The patch titled
mm: tracking shared dirty pages
has been added to the -mm tree. Its filename is
mm-tracking-shared-dirty-pages.patch
See http://www.zip.com.au/~akpm/linux/patches/stuff/added-to-mm.txt to find
out what to do about this
------------------------------------------------------
Subject: mm: tracking shared dirty pages
From: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxx>
---
fs/buffer.c | 2 -
include/linux/mm.h | 6 +++
include/linux/rmap.h | 8 ++++
mm/memory.c | 31 +++++++++++++++---
mm/mmap.c | 34 ++++++++++++++++----
mm/mprotect.c | 7 +++-
mm/page-writeback.c | 2 +
mm/rmap.c | 68 +++++++++++++++++++++++++++++++++++++++++
8 files changed, 144 insertions(+), 14 deletions(-)
diff -puN fs/buffer.c~mm-tracking-shared-dirty-pages fs/buffer.c
--- a/fs/buffer.c~mm-tracking-shared-dirty-pages
+++ a/fs/buffer.c
@@ -2983,6 +2983,7 @@ int try_to_free_buffers(struct page *pag
spin_lock(&mapping->private_lock);
ret = drop_buffers(page, &buffers_to_free);
+ spin_unlock(&mapping->private_lock);
if (ret) {
/*
* If the filesystem writes its buffers by hand (eg ext3)
@@ -2994,7 +2995,6 @@ int try_to_free_buffers(struct page *pag
*/
clear_page_dirty(page);
}
- spin_unlock(&mapping->private_lock);
out:
if (buffers_to_free) {
struct buffer_head *bh = buffers_to_free;
diff -puN include/linux/mm.h~mm-tracking-shared-dirty-pages include/linux/mm.h
--- a/include/linux/mm.h~mm-tracking-shared-dirty-pages
+++ a/include/linux/mm.h
@@ -181,6 +181,12 @@ extern unsigned int kobjsize(const void
#define VM_SequentialReadHint(v) ((v)->vm_flags & VM_SEQ_READ)
#define VM_RandomReadHint(v) ((v)->vm_flags & VM_RAND_READ)
+static inline int is_shared_writable(unsigned int flags)
+{
+ return (flags & (VM_SHARED|VM_WRITE|VM_PFNMAP)) ==
+ (VM_SHARED|VM_WRITE);
+}
+
/*
* mapping from the currently active vm_flags protection bits (the
* low four bits) to a page protection mask..
diff -puN include/linux/rmap.h~mm-tracking-shared-dirty-pages include/linux/rmap.h
--- a/include/linux/rmap.h~mm-tracking-shared-dirty-pages
+++ a/include/linux/rmap.h
@@ -103,6 +103,14 @@ pte_t *page_check_address(struct page *,
*/
unsigned long page_address_in_vma(struct page *, struct vm_area_struct *);
+/*
+ * Cleans the PTEs of shared mappings.
+ * (and since clean PTEs should also be readonly, write protects them too)
+ *
+ * returns the number of cleaned PTEs.
+ */
+int page_mkclean(struct page *);
+
#else /* !CONFIG_MMU */
#define anon_vma_init() do {} while (0)
diff -puN mm/memory.c~mm-tracking-shared-dirty-pages mm/memory.c
--- a/mm/memory.c~mm-tracking-shared-dirty-pages
+++ a/mm/memory.c
@@ -937,6 +937,12 @@ struct page *follow_page(struct vm_area_
pte = *ptep;
if (!pte_present(pte))
goto unlock;
+ /*
+ * This is not fully correct in the light of trapping write faults
+ * for writable shared mappings. However since we're going to mark
+ * the page dirty anyway some few lines downward, we might as well
+ * take the write fault now.
+ */
if ((flags & FOLL_WRITE) && !pte_write(pte))
goto unlock;
page = vm_normal_page(vma, address, pte);
@@ -1457,14 +1463,15 @@ static int do_wp_page(struct mm_struct *
{
struct page *old_page, *new_page;
pte_t entry;
- int reuse, ret = VM_FAULT_MINOR;
+ int reuse = 0;
+ int ret = VM_FAULT_MINOR;
+ struct page *dirty_page = NULL;
old_page = vm_normal_page(vma, address, orig_pte);
if (!old_page)
goto gotten;
- if (unlikely((vma->vm_flags & (VM_SHARED|VM_WRITE)) ==
- (VM_SHARED|VM_WRITE))) {
+ if (unlikely(is_shared_writable(vma->vm_flags))) {
if (vma->vm_ops && vma->vm_ops->page_mkwrite) {
/*
* Notify the address space that the page is about to
@@ -1493,13 +1500,12 @@ static int do_wp_page(struct mm_struct *
if (!pte_same(*page_table, orig_pte))
goto unlock;
}
-
+ dirty_page = old_page;
+ get_page(dirty_page);
reuse = 1;
} else if (PageAnon(old_page) && !TestSetPageLocked(old_page)) {
reuse = can_share_swap_page(old_page);
unlock_page(old_page);
- } else {
- reuse = 0;
}
if (reuse) {
@@ -1565,6 +1571,10 @@ gotten:
page_cache_release(old_page);
unlock:
pte_unmap_unlock(page_table, ptl);
+ if (dirty_page) {
+ set_page_dirty(dirty_page);
+ put_page(dirty_page);
+ }
return ret;
oom:
if (old_page)
@@ -2094,6 +2104,7 @@ static int do_no_page(struct mm_struct *
unsigned int sequence = 0;
int ret = VM_FAULT_MINOR;
int anon = 0;
+ struct page *dirty_page = NULL;
pte_unmap(page_table);
BUG_ON(vma->vm_flags & VM_PFNMAP);
@@ -2188,6 +2199,10 @@ retry:
} else {
inc_mm_counter(mm, file_rss);
page_add_file_rmap(new_page);
+ if (write_access) {
+ dirty_page = new_page;
+ get_page(dirty_page);
+ }
}
} else {
/* One of our sibling threads was faster, back out. */
@@ -2200,6 +2215,10 @@ retry:
lazy_mmu_prot_update(entry);
unlock:
pte_unmap_unlock(page_table, ptl);
+ if (dirty_page) {
+ set_page_dirty(dirty_page);
+ put_page(dirty_page);
+ }
return ret;
oom:
page_cache_release(new_page);
diff -puN mm/mmap.c~mm-tracking-shared-dirty-pages mm/mmap.c
--- a/mm/mmap.c~mm-tracking-shared-dirty-pages
+++ a/mm/mmap.c
@@ -25,6 +25,7 @@
#include <linux/mount.h>
#include <linux/mempolicy.h>
#include <linux/rmap.h>
+#include <linux/backing-dev.h>
#include <asm/uaccess.h>
#include <asm/cacheflush.h>
@@ -888,6 +889,7 @@ unsigned long do_mmap_pgoff(struct file
struct rb_node ** rb_link, * rb_parent;
int accountable = 1;
unsigned long charged = 0, reqprot = prot;
+ struct address_space *mapping = NULL;
if (file) {
if (is_file_hugepages(file))
@@ -1084,18 +1086,13 @@ munmap_back:
error = file->f_op->mmap(file, vma);
if (error)
goto unmap_and_free_vma;
+
} else if (vm_flags & VM_SHARED) {
error = shmem_zero_setup(vma);
if (error)
goto free_vma;
}
- /* Don't make the VMA automatically writable if it's shared, but the
- * backer wishes to know when pages are first written to */
- if (vma->vm_ops && vma->vm_ops->page_mkwrite)
- vma->vm_page_prot =
- protection_map[vm_flags & (VM_READ|VM_WRITE|VM_EXEC)];
-
/* We set VM_ACCOUNT in a shared mapping's vm_flags, to inform
* shmem_zero_setup (perhaps called through /dev/zero's ->mmap)
* that memory reservation must be checked; but that reservation
@@ -1113,6 +1110,31 @@ munmap_back:
pgoff = vma->vm_pgoff;
vm_flags = vma->vm_flags;
+ /*
+ * Tracking of dirty pages for shared writable mappings. Do this by
+ * write protecting writable pages, and mark dirty in the write fault.
+ *
+ * Modify vma->vm_page_prot (the default protection for new pages)
+ * to this effect.
+ *
+ * Cannot do before because the condition depends on:
+ * - backing_dev_info having the right capabilities
+ * (set by f_op->open())
+ * - vma->vm_flags being fully set
+ * (finished in f_op->mmap(), which could call remap_pfn_range())
+ *
+ * Also, cannot reset vma->vm_page_prot from vma->vm_flags because
+ * f_op->mmap() can modify it.
+ */
+ if (is_shared_writable(vm_flags) && vma->vm_file)
+ mapping = vma->vm_file->f_mapping;
+ if ((mapping && mapping_cap_account_dirty(mapping)) ||
+ (vma->vm_ops && vma->vm_ops->page_mkwrite))
+ vma->vm_page_prot =
+ __pgprot(pte_val
+ (pte_wrprotect
+ (__pte(pgprot_val(vma->vm_page_prot)))));
+
if (!file || !vma_merge(mm, prev, addr, vma->vm_end,
vma->vm_flags, NULL, file, pgoff, vma_policy(vma))) {
file = vma->vm_file;
diff -puN mm/mprotect.c~mm-tracking-shared-dirty-pages mm/mprotect.c
--- a/mm/mprotect.c~mm-tracking-shared-dirty-pages
+++ a/mm/mprotect.c
@@ -21,6 +21,7 @@
#include <linux/syscalls.h>
#include <linux/swap.h>
#include <linux/swapops.h>
+#include <linux/backing-dev.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
#include <asm/cacheflush.h>
@@ -124,6 +125,7 @@ mprotect_fixup(struct vm_area_struct *vm
long nrpages = (end - start) >> PAGE_SHIFT;
unsigned long charged = 0;
unsigned int mask;
+ struct address_space *mapping = NULL;
pgprot_t newprot;
pgoff_t pgoff;
int error;
@@ -179,7 +181,10 @@ success:
/* Don't make the VMA automatically writable if it's shared, but the
* backer wishes to know when pages are first written to */
mask = VM_READ|VM_WRITE|VM_EXEC|VM_SHARED;
- if (vma->vm_ops && vma->vm_ops->page_mkwrite)
+ if (is_shared_writable(newflags) && vma->vm_file)
+ mapping = vma->vm_file->f_mapping;
+ if ((mapping && mapping_cap_account_dirty(mapping)) ||
+ (vma->vm_ops && vma->vm_ops->page_mkwrite))
mask &= ~VM_SHARED;
newprot = protection_map[newflags & mask];
diff -puN mm/page-writeback.c~mm-tracking-shared-dirty-pages mm/page-writeback.c
--- a/mm/page-writeback.c~mm-tracking-shared-dirty-pages
+++ a/mm/page-writeback.c
@@ -29,6 +29,7 @@
#include <linux/sysctl.h>
#include <linux/cpu.h>
#include <linux/syscalls.h>
+#include <linux/rmap.h>
/*
* The maximum number of pages to writeout in a single bdflush/kupdate
@@ -759,6 +760,7 @@ int clear_page_dirty_for_io(struct page
if (mapping) {
if (TestClearPageDirty(page)) {
+ page_mkclean(page);
if (mapping_cap_account_dirty(mapping))
dec_page_state(nr_dirty);
return 1;
diff -puN mm/rmap.c~mm-tracking-shared-dirty-pages mm/rmap.c
--- a/mm/rmap.c~mm-tracking-shared-dirty-pages
+++ a/mm/rmap.c
@@ -53,6 +53,7 @@
#include <linux/rmap.h>
#include <linux/rcupdate.h>
#include <linux/module.h>
+#include <linux/backing-dev.h>
#include <asm/tlbflush.h>
@@ -434,6 +435,73 @@ int page_referenced(struct page *page, i
return referenced;
}
+static int page_mkclean_one(struct page *page, struct vm_area_struct *vma, int protect)
+{
+ struct mm_struct *mm = vma->vm_mm;
+ unsigned long address;
+ pte_t *pte, entry;
+ spinlock_t *ptl;
+ int ret = 0;
+
+ address = vma_address(page, vma);
+ if (address == -EFAULT)
+ goto out;
+
+ pte = page_check_address(page, mm, address, &ptl);
+ if (!pte)
+ goto out;
+
+ if (!(pte_dirty(*pte) || (protect && pte_write(*pte))))
+ goto unlock;
+
+ entry = ptep_get_and_clear(mm, address, pte);
+ entry = pte_mkclean(entry);
+ if (protect)
+ entry = pte_wrprotect(entry);
+ ptep_establish(vma, address, pte, entry);
+ lazy_mmu_prot_update(entry);
+ ret = 1;
+
+unlock:
+ pte_unmap_unlock(pte, ptl);
+out:
+ return ret;
+}
+
+static int page_mkclean_file(struct address_space *mapping, struct page *page)
+{
+ pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
+ struct vm_area_struct *vma;
+ struct prio_tree_iter iter;
+ int ret = 0;
+
+ BUG_ON(PageAnon(page));
+
+ spin_lock(&mapping->i_mmap_lock);
+ vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
+ int protect = mapping_cap_account_dirty(mapping) &&
+ is_shared_writable(vma->vm_flags);
+ ret += page_mkclean_one(page, vma, protect);
+ }
+ spin_unlock(&mapping->i_mmap_lock);
+ return ret;
+}
+
+int page_mkclean(struct page *page)
+{
+ int ret = 0;
+
+ BUG_ON(!PageLocked(page));
+
+ if (page_mapped(page)) {
+ struct address_space *mapping = page_mapping(page);
+ if (mapping)
+ ret = page_mkclean_file(mapping, page);
+ }
+
+ return ret;
+}
+
/**
* page_set_anon_rmap - setup new anonymous rmap
* @page: the page to add the mapping to
_
Patches currently in -mm which might be from a.p.zijlstra@xxxxxxxxx are
buglet-in-radix_tree_tag_set.patch
add-page_mkwrite-vm_operations-method-fix.patch
mm-tracking-shared-dirty-pages.patch
mm-balance-dirty-pages.patch
mm-msync-cleanup.patch
mm-optimize-the-new-mprotect-code-a-bit.patch
mm-small-cleanup-of-install_page.patch
mm-remove-some-update_mmu_cache-calls.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
