Now that we have proper isolation in place with cgroups2 we have started going
through and fixing the various priority inversions. Most are all gone now, but
this one is sort of weird since it's not necessarily a priority inversion that
happens within the kernel, but rather because of something userspace does.
We have giant applications that we want to protect, and parts of these giant
applications do things like watch the system state to determine how healthy the
box is for load balancing and such. This involves running 'ps' or other such
utilities. These utilities will often walk /proc/<pid>/whatever, and these
files can sometimes need to down_read(&task->mmap_sem). Not usually a big deal,
but we noticed when we are stress testing that sometimes our protected
application has latency spikes trying to get the mmap_sem for tasks that are in
lower priority cgroups.
This is because any down_write() on a semaphore essentially turns it into a
mutex, so even if we currently have it held for reading, any new readers will
not be allowed on to keep from starving the writer. This is fine, except a
lower priority task could be stuck doing IO because it has been throttled to the
point that its IO is taking much longer than normal. But because a higher
priority group depends on this completing it is now stuck behind lower priority
work.
In order to avoid this particular priority inversion we want to use the existing
retry mechanism to stop from holding the mmap_sem at all if we are going to do
IO. This already exists in the read case sort of, but needed to be extended for
more than just grabbing the page lock. With io.latency we throttle at
submit_bio() time, so the readahead stuff can block and even page_cache_read can
block, so all these paths need to have the mmap_sem dropped.
The other big thing is ->page_mkwrite. btrfs is particularly shitty here
because we have to reserve space for the dirty page, which can be a very
expensive operation. We use the same retry method as the read path, and simply
cache the page and verify the page is still setup properly the next pass through
->page_mkwrite().
I've tested these patches with xfstests and there are no regressions. Let me
know what you think. Thanks,
Josef
->page_mkwrite is extremely expensive in btrfs. We have to reserve
space, which can take 6 lifetimes, and we could possibly have to wait on
writeback on the page, another several lifetimes. To avoid this simply
drop the mmap_sem if we didn't have the cached page and do all of our
work and return the appropriate retry error. If we have the cached page
we know we did all the right things to set this page up and we can just
carry on.
Signed-off-by: Josef Bacik <[email protected]>
---
fs/btrfs/inode.c | 40 ++++++++++++++++++++++++++++++++++++++--
include/linux/mm.h | 14 ++++++++++++++
mm/filemap.c | 3 ++-
3 files changed, 54 insertions(+), 3 deletions(-)
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 3ea5339603cf..34c33b96d335 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -8809,7 +8809,9 @@ static void btrfs_invalidatepage(struct page *page, unsigned int offset,
vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf)
{
struct page *page = vmf->page;
- struct inode *inode = file_inode(vmf->vma->vm_file);
+ struct file *file = vmf->vma->vm_file, *fpin;
+ struct mm_struct *mm = vmf->vma->vm_mm;
+ struct inode *inode = file_inode(file);
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
struct btrfs_ordered_extent *ordered;
@@ -8828,6 +8830,29 @@ vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf)
reserved_space = PAGE_SIZE;
+ /*
+ * We have our cached page from a previous mkwrite, check it to make
+ * sure it's still dirty and our file size matches when we ran mkwrite
+ * the last time. If everything is OK then return VM_FAULT_LOCKED,
+ * otherwise do the mkwrite again.
+ */
+ if (vmf->flags & FAULT_FLAG_USED_CACHED) {
+ lock_page(page);
+ if (vmf->cached_size == i_size_read(inode) &&
+ PageDirty(page))
+ return VM_FAULT_LOCKED;
+ unlock_page(page);
+ }
+
+ /*
+ * mkwrite is extremely expensive, and we are holding the mmap_sem
+ * during this, which means we can starve out anybody trying to
+ * down_write(mmap_sem) for a long while, especially if we throw cgroups
+ * into the mix. So just drop the mmap_sem and do all of our work,
+ * we'll loop back through and verify everything is ok the next time and
+ * hopefully avoid doing the work twice.
+ */
+ fpin = maybe_unlock_mmap_for_io(vmf->vma, vmf->flags);
sb_start_pagefault(inode->i_sb);
page_start = page_offset(page);
page_end = page_start + PAGE_SIZE - 1;
@@ -8844,7 +8869,7 @@ vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf)
ret2 = btrfs_delalloc_reserve_space(inode, &data_reserved, page_start,
reserved_space);
if (!ret2) {
- ret2 = file_update_time(vmf->vma->vm_file);
+ ret2 = file_update_time(file);
reserved = 1;
}
if (ret2) {
@@ -8943,6 +8968,13 @@ vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf)
btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE, true);
sb_end_pagefault(inode->i_sb);
extent_changeset_free(data_reserved);
+ if (fpin) {
+ unlock_page(page);
+ fput(fpin);
+ vmf->cached_size = size;
+ down_read(&mm->mmap_sem);
+ return VM_FAULT_RETRY;
+ }
return VM_FAULT_LOCKED;
}
@@ -8955,6 +8987,10 @@ vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf)
out_noreserve:
sb_end_pagefault(inode->i_sb);
extent_changeset_free(data_reserved);
+ if (fpin) {
+ fput(fpin);
+ down_read(&mm->mmap_sem);
+ }
return ret;
}
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 10a0118f5485..b9ad6cb3de84 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -370,6 +370,13 @@ struct vm_fault {
* next time we loop through the fault
* handler for faster lookup.
*/
+ loff_t cached_size; /* ->page_mkwrite handlers may drop
+ * the mmap_sem to avoid starvation, in
+ * which case they need to save the
+ * i_size in order to verify the cached
+ * page we're using the next loop
+ * through hasn't changed under us.
+ */
/* These three entries are valid only while holding ptl lock */
pte_t *pte; /* Pointer to pte entry matching
* the 'address'. NULL if the page
@@ -1435,6 +1442,8 @@ extern vm_fault_t handle_mm_fault(struct vm_fault *vmf);
extern int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
unsigned long address, unsigned int fault_flags,
bool *unlocked);
+extern struct file *maybe_unlock_mmap_for_io(struct vm_area_struct *vma,
+ int flags);
void unmap_mapping_pages(struct address_space *mapping,
pgoff_t start, pgoff_t nr, bool even_cows);
void unmap_mapping_range(struct address_space *mapping,
@@ -1454,6 +1463,11 @@ static inline int fixup_user_fault(struct task_struct *tsk,
BUG();
return -EFAULT;
}
+stiatc inline struct file *maybe_unlock_mmap_for_io(struct vm_area_struct *vma,
+ int flags)
+{
+ return NULL;
+}
static inline void unmap_mapping_pages(struct address_space *mapping,
pgoff_t start, pgoff_t nr, bool even_cows) { }
static inline void unmap_mapping_range(struct address_space *mapping,
diff --git a/mm/filemap.c b/mm/filemap.c
index 75a8b252814a..748c696d23af 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2366,7 +2366,7 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
EXPORT_SYMBOL(generic_file_read_iter);
#ifdef CONFIG_MMU
-static struct file *maybe_unlock_mmap_for_io(struct vm_area_struct *vma, int flags)
+struct file *maybe_unlock_mmap_for_io(struct vm_area_struct *vma, int flags)
{
if ((flags & (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT)) == FAULT_FLAG_ALLOW_RETRY) {
struct file *file;
@@ -2377,6 +2377,7 @@ static struct file *maybe_unlock_mmap_for_io(struct vm_area_struct *vma, int fla
}
return NULL;
}
+EXPORT_SYMBOL_GPL(maybe_unlock_mmap_for_io);
/**
* page_cache_read - adds requested page to the page cache if not already there
--
2.14.3
Johannes' patches didn't quite cover all of the IO cases that we need to
drop the mmap_sem for, this patch covers the rest of them.
Signed-off-by: Josef Bacik <[email protected]>
---
mm/filemap.c | 11 +++++++++++
1 file changed, 11 insertions(+)
diff --git a/mm/filemap.c b/mm/filemap.c
index 1ed35cd99b2c..65395ee132a0 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2523,6 +2523,7 @@ vm_fault_t filemap_fault(struct vm_fault *vmf)
int error;
struct mm_struct *mm = vmf->vma->vm_mm;
struct file *file = vmf->vma->vm_file;
+ struct file *fpin = NULL;
struct address_space *mapping = file->f_mapping;
struct file_ra_state *ra = &file->f_ra;
struct inode *inode = mapping->host;
@@ -2610,11 +2611,15 @@ vm_fault_t filemap_fault(struct vm_fault *vmf)
return ret | VM_FAULT_LOCKED;
no_cached_page:
+ fpin = maybe_unlock_mmap_for_io(vmf->vma, vmf->flags);
+
/*
* We're only likely to ever get here if MADV_RANDOM is in
* effect.
*/
error = page_cache_read(file, offset, vmf->gfp_mask);
+ if (fpin)
+ goto out_retry;
/*
* The page we want has now been added to the page cache.
@@ -2634,6 +2639,8 @@ vm_fault_t filemap_fault(struct vm_fault *vmf)
return VM_FAULT_SIGBUS;
page_not_uptodate:
+ fpin = maybe_unlock_mmap_for_io(vmf->vma, vmf->flags);
+
/*
* Umm, take care of errors if the page isn't up-to-date.
* Try to re-read it _once_. We do this synchronously,
@@ -2647,6 +2654,8 @@ vm_fault_t filemap_fault(struct vm_fault *vmf)
if (!PageUptodate(page))
error = -EIO;
}
+ if (fpin)
+ goto out_retry;
put_page(page);
if (!error || error == AOP_TRUNCATED_PAGE)
@@ -2665,6 +2674,8 @@ vm_fault_t filemap_fault(struct vm_fault *vmf)
}
out_retry:
+ if (fpin)
+ fput(fpin);
if (page)
put_page(page);
return ret | VM_FAULT_RETRY;
--
2.14.3
From: Johannes Weiner <[email protected]>
We don't need to hold the mmap_sem while we're doing the IO, simply drop
it and retry appropriately.
Signed-off-by: Johannes Weiner <[email protected]>
Signed-off-by: Josef Bacik <[email protected]>
---
mm/page_io.c | 14 ++++++++++++++
1 file changed, 14 insertions(+)
diff --git a/mm/page_io.c b/mm/page_io.c
index aafd19ec1db4..bf21b56a964e 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -365,6 +365,20 @@ int swap_readpage(struct page *page, bool synchronous)
goto out;
}
+ /*
+ * XXX:
+ *
+ * Propagate mm->mmap_sem into this function. Then:
+ *
+ * get_file(sis->swap_file)
+ * up_read(mm->mmap_sem)
+ * submit io request
+ * fput
+ *
+ * After mmap_sem is dropped, sis is no longer valid. Go
+ * through swap_file->blah->bdev.
+ */
+
if (sis->flags & SWP_FILE) {
struct file *swap_file = sis->swap_file;
struct address_space *mapping = swap_file->f_mapping;
--
2.14.3
From: Johannes Weiner <[email protected]>
__read_swap_cache_async() has a misleading name. All it does is look
up or create a page in swapcache; it doesn't initiate any IO.
The swapcache has many parallels to the page cache, and shares naming
schemes with it elsewhere. Analogous to the cache lookup and creation
API, rename __read_swap_cache_async() find_or_create_swap_cache() and
lookup_swap_cache() to find_swap_cache().
Signed-off-by: Johannes Weiner <[email protected]>
Signed-off-by: Josef Bacik <[email protected]>
---
include/linux/swap.h | 14 ++++++++------
mm/memory.c | 2 +-
mm/shmem.c | 2 +-
mm/swap_state.c | 43 ++++++++++++++++++++++---------------------
mm/zswap.c | 8 ++++----
5 files changed, 36 insertions(+), 33 deletions(-)
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 8e2c11e692ba..293a84c34448 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -412,15 +412,17 @@ extern void __delete_from_swap_cache(struct page *);
extern void delete_from_swap_cache(struct page *);
extern void free_page_and_swap_cache(struct page *);
extern void free_pages_and_swap_cache(struct page **, int);
-extern struct page *lookup_swap_cache(swp_entry_t entry,
- struct vm_area_struct *vma,
- unsigned long addr);
+extern struct page *find_swap_cache(swp_entry_t entry,
+ struct vm_area_struct *vma,
+ unsigned long addr);
+extern struct page *find_or_create_swap_cache(swp_entry_t entry,
+ gfp_t gfp_mask,
+ struct vm_area_struct *vma,
+ unsigned long addr,
+ bool *created);
extern struct page *read_swap_cache_async(swp_entry_t, gfp_t,
struct vm_area_struct *vma, unsigned long addr,
bool do_poll);
-extern struct page *__read_swap_cache_async(swp_entry_t, gfp_t,
- struct vm_area_struct *vma, unsigned long addr,
- bool *new_page_allocated);
extern struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t flag,
struct vm_fault *vmf);
extern struct page *swapin_readahead(swp_entry_t entry, gfp_t flag,
diff --git a/mm/memory.c b/mm/memory.c
index 9152c2a2c9f6..f27295c1c91d 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2935,7 +2935,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
delayacct_set_flag(DELAYACCT_PF_SWAPIN);
- page = lookup_swap_cache(entry, vma, vmf->address);
+ page = find_swap_cache(entry, vma, vmf->address);
swapcache = page;
if (!page) {
diff --git a/mm/shmem.c b/mm/shmem.c
index 0376c124b043..9854903ae92f 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1679,7 +1679,7 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
if (swap.val) {
/* Look it up and read it in.. */
- page = lookup_swap_cache(swap, NULL, 0);
+ page = find_swap_cache(swap, NULL, 0);
if (!page) {
/* Or update major stats only when swapin succeeds?? */
if (fault_type) {
diff --git a/mm/swap_state.c b/mm/swap_state.c
index ecee9c6c4cc1..bae758e19f7a 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -330,8 +330,8 @@ static inline bool swap_use_vma_readahead(void)
* lock getting page table operations atomic even if we drop the page
* lock before returning.
*/
-struct page *lookup_swap_cache(swp_entry_t entry, struct vm_area_struct *vma,
- unsigned long addr)
+struct page *find_swap_cache(swp_entry_t entry, struct vm_area_struct *vma,
+ unsigned long addr)
{
struct page *page;
@@ -374,19 +374,20 @@ struct page *lookup_swap_cache(swp_entry_t entry, struct vm_area_struct *vma,
return page;
}
-struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
+struct page *find_or_create_swap_cache(swp_entry_t entry, gfp_t gfp_mask,
struct vm_area_struct *vma, unsigned long addr,
- bool *new_page_allocated)
+ bool *created)
{
struct page *found_page, *new_page = NULL;
struct address_space *swapper_space = swap_address_space(entry);
int err;
- *new_page_allocated = false;
+
+ *created = false;
do {
/*
* First check the swap cache. Since this is normally
- * called after lookup_swap_cache() failed, re-calling
+ * called after find_swap_cache() failed, re-calling
* that would confuse statistics.
*/
found_page = find_get_page(swapper_space, swp_offset(entry));
@@ -449,7 +450,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
* Initiate read into locked page and return.
*/
lru_cache_add_anon(new_page);
- *new_page_allocated = true;
+ *created = true;
return new_page;
}
radix_tree_preload_end();
@@ -475,14 +476,14 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
struct vm_area_struct *vma, unsigned long addr, bool do_poll)
{
- bool page_was_allocated;
- struct page *retpage = __read_swap_cache_async(entry, gfp_mask,
- vma, addr, &page_was_allocated);
+ struct page *page;
+ bool created;
- if (page_was_allocated)
- swap_readpage(retpage, do_poll);
+ page = find_or_create_swap_cache(entry, gfp_mask, vma, addr, &created);
+ if (created)
+ swap_readpage(page, do_poll);
- return retpage;
+ return page;
}
static unsigned int __swapin_nr_pages(unsigned long prev_offset,
@@ -573,7 +574,7 @@ struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask,
unsigned long mask;
struct swap_info_struct *si = swp_swap_info(entry);
struct blk_plug plug;
- bool do_poll = true, page_allocated;
+ bool do_poll = true, created;
struct vm_area_struct *vma = vmf->vma;
unsigned long addr = vmf->address;
@@ -593,12 +594,12 @@ struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask,
blk_start_plug(&plug);
for (offset = start_offset; offset <= end_offset ; offset++) {
/* Ok, do the async read-ahead now */
- page = __read_swap_cache_async(
+ page = find_or_create_swap_cache(
swp_entry(swp_type(entry), offset),
- gfp_mask, vma, addr, &page_allocated);
+ gfp_mask, vma, addr, &created);
if (!page)
continue;
- if (page_allocated) {
+ if (created) {
swap_readpage(page, false);
if (offset != entry_offset) {
SetPageReadahead(page);
@@ -738,7 +739,7 @@ static struct page *swap_vma_readahead(swp_entry_t fentry, gfp_t gfp_mask,
pte_t *pte, pentry;
swp_entry_t entry;
unsigned int i;
- bool page_allocated;
+ bool created;
struct vma_swap_readahead ra_info = {0,};
swap_ra_info(vmf, &ra_info);
@@ -756,11 +757,11 @@ static struct page *swap_vma_readahead(swp_entry_t fentry, gfp_t gfp_mask,
entry = pte_to_swp_entry(pentry);
if (unlikely(non_swap_entry(entry)))
continue;
- page = __read_swap_cache_async(entry, gfp_mask, vma,
- vmf->address, &page_allocated);
+ page = find_or_create_swap_cache(entry, gfp_mask, vma,
+ vmf->address, &created);
if (!page)
continue;
- if (page_allocated) {
+ if (created) {
swap_readpage(page, false);
if (i != ra_info.offset) {
SetPageReadahead(page);
diff --git a/mm/zswap.c b/mm/zswap.c
index cd91fd9d96b8..6f05faa75766 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -823,11 +823,11 @@ enum zswap_get_swap_ret {
static int zswap_get_swap_cache_page(swp_entry_t entry,
struct page **retpage)
{
- bool page_was_allocated;
+ bool created;
- *retpage = __read_swap_cache_async(entry, GFP_KERNEL,
- NULL, 0, &page_was_allocated);
- if (page_was_allocated)
+ *retpage = find_or_create_swap_cache(entry, GFP_KERNEL,
+ NULL, 0, &created);
+ if (created)
return ZSWAP_SWAPCACHE_NEW;
if (!*retpage)
return ZSWAP_SWAPCACHE_FAIL;
--
2.14.3
From: Johannes Weiner <[email protected]>
Reads can take a long time, and if anybody needs to take a write lock on
the mmap_sem it'll block any subsequent readers to the mmap_sem while
the read is outstanding, which could cause long delays. Instead drop
the mmap_sem if we do any reads at all.
Signed-off-by: Johannes Weiner <[email protected]>
Signed-off-by: Josef Bacik <[email protected]>
---
mm/filemap.c | 119 ++++++++++++++++++++++++++++++++++++++++++++---------------
1 file changed, 90 insertions(+), 29 deletions(-)
diff --git a/mm/filemap.c b/mm/filemap.c
index 52517f28e6f4..1ed35cd99b2c 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2366,6 +2366,18 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
EXPORT_SYMBOL(generic_file_read_iter);
#ifdef CONFIG_MMU
+static struct file *maybe_unlock_mmap_for_io(struct vm_area_struct *vma, int flags)
+{
+ if ((flags & (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT)) == FAULT_FLAG_ALLOW_RETRY) {
+ struct file *file;
+
+ file = get_file(vma->vm_file);
+ up_read(&vma->vm_mm->mmap_sem);
+ return file;
+ }
+ return NULL;
+}
+
/**
* page_cache_read - adds requested page to the page cache if not already there
* @file: file to read
@@ -2405,23 +2417,28 @@ static int page_cache_read(struct file *file, pgoff_t offset, gfp_t gfp_mask)
* Synchronous readahead happens when we don't even find
* a page in the page cache at all.
*/
-static void do_sync_mmap_readahead(struct vm_area_struct *vma,
- struct file_ra_state *ra,
- struct file *file,
- pgoff_t offset)
+static int do_sync_mmap_readahead(struct vm_area_struct *vma,
+ struct file_ra_state *ra,
+ struct file *file,
+ pgoff_t offset,
+ int flags)
{
struct address_space *mapping = file->f_mapping;
+ struct file *fpin;
/* If we don't want any read-ahead, don't bother */
if (vma->vm_flags & VM_RAND_READ)
- return;
+ return 0;
if (!ra->ra_pages)
- return;
+ return 0;
if (vma->vm_flags & VM_SEQ_READ) {
+ fpin = maybe_unlock_mmap_for_io(vma, flags);
page_cache_sync_readahead(mapping, ra, file, offset,
ra->ra_pages);
- return;
+ if (fpin)
+ fput(fpin);
+ return fpin ? -EAGAIN : 0;
}
/* Avoid banging the cache line if not needed */
@@ -2433,7 +2450,9 @@ static void do_sync_mmap_readahead(struct vm_area_struct *vma,
* stop bothering with read-ahead. It will only hurt.
*/
if (ra->mmap_miss > MMAP_LOTSAMISS)
- return;
+ return 0;
+
+ fpin = maybe_unlock_mmap_for_io(vma, flags);
/*
* mmap read-around
@@ -2442,28 +2461,40 @@ static void do_sync_mmap_readahead(struct vm_area_struct *vma,
ra->size = ra->ra_pages;
ra->async_size = ra->ra_pages / 4;
ra_submit(ra, mapping, file);
+
+ if (fpin)
+ fput(fpin);
+
+ return fpin ? -EAGAIN : 0;
}
/*
* Asynchronous readahead happens when we find the page and PG_readahead,
* so we want to possibly extend the readahead further..
*/
-static void do_async_mmap_readahead(struct vm_area_struct *vma,
- struct file_ra_state *ra,
- struct file *file,
- struct page *page,
- pgoff_t offset)
+static int do_async_mmap_readahead(struct vm_area_struct *vma,
+ struct file_ra_state *ra,
+ struct file *file,
+ struct page *page,
+ pgoff_t offset,
+ int flags)
{
struct address_space *mapping = file->f_mapping;
+ struct file *fpin;
/* If we don't want any read-ahead, don't bother */
if (vma->vm_flags & VM_RAND_READ)
- return;
+ return 0;
if (ra->mmap_miss > 0)
ra->mmap_miss--;
- if (PageReadahead(page))
- page_cache_async_readahead(mapping, ra, file,
- page, offset, ra->ra_pages);
+ if (!PageReadahead(page))
+ return 0;
+ fpin = maybe_unlock_mmap_for_io(vma, flags);
+ page_cache_async_readahead(mapping, ra, file,
+ page, offset, ra->ra_pages);
+ if (fpin)
+ fput(fpin);
+ return fpin ? -EAGAIN : 0;
}
/**
@@ -2479,10 +2510,8 @@ static void do_async_mmap_readahead(struct vm_area_struct *vma,
*
* vma->vm_mm->mmap_sem must be held on entry.
*
- * If our return value has VM_FAULT_RETRY set, it's because
- * lock_page_or_retry() returned 0.
- * The mmap_sem has usually been released in this case.
- * See __lock_page_or_retry() for the exception.
+ * If our return value has VM_FAULT_RETRY set, the mmap_sem has
+ * usually been released.
*
* If our return value does not have VM_FAULT_RETRY set, the mmap_sem
* has not been released.
@@ -2492,11 +2521,13 @@ static void do_async_mmap_readahead(struct vm_area_struct *vma,
vm_fault_t filemap_fault(struct vm_fault *vmf)
{
int error;
+ struct mm_struct *mm = vmf->vma->vm_mm;
struct file *file = vmf->vma->vm_file;
struct address_space *mapping = file->f_mapping;
struct file_ra_state *ra = &file->f_ra;
struct inode *inode = mapping->host;
pgoff_t offset = vmf->pgoff;
+ int flags = vmf->flags;
pgoff_t max_off;
struct page *page;
vm_fault_t ret = 0;
@@ -2509,27 +2540,44 @@ vm_fault_t filemap_fault(struct vm_fault *vmf)
* Do we have something in the page cache already?
*/
page = find_get_page(mapping, offset);
- if (likely(page) && !(vmf->flags & FAULT_FLAG_TRIED)) {
+ if (likely(page) && !(flags & FAULT_FLAG_TRIED)) {
/*
* We found the page, so try async readahead before
* waiting for the lock.
*/
- do_async_mmap_readahead(vmf->vma, ra, file, page, offset);
+ error = do_async_mmap_readahead(vmf->vma, ra, file, page, offset, vmf->flags);
+ if (error == -EAGAIN)
+ goto out_retry_wait;
} else if (!page) {
/* No page in the page cache at all */
- do_sync_mmap_readahead(vmf->vma, ra, file, offset);
- count_vm_event(PGMAJFAULT);
- count_memcg_event_mm(vmf->vma->vm_mm, PGMAJFAULT);
ret = VM_FAULT_MAJOR;
+ count_vm_event(PGMAJFAULT);
+ count_memcg_event_mm(mm, PGMAJFAULT);
+ error = do_sync_mmap_readahead(vmf->vma, ra, file, offset, vmf->flags);
+ if (error == -EAGAIN)
+ goto out_retry_wait;
retry_find:
page = find_get_page(mapping, offset);
if (!page)
goto no_cached_page;
}
- if (!lock_page_or_retry(page, vmf->vma->vm_mm, vmf->flags)) {
- put_page(page);
- return ret | VM_FAULT_RETRY;
+ if (!trylock_page(page)) {
+ if (flags & FAULT_FLAG_ALLOW_RETRY) {
+ if (flags & FAULT_FLAG_RETRY_NOWAIT)
+ goto out_retry;
+ up_read(&mm->mmap_sem);
+ goto out_retry_wait;
+ }
+ if (flags & FAULT_FLAG_KILLABLE) {
+ int ret = __lock_page_killable(page);
+
+ if (ret) {
+ up_read(&mm->mmap_sem);
+ goto out_retry;
+ }
+ } else
+ __lock_page(page);
}
/* Did it get truncated? */
@@ -2607,6 +2655,19 @@ vm_fault_t filemap_fault(struct vm_fault *vmf)
/* Things didn't work out. Return zero to tell the mm layer so. */
shrink_readahead_size_eio(file, ra);
return VM_FAULT_SIGBUS;
+
+out_retry_wait:
+ if (page) {
+ if (flags & FAULT_FLAG_KILLABLE)
+ wait_on_page_locked_killable(page);
+ else
+ wait_on_page_locked(page);
+ }
+
+out_retry:
+ if (page)
+ put_page(page);
+ return ret | VM_FAULT_RETRY;
}
EXPORT_SYMBOL(filemap_fault);
--
2.14.3
If we drop the mmap_sem we need to redo the vma lookup and then
re-lookup the page. This is kind of a waste since we've already done
the work, and we could even possibly evict the page, causing a refault.
Instead just hold a reference to the page and save it in our vm_fault.
The next time we go through filemap_fault we'll grab our page, verify
that it's the one we want and carry on.
Signed-off-by: Josef Bacik <[email protected]>
---
arch/alpha/mm/fault.c | 7 +++++--
arch/arc/mm/fault.c | 6 +++++-
arch/arm/mm/fault.c | 2 ++
arch/arm64/mm/fault.c | 2 ++
arch/hexagon/mm/vm_fault.c | 6 +++++-
arch/ia64/mm/fault.c | 6 +++++-
arch/m68k/mm/fault.c | 6 +++++-
arch/microblaze/mm/fault.c | 6 +++++-
arch/mips/mm/fault.c | 6 +++++-
arch/nds32/mm/fault.c | 3 +++
arch/nios2/mm/fault.c | 6 +++++-
arch/openrisc/mm/fault.c | 6 +++++-
arch/parisc/mm/fault.c | 6 +++++-
arch/powerpc/mm/copro_fault.c | 3 ++-
arch/powerpc/mm/fault.c | 3 +++
arch/riscv/mm/fault.c | 6 +++++-
arch/s390/mm/fault.c | 1 +
arch/sh/mm/fault.c | 8 ++++++--
arch/sparc/mm/fault_32.c | 8 +++++++-
arch/sparc/mm/fault_64.c | 6 +++++-
arch/um/kernel/trap.c | 6 +++++-
arch/unicore32/mm/fault.c | 5 ++++-
arch/x86/mm/fault.c | 2 ++
arch/xtensa/mm/fault.c | 6 +++++-
drivers/iommu/amd_iommu_v2.c | 1 +
drivers/iommu/intel-svm.c | 1 +
include/linux/mm.h | 14 ++++++++++++++
mm/filemap.c | 31 ++++++++++++++++++++++++++++---
mm/gup.c | 3 +++
mm/hmm.c | 1 +
mm/ksm.c | 1 +
31 files changed, 151 insertions(+), 23 deletions(-)
diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c
index 3c98dfef03a9..ed5929787d4a 100644
--- a/arch/alpha/mm/fault.c
+++ b/arch/alpha/mm/fault.c
@@ -152,10 +152,13 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
vm_fault_init(&vmfs, vma, flags, address);
fault = handle_mm_fault(&vmf);
- if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+ if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) {
+ vm_fault_cleanup(&vmf);
return;
+ }
if (unlikely(fault & VM_FAULT_ERROR)) {
+ vm_fault_cleanup(&vmf);
if (fault & VM_FAULT_OOM)
goto out_of_memory;
else if (fault & VM_FAULT_SIGSEGV)
@@ -181,7 +184,7 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
goto retry;
}
}
-
+ vm_fault_cleanup(&vmf);
up_read(&mm->mmap_sem);
return;
diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c
index 7aeb81ff5070..38a6c5e94fac 100644
--- a/arch/arc/mm/fault.c
+++ b/arch/arc/mm/fault.c
@@ -149,8 +149,10 @@ void do_page_fault(unsigned long address, struct pt_regs *regs)
if (unlikely(fatal_signal_pending(current))) {
if ((fault & VM_FAULT_ERROR) && !(fault & VM_FAULT_RETRY))
up_read(&mm->mmap_sem);
- if (user_mode(regs))
+ if (user_mode(regs)) {
+ vm_fault_cleanup(&vmf);
return;
+ }
}
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
@@ -176,10 +178,12 @@ void do_page_fault(unsigned long address, struct pt_regs *regs)
}
/* Fault Handled Gracefully */
+ vm_fault_cleanup(&vmf);
up_read(&mm->mmap_sem);
return;
}
+ vm_fault_cleanup(&vmf);
if (fault & VM_FAULT_OOM)
goto out_of_memory;
else if (fault & VM_FAULT_SIGSEGV)
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 885a24385a0a..f08946e78bd9 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -325,6 +325,7 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
* it would already be released in __lock_page_or_retry in
* mm/filemap.c. */
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) {
+ vm_fault_cleanup(&vmf);
if (!user_mode(regs))
goto no_context;
return 0;
@@ -356,6 +357,7 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
}
}
+ vm_fault_cleanup(&vmf);
up_read(&mm->mmap_sem);
/*
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 31e86a74cbe0..6f3e908a3820 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -506,6 +506,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
* in __lock_page_or_retry in mm/filemap.c.
*/
if (fatal_signal_pending(current)) {
+ vm_fault_cleanup(&vmf);
if (!user_mode(regs))
goto no_context;
return 0;
@@ -521,6 +522,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
goto retry;
}
}
+ vm_fault_cleanup(&vmf);
up_read(&mm->mmap_sem);
/*
diff --git a/arch/hexagon/mm/vm_fault.c b/arch/hexagon/mm/vm_fault.c
index 1ee1042bb2b5..d68aa9691184 100644
--- a/arch/hexagon/mm/vm_fault.c
+++ b/arch/hexagon/mm/vm_fault.c
@@ -106,8 +106,10 @@ void do_page_fault(unsigned long address, long cause, struct pt_regs *regs)
vm_fault_init(&vmf, vma, address, flags);
fault = handle_mm_fault(&vmf);
- if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+ if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) {
+ vm_fault_cleanup(&vmf);
return;
+ }
/* The most common case -- we are done. */
if (likely(!(fault & VM_FAULT_ERROR))) {
@@ -123,10 +125,12 @@ void do_page_fault(unsigned long address, long cause, struct pt_regs *regs)
}
}
+ vm_fault_cleanup(&vmf);
up_read(&mm->mmap_sem);
return;
}
+ vm_fault_cleanup(&vmf);
up_read(&mm->mmap_sem);
/* Handle copyin/out exception cases */
diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c
index 827b898adb5e..68b689bb619f 100644
--- a/arch/ia64/mm/fault.c
+++ b/arch/ia64/mm/fault.c
@@ -165,8 +165,10 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re
vm_fault_init(&vmf, vma, address, flags);
fault = handle_mm_fault(&vmf);
- if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+ if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) {
+ vm_fault_cleanup(&vmf);
return;
+ }
if (unlikely(fault & VM_FAULT_ERROR)) {
/*
@@ -174,6 +176,7 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re
* to us that made us unable to handle the page fault
* gracefully.
*/
+ vm_fault_cleanup(&vmf);
if (fault & VM_FAULT_OOM) {
goto out_of_memory;
} else if (fault & VM_FAULT_SIGSEGV) {
@@ -203,6 +206,7 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re
}
}
+ vm_fault_cleanup(&vmf);
up_read(&mm->mmap_sem);
return;
diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c
index e42eddc9c7ca..7e8be4665ef9 100644
--- a/arch/m68k/mm/fault.c
+++ b/arch/m68k/mm/fault.c
@@ -139,10 +139,13 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
fault = handle_mm_fault(&vmf);
pr_debug("handle_mm_fault returns %x\n", fault);
- if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+ if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) {
+ vm_fault_cleanup(&vmf);
return 0;
+ }
if (unlikely(fault & VM_FAULT_ERROR)) {
+ vm_fault_cleanup(&vmf);
if (fault & VM_FAULT_OOM)
goto out_of_memory;
else if (fault & VM_FAULT_SIGSEGV)
@@ -178,6 +181,7 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
}
}
+ vm_fault_cleanup(&vmf);
up_read(&mm->mmap_sem);
return 0;
diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c
index ade980266f65..bb320be95142 100644
--- a/arch/microblaze/mm/fault.c
+++ b/arch/microblaze/mm/fault.c
@@ -219,10 +219,13 @@ void do_page_fault(struct pt_regs *regs, unsigned long address,
vm_fault_init(&vmf, vma, address, flags);
fault = handle_mm_fault(&vmf);
- if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+ if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) {
+ vm_fault_cleanup(&vmf);
return;
+ }
if (unlikely(fault & VM_FAULT_ERROR)) {
+ vm_fault_cleanup(&vmf);
if (fault & VM_FAULT_OOM)
goto out_of_memory;
else if (fault & VM_FAULT_SIGSEGV)
@@ -251,6 +254,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long address,
}
}
+ vm_fault_cleanup(&vmf);
up_read(&mm->mmap_sem);
/*
diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c
index bf212bb70f24..8f1cfe564987 100644
--- a/arch/mips/mm/fault.c
+++ b/arch/mips/mm/fault.c
@@ -156,11 +156,14 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write,
vm_fault_init(&vmf, vma, address, flags);
fault = handle_mm_fault(&vmf);
- if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+ if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) {
+ vm_fault_cleanup(&vmf);
return;
+ }
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
if (unlikely(fault & VM_FAULT_ERROR)) {
+ vm_fault_cleanup(&vmf);
if (fault & VM_FAULT_OOM)
goto out_of_memory;
else if (fault & VM_FAULT_SIGSEGV)
@@ -193,6 +196,7 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write,
}
}
+ vm_fault_cleanup(&vmf);
up_read(&mm->mmap_sem);
return;
diff --git a/arch/nds32/mm/fault.c b/arch/nds32/mm/fault.c
index 27ac4caa5102..7cb4d9f73c1a 100644
--- a/arch/nds32/mm/fault.c
+++ b/arch/nds32/mm/fault.c
@@ -213,12 +213,14 @@ void do_page_fault(unsigned long entry, unsigned long addr,
* would already be released in __lock_page_or_retry in mm/filemap.c.
*/
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) {
+ vm_fault_cleanup(&vmf);
if (!user_mode(regs))
goto no_context;
return;
}
if (unlikely(fault & VM_FAULT_ERROR)) {
+ vm_fault_cleanup(&vmf);
if (fault & VM_FAULT_OOM)
goto out_of_memory;
else if (fault & VM_FAULT_SIGBUS)
@@ -249,6 +251,7 @@ void do_page_fault(unsigned long entry, unsigned long addr,
}
}
+ vm_fault_cleanup(&vmf);
up_read(&mm->mmap_sem);
return;
diff --git a/arch/nios2/mm/fault.c b/arch/nios2/mm/fault.c
index 693472f05065..774035116392 100644
--- a/arch/nios2/mm/fault.c
+++ b/arch/nios2/mm/fault.c
@@ -136,10 +136,13 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long cause,
vm_fault_init(&vmf, vma, address, flags);
fault = handle_mm_fault(&vmf);
- if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+ if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) {
+ vm_fault_cleanup(&vmf);
return;
+ }
if (unlikely(fault & VM_FAULT_ERROR)) {
+ vm_fault_cleanup(&vmf);
if (fault & VM_FAULT_OOM)
goto out_of_memory;
else if (fault & VM_FAULT_SIGSEGV)
@@ -175,6 +178,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long cause,
}
}
+ vm_fault_cleanup(&vmf);
up_read(&mm->mmap_sem);
return;
diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c
index 70eef1d9f7ed..9186af1b9cdc 100644
--- a/arch/openrisc/mm/fault.c
+++ b/arch/openrisc/mm/fault.c
@@ -166,10 +166,13 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long address,
vm_fault_init(&vmf, vma, address, flags);
fault = handle_mm_fault(&vmf);
- if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+ if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) {
+ vm_fault_cleanup(&vmf);
return;
+ }
if (unlikely(fault & VM_FAULT_ERROR)) {
+ vm_fault_cleanup(&vmf);
if (fault & VM_FAULT_OOM)
goto out_of_memory;
else if (fault & VM_FAULT_SIGSEGV)
@@ -198,6 +201,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long address,
}
}
+ vm_fault_cleanup(&vmf);
up_read(&mm->mmap_sem);
return;
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index 83c89cada3c0..7ad74571407e 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -304,8 +304,10 @@ void do_page_fault(struct pt_regs *regs, unsigned long code,
vm_fault_init(&vmf, vma, address, flags);
fault = handle_mm_fault(&vmf);
- if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+ if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) {
+ vm_fault_cleanup(&vmf);
return;
+ }
if (unlikely(fault & VM_FAULT_ERROR)) {
/*
@@ -313,6 +315,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long code,
* other thing happened to us that made us unable to
* handle the page fault gracefully.
*/
+ vm_fault_cleanup(&vmf);
if (fault & VM_FAULT_OOM)
goto out_of_memory;
else if (fault & VM_FAULT_SIGSEGV)
@@ -339,6 +342,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long code,
goto retry;
}
}
+ vm_fault_cleanup(&vmf);
up_read(&mm->mmap_sem);
return;
diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c
index 02dd21a54479..07ec389ac6c6 100644
--- a/arch/powerpc/mm/copro_fault.c
+++ b/arch/powerpc/mm/copro_fault.c
@@ -81,6 +81,7 @@ int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea,
vm_fault_init(&vmf, vma, ea, is_write ? FAULT_FLAG_WRITE : 0);
*flt = handle_mm_fault(&vmf);
if (unlikely(*flt & VM_FAULT_ERROR)) {
+ vm_fault_cleanup(&vmf);
if (*flt & VM_FAULT_OOM) {
ret = -ENOMEM;
goto out_unlock;
@@ -95,7 +96,7 @@ int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea,
current->maj_flt++;
else
current->min_flt++;
-
+ vm_fault_cleanup(&vmf);
out_unlock:
up_read(&mm->mmap_sem);
return ret;
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index cc00bba104fb..1940471c6a6f 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -552,6 +552,7 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address,
int pkey = vma_pkey(vma);
+ vm_fault_cleanup(&vmf);
up_read(&mm->mmap_sem);
return bad_key_fault_exception(regs, address, pkey);
}
@@ -580,9 +581,11 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address,
* User mode? Just return to handle the fatal exception otherwise
* return to bad_page_fault
*/
+ vm_fault_cleanup(&vmf);
return is_user ? 0 : SIGBUS;
}
+ vm_fault_cleanup(&vmf);
up_read(¤t->mm->mmap_sem);
if (unlikely(fault & VM_FAULT_ERROR))
diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c
index aa3db34c9eb8..64c8de82a40b 100644
--- a/arch/riscv/mm/fault.c
+++ b/arch/riscv/mm/fault.c
@@ -129,10 +129,13 @@ asmlinkage void do_page_fault(struct pt_regs *regs)
* signal first. We do not need to release the mmap_sem because it
* would already be released in __lock_page_or_retry in mm/filemap.c.
*/
- if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(tsk))
+ if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(tsk)) {
+ vm_fault_cleanup(&vmf);
return;
+ }
if (unlikely(fault & VM_FAULT_ERROR)) {
+ vm_fault_cleanup(&vmf);
if (fault & VM_FAULT_OOM)
goto out_of_memory;
else if (fault & VM_FAULT_SIGBUS)
@@ -172,6 +175,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs)
}
}
+ vm_fault_cleanup(&vmf);
up_read(&mm->mmap_sem);
return;
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 14cfd6de43ed..a91849a7e338 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -561,6 +561,7 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access)
out_up:
up_read(&mm->mmap_sem);
out:
+ vm_fault_cleanup(&vmf);
return fault;
}
diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c
index 31202706125c..ee0ad499ed53 100644
--- a/arch/sh/mm/fault.c
+++ b/arch/sh/mm/fault.c
@@ -485,9 +485,12 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
vm_fault_init(&vmf, vma, address, flags);
fault = handle_mm_fault(&vmf);
- if (unlikely(fault & (VM_FAULT_RETRY | VM_FAULT_ERROR)))
- if (mm_fault_error(regs, error_code, address, fault))
+ if (unlikely(fault & (VM_FAULT_RETRY | VM_FAULT_ERROR))) {
+ if (mm_fault_error(regs, error_code, address, fault)) {
+ vm_fault_cleanup(&vmf);
return;
+ }
+ }
if (flags & FAULT_FLAG_ALLOW_RETRY) {
if (fault & VM_FAULT_MAJOR) {
@@ -512,5 +515,6 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
}
}
+ vm_fault_cleanup(&vmf);
up_read(&mm->mmap_sem);
}
diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index a9dd62393934..0623154163c5 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -239,10 +239,13 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write,
vm_fault_init(&vmf, vma, address, flags);
fault = handle_mm_fault(vma, address, flags);
- if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+ if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) {
+ vm_fault_cleanup(&vmf);
return;
+ }
if (unlikely(fault & VM_FAULT_ERROR)) {
+ vm_fault_cleanup(&vmf);
if (fault & VM_FAULT_OOM)
goto out_of_memory;
else if (fault & VM_FAULT_SIGSEGV)
@@ -275,6 +278,7 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write,
}
}
+ vm_fault_cleanup(&vmf);
up_read(&mm->mmap_sem);
return;
@@ -412,8 +416,10 @@ static void force_user_fault(unsigned long address, int write)
switch (handle_mm_fault(&vmf)) {
case VM_FAULT_SIGBUS:
case VM_FAULT_OOM:
+ vm_fault_cleanup(&vmf);
goto do_sigbus;
}
+ vm_fault_cleanup(&vmf);
up_read(&mm->mmap_sem);
return;
bad_area:
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index 381ab905eb2c..45107ddb8478 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -437,10 +437,13 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs)
vm_fault_init(&vmf, vma, address, flags);
fault = handle_mm_fault(vma, address, flags);
- if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+ if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) {
+ vm_fault_cleanup(&vmf);
goto exit_exception;
+ }
if (unlikely(fault & VM_FAULT_ERROR)) {
+ vm_fault_cleanup(&vmf);
if (fault & VM_FAULT_OOM)
goto out_of_memory;
else if (fault & VM_FAULT_SIGSEGV)
@@ -472,6 +475,7 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs)
goto retry;
}
}
+ vm_fault_cleanup(&vmf);
up_read(&mm->mmap_sem);
mm_rss = get_mm_rss(mm);
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index c6d9e176c5c5..419f4d54bf10 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -78,10 +78,13 @@ int handle_page_fault(unsigned long address, unsigned long ip,
vm_fault_init(&vmf, vma, address, flags);
fault = handle_mm_fault(&vmf);
- if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+ if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) {
+ vm_fault_cleanup(&vmf);
goto out_nosemaphore;
+ }
if (unlikely(fault & VM_FAULT_ERROR)) {
+ vm_fault_cleanup(&vmf);
if (fault & VM_FAULT_OOM) {
goto out_of_memory;
} else if (fault & VM_FAULT_SIGSEGV) {
@@ -109,6 +112,7 @@ int handle_page_fault(unsigned long address, unsigned long ip,
pud = pud_offset(pgd, address);
pmd = pmd_offset(pud, address);
pte = pte_offset_kernel(pmd, address);
+ vm_fault_cleanup(&vmf);
} while (!pte_present(*pte));
err = 0;
/*
diff --git a/arch/unicore32/mm/fault.c b/arch/unicore32/mm/fault.c
index 68c2b0a65348..0c94b8d5187d 100644
--- a/arch/unicore32/mm/fault.c
+++ b/arch/unicore32/mm/fault.c
@@ -262,8 +262,10 @@ static int do_pf(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
* signal first. We do not need to release the mmap_sem because
* it would already be released in __lock_page_or_retry in
* mm/filemap.c. */
- if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+ if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) {
+ vm_fault_cleanup(&vmf);
return 0;
+ }
if (!(fault & VM_FAULT_ERROR) && (flags & FAULT_FLAG_ALLOW_RETRY)) {
if (fault & VM_FAULT_MAJOR)
@@ -278,6 +280,7 @@ static int do_pf(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
}
}
+ vm_fault_cleanup(&vmf);
up_read(&mm->mmap_sem);
/*
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 9919a25b15e6..a8ea7b609697 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -1410,6 +1410,7 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code,
if (!fatal_signal_pending(tsk))
goto retry;
}
+ vm_fault_cleanup(&vmf);
/* User mode? Just return to handle the fatal exception */
if (flags & FAULT_FLAG_USER)
@@ -1420,6 +1421,7 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code,
return;
}
+ vm_fault_cleanup(&vmf);
up_read(&mm->mmap_sem);
if (unlikely(fault & VM_FAULT_ERROR)) {
mm_fault_error(regs, error_code, address, &pkey, fault);
diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c
index f1b0f4f858ff..a577b73f9ca4 100644
--- a/arch/xtensa/mm/fault.c
+++ b/arch/xtensa/mm/fault.c
@@ -112,10 +112,13 @@ void do_page_fault(struct pt_regs *regs)
vm_fault_init(&vmf, vma, address, flags);
fault = handle_mm_fault(&vmf);
- if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+ if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) {
+ vm_fault_cleanup(&vmf);
return;
+ }
if (unlikely(fault & VM_FAULT_ERROR)) {
+ vm_fault_cleanup(&vmf);
if (fault & VM_FAULT_OOM)
goto out_of_memory;
else if (fault & VM_FAULT_SIGSEGV)
@@ -142,6 +145,7 @@ void do_page_fault(struct pt_regs *regs)
}
}
+ vm_fault_cleanup(&vmf);
up_read(&mm->mmap_sem);
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
if (flags & VM_FAULT_MAJOR)
diff --git a/drivers/iommu/amd_iommu_v2.c b/drivers/iommu/amd_iommu_v2.c
index 129e0ef68827..fc20bbe1c0dc 100644
--- a/drivers/iommu/amd_iommu_v2.c
+++ b/drivers/iommu/amd_iommu_v2.c
@@ -535,6 +535,7 @@ static void do_fault(struct work_struct *work)
vm_fault_init(&vmf, vma, address, flags);
ret = handle_mm_fault(&vmf);
+ vm_fault_cleanup(&vmf);
out:
up_read(&mm->mmap_sem);
diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c
index 03aa02723242..614f6aab9615 100644
--- a/drivers/iommu/intel-svm.c
+++ b/drivers/iommu/intel-svm.c
@@ -640,6 +640,7 @@ static irqreturn_t prq_event_thread(int irq, void *d)
vm_fault_init(&vmf, vma, address,
req->wr_req ? FAULT_FLAG_WRITE : 0);
ret = handle_mm_fault(&vmf);
+ vm_fault_cleanup(&vmf);
if (ret & VM_FAULT_ERROR)
goto invalid;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index e271c60af01a..724514be03b2 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -360,6 +360,12 @@ struct vm_fault {
* is set (which is also implied by
* VM_FAULT_ERROR).
*/
+ struct page *cached_page; /* ->fault handlers that return
+ * VM_FAULT_RETRY can store their
+ * previous page here to be reused the
+ * next time we loop through the fault
+ * handler for faster lookup.
+ */
/* These three entries are valid only while holding ptl lock */
pte_t *pte; /* Pointer to pte entry matching
* the 'address'. NULL if the page
@@ -953,6 +959,14 @@ static inline void put_page(struct page *page)
__put_page(page);
}
+static inline void vm_fault_cleanup(struct vm_fault *vmf)
+{
+ if (vmf->cached_page) {
+ put_page(vmf->cached_page);
+ vmf->cached_page = NULL;
+ }
+}
+
#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
#define SECTION_IN_PAGE_FLAGS
#endif
diff --git a/mm/filemap.c b/mm/filemap.c
index 65395ee132a0..49b35293fa95 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2530,13 +2530,38 @@ vm_fault_t filemap_fault(struct vm_fault *vmf)
pgoff_t offset = vmf->pgoff;
int flags = vmf->flags;
pgoff_t max_off;
- struct page *page;
+ struct page *page = NULL;
+ struct page *cached_page = vmf->cached_page;
vm_fault_t ret = 0;
max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
if (unlikely(offset >= max_off))
return VM_FAULT_SIGBUS;
+ /*
+ * We may have read in the page already and have a page from an earlier
+ * loop. If so we need to see if this page is still valid, and if not
+ * do the whole dance over again.
+ */
+ if (cached_page) {
+ if (flags & FAULT_FLAG_KILLABLE) {
+ error = lock_page_killable(cached_page);
+ if (error) {
+ up_read(&mm->mmap_sem);
+ goto out_retry;
+ }
+ } else
+ lock_page(cached_page);
+ vmf->cached_page = NULL;
+ if (cached_page->mapping == mapping &&
+ cached_page->index == offset) {
+ page = cached_page;
+ goto have_cached_page;
+ }
+ unlock_page(cached_page);
+ put_page(cached_page);
+ }
+
/*
* Do we have something in the page cache already?
*/
@@ -2587,8 +2612,8 @@ vm_fault_t filemap_fault(struct vm_fault *vmf)
put_page(page);
goto retry_find;
}
+have_cached_page:
VM_BUG_ON_PAGE(page->index != offset, page);
-
/*
* We have a locked page in the page cache, now we need to check
* that it's up-to-date. If not, it is going to be due to an error.
@@ -2677,7 +2702,7 @@ vm_fault_t filemap_fault(struct vm_fault *vmf)
if (fpin)
fput(fpin);
if (page)
- put_page(page);
+ vmf->cached_page = page;
return ret | VM_FAULT_RETRY;
}
EXPORT_SYMBOL(filemap_fault);
diff --git a/mm/gup.c b/mm/gup.c
index c12d1e98614b..75f55f4f044c 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -518,6 +518,7 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
vm_fault_init(&vmf, vma, address, fault_flags);
ret = handle_mm_fault(&vmf);
+ vm_fault_cleanup(&vmf);
if (ret & VM_FAULT_ERROR) {
int err = vm_fault_to_errno(ret, *flags);
@@ -840,6 +841,7 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
if (ret & VM_FAULT_ERROR) {
int err = vm_fault_to_errno(ret, 0);
+ vm_fault_cleanup(&vmf);
if (err)
return err;
BUG();
@@ -854,6 +856,7 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
goto retry;
}
}
+ vm_fault_cleanup(&vmf);
if (tsk) {
if (major)
diff --git a/mm/hmm.c b/mm/hmm.c
index 695ef184a7d0..b803746745a5 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -309,6 +309,7 @@ static int hmm_vma_do_fault(struct mm_walk *walk, unsigned long addr,
flags |= write_fault ? FAULT_FLAG_WRITE : 0;
vm_fault_init(&vmf, vma, addr, flags);
ret = handle_mm_fault(&vmf);
+ vm_fault_cleanup(&vmf);
if (ret & VM_FAULT_RETRY)
return -EBUSY;
if (ret & VM_FAULT_ERROR) {
diff --git a/mm/ksm.c b/mm/ksm.c
index 4b6d90357ee2..8404e230fdab 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -483,6 +483,7 @@ static int break_ksm(struct vm_area_struct *vma, unsigned long addr)
vm_fault_init(&vmf, vma, addr,
FAULT_FLAG_WRITE | FAULT_FLAG_REMOTE);
ret = handle_mm_fault(&vmf);
+ vm_fault_cleanup(&vmf);
} else
ret = VM_FAULT_WRITE;
put_page(page);
--
2.14.3
This is preparation for dropping the mmap_sem in page_mkwrite. We need
to know if we used our cached page so we can be sure it is the page we
already did the page_mkwrite stuff on so we don't have to redo all of
that work.
Signed-off-by: Josef Bacik <[email protected]>
---
include/linux/mm.h | 6 +++++-
mm/filemap.c | 5 ++++-
2 files changed, 9 insertions(+), 2 deletions(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 724514be03b2..10a0118f5485 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -318,6 +318,9 @@ extern pgprot_t protection_map[16];
#define FAULT_FLAG_USER 0x40 /* The fault originated in userspace */
#define FAULT_FLAG_REMOTE 0x80 /* faulting for non current tsk/mm */
#define FAULT_FLAG_INSTRUCTION 0x100 /* The fault was during an instruction fetch */
+#define FAULT_FLAG_USED_CACHED 0x200 /* Our vmf->page was from a previous
+ * loop through the fault handler.
+ */
#define FAULT_FLAG_TRACE \
{ FAULT_FLAG_WRITE, "WRITE" }, \
@@ -328,7 +331,8 @@ extern pgprot_t protection_map[16];
{ FAULT_FLAG_TRIED, "TRIED" }, \
{ FAULT_FLAG_USER, "USER" }, \
{ FAULT_FLAG_REMOTE, "REMOTE" }, \
- { FAULT_FLAG_INSTRUCTION, "INSTRUCTION" }
+ { FAULT_FLAG_INSTRUCTION, "INSTRUCTION" }, \
+ { FAULT_FLAG_USED_CACHED, "USED_CACHED" }
/*
* vm_fault is filled by the the pagefault handler and passed to the vma's
diff --git a/mm/filemap.c b/mm/filemap.c
index 49b35293fa95..75a8b252814a 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2556,6 +2556,7 @@ vm_fault_t filemap_fault(struct vm_fault *vmf)
if (cached_page->mapping == mapping &&
cached_page->index == offset) {
page = cached_page;
+ vmf->flags |= FAULT_FLAG_USED_CACHED;
goto have_cached_page;
}
unlock_page(cached_page);
@@ -2618,8 +2619,10 @@ vm_fault_t filemap_fault(struct vm_fault *vmf)
* We have a locked page in the page cache, now we need to check
* that it's up-to-date. If not, it is going to be due to an error.
*/
- if (unlikely(!PageUptodate(page)))
+ if (unlikely(!PageUptodate(page))) {
+ vmf->flags &= ~(FAULT_FLAG_USED_CACHED);
goto page_not_uptodate;
+ }
/*
* Found the page and have a reference on it.
--
2.14.3
In preparation for caching pages during filemap faults we need to push
the struct vm_fault up a level into the arch page fault handlers, since
they are the ones responsible for retrying if we unlock the mmap_sem.
Signed-off-by: Josef Bacik <[email protected]>
---
arch/alpha/mm/fault.c | 4 ++-
arch/arc/mm/fault.c | 2 ++
arch/arm/mm/fault.c | 18 ++++++++-----
arch/arm64/mm/fault.c | 18 +++++++------
arch/hexagon/mm/vm_fault.c | 4 ++-
arch/ia64/mm/fault.c | 4 ++-
arch/m68k/mm/fault.c | 5 ++--
arch/microblaze/mm/fault.c | 4 ++-
arch/mips/mm/fault.c | 4 ++-
arch/nds32/mm/fault.c | 5 ++--
arch/nios2/mm/fault.c | 4 ++-
arch/openrisc/mm/fault.c | 5 ++--
arch/parisc/mm/fault.c | 5 ++--
arch/powerpc/mm/copro_fault.c | 4 ++-
arch/powerpc/mm/fault.c | 4 ++-
arch/riscv/mm/fault.c | 2 ++
arch/s390/mm/fault.c | 4 ++-
arch/sh/mm/fault.c | 4 ++-
arch/sparc/mm/fault_32.c | 6 ++++-
arch/sparc/mm/fault_64.c | 2 ++
arch/um/kernel/trap.c | 4 ++-
arch/unicore32/mm/fault.c | 17 +++++++-----
arch/x86/mm/fault.c | 4 ++-
arch/xtensa/mm/fault.c | 4 ++-
drivers/iommu/amd_iommu_v2.c | 4 ++-
drivers/iommu/intel-svm.c | 6 +++--
include/linux/mm.h | 16 +++++++++---
mm/gup.c | 8 ++++--
mm/hmm.c | 4 ++-
mm/ksm.c | 10 ++++---
mm/memory.c | 61 +++++++++++++++++++++----------------------
31 files changed, 157 insertions(+), 89 deletions(-)
diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c
index d73dc473fbb9..3c98dfef03a9 100644
--- a/arch/alpha/mm/fault.c
+++ b/arch/alpha/mm/fault.c
@@ -84,6 +84,7 @@ asmlinkage void
do_page_fault(unsigned long address, unsigned long mmcsr,
long cause, struct pt_regs *regs)
{
+ struct vm_fault vmf = {};
struct vm_area_struct * vma;
struct mm_struct *mm = current->mm;
const struct exception_table_entry *fixup;
@@ -148,7 +149,8 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
/* If for any reason at all we couldn't handle the fault,
make sure we exit gracefully rather than endlessly redo
the fault. */
- fault = handle_mm_fault(vma, address, flags);
+ vm_fault_init(&vmfs, vma, flags, address);
+ fault = handle_mm_fault(&vmf);
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
return;
diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c
index db6913094be3..7aeb81ff5070 100644
--- a/arch/arc/mm/fault.c
+++ b/arch/arc/mm/fault.c
@@ -63,6 +63,7 @@ noinline static int handle_kernel_vaddr_fault(unsigned long address)
void do_page_fault(unsigned long address, struct pt_regs *regs)
{
+ struct vm_fault vmf = {};
struct vm_area_struct *vma = NULL;
struct task_struct *tsk = current;
struct mm_struct *mm = tsk->mm;
@@ -141,6 +142,7 @@ void do_page_fault(unsigned long address, struct pt_regs *regs)
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
+ vm_fault_init(&vmf, vma, address, flags);
fault = handle_mm_fault(vma, address, flags);
/* If Pagefault was interrupted by SIGKILL, exit page fault "early" */
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 3232afb6fdc0..885a24385a0a 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -225,17 +225,17 @@ static inline bool access_error(unsigned int fsr, struct vm_area_struct *vma)
}
static vm_fault_t __kprobes
-__do_page_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr,
- unsigned int flags, struct task_struct *tsk)
+__do_page_fault(struct mm_struct *mm, struct vm_fault *vm, unsigned int fsr,
+ struct task_struct *tsk)
{
struct vm_area_struct *vma;
vm_fault_t fault;
- vma = find_vma(mm, addr);
+ vma = find_vma(mm, vmf->address);
fault = VM_FAULT_BADMAP;
if (unlikely(!vma))
goto out;
- if (unlikely(vma->vm_start > addr))
+ if (unlikely(vma->vm_start > vmf->address))
goto check_stack;
/*
@@ -248,12 +248,14 @@ __do_page_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr,
goto out;
}
- return handle_mm_fault(vma, addr & PAGE_MASK, flags);
+ vmf->vma = vma;
+ return handle_mm_fault(vmf);
check_stack:
/* Don't allow expansion below FIRST_USER_ADDRESS */
if (vma->vm_flags & VM_GROWSDOWN &&
- addr >= FIRST_USER_ADDRESS && !expand_stack(vma, addr))
+ vmf->address >= FIRST_USER_ADDRESS &&
+ !expand_stack(vma, vmf->address))
goto good_area;
out:
return fault;
@@ -262,6 +264,7 @@ __do_page_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr,
static int __kprobes
do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
{
+ struct vm_fault = {};
struct task_struct *tsk;
struct mm_struct *mm;
int sig, code;
@@ -314,7 +317,8 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
#endif
}
- fault = __do_page_fault(mm, addr, fsr, flags, tsk);
+ vm_fault_init(&vmf, NULL, addr, flags);
+ fault = __do_page_fault(mm, &vmf, fsr, tsk);
/* If we need to retry but a fatal signal is pending, handle the
* signal first. We do not need to release the mmap_sem because
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 50b30ff30de4..31e86a74cbe0 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -379,18 +379,17 @@ static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *re
#define VM_FAULT_BADMAP 0x010000
#define VM_FAULT_BADACCESS 0x020000
-static vm_fault_t __do_page_fault(struct mm_struct *mm, unsigned long addr,
- unsigned int mm_flags, unsigned long vm_flags,
- struct task_struct *tsk)
+static vm_fault_t __do_page_fault(struct mm_struct *mm, struct vm_fault *vmf,
+ unsigned long vm_flags, struct task_struct *tsk)
{
struct vm_area_struct *vma;
vm_fault_t fault;
- vma = find_vma(mm, addr);
+ vma = find_vma(mm, vmf->address);
fault = VM_FAULT_BADMAP;
if (unlikely(!vma))
goto out;
- if (unlikely(vma->vm_start > addr))
+ if (unlikely(vma->vm_start > vmf->address))
goto check_stack;
/*
@@ -407,10 +406,11 @@ static vm_fault_t __do_page_fault(struct mm_struct *mm, unsigned long addr,
goto out;
}
- return handle_mm_fault(vma, addr & PAGE_MASK, mm_flags);
+ vmf->vma = vma;
+ return handle_mm_fault(vmf);
check_stack:
- if (vma->vm_flags & VM_GROWSDOWN && !expand_stack(vma, addr))
+ if (vma->vm_flags & VM_GROWSDOWN && !expand_stack(vma, vmf->address))
goto good_area;
out:
return fault;
@@ -424,6 +424,7 @@ static bool is_el0_instruction_abort(unsigned int esr)
static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
struct pt_regs *regs)
{
+ struct vm_fault vmf = {};
struct task_struct *tsk;
struct mm_struct *mm;
struct siginfo si;
@@ -493,7 +494,8 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
#endif
}
- fault = __do_page_fault(mm, addr, mm_flags, vm_flags, tsk);
+ vm_fault_init(&vmf, NULL, addr, mm_flags);
+ fault = __do_page_fault(mm, vmf, vm_flags, tsk);
major |= fault & VM_FAULT_MAJOR;
if (fault & VM_FAULT_RETRY) {
diff --git a/arch/hexagon/mm/vm_fault.c b/arch/hexagon/mm/vm_fault.c
index eb263e61daf4..1ee1042bb2b5 100644
--- a/arch/hexagon/mm/vm_fault.c
+++ b/arch/hexagon/mm/vm_fault.c
@@ -48,6 +48,7 @@
*/
void do_page_fault(unsigned long address, long cause, struct pt_regs *regs)
{
+ struct vm_fault vmf = {};
struct vm_area_struct *vma;
struct mm_struct *mm = current->mm;
int si_signo;
@@ -102,7 +103,8 @@ void do_page_fault(unsigned long address, long cause, struct pt_regs *regs)
break;
}
- fault = handle_mm_fault(vma, address, flags);
+ vm_fault_init(&vmf, vma, address, flags);
+ fault = handle_mm_fault(&vmf);
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
return;
diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c
index a9d55ad8d67b..827b898adb5e 100644
--- a/arch/ia64/mm/fault.c
+++ b/arch/ia64/mm/fault.c
@@ -82,6 +82,7 @@ mapped_kernel_page_is_present (unsigned long address)
void __kprobes
ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *regs)
{
+ struct vm_fault vmf = {};
int signal = SIGSEGV, code = SEGV_MAPERR;
struct vm_area_struct *vma, *prev_vma;
struct mm_struct *mm = current->mm;
@@ -161,7 +162,8 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re
* sure we exit gracefully rather than endlessly redo the
* fault.
*/
- fault = handle_mm_fault(vma, address, flags);
+ vm_fault_init(&vmf, vma, address, flags);
+ fault = handle_mm_fault(&vmf);
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
return;
diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c
index 9b6163c05a75..e42eddc9c7ca 100644
--- a/arch/m68k/mm/fault.c
+++ b/arch/m68k/mm/fault.c
@@ -68,6 +68,7 @@ int send_fault_sig(struct pt_regs *regs)
int do_page_fault(struct pt_regs *regs, unsigned long address,
unsigned long error_code)
{
+ struct vm_fault vmf = {};
struct mm_struct *mm = current->mm;
struct vm_area_struct * vma;
vm_fault_t fault;
@@ -134,8 +135,8 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
-
- fault = handle_mm_fault(vma, address, flags);
+ vm_fault_init(&vmf, vma, address, flags);
+ fault = handle_mm_fault(&vmf);
pr_debug("handle_mm_fault returns %x\n", fault);
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c
index 202ad6a494f5..ade980266f65 100644
--- a/arch/microblaze/mm/fault.c
+++ b/arch/microblaze/mm/fault.c
@@ -86,6 +86,7 @@ void bad_page_fault(struct pt_regs *regs, unsigned long address, int sig)
void do_page_fault(struct pt_regs *regs, unsigned long address,
unsigned long error_code)
{
+ struct vm_fault vmf = {};
struct vm_area_struct *vma;
struct mm_struct *mm = current->mm;
int code = SEGV_MAPERR;
@@ -215,7 +216,8 @@ void do_page_fault(struct pt_regs *regs, unsigned long address,
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
- fault = handle_mm_fault(vma, address, flags);
+ vm_fault_init(&vmf, vma, address, flags);
+ fault = handle_mm_fault(&vmf);
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
return;
diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c
index 73d8a0f0b810..bf212bb70f24 100644
--- a/arch/mips/mm/fault.c
+++ b/arch/mips/mm/fault.c
@@ -38,6 +38,7 @@ int show_unhandled_signals = 1;
static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write,
unsigned long address)
{
+ struct vm_fault vmf = {};
struct vm_area_struct * vma = NULL;
struct task_struct *tsk = current;
struct mm_struct *mm = tsk->mm;
@@ -152,7 +153,8 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write,
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
- fault = handle_mm_fault(vma, address, flags);
+ vm_fault_init(&vmf, vma, address, flags);
+ fault = handle_mm_fault(&vmf);
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
return;
diff --git a/arch/nds32/mm/fault.c b/arch/nds32/mm/fault.c
index b740534b152c..27ac4caa5102 100644
--- a/arch/nds32/mm/fault.c
+++ b/arch/nds32/mm/fault.c
@@ -69,6 +69,7 @@ void show_pte(struct mm_struct *mm, unsigned long addr)
void do_page_fault(unsigned long entry, unsigned long addr,
unsigned int error_code, struct pt_regs *regs)
{
+ struct vm_fault vmf = {};
struct task_struct *tsk;
struct mm_struct *mm;
struct vm_area_struct *vma;
@@ -203,8 +204,8 @@ void do_page_fault(unsigned long entry, unsigned long addr,
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
-
- fault = handle_mm_fault(vma, addr, flags);
+ vm_fault_init(&vmf, vma, addr, flags);
+ fault = handle_mm_fault(&vmf);
/*
* If we need to retry but a fatal signal is pending, handle the
diff --git a/arch/nios2/mm/fault.c b/arch/nios2/mm/fault.c
index 24fd84cf6006..693472f05065 100644
--- a/arch/nios2/mm/fault.c
+++ b/arch/nios2/mm/fault.c
@@ -43,6 +43,7 @@
asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long cause,
unsigned long address)
{
+ struct vm_fault vmf = {};
struct vm_area_struct *vma = NULL;
struct task_struct *tsk = current;
struct mm_struct *mm = tsk->mm;
@@ -132,7 +133,8 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long cause,
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
- fault = handle_mm_fault(vma, address, flags);
+ vm_fault_init(&vmf, vma, address, flags);
+ fault = handle_mm_fault(&vmf);
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
return;
diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c
index dc4dbafc1d83..70eef1d9f7ed 100644
--- a/arch/openrisc/mm/fault.c
+++ b/arch/openrisc/mm/fault.c
@@ -49,6 +49,7 @@ extern void die(char *, struct pt_regs *, long);
asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long address,
unsigned long vector, int write_acc)
{
+ struct vm_fault vmf = {};
struct task_struct *tsk;
struct mm_struct *mm;
struct vm_area_struct *vma;
@@ -162,8 +163,8 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long address,
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
-
- fault = handle_mm_fault(vma, address, flags);
+ vm_fault_init(&vmf, vma, address, flags);
+ fault = handle_mm_fault(&vmf);
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
return;
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index c8e8b7c05558..83c89cada3c0 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -258,6 +258,7 @@ show_signal_msg(struct pt_regs *regs, unsigned long code,
void do_page_fault(struct pt_regs *regs, unsigned long code,
unsigned long address)
{
+ struct vm_fault vmf = {};
struct vm_area_struct *vma, *prev_vma;
struct task_struct *tsk;
struct mm_struct *mm;
@@ -300,8 +301,8 @@ void do_page_fault(struct pt_regs *regs, unsigned long code,
* sure we exit gracefully rather than endlessly redo the
* fault.
*/
-
- fault = handle_mm_fault(vma, address, flags);
+ vm_fault_init(&vmf, vma, address, flags);
+ fault = handle_mm_fault(&vmf);
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
return;
diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c
index c8da352e8686..02dd21a54479 100644
--- a/arch/powerpc/mm/copro_fault.c
+++ b/arch/powerpc/mm/copro_fault.c
@@ -36,6 +36,7 @@
int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea,
unsigned long dsisr, vm_fault_t *flt)
{
+ struct vm_fault vmf = {};
struct vm_area_struct *vma;
unsigned long is_write;
int ret;
@@ -77,7 +78,8 @@ int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea,
}
ret = 0;
- *flt = handle_mm_fault(vma, ea, is_write ? FAULT_FLAG_WRITE : 0);
+ vm_fault_init(&vmf, vma, ea, is_write ? FAULT_FLAG_WRITE : 0);
+ *flt = handle_mm_fault(&vmf);
if (unlikely(*flt & VM_FAULT_ERROR)) {
if (*flt & VM_FAULT_OOM) {
ret = -ENOMEM;
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index d51cf5f4e45e..cc00bba104fb 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -409,6 +409,7 @@ static void sanity_check_fault(bool is_write, unsigned long error_code) { }
static int __do_page_fault(struct pt_regs *regs, unsigned long address,
unsigned long error_code)
{
+ struct vm_fault vmf = {};
struct vm_area_struct * vma;
struct mm_struct *mm = current->mm;
unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
@@ -538,7 +539,8 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address,
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
- fault = handle_mm_fault(vma, address, flags);
+ vm_fault_init(&vmf, vma, address, flags);
+ fault = handle_mm_fault(&vmf);
#ifdef CONFIG_PPC_MEM_KEYS
/*
diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c
index 88401d5125bc..aa3db34c9eb8 100644
--- a/arch/riscv/mm/fault.c
+++ b/arch/riscv/mm/fault.c
@@ -36,6 +36,7 @@
*/
asmlinkage void do_page_fault(struct pt_regs *regs)
{
+ struct vm_fault vmf = {};
struct task_struct *tsk;
struct vm_area_struct *vma;
struct mm_struct *mm;
@@ -120,6 +121,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs)
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
+ vm_fault_init(&vmf, vma, addr, flags);
fault = handle_mm_fault(vma, addr, flags);
/*
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 72af23bacbb5..14cfd6de43ed 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -404,6 +404,7 @@ static noinline void do_fault_error(struct pt_regs *regs, int access,
*/
static inline vm_fault_t do_exception(struct pt_regs *regs, int access)
{
+ struct vm_fault vmf = {};
struct gmap *gmap;
struct task_struct *tsk;
struct mm_struct *mm;
@@ -499,7 +500,8 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access)
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
- fault = handle_mm_fault(vma, address, flags);
+ vm_fault_init(&vmf, vma, address, flags);
+ fault = handle_mm_fault(&vmf);
/* No reason to continue if interrupted by SIGKILL. */
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) {
fault = VM_FAULT_SIGNAL;
diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c
index 6defd2c6d9b1..31202706125c 100644
--- a/arch/sh/mm/fault.c
+++ b/arch/sh/mm/fault.c
@@ -392,6 +392,7 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
unsigned long error_code,
unsigned long address)
{
+ stuct vm_fault vmf = {};
unsigned long vec;
struct task_struct *tsk;
struct mm_struct *mm;
@@ -481,7 +482,8 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
- fault = handle_mm_fault(vma, address, flags);
+ vm_fault_init(&vmf, vma, address, flags);
+ fault = handle_mm_fault(&vmf);
if (unlikely(fault & (VM_FAULT_RETRY | VM_FAULT_ERROR)))
if (mm_fault_error(regs, error_code, address, fault))
diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index b0440b0edd97..a9dd62393934 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -160,6 +160,7 @@ static noinline void do_fault_siginfo(int code, int sig, struct pt_regs *regs,
asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write,
unsigned long address)
{
+ struct vm_fault vmf = {};
struct vm_area_struct *vma;
struct task_struct *tsk = current;
struct mm_struct *mm = tsk->mm;
@@ -235,6 +236,7 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write,
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
+ vm_fault_init(&vmf, vma, address, flags);
fault = handle_mm_fault(vma, address, flags);
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
@@ -377,6 +379,7 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write,
/* This always deals with user addresses. */
static void force_user_fault(unsigned long address, int write)
{
+ struct vm_fault vmf = {};
struct vm_area_struct *vma;
struct task_struct *tsk = current;
struct mm_struct *mm = tsk->mm;
@@ -405,7 +408,8 @@ static void force_user_fault(unsigned long address, int write)
if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
goto bad_area;
}
- switch (handle_mm_fault(vma, address, flags)) {
+ vm_fault_init(&vmf, vma, address, flags);
+ switch (handle_mm_fault(&vmf)) {
case VM_FAULT_SIGBUS:
case VM_FAULT_OOM:
goto do_sigbus;
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index 8f8a604c1300..381ab905eb2c 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -274,6 +274,7 @@ static void noinline __kprobes bogus_32bit_fault_tpc(struct pt_regs *regs)
asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs)
{
+ struct vm_fault vmf = {};
enum ctx_state prev_state = exception_enter();
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
@@ -433,6 +434,7 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs)
goto bad_area;
}
+ vm_fault_init(&vmf, vma, address, flags);
fault = handle_mm_fault(vma, address, flags);
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index cced82946042..c6d9e176c5c5 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -25,6 +25,7 @@
int handle_page_fault(unsigned long address, unsigned long ip,
int is_write, int is_user, int *code_out)
{
+ struct vm_fault vmf = {};
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
pgd_t *pgd;
@@ -74,7 +75,8 @@ int handle_page_fault(unsigned long address, unsigned long ip,
do {
vm_fault_t fault;
- fault = handle_mm_fault(vma, address, flags);
+ vm_fault_init(&vmf, vma, address, flags);
+ fault = handle_mm_fault(&vmf);
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
goto out_nosemaphore;
diff --git a/arch/unicore32/mm/fault.c b/arch/unicore32/mm/fault.c
index 8f12a5b50a42..68c2b0a65348 100644
--- a/arch/unicore32/mm/fault.c
+++ b/arch/unicore32/mm/fault.c
@@ -168,17 +168,17 @@ static inline bool access_error(unsigned int fsr, struct vm_area_struct *vma)
return vma->vm_flags & mask ? false : true;
}
-static vm_fault_t __do_pf(struct mm_struct *mm, unsigned long addr,
- unsigned int fsr, unsigned int flags, struct task_struct *tsk)
+static vm_fault_t __do_pf(struct mm_struct *mm, struct vm_fault *vmf,
+ unsigned int fsr, struct task_struct *tsk)
{
struct vm_area_struct *vma;
vm_fault_t fault;
- vma = find_vma(mm, addr);
+ vma = find_vma(mm, vmf->address);
fault = VM_FAULT_BADMAP;
if (unlikely(!vma))
goto out;
- if (unlikely(vma->vm_start > addr))
+ if (unlikely(vma->vm_start > vmf->address))
goto check_stack;
/*
@@ -195,11 +195,12 @@ static vm_fault_t __do_pf(struct mm_struct *mm, unsigned long addr,
* If for any reason at all we couldn't handle the fault, make
* sure we exit gracefully rather than endlessly redo the fault.
*/
- fault = handle_mm_fault(vma, addr & PAGE_MASK, flags);
+ vmf->vma = vma;
+ fault = handle_mm_fault(vmf);
return fault;
check_stack:
- if (vma->vm_flags & VM_GROWSDOWN && !expand_stack(vma, addr))
+ if (vma->vm_flags & VM_GROWSDOWN && !expand_stack(vma, vmf->address))
goto good_area;
out:
return fault;
@@ -207,6 +208,7 @@ static vm_fault_t __do_pf(struct mm_struct *mm, unsigned long addr,
static int do_pf(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
{
+ struct vm_fault vmf = {};
struct task_struct *tsk;
struct mm_struct *mm;
int sig, code;
@@ -253,7 +255,8 @@ static int do_pf(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
#endif
}
- fault = __do_pf(mm, addr, fsr, flags, tsk);
+ vm_fault_init(&vmf, NULL, addr, flags);
+ fault = __do_pf(mm, &vmf, fsr, tsk);
/* If we need to retry but a fatal signal is pending, handle the
* signal first. We do not need to release the mmap_sem because
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 47bebfe6efa7..9919a25b15e6 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -1211,6 +1211,7 @@ static noinline void
__do_page_fault(struct pt_regs *regs, unsigned long error_code,
unsigned long address)
{
+ struct vm_fault vmf = {};
struct vm_area_struct *vma;
struct task_struct *tsk;
struct mm_struct *mm;
@@ -1392,7 +1393,8 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code,
* fault, so we read the pkey beforehand.
*/
pkey = vma_pkey(vma);
- fault = handle_mm_fault(vma, address, flags);
+ vm_fault_init(&vmf, vma, address, flags);
+ fault = handle_mm_fault(&vmf);
major |= fault & VM_FAULT_MAJOR;
/*
diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c
index 2ab0e0dcd166..f1b0f4f858ff 100644
--- a/arch/xtensa/mm/fault.c
+++ b/arch/xtensa/mm/fault.c
@@ -35,6 +35,7 @@ void bad_page_fault(struct pt_regs*, unsigned long, int);
void do_page_fault(struct pt_regs *regs)
{
+ struct vm_fault vmf = {};
struct vm_area_struct * vma;
struct mm_struct *mm = current->mm;
unsigned int exccause = regs->exccause;
@@ -108,7 +109,8 @@ void do_page_fault(struct pt_regs *regs)
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
- fault = handle_mm_fault(vma, address, flags);
+ vm_fault_init(&vmf, vma, address, flags);
+ fault = handle_mm_fault(&vmf);
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
return;
diff --git a/drivers/iommu/amd_iommu_v2.c b/drivers/iommu/amd_iommu_v2.c
index 58da65df03f5..129e0ef68827 100644
--- a/drivers/iommu/amd_iommu_v2.c
+++ b/drivers/iommu/amd_iommu_v2.c
@@ -506,6 +506,7 @@ static bool access_error(struct vm_area_struct *vma, struct fault *fault)
static void do_fault(struct work_struct *work)
{
+ struct vm_fault vmf = {};
struct fault *fault = container_of(work, struct fault, work);
struct vm_area_struct *vma;
vm_fault_t ret = VM_FAULT_ERROR;
@@ -532,7 +533,8 @@ static void do_fault(struct work_struct *work)
if (access_error(vma, fault))
goto out;
- ret = handle_mm_fault(vma, address, flags);
+ vm_fault_init(&vmf, vma, address, flags);
+ ret = handle_mm_fault(&vmf);
out:
up_read(&mm->mmap_sem);
diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c
index 4a03e5090952..03aa02723242 100644
--- a/drivers/iommu/intel-svm.c
+++ b/drivers/iommu/intel-svm.c
@@ -567,6 +567,7 @@ static bool is_canonical_address(u64 addr)
static irqreturn_t prq_event_thread(int irq, void *d)
{
+ struct vm_fault vmf = {};
struct intel_iommu *iommu = d;
struct intel_svm *svm = NULL;
int head, tail, handled = 0;
@@ -636,8 +637,9 @@ static irqreturn_t prq_event_thread(int irq, void *d)
if (access_error(vma, req))
goto invalid;
- ret = handle_mm_fault(vma, address,
- req->wr_req ? FAULT_FLAG_WRITE : 0);
+ vm_fault_init(&vmf, vma, address,
+ req->wr_req ? FAULT_FLAG_WRITE : 0);
+ ret = handle_mm_fault(&vmf);
if (ret & VM_FAULT_ERROR)
goto invalid;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index a61ebe8ad4ca..e271c60af01a 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -378,6 +378,16 @@ struct vm_fault {
*/
};
+static inline void vm_fault_init(struct vm_fault *vmf,
+ struct vm_area_struct *vma,
+ unsigned long address,
+ unsigned int flags)
+{
+ vmf->vma = vma;
+ vmf->address = address;
+ vmf->flags = flags;
+}
+
/* page entry size for vm->huge_fault() */
enum page_entry_size {
PE_SIZE_PTE = 0,
@@ -1403,8 +1413,7 @@ int generic_error_remove_page(struct address_space *mapping, struct page *page);
int invalidate_inode_page(struct page *page);
#ifdef CONFIG_MMU
-extern vm_fault_t handle_mm_fault(struct vm_area_struct *vma,
- unsigned long address, unsigned int flags);
+extern vm_fault_t handle_mm_fault(struct vm_fault *vmf);
extern int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
unsigned long address, unsigned int fault_flags,
bool *unlocked);
@@ -1413,8 +1422,7 @@ void unmap_mapping_pages(struct address_space *mapping,
void unmap_mapping_range(struct address_space *mapping,
loff_t const holebegin, loff_t const holelen, int even_cows);
#else
-static inline vm_fault_t handle_mm_fault(struct vm_area_struct *vma,
- unsigned long address, unsigned int flags)
+static inline vm_fault_t handle_mm_fault(struct vm_fault *vmf)
{
/* should never happen if there's no MMU */
BUG();
diff --git a/mm/gup.c b/mm/gup.c
index 1abc8b4afff6..c12d1e98614b 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -496,6 +496,7 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address,
static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
unsigned long address, unsigned int *flags, int *nonblocking)
{
+ struct vm_fault vmf = {};
unsigned int fault_flags = 0;
vm_fault_t ret;
@@ -515,7 +516,8 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
fault_flags |= FAULT_FLAG_TRIED;
}
- ret = handle_mm_fault(vma, address, fault_flags);
+ vm_fault_init(&vmf, vma, address, fault_flags);
+ ret = handle_mm_fault(&vmf);
if (ret & VM_FAULT_ERROR) {
int err = vm_fault_to_errno(ret, *flags);
@@ -817,6 +819,7 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
unsigned long address, unsigned int fault_flags,
bool *unlocked)
{
+ struct vm_fault vmf = {};
struct vm_area_struct *vma;
vm_fault_t ret, major = 0;
@@ -831,7 +834,8 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
if (!vma_permits_fault(vma, fault_flags))
return -EFAULT;
- ret = handle_mm_fault(vma, address, fault_flags);
+ vm_fault_init(&vmf, vma, address, fault_flags);
+ ret = handle_mm_fault(&vmf);
major |= ret & VM_FAULT_MAJOR;
if (ret & VM_FAULT_ERROR) {
int err = vm_fault_to_errno(ret, 0);
diff --git a/mm/hmm.c b/mm/hmm.c
index c968e49f7a0c..695ef184a7d0 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -298,6 +298,7 @@ struct hmm_vma_walk {
static int hmm_vma_do_fault(struct mm_walk *walk, unsigned long addr,
bool write_fault, uint64_t *pfn)
{
+ struct vm_fault vmf = {};
unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_REMOTE;
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
@@ -306,7 +307,8 @@ static int hmm_vma_do_fault(struct mm_walk *walk, unsigned long addr,
flags |= hmm_vma_walk->block ? 0 : FAULT_FLAG_ALLOW_RETRY;
flags |= write_fault ? FAULT_FLAG_WRITE : 0;
- ret = handle_mm_fault(vma, addr, flags);
+ vm_fault_init(&vmf, vma, addr, flags);
+ ret = handle_mm_fault(&vmf);
if (ret & VM_FAULT_RETRY)
return -EBUSY;
if (ret & VM_FAULT_ERROR) {
diff --git a/mm/ksm.c b/mm/ksm.c
index 5b0894b45ee5..4b6d90357ee2 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -478,10 +478,12 @@ static int break_ksm(struct vm_area_struct *vma, unsigned long addr)
FOLL_GET | FOLL_MIGRATION | FOLL_REMOTE);
if (IS_ERR_OR_NULL(page))
break;
- if (PageKsm(page))
- ret = handle_mm_fault(vma, addr,
- FAULT_FLAG_WRITE | FAULT_FLAG_REMOTE);
- else
+ if (PageKsm(page)) {
+ struct vm_fault vmf = {};
+ vm_fault_init(&vmf, vma, addr,
+ FAULT_FLAG_WRITE | FAULT_FLAG_REMOTE);
+ ret = handle_mm_fault(&vmf);
+ } else
ret = VM_FAULT_WRITE;
put_page(page);
} while (!(ret & (VM_FAULT_WRITE | VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV | VM_FAULT_OOM)));
diff --git a/mm/memory.c b/mm/memory.c
index c467102a5cbc..9152c2a2c9f6 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4024,36 +4024,34 @@ static vm_fault_t handle_pte_fault(struct vm_fault *vmf)
* The mmap_sem may have been released depending on flags and our
* return value. See filemap_fault() and __lock_page_or_retry().
*/
-static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma,
- unsigned long address, unsigned int flags)
+static vm_fault_t __handle_mm_fault(struct vm_fault *vmf)
{
- struct vm_fault vmf = {
- .vma = vma,
- .address = address & PAGE_MASK,
- .flags = flags,
- .pgoff = linear_page_index(vma, address),
- .gfp_mask = __get_fault_gfp_mask(vma),
- };
- unsigned int dirty = flags & FAULT_FLAG_WRITE;
+ struct vm_area_struct *vma = vmf->vma;
+ unsigned long address = vmf->address;
+ unsigned int dirty = vmf->flags & FAULT_FLAG_WRITE;
struct mm_struct *mm = vma->vm_mm;
pgd_t *pgd;
p4d_t *p4d;
vm_fault_t ret;
+ vmf->address = address & PAGE_MASK;
+ vmf->pgoff = linear_page_index(vma, address);
+ vmf->gfp_mask = __get_fault_gfp_mask(vma);
+
pgd = pgd_offset(mm, address);
p4d = p4d_alloc(mm, pgd, address);
if (!p4d)
return VM_FAULT_OOM;
- vmf.pud = pud_alloc(mm, p4d, address);
- if (!vmf.pud)
+ vmf->pud = pud_alloc(mm, p4d, address);
+ if (!vmf->pud)
return VM_FAULT_OOM;
- if (pud_none(*vmf.pud) && transparent_hugepage_enabled(vma)) {
- ret = create_huge_pud(&vmf);
+ if (pud_none(*vmf->pud) && transparent_hugepage_enabled(vma)) {
+ ret = create_huge_pud(vmf);
if (!(ret & VM_FAULT_FALLBACK))
return ret;
} else {
- pud_t orig_pud = *vmf.pud;
+ pud_t orig_pud = *vmf->pud;
barrier();
if (pud_trans_huge(orig_pud) || pud_devmap(orig_pud)) {
@@ -4061,50 +4059,50 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma,
/* NUMA case for anonymous PUDs would go here */
if (dirty && !pud_write(orig_pud)) {
- ret = wp_huge_pud(&vmf, orig_pud);
+ ret = wp_huge_pud(vmf, orig_pud);
if (!(ret & VM_FAULT_FALLBACK))
return ret;
} else {
- huge_pud_set_accessed(&vmf, orig_pud);
+ huge_pud_set_accessed(vmf, orig_pud);
return 0;
}
}
}
- vmf.pmd = pmd_alloc(mm, vmf.pud, address);
- if (!vmf.pmd)
+ vmf->pmd = pmd_alloc(mm, vmf->pud, address);
+ if (!vmf->pmd)
return VM_FAULT_OOM;
- if (pmd_none(*vmf.pmd) && transparent_hugepage_enabled(vma)) {
- ret = create_huge_pmd(&vmf);
+ if (pmd_none(*vmf->pmd) && transparent_hugepage_enabled(vma)) {
+ ret = create_huge_pmd(vmf);
if (!(ret & VM_FAULT_FALLBACK))
return ret;
} else {
- pmd_t orig_pmd = *vmf.pmd;
+ pmd_t orig_pmd = *vmf->pmd;
barrier();
if (unlikely(is_swap_pmd(orig_pmd))) {
VM_BUG_ON(thp_migration_supported() &&
!is_pmd_migration_entry(orig_pmd));
if (is_pmd_migration_entry(orig_pmd))
- pmd_migration_entry_wait(mm, vmf.pmd);
+ pmd_migration_entry_wait(mm, vmf->pmd);
return 0;
}
if (pmd_trans_huge(orig_pmd) || pmd_devmap(orig_pmd)) {
if (pmd_protnone(orig_pmd) && vma_is_accessible(vma))
- return do_huge_pmd_numa_page(&vmf, orig_pmd);
+ return do_huge_pmd_numa_page(vmf, orig_pmd);
if (dirty && !pmd_write(orig_pmd)) {
- ret = wp_huge_pmd(&vmf, orig_pmd);
+ ret = wp_huge_pmd(vmf, orig_pmd);
if (!(ret & VM_FAULT_FALLBACK))
return ret;
} else {
- huge_pmd_set_accessed(&vmf, orig_pmd);
+ huge_pmd_set_accessed(vmf, orig_pmd);
return 0;
}
}
}
- return handle_pte_fault(&vmf);
+ return handle_pte_fault(vmf);
}
/*
@@ -4113,9 +4111,10 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma,
* The mmap_sem may have been released depending on flags and our
* return value. See filemap_fault() and __lock_page_or_retry().
*/
-vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
- unsigned int flags)
+vm_fault_t handle_mm_fault(struct vm_fault *vmf)
{
+ struct vm_area_struct *vma = vmf->vma;
+ unsigned int flags = vmf->flags;
vm_fault_t ret;
__set_current_state(TASK_RUNNING);
@@ -4139,9 +4138,9 @@ vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
mem_cgroup_enter_user_fault();
if (unlikely(is_vm_hugetlb_page(vma)))
- ret = hugetlb_fault(vma->vm_mm, vma, address, flags);
+ ret = hugetlb_fault(vma->vm_mm, vma, vmf->address, flags);
else
- ret = __handle_mm_fault(vma, address, flags);
+ ret = __handle_mm_fault(vmf);
if (flags & FAULT_FLAG_USER) {
mem_cgroup_exit_user_fault();
--
2.14.3
On Tue, Sep 25, 2018 at 11:30:04AM -0400, Josef Bacik wrote:
> In preparation for caching pages during filemap faults we need to push
> the struct vm_fault up a level into the arch page fault handlers, since
> they are the ones responsible for retrying if we unlock the mmap_sem.
>
> Signed-off-by: Josef Bacik <[email protected]>
> ---
> arch/alpha/mm/fault.c | 4 ++-
> arch/arc/mm/fault.c | 2 ++
> arch/arm/mm/fault.c | 18 ++++++++-----
> arch/arm64/mm/fault.c | 18 +++++++------
> arch/hexagon/mm/vm_fault.c | 4 ++-
> arch/ia64/mm/fault.c | 4 ++-
> arch/m68k/mm/fault.c | 5 ++--
> arch/microblaze/mm/fault.c | 4 ++-
> arch/mips/mm/fault.c | 4 ++-
> arch/nds32/mm/fault.c | 5 ++--
> arch/nios2/mm/fault.c | 4 ++-
> arch/openrisc/mm/fault.c | 5 ++--
> arch/parisc/mm/fault.c | 5 ++--
> arch/powerpc/mm/copro_fault.c | 4 ++-
> arch/powerpc/mm/fault.c | 4 ++-
> arch/riscv/mm/fault.c | 2 ++
> arch/s390/mm/fault.c | 4 ++-
> arch/sh/mm/fault.c | 4 ++-
> arch/sparc/mm/fault_32.c | 6 ++++-
> arch/sparc/mm/fault_64.c | 2 ++
> arch/um/kernel/trap.c | 4 ++-
> arch/unicore32/mm/fault.c | 17 +++++++-----
> arch/x86/mm/fault.c | 4 ++-
> arch/xtensa/mm/fault.c | 4 ++-
> drivers/iommu/amd_iommu_v2.c | 4 ++-
> drivers/iommu/intel-svm.c | 6 +++--
> include/linux/mm.h | 16 +++++++++---
> mm/gup.c | 8 ++++--
> mm/hmm.c | 4 ++-
> mm/ksm.c | 10 ++++---
> mm/memory.c | 61 +++++++++++++++++++++----------------------
> 31 files changed, 157 insertions(+), 89 deletions(-)
>
> diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c
> index d73dc473fbb9..3c98dfef03a9 100644
> --- a/arch/alpha/mm/fault.c
> +++ b/arch/alpha/mm/fault.c
> @@ -84,6 +84,7 @@ asmlinkage void
> do_page_fault(unsigned long address, unsigned long mmcsr,
> long cause, struct pt_regs *regs)
> {
> + struct vm_fault vmf = {};
> struct vm_area_struct * vma;
> struct mm_struct *mm = current->mm;
> const struct exception_table_entry *fixup;
> @@ -148,7 +149,8 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
> /* If for any reason at all we couldn't handle the fault,
> make sure we exit gracefully rather than endlessly redo
> the fault. */
> - fault = handle_mm_fault(vma, address, flags);
> + vm_fault_init(&vmfs, vma, flags, address);
> + fault = handle_mm_fault(&vmf);
Doesn't compile.
> --- a/arch/arm/mm/fault.c
> +++ b/arch/arm/mm/fault.c
> @@ -225,17 +225,17 @@ static inline bool access_error(unsigned int fsr, struct vm_area_struct *vma)
> }
>
> static vm_fault_t __kprobes
> -__do_page_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr,
> - unsigned int flags, struct task_struct *tsk)
> +__do_page_fault(struct mm_struct *mm, struct vm_fault *vm, unsigned int fsr,
vm_fault is *vm....
> + struct task_struct *tsk)
> {
> struct vm_area_struct *vma;
> vm_fault_t fault;
>
> - vma = find_vma(mm, addr);
> + vma = find_vma(mm, vmf->address);
So this doesn't compile.
>
> check_stack:
> - if (vma->vm_flags & VM_GROWSDOWN && !expand_stack(vma, addr))
> + if (vma->vm_flags & VM_GROWSDOWN && !expand_stack(vma, vmf->address))
> goto good_area;
> out:
> return fault;
> @@ -424,6 +424,7 @@ static bool is_el0_instruction_abort(unsigned int esr)
> static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
> struct pt_regs *regs)
> {
> + struct vm_fault vmf = {};
> struct task_struct *tsk;
> struct mm_struct *mm;
> struct siginfo si;
> @@ -493,7 +494,8 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
> #endif
> }
>
> - fault = __do_page_fault(mm, addr, mm_flags, vm_flags, tsk);
> + vm_fault_init(&vmf, NULL, addr, mm_flags);
> + fault = __do_page_fault(mm, vmf, vm_flags, tsk);
I'm betting this doesn't compile, either.
/me stops looking.
Cheers,
Dave.
--
Dave Chinner
[email protected]
On Tue, Sep 25, 2018 at 11:30:11AM -0400, Josef Bacik wrote:
> @@ -1454,6 +1463,11 @@ static inline int fixup_user_fault(struct task_struct *tsk,
> BUG();
> return -EFAULT;
> }
> +stiatc inline struct file *maybe_unlock_mmap_for_io(struct vm_area_struct *vma,
> + int flags)
> +{
> + return NULL;
> +}
This doesn't compile either.
-Dave.
--
Dave Chinner
[email protected]