linux/mm/mprotect.c

446 lines
11 KiB
C
Raw Normal View History

/*
* mm/mprotect.c
*
* (C) Copyright 1994 Linus Torvalds
* (C) Copyright 2002 Christoph Hellwig
*
* Address space accounting code <alan@lxorguk.ukuu.org.uk>
* (C) Copyright 2002 Red Hat Inc, All Rights Reserved
*/
#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/shm.h>
#include <linux/mman.h>
#include <linux/fs.h>
#include <linux/highmem.h>
#include <linux/security.h>
#include <linux/mempolicy.h>
#include <linux/personality.h>
#include <linux/syscalls.h>
[PATCH] Swapless page migration: add R/W migration entries Implement read/write migration ptes We take the upper two swapfiles for the two types of migration ptes and define a series of macros in swapops.h. The VM is modified to handle the migration entries. migration entries can only be encountered when the page they are pointing to is locked. This limits the number of places one has to fix. We also check in copy_pte_range and in mprotect_pte_range() for migration ptes. We check for migration ptes in do_swap_cache and call a function that will then wait on the page lock. This allows us to effectively stop all accesses to apge. Migration entries are created by try_to_unmap if called for migration and removed by local functions in migrate.c From: Hugh Dickins <hugh@veritas.com> Several times while testing swapless page migration (I've no NUMA, just hacking it up to migrate recklessly while running load), I've hit the BUG_ON(!PageLocked(p)) in migration_entry_to_page. This comes from an orphaned migration entry, unrelated to the current correctly locked migration, but hit by remove_anon_migration_ptes as it checks an address in each vma of the anon_vma list. Such an orphan may be left behind if an earlier migration raced with fork: copy_one_pte can duplicate a migration entry from parent to child, after remove_anon_migration_ptes has checked the child vma, but before it has removed it from the parent vma. (If the process were later to fault on this orphaned entry, it would hit the same BUG from migration_entry_wait.) This could be fixed by locking anon_vma in copy_one_pte, but we'd rather not. There's no such problem with file pages, because vma_prio_tree_add adds child vma after parent vma, and the page table locking at each end is enough to serialize. Follow that example with anon_vma: add new vmas to the tail instead of the head. (There's no corresponding problem when inserting migration entries, because a missed pte will leave the page count and mapcount high, which is allowed for. And there's no corresponding problem when migrating via swap, because a leftover swap entry will be correctly faulted. But the swapless method has no refcounting of its entries.) From: Ingo Molnar <mingo@elte.hu> pte_unmap_unlock() takes the pte pointer as an argument. From: Hugh Dickins <hugh@veritas.com> Several times while testing swapless page migration, gcc has tried to exec a pointer instead of a string: smells like COW mappings are not being properly write-protected on fork. The protection in copy_one_pte looks very convincing, until at last you realize that the second arg to make_migration_entry is a boolean "write", and SWP_MIGRATION_READ is 30. Anyway, it's better done like in change_pte_range, using is_write_migration_entry and make_migration_entry_read. From: Hugh Dickins <hugh@veritas.com> Remove unnecessary obfuscation from sys_swapon's range check on swap type, which blew up causing memory corruption once swapless migration made MAX_SWAPFILES no longer 2 ^ MAX_SWAPFILES_SHIFT. Signed-off-by: Hugh Dickins <hugh@veritas.com> Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Christoph Lameter <clameter@engr.sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> From: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:03:35 +08:00
#include <linux/swap.h>
#include <linux/swapops.h>
mmu-notifiers: core With KVM/GFP/XPMEM there isn't just the primary CPU MMU pointing to pages. There are secondary MMUs (with secondary sptes and secondary tlbs) too. sptes in the kvm case are shadow pagetables, but when I say spte in mmu-notifier context, I mean "secondary pte". In GRU case there's no actual secondary pte and there's only a secondary tlb because the GRU secondary MMU has no knowledge about sptes and every secondary tlb miss event in the MMU always generates a page fault that has to be resolved by the CPU (this is not the case of KVM where the a secondary tlb miss will walk sptes in hardware and it will refill the secondary tlb transparently to software if the corresponding spte is present). The same way zap_page_range has to invalidate the pte before freeing the page, the spte (and secondary tlb) must also be invalidated before any page is freed and reused. Currently we take a page_count pin on every page mapped by sptes, but that means the pages can't be swapped whenever they're mapped by any spte because they're part of the guest working set. Furthermore a spte unmap event can immediately lead to a page to be freed when the pin is released (so requiring the same complex and relatively slow tlb_gather smp safe logic we have in zap_page_range and that can be avoided completely if the spte unmap event doesn't require an unpin of the page previously mapped in the secondary MMU). The mmu notifiers allow kvm/GRU/XPMEM to attach to the tsk->mm and know when the VM is swapping or freeing or doing anything on the primary MMU so that the secondary MMU code can drop sptes before the pages are freed, avoiding all page pinning and allowing 100% reliable swapping of guest physical address space. Furthermore it avoids the code that teardown the mappings of the secondary MMU, to implement a logic like tlb_gather in zap_page_range that would require many IPI to flush other cpu tlbs, for each fixed number of spte unmapped. To make an example: if what happens on the primary MMU is a protection downgrade (from writeable to wrprotect) the secondary MMU mappings will be invalidated, and the next secondary-mmu-page-fault will call get_user_pages and trigger a do_wp_page through get_user_pages if it called get_user_pages with write=1, and it'll re-establishing an updated spte or secondary-tlb-mapping on the copied page. Or it will setup a readonly spte or readonly tlb mapping if it's a guest-read, if it calls get_user_pages with write=0. This is just an example. This allows to map any page pointed by any pte (and in turn visible in the primary CPU MMU), into a secondary MMU (be it a pure tlb like GRU, or an full MMU with both sptes and secondary-tlb like the shadow-pagetable layer with kvm), or a remote DMA in software like XPMEM (hence needing of schedule in XPMEM code to send the invalidate to the remote node, while no need to schedule in kvm/gru as it's an immediate event like invalidating primary-mmu pte). At least for KVM without this patch it's impossible to swap guests reliably. And having this feature and removing the page pin allows several other optimizations that simplify life considerably. Dependencies: 1) mm_take_all_locks() to register the mmu notifier when the whole VM isn't doing anything with "mm". This allows mmu notifier users to keep track if the VM is in the middle of the invalidate_range_begin/end critical section with an atomic counter incraese in range_begin and decreased in range_end. No secondary MMU page fault is allowed to map any spte or secondary tlb reference, while the VM is in the middle of range_begin/end as any page returned by get_user_pages in that critical section could later immediately be freed without any further ->invalidate_page notification (invalidate_range_begin/end works on ranges and ->invalidate_page isn't called immediately before freeing the page). To stop all page freeing and pagetable overwrites the mmap_sem must be taken in write mode and all other anon_vma/i_mmap locks must be taken too. 2) It'd be a waste to add branches in the VM if nobody could possibly run KVM/GRU/XPMEM on the kernel, so mmu notifiers will only enabled if CONFIG_KVM=m/y. In the current kernel kvm won't yet take advantage of mmu notifiers, but this already allows to compile a KVM external module against a kernel with mmu notifiers enabled and from the next pull from kvm.git we'll start using them. And GRU/XPMEM will also be able to continue the development by enabling KVM=m in their config, until they submit all GRU/XPMEM GPLv2 code to the mainline kernel. Then they can also enable MMU_NOTIFIERS in the same way KVM does it (even if KVM=n). This guarantees nobody selects MMU_NOTIFIER=y if KVM and GRU and XPMEM are all =n. The mmu_notifier_register call can fail because mm_take_all_locks may be interrupted by a signal and return -EINTR. Because mmu_notifier_reigster is used when a driver startup, a failure can be gracefully handled. Here an example of the change applied to kvm to register the mmu notifiers. Usually when a driver startups other allocations are required anyway and -ENOMEM failure paths exists already. struct kvm *kvm_arch_create_vm(void) { struct kvm *kvm = kzalloc(sizeof(struct kvm), GFP_KERNEL); + int err; if (!kvm) return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); + kvm->arch.mmu_notifier.ops = &kvm_mmu_notifier_ops; + err = mmu_notifier_register(&kvm->arch.mmu_notifier, current->mm); + if (err) { + kfree(kvm); + return ERR_PTR(err); + } + return kvm; } mmu_notifier_unregister returns void and it's reliable. The patch also adds a few needed but missing includes that would prevent kernel to compile after these changes on non-x86 archs (x86 didn't need them by luck). [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: fix mm/filemap_xip.c build] [akpm@linux-foundation.org: fix mm/mmu_notifier.c build] Signed-off-by: Andrea Arcangeli <andrea@qumranet.com> Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Christoph Lameter <cl@linux-foundation.org> Cc: Jack Steiner <steiner@sgi.com> Cc: Robin Holt <holt@sgi.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Kanoj Sarcar <kanojsarcar@yahoo.com> Cc: Roland Dreier <rdreier@cisco.com> Cc: Steve Wise <swise@opengridcomputing.com> Cc: Avi Kivity <avi@qumranet.com> Cc: Hugh Dickins <hugh@veritas.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Anthony Liguori <aliguori@us.ibm.com> Cc: Chris Wright <chrisw@redhat.com> Cc: Marcelo Tosatti <marcelo@kvack.org> Cc: Eric Dumazet <dada1@cosmosbay.com> Cc: "Paul E. McKenney" <paulmck@us.ibm.com> Cc: Izik Eidus <izike@qumranet.com> Cc: Anthony Liguori <aliguori@us.ibm.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-29 06:46:29 +08:00
#include <linux/mmu_notifier.h>
#include <linux/migrate.h>
perf: Do the big rename: Performance Counters -> Performance Events Bye-bye Performance Counters, welcome Performance Events! In the past few months the perfcounters subsystem has grown out its initial role of counting hardware events, and has become (and is becoming) a much broader generic event enumeration, reporting, logging, monitoring, analysis facility. Naming its core object 'perf_counter' and naming the subsystem 'perfcounters' has become more and more of a misnomer. With pending code like hw-breakpoints support the 'counter' name is less and less appropriate. All in one, we've decided to rename the subsystem to 'performance events' and to propagate this rename through all fields, variables and API names. (in an ABI compatible fashion) The word 'event' is also a bit shorter than 'counter' - which makes it slightly more convenient to write/handle as well. Thanks goes to Stephane Eranian who first observed this misnomer and suggested a rename. User-space tooling and ABI compatibility is not affected - this patch should be function-invariant. (Also, defconfigs were not touched to keep the size down.) This patch has been generated via the following script: FILES=$(find * -type f | grep -vE 'oprofile|[^K]config') sed -i \ -e 's/PERF_EVENT_/PERF_RECORD_/g' \ -e 's/PERF_COUNTER/PERF_EVENT/g' \ -e 's/perf_counter/perf_event/g' \ -e 's/nb_counters/nb_events/g' \ -e 's/swcounter/swevent/g' \ -e 's/tpcounter_event/tp_event/g' \ $FILES for N in $(find . -name perf_counter.[ch]); do M=$(echo $N | sed 's/perf_counter/perf_event/g') mv $N $M done FILES=$(find . -name perf_event.*) sed -i \ -e 's/COUNTER_MASK/REG_MASK/g' \ -e 's/COUNTER/EVENT/g' \ -e 's/\<event\>/event_id/g' \ -e 's/counter/event/g' \ -e 's/Counter/Event/g' \ $FILES ... to keep it as correct as possible. This script can also be used by anyone who has pending perfcounters patches - it converts a Linux kernel tree over to the new naming. We tried to time this change to the point in time where the amount of pending patches is the smallest: the end of the merge window. Namespace clashes were fixed up in a preparatory patch - and some stylistic fallout will be fixed up in a subsequent patch. ( NOTE: 'counters' are still the proper terminology when we deal with hardware registers - and these sed scripts are a bit over-eager in renaming them. I've undone some of that, but in case there's something left where 'counter' would be better than 'event' we can undo that on an individual basis instead of touching an otherwise nicely automated patch. ) Suggested-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Paul Mackerras <paulus@samba.org> Reviewed-by: Arjan van de Ven <arjan@linux.intel.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Howells <dhowells@redhat.com> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: <linux-arch@vger.kernel.org> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 18:02:48 +08:00
#include <linux/perf_event.h>
#include <linux/ksm.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
mm: fix mprotect() behaviour on VM_LOCKED VMAs On mlock(2) we trigger COW on private writable VMA to avoid faults in future. mm/gup.c: 840 long populate_vma_page_range(struct vm_area_struct *vma, 841 unsigned long start, unsigned long end, int *nonblocking) 842 { ... 855 * We want to touch writable mappings with a write fault in order 856 * to break COW, except for shared mappings because these don't COW 857 * and we would not want to dirty them for nothing. 858 */ 859 if ((vma->vm_flags & (VM_WRITE | VM_SHARED)) == VM_WRITE) 860 gup_flags |= FOLL_WRITE; But we miss this case when we make VM_LOCKED VMA writeable via mprotect(2). The test case: #define _GNU_SOURCE #include <fcntl.h> #include <stdio.h> #include <stdlib.h> #include <unistd.h> #include <sys/mman.h> #include <sys/resource.h> #include <sys/stat.h> #include <sys/time.h> #include <sys/types.h> #define PAGE_SIZE 4096 int main(int argc, char **argv) { struct rusage usage; long before; char *p; int fd; /* Create a file and populate first page of page cache */ fd = open("/tmp", O_TMPFILE | O_RDWR, S_IRUSR | S_IWUSR); write(fd, "1", 1); /* Create a *read-only* *private* mapping of the file */ p = mmap(NULL, PAGE_SIZE, PROT_READ, MAP_PRIVATE, fd, 0); /* * Since the mapping is read-only, mlock() will populate the mapping * with PTEs pointing to page cache without triggering COW. */ mlock(p, PAGE_SIZE); /* * Mapping became read-write, but it's still populated with PTEs * pointing to page cache. */ mprotect(p, PAGE_SIZE, PROT_READ | PROT_WRITE); getrusage(RUSAGE_SELF, &usage); before = usage.ru_minflt; /* Trigger COW: fault in mlock()ed VMA. */ *p = 1; getrusage(RUSAGE_SELF, &usage); printf("faults: %ld\n", usage.ru_minflt - before); return 0; } $ ./test faults: 1 Let's fix it by triggering populating of VMA in mprotect_fixup() on this condition. We don't care about population error as we don't in other similar cases i.e. mremap. [akpm@linux-foundation.org: tweak comment text] Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-25 07:56:10 +08:00
#include "internal.h"
mm: numa: recheck for transhuge pages under lock during protection changes Sasha reported the following bug using trinity kernel BUG at mm/mprotect.c:149! invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC Dumping ftrace buffer: (ftrace buffer empty) Modules linked in: CPU: 20 PID: 26219 Comm: trinity-c216 Tainted: G W 3.14.0-rc5-next-20140305-sasha-00011-ge06f5f3-dirty #105 task: ffff8800b6c80000 ti: ffff880228436000 task.ti: ffff880228436000 RIP: change_protection_range+0x3b3/0x500 Call Trace: change_protection+0x25/0x30 change_prot_numa+0x1b/0x30 task_numa_work+0x279/0x360 task_work_run+0xae/0xf0 do_notify_resume+0x8e/0xe0 retint_signal+0x4d/0x92 The VM_BUG_ON was added in -mm by the patch "mm,numa: reorganize change_pmd_range". The race existed without the patch but was just harder to hit. The problem is that a transhuge check is made without holding the PTL. It's possible at the time of the check that a parallel fault clears the pmd and inserts a new one which then triggers the VM_BUG_ON check. This patch removes the VM_BUG_ON but fixes the race by rechecking transhuge under the PTL when marking page tables for NUMA hinting and bailing if a race occurred. It is not a problem for calls to mprotect() as they hold mmap_sem for write. Signed-off-by: Mel Gorman <mgorman@suse.de> Reported-by: Sasha Levin <sasha.levin@oracle.com> Reviewed-by: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-08 06:36:56 +08:00
/*
* For a prot_numa update we only hold mmap_sem for read so there is a
* potential race with faulting where a pmd was temporarily none. This
* function checks for a transhuge pmd under the appropriate lock. It
* returns a pte if it was successfully locked or NULL if it raced with
* a transhuge insertion.
*/
static pte_t *lock_pte_protection(struct vm_area_struct *vma, pmd_t *pmd,
unsigned long addr, int prot_numa, spinlock_t **ptl)
{
pte_t *pte;
spinlock_t *pmdl;
/* !prot_numa is protected by mmap_sem held for write */
if (!prot_numa)
return pte_offset_map_lock(vma->vm_mm, pmd, addr, ptl);
pmdl = pmd_lock(vma->vm_mm, pmd);
if (unlikely(pmd_trans_huge(*pmd) || pmd_none(*pmd))) {
spin_unlock(pmdl);
return NULL;
}
pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, ptl);
spin_unlock(pmdl);
return pte;
}
static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
unsigned long addr, unsigned long end, pgprot_t newprot,
mm: numa: Do not batch handle PMD pages With the THP migration races closed it is still possible to occasionally see corruption. The problem is related to handling PMD pages in batch. When a page fault is handled it can be assumed that the page being faulted will also be flushed from the TLB. The same flushing does not happen when handling PMD pages in batch. Fixing is straight forward but there are a number of reasons not to 1. Multiple TLB flushes may have to be sent depending on what pages get migrated 2. The handling of PMDs in batch means that faults get accounted to the task that is handling the fault. While care is taken to only mark PMDs where the last CPU and PID match it can still have problems due to PID truncation when matching PIDs. 3. Batching on the PMD level may reduce faults but setting pmd_numa requires taking a heavy lock that can contend with THP migration and handling the fault requires the release/acquisition of the PTL for every page migrated. It's still pretty heavy. PMD batch handling is not something that people ever have been happy with. This patch removes it and later patches will deal with the additional fault overhead using more installigent migrate rate adaption. Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1381141781-10992-48-git-send-email-mgorman@suse.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-10-07 18:29:25 +08:00
int dirty_accountable, int prot_numa)
{
struct mm_struct *mm = vma->vm_mm;
[PATCH] Swapless page migration: add R/W migration entries Implement read/write migration ptes We take the upper two swapfiles for the two types of migration ptes and define a series of macros in swapops.h. The VM is modified to handle the migration entries. migration entries can only be encountered when the page they are pointing to is locked. This limits the number of places one has to fix. We also check in copy_pte_range and in mprotect_pte_range() for migration ptes. We check for migration ptes in do_swap_cache and call a function that will then wait on the page lock. This allows us to effectively stop all accesses to apge. Migration entries are created by try_to_unmap if called for migration and removed by local functions in migrate.c From: Hugh Dickins <hugh@veritas.com> Several times while testing swapless page migration (I've no NUMA, just hacking it up to migrate recklessly while running load), I've hit the BUG_ON(!PageLocked(p)) in migration_entry_to_page. This comes from an orphaned migration entry, unrelated to the current correctly locked migration, but hit by remove_anon_migration_ptes as it checks an address in each vma of the anon_vma list. Such an orphan may be left behind if an earlier migration raced with fork: copy_one_pte can duplicate a migration entry from parent to child, after remove_anon_migration_ptes has checked the child vma, but before it has removed it from the parent vma. (If the process were later to fault on this orphaned entry, it would hit the same BUG from migration_entry_wait.) This could be fixed by locking anon_vma in copy_one_pte, but we'd rather not. There's no such problem with file pages, because vma_prio_tree_add adds child vma after parent vma, and the page table locking at each end is enough to serialize. Follow that example with anon_vma: add new vmas to the tail instead of the head. (There's no corresponding problem when inserting migration entries, because a missed pte will leave the page count and mapcount high, which is allowed for. And there's no corresponding problem when migrating via swap, because a leftover swap entry will be correctly faulted. But the swapless method has no refcounting of its entries.) From: Ingo Molnar <mingo@elte.hu> pte_unmap_unlock() takes the pte pointer as an argument. From: Hugh Dickins <hugh@veritas.com> Several times while testing swapless page migration, gcc has tried to exec a pointer instead of a string: smells like COW mappings are not being properly write-protected on fork. The protection in copy_one_pte looks very convincing, until at last you realize that the second arg to make_migration_entry is a boolean "write", and SWP_MIGRATION_READ is 30. Anyway, it's better done like in change_pte_range, using is_write_migration_entry and make_migration_entry_read. From: Hugh Dickins <hugh@veritas.com> Remove unnecessary obfuscation from sys_swapon's range check on swap type, which blew up causing memory corruption once swapless migration made MAX_SWAPFILES no longer 2 ^ MAX_SWAPFILES_SHIFT. Signed-off-by: Hugh Dickins <hugh@veritas.com> Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Christoph Lameter <clameter@engr.sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> From: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:03:35 +08:00
pte_t *pte, oldpte;
spinlock_t *ptl;
unsigned long pages = 0;
mm: numa: recheck for transhuge pages under lock during protection changes Sasha reported the following bug using trinity kernel BUG at mm/mprotect.c:149! invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC Dumping ftrace buffer: (ftrace buffer empty) Modules linked in: CPU: 20 PID: 26219 Comm: trinity-c216 Tainted: G W 3.14.0-rc5-next-20140305-sasha-00011-ge06f5f3-dirty #105 task: ffff8800b6c80000 ti: ffff880228436000 task.ti: ffff880228436000 RIP: change_protection_range+0x3b3/0x500 Call Trace: change_protection+0x25/0x30 change_prot_numa+0x1b/0x30 task_numa_work+0x279/0x360 task_work_run+0xae/0xf0 do_notify_resume+0x8e/0xe0 retint_signal+0x4d/0x92 The VM_BUG_ON was added in -mm by the patch "mm,numa: reorganize change_pmd_range". The race existed without the patch but was just harder to hit. The problem is that a transhuge check is made without holding the PTL. It's possible at the time of the check that a parallel fault clears the pmd and inserts a new one which then triggers the VM_BUG_ON check. This patch removes the VM_BUG_ON but fixes the race by rechecking transhuge under the PTL when marking page tables for NUMA hinting and bailing if a race occurred. It is not a problem for calls to mprotect() as they hold mmap_sem for write. Signed-off-by: Mel Gorman <mgorman@suse.de> Reported-by: Sasha Levin <sasha.levin@oracle.com> Reviewed-by: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-08 06:36:56 +08:00
pte = lock_pte_protection(vma, pmd, addr, prot_numa, &ptl);
if (!pte)
return 0;
arch_enter_lazy_mmu_mode();
do {
[PATCH] Swapless page migration: add R/W migration entries Implement read/write migration ptes We take the upper two swapfiles for the two types of migration ptes and define a series of macros in swapops.h. The VM is modified to handle the migration entries. migration entries can only be encountered when the page they are pointing to is locked. This limits the number of places one has to fix. We also check in copy_pte_range and in mprotect_pte_range() for migration ptes. We check for migration ptes in do_swap_cache and call a function that will then wait on the page lock. This allows us to effectively stop all accesses to apge. Migration entries are created by try_to_unmap if called for migration and removed by local functions in migrate.c From: Hugh Dickins <hugh@veritas.com> Several times while testing swapless page migration (I've no NUMA, just hacking it up to migrate recklessly while running load), I've hit the BUG_ON(!PageLocked(p)) in migration_entry_to_page. This comes from an orphaned migration entry, unrelated to the current correctly locked migration, but hit by remove_anon_migration_ptes as it checks an address in each vma of the anon_vma list. Such an orphan may be left behind if an earlier migration raced with fork: copy_one_pte can duplicate a migration entry from parent to child, after remove_anon_migration_ptes has checked the child vma, but before it has removed it from the parent vma. (If the process were later to fault on this orphaned entry, it would hit the same BUG from migration_entry_wait.) This could be fixed by locking anon_vma in copy_one_pte, but we'd rather not. There's no such problem with file pages, because vma_prio_tree_add adds child vma after parent vma, and the page table locking at each end is enough to serialize. Follow that example with anon_vma: add new vmas to the tail instead of the head. (There's no corresponding problem when inserting migration entries, because a missed pte will leave the page count and mapcount high, which is allowed for. And there's no corresponding problem when migrating via swap, because a leftover swap entry will be correctly faulted. But the swapless method has no refcounting of its entries.) From: Ingo Molnar <mingo@elte.hu> pte_unmap_unlock() takes the pte pointer as an argument. From: Hugh Dickins <hugh@veritas.com> Several times while testing swapless page migration, gcc has tried to exec a pointer instead of a string: smells like COW mappings are not being properly write-protected on fork. The protection in copy_one_pte looks very convincing, until at last you realize that the second arg to make_migration_entry is a boolean "write", and SWP_MIGRATION_READ is 30. Anyway, it's better done like in change_pte_range, using is_write_migration_entry and make_migration_entry_read. From: Hugh Dickins <hugh@veritas.com> Remove unnecessary obfuscation from sys_swapon's range check on swap type, which blew up causing memory corruption once swapless migration made MAX_SWAPFILES no longer 2 ^ MAX_SWAPFILES_SHIFT. Signed-off-by: Hugh Dickins <hugh@veritas.com> Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Christoph Lameter <clameter@engr.sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> From: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:03:35 +08:00
oldpte = *pte;
if (pte_present(oldpte)) {
pte_t ptent;
mm: numa: preserve PTE write permissions across a NUMA hinting fault Protecting a PTE to trap a NUMA hinting fault clears the writable bit and further faults are needed after trapping a NUMA hinting fault to set the writable bit again. This patch preserves the writable bit when trapping NUMA hinting faults. The impact is obvious from the number of minor faults trapped during the basis balancing benchmark and the system CPU usage; autonumabench 4.0.0-rc4 4.0.0-rc4 baseline preserve Time System-NUMA01 107.13 ( 0.00%) 103.13 ( 3.73%) Time System-NUMA01_THEADLOCAL 131.87 ( 0.00%) 83.30 ( 36.83%) Time System-NUMA02 8.95 ( 0.00%) 10.72 (-19.78%) Time System-NUMA02_SMT 4.57 ( 0.00%) 3.99 ( 12.69%) Time Elapsed-NUMA01 515.78 ( 0.00%) 517.26 ( -0.29%) Time Elapsed-NUMA01_THEADLOCAL 384.10 ( 0.00%) 384.31 ( -0.05%) Time Elapsed-NUMA02 48.86 ( 0.00%) 48.78 ( 0.16%) Time Elapsed-NUMA02_SMT 47.98 ( 0.00%) 48.12 ( -0.29%) 4.0.0-rc4 4.0.0-rc4 baseline preserve User 44383.95 43971.89 System 252.61 201.24 Elapsed 998.68 1000.94 Minor Faults 2597249 1981230 Major Faults 365 364 There is a similar drop in system CPU usage using Dave Chinner's xfsrepair workload 4.0.0-rc4 4.0.0-rc4 baseline preserve Amean real-xfsrepair 454.14 ( 0.00%) 442.36 ( 2.60%) Amean syst-xfsrepair 277.20 ( 0.00%) 204.68 ( 26.16%) The patch looks hacky but the alternatives looked worse. The tidest was to rewalk the page tables after a hinting fault but it was more complex than this approach and the performance was worse. It's not generally safe to just mark the page writable during the fault if it's a write fault as it may have been read-only for COW so that approach was discarded. Signed-off-by: Mel Gorman <mgorman@suse.de> Reported-by: Dave Chinner <david@fromorbit.com> Tested-by: Dave Chinner <david@fromorbit.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-03-26 06:55:40 +08:00
bool preserve_write = prot_numa && pte_write(oldpte);
/*
* Avoid trapping faults against the zero or KSM
* pages. See similar comment in change_huge_pmd.
*/
if (prot_numa) {
struct page *page;
page = vm_normal_page(vma, addr, oldpte);
if (!page || PageKsm(page))
continue;
/* Avoid TLB flush if possible */
if (pte_protnone(oldpte))
continue;
}
ptent = ptep_modify_prot_start(mm, addr, pte);
ptent = pte_modify(ptent, newprot);
mm: numa: preserve PTE write permissions across a NUMA hinting fault Protecting a PTE to trap a NUMA hinting fault clears the writable bit and further faults are needed after trapping a NUMA hinting fault to set the writable bit again. This patch preserves the writable bit when trapping NUMA hinting faults. The impact is obvious from the number of minor faults trapped during the basis balancing benchmark and the system CPU usage; autonumabench 4.0.0-rc4 4.0.0-rc4 baseline preserve Time System-NUMA01 107.13 ( 0.00%) 103.13 ( 3.73%) Time System-NUMA01_THEADLOCAL 131.87 ( 0.00%) 83.30 ( 36.83%) Time System-NUMA02 8.95 ( 0.00%) 10.72 (-19.78%) Time System-NUMA02_SMT 4.57 ( 0.00%) 3.99 ( 12.69%) Time Elapsed-NUMA01 515.78 ( 0.00%) 517.26 ( -0.29%) Time Elapsed-NUMA01_THEADLOCAL 384.10 ( 0.00%) 384.31 ( -0.05%) Time Elapsed-NUMA02 48.86 ( 0.00%) 48.78 ( 0.16%) Time Elapsed-NUMA02_SMT 47.98 ( 0.00%) 48.12 ( -0.29%) 4.0.0-rc4 4.0.0-rc4 baseline preserve User 44383.95 43971.89 System 252.61 201.24 Elapsed 998.68 1000.94 Minor Faults 2597249 1981230 Major Faults 365 364 There is a similar drop in system CPU usage using Dave Chinner's xfsrepair workload 4.0.0-rc4 4.0.0-rc4 baseline preserve Amean real-xfsrepair 454.14 ( 0.00%) 442.36 ( 2.60%) Amean syst-xfsrepair 277.20 ( 0.00%) 204.68 ( 26.16%) The patch looks hacky but the alternatives looked worse. The tidest was to rewalk the page tables after a hinting fault but it was more complex than this approach and the performance was worse. It's not generally safe to just mark the page writable during the fault if it's a write fault as it may have been read-only for COW so that approach was discarded. Signed-off-by: Mel Gorman <mgorman@suse.de> Reported-by: Dave Chinner <david@fromorbit.com> Tested-by: Dave Chinner <david@fromorbit.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-03-26 06:55:40 +08:00
if (preserve_write)
ptent = pte_mkwrite(ptent);
/* Avoid taking write faults for known dirty pages */
if (dirty_accountable && pte_dirty(ptent) &&
(pte_soft_dirty(ptent) ||
!(vma->vm_flags & VM_SOFTDIRTY))) {
ptent = pte_mkwrite(ptent);
}
ptep_modify_prot_commit(mm, addr, pte, ptent);
pages++;
} else if (IS_ENABLED(CONFIG_MIGRATION)) {
[PATCH] Swapless page migration: add R/W migration entries Implement read/write migration ptes We take the upper two swapfiles for the two types of migration ptes and define a series of macros in swapops.h. The VM is modified to handle the migration entries. migration entries can only be encountered when the page they are pointing to is locked. This limits the number of places one has to fix. We also check in copy_pte_range and in mprotect_pte_range() for migration ptes. We check for migration ptes in do_swap_cache and call a function that will then wait on the page lock. This allows us to effectively stop all accesses to apge. Migration entries are created by try_to_unmap if called for migration and removed by local functions in migrate.c From: Hugh Dickins <hugh@veritas.com> Several times while testing swapless page migration (I've no NUMA, just hacking it up to migrate recklessly while running load), I've hit the BUG_ON(!PageLocked(p)) in migration_entry_to_page. This comes from an orphaned migration entry, unrelated to the current correctly locked migration, but hit by remove_anon_migration_ptes as it checks an address in each vma of the anon_vma list. Such an orphan may be left behind if an earlier migration raced with fork: copy_one_pte can duplicate a migration entry from parent to child, after remove_anon_migration_ptes has checked the child vma, but before it has removed it from the parent vma. (If the process were later to fault on this orphaned entry, it would hit the same BUG from migration_entry_wait.) This could be fixed by locking anon_vma in copy_one_pte, but we'd rather not. There's no such problem with file pages, because vma_prio_tree_add adds child vma after parent vma, and the page table locking at each end is enough to serialize. Follow that example with anon_vma: add new vmas to the tail instead of the head. (There's no corresponding problem when inserting migration entries, because a missed pte will leave the page count and mapcount high, which is allowed for. And there's no corresponding problem when migrating via swap, because a leftover swap entry will be correctly faulted. But the swapless method has no refcounting of its entries.) From: Ingo Molnar <mingo@elte.hu> pte_unmap_unlock() takes the pte pointer as an argument. From: Hugh Dickins <hugh@veritas.com> Several times while testing swapless page migration, gcc has tried to exec a pointer instead of a string: smells like COW mappings are not being properly write-protected on fork. The protection in copy_one_pte looks very convincing, until at last you realize that the second arg to make_migration_entry is a boolean "write", and SWP_MIGRATION_READ is 30. Anyway, it's better done like in change_pte_range, using is_write_migration_entry and make_migration_entry_read. From: Hugh Dickins <hugh@veritas.com> Remove unnecessary obfuscation from sys_swapon's range check on swap type, which blew up causing memory corruption once swapless migration made MAX_SWAPFILES no longer 2 ^ MAX_SWAPFILES_SHIFT. Signed-off-by: Hugh Dickins <hugh@veritas.com> Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Christoph Lameter <clameter@engr.sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> From: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:03:35 +08:00
swp_entry_t entry = pte_to_swp_entry(oldpte);
if (is_write_migration_entry(entry)) {
pte_t newpte;
[PATCH] Swapless page migration: add R/W migration entries Implement read/write migration ptes We take the upper two swapfiles for the two types of migration ptes and define a series of macros in swapops.h. The VM is modified to handle the migration entries. migration entries can only be encountered when the page they are pointing to is locked. This limits the number of places one has to fix. We also check in copy_pte_range and in mprotect_pte_range() for migration ptes. We check for migration ptes in do_swap_cache and call a function that will then wait on the page lock. This allows us to effectively stop all accesses to apge. Migration entries are created by try_to_unmap if called for migration and removed by local functions in migrate.c From: Hugh Dickins <hugh@veritas.com> Several times while testing swapless page migration (I've no NUMA, just hacking it up to migrate recklessly while running load), I've hit the BUG_ON(!PageLocked(p)) in migration_entry_to_page. This comes from an orphaned migration entry, unrelated to the current correctly locked migration, but hit by remove_anon_migration_ptes as it checks an address in each vma of the anon_vma list. Such an orphan may be left behind if an earlier migration raced with fork: copy_one_pte can duplicate a migration entry from parent to child, after remove_anon_migration_ptes has checked the child vma, but before it has removed it from the parent vma. (If the process were later to fault on this orphaned entry, it would hit the same BUG from migration_entry_wait.) This could be fixed by locking anon_vma in copy_one_pte, but we'd rather not. There's no such problem with file pages, because vma_prio_tree_add adds child vma after parent vma, and the page table locking at each end is enough to serialize. Follow that example with anon_vma: add new vmas to the tail instead of the head. (There's no corresponding problem when inserting migration entries, because a missed pte will leave the page count and mapcount high, which is allowed for. And there's no corresponding problem when migrating via swap, because a leftover swap entry will be correctly faulted. But the swapless method has no refcounting of its entries.) From: Ingo Molnar <mingo@elte.hu> pte_unmap_unlock() takes the pte pointer as an argument. From: Hugh Dickins <hugh@veritas.com> Several times while testing swapless page migration, gcc has tried to exec a pointer instead of a string: smells like COW mappings are not being properly write-protected on fork. The protection in copy_one_pte looks very convincing, until at last you realize that the second arg to make_migration_entry is a boolean "write", and SWP_MIGRATION_READ is 30. Anyway, it's better done like in change_pte_range, using is_write_migration_entry and make_migration_entry_read. From: Hugh Dickins <hugh@veritas.com> Remove unnecessary obfuscation from sys_swapon's range check on swap type, which blew up causing memory corruption once swapless migration made MAX_SWAPFILES no longer 2 ^ MAX_SWAPFILES_SHIFT. Signed-off-by: Hugh Dickins <hugh@veritas.com> Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Christoph Lameter <clameter@engr.sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> From: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:03:35 +08:00
/*
* A protection check is difficult so
* just be safe and disable write
*/
make_migration_entry_read(&entry);
newpte = swp_entry_to_pte(entry);
if (pte_swp_soft_dirty(oldpte))
newpte = pte_swp_mksoft_dirty(newpte);
set_pte_at(mm, addr, pte, newpte);
pages++;
[PATCH] Swapless page migration: add R/W migration entries Implement read/write migration ptes We take the upper two swapfiles for the two types of migration ptes and define a series of macros in swapops.h. The VM is modified to handle the migration entries. migration entries can only be encountered when the page they are pointing to is locked. This limits the number of places one has to fix. We also check in copy_pte_range and in mprotect_pte_range() for migration ptes. We check for migration ptes in do_swap_cache and call a function that will then wait on the page lock. This allows us to effectively stop all accesses to apge. Migration entries are created by try_to_unmap if called for migration and removed by local functions in migrate.c From: Hugh Dickins <hugh@veritas.com> Several times while testing swapless page migration (I've no NUMA, just hacking it up to migrate recklessly while running load), I've hit the BUG_ON(!PageLocked(p)) in migration_entry_to_page. This comes from an orphaned migration entry, unrelated to the current correctly locked migration, but hit by remove_anon_migration_ptes as it checks an address in each vma of the anon_vma list. Such an orphan may be left behind if an earlier migration raced with fork: copy_one_pte can duplicate a migration entry from parent to child, after remove_anon_migration_ptes has checked the child vma, but before it has removed it from the parent vma. (If the process were later to fault on this orphaned entry, it would hit the same BUG from migration_entry_wait.) This could be fixed by locking anon_vma in copy_one_pte, but we'd rather not. There's no such problem with file pages, because vma_prio_tree_add adds child vma after parent vma, and the page table locking at each end is enough to serialize. Follow that example with anon_vma: add new vmas to the tail instead of the head. (There's no corresponding problem when inserting migration entries, because a missed pte will leave the page count and mapcount high, which is allowed for. And there's no corresponding problem when migrating via swap, because a leftover swap entry will be correctly faulted. But the swapless method has no refcounting of its entries.) From: Ingo Molnar <mingo@elte.hu> pte_unmap_unlock() takes the pte pointer as an argument. From: Hugh Dickins <hugh@veritas.com> Several times while testing swapless page migration, gcc has tried to exec a pointer instead of a string: smells like COW mappings are not being properly write-protected on fork. The protection in copy_one_pte looks very convincing, until at last you realize that the second arg to make_migration_entry is a boolean "write", and SWP_MIGRATION_READ is 30. Anyway, it's better done like in change_pte_range, using is_write_migration_entry and make_migration_entry_read. From: Hugh Dickins <hugh@veritas.com> Remove unnecessary obfuscation from sys_swapon's range check on swap type, which blew up causing memory corruption once swapless migration made MAX_SWAPFILES no longer 2 ^ MAX_SWAPFILES_SHIFT. Signed-off-by: Hugh Dickins <hugh@veritas.com> Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Christoph Lameter <clameter@engr.sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> From: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:03:35 +08:00
}
}
} while (pte++, addr += PAGE_SIZE, addr != end);
arch_leave_lazy_mmu_mode();
pte_unmap_unlock(pte - 1, ptl);
return pages;
}
static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
pud_t *pud, unsigned long addr, unsigned long end,
pgprot_t newprot, int dirty_accountable, int prot_numa)
{
pmd_t *pmd;
struct mm_struct *mm = vma->vm_mm;
unsigned long next;
unsigned long pages = 0;
mm: numa: return the number of base pages altered by protection changes Commit 0255d4918480 ("mm: Account for a THP NUMA hinting update as one PTE update") was added to account for the number of PTE updates when marking pages prot_numa. task_numa_work was using the old return value to track how much address space had been updated. Altering the return value causes the scanner to do more work than it is configured or documented to in a single unit of work. This patch reverts that commit and accounts for the number of THP updates separately in vmstat. It is up to the administrator to interpret the pair of values correctly. This is a straight-forward operation and likely to only be of interest when actively debugging NUMA balancing problems. The impact of this patch is that the NUMA PTE scanner will scan slower when THP is enabled and workloads may converge slower as a result. On the flip size system CPU usage should be lower than recent tests reported. This is an illustrative example of a short single JVM specjbb test specjbb 3.12.0 3.12.0 vanilla acctupdates TPut 1 26143.00 ( 0.00%) 25747.00 ( -1.51%) TPut 7 185257.00 ( 0.00%) 183202.00 ( -1.11%) TPut 13 329760.00 ( 0.00%) 346577.00 ( 5.10%) TPut 19 442502.00 ( 0.00%) 460146.00 ( 3.99%) TPut 25 540634.00 ( 0.00%) 549053.00 ( 1.56%) TPut 31 512098.00 ( 0.00%) 519611.00 ( 1.47%) TPut 37 461276.00 ( 0.00%) 474973.00 ( 2.97%) TPut 43 403089.00 ( 0.00%) 414172.00 ( 2.75%) 3.12.0 3.12.0 vanillaacctupdates User 5169.64 5184.14 System 100.45 80.02 Elapsed 252.75 251.85 Performance is similar but note the reduction in system CPU time. While this showed a performance gain, it will not be universal but at least it'll be behaving as documented. The vmstats are obviously different but here is an obvious interpretation of them from mmtests. 3.12.0 3.12.0 vanillaacctupdates NUMA page range updates 1408326 11043064 NUMA huge PMD updates 0 21040 NUMA PTE updates 1408326 291624 "NUMA page range updates" == nr_pte_updates and is the value returned to the NUMA pte scanner. NUMA huge PMD updates were the number of THP updates which in combination can be used to calculate how many ptes were updated from userspace. Signed-off-by: Mel Gorman <mgorman@suse.de> Reported-by: Alex Thorlton <athorlton@sgi.com> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-11-13 07:08:32 +08:00
unsigned long nr_huge_updates = 0;
unsigned long mni_start = 0;
pmd = pmd_offset(pud, addr);
do {
unsigned long this_pages;
next = pmd_addr_end(addr, end);
if (!pmd_trans_huge(*pmd) && pmd_none_or_clear_bad(pmd))
continue;
/* invoke the mmu notifier if the pmd is populated */
if (!mni_start) {
mni_start = addr;
mmu_notifier_invalidate_range_start(mm, mni_start, end);
}
if (pmd_trans_huge(*pmd)) {
if (next - addr != HPAGE_PMD_SIZE)
split_huge_page_pmd(vma, addr, pmd);
else {
int nr_ptes = change_huge_pmd(vma, pmd, addr,
newprot, prot_numa);
if (nr_ptes) {
mm: numa: return the number of base pages altered by protection changes Commit 0255d4918480 ("mm: Account for a THP NUMA hinting update as one PTE update") was added to account for the number of PTE updates when marking pages prot_numa. task_numa_work was using the old return value to track how much address space had been updated. Altering the return value causes the scanner to do more work than it is configured or documented to in a single unit of work. This patch reverts that commit and accounts for the number of THP updates separately in vmstat. It is up to the administrator to interpret the pair of values correctly. This is a straight-forward operation and likely to only be of interest when actively debugging NUMA balancing problems. The impact of this patch is that the NUMA PTE scanner will scan slower when THP is enabled and workloads may converge slower as a result. On the flip size system CPU usage should be lower than recent tests reported. This is an illustrative example of a short single JVM specjbb test specjbb 3.12.0 3.12.0 vanilla acctupdates TPut 1 26143.00 ( 0.00%) 25747.00 ( -1.51%) TPut 7 185257.00 ( 0.00%) 183202.00 ( -1.11%) TPut 13 329760.00 ( 0.00%) 346577.00 ( 5.10%) TPut 19 442502.00 ( 0.00%) 460146.00 ( 3.99%) TPut 25 540634.00 ( 0.00%) 549053.00 ( 1.56%) TPut 31 512098.00 ( 0.00%) 519611.00 ( 1.47%) TPut 37 461276.00 ( 0.00%) 474973.00 ( 2.97%) TPut 43 403089.00 ( 0.00%) 414172.00 ( 2.75%) 3.12.0 3.12.0 vanillaacctupdates User 5169.64 5184.14 System 100.45 80.02 Elapsed 252.75 251.85 Performance is similar but note the reduction in system CPU time. While this showed a performance gain, it will not be universal but at least it'll be behaving as documented. The vmstats are obviously different but here is an obvious interpretation of them from mmtests. 3.12.0 3.12.0 vanillaacctupdates NUMA page range updates 1408326 11043064 NUMA huge PMD updates 0 21040 NUMA PTE updates 1408326 291624 "NUMA page range updates" == nr_pte_updates and is the value returned to the NUMA pte scanner. NUMA huge PMD updates were the number of THP updates which in combination can be used to calculate how many ptes were updated from userspace. Signed-off-by: Mel Gorman <mgorman@suse.de> Reported-by: Alex Thorlton <athorlton@sgi.com> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-11-13 07:08:32 +08:00
if (nr_ptes == HPAGE_PMD_NR) {
pages += HPAGE_PMD_NR;
nr_huge_updates++;
}
mm: numa: recheck for transhuge pages under lock during protection changes Sasha reported the following bug using trinity kernel BUG at mm/mprotect.c:149! invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC Dumping ftrace buffer: (ftrace buffer empty) Modules linked in: CPU: 20 PID: 26219 Comm: trinity-c216 Tainted: G W 3.14.0-rc5-next-20140305-sasha-00011-ge06f5f3-dirty #105 task: ffff8800b6c80000 ti: ffff880228436000 task.ti: ffff880228436000 RIP: change_protection_range+0x3b3/0x500 Call Trace: change_protection+0x25/0x30 change_prot_numa+0x1b/0x30 task_numa_work+0x279/0x360 task_work_run+0xae/0xf0 do_notify_resume+0x8e/0xe0 retint_signal+0x4d/0x92 The VM_BUG_ON was added in -mm by the patch "mm,numa: reorganize change_pmd_range". The race existed without the patch but was just harder to hit. The problem is that a transhuge check is made without holding the PTL. It's possible at the time of the check that a parallel fault clears the pmd and inserts a new one which then triggers the VM_BUG_ON check. This patch removes the VM_BUG_ON but fixes the race by rechecking transhuge under the PTL when marking page tables for NUMA hinting and bailing if a race occurred. It is not a problem for calls to mprotect() as they hold mmap_sem for write. Signed-off-by: Mel Gorman <mgorman@suse.de> Reported-by: Sasha Levin <sasha.levin@oracle.com> Reviewed-by: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-08 06:36:56 +08:00
/* huge pmd was handled */
continue;
}
}
/* fall through, the trans huge pmd just split */
}
this_pages = change_pte_range(vma, pmd, addr, next, newprot,
mm: numa: Do not batch handle PMD pages With the THP migration races closed it is still possible to occasionally see corruption. The problem is related to handling PMD pages in batch. When a page fault is handled it can be assumed that the page being faulted will also be flushed from the TLB. The same flushing does not happen when handling PMD pages in batch. Fixing is straight forward but there are a number of reasons not to 1. Multiple TLB flushes may have to be sent depending on what pages get migrated 2. The handling of PMDs in batch means that faults get accounted to the task that is handling the fault. While care is taken to only mark PMDs where the last CPU and PID match it can still have problems due to PID truncation when matching PIDs. 3. Batching on the PMD level may reduce faults but setting pmd_numa requires taking a heavy lock that can contend with THP migration and handling the fault requires the release/acquisition of the PTL for every page migrated. It's still pretty heavy. PMD batch handling is not something that people ever have been happy with. This patch removes it and later patches will deal with the additional fault overhead using more installigent migrate rate adaption. Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1381141781-10992-48-git-send-email-mgorman@suse.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-10-07 18:29:25 +08:00
dirty_accountable, prot_numa);
pages += this_pages;
} while (pmd++, addr = next, addr != end);
if (mni_start)
mmu_notifier_invalidate_range_end(mm, mni_start, end);
mm: numa: return the number of base pages altered by protection changes Commit 0255d4918480 ("mm: Account for a THP NUMA hinting update as one PTE update") was added to account for the number of PTE updates when marking pages prot_numa. task_numa_work was using the old return value to track how much address space had been updated. Altering the return value causes the scanner to do more work than it is configured or documented to in a single unit of work. This patch reverts that commit and accounts for the number of THP updates separately in vmstat. It is up to the administrator to interpret the pair of values correctly. This is a straight-forward operation and likely to only be of interest when actively debugging NUMA balancing problems. The impact of this patch is that the NUMA PTE scanner will scan slower when THP is enabled and workloads may converge slower as a result. On the flip size system CPU usage should be lower than recent tests reported. This is an illustrative example of a short single JVM specjbb test specjbb 3.12.0 3.12.0 vanilla acctupdates TPut 1 26143.00 ( 0.00%) 25747.00 ( -1.51%) TPut 7 185257.00 ( 0.00%) 183202.00 ( -1.11%) TPut 13 329760.00 ( 0.00%) 346577.00 ( 5.10%) TPut 19 442502.00 ( 0.00%) 460146.00 ( 3.99%) TPut 25 540634.00 ( 0.00%) 549053.00 ( 1.56%) TPut 31 512098.00 ( 0.00%) 519611.00 ( 1.47%) TPut 37 461276.00 ( 0.00%) 474973.00 ( 2.97%) TPut 43 403089.00 ( 0.00%) 414172.00 ( 2.75%) 3.12.0 3.12.0 vanillaacctupdates User 5169.64 5184.14 System 100.45 80.02 Elapsed 252.75 251.85 Performance is similar but note the reduction in system CPU time. While this showed a performance gain, it will not be universal but at least it'll be behaving as documented. The vmstats are obviously different but here is an obvious interpretation of them from mmtests. 3.12.0 3.12.0 vanillaacctupdates NUMA page range updates 1408326 11043064 NUMA huge PMD updates 0 21040 NUMA PTE updates 1408326 291624 "NUMA page range updates" == nr_pte_updates and is the value returned to the NUMA pte scanner. NUMA huge PMD updates were the number of THP updates which in combination can be used to calculate how many ptes were updated from userspace. Signed-off-by: Mel Gorman <mgorman@suse.de> Reported-by: Alex Thorlton <athorlton@sgi.com> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-11-13 07:08:32 +08:00
if (nr_huge_updates)
count_vm_numa_events(NUMA_HUGE_PTE_UPDATES, nr_huge_updates);
return pages;
}
static inline unsigned long change_pud_range(struct vm_area_struct *vma,
pgd_t *pgd, unsigned long addr, unsigned long end,
pgprot_t newprot, int dirty_accountable, int prot_numa)
{
pud_t *pud;
unsigned long next;
unsigned long pages = 0;
pud = pud_offset(pgd, addr);
do {
next = pud_addr_end(addr, end);
if (pud_none_or_clear_bad(pud))
continue;
pages += change_pmd_range(vma, pud, addr, next, newprot,
dirty_accountable, prot_numa);
} while (pud++, addr = next, addr != end);
return pages;
}
static unsigned long change_protection_range(struct vm_area_struct *vma,
unsigned long addr, unsigned long end, pgprot_t newprot,
int dirty_accountable, int prot_numa)
{
struct mm_struct *mm = vma->vm_mm;
pgd_t *pgd;
unsigned long next;
unsigned long start = addr;
unsigned long pages = 0;
BUG_ON(addr >= end);
pgd = pgd_offset(mm, addr);
flush_cache_range(vma, addr, end);
mm: fix TLB flush race between migration, and change_protection_range There are a few subtle races, between change_protection_range (used by mprotect and change_prot_numa) on one side, and NUMA page migration and compaction on the other side. The basic race is that there is a time window between when the PTE gets made non-present (PROT_NONE or NUMA), and the TLB is flushed. During that time, a CPU may continue writing to the page. This is fine most of the time, however compaction or the NUMA migration code may come in, and migrate the page away. When that happens, the CPU may continue writing, through the cached translation, to what is no longer the current memory location of the process. This only affects x86, which has a somewhat optimistic pte_accessible. All other architectures appear to be safe, and will either always flush, or flush whenever there is a valid mapping, even with no permissions (SPARC). The basic race looks like this: CPU A CPU B CPU C load TLB entry make entry PTE/PMD_NUMA fault on entry read/write old page start migrating page change PTE/PMD to new page read/write old page [*] flush TLB reload TLB from new entry read/write new page lose data [*] the old page may belong to a new user at this point! The obvious fix is to flush remote TLB entries, by making sure that pte_accessible aware of the fact that PROT_NONE and PROT_NUMA memory may still be accessible if there is a TLB flush pending for the mm. This should fix both NUMA migration and compaction. [mgorman@suse.de: fix build] Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: Alex Thorlton <athorlton@sgi.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-12-19 09:08:44 +08:00
set_tlb_flush_pending(mm);
do {
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(pgd))
continue;
pages += change_pud_range(vma, pgd, addr, next, newprot,
dirty_accountable, prot_numa);
} while (pgd++, addr = next, addr != end);
mm: Optimize the TLB flush of sys_mprotect() and change_protection() users Reuse the NUMA code's 'modified page protections' count that change_protection() computes and skip the TLB flush if there's no changes to a range that sys_mprotect() modifies. Given that mprotect() already optimizes the same-flags case I expected this optimization to dominantly trigger on CONFIG_NUMA_BALANCING=y kernels - but even with that feature disabled it triggers rather often. There's two reasons for that: 1) While sys_mprotect() already optimizes the same-flag case: if (newflags == oldflags) { *pprev = vma; return 0; } and this test works in many cases, but it is too sharp in some others, where it differentiates between protection values that the underlying PTE format makes no distinction about, such as PROT_EXEC == PROT_READ on x86. 2) Even where the pte format over vma flag changes necessiates a modification of the pagetables, there might be no pagetables yet to modify: they might not be instantiated yet. During a regular desktop bootup this optimization hits a couple of hundred times. During a Java test I measured thousands of hits. So this optimization improves sys_mprotect() in general, not just CONFIG_NUMA_BALANCING=y kernels. [ We could further increase the efficiency of this optimization if change_pte_range() and change_huge_pmd() was a bit smarter about recognizing exact-same-value protection masks - when the hardware can do that safely. This would probably further speed up mprotect(). ] Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Hugh Dickins <hughd@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Ingo Molnar <mingo@kernel.org>
2012-11-19 10:14:24 +08:00
/* Only flush the TLB if we actually modified any entries: */
if (pages)
flush_tlb_range(vma, start, end);
mm: fix TLB flush race between migration, and change_protection_range There are a few subtle races, between change_protection_range (used by mprotect and change_prot_numa) on one side, and NUMA page migration and compaction on the other side. The basic race is that there is a time window between when the PTE gets made non-present (PROT_NONE or NUMA), and the TLB is flushed. During that time, a CPU may continue writing to the page. This is fine most of the time, however compaction or the NUMA migration code may come in, and migrate the page away. When that happens, the CPU may continue writing, through the cached translation, to what is no longer the current memory location of the process. This only affects x86, which has a somewhat optimistic pte_accessible. All other architectures appear to be safe, and will either always flush, or flush whenever there is a valid mapping, even with no permissions (SPARC). The basic race looks like this: CPU A CPU B CPU C load TLB entry make entry PTE/PMD_NUMA fault on entry read/write old page start migrating page change PTE/PMD to new page read/write old page [*] flush TLB reload TLB from new entry read/write new page lose data [*] the old page may belong to a new user at this point! The obvious fix is to flush remote TLB entries, by making sure that pte_accessible aware of the fact that PROT_NONE and PROT_NUMA memory may still be accessible if there is a TLB flush pending for the mm. This should fix both NUMA migration and compaction. [mgorman@suse.de: fix build] Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: Alex Thorlton <athorlton@sgi.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-12-19 09:08:44 +08:00
clear_tlb_flush_pending(mm);
return pages;
}
unsigned long change_protection(struct vm_area_struct *vma, unsigned long start,
unsigned long end, pgprot_t newprot,
int dirty_accountable, int prot_numa)
{
unsigned long pages;
if (is_vm_hugetlb_page(vma))
pages = hugetlb_change_protection(vma, start, end, newprot);
else
pages = change_protection_range(vma, start, end, newprot, dirty_accountable, prot_numa);
return pages;
}
int
mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
unsigned long start, unsigned long end, unsigned long newflags)
{
struct mm_struct *mm = vma->vm_mm;
unsigned long oldflags = vma->vm_flags;
long nrpages = (end - start) >> PAGE_SHIFT;
unsigned long charged = 0;
pgoff_t pgoff;
int error;
int dirty_accountable = 0;
if (newflags == oldflags) {
*pprev = vma;
return 0;
}
/*
* If we make a private mapping writable we increase our commit;
* but (without finer accounting) cannot reduce our commit if we
Do not account for the address space used by hugetlbfs using VM_ACCOUNT When overcommit is disabled, the core VM accounts for pages used by anonymous shared, private mappings and special mappings. It keeps track of VMAs that should be accounted for with VM_ACCOUNT and VMAs that never had a reserve with VM_NORESERVE. Overcommit for hugetlbfs is much riskier than overcommit for base pages due to contiguity requirements. It avoids overcommiting on both shared and private mappings using reservation counters that are checked and updated during mmap(). This ensures (within limits) that hugepages exist in the future when faults occurs or it is too easy to applications to be SIGKILLed. As hugetlbfs makes its own reservations of a different unit to the base page size, VM_ACCOUNT should never be set. Even if the units were correct, we would double account for the usage in the core VM and hugetlbfs. VM_NORESERVE may be set because an application can request no reserves be made for hugetlbfs at the risk of getting killed later. With commit fc8744adc870a8d4366908221508bb113d8b72ee, VM_NORESERVE and VM_ACCOUNT are getting unconditionally set for hugetlbfs-backed mappings. This breaks the accounting for both the core VM and hugetlbfs, can trigger an OOM storm when hugepage pools are too small lockups and corrupted counters otherwise are used. This patch brings hugetlbfs more in line with how the core VM treats VM_NORESERVE but prevents VM_ACCOUNT being set. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-02-10 22:02:27 +08:00
* make it unwritable again. hugetlb mapping were accounted for
* even if read-only so there is no need to account for them here
*/
if (newflags & VM_WRITE) {
Do not account for the address space used by hugetlbfs using VM_ACCOUNT When overcommit is disabled, the core VM accounts for pages used by anonymous shared, private mappings and special mappings. It keeps track of VMAs that should be accounted for with VM_ACCOUNT and VMAs that never had a reserve with VM_NORESERVE. Overcommit for hugetlbfs is much riskier than overcommit for base pages due to contiguity requirements. It avoids overcommiting on both shared and private mappings using reservation counters that are checked and updated during mmap(). This ensures (within limits) that hugepages exist in the future when faults occurs or it is too easy to applications to be SIGKILLed. As hugetlbfs makes its own reservations of a different unit to the base page size, VM_ACCOUNT should never be set. Even if the units were correct, we would double account for the usage in the core VM and hugetlbfs. VM_NORESERVE may be set because an application can request no reserves be made for hugetlbfs at the risk of getting killed later. With commit fc8744adc870a8d4366908221508bb113d8b72ee, VM_NORESERVE and VM_ACCOUNT are getting unconditionally set for hugetlbfs-backed mappings. This breaks the accounting for both the core VM and hugetlbfs, can trigger an OOM storm when hugepage pools are too small lockups and corrupted counters otherwise are used. This patch brings hugetlbfs more in line with how the core VM treats VM_NORESERVE but prevents VM_ACCOUNT being set. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-02-10 22:02:27 +08:00
if (!(oldflags & (VM_ACCOUNT|VM_WRITE|VM_HUGETLB|
mm: record MAP_NORESERVE status on vmas and fix small page mprotect reservations With Mel's hugetlb private reservation support patches applied, strict overcommit semantics are applied to both shared and private huge page mappings. This can be a problem if an application relied on unlimited overcommit semantics for private mappings. An example of this would be an application which maps a huge area with the intention of using it very sparsely. These application would benefit from being able to opt-out of the strict overcommit. It should be noted that prior to hugetlb supporting demand faulting all mappings were fully populated and so applications of this type should be rare. This patch stack implements the MAP_NORESERVE mmap() flag for huge page mappings. This flag has the same meaning as for small page mappings, suppressing reservations for that mapping. Thanks to Mel Gorman for reviewing a number of early versions of these patches. This patch: When a small page mapping is created with mmap() reservations are created by default for any memory pages required. When the region is read/write the reservation is increased for every page, no reservation is needed for read-only regions (as they implicitly share the zero page). Reservations are tracked via the VM_ACCOUNT vma flag which is present when the region has reservation backing it. When we convert a region from read-only to read-write new reservations are aquired and VM_ACCOUNT is set. However, when a read-only map is created with MAP_NORESERVE it is indistinguishable from a normal mapping. When we then convert that to read/write we are forced to incorrectly create reservations for it as we have no record of the original MAP_NORESERVE. This patch introduces a new vma flag VM_NORESERVE which records the presence of the original MAP_NORESERVE flag. This allows us to distinguish these two circumstances and correctly account the reserve. As well as fixing this FIXME in the code, this makes it much easier to introduce MAP_NORESERVE support for huge pages as this flag is available consistantly for the life of the mapping. VM_ACCOUNT on the other hand is heavily used at the generic level in association with small pages. Signed-off-by: Andy Whitcroft <apw@shadowen.org> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Adam Litke <agl@us.ibm.com> Cc: Johannes Weiner <hannes@saeurebad.de> Cc: Andy Whitcroft <apw@shadowen.org> Cc: William Lee Irwin III <wli@holomorphy.com> Cc: Hugh Dickins <hugh@veritas.com> Cc: Michael Kerrisk <mtk.manpages@googlemail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 12:27:28 +08:00
VM_SHARED|VM_NORESERVE))) {
charged = nrpages;
if (security_vm_enough_memory_mm(mm, charged))
return -ENOMEM;
newflags |= VM_ACCOUNT;
}
}
/*
* First try to merge with previous and/or next vma.
*/
pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
*pprev = vma_merge(mm, *pprev, start, end, newflags,
vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma),
vma->vm_userfaultfd_ctx);
if (*pprev) {
vma = *pprev;
goto success;
}
*pprev = vma;
if (start != vma->vm_start) {
error = split_vma(mm, vma, start, 1);
if (error)
goto fail;
}
if (end != vma->vm_end) {
error = split_vma(mm, vma, end, 0);
if (error)
goto fail;
}
success:
/*
* vm_flags and vm_page_prot are protected by the mmap_sem
* held in write mode.
*/
vma->vm_flags = newflags;
mm: softdirty: enable write notifications on VMAs after VM_SOFTDIRTY cleared For VMAs that don't want write notifications, PTEs created for read faults have their write bit set. If the read fault happens after VM_SOFTDIRTY is cleared, then the PTE's softdirty bit will remain clear after subsequent writes. Here's a simple code snippet to demonstrate the bug: char* m = mmap(NULL, getpagesize(), PROT_READ | PROT_WRITE, MAP_ANONYMOUS | MAP_SHARED, -1, 0); system("echo 4 > /proc/$PPID/clear_refs"); /* clear VM_SOFTDIRTY */ assert(*m == '\0'); /* new PTE allows write access */ assert(!soft_dirty(x)); *m = 'x'; /* should dirty the page */ assert(soft_dirty(x)); /* fails */ With this patch, write notifications are enabled when VM_SOFTDIRTY is cleared. Furthermore, to avoid unnecessary faults, write notifications are disabled when VM_SOFTDIRTY is set. As a side effect of enabling and disabling write notifications with care, this patch fixes a bug in mprotect where vm_page_prot bits set by drivers were zapped on mprotect. An analogous bug was fixed in mmap by commit c9d0bf241451 ("mm: uncached vma support with writenotify"). Signed-off-by: Peter Feiner <pfeiner@google.com> Reported-by: Peter Feiner <pfeiner@google.com> Suggested-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Cyrill Gorcunov <gorcunov@openvz.org> Cc: Pavel Emelyanov <xemul@parallels.com> Cc: Jamie Liu <jamieliu@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-10-14 06:55:46 +08:00
dirty_accountable = vma_wants_writenotify(vma);
vma_set_page_prot(vma);
[PATCH] mm: tracking shared dirty pages Tracking of dirty pages in shared writeable mmap()s. The idea is simple: write protect clean shared writeable pages, catch the write-fault, make writeable and set dirty. On page write-back clean all the PTE dirty bits and write protect them once again. The implementation is a tad harder, mainly because the default backing_dev_info capabilities were too loosely maintained. Hence it is not enough to test the backing_dev_info for cap_account_dirty. The current heuristic is as follows, a VMA is eligible when: - its shared writeable (vm_flags & (VM_WRITE|VM_SHARED)) == (VM_WRITE|VM_SHARED) - it is not a 'special' mapping (vm_flags & (VM_PFNMAP|VM_INSERTPAGE)) == 0 - the backing_dev_info is cap_account_dirty mapping_cap_account_dirty(vma->vm_file->f_mapping) - f_op->mmap() didn't change the default page protection Page from remap_pfn_range() are explicitly excluded because their COW semantics are already horrid enough (see vm_normal_page() in do_wp_page()) and because they don't have a backing store anyway. mprotect() is taught about the new behaviour as well. However it overrides the last condition. Cleaning the pages on write-back is done with page_mkclean() a new rmap call. It can be called on any page, but is currently only implemented for mapped pages, if the page is found the be of a VMA that accounts dirty pages it will also wrprotect the PTE. Finally, in fs/buffers.c:try_to_free_buffers(); remove clear_page_dirty() from under ->private_lock. This seems to be safe, since ->private_lock is used to serialize access to the buffers, not the page itself. This is needed because clear_page_dirty() will call into page_mkclean() and would thereby violate locking order. [dhowells@redhat.com: Provide a page_mkclean() implementation for NOMMU] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Hugh Dickins <hugh@veritas.com> Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-26 14:30:57 +08:00
change_protection(vma, start, end, vma->vm_page_prot,
dirty_accountable, 0);
mm: fix mprotect() behaviour on VM_LOCKED VMAs On mlock(2) we trigger COW on private writable VMA to avoid faults in future. mm/gup.c: 840 long populate_vma_page_range(struct vm_area_struct *vma, 841 unsigned long start, unsigned long end, int *nonblocking) 842 { ... 855 * We want to touch writable mappings with a write fault in order 856 * to break COW, except for shared mappings because these don't COW 857 * and we would not want to dirty them for nothing. 858 */ 859 if ((vma->vm_flags & (VM_WRITE | VM_SHARED)) == VM_WRITE) 860 gup_flags |= FOLL_WRITE; But we miss this case when we make VM_LOCKED VMA writeable via mprotect(2). The test case: #define _GNU_SOURCE #include <fcntl.h> #include <stdio.h> #include <stdlib.h> #include <unistd.h> #include <sys/mman.h> #include <sys/resource.h> #include <sys/stat.h> #include <sys/time.h> #include <sys/types.h> #define PAGE_SIZE 4096 int main(int argc, char **argv) { struct rusage usage; long before; char *p; int fd; /* Create a file and populate first page of page cache */ fd = open("/tmp", O_TMPFILE | O_RDWR, S_IRUSR | S_IWUSR); write(fd, "1", 1); /* Create a *read-only* *private* mapping of the file */ p = mmap(NULL, PAGE_SIZE, PROT_READ, MAP_PRIVATE, fd, 0); /* * Since the mapping is read-only, mlock() will populate the mapping * with PTEs pointing to page cache without triggering COW. */ mlock(p, PAGE_SIZE); /* * Mapping became read-write, but it's still populated with PTEs * pointing to page cache. */ mprotect(p, PAGE_SIZE, PROT_READ | PROT_WRITE); getrusage(RUSAGE_SELF, &usage); before = usage.ru_minflt; /* Trigger COW: fault in mlock()ed VMA. */ *p = 1; getrusage(RUSAGE_SELF, &usage); printf("faults: %ld\n", usage.ru_minflt - before); return 0; } $ ./test faults: 1 Let's fix it by triggering populating of VMA in mprotect_fixup() on this condition. We don't care about population error as we don't in other similar cases i.e. mremap. [akpm@linux-foundation.org: tweak comment text] Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-25 07:56:10 +08:00
/*
* Private VM_LOCKED VMA becoming writable: trigger COW to avoid major
* fault on access.
*/
if ((oldflags & (VM_WRITE | VM_SHARED | VM_LOCKED)) == VM_LOCKED &&
(newflags & VM_WRITE)) {
populate_vma_page_range(vma, start, end, NULL);
}
vm_stat_account(mm, oldflags, vma->vm_file, -nrpages);
vm_stat_account(mm, newflags, vma->vm_file, nrpages);
perf_event_mmap(vma);
return 0;
fail:
vm_unacct_memory(charged);
return error;
}
SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len,
unsigned long, prot)
{
unsigned long vm_flags, nstart, end, tmp, reqprot;
struct vm_area_struct *vma, *prev;
int error = -EINVAL;
const int grows = prot & (PROT_GROWSDOWN|PROT_GROWSUP);
prot &= ~(PROT_GROWSDOWN|PROT_GROWSUP);
if (grows == (PROT_GROWSDOWN|PROT_GROWSUP)) /* can't be both */
return -EINVAL;
if (start & ~PAGE_MASK)
return -EINVAL;
if (!len)
return 0;
len = PAGE_ALIGN(len);
end = start + len;
if (end <= start)
return -ENOMEM;
if (!arch_validate_prot(prot))
return -EINVAL;
reqprot = prot;
/*
* Does the application expect PROT_READ to imply PROT_EXEC:
*/
if ((prot & PROT_READ) && (current->personality & READ_IMPLIES_EXEC))
prot |= PROT_EXEC;
vm_flags = calc_vm_prot_bits(prot);
down_write(&current->mm->mmap_sem);
vma = find_vma(current->mm, start);
error = -ENOMEM;
if (!vma)
goto out;
prev = vma->vm_prev;
if (unlikely(grows & PROT_GROWSDOWN)) {
if (vma->vm_start >= end)
goto out;
start = vma->vm_start;
error = -EINVAL;
if (!(vma->vm_flags & VM_GROWSDOWN))
goto out;
} else {
if (vma->vm_start > start)
goto out;
if (unlikely(grows & PROT_GROWSUP)) {
end = vma->vm_end;
error = -EINVAL;
if (!(vma->vm_flags & VM_GROWSUP))
goto out;
}
}
if (start > vma->vm_start)
prev = vma;
for (nstart = start ; ; ) {
unsigned long newflags;
/* Here we know that vma->vm_start <= nstart < vma->vm_end. */
newflags = vm_flags;
newflags |= (vma->vm_flags & ~(VM_READ | VM_WRITE | VM_EXEC));
/* newflags >> 4 shift VM_MAY% in place of VM_% */
if ((newflags & ~(newflags >> 4)) & (VM_READ | VM_WRITE | VM_EXEC)) {
error = -EACCES;
goto out;
}
error = security_file_mprotect(vma, reqprot, prot);
if (error)
goto out;
tmp = vma->vm_end;
if (tmp > end)
tmp = end;
error = mprotect_fixup(vma, &prev, nstart, tmp, newflags);
if (error)
goto out;
nstart = tmp;
if (nstart < prev->vm_end)
nstart = prev->vm_end;
if (nstart >= end)
goto out;
vma = prev->vm_next;
if (!vma || vma->vm_start != nstart) {
error = -ENOMEM;
goto out;
}
}
out:
up_write(&current->mm->mmap_sem);
return error;
}