The patch titled
revert mm-msync-cleanup
has been added to the -mm tree. Its filename is
revert-mm-msync-cleanup.patch
See http://www.zip.com.au/~akpm/linux/patches/stuff/added-to-mm.txt to find
out what to do about this
------------------------------------------------------
Subject: revert mm-msync-cleanup
From: Andrew Morton <akpm@xxxxxxxx>
It broke msync. (Thanks Arjan for diagnosing..)
Cc: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
Cc: Hugh Dickins <hugh@xxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxx>
---
mm/msync.c | 194 ++++++++++++++++++++++++++++++++++++++++++---------
1 files changed, 163 insertions(+), 31 deletions(-)
diff -puN mm/msync.c~revert-mm-msync-cleanup mm/msync.c
--- a/mm/msync.c~revert-mm-msync-cleanup
+++ a/mm/msync.c
@@ -7,33 +7,149 @@
/*
* The msync() system call.
*/
+#include <linux/slab.h>
+#include <linux/pagemap.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/mman.h>
+#include <linux/hugetlb.h>
+#include <linux/writeback.h>
#include <linux/file.h>
#include <linux/syscalls.h>
+#include <asm/pgtable.h>
+#include <asm/tlbflush.h>
+
+static unsigned long msync_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
+ unsigned long addr, unsigned long end)
+{
+ pte_t *pte;
+ spinlock_t *ptl;
+ int progress = 0;
+ unsigned long ret = 0;
+
+again:
+ pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+ do {
+ struct page *page;
+
+ if (progress >= 64) {
+ progress = 0;
+ if (need_resched() || need_lockbreak(ptl))
+ break;
+ }
+ progress++;
+ if (!pte_present(*pte))
+ continue;
+ if (!pte_maybe_dirty(*pte))
+ continue;
+ page = vm_normal_page(vma, addr, *pte);
+ if (!page)
+ continue;
+ if (ptep_clear_flush_dirty(vma, addr, pte) ||
+ page_test_and_clear_dirty(page))
+ ret += set_page_dirty(page);
+ progress += 3;
+ } while (pte++, addr += PAGE_SIZE, addr != end);
+ pte_unmap_unlock(pte - 1, ptl);
+ cond_resched();
+ if (addr != end)
+ goto again;
+ return ret;
+}
+
+static inline unsigned long msync_pmd_range(struct vm_area_struct *vma,
+ pud_t *pud, unsigned long addr, unsigned long end)
+{
+ pmd_t *pmd;
+ unsigned long next;
+ unsigned long ret = 0;
+
+ pmd = pmd_offset(pud, addr);
+ do {
+ next = pmd_addr_end(addr, end);
+ if (pmd_none_or_clear_bad(pmd))
+ continue;
+ ret += msync_pte_range(vma, pmd, addr, next);
+ } while (pmd++, addr = next, addr != end);
+ return ret;
+}
+
+static inline unsigned long msync_pud_range(struct vm_area_struct *vma,
+ pgd_t *pgd, unsigned long addr, unsigned long end)
+{
+ pud_t *pud;
+ unsigned long next;
+ unsigned long ret = 0;
+
+ pud = pud_offset(pgd, addr);
+ do {
+ next = pud_addr_end(addr, end);
+ if (pud_none_or_clear_bad(pud))
+ continue;
+ ret += msync_pmd_range(vma, pud, addr, next);
+ } while (pud++, addr = next, addr != end);
+ return ret;
+}
+
+static unsigned long msync_page_range(struct vm_area_struct *vma,
+ unsigned long addr, unsigned long end)
+{
+ pgd_t *pgd;
+ unsigned long next;
+ unsigned long ret = 0;
+
+ /* For hugepages we can't go walking the page table normally,
+ * but that's ok, hugetlbfs is memory based, so we don't need
+ * to do anything more on an msync().
+ */
+ if (vma->vm_flags & VM_HUGETLB)
+ return 0;
+
+ BUG_ON(addr >= end);
+ pgd = pgd_offset(vma->vm_mm, addr);
+ flush_cache_range(vma, addr, end);
+ do {
+ next = pgd_addr_end(addr, end);
+ if (pgd_none_or_clear_bad(pgd))
+ continue;
+ ret += msync_pud_range(vma, pgd, addr, next);
+ } while (pgd++, addr = next, addr != end);
+ return ret;
+}
+
/*
* MS_SYNC syncs the entire file - including mappings.
*
- * MS_ASYNC does not start I/O (it used to, up to 2.5.67).
- * Nor does it marks the relevant pages dirty (it used to up to 2.6.17).
- * Now it doesn't do anything, since dirty pages are properly tracked.
- *
- * The application may now run fsync() to
+ * MS_ASYNC does not start I/O (it used to, up to 2.5.67). Instead, it just
+ * marks the relevant pages dirty. The application may now run fsync() to
* write out the dirty pages and wait on the writeout and check the result.
* Or the application may run fadvise(FADV_DONTNEED) against the fd to start
* async writeout immediately.
* So by _not_ starting I/O in MS_ASYNC we provide complete flexibility to
* applications.
*/
+static int msync_interval(struct vm_area_struct *vma, unsigned long addr,
+ unsigned long end, int flags,
+ unsigned long *nr_pages_dirtied)
+{
+ struct file *file = vma->vm_file;
+
+ if ((flags & MS_INVALIDATE) && (vma->vm_flags & VM_LOCKED))
+ return -EBUSY;
+
+ if (file && (vma->vm_flags & VM_SHARED))
+ *nr_pages_dirtied = msync_page_range(vma, addr, end);
+ return 0;
+}
+
asmlinkage long sys_msync(unsigned long start, size_t len, int flags)
{
unsigned long end;
- struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
int unmapped_error = 0;
int error = -EINVAL;
+ int done = 0;
if (flags & ~(MS_ASYNC | MS_INVALIDATE | MS_SYNC))
goto out;
@@ -53,48 +169,64 @@ asmlinkage long sys_msync(unsigned long
* If the interval [start,end) covers some unmapped address ranges,
* just ignore them, but return -ENOMEM at the end.
*/
- down_read(&mm->mmap_sem);
- vma = find_vma(mm, start);
- for (;;) {
+ down_read(¤t->mm->mmap_sem);
+ vma = find_vma(current->mm, start);
+ if (!vma) {
+ error = -ENOMEM;
+ goto out_unlock;
+ }
+ do {
+ unsigned long nr_pages_dirtied = 0;
struct file *file;
- /* Still start < end. */
- error = -ENOMEM;
- if (!vma)
- goto out_unlock;
/* Here start < vma->vm_end. */
if (start < vma->vm_start) {
- start = vma->vm_start;
- if (start >= end)
- goto out_unlock;
unmapped_error = -ENOMEM;
+ start = vma->vm_start;
}
/* Here vma->vm_start <= start < vma->vm_end. */
- if ((flags & MS_INVALIDATE) &&
- (vma->vm_flags & VM_LOCKED)) {
- error = -EBUSY;
- goto out_unlock;
+ if (end <= vma->vm_end) {
+ if (start < end) {
+ error = msync_interval(vma, start, end, flags,
+ &nr_pages_dirtied);
+ if (error)
+ goto out_unlock;
+ }
+ error = unmapped_error;
+ done = 1;
+ } else {
+ /* Here vma->vm_start <= start < vma->vm_end < end. */
+ error = msync_interval(vma, start, vma->vm_end, flags,
+ &nr_pages_dirtied);
+ if (error)
+ goto out_unlock;
}
file = vma->vm_file;
start = vma->vm_end;
- if ((flags & MS_SYNC) && file &&
+ if ((flags & MS_ASYNC) && file && nr_pages_dirtied) {
+ get_file(file);
+ up_read(¤t->mm->mmap_sem);
+ balance_dirty_pages_ratelimited_nr(file->f_mapping,
+ nr_pages_dirtied);
+ fput(file);
+ down_read(¤t->mm->mmap_sem);
+ vma = find_vma(current->mm, start);
+ } else if ((flags & MS_SYNC) && file &&
(vma->vm_flags & VM_SHARED)) {
get_file(file);
- up_read(&mm->mmap_sem);
+ up_read(¤t->mm->mmap_sem);
error = do_fsync(file, 0);
fput(file);
- if (error || start >= end)
- goto out;
- down_read(&mm->mmap_sem);
- vma = find_vma(mm, start);
- } else {
- if (start >= end)
+ down_read(¤t->mm->mmap_sem);
+ if (error)
goto out_unlock;
+ vma = find_vma(current->mm, start);
+ } else {
vma = vma->vm_next;
}
- }
+ } while (vma && !done);
out_unlock:
- up_read(&mm->mmap_sem);
+ up_read(¤t->mm->mmap_sem);
out:
- return error ? : unmapped_error;
+ return error;
}
_
Patches currently in -mm which might be from akpm@xxxxxxxx are
origin.patch
msrc-use-register_hotcpu_notifier.patch
disable-debugging-version-of-write_lock.patch
git-acpi.patch
git-acpi-fixup.patch
acpi_srat-needs-acpi.patch
acpi-asus-s3-resume-fix-fix.patch
sony_apci-resume.patch
git-agpgart.patch
git-agpgart-fixup.patch
kauditd_thread-warning-fix.patch
git-dvb.patch
i2c-801-64bit-resource-fix.patch
git-geode-fixup.patch
git-gfs2.patch
git-gfs2-fixup.patch
gfs2-get_sb_dev-fix.patch
git-ia64-fixup.patch
genirq-rename-desc-handler-to-desc-chip-ia64-fix-2.patch
revert-input-atkbd-fix-hangeul-hanja-keys.patch
revert-ignore-makes-built-in-rules-variables.patch
revert-sparc-build-breakage.patch
git-klibc.patch
git-klibc-fixup.patch
git-hdrcleanup-vs-git-klibc-on-ia64.patch
git-hdrcleanup-vs-git-klibc-on-ia64-2.patch
git-libata-all.patch
sata-is-bust-on-s390.patch
forcedeth-typecast-cleanup.patch
drivers-net-ns83820c-add-paramter-to-disable-auto.patch
af_unix-datagram-getpeersec-fix.patch
git-pcmcia-fixup.patch
git-sas.patch
serial-8250-sysrq-deadlock-fix.patch
serial-fix-uart_bug_txen-test.patch
revert-gregkh-pci-pci-test-that-drivers-properly-call-pci_set_master.patch
clear-abnormal-poweroff-flag-on-via-southbridges-fix-resume-fix.patch
revert-VIA-quirk-fixup-additional-PCI-IDs.patch
revert-PCI-quirk-VIA-IRQ-fixup-should-only-run-for-VIA-southbridges.patch
git-scsi-misc.patch
areca-raid-linux-scsi-driver.patch
git-scsi-target-fixup.patch
pm-usb-hcds-use-pm_event_prethaw-fix.patch
git-supertrak-fixup.patch
bcm43xx-opencoded-locking-fix.patch
adix-tree-rcu-lockless-readside-update-tidy.patch
zoned-vm-counters-create-vmstatc-h-from-page_allocc-h-s390-fix.patch
zoned-vm-counters-create-vmstatc-h-from-page_allocc-h-fix.patch
zoned-vm-counters-basic-zvc-zoned-vm-counter-implementation-tidy.patch
zoned-vm-counters-basic-zvc-zoned-vm-counter-implementation-export-vm_stat.patch
zoned-vm-counters-convert-nr_mapped-to-per-zone-counter-fix.patch
zoned-vm-counters-remove-nr_file_mapped-from-scan-control-structure-fix.patch
zoned-vm-counters-conversion-of-nr_slab-to-per-zone-counter-fix.patch
zoned-vm-counters-conversion-of-nr_pagetables-to-per-zone-counter-fix.patch
zoned-vm-counters-conversion-of-nr_dirty-to-per-zone-counter-fix.patch
zoned-vm-counters-conversion-of-nr_writeback-to-per-zone-counter.patch
zoned-vm-counters-conversion-of-nr_writeback-to-per-zone-counter-fix.patch
zoned-vm-counters-conversion-of-nr_unstable-to-per-zone-counter-nfs-fix.patch
zoned-vm-counters-conversion-of-nr_unstable-to-per-zone-counter-fix.patch
zoned-vm-counters-conversion-of-nr_bounce-to-per-zone-counter.patch
zoned-vm-counters-conversion-of-nr_bounce-to-per-zone-counter-fix.patch
zoned-vm-counters-remove-read_page_state.patch
mm-tracking-shared-dirty-pages-checks.patch
mm-tracking-shared-dirty-pages-wimp.patch
slab-consolidate-code-to-free-slabs-from-freelist-fix.patch
acx1xx-wireless-driver.patch
tiacx-pci-build-fix.patch
tiacx-ia64-fix.patch
add-smp_setup_processor_id.patch
deprecate-smbfs-in-favour-of-cifs.patch
destroy-the-dentries-contributed-by-a-superblock-on-unmounting-fix.patch
cond_resched-fix.patch
reiserfs-on-demand-bitmap-loading-fix.patch
per-task-delay-accounting-proc-export-of-aggregated-block-i-o-delays-warning-fix.patch
delay-accounting-taskstats-interface-send-tgid-once-fixes.patch
sched-clean-up-fallout-of-recent-changes-fix.patch
swap_prefetch-vs-zoned-counters.patch
mark-address_space_operations-const-vs-ecryptfs-mmap-operations.patch
ecryptfs-alpha-build-fix.patch
ecryptfs-more-elegant-aes-key-size-manipulation-tidy.patch
ecryptfs-get_sb_dev-fix.patch
namespaces-add-nsproxy-dont-include-compileh.patch
namespaces-utsname-switch-to-using-uts-namespaces-alpha-fix.patch
namespaces-utsname-use-init_utsname-when-appropriate-cifs-update.patch
namespaces-utsname-implement-utsname-namespaces-export.patch
namespaces-utsname-implement-utsname-namespaces-dont-include-compileh.patch
namespaces-utsname-sysctl-hack-cleanup-2-fix.patch
ipc-namespace-core-fix.patch
task-watchers-task-watchers-tidy.patch
task-watchers-add-support-for-per-task-watchers-warning-fix.patch
readahead-sysctl-parameters-fix.patch
make-copy_from_user_inatomic-not-zero-the-tail-on-i386-vs-reiser4.patch
reiser4-hardirq-include-fix.patch
reiser4-run-truncate_inode_pages-in-reiser4_delete_inode.patch
reiser4-get_sb_dev-fix.patch
reiser4-vs-zoned-allocator.patch
hpt3xx-rework-rate-filtering-tidy.patch
lockdep-add-disable-enable_irq_lockdep-api.patch
lockdep-irqtrace-subsystem-x86_64-support.patch
genirq-convert-the-i386-architecture-to-irq-chips-fix-2.patch
genirq-msi-simplify-msi-enable-and-disable-fix.patch
genirq-i386-irq-remove-the-msi-assumption-that-irq-==-vector-fix-tidies.patch
srcu-rcu-variant-permitting-read-side-blocking-fixes.patch
srcu-add-srcu-operations-to-rcutorture-fix.patch
srcu-2-add-srcu-operations-to-rcutorture-fix.patch
nr_blockdev_pages-in_interrupt-warning.patch
device-suspend-debug.patch
revert-tty-buffering-comment-out-debug-code.patch
slab-leaks3-default-y.patch
x86-kmap_atomic-debugging.patch
revert-mm-msync-cleanup.patch
-
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
