summaryrefslogtreecommitdiff
path: root/mm/mprotect.c
diff options
context:
space:
mode:
authorDavid Hildenbrand <david@redhat.com>2022-06-14 11:36:29 +0200
committerakpm <akpm@linux-foundation.org>2022-07-03 18:08:44 -0700
commit64fe24a3e05e5f3ac56fcd45afd2fd1d9cc8fcb6 (patch)
treec2522e10486a6c5962dada98f9d03d31a0930e7f /mm/mprotect.c
parent50b0f797cab6cb7dff418777e1acf82dfd3568f8 (diff)
downloadlinux-64fe24a3e05e5f3ac56fcd45afd2fd1d9cc8fcb6.tar.gz
mm/mprotect: try avoiding write faults for exclusive anonymous pages when changing protection
Similar to our MM_CP_DIRTY_ACCT handling for shared, writable mappings, we can try mapping anonymous pages in a private writable mapping writable if they are exclusive, the PTE is already dirty, and no special handling applies. Mapping the anonymous page writable is essentially the same thing the write fault handler would do in this case. Special handling is required for uffd-wp and softdirty tracking, so take care of that properly. Also, leave PROT_NONE handling alone for now; in the future, we could similarly extend the logic in do_numa_page() or use pte_mk_savedwrite() here. While this improves mprotect(PROT_READ)+mprotect(PROT_READ|PROT_WRITE) performance, it should also be a valuable optimization for uffd-wp, when un-protecting. This has been previously suggested by Peter Collingbourne in [1], relevant in the context of the Scudo memory allocator, before we had PageAnonExclusive. This commit doesn't add the same handling for PMDs (i.e., anonymous THP, anonymous hugetlb); benchmark results from Andrea indicate that there are minor performance gains, so it's might still be valuable to streamline that logic for all anonymous pages in the future. As we now also set MM_CP_DIRTY_ACCT for private mappings, let's rename it to MM_CP_TRY_CHANGE_WRITABLE, to make it clearer what's actually happening. Micro-benchmark courtesy of Andrea: === #define _GNU_SOURCE #include <sys/mman.h> #include <stdlib.h> #include <string.h> #include <stdio.h> #include <unistd.h> #define SIZE (1024*1024*1024) int main(int argc, char *argv[]) { char *p; if (posix_memalign((void **)&p, sysconf(_SC_PAGESIZE)*512, SIZE)) perror("posix_memalign"), exit(1); if (madvise(p, SIZE, argc > 1 ? MADV_HUGEPAGE : MADV_NOHUGEPAGE)) perror("madvise"); explicit_bzero(p, SIZE); for (int loops = 0; loops < 40; loops++) { if (mprotect(p, SIZE, PROT_READ)) perror("mprotect"), exit(1); if (mprotect(p, SIZE, PROT_READ|PROT_WRITE)) perror("mprotect"), exit(1); explicit_bzero(p, SIZE); } } === Results on my Ryzen 9 3900X: Stock 10 runs (lower is better): AVG 6.398s, STDEV 0.043 Patched 10 runs (lower is better): AVG 3.780s, STDEV 0.026 === [1] https://lkml.kernel.org/r/20210429214801.2583336-1-pcc@google.com Link: https://lkml.kernel.org/r/20220614093629.76309-1-david@redhat.com Signed-off-by: David Hildenbrand <david@redhat.com> Suggested-by: Peter Collingbourne <pcc@google.com> Acked-by: Peter Xu <peterx@redhat.com> Cc: Nadav Amit <nadav.amit@gmail.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Hugh Dickins <hughd@google.com> Cc: Mel Gorman <mgorman@techsingularity.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Diffstat (limited to 'mm/mprotect.c')
-rw-r--r--mm/mprotect.c77
1 files changed, 62 insertions, 15 deletions
diff --git a/mm/mprotect.c b/mm/mprotect.c
index ba5592655ee3..996a97e213ad 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -38,6 +38,39 @@
#include "internal.h"
+static inline bool can_change_pte_writable(struct vm_area_struct *vma,
+ unsigned long addr, pte_t pte)
+{
+ struct page *page;
+
+ VM_BUG_ON(!(vma->vm_flags & VM_WRITE) || pte_write(pte));
+
+ if (pte_protnone(pte) || !pte_dirty(pte))
+ return false;
+
+ /* Do we need write faults for softdirty tracking? */
+ if ((vma->vm_flags & VM_SOFTDIRTY) && !pte_soft_dirty(pte))
+ return false;
+
+ /* Do we need write faults for uffd-wp tracking? */
+ if (userfaultfd_pte_wp(vma, pte))
+ return false;
+
+ if (!(vma->vm_flags & VM_SHARED)) {
+ /*
+ * We can only special-case on exclusive anonymous pages,
+ * because we know that our write-fault handler similarly would
+ * map them writable without any additional checks while holding
+ * the PT lock.
+ */
+ page = vm_normal_page(vma, addr, pte);
+ if (!page || !PageAnon(page) || !PageAnonExclusive(page))
+ return false;
+ }
+
+ return true;
+}
+
static unsigned long change_pte_range(struct mmu_gather *tlb,
struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr,
unsigned long end, pgprot_t newprot, unsigned long cp_flags)
@@ -46,7 +79,6 @@ static unsigned long change_pte_range(struct mmu_gather *tlb,
spinlock_t *ptl;
unsigned long pages = 0;
int target_node = NUMA_NO_NODE;
- bool dirty_accountable = cp_flags & MM_CP_DIRTY_ACCT;
bool prot_numa = cp_flags & MM_CP_PROT_NUMA;
bool uffd_wp = cp_flags & MM_CP_UFFD_WP;
bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE;
@@ -137,21 +169,27 @@ static unsigned long change_pte_range(struct mmu_gather *tlb,
ptent = pte_wrprotect(ptent);
ptent = pte_mkuffd_wp(ptent);
} else if (uffd_wp_resolve) {
- /*
- * Leave the write bit to be handled
- * by PF interrupt handler, then
- * things like COW could be properly
- * handled.
- */
ptent = pte_clear_uffd_wp(ptent);
}
- /* Avoid taking write faults for known dirty pages */
- if (dirty_accountable && pte_dirty(ptent) &&
- (pte_soft_dirty(ptent) ||
- !(vma->vm_flags & VM_SOFTDIRTY))) {
+ /*
+ * In some writable, shared mappings, we might want
+ * to catch actual write access -- see
+ * vma_wants_writenotify().
+ *
+ * In all writable, private mappings, we have to
+ * properly handle COW.
+ *
+ * In both cases, we can sometimes still change PTEs
+ * writable and avoid the write-fault handler, for
+ * example, if a PTE is already dirty and no other
+ * COW or special handling is required.
+ */
+ if ((cp_flags & MM_CP_TRY_CHANGE_WRITABLE) &&
+ !pte_write(ptent) &&
+ can_change_pte_writable(vma, addr, ptent))
ptent = pte_mkwrite(ptent);
- }
+
ptep_modify_prot_commit(vma, addr, pte, oldpte, ptent);
if (pte_needs_flush(oldpte, ptent))
tlb_flush_pte_range(tlb, addr, PAGE_SIZE);
@@ -505,9 +543,9 @@ mprotect_fixup(struct mmu_gather *tlb, struct vm_area_struct *vma,
unsigned long oldflags = vma->vm_flags;
long nrpages = (end - start) >> PAGE_SHIFT;
unsigned long charged = 0;
+ bool try_change_writable;
pgoff_t pgoff;
int error;
- int dirty_accountable = 0;
if (newflags == oldflags) {
*pprev = vma;
@@ -583,11 +621,20 @@ success:
* held in write mode.
*/
vma->vm_flags = newflags;
- dirty_accountable = vma_wants_writenotify(vma, vma->vm_page_prot);
+ /*
+ * We want to check manually if we can change individual PTEs writable
+ * if we can't do that automatically for all PTEs in a mapping. For
+ * private mappings, that's always the case when we have write
+ * permissions as we properly have to handle COW.
+ */
+ if (vma->vm_flags & VM_SHARED)
+ try_change_writable = vma_wants_writenotify(vma, vma->vm_page_prot);
+ else
+ try_change_writable = !!(vma->vm_flags & VM_WRITE);
vma_set_page_prot(vma);
change_protection(tlb, vma, start, end, vma->vm_page_prot,
- dirty_accountable ? MM_CP_DIRTY_ACCT : 0);
+ try_change_writable ? MM_CP_TRY_CHANGE_WRITABLE : 0);
/*
* Private VM_LOCKED VMA becoming writable: trigger COW to avoid major