When a failure occurs in rproc_add() it returns an error, but does
not cleanup after itself. This change adds the failure path in such
cases.
Signed-off-by: Siddharth Gupta <sidgup(a)codeaurora.org>
Cc: stable(a)vger.kernel.org
---
drivers/remoteproc/remoteproc_core.c | 15 ++++++++++++---
1 file changed, 12 insertions(+), 3 deletions(-)
diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c
index b874280..d823f70 100644
--- a/drivers/remoteproc/remoteproc_core.c
+++ b/drivers/remoteproc/remoteproc_core.c
@@ -2343,8 +2343,10 @@ int rproc_add(struct rproc *rproc)
return ret;
ret = device_add(dev);
- if (ret < 0)
- return ret;
+ if (ret < 0) {
+ put_device(dev);
+ goto rproc_remove_cdev;
+ }
dev_info(dev, "%s is available\n", rproc->name);
@@ -2355,7 +2357,7 @@ int rproc_add(struct rproc *rproc)
if (rproc->auto_boot) {
ret = rproc_trigger_auto_boot(rproc);
if (ret < 0)
- return ret;
+ goto rproc_remove_dev;
}
/* expose to rproc_get_by_phandle users */
@@ -2364,6 +2366,13 @@ int rproc_add(struct rproc *rproc)
mutex_unlock(&rproc_list_mutex);
return 0;
+
+rproc_remove_dev:
+ rproc_delete_debug_dir(rproc);
+ device_del(dev);
+rproc_remove_cdev:
+ rproc_char_device_remove(rproc);
+ return ret;
}
EXPORT_SYMBOL(rproc_add);
--
Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum,
a Linux Foundation Collaborative Project
Commit bfb819ea20ce ("proc: Check /proc/$pid/attr/ writes against file opener")
tried to make sure that there could not be a confusion between the opener of
a /proc/$pid/attr/ file and the writer. It used struct cred to make sure
the privileges didn't change. However, there were existing cases where a more
privileged thread was passing the opened fd to a differently privileged thread
(during container setup). Instead, use mm_struct to track whether the opener
and writer are still the same process. (This is what several other proc files
already do, though for different reasons.)
Reported-by: Christian Brauner <christian.brauner(a)ubuntu.com>
Reported-by: Andrea Righi <andrea.righi(a)canonical.com>
Tested-by: Andrea Righi <andrea.righi(a)canonical.com>
Fixes: bfb819ea20ce ("proc: Check /proc/$pid/attr/ writes against file opener")
Cc: stable(a)vger.kernel.org
Signed-off-by: Kees Cook <keescook(a)chromium.org>
---
fs/proc/base.c | 9 ++++++++-
1 file changed, 8 insertions(+), 1 deletion(-)
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 58bbf334265b..7118ebe38fa6 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -2674,6 +2674,11 @@ static int proc_pident_readdir(struct file *file, struct dir_context *ctx,
}
#ifdef CONFIG_SECURITY
+static int proc_pid_attr_open(struct inode *inode, struct file *file)
+{
+ return __mem_open(inode, file, PTRACE_MODE_READ_FSCREDS);
+}
+
static ssize_t proc_pid_attr_read(struct file * file, char __user * buf,
size_t count, loff_t *ppos)
{
@@ -2704,7 +2709,7 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf,
int rv;
/* A task may only write when it was the opener. */
- if (file->f_cred != current_real_cred())
+ if (file->private_data != current->mm)
return -EPERM;
rcu_read_lock();
@@ -2754,9 +2759,11 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf,
}
static const struct file_operations proc_pid_attr_operations = {
+ .open = proc_pid_attr_open,
.read = proc_pid_attr_read,
.write = proc_pid_attr_write,
.llseek = generic_file_llseek,
+ .release = mem_release,
};
#define LSM_DIR_OPS(LSM) \
--
2.25.1
This series has two fixes for FDMI.
Attributes length corrected for RHBA.
Fixed the wrong condition check in fc_ct_ms_fill_attr().
Kindly apply this series to scsi-queue at your earliest convenience.
Javed Hasan (2):
scsi: fc: Corrected RHBA attributes length
libfc: Corrected the condition check and invalid argument passed
drivers/scsi/libfc/fc_encode.h | 8 +++++---
include/scsi/fc/fc_ms.h | 4 ++--
2 files changed, 7 insertions(+), 5 deletions(-)
--
2.26.2
From: Hugh Dickins <hughd(a)google.com>
Subject: mm/thp: unmap_mapping_page() to fix THP truncate_cleanup_page()
There is a race between THP unmapping and truncation, when truncate sees
pmd_none() and skips the entry, after munmap's zap_huge_pmd() cleared it,
but before its page_remove_rmap() gets to decrement compound_mapcount:
generating false "BUG: Bad page cache" reports that the page is still
mapped when deleted. This commit fixes that, but not in the way I hoped.
The first attempt used try_to_unmap(page, TTU_SYNC|TTU_IGNORE_MLOCK)
instead of unmap_mapping_range() in truncate_cleanup_page(): it has often
been an annoyance that we usually call unmap_mapping_range() with no pages
locked, but there apply it to a single locked page. try_to_unmap() looks
more suitable for a single locked page.
However, try_to_unmap_one() contains a VM_BUG_ON_PAGE(!pvmw.pte,page): it
is used to insert THP migration entries, but not used to unmap THPs. Copy
zap_huge_pmd() and add THP handling now? Perhaps, but their TLB needs are
different, I'm too ignorant of the DAX cases, and couldn't decide how far
to go for anon+swap. Set that aside.
The second attempt took a different tack: make no change in truncate.c,
but modify zap_huge_pmd() to insert an invalidated huge pmd instead of
clearing it initially, then pmd_clear() between page_remove_rmap() and
unlocking at the end. Nice. But powerpc blows that approach out of the
water, with its serialize_against_pte_lookup(), and interesting pgtable
usage. It would need serious help to get working on powerpc (with a minor
optimization issue on s390 too). Set that aside.
Just add an "if (page_mapped(page)) synchronize_rcu();" or other such
delay, after unmapping in truncate_cleanup_page()? Perhaps, but though
that's likely to reduce or eliminate the number of incidents, it would
give less assurance of whether we had identified the problem correctly.
This successful iteration introduces "unmap_mapping_page(page)" instead of
try_to_unmap(), and goes the usual unmap_mapping_range_tree() route, with
an addition to details. Then zap_pmd_range() watches for this case, and
does spin_unlock(pmd_lock) if so - just like page_vma_mapped_walk() now
does in the PVMW_SYNC case. Not pretty, but safe.
Note that unmap_mapping_page() is doing a VM_BUG_ON(!PageLocked) to assert
its interface; but currently that's only used to make sure that
page->mapping is stable, and zap_pmd_range() doesn't care if the page is
locked or not. Along these lines, in invalidate_inode_pages2_range() move
the initial unmap_mapping_range() out from under page lock, before then
calling unmap_mapping_page() under page lock if still mapped.
Link: https://lkml.kernel.org/r/a2a4a148-cdd8-942c-4ef8-51b77f643dbe@google.com
Fixes: fc127da085c2 ("truncate: handle file thp")
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov(a)linux.intel.com>
Reviewed-by: Yang Shi <shy828301(a)gmail.com>
Cc: Alistair Popple <apopple(a)nvidia.com>
Cc: Jan Kara <jack(a)suse.cz>
Cc: Jue Wang <juew(a)google.com>
Cc: "Matthew Wilcox (Oracle)" <willy(a)infradead.org>
Cc: Miaohe Lin <linmiaohe(a)huawei.com>
Cc: Minchan Kim <minchan(a)kernel.org>
Cc: Naoya Horiguchi <naoya.horiguchi(a)nec.com>
Cc: Oscar Salvador <osalvador(a)suse.de>
Cc: Peter Xu <peterx(a)redhat.com>
Cc: Ralph Campbell <rcampbell(a)nvidia.com>
Cc: Shakeel Butt <shakeelb(a)google.com>
Cc: Wang Yugui <wangyugui(a)e16-tech.com>
Cc: Zi Yan <ziy(a)nvidia.com>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
include/linux/mm.h | 3 +++
mm/memory.c | 41 +++++++++++++++++++++++++++++++++++++++++
mm/truncate.c | 43 +++++++++++++++++++------------------------
3 files changed, 63 insertions(+), 24 deletions(-)
--- a/include/linux/mm.h~mm-thp-unmap_mapping_page-to-fix-thp-truncate_cleanup_page
+++ a/include/linux/mm.h
@@ -1719,6 +1719,7 @@ struct zap_details {
struct address_space *check_mapping; /* Check page->mapping if set */
pgoff_t first_index; /* Lowest page->index to unmap */
pgoff_t last_index; /* Highest page->index to unmap */
+ struct page *single_page; /* Locked page to be unmapped */
};
struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
@@ -1766,6 +1767,7 @@ extern vm_fault_t handle_mm_fault(struct
extern int fixup_user_fault(struct mm_struct *mm,
unsigned long address, unsigned int fault_flags,
bool *unlocked);
+void unmap_mapping_page(struct page *page);
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,
@@ -1786,6 +1788,7 @@ static inline int fixup_user_fault(struc
BUG();
return -EFAULT;
}
+static inline void unmap_mapping_page(struct page *page) { }
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,
--- a/mm/memory.c~mm-thp-unmap_mapping_page-to-fix-thp-truncate_cleanup_page
+++ a/mm/memory.c
@@ -1361,7 +1361,18 @@ static inline unsigned long zap_pmd_rang
else if (zap_huge_pmd(tlb, vma, pmd, addr))
goto next;
/* fall through */
+ } else if (details && details->single_page &&
+ PageTransCompound(details->single_page) &&
+ next - addr == HPAGE_PMD_SIZE && pmd_none(*pmd)) {
+ spinlock_t *ptl = pmd_lock(tlb->mm, pmd);
+ /*
+ * Take and drop THP pmd lock so that we cannot return
+ * prematurely, while zap_huge_pmd() has cleared *pmd,
+ * but not yet decremented compound_mapcount().
+ */
+ spin_unlock(ptl);
}
+
/*
* Here there can be other concurrent MADV_DONTNEED or
* trans huge page faults running, and if the pmd is
@@ -3237,6 +3248,36 @@ static inline void unmap_mapping_range_t
}
/**
+ * unmap_mapping_page() - Unmap single page from processes.
+ * @page: The locked page to be unmapped.
+ *
+ * Unmap this page from any userspace process which still has it mmaped.
+ * Typically, for efficiency, the range of nearby pages has already been
+ * unmapped by unmap_mapping_pages() or unmap_mapping_range(). But once
+ * truncation or invalidation holds the lock on a page, it may find that
+ * the page has been remapped again: and then uses unmap_mapping_page()
+ * to unmap it finally.
+ */
+void unmap_mapping_page(struct page *page)
+{
+ struct address_space *mapping = page->mapping;
+ struct zap_details details = { };
+
+ VM_BUG_ON(!PageLocked(page));
+ VM_BUG_ON(PageTail(page));
+
+ details.check_mapping = mapping;
+ details.first_index = page->index;
+ details.last_index = page->index + thp_nr_pages(page) - 1;
+ details.single_page = page;
+
+ i_mmap_lock_write(mapping);
+ if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root)))
+ unmap_mapping_range_tree(&mapping->i_mmap, &details);
+ i_mmap_unlock_write(mapping);
+}
+
+/**
* unmap_mapping_pages() - Unmap pages from processes.
* @mapping: The address space containing pages to be unmapped.
* @start: Index of first page to be unmapped.
--- a/mm/truncate.c~mm-thp-unmap_mapping_page-to-fix-thp-truncate_cleanup_page
+++ a/mm/truncate.c
@@ -167,13 +167,10 @@ void do_invalidatepage(struct page *page
* its lock, b) when a concurrent invalidate_mapping_pages got there first and
* c) when tmpfs swizzles a page between a tmpfs inode and swapper_space.
*/
-static void
-truncate_cleanup_page(struct address_space *mapping, struct page *page)
+static void truncate_cleanup_page(struct page *page)
{
- if (page_mapped(page)) {
- unsigned int nr = thp_nr_pages(page);
- unmap_mapping_pages(mapping, page->index, nr, false);
- }
+ if (page_mapped(page))
+ unmap_mapping_page(page);
if (page_has_private(page))
do_invalidatepage(page, 0, thp_size(page));
@@ -218,7 +215,7 @@ int truncate_inode_page(struct address_s
if (page->mapping != mapping)
return -EIO;
- truncate_cleanup_page(mapping, page);
+ truncate_cleanup_page(page);
delete_from_page_cache(page);
return 0;
}
@@ -325,7 +322,7 @@ void truncate_inode_pages_range(struct a
index = indices[pagevec_count(&pvec) - 1] + 1;
truncate_exceptional_pvec_entries(mapping, &pvec, indices);
for (i = 0; i < pagevec_count(&pvec); i++)
- truncate_cleanup_page(mapping, pvec.pages[i]);
+ truncate_cleanup_page(pvec.pages[i]);
delete_from_page_cache_batch(mapping, &pvec);
for (i = 0; i < pagevec_count(&pvec); i++)
unlock_page(pvec.pages[i]);
@@ -639,6 +636,16 @@ int invalidate_inode_pages2_range(struct
continue;
}
+ if (!did_range_unmap && page_mapped(page)) {
+ /*
+ * If page is mapped, before taking its lock,
+ * zap the rest of the file in one hit.
+ */
+ unmap_mapping_pages(mapping, index,
+ (1 + end - index), false);
+ did_range_unmap = 1;
+ }
+
lock_page(page);
WARN_ON(page_to_index(page) != index);
if (page->mapping != mapping) {
@@ -646,23 +653,11 @@ int invalidate_inode_pages2_range(struct
continue;
}
wait_on_page_writeback(page);
- if (page_mapped(page)) {
- if (!did_range_unmap) {
- /*
- * Zap the rest of the file in one hit.
- */
- unmap_mapping_pages(mapping, index,
- (1 + end - index), false);
- did_range_unmap = 1;
- } else {
- /*
- * Just zap this page
- */
- unmap_mapping_pages(mapping, index,
- 1, false);
- }
- }
+
+ if (page_mapped(page))
+ unmap_mapping_page(page);
BUG_ON(page_mapped(page));
+
ret2 = do_launder_page(mapping, page);
if (ret2 == 0) {
if (!invalidate_complete_page2(mapping, page))
_
From: Jue Wang <juew(a)google.com>
Subject: mm/thp: fix page_address_in_vma() on file THP tails
Anon THP tails were already supported, but memory-failure may need to use
page_address_in_vma() on file THP tails, which its page->mapping check did
not permit: fix it.
hughd adds: no current usage is known to hit the issue, but this does fix
a subtle trap in a general helper: best fixed in stable sooner than later.
Link: https://lkml.kernel.org/r/a0d9b53-bf5d-8bab-ac5-759dc61819c1@google.com
Fixes: 800d8c63b2e9 ("shmem: add huge pages support")
Signed-off-by: Jue Wang <juew(a)google.com>
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Reviewed-by: Matthew Wilcox (Oracle) <willy(a)infradead.org>
Reviewed-by: Yang Shi <shy828301(a)gmail.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov(a)linux.intel.com>
Cc: Alistair Popple <apopple(a)nvidia.com>
Cc: Jan Kara <jack(a)suse.cz>
Cc: Miaohe Lin <linmiaohe(a)huawei.com>
Cc: Minchan Kim <minchan(a)kernel.org>
Cc: Naoya Horiguchi <naoya.horiguchi(a)nec.com>
Cc: Oscar Salvador <osalvador(a)suse.de>
Cc: Peter Xu <peterx(a)redhat.com>
Cc: Ralph Campbell <rcampbell(a)nvidia.com>
Cc: Shakeel Butt <shakeelb(a)google.com>
Cc: Wang Yugui <wangyugui(a)e16-tech.com>
Cc: Zi Yan <ziy(a)nvidia.com>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
mm/rmap.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
--- a/mm/rmap.c~mm-thp-fix-page_address_in_vma-on-file-thp-tails
+++ a/mm/rmap.c
@@ -716,11 +716,11 @@ unsigned long page_address_in_vma(struct
if (!vma->anon_vma || !page__anon_vma ||
vma->anon_vma->root != page__anon_vma->root)
return -EFAULT;
- } else if (page->mapping) {
- if (!vma->vm_file || vma->vm_file->f_mapping != page->mapping)
- return -EFAULT;
- } else
+ } else if (!vma->vm_file) {
+ return -EFAULT;
+ } else if (vma->vm_file->f_mapping != compound_head(page)->mapping) {
return -EFAULT;
+ }
return vma_address(page, vma);
}
_
From: Hugh Dickins <hughd(a)google.com>
Subject: mm/thp: fix vma_address() if virtual address below file offset
Running certain tests with a DEBUG_VM kernel would crash within hours, on
the total_mapcount BUG() in split_huge_page_to_list(), while trying to
free up some memory by punching a hole in a shmem huge page: split's
try_to_unmap() was unable to find all the mappings of the page (which, on
a !DEBUG_VM kernel, would then keep the huge page pinned in memory).
When that BUG() was changed to a WARN(), it would later crash on the
VM_BUG_ON_VMA(end < vma->vm_start || start >= vma->vm_end, vma) in
mm/internal.h:vma_address(), used by rmap_walk_file() for try_to_unmap().
vma_address() is usually correct, but there's a wraparound case when the
vm_start address is unusually low, but vm_pgoff not so low: vma_address()
chooses max(start, vma->vm_start), but that decides on the wrong address,
because start has become almost ULONG_MAX.
Rewrite vma_address() to be more careful about vm_pgoff; move the
VM_BUG_ON_VMA() out of it, returning -EFAULT for errors, so that it can be
safely used from page_mapped_in_vma() and page_address_in_vma() too.
Add vma_address_end() to apply similar care to end address calculation, in
page_vma_mapped_walk() and page_mkclean_one() and try_to_unmap_one();
though it raises a question of whether callers would do better to supply
pvmw->end to page_vma_mapped_walk() - I chose not, for a smaller patch.
An irritation is that their apparent generality breaks down on KSM pages,
which cannot be located by the page->index that page_to_pgoff() uses: as
4b0ece6fa016 ("mm: migrate: fix remove_migration_pte() for ksm pages")
once discovered. I dithered over the best thing to do about that, and
have ended up with a VM_BUG_ON_PAGE(PageKsm) in both vma_address() and
vma_address_end(); though the only place in danger of using it on them was
try_to_unmap_one().
Sidenote: vma_address() and vma_address_end() now use compound_nr() on a
head page, instead of thp_size(): to make the right calculation on a
hugetlbfs page, whether or not THPs are configured. try_to_unmap() is
used on hugetlbfs pages, but perhaps the wrong calculation never mattered.
Link: https://lkml.kernel.org/r/caf1c1a3-7cfb-7f8f-1beb-ba816e932825@google.com
Fixes: a8fa41ad2f6f ("mm, rmap: check all VMAs that PTE-mapped THP can be part of")
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov(a)linux.intel.com>
Cc: Alistair Popple <apopple(a)nvidia.com>
Cc: Jan Kara <jack(a)suse.cz>
Cc: Jue Wang <juew(a)google.com>
Cc: "Matthew Wilcox (Oracle)" <willy(a)infradead.org>
Cc: Miaohe Lin <linmiaohe(a)huawei.com>
Cc: Minchan Kim <minchan(a)kernel.org>
Cc: Naoya Horiguchi <naoya.horiguchi(a)nec.com>
Cc: Oscar Salvador <osalvador(a)suse.de>
Cc: Peter Xu <peterx(a)redhat.com>
Cc: Ralph Campbell <rcampbell(a)nvidia.com>
Cc: Shakeel Butt <shakeelb(a)google.com>
Cc: Wang Yugui <wangyugui(a)e16-tech.com>
Cc: Yang Shi <shy828301(a)gmail.com>
Cc: Zi Yan <ziy(a)nvidia.com>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
mm/internal.h | 51 ++++++++++++++++++++++++++++++-----------
mm/page_vma_mapped.c | 16 ++++--------
mm/rmap.c | 16 ++++++------
3 files changed, 52 insertions(+), 31 deletions(-)
--- a/mm/internal.h~mm-thp-fix-vma_address-if-virtual-address-below-file-offset
+++ a/mm/internal.h
@@ -384,27 +384,52 @@ static inline void mlock_migrate_page(st
extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma);
/*
- * At what user virtual address is page expected in @vma?
+ * At what user virtual address is page expected in vma?
+ * Returns -EFAULT if all of the page is outside the range of vma.
+ * If page is a compound head, the entire compound page is considered.
*/
static inline unsigned long
-__vma_address(struct page *page, struct vm_area_struct *vma)
+vma_address(struct page *page, struct vm_area_struct *vma)
{
- pgoff_t pgoff = page_to_pgoff(page);
- return vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
+ pgoff_t pgoff;
+ unsigned long address;
+
+ VM_BUG_ON_PAGE(PageKsm(page), page); /* KSM page->index unusable */
+ pgoff = page_to_pgoff(page);
+ if (pgoff >= vma->vm_pgoff) {
+ address = vma->vm_start +
+ ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
+ /* Check for address beyond vma (or wrapped through 0?) */
+ if (address < vma->vm_start || address >= vma->vm_end)
+ address = -EFAULT;
+ } else if (PageHead(page) &&
+ pgoff + compound_nr(page) - 1 >= vma->vm_pgoff) {
+ /* Test above avoids possibility of wrap to 0 on 32-bit */
+ address = vma->vm_start;
+ } else {
+ address = -EFAULT;
+ }
+ return address;
}
+/*
+ * Then at what user virtual address will none of the page be found in vma?
+ * Assumes that vma_address() already returned a good starting address.
+ * If page is a compound head, the entire compound page is considered.
+ */
static inline unsigned long
-vma_address(struct page *page, struct vm_area_struct *vma)
+vma_address_end(struct page *page, struct vm_area_struct *vma)
{
- unsigned long start, end;
-
- start = __vma_address(page, vma);
- end = start + thp_size(page) - PAGE_SIZE;
-
- /* page should be within @vma mapping range */
- VM_BUG_ON_VMA(end < vma->vm_start || start >= vma->vm_end, vma);
+ pgoff_t pgoff;
+ unsigned long address;
- return max(start, vma->vm_start);
+ VM_BUG_ON_PAGE(PageKsm(page), page); /* KSM page->index unusable */
+ pgoff = page_to_pgoff(page) + compound_nr(page);
+ address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
+ /* Check for address beyond vma (or wrapped through 0?) */
+ if (address < vma->vm_start || address > vma->vm_end)
+ address = vma->vm_end;
+ return address;
}
static inline struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf,
--- a/mm/page_vma_mapped.c~mm-thp-fix-vma_address-if-virtual-address-below-file-offset
+++ a/mm/page_vma_mapped.c
@@ -228,18 +228,18 @@ restart:
if (!map_pte(pvmw))
goto next_pte;
while (1) {
+ unsigned long end;
+
if (check_pte(pvmw))
return true;
next_pte:
/* Seek to next pte only makes sense for THP */
if (!PageTransHuge(pvmw->page) || PageHuge(pvmw->page))
return not_found(pvmw);
+ end = vma_address_end(pvmw->page, pvmw->vma);
do {
pvmw->address += PAGE_SIZE;
- if (pvmw->address >= pvmw->vma->vm_end ||
- pvmw->address >=
- __vma_address(pvmw->page, pvmw->vma) +
- thp_size(pvmw->page))
+ if (pvmw->address >= end)
return not_found(pvmw);
/* Did we cross page table boundary? */
if (pvmw->address % PMD_SIZE == 0) {
@@ -277,14 +277,10 @@ int page_mapped_in_vma(struct page *page
.vma = vma,
.flags = PVMW_SYNC,
};
- unsigned long start, end;
-
- start = __vma_address(page, vma);
- end = start + thp_size(page) - PAGE_SIZE;
- if (unlikely(end < vma->vm_start || start >= vma->vm_end))
+ pvmw.address = vma_address(page, vma);
+ if (pvmw.address == -EFAULT)
return 0;
- pvmw.address = max(start, vma->vm_start);
if (!page_vma_mapped_walk(&pvmw))
return 0;
page_vma_mapped_walk_done(&pvmw);
--- a/mm/rmap.c~mm-thp-fix-vma_address-if-virtual-address-below-file-offset
+++ a/mm/rmap.c
@@ -707,7 +707,6 @@ static bool should_defer_flush(struct mm
*/
unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma)
{
- unsigned long address;
if (PageAnon(page)) {
struct anon_vma *page__anon_vma = page_anon_vma(page);
/*
@@ -722,10 +721,8 @@ unsigned long page_address_in_vma(struct
return -EFAULT;
} else
return -EFAULT;
- address = __vma_address(page, vma);
- if (unlikely(address < vma->vm_start || address >= vma->vm_end))
- return -EFAULT;
- return address;
+
+ return vma_address(page, vma);
}
pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address)
@@ -919,7 +916,7 @@ static bool page_mkclean_one(struct page
*/
mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE,
0, vma, vma->vm_mm, address,
- min(vma->vm_end, address + page_size(page)));
+ vma_address_end(page, vma));
mmu_notifier_invalidate_range_start(&range);
while (page_vma_mapped_walk(&pvmw)) {
@@ -1435,9 +1432,10 @@ static bool try_to_unmap_one(struct page
* Note that the page can not be free in this function as call of
* try_to_unmap() must hold a reference on the page.
*/
+ range.end = PageKsm(page) ?
+ address + PAGE_SIZE : vma_address_end(page, vma);
mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm,
- address,
- min(vma->vm_end, address + page_size(page)));
+ address, range.end);
if (PageHuge(page)) {
/*
* If sharing is possible, start and end will be adjusted
@@ -1889,6 +1887,7 @@ static void rmap_walk_anon(struct page *
struct vm_area_struct *vma = avc->vma;
unsigned long address = vma_address(page, vma);
+ VM_BUG_ON_VMA(address == -EFAULT, vma);
cond_resched();
if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg))
@@ -1943,6 +1942,7 @@ static void rmap_walk_file(struct page *
pgoff_start, pgoff_end) {
unsigned long address = vma_address(page, vma);
+ VM_BUG_ON_VMA(address == -EFAULT, vma);
cond_resched();
if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg))
_
From: Hugh Dickins <hughd(a)google.com>
Subject: mm/thp: try_to_unmap() use TTU_SYNC for safe splitting
Stressing huge tmpfs often crashed on unmap_page()'s VM_BUG_ON_PAGE
(!unmap_success): with dump_page() showing mapcount:1, but then its raw
struct page output showing _mapcount ffffffff i.e. mapcount 0.
And even if that particular VM_BUG_ON_PAGE(!unmap_success) is removed, it
is immediately followed by a VM_BUG_ON_PAGE(compound_mapcount(head)), and
further down an IS_ENABLED(CONFIG_DEBUG_VM) total_mapcount BUG(): all
indicative of some mapcount difficulty in development here perhaps. But
the !CONFIG_DEBUG_VM path handles the failures correctly and silently.
I believe the problem is that once a racing unmap has cleared pte or pmd,
try_to_unmap_one() may skip taking the page table lock, and emerge from
try_to_unmap() before the racing task has reached decrementing mapcount.
Instead of abandoning the unsafe VM_BUG_ON_PAGE(), and the ones that
follow, use PVMW_SYNC in try_to_unmap_one() in this case: adding TTU_SYNC
to the options, and passing that from unmap_page().
When CONFIG_DEBUG_VM, or for non-debug too? Consensus is to do the same
for both: the slight overhead added should rarely matter, except perhaps
if splitting sparsely-populated multiply-mapped shmem. Once confident
that bugs are fixed, TTU_SYNC here can be removed, and the race tolerated.
Link: https://lkml.kernel.org/r/c1e95853-8bcd-d8fd-55fa-e7f2488e78f@google.com
Fixes: fec89c109f3a ("thp: rewrite freeze_page()/unfreeze_page() with generic rmap walkers")
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Cc: Alistair Popple <apopple(a)nvidia.com>
Cc: Jan Kara <jack(a)suse.cz>
Cc: Jue Wang <juew(a)google.com>
Cc: Kirill A. Shutemov <kirill.shutemov(a)linux.intel.com>
Cc: "Matthew Wilcox (Oracle)" <willy(a)infradead.org>
Cc: Miaohe Lin <linmiaohe(a)huawei.com>
Cc: Minchan Kim <minchan(a)kernel.org>
Cc: Naoya Horiguchi <naoya.horiguchi(a)nec.com>
Cc: Oscar Salvador <osalvador(a)suse.de>
Cc: Peter Xu <peterx(a)redhat.com>
Cc: Ralph Campbell <rcampbell(a)nvidia.com>
Cc: Shakeel Butt <shakeelb(a)google.com>
Cc: Wang Yugui <wangyugui(a)e16-tech.com>
Cc: Yang Shi <shy828301(a)gmail.com>
Cc: Zi Yan <ziy(a)nvidia.com>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
include/linux/rmap.h | 1 +
mm/huge_memory.c | 2 +-
mm/page_vma_mapped.c | 11 +++++++++++
mm/rmap.c | 17 ++++++++++++++++-
4 files changed, 29 insertions(+), 2 deletions(-)
--- a/include/linux/rmap.h~mm-thp-try_to_unmap-use-ttu_sync-for-safe-splitting
+++ a/include/linux/rmap.h
@@ -91,6 +91,7 @@ enum ttu_flags {
TTU_SPLIT_HUGE_PMD = 0x4, /* split huge PMD if any */
TTU_IGNORE_MLOCK = 0x8, /* ignore mlock */
+ TTU_SYNC = 0x10, /* avoid racy checks with PVMW_SYNC */
TTU_IGNORE_HWPOISON = 0x20, /* corrupted page is recoverable */
TTU_BATCH_FLUSH = 0x40, /* Batch TLB flushes where possible
* and caller guarantees they will
--- a/mm/huge_memory.c~mm-thp-try_to_unmap-use-ttu_sync-for-safe-splitting
+++ a/mm/huge_memory.c
@@ -2350,7 +2350,7 @@ void vma_adjust_trans_huge(struct vm_are
static void unmap_page(struct page *page)
{
- enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK |
+ enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK | TTU_SYNC |
TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD;
bool unmap_success;
--- a/mm/page_vma_mapped.c~mm-thp-try_to_unmap-use-ttu_sync-for-safe-splitting
+++ a/mm/page_vma_mapped.c
@@ -212,6 +212,17 @@ restart:
pvmw->ptl = NULL;
}
} else if (!pmd_present(pmde)) {
+ /*
+ * If PVMW_SYNC, take and drop THP pmd lock so that we
+ * cannot return prematurely, while zap_huge_pmd() has
+ * cleared *pmd but not decremented compound_mapcount().
+ */
+ if ((pvmw->flags & PVMW_SYNC) &&
+ PageTransCompound(pvmw->page)) {
+ spinlock_t *ptl = pmd_lock(mm, pvmw->pmd);
+
+ spin_unlock(ptl);
+ }
return false;
}
if (!map_pte(pvmw))
--- a/mm/rmap.c~mm-thp-try_to_unmap-use-ttu_sync-for-safe-splitting
+++ a/mm/rmap.c
@@ -1405,6 +1405,15 @@ static bool try_to_unmap_one(struct page
struct mmu_notifier_range range;
enum ttu_flags flags = (enum ttu_flags)(long)arg;
+ /*
+ * When racing against e.g. zap_pte_range() on another cpu,
+ * in between its ptep_get_and_clear_full() and page_remove_rmap(),
+ * try_to_unmap() may return false when it is about to become true,
+ * if page table locking is skipped: use TTU_SYNC to wait for that.
+ */
+ if (flags & TTU_SYNC)
+ pvmw.flags = PVMW_SYNC;
+
/* munlock has nothing to gain from examining un-locked vmas */
if ((flags & TTU_MUNLOCK) && !(vma->vm_flags & VM_LOCKED))
return true;
@@ -1777,7 +1786,13 @@ bool try_to_unmap(struct page *page, enu
else
rmap_walk(page, &rwc);
- return !page_mapcount(page) ? true : false;
+ /*
+ * When racing against e.g. zap_pte_range() on another cpu,
+ * in between its ptep_get_and_clear_full() and page_remove_rmap(),
+ * try_to_unmap() may return false when it is about to become true,
+ * if page table locking is skipped: use TTU_SYNC to wait for that.
+ */
+ return !page_mapcount(page);
}
/**
_
From: Hugh Dickins <hughd(a)google.com>
Subject: mm/thp: make is_huge_zero_pmd() safe and quicker
Most callers of is_huge_zero_pmd() supply a pmd already verified present;
but a few (notably zap_huge_pmd()) do not - it might be a pmd migration
entry, in which the pfn is encoded differently from a present pmd: which
might pass the is_huge_zero_pmd() test (though not on x86, since L1TF
forced us to protect against that); or perhaps even crash in pmd_page()
applied to a swap-like entry.
Make it safe by adding pmd_present() check into is_huge_zero_pmd() itself;
and make it quicker by saving huge_zero_pfn, so that is_huge_zero_pmd()
will not need to do that pmd_page() lookup each time.
__split_huge_pmd_locked() checked pmd_trans_huge() before: that worked,
but is unnecessary now that is_huge_zero_pmd() checks present.
Link: https://lkml.kernel.org/r/21ea9ca-a1f5-8b90-5e88-95fb1c49bbfa@google.com
Fixes: e71769ae5260 ("mm: enable thp migration for shmem thp")
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov(a)linux.intel.com>
Reviewed-by: Yang Shi <shy828301(a)gmail.com>
Cc: Alistair Popple <apopple(a)nvidia.com>
Cc: Jan Kara <jack(a)suse.cz>
Cc: Jue Wang <juew(a)google.com>
Cc: "Matthew Wilcox (Oracle)" <willy(a)infradead.org>
Cc: Miaohe Lin <linmiaohe(a)huawei.com>
Cc: Minchan Kim <minchan(a)kernel.org>
Cc: Naoya Horiguchi <naoya.horiguchi(a)nec.com>
Cc: Oscar Salvador <osalvador(a)suse.de>
Cc: Peter Xu <peterx(a)redhat.com>
Cc: Ralph Campbell <rcampbell(a)nvidia.com>
Cc: Shakeel Butt <shakeelb(a)google.com>
Cc: Wang Yugui <wangyugui(a)e16-tech.com>
Cc: Zi Yan <ziy(a)nvidia.com>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
include/linux/huge_mm.h | 8 +++++++-
mm/huge_memory.c | 5 ++++-
2 files changed, 11 insertions(+), 2 deletions(-)
--- a/include/linux/huge_mm.h~mm-thp-make-is_huge_zero_pmd-safe-and-quicker
+++ a/include/linux/huge_mm.h
@@ -286,6 +286,7 @@ struct page *follow_devmap_pud(struct vm
vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd);
extern struct page *huge_zero_page;
+extern unsigned long huge_zero_pfn;
static inline bool is_huge_zero_page(struct page *page)
{
@@ -294,7 +295,7 @@ static inline bool is_huge_zero_page(str
static inline bool is_huge_zero_pmd(pmd_t pmd)
{
- return is_huge_zero_page(pmd_page(pmd));
+ return READ_ONCE(huge_zero_pfn) == pmd_pfn(pmd) && pmd_present(pmd);
}
static inline bool is_huge_zero_pud(pud_t pud)
@@ -439,6 +440,11 @@ static inline bool is_huge_zero_page(str
{
return false;
}
+
+static inline bool is_huge_zero_pmd(pmd_t pmd)
+{
+ return false;
+}
static inline bool is_huge_zero_pud(pud_t pud)
{
--- a/mm/huge_memory.c~mm-thp-make-is_huge_zero_pmd-safe-and-quicker
+++ a/mm/huge_memory.c
@@ -62,6 +62,7 @@ static struct shrinker deferred_split_sh
static atomic_t huge_zero_refcount;
struct page *huge_zero_page __read_mostly;
+unsigned long huge_zero_pfn __read_mostly = ~0UL;
bool transparent_hugepage_enabled(struct vm_area_struct *vma)
{
@@ -98,6 +99,7 @@ retry:
__free_pages(zero_page, compound_order(zero_page));
goto retry;
}
+ WRITE_ONCE(huge_zero_pfn, page_to_pfn(zero_page));
/* We take additional reference here. It will be put back by shrinker */
atomic_set(&huge_zero_refcount, 2);
@@ -147,6 +149,7 @@ static unsigned long shrink_huge_zero_pa
if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) {
struct page *zero_page = xchg(&huge_zero_page, NULL);
BUG_ON(zero_page == NULL);
+ WRITE_ONCE(huge_zero_pfn, ~0UL);
__free_pages(zero_page, compound_order(zero_page));
return HPAGE_PMD_NR;
}
@@ -2071,7 +2074,7 @@ static void __split_huge_pmd_locked(stru
return;
}
- if (pmd_trans_huge(*pmd) && is_huge_zero_pmd(*pmd)) {
+ if (is_huge_zero_pmd(*pmd)) {
/*
* FIXME: Do we want to invalidate secondary mmu by calling
* mmu_notifier_invalidate_range() see comments below inside
_