From 788c7df451467df71638dd79a2d63d78c6e13b9c Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Tue, 23 Jun 2009 13:49:05 +0100 Subject: hugetlb: fault flags instead of write_access handle_mm_fault() is now passing fault flags rather than write_access down to hugetlb_fault(), so better recognize that in hugetlb_fault(), and in hugetlb_no_page(). Signed-off-by: Hugh Dickins Acked-by: Wu Fengguang Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux/hugetlb.h') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index a05a5ef33391..2723513a5651 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -33,7 +33,7 @@ void hugetlb_report_meminfo(struct seq_file *); int hugetlb_report_node_meminfo(int, char *); unsigned long hugetlb_total_pages(void); int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, int write_access); + unsigned long address, unsigned int flags); int hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_struct *vma, int acctflags); @@ -98,7 +98,7 @@ static inline void hugetlb_report_meminfo(struct seq_file *m) #define pud_huge(x) 0 #define is_hugepage_only_range(mm, addr, len) 0 #define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) ({BUG(); 0; }) -#define hugetlb_fault(mm, vma, addr, write) ({ BUG(); 0; }) +#define hugetlb_fault(mm, vma, addr, flags) ({ BUG(); 0; }) #define hugetlb_change_protection(vma, address, end, newprot) -- cgit v1.2.3 From 353d5c30c666580347515da609dd74a2b8e9b828 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Mon, 24 Aug 2009 16:30:28 +0100 Subject: mm: fix hugetlb bug due to user_shm_unlock call 2.6.30's commit 8a0bdec194c21c8fdef840989d0d7b742bb5d4bc removed user_shm_lock() calls in hugetlb_file_setup() but left the user_shm_unlock call in shm_destroy(). In detail: Assume that can_do_hugetlb_shm() returns true and hence user_shm_lock() is not called in hugetlb_file_setup(). However, user_shm_unlock() is called in any case in shm_destroy() and in the following atomic_dec_and_lock(&up->__count) in free_uid() is executed and if up->__count gets zero, also cleanup_user_struct() is scheduled. Note that sched_destroy_user() is empty if CONFIG_USER_SCHED is not set. However, the ref counter up->__count gets unexpectedly non-positive and the corresponding structs are freed even though there are live references to them, resulting in a kernel oops after a lots of shmget(SHM_HUGETLB)/shmctl(IPC_RMID) cycles and CONFIG_USER_SCHED set. Hugh changed Stefan's suggested patch: can_do_hugetlb_shm() at the time of shm_destroy() may give a different answer from at the time of hugetlb_file_setup(). And fixed newseg()'s no_id error path, which has missed user_shm_unlock() ever since it came in 2.6.9. Reported-by: Stefan Huber Signed-off-by: Hugh Dickins Tested-by: Stefan Huber Cc: stable@kernel.org Signed-off-by: Linus Torvalds --- fs/hugetlbfs/inode.c | 20 ++++++++++++-------- include/linux/hugetlb.h | 6 ++++-- ipc/shm.c | 8 +++++--- 3 files changed, 21 insertions(+), 13 deletions(-) (limited to 'include/linux/hugetlb.h') diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 941c8425c10b..cb88dac8ccaa 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -935,26 +935,28 @@ static int can_do_hugetlb_shm(void) return capable(CAP_IPC_LOCK) || in_group_p(sysctl_hugetlb_shm_group); } -struct file *hugetlb_file_setup(const char *name, size_t size, int acctflag) +struct file *hugetlb_file_setup(const char *name, size_t size, int acctflag, + struct user_struct **user) { int error = -ENOMEM; - int unlock_shm = 0; struct file *file; struct inode *inode; struct dentry *dentry, *root; struct qstr quick_string; - struct user_struct *user = current_user(); + *user = NULL; if (!hugetlbfs_vfsmount) return ERR_PTR(-ENOENT); if (!can_do_hugetlb_shm()) { - if (user_shm_lock(size, user)) { - unlock_shm = 1; + *user = current_user(); + if (user_shm_lock(size, *user)) { WARN_ONCE(1, "Using mlock ulimits for SHM_HUGETLB deprecated\n"); - } else + } else { + *user = NULL; return ERR_PTR(-EPERM); + } } root = hugetlbfs_vfsmount->mnt_root; @@ -996,8 +998,10 @@ out_inode: out_dentry: dput(dentry); out_shm_unlock: - if (unlock_shm) - user_shm_unlock(size, user); + if (*user) { + user_shm_unlock(size, *user); + *user = NULL; + } return ERR_PTR(error); } diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 2723513a5651..5cbc620bdfe0 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -10,6 +10,7 @@ #include struct ctl_table; +struct user_struct; int PageHuge(struct page *page); @@ -146,7 +147,8 @@ static inline struct hugetlbfs_sb_info *HUGETLBFS_SB(struct super_block *sb) extern const struct file_operations hugetlbfs_file_operations; extern struct vm_operations_struct hugetlb_vm_ops; -struct file *hugetlb_file_setup(const char *name, size_t, int); +struct file *hugetlb_file_setup(const char *name, size_t size, int acct, + struct user_struct **user); int hugetlb_get_quota(struct address_space *mapping, long delta); void hugetlb_put_quota(struct address_space *mapping, long delta); @@ -168,7 +170,7 @@ static inline void set_file_hugepages(struct file *file) #define is_file_hugepages(file) 0 #define set_file_hugepages(file) BUG() -#define hugetlb_file_setup(name,size,acctflag) ERR_PTR(-ENOSYS) +#define hugetlb_file_setup(name,size,acct,user) ERR_PTR(-ENOSYS) #endif /* !CONFIG_HUGETLBFS */ diff --git a/ipc/shm.c b/ipc/shm.c index 15dd238e5338..1bc4701ef4f0 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -174,7 +174,7 @@ static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp) shm_unlock(shp); if (!is_file_hugepages(shp->shm_file)) shmem_lock(shp->shm_file, 0, shp->mlock_user); - else + else if (shp->mlock_user) user_shm_unlock(shp->shm_file->f_path.dentry->d_inode->i_size, shp->mlock_user); fput (shp->shm_file); @@ -369,8 +369,8 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) /* hugetlb_file_setup applies strict accounting */ if (shmflg & SHM_NORESERVE) acctflag = VM_NORESERVE; - file = hugetlb_file_setup(name, size, acctflag); - shp->mlock_user = current_user(); + file = hugetlb_file_setup(name, size, acctflag, + &shp->mlock_user); } else { /* * Do not allow no accounting for OVERCOMMIT_NEVER, even @@ -410,6 +410,8 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) return error; no_id: + if (shp->mlock_user) /* shmflg & SHM_HUGETLB case */ + user_shm_unlock(size, shp->mlock_user); fput(file); no_file: security_shm_free(shp); -- cgit v1.2.3 From e8c5c8249878fb6564125680a1d15e06adbd5639 Mon Sep 17 00:00:00 2001 From: Lee Schermerhorn Date: Mon, 21 Sep 2009 17:01:22 -0700 Subject: hugetlb: balance freeing of huge pages across nodes Free huges pages from nodes in round robin fashion in an attempt to keep [persistent a.k.a static] hugepages balanced across nodes New function free_pool_huge_page() is modeled on and performs roughly the inverse of alloc_fresh_huge_page(). Replaces dequeue_huge_page() which now has no callers, so this patch removes it. Helper function hstate_next_node_to_free() uses new hstate member next_to_free_nid to distribute "frees" across all nodes with huge pages. Acked-by: David Rientjes Signed-off-by: Lee Schermerhorn Acked-by: Mel Gorman Cc: Nishanth Aravamudan Cc: Adam Litke Cc: Andy Whitcroft Cc: Eric Whitney Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 3 +- mm/hugetlb.c | 132 +++++++++++++++++++++++++++++++----------------- 2 files changed, 88 insertions(+), 47 deletions(-) (limited to 'include/linux/hugetlb.h') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 5cbc620bdfe0..16cdb75a543a 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -185,7 +185,8 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, #define HSTATE_NAME_LEN 32 /* Defines one hugetlb page size */ struct hstate { - int hugetlb_next_nid; + int next_nid_to_alloc; + int next_nid_to_free; unsigned int order; unsigned long mask; unsigned long max_huge_pages; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index b16d63634777..38dab5586827 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -456,24 +456,6 @@ static void enqueue_huge_page(struct hstate *h, struct page *page) h->free_huge_pages_node[nid]++; } -static struct page *dequeue_huge_page(struct hstate *h) -{ - int nid; - struct page *page = NULL; - - for (nid = 0; nid < MAX_NUMNODES; ++nid) { - if (!list_empty(&h->hugepage_freelists[nid])) { - page = list_entry(h->hugepage_freelists[nid].next, - struct page, lru); - list_del(&page->lru); - h->free_huge_pages--; - h->free_huge_pages_node[nid]--; - break; - } - } - return page; -} - static struct page *dequeue_huge_page_vma(struct hstate *h, struct vm_area_struct *vma, unsigned long address, int avoid_reserve) @@ -641,7 +623,7 @@ static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid) /* * Use a helper variable to find the next node and then - * copy it back to hugetlb_next_nid afterwards: + * copy it back to next_nid_to_alloc afterwards: * otherwise there's a window in which a racer might * pass invalid nid MAX_NUMNODES to alloc_pages_exact_node. * But we don't need to use a spin_lock here: it really @@ -650,13 +632,13 @@ static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid) * if we just successfully allocated a hugepage so that * the next caller gets hugepages on the next node. */ -static int hstate_next_node(struct hstate *h) +static int hstate_next_node_to_alloc(struct hstate *h) { int next_nid; - next_nid = next_node(h->hugetlb_next_nid, node_online_map); + next_nid = next_node(h->next_nid_to_alloc, node_online_map); if (next_nid == MAX_NUMNODES) next_nid = first_node(node_online_map); - h->hugetlb_next_nid = next_nid; + h->next_nid_to_alloc = next_nid; return next_nid; } @@ -667,14 +649,15 @@ static int alloc_fresh_huge_page(struct hstate *h) int next_nid; int ret = 0; - start_nid = h->hugetlb_next_nid; + start_nid = h->next_nid_to_alloc; + next_nid = start_nid; do { - page = alloc_fresh_huge_page_node(h, h->hugetlb_next_nid); + page = alloc_fresh_huge_page_node(h, next_nid); if (page) ret = 1; - next_nid = hstate_next_node(h); - } while (!page && h->hugetlb_next_nid != start_nid); + next_nid = hstate_next_node_to_alloc(h); + } while (!page && next_nid != start_nid); if (ret) count_vm_event(HTLB_BUDDY_PGALLOC); @@ -684,6 +667,52 @@ static int alloc_fresh_huge_page(struct hstate *h) return ret; } +/* + * helper for free_pool_huge_page() - find next node + * from which to free a huge page + */ +static int hstate_next_node_to_free(struct hstate *h) +{ + int next_nid; + next_nid = next_node(h->next_nid_to_free, node_online_map); + if (next_nid == MAX_NUMNODES) + next_nid = first_node(node_online_map); + h->next_nid_to_free = next_nid; + return next_nid; +} + +/* + * Free huge page from pool from next node to free. + * Attempt to keep persistent huge pages more or less + * balanced over allowed nodes. + * Called with hugetlb_lock locked. + */ +static int free_pool_huge_page(struct hstate *h) +{ + int start_nid; + int next_nid; + int ret = 0; + + start_nid = h->next_nid_to_free; + next_nid = start_nid; + + do { + if (!list_empty(&h->hugepage_freelists[next_nid])) { + struct page *page = + list_entry(h->hugepage_freelists[next_nid].next, + struct page, lru); + list_del(&page->lru); + h->free_huge_pages--; + h->free_huge_pages_node[next_nid]--; + update_and_free_page(h, page); + ret = 1; + } + next_nid = hstate_next_node_to_free(h); + } while (!ret && next_nid != start_nid); + + return ret; +} + static struct page *alloc_buddy_huge_page(struct hstate *h, struct vm_area_struct *vma, unsigned long address) { @@ -1008,7 +1037,7 @@ int __weak alloc_bootmem_huge_page(struct hstate *h) void *addr; addr = __alloc_bootmem_node_nopanic( - NODE_DATA(h->hugetlb_next_nid), + NODE_DATA(h->next_nid_to_alloc), huge_page_size(h), huge_page_size(h), 0); if (addr) { @@ -1020,7 +1049,7 @@ int __weak alloc_bootmem_huge_page(struct hstate *h) m = addr; goto found; } - hstate_next_node(h); + hstate_next_node_to_alloc(h); nr_nodes--; } return 0; @@ -1141,31 +1170,43 @@ static inline void try_to_free_low(struct hstate *h, unsigned long count) */ static int adjust_pool_surplus(struct hstate *h, int delta) { - static int prev_nid; - int nid = prev_nid; + int start_nid, next_nid; int ret = 0; VM_BUG_ON(delta != -1 && delta != 1); - do { - nid = next_node(nid, node_online_map); - if (nid == MAX_NUMNODES) - nid = first_node(node_online_map); - /* To shrink on this node, there must be a surplus page */ - if (delta < 0 && !h->surplus_huge_pages_node[nid]) - continue; - /* Surplus cannot exceed the total number of pages */ - if (delta > 0 && h->surplus_huge_pages_node[nid] >= + if (delta < 0) + start_nid = h->next_nid_to_alloc; + else + start_nid = h->next_nid_to_free; + next_nid = start_nid; + + do { + int nid = next_nid; + if (delta < 0) { + next_nid = hstate_next_node_to_alloc(h); + /* + * To shrink on this node, there must be a surplus page + */ + if (!h->surplus_huge_pages_node[nid]) + continue; + } + if (delta > 0) { + next_nid = hstate_next_node_to_free(h); + /* + * Surplus cannot exceed the total number of pages + */ + if (h->surplus_huge_pages_node[nid] >= h->nr_huge_pages_node[nid]) - continue; + continue; + } h->surplus_huge_pages += delta; h->surplus_huge_pages_node[nid] += delta; ret = 1; break; - } while (nid != prev_nid); + } while (next_nid != start_nid); - prev_nid = nid; return ret; } @@ -1227,10 +1268,8 @@ static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count) min_count = max(count, min_count); try_to_free_low(h, min_count); while (min_count < persistent_huge_pages(h)) { - struct page *page = dequeue_huge_page(h); - if (!page) + if (!free_pool_huge_page(h)) break; - update_and_free_page(h, page); } while (count < persistent_huge_pages(h)) { if (!adjust_pool_surplus(h, 1)) @@ -1442,7 +1481,8 @@ void __init hugetlb_add_hstate(unsigned order) h->free_huge_pages = 0; for (i = 0; i < MAX_NUMNODES; ++i) INIT_LIST_HEAD(&h->hugepage_freelists[i]); - h->hugetlb_next_nid = first_node(node_online_map); + h->next_nid_to_alloc = first_node(node_online_map); + h->next_nid_to_free = first_node(node_online_map); snprintf(h->name, HSTATE_NAME_LEN, "hugepages-%lukB", huge_page_size(h)/1024); -- cgit v1.2.3 From 2a15efc953b26ad57d7d38b9e6782d57e53b4ab2 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Mon, 21 Sep 2009 17:03:27 -0700 Subject: mm: follow_hugetlb_page flags follow_hugetlb_page() shouldn't be guessing about the coredump case either: pass the foll_flags down to it, instead of just the write bit. Remove that obscure huge_zeropage_ok() test. The decision is easy, though unlike the non-huge case - here vm_ops->fault is always set. But we know that a fault would serve up zeroes, unless there's already a hugetlbfs pagecache page to back the range. (Alternatively, since hugetlb pages aren't swapped out under pressure, you could save more dump space by arguing that a page not yet faulted into this process cannot be relevant to the dump; but that would be more surprising.) Signed-off-by: Hugh Dickins Acked-by: Rik van Riel Cc: KAMEZAWA Hiroyuki Cc: KOSAKI Motohiro Cc: Nick Piggin Cc: Mel Gorman Cc: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 4 +++- mm/hugetlb.c | 62 +++++++++++++++++++++++++++++-------------------- mm/memory.c | 14 ++++++----- 3 files changed, 48 insertions(+), 32 deletions(-) (limited to 'include/linux/hugetlb.h') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 16cdb75a543a..e7f0fabfa1c2 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -24,7 +24,9 @@ int hugetlb_sysctl_handler(struct ctl_table *, int, struct file *, void __user * 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 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 **, unsigned long *, int *, int, int); +int follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *, + struct page **, struct vm_area_struct **, + unsigned long *, int *, int, unsigned int flags); void unmap_hugepage_range(struct vm_area_struct *, unsigned long, unsigned long, struct page *); void __unmap_hugepage_range(struct vm_area_struct *, diff --git a/mm/hugetlb.c b/mm/hugetlb.c index c001f846f17d..6b41f70bbc7f 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2016,6 +2016,23 @@ static struct page *hugetlbfs_pagecache_page(struct hstate *h, return find_lock_page(mapping, idx); } +/* Return whether there is a pagecache page to back given address within VMA */ +static bool hugetlbfs_backed(struct hstate *h, + struct vm_area_struct *vma, unsigned long address) +{ + struct address_space *mapping; + pgoff_t idx; + struct page *page; + + mapping = vma->vm_file->f_mapping; + idx = vma_hugecache_offset(h, vma, address); + + page = find_get_page(mapping, idx); + if (page) + put_page(page); + return page != NULL; +} + static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pte_t *ptep, unsigned int flags) { @@ -2211,54 +2228,52 @@ follow_huge_pud(struct mm_struct *mm, unsigned long address, return NULL; } -static int huge_zeropage_ok(pte_t *ptep, int write, int shared) -{ - if (!ptep || write || shared) - return 0; - else - return huge_pte_none(huge_ptep_get(ptep)); -} - int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, struct page **pages, struct vm_area_struct **vmas, unsigned long *position, int *length, int i, - int write) + unsigned int flags) { unsigned long pfn_offset; unsigned long vaddr = *position; int remainder = *length; struct hstate *h = hstate_vma(vma); - int zeropage_ok = 0; - int shared = vma->vm_flags & VM_SHARED; spin_lock(&mm->page_table_lock); while (vaddr < vma->vm_end && remainder) { pte_t *pte; + int absent; struct page *page; /* * Some archs (sparc64, sh*) have multiple pte_ts to - * each hugepage. We have to make * sure we get the + * each hugepage. We have to make sure we get the * first, for the page indexing below to work. */ pte = huge_pte_offset(mm, vaddr & huge_page_mask(h)); - if (huge_zeropage_ok(pte, write, shared)) - zeropage_ok = 1; + absent = !pte || huge_pte_none(huge_ptep_get(pte)); + + /* + * When coredumping, it suits get_dump_page if we just return + * an error if there's a hole and no huge pagecache to back it. + */ + if (absent && + ((flags & FOLL_DUMP) && !hugetlbfs_backed(h, vma, vaddr))) { + remainder = 0; + break; + } - if (!pte || - (huge_pte_none(huge_ptep_get(pte)) && !zeropage_ok) || - (write && !pte_write(huge_ptep_get(pte)))) { + if (absent || + ((flags & FOLL_WRITE) && !pte_write(huge_ptep_get(pte)))) { int ret; spin_unlock(&mm->page_table_lock); - ret = hugetlb_fault(mm, vma, vaddr, write); + ret = hugetlb_fault(mm, vma, vaddr, + (flags & FOLL_WRITE) ? FAULT_FLAG_WRITE : 0); spin_lock(&mm->page_table_lock); if (!(ret & VM_FAULT_ERROR)) continue; remainder = 0; - if (!i) - i = -EFAULT; break; } @@ -2266,10 +2281,7 @@ int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, page = pte_page(huge_ptep_get(pte)); same_page: if (pages) { - if (zeropage_ok) - pages[i] = ZERO_PAGE(0); - else - pages[i] = mem_map_offset(page, pfn_offset); + pages[i] = mem_map_offset(page, pfn_offset); get_page(pages[i]); } @@ -2293,7 +2305,7 @@ same_page: *length = remainder; *position = vaddr; - return i; + return i ? i : -EFAULT; } void hugetlb_change_protection(struct vm_area_struct *vma, diff --git a/mm/memory.c b/mm/memory.c index 532a55bce6a4..6359a4f80c4a 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1260,17 +1260,19 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, !(vm_flags & vma->vm_flags)) return i ? : -EFAULT; - if (is_vm_hugetlb_page(vma)) { - i = follow_hugetlb_page(mm, vma, pages, vmas, - &start, &nr_pages, i, write); - continue; - } - foll_flags = FOLL_TOUCH; if (pages) foll_flags |= FOLL_GET; if (flags & GUP_FLAGS_DUMP) foll_flags |= FOLL_DUMP; + if (write) + foll_flags |= FOLL_WRITE; + + if (is_vm_hugetlb_page(vma)) { + i = follow_hugetlb_page(mm, vma, pages, vmas, + &start, &nr_pages, i, foll_flags); + continue; + } do { struct page *page; -- cgit v1.2.3 From 6bfde05bf5c9682e255c6a2c669dc80f91af6296 Mon Sep 17 00:00:00 2001 From: Eric B Munson Date: Mon, 21 Sep 2009 17:03:43 -0700 Subject: hugetlbfs: allow the creation of files suitable for MAP_PRIVATE on the vfs internal mount This patchset adds a flag to mmap that allows the user to request that an anonymous mapping be backed with huge pages. This mapping will borrow functionality from the huge page shm code to create a file on the kernel internal mount and use it to approximate an anonymous mapping. The MAP_HUGETLB flag is a modifier to MAP_ANONYMOUS and will not work without both flags being preset. A new flag is necessary because there is no other way to hook into huge pages without creating a file on a hugetlbfs mount which wouldn't be MAP_ANONYMOUS. To userspace, this mapping will behave just like an anonymous mapping because the file is not accessible outside of the kernel. This patchset is meant to simplify the programming model. Presently there is a large chunk of boiler platecode, contained in libhugetlbfs, required to create private, hugepage backed mappings. This patch set would allow use of hugepages without linking to libhugetlbfs or having hugetblfs mounted. Unification of the VM code would provide these same benefits, but it has been resisted each time that it has been suggested for several reasons: it would break PAGE_SIZE assumptions across the kernel, it makes page-table abstractions really expensive, and it does not provide any benefit on architectures that do not support huge pages, incurring fast path penalties without providing any benefit on these architectures. This patch: There are two means of creating mappings backed by huge pages: 1. mmap() a file created on hugetlbfs 2. Use shm which creates a file on an internal mount which essentially maps it MAP_SHARED The internal mount is only used for shared mappings but there is very little that stops it being used for private mappings. This patch extends hugetlbfs_file_setup() to deal with the creation of files that will be mapped MAP_PRIVATE on the internal hugetlbfs mount. This extended API is used in a subsequent patch to implement the MAP_HUGETLB mmap() flag. Signed-off-by: Eric Munson Acked-by: David Rientjes Cc: Mel Gorman Cc: Adam Litke Cc: David Gibson Cc: Lee Schermerhorn Cc: Nick Piggin Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/hugetlbfs/inode.c | 21 +++++++++++++++++---- include/linux/hugetlb.h | 12 ++++++++++-- ipc/shm.c | 2 +- 3 files changed, 28 insertions(+), 7 deletions(-) (limited to 'include/linux/hugetlb.h') diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index a93b885311d8..06b7c2623f99 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -507,6 +507,13 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, uid_t uid, inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; INIT_LIST_HEAD(&inode->i_mapping->private_list); info = HUGETLBFS_I(inode); + /* + * The policy is initialized here even if we are creating a + * private inode because initialization simply creates an + * an empty rb tree and calls spin_lock_init(), later when we + * call mpol_free_shared_policy() it will just return because + * the rb tree will still be empty. + */ mpol_shared_policy_init(&info->policy, NULL); switch (mode & S_IFMT) { default: @@ -931,13 +938,19 @@ static struct file_system_type hugetlbfs_fs_type = { static struct vfsmount *hugetlbfs_vfsmount; -static int can_do_hugetlb_shm(void) +static int can_do_hugetlb_shm(int creat_flags) { - return capable(CAP_IPC_LOCK) || in_group_p(sysctl_hugetlb_shm_group); + if (creat_flags != HUGETLB_SHMFS_INODE) + return 0; + if (capable(CAP_IPC_LOCK)) + return 1; + if (in_group_p(sysctl_hugetlb_shm_group)) + return 1; + return 0; } struct file *hugetlb_file_setup(const char *name, size_t size, int acctflag, - struct user_struct **user) + struct user_struct **user, int creat_flags) { int error = -ENOMEM; struct file *file; @@ -949,7 +962,7 @@ struct file *hugetlb_file_setup(const char *name, size_t size, int acctflag, if (!hugetlbfs_vfsmount) return ERR_PTR(-ENOENT); - if (!can_do_hugetlb_shm()) { + if (!can_do_hugetlb_shm(creat_flags)) { *user = current_user(); if (user_shm_lock(size, *user)) { WARN_ONCE(1, diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index e7f0fabfa1c2..f6505ad86657 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -112,6 +112,14 @@ static inline void hugetlb_report_meminfo(struct seq_file *m) #endif /* !CONFIG_HUGETLB_PAGE */ +enum { + /* + * The file will be used as an shm file so shmfs accounting rules + * apply + */ + HUGETLB_SHMFS_INODE = 1, +}; + #ifdef CONFIG_HUGETLBFS struct hugetlbfs_config { uid_t uid; @@ -150,7 +158,7 @@ static inline struct hugetlbfs_sb_info *HUGETLBFS_SB(struct super_block *sb) extern const struct file_operations hugetlbfs_file_operations; extern struct vm_operations_struct hugetlb_vm_ops; struct file *hugetlb_file_setup(const char *name, size_t size, int acct, - struct user_struct **user); + struct user_struct **user, int creat_flags); int hugetlb_get_quota(struct address_space *mapping, long delta); void hugetlb_put_quota(struct address_space *mapping, long delta); @@ -172,7 +180,7 @@ static inline void set_file_hugepages(struct file *file) #define is_file_hugepages(file) 0 #define set_file_hugepages(file) BUG() -#define hugetlb_file_setup(name,size,acct,user) ERR_PTR(-ENOSYS) +#define hugetlb_file_setup(name,size,acct,user,creat) ERR_PTR(-ENOSYS) #endif /* !CONFIG_HUGETLBFS */ diff --git a/ipc/shm.c b/ipc/shm.c index 30162a59621a..9eb1488b543b 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -370,7 +370,7 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) if (shmflg & SHM_NORESERVE) acctflag = VM_NORESERVE; file = hugetlb_file_setup(name, size, acctflag, - &shp->mlock_user); + &shp->mlock_user, HUGETLB_SHMFS_INODE); } else { /* * Do not allow no accounting for OVERCOMMIT_NEVER, even -- cgit v1.2.3 From 4e52780d41a741fb4861ae1df2413dd816ec11b1 Mon Sep 17 00:00:00 2001 From: Eric B Munson Date: Mon, 21 Sep 2009 17:03:47 -0700 Subject: hugetlb: add MAP_HUGETLB for mmaping pseudo-anonymous huge page regions Add a flag for mmap that will be used to request a huge page region that will look like anonymous memory to userspace. This is accomplished by using a file on the internal vfsmount. MAP_HUGETLB is a modifier of MAP_ANONYMOUS and so must be specified with it. The region will behave the same as a MAP_ANONYMOUS region using small pages. [akpm@linux-foundation.org: fix arch definitions of MAP_HUGETLB] Signed-off-by: Eric B Munson Acked-by: David Rientjes Cc: Mel Gorman Cc: Adam Litke Cc: David Gibson Cc: Lee Schermerhorn Cc: Nick Piggin Cc: Hugh Dickins Cc: Arnd Bergmann Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 7 +++++++ mm/mmap.c | 18 ++++++++++++++++++ 2 files changed, 25 insertions(+) (limited to 'include/linux/hugetlb.h') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index f6505ad86657..176e7ee73eff 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -112,12 +112,19 @@ static inline void hugetlb_report_meminfo(struct seq_file *m) #endif /* !CONFIG_HUGETLB_PAGE */ +#define HUGETLB_ANON_FILE "anon_hugepage" + enum { /* * The file will be used as an shm file so shmfs accounting rules * apply */ HUGETLB_SHMFS_INODE = 1, + /* + * The file is being created on the internal vfs mount and shmfs + * accounting rules do not apply + */ + HUGETLB_ANONHUGE_INODE = 2, }; #ifdef CONFIG_HUGETLBFS diff --git a/mm/mmap.c b/mm/mmap.c index 1aeef6625e6a..21d4029a07b3 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -949,6 +949,24 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, if (mm->map_count > sysctl_max_map_count) return -ENOMEM; + if (flags & MAP_HUGETLB) { + struct user_struct *user = NULL; + if (file) + return -EINVAL; + + /* + * VM_NORESERVE is used because the reservations will be + * taken when vm_ops->mmap() is called + * A dummy user value is used because we are not locking + * memory so no accounting is necessary + */ + len = ALIGN(len, huge_page_size(&default_hstate)); + file = hugetlb_file_setup(HUGETLB_ANON_FILE, len, VM_NORESERVE, + &user, HUGETLB_ANONHUGE_INODE); + if (IS_ERR(file)) + return PTR_ERR(file); + } + /* Obtain the address to map to. we verify (or select) it and ensure * that it represents a valid section of the address space. */ -- 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 'include/linux/hugetlb.h') diff --git a/arch/frv/kernel/pm.c b/arch/frv/kernel/pm.c index be722fc1acff..0d4d3e3a4cfc 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 3f04d4c406b7..b3deed8db619 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 264528e4f58d..b55fd7ed1c31 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 4c512561687d..20f282c911c2 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 413c240cbca7..b201135cc18c 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 e63cf7d441e1..139d4c1a33a7 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 cb66a22d98ad..7ff61d6a188a 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 cf53a78e2dcf..8cb4974ff599 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 71d1b9bab70b..614da5b8613a 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 d8a9255e1a3f..04b505e5a5e2 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 2ab1d59870f4..a8b689635a3b 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 554e11f9e1ce..8eefe56f1cbe 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 8ccd5ed81d9c..d99860a33890 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 a2edb7913447..31f4b0e6d72c 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 334ce39881f8..8eb44042e009 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 9b1e4e9a16bf..f667e8aeabdf 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 916c0ffb6083..c5bc67c4e3bb 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 51803528b095..33ed6644abd0 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 3c0924a18daf..cd3d2abaf30a 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 176e7ee73eff..11ab19ac6b3d 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 b6eae5e3144b..87218ae84e36 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 652ef01be582..6f7561730d88 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 e951bd2eb9fc..811cd96524d7 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 d050b66ab9ef..239e40d0450b 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 4c78fea989b9..82232dbea3f7 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 e76d3b22a466..1e4743ee6831 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 75cf58666ff9..66ebddcff664 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 72c36926c26d..5b26a0bd178e 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 1459ed3e2697..f76f22d05721 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 40eab7314aeb..7d3704750efc 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 24ae46dfe45d..8a058711fc10 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 022a4927b785..d4e841747400 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 0d0361b9dbb3..ee61f454a98b 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 ecc637a0d591..4e777b47eeda 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 09d7519557d3..0d31135efbf4 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 88796c330838..81324d12eb35 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 37abb8c3995b..a02697b7cb97 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 23df7771c937..a142579765bf 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 0f6facb050a1..8504ac71e4e8 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 92359cc747a7..69eae358a726 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 815dbd4a6dcb..6f048fcc749c 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 5f378dd58802..be197f71b096 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 5717f27a0704..88248b3c20bb 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 2423782214ab..f444b7409085 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 907a82e9023d..a16a2342f6bf 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 1c6a5bb6f0c8..6e1f085db06a 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 5bcd592ae6dd..26b0ab1e9f56 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 07336c6201f0..e92f1fd28aa5 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 df9347314538..bb4199252026 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 4710d219f06a..2dcf04d9b005 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 55f486d89c88..1fd0a3d775d2 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 7015478797f6..498b9b0b0fad 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 77aecbe8ff6c..d6fe7646a8ff 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 57f8817c3979..5c86567e5a78 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 fba2892b99e1..446e9bd4b4bc 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 4e620305f28c..c93494fef8ef 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 7b5749ee2765..2220f3322326 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 5231f7aaac0e..42f9748ae093 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 87101177825b..35fb68b9c8ec 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 14cc7b3b8d03..c844eed7915d 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 e9ea0e2d1d00959b451dfc239df126d3c6a22043 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Thu, 24 Sep 2009 14:47:45 -0700 Subject: hugetlb_file_setup(): use C, not cpp Why macros are always wrong: mm/mmap.c: In function 'do_mmap_pgoff': mm/mmap.c:953: warning: unused variable 'user' also, move a couple of struct forward-decls outside `#ifdef CONFIG_HUGETLB_PAGE' - it's pointless and frequently harmful to make these conditional (eg, this patch needed `struct user_struct'). Cc: Lee Schermerhorn Cc: Mel Gorman Cc: Nishanth Aravamudan Cc: David Rientjes Cc: Adam Litke Cc: Andy Whitcroft Cc: Eric Whitney Cc: Eric B Munson Cc: David Howells Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux/hugetlb.h') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 11ab19ac6b3d..16937995abd4 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -3,15 +3,15 @@ #include +struct ctl_table; +struct user_struct; + #ifdef CONFIG_HUGETLB_PAGE #include #include #include -struct ctl_table; -struct user_struct; - int PageHuge(struct page *page); static inline int is_vm_hugetlb_page(struct vm_area_struct *vma) @@ -187,7 +187,11 @@ static inline void set_file_hugepages(struct file *file) #define is_file_hugepages(file) 0 #define set_file_hugepages(file) BUG() -#define hugetlb_file_setup(name,size,acct,user,creat) ERR_PTR(-ENOSYS) +static inline struct file *hugetlb_file_setup(const char *name, size_t size, + int acctflag, struct user_struct **user, int creat_flags) +{ + return ERR_PTR(-ENOSYS); +} #endif /* !CONFIG_HUGETLBFS */ -- cgit v1.2.3 From f0f37e2f77731b3473fa6bd5ee53255d9a9cdb40 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Sun, 27 Sep 2009 22:29:37 +0400 Subject: const: mark struct vm_struct_operations * mark struct vm_area_struct::vm_ops as const * mark vm_ops in AGP code But leave TTM code alone, something is fishy there with global vm_ops being used. Signed-off-by: Alexey Dobriyan Signed-off-by: Linus Torvalds --- arch/ia64/ia32/binfmt_elf32.c | 4 ++-- arch/powerpc/platforms/cell/spufs/file.c | 14 +++++++------- arch/x86/pci/i386.c | 2 +- drivers/char/agp/agp.h | 2 +- drivers/char/agp/alpha-agp.c | 2 +- drivers/char/mem.c | 2 +- drivers/char/mspec.c | 2 +- drivers/gpu/drm/drm_vm.c | 8 ++++---- drivers/gpu/drm/radeon/radeon_ttm.c | 2 +- drivers/gpu/drm/ttm/ttm_bo_vm.c | 2 +- drivers/ieee1394/dma.c | 2 +- drivers/infiniband/hw/ehca/ehca_uverbs.c | 2 +- drivers/infiniband/hw/ipath/ipath_file_ops.c | 2 +- drivers/infiniband/hw/ipath/ipath_mmap.c | 2 +- drivers/media/video/cafe_ccic.c | 2 +- drivers/media/video/et61x251/et61x251_core.c | 2 +- drivers/media/video/gspca/gspca.c | 2 +- drivers/media/video/meye.c | 2 +- drivers/media/video/sn9c102/sn9c102_core.c | 2 +- drivers/media/video/stk-webcam.c | 2 +- drivers/media/video/uvc/uvc_v4l2.c | 2 +- drivers/media/video/videobuf-dma-contig.c | 2 +- drivers/media/video/videobuf-dma-sg.c | 2 +- drivers/media/video/videobuf-vmalloc.c | 2 +- drivers/media/video/vino.c | 2 +- drivers/media/video/zc0301/zc0301_core.c | 2 +- drivers/media/video/zoran/zoran_driver.c | 2 +- drivers/misc/sgi-gru/grufile.c | 2 +- drivers/misc/sgi-gru/grutables.h | 2 +- drivers/scsi/sg.c | 2 +- drivers/uio/uio.c | 2 +- drivers/usb/mon/mon_bin.c | 2 +- drivers/video/fb_defio.c | 2 +- drivers/video/omap/dispc.c | 2 +- fs/btrfs/file.c | 2 +- fs/ext4/file.c | 2 +- fs/fuse/file.c | 2 +- fs/gfs2/file.c | 2 +- fs/ncpfs/mmap.c | 2 +- fs/nfs/file.c | 4 ++-- fs/nilfs2/file.c | 2 +- fs/ocfs2/mmap.c | 2 +- fs/sysfs/bin.c | 4 ++-- fs/ubifs/file.c | 2 +- fs/xfs/linux-2.6/xfs_file.c | 4 ++-- include/linux/agp_backend.h | 2 +- include/linux/hugetlb.h | 2 +- include/linux/mm_types.h | 2 +- include/linux/ramfs.h | 2 +- ipc/shm.c | 4 ++-- kernel/perf_event.c | 2 +- kernel/relay.c | 2 +- mm/filemap.c | 2 +- mm/filemap_xip.c | 2 +- mm/hugetlb.c | 2 +- mm/mmap.c | 2 +- mm/nommu.c | 2 +- mm/shmem.c | 4 ++-- net/packet/af_packet.c | 2 +- sound/core/pcm_native.c | 8 ++++---- sound/usb/usx2y/us122l.c | 2 +- sound/usb/usx2y/usX2Yhwdep.c | 2 +- sound/usb/usx2y/usx2yhwdeppcm.c | 2 +- virt/kvm/kvm_main.c | 4 ++-- 64 files changed, 83 insertions(+), 83 deletions(-) (limited to 'include/linux/hugetlb.h') diff --git a/arch/ia64/ia32/binfmt_elf32.c b/arch/ia64/ia32/binfmt_elf32.c index f92bdaac8976..c69552bf893e 100644 --- a/arch/ia64/ia32/binfmt_elf32.c +++ b/arch/ia64/ia32/binfmt_elf32.c @@ -69,11 +69,11 @@ ia32_install_gate_page (struct vm_area_struct *vma, struct vm_fault *vmf) } -static struct vm_operations_struct ia32_shared_page_vm_ops = { +static const struct vm_operations_struct ia32_shared_page_vm_ops = { .fault = ia32_install_shared_page }; -static struct vm_operations_struct ia32_gate_page_vm_ops = { +static const struct vm_operations_struct ia32_gate_page_vm_ops = { .fault = ia32_install_gate_page }; diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c index 8f079b865ad0..961309446170 100644 --- a/arch/powerpc/platforms/cell/spufs/file.c +++ b/arch/powerpc/platforms/cell/spufs/file.c @@ -309,7 +309,7 @@ static int spufs_mem_mmap_access(struct vm_area_struct *vma, return len; } -static struct vm_operations_struct spufs_mem_mmap_vmops = { +static const struct vm_operations_struct spufs_mem_mmap_vmops = { .fault = spufs_mem_mmap_fault, .access = spufs_mem_mmap_access, }; @@ -436,7 +436,7 @@ static int spufs_cntl_mmap_fault(struct vm_area_struct *vma, return spufs_ps_fault(vma, vmf, 0x4000, SPUFS_CNTL_MAP_SIZE); } -static struct vm_operations_struct spufs_cntl_mmap_vmops = { +static const struct vm_operations_struct spufs_cntl_mmap_vmops = { .fault = spufs_cntl_mmap_fault, }; @@ -1143,7 +1143,7 @@ spufs_signal1_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) #endif } -static struct vm_operations_struct spufs_signal1_mmap_vmops = { +static const struct vm_operations_struct spufs_signal1_mmap_vmops = { .fault = spufs_signal1_mmap_fault, }; @@ -1279,7 +1279,7 @@ spufs_signal2_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) #endif } -static struct vm_operations_struct spufs_signal2_mmap_vmops = { +static const struct vm_operations_struct spufs_signal2_mmap_vmops = { .fault = spufs_signal2_mmap_fault, }; @@ -1397,7 +1397,7 @@ spufs_mss_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) return spufs_ps_fault(vma, vmf, 0x0000, SPUFS_MSS_MAP_SIZE); } -static struct vm_operations_struct spufs_mss_mmap_vmops = { +static const struct vm_operations_struct spufs_mss_mmap_vmops = { .fault = spufs_mss_mmap_fault, }; @@ -1458,7 +1458,7 @@ spufs_psmap_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) return spufs_ps_fault(vma, vmf, 0x0000, SPUFS_PS_MAP_SIZE); } -static struct vm_operations_struct spufs_psmap_mmap_vmops = { +static const struct vm_operations_struct spufs_psmap_mmap_vmops = { .fault = spufs_psmap_mmap_fault, }; @@ -1517,7 +1517,7 @@ spufs_mfc_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) return spufs_ps_fault(vma, vmf, 0x3000, SPUFS_MFC_MAP_SIZE); } -static struct vm_operations_struct spufs_mfc_mmap_vmops = { +static const struct vm_operations_struct spufs_mfc_mmap_vmops = { .fault = spufs_mfc_mmap_fault, }; diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c index 52e62e57fedd..b22d13b0c71d 100644 --- a/arch/x86/pci/i386.c +++ b/arch/x86/pci/i386.c @@ -266,7 +266,7 @@ void pcibios_set_master(struct pci_dev *dev) pci_write_config_byte(dev, PCI_LATENCY_TIMER, lat); } -static struct vm_operations_struct pci_mmap_ops = { +static const struct vm_operations_struct pci_mmap_ops = { .access = generic_access_phys, }; diff --git a/drivers/char/agp/agp.h b/drivers/char/agp/agp.h index d6f36c004d9b..870f12cfed93 100644 --- a/drivers/char/agp/agp.h +++ b/drivers/char/agp/agp.h @@ -131,7 +131,7 @@ struct agp_bridge_driver { struct agp_bridge_data { const struct agp_version *version; const struct agp_bridge_driver *driver; - struct vm_operations_struct *vm_ops; + const struct vm_operations_struct *vm_ops; void *previous_size; void *current_size; void *dev_private_data; diff --git a/drivers/char/agp/alpha-agp.c b/drivers/char/agp/alpha-agp.c index 5ea4da8e9954..dd84af4d4f7e 100644 --- a/drivers/char/agp/alpha-agp.c +++ b/drivers/char/agp/alpha-agp.c @@ -40,7 +40,7 @@ static struct aper_size_info_fixed alpha_core_agp_sizes[] = { 0, 0, 0 }, /* filled in by alpha_core_agp_setup */ }; -struct vm_operations_struct alpha_core_agp_vm_ops = { +static const struct vm_operations_struct alpha_core_agp_vm_ops = { .fault = alpha_core_agp_vm_fault, }; diff --git a/drivers/char/mem.c b/drivers/char/mem.c index 6c8b65d069e5..a074fceb67d3 100644 --- a/drivers/char/mem.c +++ b/drivers/char/mem.c @@ -301,7 +301,7 @@ static inline int private_mapping_ok(struct vm_area_struct *vma) } #endif -static struct vm_operations_struct mmap_mem_ops = { +static const struct vm_operations_struct mmap_mem_ops = { #ifdef CONFIG_HAVE_IOREMAP_PROT .access = generic_access_phys #endif diff --git a/drivers/char/mspec.c b/drivers/char/mspec.c index 30f095a8c2d4..1997270bb6f4 100644 --- a/drivers/char/mspec.c +++ b/drivers/char/mspec.c @@ -239,7 +239,7 @@ mspec_fault(struct vm_area_struct *vma, struct vm_fault *vmf) return VM_FAULT_NOPAGE; } -static struct vm_operations_struct mspec_vm_ops = { +static const struct vm_operations_struct mspec_vm_ops = { .open = mspec_open, .close = mspec_close, .fault = mspec_fault, diff --git a/drivers/gpu/drm/drm_vm.c b/drivers/gpu/drm/drm_vm.c index 7e1fbe5d4779..4ac900f4647f 100644 --- a/drivers/gpu/drm/drm_vm.c +++ b/drivers/gpu/drm/drm_vm.c @@ -369,28 +369,28 @@ static int drm_vm_sg_fault(struct vm_area_struct *vma, struct vm_fault *vmf) } /** AGP virtual memory operations */ -static struct vm_operations_struct drm_vm_ops = { +static const struct vm_operations_struct drm_vm_ops = { .fault = drm_vm_fault, .open = drm_vm_open, .close = drm_vm_close, }; /** Shared virtual memory operations */ -static struct vm_operations_struct drm_vm_shm_ops = { +static const struct vm_operations_struct drm_vm_shm_ops = { .fault = drm_vm_shm_fault, .open = drm_vm_open, .close = drm_vm_shm_close, }; /** DMA virtual memory operations */ -static struct vm_operations_struct drm_vm_dma_ops = { +static const struct vm_operations_struct drm_vm_dma_ops = { .fault = drm_vm_dma_fault, .open = drm_vm_open, .close = drm_vm_close, }; /** Scatter-gather virtual memory operations */ -static struct vm_operations_struct drm_vm_sg_ops = { +static const struct vm_operations_struct drm_vm_sg_ops = { .fault = drm_vm_sg_fault, .open = drm_vm_open, .close = drm_vm_close, diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index acd889c94549..5b1cf04a011a 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -530,7 +530,7 @@ void radeon_ttm_fini(struct radeon_device *rdev) } static struct vm_operations_struct radeon_ttm_vm_ops; -static struct vm_operations_struct *ttm_vm_ops = NULL; +static const struct vm_operations_struct *ttm_vm_ops = NULL; static int radeon_ttm_fault(struct vm_area_struct *vma, struct vm_fault *vmf) { diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c index 33de7637c0c6..1c040d040338 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_vm.c +++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c @@ -228,7 +228,7 @@ static void ttm_bo_vm_close(struct vm_area_struct *vma) vma->vm_private_data = NULL; } -static struct vm_operations_struct ttm_bo_vm_ops = { +static const struct vm_operations_struct ttm_bo_vm_ops = { .fault = ttm_bo_vm_fault, .open = ttm_bo_vm_open, .close = ttm_bo_vm_close diff --git a/drivers/ieee1394/dma.c b/drivers/ieee1394/dma.c index 1aba8c13fe8f..8e7e3344c4b3 100644 --- a/drivers/ieee1394/dma.c +++ b/drivers/ieee1394/dma.c @@ -247,7 +247,7 @@ static int dma_region_pagefault(struct vm_area_struct *vma, return 0; } -static struct vm_operations_struct dma_region_vm_ops = { +static const struct vm_operations_struct dma_region_vm_ops = { .fault = dma_region_pagefault, }; diff --git a/drivers/infiniband/hw/ehca/ehca_uverbs.c b/drivers/infiniband/hw/ehca/ehca_uverbs.c index 3cb688d29131..f1565cae8ec6 100644 --- a/drivers/infiniband/hw/ehca/ehca_uverbs.c +++ b/drivers/infiniband/hw/ehca/ehca_uverbs.c @@ -95,7 +95,7 @@ static void ehca_mm_close(struct vm_area_struct *vma) vma->vm_start, vma->vm_end, *count); } -static struct vm_operations_struct vm_ops = { +static const struct vm_operations_struct vm_ops = { .open = ehca_mm_open, .close = ehca_mm_close, }; diff --git a/drivers/infiniband/hw/ipath/ipath_file_ops.c b/drivers/infiniband/hw/ipath/ipath_file_ops.c index 38a287006612..40dbe54056c7 100644 --- a/drivers/infiniband/hw/ipath/ipath_file_ops.c +++ b/drivers/infiniband/hw/ipath/ipath_file_ops.c @@ -1151,7 +1151,7 @@ static int ipath_file_vma_fault(struct vm_area_struct *vma, return 0; } -static struct vm_operations_struct ipath_file_vm_ops = { +static const struct vm_operations_struct ipath_file_vm_ops = { .fault = ipath_file_vma_fault, }; diff --git a/drivers/infiniband/hw/ipath/ipath_mmap.c b/drivers/infiniband/hw/ipath/ipath_mmap.c index fa830e22002f..b28865faf435 100644 --- a/drivers/infiniband/hw/ipath/ipath_mmap.c +++ b/drivers/infiniband/hw/ipath/ipath_mmap.c @@ -74,7 +74,7 @@ static void ipath_vma_close(struct vm_area_struct *vma) kref_put(&ip->ref, ipath_release_mmap_info); } -static struct vm_operations_struct ipath_vm_ops = { +static const struct vm_operations_struct ipath_vm_ops = { .open = ipath_vma_open, .close = ipath_vma_close, }; diff --git a/drivers/media/video/cafe_ccic.c b/drivers/media/video/cafe_ccic.c index 657c481d255c..10230cb3d210 100644 --- a/drivers/media/video/cafe_ccic.c +++ b/drivers/media/video/cafe_ccic.c @@ -1325,7 +1325,7 @@ static void cafe_v4l_vm_close(struct vm_area_struct *vma) mutex_unlock(&sbuf->cam->s_mutex); } -static struct vm_operations_struct cafe_v4l_vm_ops = { +static const struct vm_operations_struct cafe_v4l_vm_ops = { .open = cafe_v4l_vm_open, .close = cafe_v4l_vm_close }; diff --git a/drivers/media/video/et61x251/et61x251_core.c b/drivers/media/video/et61x251/et61x251_core.c index 74092f436be6..88987a57cf7b 100644 --- a/drivers/media/video/et61x251/et61x251_core.c +++ b/drivers/media/video/et61x251/et61x251_core.c @@ -1496,7 +1496,7 @@ static void et61x251_vm_close(struct vm_area_struct* vma) } -static struct vm_operations_struct et61x251_vm_ops = { +static const struct vm_operations_struct et61x251_vm_ops = { .open = et61x251_vm_open, .close = et61x251_vm_close, }; diff --git a/drivers/media/video/gspca/gspca.c b/drivers/media/video/gspca/gspca.c index cf6540da1e42..23d3fb776918 100644 --- a/drivers/media/video/gspca/gspca.c +++ b/drivers/media/video/gspca/gspca.c @@ -99,7 +99,7 @@ static void gspca_vm_close(struct vm_area_struct *vma) frame->v4l2_buf.flags &= ~V4L2_BUF_FLAG_MAPPED; } -static struct vm_operations_struct gspca_vm_ops = { +static const struct vm_operations_struct gspca_vm_ops = { .open = gspca_vm_open, .close = gspca_vm_close, }; diff --git a/drivers/media/video/meye.c b/drivers/media/video/meye.c index d0765bed79c9..4b1bc05a462c 100644 --- a/drivers/media/video/meye.c +++ b/drivers/media/video/meye.c @@ -1589,7 +1589,7 @@ static void meye_vm_close(struct vm_area_struct *vma) meye.vma_use_count[idx]--; } -static struct vm_operations_struct meye_vm_ops = { +static const struct vm_operations_struct meye_vm_ops = { .open = meye_vm_open, .close = meye_vm_close, }; diff --git a/drivers/media/video/sn9c102/sn9c102_core.c b/drivers/media/video/sn9c102/sn9c102_core.c index 9d84c94e8a40..4a7711c3e745 100644 --- a/drivers/media/video/sn9c102/sn9c102_core.c +++ b/drivers/media/video/sn9c102/sn9c102_core.c @@ -2077,7 +2077,7 @@ static void sn9c102_vm_close(struct vm_area_struct* vma) } -static struct vm_operations_struct sn9c102_vm_ops = { +static const struct vm_operations_struct sn9c102_vm_ops = { .open = sn9c102_vm_open, .close = sn9c102_vm_close, }; diff --git a/drivers/media/video/stk-webcam.c b/drivers/media/video/stk-webcam.c index 0b996ea4134e..6b41865f42bd 100644 --- a/drivers/media/video/stk-webcam.c +++ b/drivers/media/video/stk-webcam.c @@ -790,7 +790,7 @@ static void stk_v4l_vm_close(struct vm_area_struct *vma) if (sbuf->mapcount == 0) sbuf->v4lbuf.flags &= ~V4L2_BUF_FLAG_MAPPED; } -static struct vm_operations_struct stk_v4l_vm_ops = { +static const struct vm_operations_struct stk_v4l_vm_ops = { .open = stk_v4l_vm_open, .close = stk_v4l_vm_close }; diff --git a/drivers/media/video/uvc/uvc_v4l2.c b/drivers/media/video/uvc/uvc_v4l2.c index 9e7351569b5d..a2bdd806efab 100644 --- a/drivers/media/video/uvc/uvc_v4l2.c +++ b/drivers/media/video/uvc/uvc_v4l2.c @@ -1069,7 +1069,7 @@ static void uvc_vm_close(struct vm_area_struct *vma) buffer->vma_use_count--; } -static struct vm_operations_struct uvc_vm_ops = { +static const struct vm_operations_struct uvc_vm_ops = { .open = uvc_vm_open, .close = uvc_vm_close, }; diff --git a/drivers/media/video/videobuf-dma-contig.c b/drivers/media/video/videobuf-dma-contig.c index d09ce83a9429..635ffc7b0391 100644 --- a/drivers/media/video/videobuf-dma-contig.c +++ b/drivers/media/video/videobuf-dma-contig.c @@ -105,7 +105,7 @@ static void videobuf_vm_close(struct vm_area_struct *vma) } } -static struct vm_operations_struct videobuf_vm_ops = { +static const struct vm_operations_struct videobuf_vm_ops = { .open = videobuf_vm_open, .close = videobuf_vm_close, }; diff --git a/drivers/media/video/videobuf-dma-sg.c b/drivers/media/video/videobuf-dma-sg.c index a8dd22ace3fb..53cdd67cebe1 100644 --- a/drivers/media/video/videobuf-dma-sg.c +++ b/drivers/media/video/videobuf-dma-sg.c @@ -394,7 +394,7 @@ videobuf_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf) return 0; } -static struct vm_operations_struct videobuf_vm_ops = +static const struct vm_operations_struct videobuf_vm_ops = { .open = videobuf_vm_open, .close = videobuf_vm_close, diff --git a/drivers/media/video/videobuf-vmalloc.c b/drivers/media/video/videobuf-vmalloc.c index 30ae30f99ccc..35f3900c5633 100644 --- a/drivers/media/video/videobuf-vmalloc.c +++ b/drivers/media/video/videobuf-vmalloc.c @@ -116,7 +116,7 @@ static void videobuf_vm_close(struct vm_area_struct *vma) return; } -static struct vm_operations_struct videobuf_vm_ops = +static const struct vm_operations_struct videobuf_vm_ops = { .open = videobuf_vm_open, .close = videobuf_vm_close, diff --git a/drivers/media/video/vino.c b/drivers/media/video/vino.c index cd6a3446ab7e..b034a81d2b1c 100644 --- a/drivers/media/video/vino.c +++ b/drivers/media/video/vino.c @@ -3857,7 +3857,7 @@ static void vino_vm_close(struct vm_area_struct *vma) dprintk("vino_vm_close(): count = %d\n", fb->map_count); } -static struct vm_operations_struct vino_vm_ops = { +static const struct vm_operations_struct vino_vm_ops = { .open = vino_vm_open, .close = vino_vm_close, }; diff --git a/drivers/media/video/zc0301/zc0301_core.c b/drivers/media/video/zc0301/zc0301_core.c index b3c6436b33ba..312a71336fd0 100644 --- a/drivers/media/video/zc0301/zc0301_core.c +++ b/drivers/media/video/zc0301/zc0301_core.c @@ -935,7 +935,7 @@ static void zc0301_vm_close(struct vm_area_struct* vma) } -static struct vm_operations_struct zc0301_vm_ops = { +static const struct vm_operations_struct zc0301_vm_ops = { .open = zc0301_vm_open, .close = zc0301_vm_close, }; diff --git a/drivers/media/video/zoran/zoran_driver.c b/drivers/media/video/zoran/zoran_driver.c index bcdefb1bcb3d..47137deafcfd 100644 --- a/drivers/media/video/zoran/zoran_driver.c +++ b/drivers/media/video/zoran/zoran_driver.c @@ -3172,7 +3172,7 @@ zoran_vm_close (struct vm_area_struct *vma) mutex_unlock(&zr->resource_lock); } -static struct vm_operations_struct zoran_vm_ops = { +static const struct vm_operations_struct zoran_vm_ops = { .open = zoran_vm_open, .close = zoran_vm_close, }; diff --git a/drivers/misc/sgi-gru/grufile.c b/drivers/misc/sgi-gru/grufile.c index aed609832bc2..300e7ba391a0 100644 --- a/drivers/misc/sgi-gru/grufile.c +++ b/drivers/misc/sgi-gru/grufile.c @@ -438,7 +438,7 @@ static struct miscdevice gru_miscdev = { .fops = &gru_fops, }; -struct vm_operations_struct gru_vm_ops = { +const struct vm_operations_struct gru_vm_ops = { .close = gru_vma_close, .fault = gru_fault, }; diff --git a/drivers/misc/sgi-gru/grutables.h b/drivers/misc/sgi-gru/grutables.h index 34ab3d453919..46990bcfa536 100644 --- a/drivers/misc/sgi-gru/grutables.h +++ b/drivers/misc/sgi-gru/grutables.h @@ -624,7 +624,7 @@ static inline int is_kernel_context(struct gru_thread_state *gts) */ struct gru_unload_context_req; -extern struct vm_operations_struct gru_vm_ops; +extern const struct vm_operations_struct gru_vm_ops; extern struct device *grudev; extern struct gru_vma_data *gru_alloc_vma_data(struct vm_area_struct *vma, diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 848b59466850..0cb049f5cc56 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -1185,7 +1185,7 @@ sg_vma_fault(struct vm_area_struct *vma, struct vm_fault *vmf) return VM_FAULT_SIGBUS; } -static struct vm_operations_struct sg_mmap_vm_ops = { +static const struct vm_operations_struct sg_mmap_vm_ops = { .fault = sg_vma_fault, }; diff --git a/drivers/uio/uio.c b/drivers/uio/uio.c index 03efb065455f..a9d707047202 100644 --- a/drivers/uio/uio.c +++ b/drivers/uio/uio.c @@ -658,7 +658,7 @@ static int uio_vma_fault(struct vm_area_struct *vma, struct vm_fault *vmf) return 0; } -static struct vm_operations_struct uio_vm_ops = { +static const struct vm_operations_struct uio_vm_ops = { .open = uio_vma_open, .close = uio_vma_close, .fault = uio_vma_fault, diff --git a/drivers/usb/mon/mon_bin.c b/drivers/usb/mon/mon_bin.c index dfdc43e2e00d..9ed3e741bee1 100644 --- a/drivers/usb/mon/mon_bin.c +++ b/drivers/usb/mon/mon_bin.c @@ -1174,7 +1174,7 @@ static int mon_bin_vma_fault(struct vm_area_struct *vma, struct vm_fault *vmf) return 0; } -static struct vm_operations_struct mon_bin_vm_ops = { +static const struct vm_operations_struct mon_bin_vm_ops = { .open = mon_bin_vma_open, .close = mon_bin_vma_close, .fault = mon_bin_vma_fault, diff --git a/drivers/video/fb_defio.c b/drivers/video/fb_defio.c index 0a7a6679ee6e..c27ab1ed9604 100644 --- a/drivers/video/fb_defio.c +++ b/drivers/video/fb_defio.c @@ -125,7 +125,7 @@ page_already_added: return 0; } -static struct vm_operations_struct fb_deferred_io_vm_ops = { +static const struct vm_operations_struct fb_deferred_io_vm_ops = { .fault = fb_deferred_io_fault, .page_mkwrite = fb_deferred_io_mkwrite, }; diff --git a/drivers/video/omap/dispc.c b/drivers/video/omap/dispc.c index 80a11d078df4..f16e42154229 100644 --- a/drivers/video/omap/dispc.c +++ b/drivers/video/omap/dispc.c @@ -1035,7 +1035,7 @@ static void mmap_user_close(struct vm_area_struct *vma) atomic_dec(&dispc.map_count[plane]); } -static struct vm_operations_struct mmap_user_ops = { +static const struct vm_operations_struct mmap_user_ops = { .open = mmap_user_open, .close = mmap_user_close, }; diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 571ad3c13b47..a3492a3ad96b 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1184,7 +1184,7 @@ out: return ret > 0 ? EIO : ret; } -static struct vm_operations_struct btrfs_file_vm_ops = { +static const struct vm_operations_struct btrfs_file_vm_ops = { .fault = filemap_fault, .page_mkwrite = btrfs_page_mkwrite, }; diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 5ca3eca70a1e..9630583cef28 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -81,7 +81,7 @@ ext4_file_write(struct kiocb *iocb, const struct iovec *iov, return generic_file_aio_write(iocb, iov, nr_segs, pos); } -static struct vm_operations_struct ext4_file_vm_ops = { +static const struct vm_operations_struct ext4_file_vm_ops = { .fault = filemap_fault, .page_mkwrite = ext4_page_mkwrite, }; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index cbc464043b6f..a3492f7d207c 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1313,7 +1313,7 @@ static int fuse_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) return 0; } -static struct vm_operations_struct fuse_file_vm_ops = { +static const struct vm_operations_struct fuse_file_vm_ops = { .close = fuse_vma_close, .fault = filemap_fault, .page_mkwrite = fuse_page_mkwrite, diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 166f38fbd246..4eb308aa3234 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -418,7 +418,7 @@ out: return ret; } -static struct vm_operations_struct gfs2_vm_ops = { +static const struct vm_operations_struct gfs2_vm_ops = { .fault = filemap_fault, .page_mkwrite = gfs2_page_mkwrite, }; diff --git a/fs/ncpfs/mmap.c b/fs/ncpfs/mmap.c index 5d8dcb9ee326..15458decdb8a 100644 --- a/fs/ncpfs/mmap.c +++ b/fs/ncpfs/mmap.c @@ -95,7 +95,7 @@ static int ncp_file_mmap_fault(struct vm_area_struct *area, return VM_FAULT_MAJOR; } -static struct vm_operations_struct ncp_file_mmap = +static const struct vm_operations_struct ncp_file_mmap = { .fault = ncp_file_mmap_fault, }; diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 86d6b4db1096..f5fdd39e037a 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -59,7 +59,7 @@ static int nfs_lock(struct file *filp, int cmd, struct file_lock *fl); static int nfs_flock(struct file *filp, int cmd, struct file_lock *fl); static int nfs_setlease(struct file *file, long arg, struct file_lock **fl); -static struct vm_operations_struct nfs_file_vm_ops; +static const struct vm_operations_struct nfs_file_vm_ops; const struct file_operations nfs_file_operations = { .llseek = nfs_file_llseek, @@ -572,7 +572,7 @@ out_unlock: return VM_FAULT_SIGBUS; } -static struct vm_operations_struct nfs_file_vm_ops = { +static const struct vm_operations_struct nfs_file_vm_ops = { .fault = filemap_fault, .page_mkwrite = nfs_vm_page_mkwrite, }; diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c index fc8278c77cdd..7d7b4983dee3 100644 --- a/fs/nilfs2/file.c +++ b/fs/nilfs2/file.c @@ -117,7 +117,7 @@ static int nilfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) return 0; } -struct vm_operations_struct nilfs_file_vm_ops = { +static const struct vm_operations_struct nilfs_file_vm_ops = { .fault = filemap_fault, .page_mkwrite = nilfs_page_mkwrite, }; diff --git a/fs/ocfs2/mmap.c b/fs/ocfs2/mmap.c index b606496b72ec..39737613424a 100644 --- a/fs/ocfs2/mmap.c +++ b/fs/ocfs2/mmap.c @@ -202,7 +202,7 @@ out: return ret; } -static struct vm_operations_struct ocfs2_file_vm_ops = { +static const struct vm_operations_struct ocfs2_file_vm_ops = { .fault = ocfs2_fault, .page_mkwrite = ocfs2_page_mkwrite, }; diff --git a/fs/sysfs/bin.c b/fs/sysfs/bin.c index 2524714bece1..60c702bc10ae 100644 --- a/fs/sysfs/bin.c +++ b/fs/sysfs/bin.c @@ -40,7 +40,7 @@ struct bin_buffer { struct mutex mutex; void *buffer; int mmapped; - struct vm_operations_struct *vm_ops; + const struct vm_operations_struct *vm_ops; struct file *file; struct hlist_node list; }; @@ -331,7 +331,7 @@ static int bin_migrate(struct vm_area_struct *vma, const nodemask_t *from, } #endif -static struct vm_operations_struct bin_vm_ops = { +static const struct vm_operations_struct bin_vm_ops = { .open = bin_vma_open, .close = bin_vma_close, .fault = bin_fault, diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 2e6481a7701c..1009adc8d602 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -1534,7 +1534,7 @@ out_unlock: return err; } -static struct vm_operations_struct ubifs_file_vm_ops = { +static const struct vm_operations_struct ubifs_file_vm_ops = { .fault = filemap_fault, .page_mkwrite = ubifs_vm_page_mkwrite, }; diff --git a/fs/xfs/linux-2.6/xfs_file.c b/fs/xfs/linux-2.6/xfs_file.c index 988d8f87bc0f..629370974e57 100644 --- a/fs/xfs/linux-2.6/xfs_file.c +++ b/fs/xfs/linux-2.6/xfs_file.c @@ -42,7 +42,7 @@ #include -static struct vm_operations_struct xfs_file_vm_ops; +static const struct vm_operations_struct xfs_file_vm_ops; STATIC ssize_t xfs_file_aio_read( @@ -280,7 +280,7 @@ const struct file_operations xfs_dir_file_operations = { .fsync = xfs_file_fsync, }; -static struct vm_operations_struct xfs_file_vm_ops = { +static const struct vm_operations_struct xfs_file_vm_ops = { .fault = filemap_fault, .page_mkwrite = xfs_vm_page_mkwrite, }; diff --git a/include/linux/agp_backend.h b/include/linux/agp_backend.h index 880130f7311f..9101ed64f803 100644 --- a/include/linux/agp_backend.h +++ b/include/linux/agp_backend.h @@ -53,7 +53,7 @@ struct agp_kern_info { int current_memory; bool cant_use_aperture; unsigned long page_mask; - struct vm_operations_struct *vm_ops; + const struct vm_operations_struct *vm_ops; }; /* diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 16937995abd4..41a59afc70fa 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -163,7 +163,7 @@ static inline struct hugetlbfs_sb_info *HUGETLBFS_SB(struct super_block *sb) } extern const struct file_operations hugetlbfs_file_operations; -extern struct vm_operations_struct hugetlb_vm_ops; +extern const struct vm_operations_struct hugetlb_vm_ops; struct file *hugetlb_file_setup(const char *name, size_t size, int acct, struct user_struct **user, int creat_flags); int hugetlb_get_quota(struct address_space *mapping, long delta); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 21d6aa45206a..84a524afb3dc 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -171,7 +171,7 @@ struct vm_area_struct { struct anon_vma *anon_vma; /* Serialized by page_table_lock */ /* Function pointers to deal with this struct. */ - struct vm_operations_struct * vm_ops; + const struct vm_operations_struct *vm_ops; /* Information about our backing store: */ unsigned long vm_pgoff; /* Offset (within vm_file) in PAGE_SIZE diff --git a/include/linux/ramfs.h b/include/linux/ramfs.h index 37aaf2b39863..4e768dda87b0 100644 --- a/include/linux/ramfs.h +++ b/include/linux/ramfs.h @@ -17,7 +17,7 @@ extern int ramfs_nommu_mmap(struct file *file, struct vm_area_struct *vma); #endif extern const struct file_operations ramfs_file_operations; -extern struct vm_operations_struct generic_file_vm_ops; +extern const struct vm_operations_struct generic_file_vm_ops; extern int __init init_rootfs(void); #endif diff --git a/ipc/shm.c b/ipc/shm.c index 9eb1488b543b..464694e0aa4a 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -55,7 +55,7 @@ struct shm_file_data { #define shm_file_data(file) (*((struct shm_file_data **)&(file)->private_data)) static const struct file_operations shm_file_operations; -static struct vm_operations_struct shm_vm_ops; +static const struct vm_operations_struct shm_vm_ops; #define shm_ids(ns) ((ns)->ids[IPC_SHM_IDS]) @@ -312,7 +312,7 @@ static const struct file_operations shm_file_operations = { .get_unmapped_area = shm_get_unmapped_area, }; -static struct vm_operations_struct shm_vm_ops = { +static const struct vm_operations_struct shm_vm_ops = { .open = shm_open, /* callback for a new vm-area open */ .close = shm_close, /* callback for when the vm-area is released */ .fault = shm_fault, diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 76ac4db405e9..0f86feb6db0c 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -2253,7 +2253,7 @@ static void perf_mmap_close(struct vm_area_struct *vma) } } -static struct vm_operations_struct perf_mmap_vmops = { +static const struct vm_operations_struct perf_mmap_vmops = { .open = perf_mmap_open, .close = perf_mmap_close, .fault = perf_mmap_fault, diff --git a/kernel/relay.c b/kernel/relay.c index bc188549788f..760c26209a3c 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -60,7 +60,7 @@ static int relay_buf_fault(struct vm_area_struct *vma, struct vm_fault *vmf) /* * vm_ops for relay file mappings. */ -static struct vm_operations_struct relay_file_mmap_ops = { +static const struct vm_operations_struct relay_file_mmap_ops = { .fault = relay_buf_fault, .close = relay_file_mmap_close, }; diff --git a/mm/filemap.c b/mm/filemap.c index 6c84e598b4a9..ef169f37156d 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1611,7 +1611,7 @@ page_not_uptodate: } EXPORT_SYMBOL(filemap_fault); -struct vm_operations_struct generic_file_vm_ops = { +const struct vm_operations_struct generic_file_vm_ops = { .fault = filemap_fault, }; diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c index 427dfe3ce78c..1888b2d71bb8 100644 --- a/mm/filemap_xip.c +++ b/mm/filemap_xip.c @@ -296,7 +296,7 @@ out: } } -static struct vm_operations_struct xip_file_vm_ops = { +static const struct vm_operations_struct xip_file_vm_ops = { .fault = xip_file_fault, }; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 6f048fcc749c..5d7601b02874 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1721,7 +1721,7 @@ static int hugetlb_vm_op_fault(struct vm_area_struct *vma, struct vm_fault *vmf) return 0; } -struct vm_operations_struct hugetlb_vm_ops = { +const struct vm_operations_struct hugetlb_vm_ops = { .fault = hugetlb_vm_op_fault, .open = hugetlb_vm_op_open, .close = hugetlb_vm_op_close, diff --git a/mm/mmap.c b/mm/mmap.c index 21d4029a07b3..73f5e4b64010 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2282,7 +2282,7 @@ static void special_mapping_close(struct vm_area_struct *vma) { } -static struct vm_operations_struct special_mapping_vmops = { +static const struct vm_operations_struct special_mapping_vmops = { .close = special_mapping_close, .fault = special_mapping_fault, }; diff --git a/mm/nommu.c b/mm/nommu.c index c73aa4753d79..5189b5aed8c0 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -79,7 +79,7 @@ static struct kmem_cache *vm_region_jar; struct rb_root nommu_region_tree = RB_ROOT; DECLARE_RWSEM(nommu_region_sem); -struct vm_operations_struct generic_file_vm_ops = { +const struct vm_operations_struct generic_file_vm_ops = { }; /* diff --git a/mm/shmem.c b/mm/shmem.c index ccf446a9faa1..356dd99566ec 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -218,7 +218,7 @@ static const struct file_operations shmem_file_operations; static const struct inode_operations shmem_inode_operations; static const struct inode_operations shmem_dir_inode_operations; static const struct inode_operations shmem_special_inode_operations; -static struct vm_operations_struct shmem_vm_ops; +static const struct vm_operations_struct shmem_vm_ops; static struct backing_dev_info shmem_backing_dev_info __read_mostly = { .ra_pages = 0, /* No readahead */ @@ -2498,7 +2498,7 @@ static const struct super_operations shmem_ops = { .put_super = shmem_put_super, }; -static struct vm_operations_struct shmem_vm_ops = { +static const struct vm_operations_struct shmem_vm_ops = { .fault = shmem_fault, #ifdef CONFIG_NUMA .set_policy = shmem_set_policy, diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index d3d52c66cdc2..103d5611b818 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2084,7 +2084,7 @@ static void packet_mm_close(struct vm_area_struct *vma) atomic_dec(&pkt_sk(sk)->mapped); } -static struct vm_operations_struct packet_mmap_ops = { +static const struct vm_operations_struct packet_mmap_ops = { .open = packet_mm_open, .close = packet_mm_close, }; diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 561d6d95a2d3..ab73edf2c89a 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -2985,7 +2985,7 @@ static int snd_pcm_mmap_status_fault(struct vm_area_struct *area, return 0; } -static struct vm_operations_struct snd_pcm_vm_ops_status = +static const struct vm_operations_struct snd_pcm_vm_ops_status = { .fault = snd_pcm_mmap_status_fault, }; @@ -3024,7 +3024,7 @@ static int snd_pcm_mmap_control_fault(struct vm_area_struct *area, return 0; } -static struct vm_operations_struct snd_pcm_vm_ops_control = +static const struct vm_operations_struct snd_pcm_vm_ops_control = { .fault = snd_pcm_mmap_control_fault, }; @@ -3094,7 +3094,7 @@ static int snd_pcm_mmap_data_fault(struct vm_area_struct *area, return 0; } -static struct vm_operations_struct snd_pcm_vm_ops_data = +static const struct vm_operations_struct snd_pcm_vm_ops_data = { .open = snd_pcm_mmap_data_open, .close = snd_pcm_mmap_data_close, @@ -3118,7 +3118,7 @@ static int snd_pcm_default_mmap(struct snd_pcm_substream *substream, * mmap the DMA buffer on I/O memory area */ #if SNDRV_PCM_INFO_MMAP_IOMEM -static struct vm_operations_struct snd_pcm_vm_ops_data_mmio = +static const struct vm_operations_struct snd_pcm_vm_ops_data_mmio = { .open = snd_pcm_mmap_data_open, .close = snd_pcm_mmap_data_close, diff --git a/sound/usb/usx2y/us122l.c b/sound/usb/usx2y/us122l.c index fd44946ce4b3..99f33766cd51 100644 --- a/sound/usb/usx2y/us122l.c +++ b/sound/usb/usx2y/us122l.c @@ -154,7 +154,7 @@ static void usb_stream_hwdep_vm_close(struct vm_area_struct *area) snd_printdd(KERN_DEBUG "%i\n", atomic_read(&us122l->mmap_count)); } -static struct vm_operations_struct usb_stream_hwdep_vm_ops = { +static const struct vm_operations_struct usb_stream_hwdep_vm_ops = { .open = usb_stream_hwdep_vm_open, .fault = usb_stream_hwdep_vm_fault, .close = usb_stream_hwdep_vm_close, diff --git a/sound/usb/usx2y/usX2Yhwdep.c b/sound/usb/usx2y/usX2Yhwdep.c index f3d8f71265dd..52e04b2f35d3 100644 --- a/sound/usb/usx2y/usX2Yhwdep.c +++ b/sound/usb/usx2y/usX2Yhwdep.c @@ -53,7 +53,7 @@ static int snd_us428ctls_vm_fault(struct vm_area_struct *area, return 0; } -static struct vm_operations_struct us428ctls_vm_ops = { +static const struct vm_operations_struct us428ctls_vm_ops = { .fault = snd_us428ctls_vm_fault, }; diff --git a/sound/usb/usx2y/usx2yhwdeppcm.c b/sound/usb/usx2y/usx2yhwdeppcm.c index 117946f2debb..4b2304c2e02d 100644 --- a/sound/usb/usx2y/usx2yhwdeppcm.c +++ b/sound/usb/usx2y/usx2yhwdeppcm.c @@ -697,7 +697,7 @@ static int snd_usX2Y_hwdep_pcm_vm_fault(struct vm_area_struct *area, } -static struct vm_operations_struct snd_usX2Y_hwdep_pcm_vm_ops = { +static const struct vm_operations_struct snd_usX2Y_hwdep_pcm_vm_ops = { .open = snd_usX2Y_hwdep_pcm_vm_open, .close = snd_usX2Y_hwdep_pcm_vm_close, .fault = snd_usX2Y_hwdep_pcm_vm_fault, diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 034a798b0431..b5e7e3f1183f 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1713,7 +1713,7 @@ static int kvm_vcpu_fault(struct vm_area_struct *vma, struct vm_fault *vmf) return 0; } -static struct vm_operations_struct kvm_vcpu_vm_ops = { +static const struct vm_operations_struct kvm_vcpu_vm_ops = { .fault = kvm_vcpu_fault, }; @@ -2317,7 +2317,7 @@ static int kvm_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf) return 0; } -static struct vm_operations_struct kvm_vm_vm_ops = { +static const struct vm_operations_struct kvm_vm_vm_ops = { .fault = kvm_vm_fault, }; -- cgit v1.2.3 From 06808b0827e1cd14eedc96bac2655d5b37ac246c Mon Sep 17 00:00:00 2001 From: Lee Schermerhorn Date: Mon, 14 Dec 2009 17:58:21 -0800 Subject: hugetlb: derive huge pages nodes allowed from task mempolicy This patch derives a "nodes_allowed" node mask from the numa mempolicy of the task modifying the number of persistent huge pages to control the allocation, freeing and adjusting of surplus huge pages when the pool page count is modified via the new sysctl or sysfs attribute "nr_hugepages_mempolicy". The nodes_allowed mask is derived as follows: * For "default" [NULL] task mempolicy, a NULL nodemask_t pointer is produced. This will cause the hugetlb subsystem to use node_online_map as the "nodes_allowed". This preserves the behavior before this patch. * For "preferred" mempolicy, including explicit local allocation, a nodemask with the single preferred node will be produced. "local" policy will NOT track any internode migrations of the task adjusting nr_hugepages. * For "bind" and "interleave" policy, the mempolicy's nodemask will be used. * Other than to inform the construction of the nodes_allowed node mask, the actual mempolicy mode is ignored. That is, all modes behave like interleave over the resulting nodes_allowed mask with no "fallback". See the updated documentation [next patch] for more information about the implications of this patch. Examples: Starting with: Node 0 HugePages_Total: 0 Node 1 HugePages_Total: 0 Node 2 HugePages_Total: 0 Node 3 HugePages_Total: 0 Default behavior [with or without this patch] balances persistent hugepage allocation across nodes [with sufficient contiguous memory]: sysctl vm.nr_hugepages[_mempolicy]=32 yields: Node 0 HugePages_Total: 8 Node 1 HugePages_Total: 8 Node 2 HugePages_Total: 8 Node 3 HugePages_Total: 8 Of course, we only have nr_hugepages_mempolicy with the patch, but with default mempolicy, nr_hugepages_mempolicy behaves the same as nr_hugepages. Applying mempolicy--e.g., with numactl [using '-m' a.k.a. '--membind' because it allows multiple nodes to be specified and it's easy to type]--we can allocate huge pages on individual nodes or sets of nodes. So, starting from the condition above, with 8 huge pages per node, add 8 more to node 2 using: numactl -m 2 sysctl vm.nr_hugepages_mempolicy=40 This yields: Node 0 HugePages_Total: 8 Node 1 HugePages_Total: 8 Node 2 HugePages_Total: 16 Node 3 HugePages_Total: 8 The incremental 8 huge pages were restricted to node 2 by the specified mempolicy. Similarly, we can use mempolicy to free persistent huge pages from specified nodes: numactl -m 0,1 sysctl vm.nr_hugepages_mempolicy=32 yields: Node 0 HugePages_Total: 4 Node 1 HugePages_Total: 4 Node 2 HugePages_Total: 16 Node 3 HugePages_Total: 8 The 8 huge pages freed were balanced over nodes 0 and 1. [rientjes@google.com: accomodate reworked NODEMASK_ALLOC] Signed-off-by: David Rientjes Signed-off-by: Lee Schermerhorn Acked-by: Mel Gorman Reviewed-by: Andi Kleen Cc: KAMEZAWA Hiroyuki Cc: Randy Dunlap Cc: Nishanth Aravamudan Cc: Adam Litke Cc: Andy Whitcroft Cc: Eric Whitney Cc: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 6 +++ include/linux/mempolicy.h | 3 ++ kernel/sysctl.c | 15 +++++++- mm/hugetlb.c | 97 ++++++++++++++++++++++++++++++++++++++++------- mm/mempolicy.c | 47 +++++++++++++++++++++++ 5 files changed, 153 insertions(+), 15 deletions(-) (limited to 'include/linux/hugetlb.h') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 41a59afc70fa..78b4bc64c006 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -23,6 +23,12 @@ void reset_vma_resv_huge_pages(struct vm_area_struct *vma); 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 *); + +#ifdef CONFIG_NUMA +int hugetlb_mempolicy_sysctl_handler(struct ctl_table *, int, + void __user *, size_t *, loff_t *); +#endif + 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/mempolicy.h b/include/linux/mempolicy.h index 085c903fe0f1..1cc966cd3e5f 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -201,6 +201,7 @@ extern void mpol_fix_fork_child_flag(struct task_struct *p); extern struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, nodemask_t **nodemask); +extern bool init_nodemask_of_mempolicy(nodemask_t *mask); extern unsigned slab_node(struct mempolicy *policy); extern enum zone_type policy_zone; @@ -328,6 +329,8 @@ static inline struct zonelist *huge_zonelist(struct vm_area_struct *vma, return node_zonelist(0, gfp_flags); } +static inline bool init_nodemask_of_mempolicy(nodemask_t *m) { return false; } + static inline int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from_nodes, const nodemask_t *to_nodes, int flags) diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 554ac4894f0f..60fc93131095 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1051,7 +1051,7 @@ static struct ctl_table vm_table[] = { .extra2 = &one_hundred, }, #ifdef CONFIG_HUGETLB_PAGE - { + { .procname = "nr_hugepages", .data = NULL, .maxlen = sizeof(unsigned long), @@ -1059,7 +1059,18 @@ static struct ctl_table vm_table[] = { .proc_handler = hugetlb_sysctl_handler, .extra1 = (void *)&hugetlb_zero, .extra2 = (void *)&hugetlb_infinity, - }, + }, +#ifdef CONFIG_NUMA + { + .procname = "nr_hugepages_mempolicy", + .data = NULL, + .maxlen = sizeof(unsigned long), + .mode = 0644, + .proc_handler = &hugetlb_mempolicy_sysctl_handler, + .extra1 = (void *)&hugetlb_zero, + .extra2 = (void *)&hugetlb_infinity, + }, +#endif { .procname = "hugetlb_shm_group", .data = &sysctl_hugetlb_shm_group, diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 324d1abae876..1125d818ea06 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1330,29 +1330,71 @@ static struct hstate *kobj_to_hstate(struct kobject *kobj) return NULL; } -static ssize_t nr_hugepages_show(struct kobject *kobj, +static ssize_t nr_hugepages_show_common(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct hstate *h = kobj_to_hstate(kobj); return sprintf(buf, "%lu\n", h->nr_huge_pages); } -static ssize_t nr_hugepages_store(struct kobject *kobj, - struct kobj_attribute *attr, const char *buf, size_t count) +static ssize_t nr_hugepages_store_common(bool obey_mempolicy, + struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t len) { int err; - unsigned long input; + unsigned long count; struct hstate *h = kobj_to_hstate(kobj); + NODEMASK_ALLOC(nodemask_t, nodes_allowed); - err = strict_strtoul(buf, 10, &input); + err = strict_strtoul(buf, 10, &count); if (err) return 0; - h->max_huge_pages = set_max_huge_pages(h, input, &node_online_map); + if (!(obey_mempolicy && init_nodemask_of_mempolicy(nodes_allowed))) { + NODEMASK_FREE(nodes_allowed); + nodes_allowed = &node_online_map; + } + h->max_huge_pages = set_max_huge_pages(h, count, nodes_allowed); - return count; + if (nodes_allowed != &node_online_map) + NODEMASK_FREE(nodes_allowed); + + return len; +} + +static ssize_t nr_hugepages_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return nr_hugepages_show_common(kobj, attr, buf); +} + +static ssize_t nr_hugepages_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t len) +{ + return nr_hugepages_store_common(false, kobj, attr, buf, len); } HSTATE_ATTR(nr_hugepages); +#ifdef CONFIG_NUMA + +/* + * hstate attribute for optionally mempolicy-based constraint on persistent + * huge page alloc/free. + */ +static ssize_t nr_hugepages_mempolicy_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return nr_hugepages_show_common(kobj, attr, buf); +} + +static ssize_t nr_hugepages_mempolicy_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t len) +{ + return nr_hugepages_store_common(true, kobj, attr, buf, len); +} +HSTATE_ATTR(nr_hugepages_mempolicy); +#endif + + static ssize_t nr_overcommit_hugepages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { @@ -1408,6 +1450,9 @@ static struct attribute *hstate_attrs[] = { &free_hugepages_attr.attr, &resv_hugepages_attr.attr, &surplus_hugepages_attr.attr, +#ifdef CONFIG_NUMA + &nr_hugepages_mempolicy_attr.attr, +#endif NULL, }; @@ -1574,9 +1619,9 @@ static unsigned int cpuset_mems_nr(unsigned int *array) } #ifdef CONFIG_SYSCTL -int hugetlb_sysctl_handler(struct ctl_table *table, int write, - void __user *buffer, - size_t *length, loff_t *ppos) +static int hugetlb_sysctl_handler_common(bool obey_mempolicy, + struct ctl_table *table, int write, + void __user *buffer, size_t *length, loff_t *ppos) { struct hstate *h = &default_hstate; unsigned long tmp; @@ -1588,13 +1633,39 @@ int hugetlb_sysctl_handler(struct ctl_table *table, int write, table->maxlen = sizeof(unsigned long); proc_doulongvec_minmax(table, write, buffer, length, ppos); - if (write) - h->max_huge_pages = set_max_huge_pages(h, tmp, - &node_online_map); + if (write) { + NODEMASK_ALLOC(nodemask_t, nodes_allowed); + if (!(obey_mempolicy && + init_nodemask_of_mempolicy(nodes_allowed))) { + NODEMASK_FREE(nodes_allowed); + nodes_allowed = &node_states[N_HIGH_MEMORY]; + } + h->max_huge_pages = set_max_huge_pages(h, tmp, nodes_allowed); + + if (nodes_allowed != &node_states[N_HIGH_MEMORY]) + NODEMASK_FREE(nodes_allowed); + } return 0; } +int hugetlb_sysctl_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *length, loff_t *ppos) +{ + + return hugetlb_sysctl_handler_common(false, table, write, + buffer, length, ppos); +} + +#ifdef CONFIG_NUMA +int hugetlb_mempolicy_sysctl_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *length, loff_t *ppos) +{ + return hugetlb_sysctl_handler_common(true, table, write, + buffer, length, ppos); +} +#endif /* CONFIG_NUMA */ + int hugetlb_treat_movable_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 0f89eabbaf3e..f11fdad06204 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1568,6 +1568,53 @@ struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr, } return zl; } + +/* + * init_nodemask_of_mempolicy + * + * If the current task's mempolicy is "default" [NULL], return 'false' + * to indicate default policy. Otherwise, extract the policy nodemask + * for 'bind' or 'interleave' policy into the argument nodemask, or + * initialize the argument nodemask to contain the single node for + * 'preferred' or 'local' policy and return 'true' to indicate presence + * of non-default mempolicy. + * + * We don't bother with reference counting the mempolicy [mpol_get/put] + * because the current task is examining it's own mempolicy and a task's + * mempolicy is only ever changed by the task itself. + * + * N.B., it is the caller's responsibility to free a returned nodemask. + */ +bool init_nodemask_of_mempolicy(nodemask_t *mask) +{ + struct mempolicy *mempolicy; + int nid; + + if (!(mask && current->mempolicy)) + return false; + + mempolicy = current->mempolicy; + switch (mempolicy->mode) { + case MPOL_PREFERRED: + if (mempolicy->flags & MPOL_F_LOCAL) + nid = numa_node_id(); + else + nid = mempolicy->v.preferred_node; + init_nodemask_of_node(mask, nid); + break; + + case MPOL_BIND: + /* Fall through */ + case MPOL_INTERLEAVE: + *mask = mempolicy->v.nodes; + break; + + default: + BUG(); + } + + return true; +} #endif /* Allocate a page in interleaved policy. -- cgit v1.2.3 From 8edf344c66a3f214d709dad1421c29d678915b3f Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Fri, 28 May 2010 09:29:15 +0900 Subject: hugetlb: move definition of is_vm_hugetlb_page() to hugepage_inline.h is_vm_hugetlb_page() is a widely used inline function to insert hooks into hugetlb code. But we can't use it in pagemap.h because of circular dependency of the header files. This patch removes this limitation. Acked-by: Mel Gorman Acked-by: Fengguang Wu Signed-off-by: Naoya Horiguchi Signed-off-by: Andi Kleen --- include/linux/hugetlb.h | 11 +---------- include/linux/hugetlb_inline.h | 22 ++++++++++++++++++++++ include/linux/pagemap.h | 1 + 3 files changed, 24 insertions(+), 10 deletions(-) create mode 100644 include/linux/hugetlb_inline.h (limited to 'include/linux/hugetlb.h') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 78b4bc64c006..d47a7c41745d 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -2,6 +2,7 @@ #define _LINUX_HUGETLB_H #include +#include struct ctl_table; struct user_struct; @@ -14,11 +15,6 @@ struct user_struct; int PageHuge(struct page *page); -static inline int is_vm_hugetlb_page(struct vm_area_struct *vma) -{ - return vma->vm_flags & VM_HUGETLB; -} - void reset_vma_resv_huge_pages(struct vm_area_struct *vma); 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 *); @@ -77,11 +73,6 @@ static inline int PageHuge(struct page *page) return 0; } -static inline int is_vm_hugetlb_page(struct vm_area_struct *vma) -{ - return 0; -} - static inline void reset_vma_resv_huge_pages(struct vm_area_struct *vma) { } diff --git a/include/linux/hugetlb_inline.h b/include/linux/hugetlb_inline.h new file mode 100644 index 000000000000..cf00b6df53dc --- /dev/null +++ b/include/linux/hugetlb_inline.h @@ -0,0 +1,22 @@ +#ifndef _LINUX_HUGETLB_INLINE_H +#define _LINUX_HUGETLB_INLINE_H 1 + +#ifdef CONFIG_HUGETLBFS + +#include + +static inline int is_vm_hugetlb_page(struct vm_area_struct *vma) +{ + return vma->vm_flags & VM_HUGETLB; +} + +#else + +static inline int is_vm_hugetlb_page(struct vm_area_struct *vma) +{ + return 0; +} + +#endif + +#endif diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 3c62ed408492..b2bd2bae9775 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -13,6 +13,7 @@ #include #include #include /* for in_interrupt() */ +#include /* * Bits in mapping->flags. The lower __GFP_BITS_SHIFT bits are the page -- cgit v1.2.3 From 0fe6e20b9c4c53b3e97096ee73a0857f60aad43f Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Fri, 28 May 2010 09:29:16 +0900 Subject: hugetlb, rmap: add reverse mapping for hugepage This patch adds reverse mapping feature for hugepage by introducing mapcount for shared/private-mapped hugepage and anon_vma for private-mapped hugepage. While hugepage is not currently swappable, reverse mapping can be useful for memory error handler. Without this patch, memory error handler cannot identify processes using the bad hugepage nor unmap it from them. That is: - for shared hugepage: we can collect processes using a hugepage through pagecache, but can not unmap the hugepage because of the lack of mapcount. - for privately mapped hugepage: we can neither collect processes nor unmap the hugepage. This patch solves these problems. This patch include the bug fix given by commit 23be7468e8, so reverts it. Dependency: "hugetlb: move definition of is_vm_hugetlb_page() to hugepage_inline.h" ChangeLog since May 24. - create hugetlb_inline.h and move is_vm_hugetlb_index() in it. - move functions setting up anon_vma for hugepage into mm/rmap.c. ChangeLog since May 13. - rebased to 2.6.34 - fix logic error (in case that private mapping and shared mapping coexist) - move is_vm_hugetlb_page() into include/linux/mm.h to use this function from linear_page_index() - define and use linear_hugepage_index() instead of compound_order() - use page_move_anon_rmap() in hugetlb_cow() - copy exclusive switch of __set_page_anon_rmap() into hugepage counterpart. - revert commit 24be7468 completely Signed-off-by: Naoya Horiguchi Cc: Andi Kleen Cc: Andrew Morton Cc: Mel Gorman Cc: Andrea Arcangeli Cc: Larry Woodman Cc: Lee Schermerhorn Acked-by: Fengguang Wu Acked-by: Mel Gorman Signed-off-by: Andi Kleen --- include/linux/hugetlb.h | 1 + include/linux/pagemap.h | 8 ++++++- include/linux/poison.h | 9 -------- include/linux/rmap.h | 5 +++++ mm/hugetlb.c | 44 ++++++++++++++++++++++++++++++++++-- mm/rmap.c | 59 +++++++++++++++++++++++++++++++++++++++++++++++++ 6 files changed, 114 insertions(+), 12 deletions(-) (limited to 'include/linux/hugetlb.h') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index d47a7c41745d..e688fd89354d 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -99,6 +99,7 @@ static inline void hugetlb_report_meminfo(struct seq_file *m) #define is_hugepage_only_range(mm, addr, len) 0 #define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) ({BUG(); 0; }) #define hugetlb_fault(mm, vma, addr, flags) ({ BUG(); 0; }) +#define huge_pte_offset(mm, address) 0 #define hugetlb_change_protection(vma, address, end, newprot) diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index b2bd2bae9775..a547d9689170 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -282,10 +282,16 @@ static inline loff_t page_offset(struct page *page) return ((loff_t)page->index) << PAGE_CACHE_SHIFT; } +extern pgoff_t linear_hugepage_index(struct vm_area_struct *vma, + unsigned long address); + static inline pgoff_t linear_page_index(struct vm_area_struct *vma, unsigned long address) { - pgoff_t pgoff = (address - vma->vm_start) >> PAGE_SHIFT; + pgoff_t pgoff; + if (unlikely(is_vm_hugetlb_page(vma))) + return linear_hugepage_index(vma, address); + pgoff = (address - vma->vm_start) >> PAGE_SHIFT; pgoff += vma->vm_pgoff; return pgoff >> (PAGE_CACHE_SHIFT - PAGE_SHIFT); } diff --git a/include/linux/poison.h b/include/linux/poison.h index 34066ffd893d..2110a81c5e2a 100644 --- a/include/linux/poison.h +++ b/include/linux/poison.h @@ -48,15 +48,6 @@ #define POISON_FREE 0x6b /* for use-after-free poisoning */ #define POISON_END 0xa5 /* end-byte of poisoning */ -/********** mm/hugetlb.c **********/ -/* - * Private mappings of hugetlb pages use this poisoned value for - * page->mapping. The core VM should not be doing anything with this mapping - * but futex requires the existence of some page->mapping value even though it - * is unused if PAGE_MAPPING_ANON is set. - */ -#define HUGETLB_POISON ((void *)(0x00300300 + POISON_POINTER_DELTA + PAGE_MAPPING_ANON)) - /********** arch/$ARCH/mm/init.c **********/ #define POISON_FREE_INITMEM 0xcc diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 77216742c178..9d50e7ef5f5a 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -140,6 +140,11 @@ void page_add_new_anon_rmap(struct page *, struct vm_area_struct *, unsigned lon void page_add_file_rmap(struct page *); void page_remove_rmap(struct page *); +void hugepage_add_anon_rmap(struct page *, struct vm_area_struct *, + unsigned long); +void hugepage_add_new_anon_rmap(struct page *, struct vm_area_struct *, + unsigned long); + static inline void page_dup_rmap(struct page *page) { atomic_inc(&page->_mapcount); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 54d42b009dbe..aa3c51739378 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include @@ -220,6 +221,12 @@ static pgoff_t vma_hugecache_offset(struct hstate *h, (vma->vm_pgoff >> huge_page_order(h)); } +pgoff_t linear_hugepage_index(struct vm_area_struct *vma, + unsigned long address) +{ + return vma_hugecache_offset(hstate_vma(vma), vma, address); +} + /* * Return the size of the pages allocated when backing a VMA. In the majority * cases this will be same size as used by the page table entries. @@ -552,6 +559,7 @@ static void free_huge_page(struct page *page) set_page_private(page, 0); page->mapping = NULL; BUG_ON(page_count(page)); + BUG_ON(page_mapcount(page)); INIT_LIST_HEAD(&page->lru); spin_lock(&hugetlb_lock); @@ -2129,6 +2137,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, entry = huge_ptep_get(src_pte); ptepage = pte_page(entry); get_page(ptepage); + page_dup_rmap(ptepage); set_huge_pte_at(dst, addr, dst_pte, entry); } spin_unlock(&src->page_table_lock); @@ -2207,6 +2216,7 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, flush_tlb_range(vma, start, end); mmu_notifier_invalidate_range_end(mm, start, end); list_for_each_entry_safe(page, tmp, &page_list, lru) { + page_remove_rmap(page); list_del(&page->lru); put_page(page); } @@ -2272,6 +2282,9 @@ static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma, return 1; } +/* + * Hugetlb_cow() should be called with page lock of the original hugepage held. + */ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pte_t *ptep, pte_t pte, struct page *pagecache_page) @@ -2286,8 +2299,11 @@ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma, retry_avoidcopy: /* If no-one else is actually using this page, avoid the copy * and just make the page writable */ - avoidcopy = (page_count(old_page) == 1); + avoidcopy = (page_mapcount(old_page) == 1); if (avoidcopy) { + if (!trylock_page(old_page)) + if (PageAnon(old_page)) + page_move_anon_rmap(old_page, vma, address); set_huge_ptep_writable(vma, address, ptep); return 0; } @@ -2338,6 +2354,13 @@ retry_avoidcopy: return -PTR_ERR(new_page); } + /* + * When the original hugepage is shared one, it does not have + * anon_vma prepared. + */ + if (unlikely(anon_vma_prepare(vma))) + return VM_FAULT_OOM; + copy_huge_page(new_page, old_page, address, vma); __SetPageUptodate(new_page); @@ -2352,6 +2375,8 @@ retry_avoidcopy: huge_ptep_clear_flush(vma, address, ptep); set_huge_pte_at(mm, address, ptep, make_huge_pte(vma, new_page, 1)); + page_remove_rmap(old_page); + hugepage_add_anon_rmap(new_page, vma, address); /* Make the old page be freed below */ new_page = old_page; } @@ -2452,10 +2477,17 @@ retry: spin_lock(&inode->i_lock); inode->i_blocks += blocks_per_huge_page(h); spin_unlock(&inode->i_lock); + page_dup_rmap(page); } else { lock_page(page); - page->mapping = HUGETLB_POISON; + if (unlikely(anon_vma_prepare(vma))) { + ret = VM_FAULT_OOM; + goto backout_unlocked; + } + hugepage_add_new_anon_rmap(page, vma, address); } + } else { + page_dup_rmap(page); } /* @@ -2507,6 +2539,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, pte_t *ptep; pte_t entry; int ret; + struct page *page = NULL; struct page *pagecache_page = NULL; static DEFINE_MUTEX(hugetlb_instantiation_mutex); struct hstate *h = hstate_vma(vma); @@ -2548,6 +2581,11 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, vma, address); } + if (!pagecache_page) { + page = pte_page(entry); + lock_page(page); + } + spin_lock(&mm->page_table_lock); /* Check for a racing update before calling hugetlb_cow */ if (unlikely(!pte_same(entry, huge_ptep_get(ptep)))) @@ -2573,6 +2611,8 @@ out_page_table_lock: if (pagecache_page) { unlock_page(pagecache_page); put_page(pagecache_page); + } else { + unlock_page(page); } out_mutex: diff --git a/mm/rmap.c b/mm/rmap.c index 38a336e2eea1..0ad53572eaf2 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -56,6 +56,7 @@ #include #include #include +#include #include @@ -326,6 +327,8 @@ vma_address(struct page *page, struct vm_area_struct *vma) pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); unsigned long address; + if (unlikely(is_vm_hugetlb_page(vma))) + pgoff = page->index << huge_page_order(page_hstate(page)); address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); if (unlikely(address < vma->vm_start || address >= vma->vm_end)) { /* page should be within @vma mapping range */ @@ -369,6 +372,12 @@ pte_t *page_check_address(struct page *page, struct mm_struct *mm, pte_t *pte; spinlock_t *ptl; + if (unlikely(PageHuge(page))) { + pte = huge_pte_offset(mm, address); + ptl = &mm->page_table_lock; + goto check; + } + pgd = pgd_offset(mm, address); if (!pgd_present(*pgd)) return NULL; @@ -389,6 +398,7 @@ pte_t *page_check_address(struct page *page, struct mm_struct *mm, } ptl = pte_lockptr(mm, pmd); +check: spin_lock(ptl); if (pte_present(*pte) && page_to_pfn(page) == pte_pfn(*pte)) { *ptlp = ptl; @@ -873,6 +883,12 @@ void page_remove_rmap(struct page *page) page_clear_dirty(page); set_page_dirty(page); } + /* + * Hugepages are not counted in NR_ANON_PAGES nor NR_FILE_MAPPED + * and not charged by memcg for now. + */ + if (unlikely(PageHuge(page))) + return; if (PageAnon(page)) { mem_cgroup_uncharge_page(page); __dec_zone_page_state(page, NR_ANON_PAGES); @@ -1445,3 +1461,46 @@ int rmap_walk(struct page *page, int (*rmap_one)(struct page *, return rmap_walk_file(page, rmap_one, arg); } #endif /* CONFIG_MIGRATION */ + +#ifdef CONFIG_HUGETLBFS +/* + * The following three functions are for anonymous (private mapped) hugepages. + * Unlike common anonymous pages, anonymous hugepages have no accounting code + * and no lru code, because we handle hugepages differently from common pages. + */ +static void __hugepage_set_anon_rmap(struct page *page, + struct vm_area_struct *vma, unsigned long address, int exclusive) +{ + struct anon_vma *anon_vma = vma->anon_vma; + BUG_ON(!anon_vma); + if (!exclusive) { + struct anon_vma_chain *avc; + avc = list_entry(vma->anon_vma_chain.prev, + struct anon_vma_chain, same_vma); + anon_vma = avc->anon_vma; + } + anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON; + page->mapping = (struct address_space *) anon_vma; + page->index = linear_page_index(vma, address); +} + +void hugepage_add_anon_rmap(struct page *page, + struct vm_area_struct *vma, unsigned long address) +{ + struct anon_vma *anon_vma = vma->anon_vma; + int first; + BUG_ON(!anon_vma); + BUG_ON(address < vma->vm_start || address >= vma->vm_end); + first = atomic_inc_and_test(&page->_mapcount); + if (first) + __hugepage_set_anon_rmap(page, vma, address, 0); +} + +void hugepage_add_new_anon_rmap(struct page *page, + struct vm_area_struct *vma, unsigned long address) +{ + BUG_ON(address < vma->vm_start || address >= vma->vm_end); + atomic_set(&page->_mapcount, 0); + __hugepage_set_anon_rmap(page, vma, address, 1); +} +#endif /* CONFIG_HUGETLBFS */ -- cgit v1.2.3 From 93f70f900da36fbc19c13c2aa04b2e468c8d00fb Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Fri, 28 May 2010 09:29:20 +0900 Subject: HWPOISON, hugetlb: isolate corrupted hugepage If error hugepage is not in-use, we can fully recovery from error by dequeuing it from freelist, so return RECOVERY. Otherwise whether or not we can recovery depends on user processes, so return DELAYED. Dependency: "HWPOISON, hugetlb: enable error handling path for hugepage" Signed-off-by: Naoya Horiguchi Cc: Andrew Morton Acked-by: Fengguang Wu Signed-off-by: Andi Kleen --- include/linux/hugetlb.h | 2 ++ mm/hugetlb.c | 16 ++++++++++++++++ mm/memory-failure.c | 28 ++++++++++++++++++++-------- 3 files changed, 38 insertions(+), 8 deletions(-) (limited to 'include/linux/hugetlb.h') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index e688fd89354d..f479700df61b 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -43,6 +43,7 @@ int hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_struct *vma, int acctflags); void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed); +void __isolate_hwpoisoned_huge_page(struct page *page); extern unsigned long hugepages_treat_as_movable; extern const unsigned long hugetlb_zero, hugetlb_infinity; @@ -100,6 +101,7 @@ static inline void hugetlb_report_meminfo(struct seq_file *m) #define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) ({BUG(); 0; }) #define hugetlb_fault(mm, vma, addr, flags) ({ BUG(); 0; }) #define huge_pte_offset(mm, address) 0 +#define __isolate_hwpoisoned_huge_page(page) 0 #define hugetlb_change_protection(vma, address, end, newprot) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index aa3c51739378..8c163f64cf10 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2825,3 +2825,19 @@ void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed) hugetlb_put_quota(inode->i_mapping, (chg - freed)); hugetlb_acct_memory(h, -(chg - freed)); } + +/* + * This function is called from memory failure code. + * Assume the caller holds page lock of the head page. + */ +void __isolate_hwpoisoned_huge_page(struct page *hpage) +{ + struct hstate *h = page_hstate(hpage); + int nid = page_to_nid(hpage); + + spin_lock(&hugetlb_lock); + list_del(&hpage->lru); + h->free_huge_pages--; + h->free_huge_pages_node[nid]--; + spin_unlock(&hugetlb_lock); +} diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 473f15a3356d..d0b420aba726 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -690,17 +690,29 @@ static int me_swapcache_clean(struct page *p, unsigned long pfn) /* * Huge pages. Needs work. * Issues: - * No rmap support so we cannot find the original mapper. In theory could walk - * all MMs and look for the mappings, but that would be non atomic and racy. - * Need rmap for hugepages for this. Alternatively we could employ a heuristic, - * like just walking the current process and hoping it has it mapped (that - * should be usually true for the common "shared database cache" case) - * Should handle free huge pages and dequeue them too, but this needs to - * handle huge page accounting correctly. + * - Error on hugepage is contained in hugepage unit (not in raw page unit.) + * To narrow down kill region to one page, we need to break up pmd. + * - To support soft-offlining for hugepage, we need to support hugepage + * migration. */ static int me_huge_page(struct page *p, unsigned long pfn) { - return FAILED; + struct page *hpage = compound_head(p); + /* + * We can safely recover from error on free or reserved (i.e. + * not in-use) hugepage by dequeuing it from freelist. + * To check whether a hugepage is in-use or not, we can't use + * page->lru because it can be used in other hugepage operations, + * such as __unmap_hugepage_range() and gather_surplus_pages(). + * So instead we use page_mapping() and PageAnon(). + * We assume that this function is called with page lock held, + * so there is no race between isolation and mapping/unmapping. + */ + if (!(page_mapping(hpage) || PageAnon(hpage))) { + __isolate_hwpoisoned_huge_page(hpage); + return RECOVERED; + } + return DELAYED; } /* -- cgit v1.2.3 From bf50bab2b34483316162443587b8467952e07730 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Wed, 8 Sep 2010 10:19:33 +0900 Subject: hugetlb: add allocate function for hugepage migration We can't use existing hugepage allocation functions to allocate hugepage for page migration, because page migration can happen asynchronously with the running processes and page migration users should call the allocation function with physical addresses (not virtual addresses) as arguments. ChangeLog since v3: - unify alloc_buddy_huge_page() and alloc_buddy_huge_page_node() ChangeLog since v2: - remove unnecessary get/put_mems_allowed() (thanks to David Rientjes) ChangeLog since v1: - add comment on top of alloc_huge_page_no_vma() Signed-off-by: Naoya Horiguchi Acked-by: Mel Gorman Signed-off-by: Jun'ichi Nomura Reviewed-by: Christoph Lameter Signed-off-by: Andi Kleen --- include/linux/hugetlb.h | 3 ++ mm/hugetlb.c | 79 +++++++++++++++++++++++++++++++++---------------- 2 files changed, 57 insertions(+), 25 deletions(-) (limited to 'include/linux/hugetlb.h') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index f479700df61b..0b73c536afd2 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -228,6 +228,8 @@ struct huge_bootmem_page { struct hstate *hstate; }; +struct page *alloc_huge_page_node(struct hstate *h, int nid); + /* arch callback */ int __init alloc_bootmem_huge_page(struct hstate *h); @@ -303,6 +305,7 @@ static inline struct hstate *page_hstate(struct page *page) #else struct hstate {}; +#define alloc_huge_page_node(h, nid) NULL #define alloc_bootmem_huge_page(h) NULL #define hstate_file(f) NULL #define hstate_vma(v) NULL diff --git a/mm/hugetlb.c b/mm/hugetlb.c index bd031a4c738e..83fa0c3b6e2b 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -466,11 +466,23 @@ static void enqueue_huge_page(struct hstate *h, struct page *page) h->free_huge_pages_node[nid]++; } +static struct page *dequeue_huge_page_node(struct hstate *h, int nid) +{ + struct page *page; + + if (list_empty(&h->hugepage_freelists[nid])) + return NULL; + page = list_entry(h->hugepage_freelists[nid].next, struct page, lru); + list_del(&page->lru); + h->free_huge_pages--; + h->free_huge_pages_node[nid]--; + return page; +} + static struct page *dequeue_huge_page_vma(struct hstate *h, struct vm_area_struct *vma, unsigned long address, int avoid_reserve) { - int nid; struct page *page = NULL; struct mempolicy *mpol; nodemask_t *nodemask; @@ -496,19 +508,13 @@ static struct page *dequeue_huge_page_vma(struct hstate *h, for_each_zone_zonelist_nodemask(zone, z, zonelist, MAX_NR_ZONES - 1, nodemask) { - nid = zone_to_nid(zone); - if (cpuset_zone_allowed_softwall(zone, htlb_alloc_mask) && - !list_empty(&h->hugepage_freelists[nid])) { - page = list_entry(h->hugepage_freelists[nid].next, - struct page, lru); - list_del(&page->lru); - h->free_huge_pages--; - h->free_huge_pages_node[nid]--; - - if (!avoid_reserve) - decrement_hugepage_resv_vma(h, vma); - - break; + if (cpuset_zone_allowed_softwall(zone, htlb_alloc_mask)) { + page = dequeue_huge_page_node(h, zone_to_nid(zone)); + if (page) { + if (!avoid_reserve) + decrement_hugepage_resv_vma(h, vma); + break; + } } } err: @@ -770,11 +776,10 @@ static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed, return ret; } -static struct page *alloc_buddy_huge_page(struct hstate *h, - struct vm_area_struct *vma, unsigned long address) +static struct page *alloc_buddy_huge_page(struct hstate *h, int nid) { struct page *page; - unsigned int nid; + unsigned int r_nid; if (h->order >= MAX_ORDER) return NULL; @@ -812,9 +817,14 @@ static struct page *alloc_buddy_huge_page(struct hstate *h, } spin_unlock(&hugetlb_lock); - page = alloc_pages(htlb_alloc_mask|__GFP_COMP| - __GFP_REPEAT|__GFP_NOWARN, - huge_page_order(h)); + if (nid == NUMA_NO_NODE) + page = alloc_pages(htlb_alloc_mask|__GFP_COMP| + __GFP_REPEAT|__GFP_NOWARN, + huge_page_order(h)); + else + page = alloc_pages_exact_node(nid, + htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE| + __GFP_REPEAT|__GFP_NOWARN, huge_page_order(h)); if (page && arch_prepare_hugepage(page)) { __free_pages(page, huge_page_order(h)); @@ -829,13 +839,13 @@ static struct page *alloc_buddy_huge_page(struct hstate *h, */ put_page_testzero(page); VM_BUG_ON(page_count(page)); - nid = page_to_nid(page); + r_nid = page_to_nid(page); set_compound_page_dtor(page, free_huge_page); /* * We incremented the global counters already */ - h->nr_huge_pages_node[nid]++; - h->surplus_huge_pages_node[nid]++; + h->nr_huge_pages_node[r_nid]++; + h->surplus_huge_pages_node[r_nid]++; __count_vm_event(HTLB_BUDDY_PGALLOC); } else { h->nr_huge_pages--; @@ -847,6 +857,25 @@ static struct page *alloc_buddy_huge_page(struct hstate *h, return page; } +/* + * This allocation function is useful in the context where vma is irrelevant. + * E.g. soft-offlining uses this function because it only cares physical + * address of error page. + */ +struct page *alloc_huge_page_node(struct hstate *h, int nid) +{ + struct page *page; + + spin_lock(&hugetlb_lock); + page = dequeue_huge_page_node(h, nid); + spin_unlock(&hugetlb_lock); + + if (!page) + page = alloc_buddy_huge_page(h, nid); + + return page; +} + /* * Increase the hugetlb pool such that it can accomodate a reservation * of size 'delta'. @@ -871,7 +900,7 @@ static int gather_surplus_pages(struct hstate *h, int delta) retry: spin_unlock(&hugetlb_lock); for (i = 0; i < needed; i++) { - page = alloc_buddy_huge_page(h, NULL, 0); + page = alloc_buddy_huge_page(h, NUMA_NO_NODE); if (!page) { /* * We were not able to allocate enough pages to @@ -1052,7 +1081,7 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma, spin_unlock(&hugetlb_lock); if (!page) { - page = alloc_buddy_huge_page(h, vma, addr); + page = alloc_buddy_huge_page(h, NUMA_NO_NODE); if (!page) { hugetlb_put_quota(inode->i_mapping, chg); return ERR_PTR(-VM_FAULT_SIGBUS); -- cgit v1.2.3 From 0ebabb416f585ace711769057422af4bbc9d1110 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Wed, 8 Sep 2010 10:19:34 +0900 Subject: hugetlb: redefine hugepage copy functions This patch modifies hugepage copy functions to have only destination and source hugepages as arguments for later use. The old ones are renamed from copy_{gigantic,huge}_page() to copy_user_{gigantic,huge}_page(). This naming convention is consistent with that between copy_highpage() and copy_user_highpage(). ChangeLog since v4: - add blank line between local declaration and code - remove unnecessary might_sleep() ChangeLog since v2: - change copy_huge_page() from macro to inline dummy function to avoid compile warning when !CONFIG_HUGETLB_PAGE. Signed-off-by: Naoya Horiguchi Acked-by: Mel Gorman Reviewed-by: Christoph Lameter Signed-off-by: Andi Kleen --- include/linux/hugetlb.h | 4 ++++ mm/hugetlb.c | 45 ++++++++++++++++++++++++++++++++++++++++----- 2 files changed, 44 insertions(+), 5 deletions(-) (limited to 'include/linux/hugetlb.h') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 0b73c536afd2..9e51f77d44ca 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -44,6 +44,7 @@ int hugetlb_reserve_pages(struct inode *inode, long from, long to, int acctflags); void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed); void __isolate_hwpoisoned_huge_page(struct page *page); +void copy_huge_page(struct page *dst, struct page *src); extern unsigned long hugepages_treat_as_movable; extern const unsigned long hugetlb_zero, hugetlb_infinity; @@ -102,6 +103,9 @@ static inline void hugetlb_report_meminfo(struct seq_file *m) #define hugetlb_fault(mm, vma, addr, flags) ({ BUG(); 0; }) #define huge_pte_offset(mm, address) 0 #define __isolate_hwpoisoned_huge_page(page) 0 +static inline void copy_huge_page(struct page *dst, struct page *src) +{ +} #define hugetlb_change_protection(vma, address, end, newprot) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 83fa0c3b6e2b..a73dbdcb89eb 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -423,14 +423,14 @@ static void clear_huge_page(struct page *page, } } -static void copy_gigantic_page(struct page *dst, struct page *src, +static void copy_user_gigantic_page(struct page *dst, struct page *src, unsigned long addr, struct vm_area_struct *vma) { int i; struct hstate *h = hstate_vma(vma); struct page *dst_base = dst; struct page *src_base = src; - might_sleep(); + for (i = 0; i < pages_per_huge_page(h); ) { cond_resched(); copy_user_highpage(dst, src, addr + i*PAGE_SIZE, vma); @@ -440,14 +440,15 @@ static void copy_gigantic_page(struct page *dst, struct page *src, src = mem_map_next(src, src_base, i); } } -static void copy_huge_page(struct page *dst, struct page *src, + +static void copy_user_huge_page(struct page *dst, struct page *src, unsigned long addr, struct vm_area_struct *vma) { int i; struct hstate *h = hstate_vma(vma); if (unlikely(pages_per_huge_page(h) > MAX_ORDER_NR_PAGES)) { - copy_gigantic_page(dst, src, addr, vma); + copy_user_gigantic_page(dst, src, addr, vma); return; } @@ -458,6 +459,40 @@ static void copy_huge_page(struct page *dst, struct page *src, } } +static void copy_gigantic_page(struct page *dst, struct page *src) +{ + int i; + struct hstate *h = page_hstate(src); + struct page *dst_base = dst; + struct page *src_base = src; + + for (i = 0; i < pages_per_huge_page(h); ) { + cond_resched(); + copy_highpage(dst, src); + + i++; + dst = mem_map_next(dst, dst_base, i); + src = mem_map_next(src, src_base, i); + } +} + +void copy_huge_page(struct page *dst, struct page *src) +{ + int i; + struct hstate *h = page_hstate(src); + + if (unlikely(pages_per_huge_page(h) > MAX_ORDER_NR_PAGES)) { + copy_gigantic_page(dst, src); + return; + } + + might_sleep(); + for (i = 0; i < pages_per_huge_page(h); i++) { + cond_resched(); + copy_highpage(dst + i, src + i); + } +} + static void enqueue_huge_page(struct hstate *h, struct page *page) { int nid = page_to_nid(page); @@ -2412,7 +2447,7 @@ retry_avoidcopy: if (unlikely(anon_vma_prepare(vma))) return VM_FAULT_OOM; - copy_huge_page(new_page, old_page, address, vma); + copy_user_huge_page(new_page, old_page, address, vma); __SetPageUptodate(new_page); /* -- cgit v1.2.3 From 6de2b1aab94355482bd2accdc115666509667458 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Wed, 8 Sep 2010 10:19:36 +0900 Subject: HWPOISON, hugetlb: add free check to dequeue_hwpoison_huge_page() This check is necessary to avoid race between dequeue and allocation, which can cause a free hugepage to be dequeued twice and get kernel unstable. Signed-off-by: Naoya Horiguchi Signed-off-by: Wu Fengguang Acked-by: Mel Gorman Reviewed-by: Christoph Lameter Signed-off-by: Andi Kleen --- include/linux/hugetlb.h | 4 ++-- mm/hugetlb.c | 29 +++++++++++++++++++++++++---- mm/memory-failure.c | 6 ++++-- 3 files changed, 31 insertions(+), 8 deletions(-) (limited to 'include/linux/hugetlb.h') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 9e51f77d44ca..796f30e00806 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -43,7 +43,7 @@ int hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_struct *vma, int acctflags); void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed); -void __isolate_hwpoisoned_huge_page(struct page *page); +int dequeue_hwpoisoned_huge_page(struct page *page); void copy_huge_page(struct page *dst, struct page *src); extern unsigned long hugepages_treat_as_movable; @@ -102,7 +102,7 @@ static inline void hugetlb_report_meminfo(struct seq_file *m) #define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) ({BUG(); 0; }) #define hugetlb_fault(mm, vma, addr, flags) ({ BUG(); 0; }) #define huge_pte_offset(mm, address) 0 -#define __isolate_hwpoisoned_huge_page(page) 0 +#define dequeue_hwpoisoned_huge_page(page) 0 static inline void copy_huge_page(struct page *dst, struct page *src) { } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 0fa9de8361bd..deb7bebefe68 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2955,18 +2955,39 @@ void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed) hugetlb_acct_memory(h, -(chg - freed)); } +/* Should be called in hugetlb_lock */ +static int is_hugepage_on_freelist(struct page *hpage) +{ + struct page *page; + struct page *tmp; + struct hstate *h = page_hstate(hpage); + int nid = page_to_nid(hpage); + + list_for_each_entry_safe(page, tmp, &h->hugepage_freelists[nid], lru) + if (page == hpage) + return 1; + return 0; +} + +#ifdef CONFIG_MEMORY_FAILURE /* * This function is called from memory failure code. * Assume the caller holds page lock of the head page. */ -void __isolate_hwpoisoned_huge_page(struct page *hpage) +int dequeue_hwpoisoned_huge_page(struct page *hpage) { struct hstate *h = page_hstate(hpage); int nid = page_to_nid(hpage); + int ret = -EBUSY; spin_lock(&hugetlb_lock); - list_del(&hpage->lru); - h->free_huge_pages--; - h->free_huge_pages_node[nid]--; + if (is_hugepage_on_freelist(hpage)) { + list_del(&hpage->lru); + h->free_huge_pages--; + h->free_huge_pages_node[nid]--; + ret = 0; + } spin_unlock(&hugetlb_lock); + return ret; } +#endif diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 757f6b0accfe..5c7158a11592 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -698,6 +698,7 @@ static int me_swapcache_clean(struct page *p, unsigned long pfn) */ static int me_huge_page(struct page *p, unsigned long pfn) { + int res = 0; struct page *hpage = compound_head(p); /* * We can safely recover from error on free or reserved (i.e. @@ -710,8 +711,9 @@ static int me_huge_page(struct page *p, unsigned long pfn) * so there is no race between isolation and mapping/unmapping. */ if (!(page_mapping(hpage) || PageAnon(hpage))) { - __isolate_hwpoisoned_huge_page(hpage); - return RECOVERED; + res = dequeue_hwpoisoned_huge_page(hpage); + if (!res) + return RECOVERED; } return DELAYED; } -- cgit v1.2.3 From aa50d3a7aa8147b9e14dc9d5972a5d2359db4ef8 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 6 Oct 2010 21:45:00 +0200 Subject: Encode huge page size for VM_FAULT_HWPOISON errors This fixes a problem introduced with the hugetlb hwpoison handling The user space SIGBUS signalling wants to know the size of the hugepage that caused a HWPOISON fault. Unfortunately the architecture page fault handlers do not have easy access to the struct page. Pass the information out in the fault error code instead. I added a separate VM_FAULT_HWPOISON_LARGE bit for this case and encode the hpage index in some free upper bits of the fault code. The small page hwpoison keeps stays with the VM_FAULT_HWPOISON name to minimize changes. Also add code to hugetlb.h to convert that index into a page shift. Will be used in a further patch. Cc: Naoya Horiguchi Cc: fengguang.wu@intel.com Signed-off-by: Andi Kleen --- include/linux/hugetlb.h | 6 ++++++ include/linux/mm.h | 12 ++++++++++-- mm/hugetlb.c | 6 ++++-- mm/memory.c | 3 ++- 4 files changed, 22 insertions(+), 5 deletions(-) (limited to 'include/linux/hugetlb.h') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 796f30e00806..943c76b3d4bb 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -307,6 +307,11 @@ static inline struct hstate *page_hstate(struct page *page) return size_to_hstate(PAGE_SIZE << compound_order(page)); } +static inline unsigned hstate_index_to_shift(unsigned index) +{ + return hstates[index].order + PAGE_SHIFT; +} + #else struct hstate {}; #define alloc_huge_page_node(h, nid) NULL @@ -324,6 +329,7 @@ static inline unsigned int pages_per_huge_page(struct hstate *h) { return 1; } +#define hstate_index_to_shift(index) 0 #endif #endif /* _LINUX_HUGETLB_H */ diff --git a/include/linux/mm.h b/include/linux/mm.h index 74949fbef8c6..f7e9efc6720b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -718,12 +718,20 @@ static inline int page_mapped(struct page *page) #define VM_FAULT_SIGBUS 0x0002 #define VM_FAULT_MAJOR 0x0004 #define VM_FAULT_WRITE 0x0008 /* Special case for get_user_pages */ -#define VM_FAULT_HWPOISON 0x0010 /* Hit poisoned page */ +#define VM_FAULT_HWPOISON 0x0010 /* Hit poisoned small page */ +#define VM_FAULT_HWPOISON_LARGE 0x0020 /* Hit poisoned large page. Index encoded in upper bits */ #define VM_FAULT_NOPAGE 0x0100 /* ->fault installed the pte, not return page */ #define VM_FAULT_LOCKED 0x0200 /* ->fault locked the returned page */ -#define VM_FAULT_ERROR (VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_HWPOISON) +#define VM_FAULT_HWPOISON_LARGE_MASK 0xf000 /* encodes hpage index for large hwpoison */ + +#define VM_FAULT_ERROR (VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_HWPOISON | \ + VM_FAULT_HWPOISON_LARGE) + +/* Encode hstate index for a hwpoisoned large page */ +#define VM_FAULT_SET_HINDEX(x) ((x) << 12) +#define VM_FAULT_GET_HINDEX(x) (((x) >> 12) & 0xf) /* * Can be called by the pagefault handler when it gets a VM_FAULT_OOM. diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 67cd03239b75..96991ded82fe 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2589,7 +2589,8 @@ retry: * So we need to block hugepage fault by PG_hwpoison bit check. */ if (unlikely(PageHWPoison(page))) { - ret = VM_FAULT_HWPOISON; + ret = VM_FAULT_HWPOISON | + VM_FAULT_SET_HINDEX(h - hstates); goto backout_unlocked; } page_dup_rmap(page); @@ -2656,7 +2657,8 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, migration_entry_wait(mm, (pmd_t *)ptep, address); return 0; } else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) - return VM_FAULT_HWPOISON; + return VM_FAULT_HWPOISON_LARGE | + VM_FAULT_SET_HINDEX(h - hstates); } ptep = huge_pte_alloc(mm, address, huge_page_size(h)); diff --git a/mm/memory.c b/mm/memory.c index 0e18b4d649ec..c2d6dd315659 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1450,7 +1450,8 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, if (ret & VM_FAULT_OOM) return i ? i : -ENOMEM; if (ret & - (VM_FAULT_HWPOISON|VM_FAULT_SIGBUS)) + (VM_FAULT_HWPOISON|VM_FAULT_HWPOISON_LARGE| + VM_FAULT_SIGBUS)) return i ? i : -EFAULT; BUG(); } -- cgit v1.2.3