[PATCH v8 07/18] fs, dax: use page->mapping to warn if truncate collides with a busy page

[Dan Williams]

Catch cases where extent unmap operations encounter pages that are
pinned / busy. Typically this is pinned pages that are under active dma.
This warning is a canary for potential data corruption as truncated
blocks could be allocated to a new file while the device is still
performing i/o.

Here is an example of a collision that this implementation catches:

 WARNING: CPU: 2 PID: 1286 at fs/dax.c:343 dax_disassociate_entry+0x55/0x80
 [..]
 Call Trace:
  __dax_invalidate_mapping_entry+0x6c/0xf0
  dax_delete_mapping_entry+0xf/0x20
  truncate_exceptional_pvec_entries.part.12+0x1af/0x200
  truncate_inode_pages_range+0x268/0x970
  ? tlb_gather_mmu+0x10/0x20
  ? up_write+0x1c/0x40
  ? unmap_mapping_range+0x73/0x140
  xfs_free_file_space+0x1b6/0x5b0 [xfs]
  ? xfs_file_fallocate+0x7f/0x320 [xfs]
  ? down_write_nested+0x40/0x70
  ? xfs_ilock+0x21d/0x2f0 [xfs]
  xfs_file_fallocate+0x162/0x320 [xfs]
  ? rcu_read_lock_sched_held+0x3f/0x70
  ? rcu_sync_lockdep_assert+0x2a/0x50
  ? __sb_start_write+0xd0/0x1b0
  ? vfs_fallocate+0x20c/0x270
  vfs_fallocate+0x154/0x270
  SyS_fallocate+0x43/0x80
  entry_SYSCALL_64_fastpath+0x1f/0x96

Cc: Jeff Moyer 
Cc: Matthew Wilcox 
Cc: Ross Zwisler 
Reviewed-by: Jan Kara 
Reviewed-by: Christoph Hellwig 
Signed-off-by: Dan Williams 
---
 fs/dax.c |   63 ++
 1 file changed, 63 insertions(+)

diff --git a/fs/dax.c b/fs/dax.c
index b646a46e4d12..a77394fe586e 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -298,6 +298,63 @@ static void put_unlocked_mapping_entry(struct 
address_space *mapping,
dax_wake_mapping_entry_waiter(mapping, index, entry, false);
 }
 
+static unsigned long dax_entry_size(void *entry)
+{
+   if (dax_is_zero_entry(entry))
+   return 0;
+   else if (dax_is_empty_entry(entry))
+   return 0;
+   else if (dax_is_pmd_entry(entry))
+   return PMD_SIZE;
+   else
+   return PAGE_SIZE;
+}
+
+static unsigned long dax_radix_end_pfn(void *entry)
+{
+   return dax_radix_pfn(entry) + dax_entry_size(entry) / PAGE_SIZE;
+}
+
+/*
+ * Iterate through all mapped pfns represented by an entry, i.e. skip
+ * 'empty' and 'zero' entries.
+ */
+#define for_each_mapped_pfn(entry, pfn) \
+   for (pfn = dax_radix_pfn(entry); \
+   pfn < dax_radix_end_pfn(entry); pfn++)
+
+static void dax_associate_entry(void *entry, struct address_space *mapping)
+{
+   unsigned long pfn;
+
+   if (IS_ENABLED(CONFIG_FS_DAX_LIMITED))
+   return;
+
+   for_each_mapped_pfn(entry, pfn) {
+   struct page *page = pfn_to_page(pfn);
+
+   WARN_ON_ONCE(page->mapping);
+   page->mapping = mapping;
+   }
+}
+
+static void dax_disassociate_entry(void *entry, struct address_space *mapping,
+   bool trunc)
+{
+   unsigned long pfn;
+
+   if (IS_ENABLED(CONFIG_FS_DAX_LIMITED))
+   return;
+
+   for_each_mapped_pfn(entry, pfn) {
+   struct page *page = pfn_to_page(pfn);
+
+   WARN_ON_ONCE(trunc && page_ref_count(page) > 1);
+   WARN_ON_ONCE(page->mapping && page->mapping != mapping);
+   page->mapping = NULL;
+   }
+}
+
 /*
  * Find radix tree entry at given index. If it points to an exceptional entry,
  * return it with the radix tree entry locked. If the radix tree doesn't
@@ -404,6 +461,7 @@ static void *grab_mapping_entry(struct address_space 
*mapping, pgoff_t index,
}
 
if (pmd_downgrade) {
+   dax_disassociate_entry(entry, mapping, false);
radix_tree_delete(>page_tree, index);
mapping->nrexceptional--;
dax_wake_mapping_entry_waiter(mapping, index, entry,
@@ -453,6 +511,7 @@ static int __dax_invalidate_mapping_entry(struct 
address_space *mapping,
(radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_DIRTY) ||
 radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_TOWRITE)))
goto out;
+   dax_disassociate_entry(entry, mapping, trunc);
radix_tree_delete(page_tree, index);
mapping->nrexceptional--;
ret = 1;
@@ -547,6 +606,10 @@ static void *dax_insert_mapping_entry(struct address_space 
*mapping,
 
spin_lock_irq(>tree_lock);
new_entry = dax_radix_locked_entry(pfn, flags);
+   if (dax_entry_size(entry) != dax_entry_size(new_entry)) {
+   dax_disassociate_entry(entry, mapping, false);
+   dax_associate_entry(new_entry, mapping);
+   }
 
if (dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) {
/*

[PATCH v8 07/18] fs, dax: use page->mapping to warn if truncate collides with a busy page

[Dan Williams]

Catch cases where extent unmap operations encounter pages that are
pinned / busy. Typically this is pinned pages that are under active dma.
This warning is a canary for potential data corruption as truncated
blocks could be allocated to a new file while the device is still
performing i/o.

Here is an example of a collision that this implementation catches:

 WARNING: CPU: 2 PID: 1286 at fs/dax.c:343 dax_disassociate_entry+0x55/0x80
 [..]
 Call Trace:
  __dax_invalidate_mapping_entry+0x6c/0xf0
  dax_delete_mapping_entry+0xf/0x20
  truncate_exceptional_pvec_entries.part.12+0x1af/0x200
  truncate_inode_pages_range+0x268/0x970
  ? tlb_gather_mmu+0x10/0x20
  ? up_write+0x1c/0x40
  ? unmap_mapping_range+0x73/0x140
  xfs_free_file_space+0x1b6/0x5b0 [xfs]
  ? xfs_file_fallocate+0x7f/0x320 [xfs]
  ? down_write_nested+0x40/0x70
  ? xfs_ilock+0x21d/0x2f0 [xfs]
  xfs_file_fallocate+0x162/0x320 [xfs]
  ? rcu_read_lock_sched_held+0x3f/0x70
  ? rcu_sync_lockdep_assert+0x2a/0x50
  ? __sb_start_write+0xd0/0x1b0
  ? vfs_fallocate+0x20c/0x270
  vfs_fallocate+0x154/0x270
  SyS_fallocate+0x43/0x80
  entry_SYSCALL_64_fastpath+0x1f/0x96

Cc: Jeff Moyer 
Cc: Matthew Wilcox 
Cc: Ross Zwisler 
Reviewed-by: Jan Kara 
Reviewed-by: Christoph Hellwig 
Signed-off-by: Dan Williams 
---
 fs/dax.c |   63 ++
 1 file changed, 63 insertions(+)

diff --git a/fs/dax.c b/fs/dax.c
index b646a46e4d12..a77394fe586e 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -298,6 +298,63 @@ static void put_unlocked_mapping_entry(struct 
address_space *mapping,
dax_wake_mapping_entry_waiter(mapping, index, entry, false);
 }
 
+static unsigned long dax_entry_size(void *entry)
+{
+   if (dax_is_zero_entry(entry))
+   return 0;
+   else if (dax_is_empty_entry(entry))
+   return 0;
+   else if (dax_is_pmd_entry(entry))
+   return PMD_SIZE;
+   else
+   return PAGE_SIZE;
+}
+
+static unsigned long dax_radix_end_pfn(void *entry)
+{
+   return dax_radix_pfn(entry) + dax_entry_size(entry) / PAGE_SIZE;
+}
+
+/*
+ * Iterate through all mapped pfns represented by an entry, i.e. skip
+ * 'empty' and 'zero' entries.
+ */
+#define for_each_mapped_pfn(entry, pfn) \
+   for (pfn = dax_radix_pfn(entry); \
+   pfn < dax_radix_end_pfn(entry); pfn++)
+
+static void dax_associate_entry(void *entry, struct address_space *mapping)
+{
+   unsigned long pfn;
+
+   if (IS_ENABLED(CONFIG_FS_DAX_LIMITED))
+   return;
+
+   for_each_mapped_pfn(entry, pfn) {
+   struct page *page = pfn_to_page(pfn);
+
+   WARN_ON_ONCE(page->mapping);
+   page->mapping = mapping;
+   }
+}
+
+static void dax_disassociate_entry(void *entry, struct address_space *mapping,
+   bool trunc)
+{
+   unsigned long pfn;
+
+   if (IS_ENABLED(CONFIG_FS_DAX_LIMITED))
+   return;
+
+   for_each_mapped_pfn(entry, pfn) {
+   struct page *page = pfn_to_page(pfn);
+
+   WARN_ON_ONCE(trunc && page_ref_count(page) > 1);
+   WARN_ON_ONCE(page->mapping && page->mapping != mapping);
+   page->mapping = NULL;
+   }
+}
+
 /*
  * Find radix tree entry at given index. If it points to an exceptional entry,
  * return it with the radix tree entry locked. If the radix tree doesn't
@@ -404,6 +461,7 @@ static void *grab_mapping_entry(struct address_space 
*mapping, pgoff_t index,
}
 
if (pmd_downgrade) {
+   dax_disassociate_entry(entry, mapping, false);
radix_tree_delete(>page_tree, index);
mapping->nrexceptional--;
dax_wake_mapping_entry_waiter(mapping, index, entry,
@@ -453,6 +511,7 @@ static int __dax_invalidate_mapping_entry(struct 
address_space *mapping,
(radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_DIRTY) ||
 radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_TOWRITE)))
goto out;
+   dax_disassociate_entry(entry, mapping, trunc);
radix_tree_delete(page_tree, index);
mapping->nrexceptional--;
ret = 1;
@@ -547,6 +606,10 @@ static void *dax_insert_mapping_entry(struct address_space 
*mapping,
 
spin_lock_irq(>tree_lock);
new_entry = dax_radix_locked_entry(pfn, flags);
+   if (dax_entry_size(entry) != dax_entry_size(new_entry)) {
+   dax_disassociate_entry(entry, mapping, false);
+   dax_associate_entry(new_entry, mapping);
+   }
 
if (dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) {
/*