From c58267c32429ea6535428ca6b8a036892c1697f2 Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Fri, 5 Mar 2010 13:41:43 -0800 Subject: mm: mlock_vma_pages_range() never return negative value Currently, mlock_vma_pages_range() never return negative value. Then, we can remove some worthless error check. Signed-off-by: KOSAKI Motohiro Cc: Nick Piggin Cc: Lee Schermerhorn Cc: Rik van Riel Cc: KAMEZAWA Hiroyuki Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mmap.c | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) (limited to 'mm/mmap.c') diff --git a/mm/mmap.c b/mm/mmap.c index ee2298936fe6..7acd7b0ad176 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1265,12 +1265,7 @@ out: mm->total_vm += len >> PAGE_SHIFT; vm_stat_account(mm, vm_flags, file, len >> PAGE_SHIFT); if (vm_flags & VM_LOCKED) { - /* - * makes pages present; downgrades, drops, reacquires mmap_sem - */ long nr_pages = mlock_vma_pages_range(vma, addr, addr + len); - if (nr_pages < 0) - return nr_pages; /* vma gone! */ mm->locked_vm += (len >> PAGE_SHIFT) - nr_pages; } else if ((flags & MAP_POPULATE) && !(flags & MAP_NONBLOCK)) make_pages_present(addr, addr + len); @@ -1754,8 +1749,7 @@ find_extend_vma(struct mm_struct *mm, unsigned long addr) if (!prev || expand_stack(prev, addr)) return NULL; if (prev->vm_flags & VM_LOCKED) { - if (mlock_vma_pages_range(prev, addr, prev->vm_end) < 0) - return NULL; /* vma gone! */ + mlock_vma_pages_range(prev, addr, prev->vm_end); } return prev; } @@ -1783,8 +1777,7 @@ find_extend_vma(struct mm_struct * mm, unsigned long addr) if (expand_stack(vma, addr)) return NULL; if (vma->vm_flags & VM_LOCKED) { - if (mlock_vma_pages_range(vma, addr, start) < 0) - return NULL; /* vma gone! */ + mlock_vma_pages_range(vma, addr, start); } return vma; } -- cgit v1.2.3 From 06f9d8c2b50060543fb6e0af87ddb86e654dee6b Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Fri, 5 Mar 2010 13:41:43 -0800 Subject: mm: mlock_vma_pages_range() only return success or failure Currently, mlock_vma_pages_range() only return len or 0. then current error handling of mmap_region() is meaningless complex. This patch makes simplify and makes consist with brk() code. Signed-off-by: KOSAKI Motohiro Cc: Nick Piggin Cc: Lee Schermerhorn Cc: Rik van Riel Cc: KAMEZAWA Hiroyuki Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mmap.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'mm/mmap.c') diff --git a/mm/mmap.c b/mm/mmap.c index 7acd7b0ad176..c646618702cf 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1265,8 +1265,8 @@ out: mm->total_vm += len >> PAGE_SHIFT; vm_stat_account(mm, vm_flags, file, len >> PAGE_SHIFT); if (vm_flags & VM_LOCKED) { - long nr_pages = mlock_vma_pages_range(vma, addr, addr + len); - mm->locked_vm += (len >> PAGE_SHIFT) - nr_pages; + if (!mlock_vma_pages_range(vma, addr, addr + len)) + mm->locked_vm += (len >> PAGE_SHIFT); } else if ((flags & MAP_POPULATE) && !(flags & MAP_NONBLOCK)) make_pages_present(addr, addr + len); return addr; -- cgit v1.2.3 From 59e99e5b9706867f18d4a36c1e4645fbaacbec2e Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 5 Mar 2010 13:41:44 -0800 Subject: mm: use rlimit helpers Make sure compiler won't do weird things with limits. E.g. fetching them twice may return 2 different values after writable limits are implemented. I.e. either use rlimit helpers added in 3e10e716abf3c71bdb5d86b8f507f9e72236c9cd ("resource: add helpers for fetching rlimits") or ACCESS_ONCE if not applicable. Signed-off-by: Jiri Slaby Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mmap.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'mm/mmap.c') diff --git a/mm/mmap.c b/mm/mmap.c index c646618702cf..31656147128e 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -265,7 +265,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk) * segment grow beyond its set limit the in case where the limit is * not page aligned -Ram Gupta */ - rlim = current->signal->rlim[RLIMIT_DATA].rlim_cur; + rlim = rlimit(RLIMIT_DATA); if (rlim < RLIM_INFINITY && (brk - mm->start_brk) + (mm->end_data - mm->start_data) > rlim) goto out; @@ -967,7 +967,7 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, unsigned long locked, lock_limit; locked = len >> PAGE_SHIFT; locked += mm->locked_vm; - lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur; + lock_limit = rlimit(RLIMIT_MEMLOCK); lock_limit >>= PAGE_SHIFT; if (locked > lock_limit && !capable(CAP_IPC_LOCK)) return -EAGAIN; @@ -1594,7 +1594,7 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns return -ENOMEM; /* Stack limit test */ - if (size > rlim[RLIMIT_STACK].rlim_cur) + if (size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur)) return -ENOMEM; /* mlock limit tests */ @@ -1602,7 +1602,8 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns unsigned long locked; unsigned long limit; locked = mm->locked_vm + grow; - limit = rlim[RLIMIT_MEMLOCK].rlim_cur >> PAGE_SHIFT; + limit = ACCESS_ONCE(rlim[RLIMIT_MEMLOCK].rlim_cur); + limit >>= PAGE_SHIFT; if (locked > limit && !capable(CAP_IPC_LOCK)) return -ENOMEM; } @@ -2067,7 +2068,7 @@ unsigned long do_brk(unsigned long addr, unsigned long len) unsigned long locked, lock_limit; locked = len >> PAGE_SHIFT; locked += mm->locked_vm; - lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur; + lock_limit = rlimit(RLIMIT_MEMLOCK); lock_limit >>= PAGE_SHIFT; if (locked > lock_limit && !capable(CAP_IPC_LOCK)) return -EAGAIN; @@ -2281,7 +2282,7 @@ int may_expand_vm(struct mm_struct *mm, unsigned long npages) unsigned long cur = mm->total_vm; /* pages */ unsigned long lim; - lim = current->signal->rlim[RLIMIT_AS].rlim_cur >> PAGE_SHIFT; + lim = rlimit(RLIMIT_AS) >> PAGE_SHIFT; if (cur + npages > lim) return 0; -- cgit v1.2.3 From 5beb49305251e5669852ed541e8e2f2f7696c53e Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Fri, 5 Mar 2010 13:42:07 -0800 Subject: mm: change anon_vma linking to fix multi-process server scalability issue The old anon_vma code can lead to scalability issues with heavily forking workloads. Specifically, each anon_vma will be shared between the parent process and all its child processes. In a workload with 1000 child processes and a VMA with 1000 anonymous pages per process that get COWed, this leads to a system with a million anonymous pages in the same anon_vma, each of which is mapped in just one of the 1000 processes. However, the current rmap code needs to walk them all, leading to O(N) scanning complexity for each page. This can result in systems where one CPU is walking the page tables of 1000 processes in page_referenced_one, while all other CPUs are stuck on the anon_vma lock. This leads to catastrophic failure for a benchmark like AIM7, where the total number of processes can reach in the tens of thousands. Real workloads are still a factor 10 less process intensive than AIM7, but they are catching up. This patch changes the way anon_vmas and VMAs are linked, which allows us to associate multiple anon_vmas with a VMA. At fork time, each child process gets its own anon_vmas, in which its COWed pages will be instantiated. The parents' anon_vma is also linked to the VMA, because non-COWed pages could be present in any of the children. This reduces rmap scanning complexity to O(1) for the pages of the 1000 child processes, with O(N) complexity for at most 1/N pages in the system. This reduces the average scanning cost in heavily forking workloads from O(N) to 2. The only real complexity in this patch stems from the fact that linking a VMA to anon_vmas now involves memory allocations. This means vma_adjust can fail, if it needs to attach a VMA to anon_vma structures. This in turn means error handling needs to be added to the calling functions. A second source of complexity is that, because there can be multiple anon_vmas, the anon_vma linking in vma_adjust can no longer be done under "the" anon_vma lock. To prevent the rmap code from walking up an incomplete VMA, this patch introduces the VM_LOCK_RMAP VMA flag. This bit flag uses the same slot as the NOMMU VM_MAPPED_COPY, with an ifdef in mm.h to make sure it is impossible to compile a kernel that needs both symbolic values for the same bitflag. Some test results: Without the anon_vma changes, when AIM7 hits around 9.7k users (on a test box with 16GB RAM and not quite enough IO), the system ends up running >99% in system time, with every CPU on the same anon_vma lock in the pageout code. With these changes, AIM7 hits the cross-over point around 29.7k users. This happens with ~99% IO wait time, there never seems to be any spike in system time. The anon_vma lock contention appears to be resolved. [akpm@linux-foundation.org: cleanups] Signed-off-by: Rik van Riel Cc: KOSAKI Motohiro Cc: Larry Woodman Cc: Lee Schermerhorn Cc: Minchan Kim Cc: Andrea Arcangeli Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mmap.c | 138 +++++++++++++++++++++++++++++++++++++++++++------------------- 1 file changed, 97 insertions(+), 41 deletions(-) (limited to 'mm/mmap.c') diff --git a/mm/mmap.c b/mm/mmap.c index 31656147128e..6a0c15db7f60 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -437,7 +437,6 @@ __vma_link(struct mm_struct *mm, struct vm_area_struct *vma, { __vma_link_list(mm, vma, prev, rb_parent); __vma_link_rb(mm, vma, rb_link, rb_parent); - __anon_vma_link(vma); } static void vma_link(struct mm_struct *mm, struct vm_area_struct *vma, @@ -499,7 +498,7 @@ __vma_unlink(struct mm_struct *mm, struct vm_area_struct *vma, * are necessary. The "insert" vma (if any) is to be inserted * before we drop the necessary locks. */ -void vma_adjust(struct vm_area_struct *vma, unsigned long start, +int vma_adjust(struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert) { struct mm_struct *mm = vma->vm_mm; @@ -542,6 +541,28 @@ again: remove_next = 1 + (end > next->vm_end); } } + /* + * When changing only vma->vm_end, we don't really need anon_vma lock. + */ + if (vma->anon_vma && (insert || importer || start != vma->vm_start)) + anon_vma = vma->anon_vma; + if (anon_vma) { + /* + * Easily overlooked: when mprotect shifts the boundary, + * make sure the expanding vma has anon_vma set if the + * shrinking vma had, to cover any anon pages imported. + */ + if (importer && !importer->anon_vma) { + /* Block reverse map lookups until things are set up. */ + importer->vm_flags |= VM_LOCK_RMAP; + if (anon_vma_clone(importer, vma)) { + importer->vm_flags &= ~VM_LOCK_RMAP; + return -ENOMEM; + } + importer->anon_vma = anon_vma; + } + } + if (file) { mapping = file->f_mapping; if (!(vma->vm_flags & VM_NONLINEAR)) @@ -567,25 +588,6 @@ again: remove_next = 1 + (end > next->vm_end); } } - /* - * When changing only vma->vm_end, we don't really need - * anon_vma lock. - */ - if (vma->anon_vma && (insert || importer || start != vma->vm_start)) - anon_vma = vma->anon_vma; - if (anon_vma) { - spin_lock(&anon_vma->lock); - /* - * Easily overlooked: when mprotect shifts the boundary, - * make sure the expanding vma has anon_vma set if the - * shrinking vma had, to cover any anon pages imported. - */ - if (importer && !importer->anon_vma) { - importer->anon_vma = anon_vma; - __anon_vma_link(importer); - } - } - if (root) { flush_dcache_mmap_lock(mapping); vma_prio_tree_remove(vma, root); @@ -616,8 +618,11 @@ again: remove_next = 1 + (end > next->vm_end); __vma_unlink(mm, next, vma); if (file) __remove_shared_vm_struct(next, file, mapping); - if (next->anon_vma) - __anon_vma_merge(vma, next); + /* + * This VMA is now dead, no need for rmap to follow it. + * Call anon_vma_merge below, outside of i_mmap_lock. + */ + next->vm_flags |= VM_LOCK_RMAP; } else if (insert) { /* * split_vma has split insert from vma, and needs @@ -627,17 +632,25 @@ again: remove_next = 1 + (end > next->vm_end); __insert_vm_struct(mm, insert); } - if (anon_vma) - spin_unlock(&anon_vma->lock); if (mapping) spin_unlock(&mapping->i_mmap_lock); + /* + * The current VMA has been set up. It is now safe for the + * rmap code to get from the pages to the ptes. + */ + if (anon_vma && importer) + importer->vm_flags &= ~VM_LOCK_RMAP; + if (remove_next) { if (file) { fput(file); if (next->vm_flags & VM_EXECUTABLE) removed_exe_file_vma(mm); } + /* Protected by mmap_sem and VM_LOCK_RMAP. */ + if (next->anon_vma) + anon_vma_merge(vma, next); mm->map_count--; mpol_put(vma_policy(next)); kmem_cache_free(vm_area_cachep, next); @@ -653,6 +666,8 @@ again: remove_next = 1 + (end > next->vm_end); } validate_mm(mm); + + return 0; } /* @@ -759,6 +774,7 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, { pgoff_t pglen = (end - addr) >> PAGE_SHIFT; struct vm_area_struct *area, *next; + int err; /* * We later require that vma->vm_flags == vm_flags, @@ -792,11 +808,13 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, is_mergeable_anon_vma(prev->anon_vma, next->anon_vma)) { /* cases 1, 6 */ - vma_adjust(prev, prev->vm_start, + err = vma_adjust(prev, prev->vm_start, next->vm_end, prev->vm_pgoff, NULL); } else /* cases 2, 5, 7 */ - vma_adjust(prev, prev->vm_start, + err = vma_adjust(prev, prev->vm_start, end, prev->vm_pgoff, NULL); + if (err) + return NULL; return prev; } @@ -808,11 +826,13 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, can_vma_merge_before(next, vm_flags, anon_vma, file, pgoff+pglen)) { if (prev && addr < prev->vm_end) /* case 4 */ - vma_adjust(prev, prev->vm_start, + err = vma_adjust(prev, prev->vm_start, addr, prev->vm_pgoff, NULL); else /* cases 3, 8 */ - vma_adjust(area, addr, next->vm_end, + err = vma_adjust(area, addr, next->vm_end, next->vm_pgoff - pglen, NULL); + if (err) + return NULL; return area; } @@ -1205,6 +1225,7 @@ munmap_back: vma->vm_flags = vm_flags; vma->vm_page_prot = vm_get_page_prot(vm_flags); vma->vm_pgoff = pgoff; + INIT_LIST_HEAD(&vma->anon_vma_chain); if (file) { error = -EINVAL; @@ -1865,6 +1886,7 @@ static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma, { struct mempolicy *pol; struct vm_area_struct *new; + int err = -ENOMEM; if (is_vm_hugetlb_page(vma) && (addr & ~(huge_page_mask(hstate_vma(vma))))) @@ -1872,11 +1894,13 @@ static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma, new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); if (!new) - return -ENOMEM; + goto out_err; /* most fields are the same, copy all, and then fixup */ *new = *vma; + INIT_LIST_HEAD(&new->anon_vma_chain); + if (new_below) new->vm_end = addr; else { @@ -1886,11 +1910,14 @@ static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma, pol = mpol_dup(vma_policy(vma)); if (IS_ERR(pol)) { - kmem_cache_free(vm_area_cachep, new); - return PTR_ERR(pol); + err = PTR_ERR(pol); + goto out_free_vma; } vma_set_policy(new, pol); + if (anon_vma_clone(new, vma)) + goto out_free_mpol; + if (new->vm_file) { get_file(new->vm_file); if (vma->vm_flags & VM_EXECUTABLE) @@ -1901,12 +1928,28 @@ static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma, new->vm_ops->open(new); if (new_below) - vma_adjust(vma, addr, vma->vm_end, vma->vm_pgoff + + err = vma_adjust(vma, addr, vma->vm_end, vma->vm_pgoff + ((addr - new->vm_start) >> PAGE_SHIFT), new); else - vma_adjust(vma, vma->vm_start, addr, vma->vm_pgoff, new); + err = vma_adjust(vma, vma->vm_start, addr, vma->vm_pgoff, new); - return 0; + /* Success. */ + if (!err) + return 0; + + /* Clean everything up if vma_adjust failed. */ + new->vm_ops->close(new); + if (new->vm_file) { + if (vma->vm_flags & VM_EXECUTABLE) + removed_exe_file_vma(mm); + fput(new->vm_file); + } + out_free_mpol: + mpol_put(pol); + out_free_vma: + kmem_cache_free(vm_area_cachep, new); + out_err: + return err; } /* @@ -2116,6 +2159,7 @@ unsigned long do_brk(unsigned long addr, unsigned long len) return -ENOMEM; } + INIT_LIST_HEAD(&vma->anon_vma_chain); vma->vm_mm = mm; vma->vm_start = addr; vma->vm_end = addr + len; @@ -2252,10 +2296,11 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, if (new_vma) { *new_vma = *vma; pol = mpol_dup(vma_policy(vma)); - if (IS_ERR(pol)) { - kmem_cache_free(vm_area_cachep, new_vma); - return NULL; - } + if (IS_ERR(pol)) + goto out_free_vma; + INIT_LIST_HEAD(&new_vma->anon_vma_chain); + if (anon_vma_clone(new_vma, vma)) + goto out_free_mempol; vma_set_policy(new_vma, pol); new_vma->vm_start = addr; new_vma->vm_end = addr + len; @@ -2271,6 +2316,12 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, } } return new_vma; + + out_free_mempol: + mpol_put(pol); + out_free_vma: + kmem_cache_free(vm_area_cachep, new_vma); + return NULL; } /* @@ -2348,6 +2399,7 @@ int install_special_mapping(struct mm_struct *mm, if (unlikely(vma == NULL)) return -ENOMEM; + INIT_LIST_HEAD(&vma->anon_vma_chain); vma->vm_mm = mm; vma->vm_start = addr; vma->vm_end = addr + len; @@ -2448,6 +2500,7 @@ static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping) int mm_take_all_locks(struct mm_struct *mm) { struct vm_area_struct *vma; + struct anon_vma_chain *avc; int ret = -EINTR; BUG_ON(down_read_trylock(&mm->mmap_sem)); @@ -2465,7 +2518,8 @@ int mm_take_all_locks(struct mm_struct *mm) if (signal_pending(current)) goto out_unlock; if (vma->anon_vma) - vm_lock_anon_vma(mm, vma->anon_vma); + list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) + vm_lock_anon_vma(mm, avc->anon_vma); } ret = 0; @@ -2520,13 +2574,15 @@ static void vm_unlock_mapping(struct address_space *mapping) void mm_drop_all_locks(struct mm_struct *mm) { struct vm_area_struct *vma; + struct anon_vma_chain *avc; BUG_ON(down_read_trylock(&mm->mmap_sem)); BUG_ON(!mutex_is_locked(&mm_all_locks_mutex)); for (vma = mm->mmap; vma; vma = vma->vm_next) { if (vma->anon_vma) - vm_unlock_anon_vma(vma->anon_vma); + list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) + vm_unlock_anon_vma(avc->anon_vma); if (vma->vm_file && vma->vm_file->f_mapping) vm_unlock_mapping(vma->vm_file->f_mapping); } -- cgit v1.2.3 From fc148a5f7e0532750c312385c7ee9fa3e9311f34 Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Fri, 5 Mar 2010 13:42:10 -0800 Subject: mm: remove VM_LOCK_RMAP code When a VMA is in an inconsistent state during setup or teardown, the worst that can happen is that the rmap code will not be able to find the page. The mapping is in the process of being torn down (PTEs just got invalidated by munmap), or set up (no PTEs have been instantiated yet). It is also impossible for the rmap code to follow a pointer to an already freed VMA, because the rmap code holds the anon_vma->lock, which the VMA teardown code needs to take before the VMA is removed from the anon_vma chain. Hence, we should not need the VM_LOCK_RMAP locking at all. Signed-off-by: Rik van Riel Cc: Nick Piggin Cc: KOSAKI Motohiro Cc: Larry Woodman Cc: Lee Schermerhorn Cc: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mmap.c | 15 --------------- 1 file changed, 15 deletions(-) (limited to 'mm/mmap.c') diff --git a/mm/mmap.c b/mm/mmap.c index 6a0c15db7f60..f1b4448626bf 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -554,9 +554,7 @@ again: remove_next = 1 + (end > next->vm_end); */ if (importer && !importer->anon_vma) { /* Block reverse map lookups until things are set up. */ - importer->vm_flags |= VM_LOCK_RMAP; if (anon_vma_clone(importer, vma)) { - importer->vm_flags &= ~VM_LOCK_RMAP; return -ENOMEM; } importer->anon_vma = anon_vma; @@ -618,11 +616,6 @@ again: remove_next = 1 + (end > next->vm_end); __vma_unlink(mm, next, vma); if (file) __remove_shared_vm_struct(next, file, mapping); - /* - * This VMA is now dead, no need for rmap to follow it. - * Call anon_vma_merge below, outside of i_mmap_lock. - */ - next->vm_flags |= VM_LOCK_RMAP; } else if (insert) { /* * split_vma has split insert from vma, and needs @@ -635,20 +628,12 @@ again: remove_next = 1 + (end > next->vm_end); if (mapping) spin_unlock(&mapping->i_mmap_lock); - /* - * The current VMA has been set up. It is now safe for the - * rmap code to get from the pages to the ptes. - */ - if (anon_vma && importer) - importer->vm_flags &= ~VM_LOCK_RMAP; - if (remove_next) { if (file) { fput(file); if (next->vm_flags & VM_EXECUTABLE) removed_exe_file_vma(mm); } - /* Protected by mmap_sem and VM_LOCK_RMAP. */ if (next->anon_vma) anon_vma_merge(vma, next); mm->map_count--; -- cgit v1.2.3 From a4679373cf4ee0e7792dc56205365732b725c2c1 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 10 Mar 2010 15:21:15 -0800 Subject: Add generic sys_old_mmap() Add a generic implementation of the old mmap() syscall, which expects its argument in a memory block and switch all architectures over to use it. Signed-off-by: Christoph Hellwig Cc: Ralf Baechle Cc: Benjamin Herrenschmidt Cc: Paul Mundt Cc: Jeff Dike Cc: Hirokazu Takata Cc: Thomas Gleixner Cc: Ingo Molnar Reviewed-by: H. Peter Anvin Cc: Al Viro Cc: Arnd Bergmann Cc: Heiko Carstens Cc: Martin Schwidefsky Cc: "Luck, Tony" Cc: James Morris Cc: Andreas Schwab Acked-by: Jesper Nilsson Acked-by: Russell King Acked-by: Greg Ungerer Acked-by: David Howells Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mmap.c | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'mm/mmap.c') diff --git a/mm/mmap.c b/mm/mmap.c index f1b4448626bf..75557c639ad4 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1088,6 +1088,30 @@ out: return retval; } +#ifdef __ARCH_WANT_SYS_OLD_MMAP +struct mmap_arg_struct { + unsigned long addr; + unsigned long len; + unsigned long prot; + unsigned long flags; + unsigned long fd; + unsigned long offset; +}; + +SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg) +{ + struct mmap_arg_struct a; + + if (copy_from_user(&a, arg, sizeof(a))) + return -EFAULT; + if (a.offset & ~PAGE_MASK) + return -EINVAL; + + return sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, + a.offset >> PAGE_SHIFT); +} +#endif /* __ARCH_WANT_SYS_OLD_MMAP */ + /* * Some shared mappigns will want the pages marked read-only * to track write events. If so, we'll downgrade vm_page_prot -- cgit v1.2.3