1; } -static int cm_procctl(ctl_table *ctl, int write, struct file *filp, +static int cm_procctl(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *fpos) { int new_cm; if (!write) - return proc_dointvec(ctl, write, filp, buffer, lenp, fpos); + return proc_dointvec(ctl, write, buffer, lenp, fpos); new_cm = user_atoi(buffer, *lenp); diff --git a/arch/mips/lasat/sysctl.c b/arch/mips/lasat/sysctl.c index 3f04d4c406b..b3deed8db61 100644 --- a/arch/mips/lasat/sysctl.c +++ b/arch/mips/lasat/sysctl.c @@ -56,12 +56,12 @@ int sysctl_lasatstring(ctl_table *table, /* And the same for proc */ -int proc_dolasatstring(ctl_table *table, int write, struct file *filp, +int proc_dolasatstring(ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int r; - r = proc_dostring(table, write, filp, buffer, lenp, ppos); + r = proc_dostring(table, write, buffer, lenp, ppos); if ((!write) || r) return r; @@ -71,12 +71,12 @@ int proc_dolasatstring(ctl_table *table, int write, struct file *filp, } /* proc function to write EEPROM after changing int entry */ -int proc_dolasatint(ctl_table *table, int write, struct file *filp, +int proc_dolasatint(ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int r; - r = proc_dointvec(table, write, filp, buffer, lenp, ppos); + r = proc_dointvec(table, write, buffer, lenp, ppos); if ((!write) || r) return r; @@ -89,7 +89,7 @@ int proc_dolasatint(ctl_table *table, int write, struct file *filp, static int rtctmp; /* proc function to read/write RealTime Clock */ -int proc_dolasatrtc(ctl_table *table, int write, struct file *filp, +int proc_dolasatrtc(ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct timespec ts; @@ -102,7 +102,7 @@ int proc_dolasatrtc(ctl_table *table, int write, struct file *filp, if (rtctmp < 0) rtctmp = 0; } - r = proc_dointvec(table, write, filp, buffer, lenp, ppos); + r = proc_dointvec(table, write, buffer, lenp, ppos); if (r) return r; @@ -154,7 +154,7 @@ int sysctl_lasat_rtc(ctl_table *table, #endif #ifdef CONFIG_INET -int proc_lasat_ip(ctl_table *table, int write, struct file *filp, +int proc_lasat_ip(ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { unsigned int ip; @@ -231,12 +231,12 @@ static int sysctl_lasat_prid(ctl_table *table, return 0; } -int proc_lasat_prid(ctl_table *table, int write, struct file *filp, +int proc_lasat_prid(ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int r; - r = proc_dointvec(table, write, filp, buffer, lenp, ppos); + r = proc_dointvec(table, write, buffer, lenp, ppos); if (r < 0) return r; if (write) { diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c index 264528e4f58..b55fd7ed1c3 100644 --- a/arch/s390/appldata/appldata_base.c +++ b/arch/s390/appldata/appldata_base.c @@ -50,10 +50,9 @@ static struct platform_device *appldata_pdev; * /proc entries (sysctl) */ static const char appldata_proc_name[APPLDATA_PROC_NAME_LENGTH] = "appldata"; -static int appldata_timer_handler(ctl_table *ctl, int write, struct file *filp, +static int appldata_timer_handler(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos); static int appldata_interval_handler(ctl_table *ctl, int write, - struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos); @@ -247,7 +246,7 @@ __appldata_vtimer_setup(int cmd) * Start/Stop timer, show status of timer (0 = not active, 1 = active) */ static int -appldata_timer_handler(ctl_table *ctl, int write, struct file *filp, +appldata_timer_handler(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int len; @@ -289,7 +288,7 @@ out: * current timer interval. */ static int -appldata_interval_handler(ctl_table *ctl, int write, struct file *filp, +appldata_interval_handler(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int len, interval; @@ -335,7 +334,7 @@ out: * monitoring (0 = not in process, 1 = in process) */ static int -appldata_generic_handler(ctl_table *ctl, int write, struct file *filp, +appldata_generic_handler(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { struct appldata_ops *ops = NULL, *tmp_ops; diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c index 4c512561687..20f282c911c 100644 --- a/arch/s390/kernel/debug.c +++ b/arch/s390/kernel/debug.c @@ -881,11 +881,11 @@ static int debug_active=1; * if debug_active is already off */ static int -s390dbf_procactive(ctl_table *table, int write, struct file *filp, +s390dbf_procactive(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { if (!write || debug_stoppable || !debug_active) - return proc_dointvec(table, write, filp, buffer, lenp, ppos); + return proc_dointvec(table, write, buffer, lenp, ppos); else return 0; } diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c index 413c240cbca..b201135cc18 100644 --- a/arch/s390/mm/cmm.c +++ b/arch/s390/mm/cmm.c @@ -262,7 +262,7 @@ cmm_skip_blanks(char *cp, char **endp) static struct ctl_table cmm_table[]; static int -cmm_pages_handler(ctl_table *ctl, int write, struct file *filp, +cmm_pages_handler(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { char buf[16], *p; @@ -303,7 +303,7 @@ cmm_pages_handler(ctl_table *ctl, int write, struct file *filp, } static int -cmm_timeout_handler(ctl_table *ctl, int write, struct file *filp, +cmm_timeout_handler(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { char buf[64], *p; diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h index e63cf7d441e..139d4c1a33a 100644 --- a/arch/x86/include/asm/nmi.h +++ b/arch/x86/include/asm/nmi.h @@ -40,8 +40,7 @@ extern unsigned int nmi_watchdog; #define NMI_INVALID 3 struct ctl_table; -struct file; -extern int proc_nmi_enabled(struct ctl_table *, int , struct file *, +extern int proc_nmi_enabled(struct ctl_table *, int , void __user *, size_t *, loff_t *); extern int unknown_nmi_panic; diff --git a/arch/x86/kernel/apic/nmi.c b/arch/x86/kernel/apic/nmi.c index cb66a22d98a..7ff61d6a188 100644 --- a/arch/x86/kernel/apic/nmi.c +++ b/arch/x86/kernel/apic/nmi.c @@ -508,14 +508,14 @@ static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu) /* * proc handler for /proc/sys/kernel/nmi */ -int proc_nmi_enabled(struct ctl_table *table, int write, struct file *file, +int proc_nmi_enabled(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) { int old_state; nmi_watchdog_enabled = (atomic_read(&nmi_active) > 0) ? 1 : 0; old_state = nmi_watchdog_enabled; - proc_dointvec(table, write, file, buffer, length, ppos); + proc_dointvec(table, write, buffer, length, ppos); if (!!old_state == !!nmi_watchdog_enabled) return 0; diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index cf53a78e2dc..8cb4974ff59 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -228,19 +228,11 @@ static long __vsyscall(3) venosys_1(void) } #ifdef CONFIG_SYSCTL - -static int -vsyscall_sysctl_change(ctl_table *ctl, int write, struct file * filp, - void __user *buffer, size_t *lenp, loff_t *ppos) -{ - return proc_dointvec(ctl, write, filp, buffer, lenp, ppos); -} - static ctl_table kernel_table2[] = { { .procname = "vsyscall64", .data = &vsyscall_gtod_data.sysctl_enabled, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = vsyscall_sysctl_change }, + .proc_handler = proc_dointvec }, {} }; diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index 71d1b9bab70..614da5b8613 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -3412,7 +3412,7 @@ static int cdrom_print_info(const char *header, int val, char *info, return 0; } -static int cdrom_sysctl_info(ctl_table *ctl, int write, struct file * filp, +static int cdrom_sysctl_info(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int pos; @@ -3489,7 +3489,7 @@ static int cdrom_sysctl_info(ctl_table *ctl, int write, struct file * filp, goto done; doit: mutex_unlock(&cdrom_mutex); - return proc_dostring(ctl, write, filp, buffer, lenp, ppos); + return proc_dostring(ctl, write, buffer, lenp, ppos); done: printk(KERN_INFO "cdrom: info buffer too small\n"); goto doit; @@ -3525,12 +3525,12 @@ static void cdrom_update_settings(void) mutex_unlock(&cdrom_mutex); } -static int cdrom_sysctl_handler(ctl_table *ctl, int write, struct file * filp, +static int cdrom_sysctl_handler(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int ret; - ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos); + ret = proc_dointvec(ctl, write, buffer, lenp, ppos); if (write) { diff --git a/drivers/char/random.c b/drivers/char/random.c index d8a9255e1a3..04b505e5a5e 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1231,7 +1231,7 @@ static char sysctl_bootid[16]; * as an ASCII string in the standard UUID format. If accesses via the * sysctl system call, it is returned as 16 bytes of binary data. */ -static int proc_do_uuid(ctl_table *table, int write, struct file *filp, +static int proc_do_uuid(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { ctl_table fake_table; @@ -1254,7 +1254,7 @@ static int proc_do_uuid(ctl_table *table, int write, struct file *filp, fake_table.data = buf; fake_table.maxlen = sizeof(buf); - return proc_dostring(&fake_table, write, filp, buffer, lenp, ppos); + return proc_dostring(&fake_table, write, buffer, lenp, ppos); } static int uuid_strategy(ctl_table *table, diff --git a/drivers/net/wireless/arlan-proc.c b/drivers/net/wireless/arlan-proc.c index 2ab1d59870f..a8b689635a3 100644 --- a/drivers/net/wireless/arlan-proc.c +++ b/drivers/net/wireless/arlan-proc.c @@ -402,7 +402,7 @@ static int arlan_setup_card_by_book(struct net_device *dev) static char arlan_drive_info[ARLAN_STR_SIZE] = "A655\n\0"; -static int arlan_sysctl_info(ctl_table * ctl, int write, struct file *filp, +static int arlan_sysctl_info(ctl_table * ctl, int write, void __user *buffer, size_t * lenp, loff_t *ppos) { int i; @@ -629,7 +629,7 @@ final: *lenp = pos; if (!write) - retv = proc_dostring(ctl, write, filp, buffer, lenp, ppos); + retv = proc_dostring(ctl, write, buffer, lenp, ppos); else { *lenp = 0; @@ -639,7 +639,7 @@ final: } -static int arlan_sysctl_info161719(ctl_table * ctl, int write, struct file *filp, +static int arlan_sysctl_info161719(ctl_table * ctl, int write, void __user *buffer, size_t * lenp, loff_t *ppos) { int i; @@ -669,11 +669,11 @@ static int arlan_sysctl_info161719(ctl_table * ctl, int write, struct file *filp final: *lenp = pos; - retv = proc_dostring(ctl, write, filp, buffer, lenp, ppos); + retv = proc_dostring(ctl, write, buffer, lenp, ppos); return retv; } -static int arlan_sysctl_infotxRing(ctl_table * ctl, int write, struct file *filp, +static int arlan_sysctl_infotxRing(ctl_table * ctl, int write, void __user *buffer, size_t * lenp, loff_t *ppos) { int i; @@ -698,11 +698,11 @@ static int arlan_sysctl_infotxRing(ctl_table * ctl, int write, struct file *filp SARLBNpln(u_char, txBuffer, 0x800); final: *lenp = pos; - retv = proc_dostring(ctl, write, filp, buffer, lenp, ppos); + retv = proc_dostring(ctl, write, buffer, lenp, ppos); return retv; } -static int arlan_sysctl_inforxRing(ctl_table * ctl, int write, struct file *filp, +static int arlan_sysctl_inforxRing(ctl_table * ctl, int write, void __user *buffer, size_t * lenp, loff_t *ppos) { int i; @@ -726,11 +726,11 @@ static int arlan_sysctl_inforxRing(ctl_table * ctl, int write, struct file *filp SARLBNpln(u_char, rxBuffer, 0x800); final: *lenp = pos; - retv = proc_dostring(ctl, write, filp, buffer, lenp, ppos); + retv = proc_dostring(ctl, write, buffer, lenp, ppos); return retv; } -static int arlan_sysctl_info18(ctl_table * ctl, int write, struct file *filp, +static int arlan_sysctl_info18(ctl_table * ctl, int write, void __user *buffer, size_t * lenp, loff_t *ppos) { int i; @@ -756,7 +756,7 @@ static int arlan_sysctl_info18(ctl_table * ctl, int write, struct file *filp, final: *lenp = pos; - retv = proc_dostring(ctl, write, filp, buffer, lenp, ppos); + retv = proc_dostring(ctl, write, buffer, lenp, ppos); return retv; } @@ -766,7 +766,7 @@ final: static char conf_reset_result[200]; -static int arlan_configure(ctl_table * ctl, int write, struct file *filp, +static int arlan_configure(ctl_table * ctl, int write, void __user *buffer, size_t * lenp, loff_t *ppos) { int pos = 0; @@ -788,10 +788,10 @@ static int arlan_configure(ctl_table * ctl, int write, struct file *filp, return -1; *lenp = pos; - return proc_dostring(ctl, write, filp, buffer, lenp, ppos); + return proc_dostring(ctl, write, buffer, lenp, ppos); } -static int arlan_sysctl_reset(ctl_table * ctl, int write, struct file *filp, +static int arlan_sysctl_reset(ctl_table * ctl, int write, void __user *buffer, size_t * lenp, loff_t *ppos) { int pos = 0; @@ -811,7 +811,7 @@ static int arlan_sysctl_reset(ctl_table * ctl, int write, struct file *filp, } else return -1; *lenp = pos + 3; - return proc_dostring(ctl, write, filp, buffer, lenp, ppos); + return proc_dostring(ctl, write, buffer, lenp, ppos); } diff --git a/drivers/parport/procfs.c b/drivers/parport/procfs.c index 554e11f9e1c..8eefe56f1cb 100644 --- a/drivers/parport/procfs.c +++ b/drivers/parport/procfs.c @@ -31,7 +31,7 @@ #define PARPORT_MIN_SPINTIME_VALUE 1 #define PARPORT_MAX_SPINTIME_VALUE 1000 -static int do_active_device(ctl_table *table, int write, struct file *filp, +static int do_active_device(ctl_table *table, int write, void __user *result, size_t *lenp, loff_t *ppos) { struct parport *port = (struct parport *)table->extra1; @@ -68,7 +68,7 @@ static int do_active_device(ctl_table *table, int write, struct file *filp, } #ifdef CONFIG_PARPORT_1284 -static int do_autoprobe(ctl_table *table, int write, struct file *filp, +static int do_autoprobe(ctl_table *table, int write, void __user *result, size_t *lenp, loff_t *ppos) { struct parport_device_info *info = table->extra2; @@ -111,7 +111,7 @@ static int do_autoprobe(ctl_table *table, int write, struct file *filp, #endif /* IEEE1284.3 support. */ static int do_hardware_base_addr (ctl_table *table, int write, - struct file *filp, void __user *result, + void __user *result, size_t *lenp, loff_t *ppos) { struct parport *port = (struct parport *)table->extra1; @@ -139,7 +139,7 @@ static int do_hardware_base_addr (ctl_table *table, int write, } static int do_hardware_irq (ctl_table *table, int write, - struct file *filp, void __user *result, + void __user *result, size_t *lenp, loff_t *ppos) { struct parport *port = (struct parport *)table->extra1; @@ -167,7 +167,7 @@ static int do_hardware_irq (ctl_table *table, int write, } static int do_hardware_dma (ctl_table *table, int write, - struct file *filp, void __user *result, + void __user *result, size_t *lenp, loff_t *ppos) { struct parport *port = (struct parport *)table->extra1; @@ -195,7 +195,7 @@ static int do_hardware_dma (ctl_table *table, int write, } static int do_hardware_modes (ctl_table *table, int write, - struct file *filp, void __user *result, + void __user *result, size_t *lenp, loff_t *ppos) { struct parport *port = (struct parport *)table->extra1; diff --git a/fs/coda/coda_int.h b/fs/coda/coda_int.h index 8ccd5ed81d9..d99860a3389 100644 --- a/fs/coda/coda_int.h +++ b/fs/coda/coda_int.h @@ -2,6 +2,7 @@ #define _CODA_INT_ struct dentry; +struct file; extern struct file_system_type coda_fs_type; extern unsigned long coda_timeout; diff --git a/fs/drop_caches.c b/fs/drop_caches.c index a2edb791344..31f4b0e6d72 100644 --- a/fs/drop_caches.c +++ b/fs/drop_caches.c @@ -63,9 +63,9 @@ static void drop_slab(void) } int drop_caches_sysctl_handler(ctl_table *table, int write, - struct file *file, void __user *buffer, size_t *length, loff_t *ppos) + void __user *buffer, size_t *length, loff_t *ppos) { - proc_dointvec_minmax(table, write, file, buffer, length, ppos); + proc_dointvec_minmax(table, write, buffer, length, ppos); if (write) { if (sysctl_drop_caches & 1) drop_pagecache(); diff --git a/fs/file_table.c b/fs/file_table.c index 334ce39881f..8eb44042e00 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -74,14 +74,14 @@ EXPORT_SYMBOL_GPL(get_max_files); * Handle nr_files sysctl */ #if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS) -int proc_nr_files(ctl_table *table, int write, struct file *filp, +int proc_nr_files(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { files_stat.nr_files = get_nr_files(); - return proc_dointvec(table, write, filp, buffer, lenp, ppos); + return proc_dointvec(table, write, buffer, lenp, ppos); } #else -int proc_nr_files(ctl_table *table, int write, struct file *filp, +int proc_nr_files(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 9b1e4e9a16b..f667e8aeabd 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -153,7 +153,7 @@ static ssize_t proc_sys_call_handler(struct file *filp, void __user *buf, /* careful: calling conventions are nasty here */ res = count; - error = table->proc_handler(table, write, filp, buf, &res, ppos); + error = table->proc_handler(table, write, buf, &res, ppos); if (!error) error = res; out: diff --git a/fs/xfs/linux-2.6/xfs_sysctl.c b/fs/xfs/linux-2.6/xfs_sysctl.c index 916c0ffb608..c5bc67c4e3b 100644 --- a/fs/xfs/linux-2.6/xfs_sysctl.c +++ b/fs/xfs/linux-2.6/xfs_sysctl.c @@ -26,7 +26,6 @@ STATIC int xfs_stats_clear_proc_handler( ctl_table *ctl, int write, - struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos) @@ -34,7 +33,7 @@ xfs_stats_clear_proc_handler( int c, ret, *valp = ctl->data; __uint32_t vn_active; - ret = proc_dointvec_minmax(ctl, write, filp, buffer, lenp, ppos); + ret = proc_dointvec_minmax(ctl, write, buffer, lenp, ppos); if (!ret && write && *valp) { printk("XFS Clearing xfsstats\n"); diff --git a/include/linux/fs.h b/include/linux/fs.h index 51803528b09..33ed6644abd 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2467,7 +2467,7 @@ ssize_t simple_attr_write(struct file *file, const char __user *buf, size_t len, loff_t *ppos); struct ctl_table; -int proc_nr_files(struct ctl_table *table, int write, struct file *filp, +int proc_nr_files(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); int __init get_filesystem_list(char *buf); diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 3c0924a18da..cd3d2abaf30 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -19,7 +19,7 @@ extern int ftrace_enabled; extern int ftrace_enable_sysctl(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, + void __user *buffer, size_t *lenp, loff_t *ppos); typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip); @@ -94,7 +94,7 @@ static inline void ftrace_start(void) { } extern int stack_tracer_enabled; int stack_trace_sysctl(struct ctl_table *table, int write, - struct file *file, void __user *buffer, size_t *lenp, + void __user *buffer, size_t *lenp, loff_t *ppos); #endif diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 176e7ee73ef..11ab19ac6b3 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -20,9 +20,9 @@ static inline int is_vm_hugetlb_page(struct vm_area_struct *vma) } void reset_vma_resv_huge_pages(struct vm_area_struct *vma); -int hugetlb_sysctl_handler(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *); -int hugetlb_overcommit_handler(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *); -int hugetlb_treat_movable_handler(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *); +int hugetlb_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); +int hugetlb_overcommit_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); +int hugetlb_treat_movable_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *); int follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *, struct page **, struct vm_area_struct **, diff --git a/include/linux/mm.h b/include/linux/mm.h index b6eae5e3144..87218ae84e3 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1279,7 +1279,7 @@ int in_gate_area_no_task(unsigned long addr); #define in_gate_area(task, addr) ({(void)task; in_gate_area_no_task(addr);}) #endif /* __HAVE_ARCH_GATE_AREA */ -int drop_caches_sysctl_handler(struct ctl_table *, int, struct file *, +int drop_caches_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask, unsigned long lru_pages); diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 652ef01be58..6f7561730d8 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -755,21 +755,20 @@ static inline int is_dma(struct zone *zone) /* These two functions are used to setup the per zone pages min values */ struct ctl_table; -struct file; -int min_free_kbytes_sysctl_handler(struct ctl_table *, int, struct file *, +int min_free_kbytes_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1]; -int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int, struct file *, +int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); -int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *, int, struct file *, +int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *, int, - struct file *, void __user *, size_t *, loff_t *); + void __user *, size_t *, loff_t *); int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *, int, - struct file *, void __user *, size_t *, loff_t *); + void __user *, size_t *, loff_t *); extern int numa_zonelist_order_handler(struct ctl_table *, int, - struct file *, void __user *, size_t *, loff_t *); + void __user *, size_t *, loff_t *); extern char numa_zonelist_order[]; #define NUMA_ZONELIST_ORDER_LEN 16 /* string buffer size */ diff --git a/include/linux/sched.h b/include/linux/sched.h index e951bd2eb9f..811cd96524d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -309,7 +309,7 @@ extern void softlockup_tick(void); extern void touch_softlockup_watchdog(void); extern void touch_all_softlockup_watchdogs(void); extern int proc_dosoftlockup_thresh(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, + void __user *buffer, size_t *lenp, loff_t *ppos); extern unsigned int softlockup_panic; extern int softlockup_thresh; @@ -331,7 +331,7 @@ extern unsigned long sysctl_hung_task_check_count; extern unsigned long sysctl_hung_task_timeout_secs; extern unsigned long sysctl_hung_task_warnings; extern int proc_dohung_task_timeout_secs(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, + void __user *buffer, size_t *lenp, loff_t *ppos); #endif @@ -1906,7 +1906,7 @@ extern unsigned int sysctl_sched_time_avg; extern unsigned int sysctl_timer_migration; int sched_nr_latency_handler(struct ctl_table *table, int write, - struct file *file, void __user *buffer, size_t *length, + void __user *buffer, size_t *length, loff_t *ppos); #endif #ifdef CONFIG_SCHED_DEBUG @@ -1924,7 +1924,7 @@ extern unsigned int sysctl_sched_rt_period; extern int sysctl_sched_rt_runtime; int sched_rt_handler(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, + void __user *buffer, size_t *lenp, loff_t *ppos); extern unsigned int sysctl_sched_compat_yield; diff --git a/include/linux/security.h b/include/linux/security.h index d050b66ab9e..239e40d0450 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -133,7 +133,7 @@ static inline unsigned long round_hint_to_min(unsigned long hint) return PAGE_ALIGN(mmap_min_addr); return hint; } -extern int mmap_min_addr_handler(struct ctl_table *table, int write, struct file *filp, +extern int mmap_min_addr_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); #ifdef CONFIG_SECURITY diff --git a/include/linux/swap.h b/include/linux/swap.h index 4c78fea989b..82232dbea3f 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -245,7 +245,7 @@ extern int page_evictable(struct page *page, struct vm_area_struct *vma); extern void scan_mapping_unevictable_pages(struct address_space *); extern unsigned long scan_unevictable_pages; -extern int scan_unevictable_handler(struct ctl_table *, int, struct file *, +extern int scan_unevictable_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); extern int scan_unevictable_register_node(struct node *node); extern void scan_unevictable_unregister_node(struct node *node); diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index e76d3b22a46..1e4743ee683 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -29,7 +29,6 @@ #include #include -struct file; struct completion; #define CTL_MAXNAME 10 /* how many path components do we allow in a @@ -977,25 +976,25 @@ typedef int ctl_handler (struct ctl_table *table, void __user *oldval, size_t __user *oldlenp, void __user *newval, size_t newlen); -typedef int proc_handler (struct ctl_table *ctl, int write, struct file * filp, +typedef int proc_handler (struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos); -extern int proc_dostring(struct ctl_table *, int, struct file *, +extern int proc_dostring(struct ctl_table *, int, void __user *, size_t *, loff_t *); -extern int proc_dointvec(struct ctl_table *, int, struct file *, +extern int proc_dointvec(struct ctl_table *, int, void __user *, size_t *, loff_t *); -extern int proc_dointvec_minmax(struct ctl_table *, int, struct file *, +extern int proc_dointvec_minmax(struct ctl_table *, int, void __user *, size_t *, loff_t *); -extern int proc_dointvec_jiffies(struct ctl_table *, int, struct file *, +extern int proc_dointvec_jiffies(struct ctl_table *, int, void __user *, size_t *, loff_t *); -extern int proc_dointvec_userhz_jiffies(struct ctl_table *, int, struct file *, +extern int proc_dointvec_userhz_jiffies(struct ctl_table *, int, void __user *, size_t *, loff_t *); -extern int proc_dointvec_ms_jiffies(struct ctl_table *, int, struct file *, +extern int proc_dointvec_ms_jiffies(struct ctl_table *, int, void __user *, size_t *, loff_t *); -extern int proc_doulongvec_minmax(struct ctl_table *, int, struct file *, +extern int proc_doulongvec_minmax(struct ctl_table *, int, void __user *, size_t *, loff_t *); extern int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int, - struct file *, void __user *, size_t *, loff_t *); + void __user *, size_t *, loff_t *); extern int do_sysctl (int __user *name, int nlen, void __user *oldval, size_t __user *oldlenp, diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 75cf58666ff..66ebddcff66 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -110,21 +110,20 @@ extern int laptop_mode; extern unsigned long determine_dirtyable_memory(void); extern int dirty_background_ratio_handler(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, + void __user *buffer, size_t *lenp, loff_t *ppos); extern int dirty_background_bytes_handler(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, + void __user *buffer, size_t *lenp, loff_t *ppos); extern int dirty_ratio_handler(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, + void __user *buffer, size_t *lenp, loff_t *ppos); extern int dirty_bytes_handler(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, + void __user *buffer, size_t *lenp, loff_t *ppos); struct ctl_table; -struct file; -int dirty_writeback_centisecs_handler(struct ctl_table *, int, struct file *, +int dirty_writeback_centisecs_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); void get_dirty_limits(unsigned long *pbackground, unsigned long *pdirty, diff --git a/include/net/ip.h b/include/net/ip.h index 72c36926c26..5b26a0bd178 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -399,7 +399,7 @@ extern void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 dport, * fed into the routing cache should use these handlers. */ int ipv4_doint_and_flush(ctl_table *ctl, int write, - struct file* filp, void __user *buffer, + void __user *buffer, size_t *lenp, loff_t *ppos); int ipv4_doint_and_flush_strategy(ctl_table *table, void __user *oldval, size_t __user *oldlenp, diff --git a/include/net/ndisc.h b/include/net/ndisc.h index 1459ed3e269..f76f22d0572 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -55,7 +55,6 @@ enum { #include struct ctl_table; -struct file; struct inet6_dev; struct net_device; struct net_proto_family; @@ -139,7 +138,6 @@ extern int igmp6_event_report(struct sk_buff *skb); #ifdef CONFIG_SYSCTL extern int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write, - struct file * filp, void __user *buffer, size_t *lenp, loff_t *ppos); diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c index 40eab7314ae..7d3704750ef 100644 --- a/ipc/ipc_sysctl.c +++ b/ipc/ipc_sysctl.c @@ -27,18 +27,18 @@ static void *get_ipc(ctl_table *table) } #ifdef CONFIG_PROC_SYSCTL -static int proc_ipc_dointvec(ctl_table *table, int write, struct file *filp, +static int proc_ipc_dointvec(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table ipc_table; memcpy(&ipc_table, table, sizeof(ipc_table)); ipc_table.data = get_ipc(table); - return proc_dointvec(&ipc_table, write, filp, buffer, lenp, ppos); + return proc_dointvec(&ipc_table, write, buffer, lenp, ppos); } static int proc_ipc_callback_dointvec(ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos) + void __user *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table ipc_table; size_t lenp_bef = *lenp; @@ -47,7 +47,7 @@ static int proc_ipc_callback_dointvec(ctl_table *table, int write, memcpy(&ipc_table, table, sizeof(ipc_table)); ipc_table.data = get_ipc(table); - rc = proc_dointvec(&ipc_table, write, filp, buffer, lenp, ppos); + rc = proc_dointvec(&ipc_table, write, buffer, lenp, ppos); if (write && !rc && lenp_bef == *lenp) /* @@ -61,13 +61,13 @@ static int proc_ipc_callback_dointvec(ctl_table *table, int write, } static int proc_ipc_doulongvec_minmax(ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos) + void __user *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table ipc_table; memcpy(&ipc_table, table, sizeof(ipc_table)); ipc_table.data = get_ipc(table); - return proc_doulongvec_minmax(&ipc_table, write, filp, buffer, + return proc_doulongvec_minmax(&ipc_table, write, buffer, lenp, ppos); } @@ -95,7 +95,7 @@ static void ipc_auto_callback(int val) } static int proc_ipcauto_dointvec_minmax(ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos) + void __user *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table ipc_table; size_t lenp_bef = *lenp; @@ -106,7 +106,7 @@ static int proc_ipcauto_dointvec_minmax(ctl_table *table, int write, ipc_table.data = get_ipc(table); oldval = *((int *)(ipc_table.data)); - rc = proc_dointvec_minmax(&ipc_table, write, filp, buffer, lenp, ppos); + rc = proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos); if (write && !rc && lenp_bef == *lenp) { int newval = *((int *)(ipc_table.data)); diff --git a/ipc/mq_sysctl.c b/ipc/mq_sysctl.c index 24ae46dfe45..8a058711fc1 100644 --- a/ipc/mq_sysctl.c +++ b/ipc/mq_sysctl.c @@ -31,24 +31,24 @@ static void *get_mq(ctl_table *table) return which; } -static int proc_mq_dointvec(ctl_table *table, int write, struct file *filp, +static int proc_mq_dointvec(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table mq_table; memcpy(&mq_table, table, sizeof(mq_table)); mq_table.data = get_mq(table); - return proc_dointvec(&mq_table, write, filp, buffer, lenp, ppos); + return proc_dointvec(&mq_table, write, buffer, lenp, ppos); } static int proc_mq_dointvec_minmax(ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos) + void __user *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table mq_table; memcpy(&mq_table, table, sizeof(mq_table)); mq_table.data = get_mq(table); - return proc_dointvec_minmax(&mq_table, write, filp, buffer, + return proc_dointvec_minmax(&mq_table, write, buffer, lenp, ppos); } #else diff --git a/kernel/hung_task.c b/kernel/hung_task.c index 022a4927b78..d4e84174740 100644 --- a/kernel/hung_task.c +++ b/kernel/hung_task.c @@ -171,12 +171,12 @@ static unsigned long timeout_jiffies(unsigned long timeout) * Process updating of timeout sysctl */ int proc_dohung_task_timeout_secs(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, + void __user *buffer, size_t *lenp, loff_t *ppos) { int ret; - ret = proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos); + ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos); if (ret || !write) goto out; diff --git a/kernel/sched.c b/kernel/sched.c index 0d0361b9dbb..ee61f454a98 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -10312,7 +10312,7 @@ static int sched_rt_global_constraints(void) #endif /* CONFIG_RT_GROUP_SCHED */ int sched_rt_handler(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, + void __user *buffer, size_t *lenp, loff_t *ppos) { int ret; @@ -10323,7 +10323,7 @@ int sched_rt_handler(struct ctl_table *table, int write, old_period = sysctl_sched_rt_period; old_runtime = sysctl_sched_rt_runtime; - ret = proc_dointvec(table, write, filp, buffer, lenp, ppos); + ret = proc_dointvec(table, write, buffer, lenp, ppos); if (!ret && write) { ret = sched_rt_global_constraints(); diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index ecc637a0d59..4e777b47eed 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -384,10 +384,10 @@ static struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq) #ifdef CONFIG_SCHED_DEBUG int sched_nr_latency_handler(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, + void __user *buffer, size_t *lenp, loff_t *ppos) { - int ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos); + int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret || !write) return ret; diff --git a/kernel/slow-work.c b/kernel/slow-work.c index 09d7519557d..0d31135efbf 100644 --- a/kernel/slow-work.c +++ b/kernel/slow-work.c @@ -26,10 +26,10 @@ static void slow_work_cull_timeout(unsigned long); static void slow_work_oom_timeout(unsigned long); #ifdef CONFIG_SYSCTL -static int slow_work_min_threads_sysctl(struct ctl_table *, int, struct file *, +static int slow_work_min_threads_sysctl(struct ctl_table *, int, void __user *, size_t *, loff_t *); -static int slow_work_max_threads_sysctl(struct ctl_table *, int , struct file *, +static int slow_work_max_threads_sysctl(struct ctl_table *, int , void __user *, size_t *, loff_t *); #endif @@ -493,10 +493,10 @@ static void slow_work_oom_timeout(unsigned long data) * Handle adjustment of the minimum number of threads */ static int slow_work_min_threads_sysctl(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, + void __user *buffer, size_t *lenp, loff_t *ppos) { - int ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos); + int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); int n; if (ret == 0) { @@ -521,10 +521,10 @@ static int slow_work_min_threads_sysctl(struct ctl_table *table, int write, * Handle adjustment of the maximum number of threads */ static int slow_work_max_threads_sysctl(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, + void __user *buffer, size_t *lenp, loff_t *ppos) { - int ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos); + int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); int n; if (ret == 0) { diff --git a/kernel/softlockup.c b/kernel/softlockup.c index 88796c33083..81324d12eb3 100644 --- a/kernel/softlockup.c +++ b/kernel/softlockup.c @@ -90,11 +90,11 @@ void touch_all_softlockup_watchdogs(void) EXPORT_SYMBOL(touch_all_softlockup_watchdogs); int proc_dosoftlockup_thresh(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, + void __user *buffer, size_t *lenp, loff_t *ppos) { touch_all_softlockup_watchdogs(); - return proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos); + return proc_dointvec_minmax(table, write, buffer, lenp, ppos); } /* diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 37abb8c3995..a02697b7cb9 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -163,9 +163,9 @@ extern int max_lock_depth; #endif #ifdef CONFIG_PROC_SYSCTL -static int proc_do_cad_pid(struct ctl_table *table, int write, struct file *filp, +static int proc_do_cad_pid(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); -static int proc_taint(struct ctl_table *table, int write, struct file *filp, +static int proc_taint(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); #endif @@ -2226,7 +2226,7 @@ void sysctl_head_put(struct ctl_table_header *head) #ifdef CONFIG_PROC_SYSCTL static int _proc_do_string(void* data, int maxlen, int write, - struct file *filp, void __user *buffer, + void __user *buffer, size_t *lenp, loff_t *ppos) { size_t len; @@ -2287,7 +2287,6 @@ static int _proc_do_string(void* data, int maxlen, int write, * proc_dostring - read a string sysctl * @table: the sysctl table * @write: %TRUE if this is a write to the sysctl file - * @filp: the file structure * @buffer: the user buffer * @lenp: the size of the user buffer * @ppos: file position @@ -2301,10 +2300,10 @@ static int _proc_do_string(void* data, int maxlen, int write, * * Returns 0 on success. */ -int proc_dostring(struct ctl_table *table, int write, struct file *filp, +int proc_dostring(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - return _proc_do_string(table->data, table->maxlen, write, filp, + return _proc_do_string(table->data, table->maxlen, write, buffer, lenp, ppos); } @@ -2329,7 +2328,7 @@ static int do_proc_dointvec_conv(int *negp, unsigned long *lvalp, } static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table, - int write, struct file *filp, void __user *buffer, + int write, void __user *buffer, size_t *lenp, loff_t *ppos, int (*conv)(int *negp, unsigned long *lvalp, int *valp, int write, void *data), @@ -2436,13 +2435,13 @@ static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table, #undef TMPBUFLEN } -static int do_proc_dointvec(struct ctl_table *table, int write, struct file *filp, +static int do_proc_dointvec(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos, int (*conv)(int *negp, unsigned long *lvalp, int *valp, int write, void *data), void *data) { - return __do_proc_dointvec(table->data, table, write, filp, + return __do_proc_dointvec(table->data, table, write, buffer, lenp, ppos, conv, data); } @@ -2450,7 +2449,6 @@ static int do_proc_dointvec(struct ctl_table *table, int write, struct file *fil * proc_dointvec - read a vector of integers * @table: the sysctl table * @write: %TRUE if this is a write to the sysctl file - * @filp: the file structure * @buffer: the user buffer * @lenp: the size of the user buffer * @ppos: file position @@ -2460,10 +2458,10 @@ static int do_proc_dointvec(struct ctl_table *table, int write, struct file *fil * * Returns 0 on success. */ -int proc_dointvec(struct ctl_table *table, int write, struct file *filp, +int proc_dointvec(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - return do_proc_dointvec(table,write,filp,buffer,lenp,ppos, + return do_proc_dointvec(table,write,buffer,lenp,ppos, NULL,NULL); } @@ -2471,7 +2469,7 @@ int proc_dointvec(struct ctl_table *table, int write, struct file *filp, * Taint values can only be increased * This means we can safely use a temporary. */ -static int proc_taint(struct ctl_table *table, int write, struct file *filp, +static int proc_taint(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table t; @@ -2483,7 +2481,7 @@ static int proc_taint(struct ctl_table *table, int write, struct file *filp, t = *table; t.data = &tmptaint; - err = proc_doulongvec_minmax(&t, write, filp, buffer, lenp, ppos); + err = proc_doulongvec_minmax(&t, write, buffer, lenp, ppos); if (err < 0) return err; @@ -2535,7 +2533,6 @@ static int do_proc_dointvec_minmax_conv(int *negp, unsigned long *lvalp, * proc_dointvec_minmax - read a vector of integers with min/max values * @table: the sysctl table * @write: %TRUE if this is a write to the sysctl file - * @filp: the file structure * @buffer: the user buffer * @lenp: the size of the user buffer * @ppos: file position @@ -2548,19 +2545,18 @@ static int do_proc_dointvec_minmax_conv(int *negp, unsigned long *lvalp, * * Returns 0 on success. */ -int proc_dointvec_minmax(struct ctl_table *table, int write, struct file *filp, +int proc_dointvec_minmax(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { struct do_proc_dointvec_minmax_conv_param param = { .min = (int *) table->extra1, .max = (int *) table->extra2, }; - return do_proc_dointvec(table, write, filp, buffer, lenp, ppos, + return do_proc_dointvec(table, write, buffer, lenp, ppos, do_proc_dointvec_minmax_conv, ¶m); } static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos, unsigned long convmul, @@ -2665,21 +2661,19 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int } static int do_proc_doulongvec_minmax(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos, unsigned long convmul, unsigned long convdiv) { return __do_proc_doulongvec_minmax(table->data, table, write, - filp, buffer, lenp, ppos, convmul, convdiv); + buffer, lenp, ppos, convmul, convdiv); } /** * proc_doulongvec_minmax - read a vector of long integers with min/max values * @table: the sysctl table * @write: %TRUE if this is a write to the sysctl file - * @filp: the file structure * @buffer: the user buffer * @lenp: the size of the user buffer * @ppos: file position @@ -2692,17 +2686,16 @@ static int do_proc_doulongvec_minmax(struct ctl_table *table, int write, * * Returns 0 on success. */ -int proc_doulongvec_minmax(struct ctl_table *table, int write, struct file *filp, +int proc_doulongvec_minmax(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - return do_proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos, 1l, 1l); + return do_proc_doulongvec_minmax(table, write, buffer, lenp, ppos, 1l, 1l); } /** * proc_doulongvec_ms_jiffies_minmax - read a vector of millisecond values with min/max values * @table: the sysctl table * @write: %TRUE if this is a write to the sysctl file - * @filp: the file structure * @buffer: the user buffer * @lenp: the size of the user buffer * @ppos: file position @@ -2717,11 +2710,10 @@ int proc_doulongvec_minmax(struct ctl_table *table, int write, struct file *filp * Returns 0 on success. */ int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos) { - return do_proc_doulongvec_minmax(table, write, filp, buffer, + return do_proc_doulongvec_minmax(table, write, buffer, lenp, ppos, HZ, 1000l); } @@ -2797,7 +2789,6 @@ static int do_proc_dointvec_ms_jiffies_conv(int *negp, unsigned long *lvalp, * proc_dointvec_jiffies - read a vector of integers as seconds * @table: the sysctl table * @write: %TRUE if this is a write to the sysctl file - * @filp: the file structure * @buffer: the user buffer * @lenp: the size of the user buffer * @ppos: file position @@ -2809,10 +2800,10 @@ static int do_proc_dointvec_ms_jiffies_conv(int *negp, unsigned long *lvalp, * * Returns 0 on success. */ -int proc_dointvec_jiffies(struct ctl_table *table, int write, struct file *filp, +int proc_dointvec_jiffies(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - return do_proc_dointvec(table,write,filp,buffer,lenp,ppos, + return do_proc_dointvec(table,write,buffer,lenp,ppos, do_proc_dointvec_jiffies_conv,NULL); } @@ -2820,7 +2811,6 @@ int proc_dointvec_jiffies(struct ctl_table *table, int write, struct file *filp, * proc_dointvec_userhz_jiffies - read a vector of integers as 1/USER_HZ seconds * @table: the sysctl table * @write: %TRUE if this is a write to the sysctl file - * @filp: the file structure * @buffer: the user buffer * @lenp: the size of the user buffer * @ppos: pointer to the file position @@ -2832,10 +2822,10 @@ int proc_dointvec_jiffies(struct ctl_table *table, int write, struct file *filp, * * Returns 0 on success. */ -int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write, struct file *filp, +int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - return do_proc_dointvec(table,write,filp,buffer,lenp,ppos, + return do_proc_dointvec(table,write,buffer,lenp,ppos, do_proc_dointvec_userhz_jiffies_conv,NULL); } @@ -2843,7 +2833,6 @@ int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write, struct file * proc_dointvec_ms_jiffies - read a vector of integers as 1 milliseconds * @table: the sysctl table * @write: %TRUE if this is a write to the sysctl file - * @filp: the file structure * @buffer: the user buffer * @lenp: the size of the user buffer * @ppos: file position @@ -2856,14 +2845,14 @@ int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write, struct file * * Returns 0 on success. */ -int proc_dointvec_ms_jiffies(struct ctl_table *table, int write, struct file *filp, +int proc_dointvec_ms_jiffies(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - return do_proc_dointvec(table, write, filp, buffer, lenp, ppos, + return do_proc_dointvec(table, write, buffer, lenp, ppos, do_proc_dointvec_ms_jiffies_conv, NULL); } -static int proc_do_cad_pid(struct ctl_table *table, int write, struct file *filp, +static int proc_do_cad_pid(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { struct pid *new_pid; @@ -2872,7 +2861,7 @@ static int proc_do_cad_pid(struct ctl_table *table, int write, struct file *filp tmp = pid_vnr(cad_pid); - r = __do_proc_dointvec(&tmp, table, write, filp, buffer, + r = __do_proc_dointvec(&tmp, table, write, buffer, lenp, ppos, NULL, NULL); if (r || !write) return r; @@ -2887,50 +2876,49 @@ static int proc_do_cad_pid(struct ctl_table *table, int write, struct file *filp #else /* CONFIG_PROC_FS */ -int proc_dostring(struct ctl_table *table, int write, struct file *filp, +int proc_dostring(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; } -int proc_dointvec(struct ctl_table *table, int write, struct file *filp, +int proc_dointvec(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; } -int proc_dointvec_minmax(struct ctl_table *table, int write, struct file *filp, +int proc_dointvec_minmax(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; } -int proc_dointvec_jiffies(struct ctl_table *table, int write, struct file *filp, +int proc_dointvec_jiffies(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; } -int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write, struct file *filp, +int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; } -int proc_dointvec_ms_jiffies(struct ctl_table *table, int write, struct file *filp, +int proc_dointvec_ms_jiffies(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; } -int proc_doulongvec_minmax(struct ctl_table *table, int write, struct file *filp, +int proc_doulongvec_minmax(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; } int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos) { diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 23df7771c93..a142579765b 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -3015,7 +3015,7 @@ int unregister_ftrace_function(struct ftrace_ops *ops) int ftrace_enable_sysctl(struct ctl_table *table, int write, - struct file *file, void __user *buffer, size_t *lenp, + void __user *buffer, size_t *lenp, loff_t *ppos) { int ret; @@ -3025,7 +3025,7 @@ ftrace_enable_sysctl(struct ctl_table *table, int write, mutex_lock(&ftrace_lock); - ret = proc_dointvec(table, write, file, buffer, lenp, ppos); + ret = proc_dointvec(table, write, buffer, lenp, ppos); if (ret || !write || (last_ftrace_enabled == !!ftrace_enabled)) goto out; diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 0f6facb050a..8504ac71e4e 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -296,14 +296,14 @@ static const struct file_operations stack_trace_fops = { int stack_trace_sysctl(struct ctl_table *table, int write, - struct file *file, void __user *buffer, size_t *lenp, + void __user *buffer, size_t *lenp, loff_t *ppos) { int ret; mutex_lock(&stack_sysctl_mutex); - ret = proc_dointvec(table, write, file, buffer, lenp, ppos); + ret = proc_dointvec(table, write, buffer, lenp, ppos); if (ret || !write || (last_stack_tracer_enabled == !!stack_tracer_enabled)) diff --git a/kernel/utsname_sysctl.c b/kernel/utsname_sysctl.c index 92359cc747a..69eae358a72 100644 --- a/kernel/utsname_sysctl.c +++ b/kernel/utsname_sysctl.c @@ -42,14 +42,14 @@ static void put_uts(ctl_table *table, int write, void *which) * Special case of dostring for the UTS structure. This has locks * to observe. Should this be in kernel/sys.c ???? */ -static int proc_do_uts_string(ctl_table *table, int write, struct file *filp, +static int proc_do_uts_string(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table uts_table; int r; memcpy(&uts_table, table, sizeof(uts_table)); uts_table.data = get_uts(table, write); - r = proc_dostring(&uts_table,write,filp,buffer,lenp, ppos); + r = proc_dostring(&uts_table,write,buffer,lenp, ppos); put_uts(table, write, uts_table.data); return r; } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 815dbd4a6dc..6f048fcc749 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1537,7 +1537,7 @@ static unsigned int cpuset_mems_nr(unsigned int *array) #ifdef CONFIG_SYSCTL int hugetlb_sysctl_handler(struct ctl_table *table, int write, - struct file *file, void __user *buffer, + void __user *buffer, size_t *length, loff_t *ppos) { struct hstate *h = &default_hstate; @@ -1548,7 +1548,7 @@ int hugetlb_sysctl_handler(struct ctl_table *table, int write, table->data = &tmp; table->maxlen = sizeof(unsigned long); - proc_doulongvec_minmax(table, write, file, buffer, length, ppos); + proc_doulongvec_minmax(table, write, buffer, length, ppos); if (write) h->max_huge_pages = set_max_huge_pages(h, tmp); @@ -1557,10 +1557,10 @@ int hugetlb_sysctl_handler(struct ctl_table *table, int write, } int hugetlb_treat_movable_handler(struct ctl_table *table, int write, - struct file *file, void __user *buffer, + void __user *buffer, size_t *length, loff_t *ppos) { - proc_dointvec(table, write, file, buffer, length, ppos); + proc_dointvec(table, write, buffer, length, ppos); if (hugepages_treat_as_movable) htlb_alloc_mask = GFP_HIGHUSER_MOVABLE; else @@ -1569,7 +1569,7 @@ int hugetlb_treat_movable_handler(struct ctl_table *table, int write, } int hugetlb_overcommit_handler(struct ctl_table *table, int write, - struct file *file, void __user *buffer, + void __user *buffer, size_t *length, loff_t *ppos) { struct hstate *h = &default_hstate; @@ -1580,7 +1580,7 @@ int hugetlb_overcommit_handler(struct ctl_table *table, int write, table->data = &tmp; table->maxlen = sizeof(unsigned long); - proc_doulongvec_minmax(table, write, file, buffer, length, ppos); + proc_doulongvec_minmax(table, write, buffer, length, ppos); if (write) { spin_lock(&hugetlb_lock); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 5f378dd5880..be197f71b09 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -155,37 +155,37 @@ static void update_completion_period(void) } int dirty_background_ratio_handler(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, + void __user *buffer, size_t *lenp, loff_t *ppos) { int ret; - ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos); + ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write) dirty_background_bytes = 0; return ret; } int dirty_background_bytes_handler(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, + void __user *buffer, size_t *lenp, loff_t *ppos) { int ret; - ret = proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos); + ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write) dirty_background_ratio = 0; return ret; } int dirty_ratio_handler(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, + void __user *buffer, size_t *lenp, loff_t *ppos) { int old_ratio = vm_dirty_ratio; int ret; - ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos); + ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write && vm_dirty_ratio != old_ratio) { update_completion_period(); vm_dirty_bytes = 0; @@ -195,13 +195,13 @@ int dirty_ratio_handler(struct ctl_table *table, int write, int dirty_bytes_handler(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, + void __user *buffer, size_t *lenp, loff_t *ppos) { unsigned long old_bytes = vm_dirty_bytes; int ret; - ret = proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos); + ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write && vm_dirty_bytes != old_bytes) { update_completion_period(); vm_dirty_ratio = 0; @@ -686,9 +686,9 @@ static DEFINE_TIMER(laptop_mode_wb_timer, laptop_timer_fn, 0, 0); * sysctl handler for /proc/sys/vm/dirty_writeback_centisecs */ int dirty_writeback_centisecs_handler(ctl_table *table, int write, - struct file *file, void __user *buffer, size_t *length, loff_t *ppos) + void __user *buffer, size_t *length, loff_t *ppos) { - proc_dointvec(table, write, file, buffer, length, ppos); + proc_dointvec(table, write, buffer, length, ppos); return 0; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 5717f27a070..88248b3c20b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2373,7 +2373,7 @@ early_param("numa_zonelist_order", setup_numa_zonelist_order); * sysctl handler for numa_zonelist_order */ int numa_zonelist_order_handler(ctl_table *table, int write, - struct file *file, void __user *buffer, size_t *length, + void __user *buffer, size_t *length, loff_t *ppos) { char saved_string[NUMA_ZONELIST_ORDER_LEN]; @@ -2382,7 +2382,7 @@ int numa_zonelist_order_handler(ctl_table *table, int write, if (write) strncpy(saved_string, (char*)table->data, NUMA_ZONELIST_ORDER_LEN); - ret = proc_dostring(table, write, file, buffer, length, ppos); + ret = proc_dostring(table, write, buffer, length, ppos); if (ret) return ret; if (write) { @@ -4706,9 +4706,9 @@ module_init(init_per_zone_wmark_min) * changes. */ int min_free_kbytes_sysctl_handler(ctl_table *table, int write, - struct file *file, void __user *buffer, size_t *length, loff_t *ppos) + void __user *buffer, size_t *length, loff_t *ppos) { - proc_dointvec(table, write, file, buffer, length, ppos); + proc_dointvec(table, write, buffer, length, ppos); if (write) setup_per_zone_wmarks(); return 0; @@ -4716,12 +4716,12 @@ int min_free_kbytes_sysctl_handler(ctl_table *table, int write, #ifdef CONFIG_NUMA int sysctl_min_unmapped_ratio_sysctl_handler(ctl_table *table, int write, - struct file *file, void __user *buffer, size_t *length, loff_t *ppos) + void __user *buffer, size_t *length, loff_t *ppos) { struct zone *zone; int rc; - rc = proc_dointvec_minmax(table, write, file, buffer, length, ppos); + rc = proc_dointvec_minmax(table, write, buffer, length, ppos); if (rc) return rc; @@ -4732,12 +4732,12 @@ int sysctl_min_unmapped_ratio_sysctl_handler(ctl_table *table, int write, } int sysctl_min_slab_ratio_sysctl_handler(ctl_table *table, int write, - struct file *file, void __user *buffer, size_t *length, loff_t *ppos) + void __user *buffer, size_t *length, loff_t *ppos) { struct zone *zone; int rc; - rc = proc_dointvec_minmax(table, write, file, buffer, length, ppos); + rc = proc_dointvec_minmax(table, write, buffer, length, ppos); if (rc) return rc; @@ -4758,9 +4758,9 @@ int sysctl_min_slab_ratio_sysctl_handler(ctl_table *table, int write, * if in function of the boot time zone sizes. */ int lowmem_reserve_ratio_sysctl_handler(ctl_table *table, int write, - struct file *file, void __user *buffer, size_t *length, loff_t *ppos) + void __user *buffer, size_t *length, loff_t *ppos) { - proc_dointvec_minmax(table, write, file, buffer, length, ppos); + proc_dointvec_minmax(table, write, buffer, length, ppos); setup_per_zone_lowmem_reserve(); return 0; } @@ -4772,13 +4772,13 @@ int lowmem_reserve_ratio_sysctl_handler(ctl_table *table, int write, */ int percpu_pagelist_fraction_sysctl_handler(ctl_table *table, int write, - struct file *file, void __user *buffer, size_t *length, loff_t *ppos) + void __user *buffer, size_t *length, loff_t *ppos) { struct zone *zone; unsigned int cpu; int ret; - ret = proc_dointvec_minmax(table, write, file, buffer, length, ppos); + ret = proc_dointvec_minmax(table, write, buffer, length, ppos); if (!write || (ret == -EINVAL)) return ret; for_each_populated_zone(zone) { diff --git a/mm/vmscan.c b/mm/vmscan.c index 2423782214a..f444b740908 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2844,10 +2844,10 @@ static void scan_all_zones_unevictable_pages(void) unsigned long scan_unevictable_pages; int scan_unevictable_handler(struct ctl_table *table, int write, - struct file *file, void __user *buffer, + void __user *buffer, size_t *length, loff_t *ppos) { - proc_doulongvec_minmax(table, write, file, buffer, length, ppos); + proc_doulongvec_minmax(table, write, buffer, length, ppos); if (write && *(unsigned long *)table->data) scan_all_zones_unevictable_pages(); diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index 907a82e9023..a16a2342f6b 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -965,12 +965,12 @@ static struct nf_hook_ops br_nf_ops[] __read_mostly = { #ifdef CONFIG_SYSCTL static -int brnf_sysctl_call_tables(ctl_table * ctl, int write, struct file *filp, +int brnf_sysctl_call_tables(ctl_table * ctl, int write, void __user * buffer, size_t * lenp, loff_t * ppos) { int ret; - ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos); + ret = proc_dointvec(ctl, write, buffer, lenp, ppos); if (write && *(int *)(ctl->data)) *(int *)(ctl->data) = 1; diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index 1c6a5bb6f0c..6e1f085db06 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -164,7 +164,7 @@ static int max_t3[] = { 8191 }; /* Must fit in 16 bits when multiplied by BCT3MU static int min_priority[1]; static int max_priority[] = { 127 }; /* From DECnet spec */ -static int dn_forwarding_proc(ctl_table *, int, struct file *, +static int dn_forwarding_proc(ctl_table *, int, void __user *, size_t *, loff_t *); static int dn_forwarding_sysctl(ctl_table *table, void __user *oldval, size_t __user *oldlenp, @@ -274,7 +274,6 @@ static void dn_dev_sysctl_unregister(struct dn_dev_parms *parms) } static int dn_forwarding_proc(ctl_table *table, int write, - struct file *filep, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -290,7 +289,7 @@ static int dn_forwarding_proc(ctl_table *table, int write, dn_db = dev->dn_ptr; old = dn_db->parms.forwarding; - err = proc_dointvec(table, write, filep, buffer, lenp, ppos); + err = proc_dointvec(table, write, buffer, lenp, ppos); if ((err >= 0) && write) { if (dn_db->parms.forwarding < 0) diff --git a/net/decnet/sysctl_net_decnet.c b/net/decnet/sysctl_net_decnet.c index 5bcd592ae6d..26b0ab1e9f5 100644 --- a/net/decnet/sysctl_net_decnet.c +++ b/net/decnet/sysctl_net_decnet.c @@ -165,7 +165,6 @@ static int dn_node_address_strategy(ctl_table *table, } static int dn_node_address_handler(ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -276,7 +275,6 @@ static int dn_def_dev_strategy(ctl_table *table, static int dn_def_dev_handler(ctl_table *table, int write, - struct file * filp, void __user *buffer, size_t *lenp, loff_t *ppos) { diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 07336c6201f..e92f1fd28aa 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1270,10 +1270,10 @@ static void inet_forward_change(struct net *net) } static int devinet_conf_proc(ctl_table *ctl, int write, - struct file *filp, void __user *buffer, + void __user *buffer, size_t *lenp, loff_t *ppos) { - int ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos); + int ret = proc_dointvec(ctl, write, buffer, lenp, ppos); if (write) { struct ipv4_devconf *cnf = ctl->extra1; @@ -1342,12 +1342,12 @@ static int devinet_conf_sysctl(ctl_table *table, } static int devinet_sysctl_forward(ctl_table *ctl, int write, - struct file *filp, void __user *buffer, + void __user *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; int val = *valp; - int ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos); + int ret = proc_dointvec(ctl, write, buffer, lenp, ppos); if (write && *valp != val) { struct net *net = ctl->extra2; @@ -1372,12 +1372,12 @@ static int devinet_sysctl_forward(ctl_table *ctl, int write, } int ipv4_doint_and_flush(ctl_table *ctl, int write, - struct file *filp, void __user *buffer, + void __user *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; int val = *valp; - int ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos); + int ret = proc_dointvec(ctl, write, buffer, lenp, ppos); struct net *net = ctl->extra2; if (write && *valp != val) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index df934731453..bb419925202 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -3036,7 +3036,7 @@ void ip_rt_multicast_event(struct in_device *in_dev) #ifdef CONFIG_SYSCTL static int ipv4_sysctl_rtcache_flush(ctl_table *__ctl, int write, - struct file *filp, void __user *buffer, + void __user *buffer, size_t *lenp, loff_t *ppos) { if (write) { @@ -3046,7 +3046,7 @@ static int ipv4_sysctl_rtcache_flush(ctl_table *__ctl, int write, memcpy(&ctl, __ctl, sizeof(ctl)); ctl.data = &flush_delay; - proc_dointvec(&ctl, write, filp, buffer, lenp, ppos); + proc_dointvec(&ctl, write, buffer, lenp, ppos); net = (struct net *)__ctl->extra1; rt_cache_flush(net, flush_delay); @@ -3106,12 +3106,11 @@ static void rt_secret_reschedule(int old) } static int ipv4_sysctl_rt_secret_interval(ctl_table *ctl, int write, - struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos) { int old = ip_rt_secret_interval; - int ret = proc_dointvec_jiffies(ctl, write, filp, buffer, lenp, ppos); + int ret = proc_dointvec_jiffies(ctl, write, buffer, lenp, ppos); rt_secret_reschedule(old); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 4710d219f06..2dcf04d9b00 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -36,7 +36,7 @@ static void set_local_port_range(int range[2]) } /* Validate changes from /proc interface. */ -static int ipv4_local_port_range(ctl_table *table, int write, struct file *filp, +static int ipv4_local_port_range(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -51,7 +51,7 @@ static int ipv4_local_port_range(ctl_table *table, int write, struct file *filp, }; inet_get_local_port_range(range, range + 1); - ret = proc_dointvec_minmax(&tmp, write, filp, buffer, lenp, ppos); + ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); if (write && ret == 0) { if (range[1] < range[0]) @@ -91,7 +91,7 @@ static int ipv4_sysctl_local_port_range(ctl_table *table, } -static int proc_tcp_congestion_control(ctl_table *ctl, int write, struct file * filp, +static int proc_tcp_congestion_control(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { char val[TCP_CA_NAME_MAX]; @@ -103,7 +103,7 @@ static int proc_tcp_congestion_control(ctl_table *ctl, int write, struct file * tcp_get_default_congestion_control(val); - ret = proc_dostring(&tbl, write, filp, buffer, lenp, ppos); + ret = proc_dostring(&tbl, write, buffer, lenp, ppos); if (write && ret == 0) ret = tcp_set_default_congestion_control(val); return ret; @@ -129,7 +129,7 @@ static int sysctl_tcp_congestion_control(ctl_table *table, } static int proc_tcp_available_congestion_control(ctl_table *ctl, - int write, struct file * filp, + int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -140,13 +140,13 @@ static int proc_tcp_available_congestion_control(ctl_table *ctl, if (!tbl.data) return -ENOMEM; tcp_get_available_congestion_control(tbl.data, TCP_CA_BUF_MAX); - ret = proc_dostring(&tbl, write, filp, buffer, lenp, ppos); + ret = proc_dostring(&tbl, write, buffer, lenp, ppos); kfree(tbl.data); return ret; } static int proc_allowed_congestion_control(ctl_table *ctl, - int write, struct file * filp, + int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -158,7 +158,7 @@ static int proc_allowed_congestion_control(ctl_table *ctl, return -ENOMEM; tcp_get_allowed_congestion_control(tbl.data, tbl.maxlen); - ret = proc_dostring(&tbl, write, filp, buffer, lenp, ppos); + ret = proc_dostring(&tbl, write, buffer, lenp, ppos); if (write && ret == 0) ret = tcp_set_allowed_congestion_control(tbl.data); kfree(tbl.data); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 55f486d89c8..1fd0a3d775d 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3986,14 +3986,14 @@ static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) #ifdef CONFIG_SYSCTL static -int addrconf_sysctl_forward(ctl_table *ctl, int write, struct file * filp, +int addrconf_sysctl_forward(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; int val = *valp; int ret; - ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos); + ret = proc_dointvec(ctl, write, buffer, lenp, ppos); if (write) ret = addrconf_fixup_forwarding(ctl, valp, val); @@ -4090,14 +4090,14 @@ static int addrconf_disable_ipv6(struct ctl_table *table, int *p, int old) } static -int addrconf_sysctl_disable(ctl_table *ctl, int write, struct file * filp, +int addrconf_sysctl_disable(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; int val = *valp; int ret; - ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos); + ret = proc_dointvec(ctl, write, buffer, lenp, ppos); if (write) ret = addrconf_disable_ipv6(ctl, valp, val); diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 7015478797f..498b9b0b0fa 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1735,7 +1735,7 @@ static void ndisc_warn_deprecated_sysctl(struct ctl_table *ctl, } } -int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write, struct file * filp, void __user *buffer, size_t *lenp, loff_t *ppos) +int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { struct net_device *dev = ctl->extra1; struct inet6_dev *idev; @@ -1746,16 +1746,16 @@ int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write, struct file * f ndisc_warn_deprecated_sysctl(ctl, "syscall", dev ? dev->name : "default"); if (strcmp(ctl->procname, "retrans_time") == 0) - ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos); + ret = proc_dointvec(ctl, write, buffer, lenp, ppos); else if (strcmp(ctl->procname, "base_reachable_time") == 0) ret = proc_dointvec_jiffies(ctl, write, - filp, buffer, lenp, ppos); + buffer, lenp, ppos); else if ((strcmp(ctl->procname, "retrans_time_ms") == 0) || (strcmp(ctl->procname, "base_reachable_time_ms") == 0)) ret = proc_dointvec_ms_jiffies(ctl, write, - filp, buffer, lenp, ppos); + buffer, lenp, ppos); else ret = -1; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 77aecbe8ff6..d6fe7646a8f 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2524,13 +2524,13 @@ static const struct file_operations rt6_stats_seq_fops = { #ifdef CONFIG_SYSCTL static -int ipv6_sysctl_rtcache_flush(ctl_table *ctl, int write, struct file * filp, +int ipv6_sysctl_rtcache_flush(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { struct net *net = current->nsproxy->net_ns; int delay = net->ipv6.sysctl.flush_delay; if (write) { - proc_dointvec(ctl, write, filp, buffer, lenp, ppos); + proc_dointvec(ctl, write, buffer, lenp, ppos); fib6_run_gc(delay <= 0 ? ~0UL : (unsigned long)delay, net); return 0; } else diff --git a/net/irda/irsysctl.c b/net/irda/irsysctl.c index 57f8817c397..5c86567e5a7 100644 --- a/net/irda/irsysctl.c +++ b/net/irda/irsysctl.c @@ -73,12 +73,12 @@ static int min_lap_keepalive_time = 100; /* 100us */ /* For other sysctl, I've no idea of the range. Maybe Dag could help * us on that - Jean II */ -static int do_devname(ctl_table *table, int write, struct file *filp, +static int do_devname(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int ret; - ret = proc_dostring(table, write, filp, buffer, lenp, ppos); + ret = proc_dostring(table, write, buffer, lenp, ppos); if (ret == 0 && write) { struct ias_value *val; @@ -90,12 +90,12 @@ static int do_devname(ctl_table *table, int write, struct file *filp, } -static int do_discovery(ctl_table *table, int write, struct file *filp, +static int do_discovery(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int ret; - ret = proc_dointvec(table, write, filp, buffer, lenp, ppos); + ret = proc_dointvec(table, write, buffer, lenp, ppos); if (ret) return ret; diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index fba2892b99e..446e9bd4b4b 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -1496,14 +1496,14 @@ static int ip_vs_zero_all(void) static int -proc_do_defense_mode(ctl_table *table, int write, struct file * filp, +proc_do_defense_mode(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int *valp = table->data; int val = *valp; int rc; - rc = proc_dointvec(table, write, filp, buffer, lenp, ppos); + rc = proc_dointvec(table, write, buffer, lenp, ppos); if (write && (*valp != val)) { if ((*valp < 0) || (*valp > 3)) { /* Restore the correct value */ @@ -1517,7 +1517,7 @@ proc_do_defense_mode(ctl_table *table, int write, struct file * filp, static int -proc_do_sync_threshold(ctl_table *table, int write, struct file *filp, +proc_do_sync_threshold(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int *valp = table->data; @@ -1527,7 +1527,7 @@ proc_do_sync_threshold(ctl_table *table, int write, struct file *filp, /* backup the value first */ memcpy(val, valp, sizeof(val)); - rc = proc_dointvec(table, write, filp, buffer, lenp, ppos); + rc = proc_dointvec(table, write, buffer, lenp, ppos); if (write && (valp[0] < 0 || valp[1] < 0 || valp[0] >= valp[1])) { /* Restore the correct value */ memcpy(valp, val, sizeof(val)); diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index 4e620305f28..c93494fef8e 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -226,7 +226,7 @@ static char nf_log_sysctl_fnames[NFPROTO_NUMPROTO-NFPROTO_UNSPEC][3]; static struct ctl_table nf_log_sysctl_table[NFPROTO_NUMPROTO+1]; static struct ctl_table_header *nf_log_dir_header; -static int nf_log_proc_dostring(ctl_table *table, int write, struct file *filp, +static int nf_log_proc_dostring(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { const struct nf_logger *logger; @@ -260,7 +260,7 @@ static int nf_log_proc_dostring(ctl_table *table, int write, struct file *filp, table->data = "NONE"; else table->data = logger->name; - r = proc_dostring(table, write, filp, buffer, lenp, ppos); + r = proc_dostring(table, write, buffer, lenp, ppos); mutex_unlock(&nf_log_mutex); } diff --git a/net/phonet/sysctl.c b/net/phonet/sysctl.c index 7b5749ee276..2220f332232 100644 --- a/net/phonet/sysctl.c +++ b/net/phonet/sysctl.c @@ -56,7 +56,7 @@ void phonet_get_local_port_range(int *min, int *max) } while (read_seqretry(&local_port_range_lock, seq)); } -static int proc_local_port_range(ctl_table *table, int write, struct file *filp, +static int proc_local_port_range(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -70,7 +70,7 @@ static int proc_local_port_range(ctl_table *table, int write, struct file *filp, .extra2 = &local_port_range_max, }; - ret = proc_dointvec_minmax(&tmp, write, filp, buffer, lenp, ppos); + ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); if (write && ret == 0) { if (range[1] < range[0]) diff --git a/net/sunrpc/sysctl.c b/net/sunrpc/sysctl.c index 5231f7aaac0..42f9748ae09 100644 --- a/net/sunrpc/sysctl.c +++ b/net/sunrpc/sysctl.c @@ -56,7 +56,7 @@ rpc_unregister_sysctl(void) } } -static int proc_do_xprt(ctl_table *table, int write, struct file *file, +static int proc_do_xprt(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { char tmpbuf[256]; @@ -71,7 +71,7 @@ static int proc_do_xprt(ctl_table *table, int write, struct file *file, } static int -proc_dodebug(ctl_table *table, int write, struct file *file, +proc_dodebug(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { char tmpbuf[20], c, *s; diff --git a/net/sunrpc/xprtrdma/svc_rdma.c b/net/sunrpc/xprtrdma/svc_rdma.c index 87101177825..35fb68b9c8e 100644 --- a/net/sunrpc/xprtrdma/svc_rdma.c +++ b/net/sunrpc/xprtrdma/svc_rdma.c @@ -80,7 +80,7 @@ struct kmem_cache *svc_rdma_ctxt_cachep; * current value. */ static int read_reset_stat(ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, + void __user *buffer, size_t *lenp, loff_t *ppos) { atomic_t *stat = (atomic_t *)table->data; diff --git a/security/min_addr.c b/security/min_addr.c index 14cc7b3b8d0..c844eed7915 100644 --- a/security/min_addr.c +++ b/security/min_addr.c @@ -28,12 +28,12 @@ static void update_mmap_min_addr(void) * sysctl handler which just sets dac_mmap_min_addr = the new value and then * calls update_mmap_min_addr() so non MAP_FIXED hints get rounded properly */ -int mmap_min_addr_handler(struct ctl_table *table, int write, struct file *filp, +int mmap_min_addr_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int ret; - ret = proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos); + ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos); update_mmap_min_addr(); -- cgit v1.2.3 From c44972f1782124f945ec8bea8a78f30f1a3538bd Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Thu, 24 Sep 2009 14:47:43 -0700 Subject: procfs: disable per-task stack usage on NOMMU It needs walk_page_range(). Reported-by: Michal Simek Tested-by: Michal Simek Cc: Stefani Seibold Cc: David Howells Cc: Paul Mundt Cc: Geert Uytterhoeven Cc: Greg Ungerer Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/array.c | 7 +++++++ mm/Makefile | 4 ++-- 2 files changed, 9 insertions(+), 2 deletions(-) (limited to 'fs/proc') diff --git a/fs/proc/array.c b/fs/proc/array.c index 0c6bc602e6c..07f77a7945c 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -322,6 +322,8 @@ static inline void task_context_switch_counts(struct seq_file *m, p->nivcsw); } +#ifdef CONFIG_MMU + struct stack_stats { struct vm_area_struct *vma; unsigned long startpage; @@ -402,6 +404,11 @@ static inline void task_show_stack_usage(struct seq_file *m, mmput(mm); } } +#else +static void task_show_stack_usage(struct seq_file *m, struct task_struct *task) +{ +} +#endif /* CONFIG_MMU */ int proc_pid_status(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) diff --git a/mm/Makefile b/mm/Makefile index 515fd793c17..ebf849042ed 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -5,14 +5,14 @@ mmu-y := nommu.o mmu-$(CONFIG_MMU) := fremap.o highmem.o madvise.o memory.o mincore.o \ mlock.o mmap.o mprotect.o mremap.o msync.o rmap.o \ - vmalloc.o + vmalloc.o pagewalk.o obj-y := bootmem.o filemap.o mempool.o oom_kill.o fadvise.o \ maccess.o page_alloc.o page-writeback.o \ readahead.o swap.o truncate.o vmscan.o shmem.o \ prio_tree.o util.o mmzone.o vmstat.o backing-dev.o \ page_isolation.o mm_init.o mmu_context.o \ - pagewalk.o $(mmu-y) + $(mmu-y) obj-y += init-mm.o obj-$(CONFIG_BOUNCE) += bounce.o -- cgit v1.2.3 From 4055e97318809638a57fbe1746b93bc7a90ef0d3 Mon Sep 17 00:00:00 2001 From: Jaswinder Singh Rajput Date: Wed, 7 Oct 2009 16:32:24 -0700 Subject: fs: includecheck fix: proc, kcore.c fix the following 'make includecheck' warning: fs/proc/kcore.c: linux/mm.h is included more than once. Signed-off-by: Jaswinder Singh Rajput Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/kcore.c | 1 - 1 file changed, 1 deletion(-) (limited to 'fs/proc') diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index 56013371f9f..a44a7897fd4 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -23,7 +23,6 @@ #include #include #include -#include #include #include -- cgit v1.2.3 From 253fb02d62571e5455eedc9e39b9d660e86a40f0 Mon Sep 17 00:00:00 2001 From: Wu Fengguang Date: Wed, 7 Oct 2009 16:32:27 -0700 Subject: pagemap: export KPF_HWPOISON This flag indicates a hardware detected memory corruption on the page. Any future access of the page data may bring down the machine. Signed-off-by: Wu Fengguang Cc: Andi Kleen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/vm/page-types.c | 2 ++ Documentation/vm/pagemap.txt | 4 ++++ fs/proc/page.c | 5 +++++ 3 files changed, 11 insertions(+) (limited to 'fs/proc') diff --git a/Documentation/vm/page-types.c b/Documentation/vm/page-types.c index fa1a30d9e9d..87f57228f56 100644 --- a/Documentation/vm/page-types.c +++ b/Documentation/vm/page-types.c @@ -69,6 +69,7 @@ #define KPF_COMPOUND_TAIL 16 #define KPF_HUGE 17 #define KPF_UNEVICTABLE 18 +#define KPF_HWPOISON 19 #define KPF_NOPAGE 20 /* [32-] kernel hacking assistances */ @@ -116,6 +117,7 @@ static char *page_flag_names[] = { [KPF_COMPOUND_TAIL] = "T:compound_tail", [KPF_HUGE] = "G:huge", [KPF_UNEVICTABLE] = "u:unevictable", + [KPF_HWPOISON] = "X:hwpoison", [KPF_NOPAGE] = "n:nopage", [KPF_RESERVED] = "r:reserved", diff --git a/Documentation/vm/pagemap.txt b/Documentation/vm/pagemap.txt index 600a304a828..2fdd84a1910 100644 --- a/Documentation/vm/pagemap.txt +++ b/Documentation/vm/pagemap.txt @@ -57,6 +57,7 @@ There are three components to pagemap: 16. COMPOUND_TAIL 16. HUGE 18. UNEVICTABLE + 19. HWPOISON 20. NOPAGE Short descriptions to the page flags: @@ -86,6 +87,9 @@ Short descriptions to the page flags: 17. HUGE this is an integral part of a HugeTLB page +19. HWPOISON + hardware detected memory corruption on this page: don't touch the data! + 20. NOPAGE no page frame exists at the requested address diff --git a/fs/proc/page.c b/fs/proc/page.c index 2281c2cbfe2..5033ce0d254 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -94,6 +94,7 @@ static const struct file_operations proc_kpagecount_operations = { #define KPF_COMPOUND_TAIL 16 #define KPF_HUGE 17 #define KPF_UNEVICTABLE 18 +#define KPF_HWPOISON 19 #define KPF_NOPAGE 20 #define KPF_KSM 21 @@ -180,6 +181,10 @@ static u64 get_uflags(struct page *page) u |= kpf_copy_bit(k, KPF_UNEVICTABLE, PG_unevictable); u |= kpf_copy_bit(k, KPF_MLOCKED, PG_mlocked); +#ifdef CONFIG_MEMORY_FAILURE + u |= kpf_copy_bit(k, KPF_HWPOISON, PG_hwpoison); +#endif + #ifdef CONFIG_IA64_UNCACHED_ALLOCATOR u |= kpf_copy_bit(k, KPF_UNCACHED, PG_uncached); #endif -- cgit v1.2.3