The patch below does not apply to the 4.4-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From 94db151dc89262bfa82922c44e8320cea2334667 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams(a)intel.com>
Date: Sun, 4 Feb 2018 10:34:02 -0800
Subject: [PATCH] vfio: disable filesystem-dax page pinning
Filesystem-DAX is incompatible with 'longterm' page pinning. Without
page cache indirection a DAX mapping maps filesystem blocks directly.
This means that the filesystem must not modify a file's block map while
any page in a mapping is pinned. In order to prevent the situation of
userspace holding of filesystem operations indefinitely, disallow
'longterm' Filesystem-DAX mappings.
RDMA has the same conflict and the plan there is to add a 'with lease'
mechanism to allow the kernel to notify userspace that the mapping is
being torn down for block-map maintenance. Perhaps something similar can
be put in place for vfio.
Note that xfs and ext4 still report:
"DAX enabled. Warning: EXPERIMENTAL, use at your own risk"
...at mount time, and resolving the dax-dma-vs-truncate problem is one
of the last hurdles to remove that designation.
Acked-by: Alex Williamson <alex.williamson(a)redhat.com>
Cc: Michal Hocko <mhocko(a)suse.com>
Cc: kvm(a)vger.kernel.org
Cc: <stable(a)vger.kernel.org>
Reported-by: Haozhong Zhang <haozhong.zhang(a)intel.com>
Tested-by: Haozhong Zhang <haozhong.zhang(a)intel.com>
Fixes: d475c6346a38 ("dax,ext2: replace XIP read and write with DAX I/O")
Reviewed-by: Christoph Hellwig <hch(a)lst.de>
Signed-off-by: Dan Williams <dan.j.williams(a)intel.com>
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index e30e29ae4819..45657e2b1ff7 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -338,11 +338,12 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr,
{
struct page *page[1];
struct vm_area_struct *vma;
+ struct vm_area_struct *vmas[1];
int ret;
if (mm == current->mm) {
- ret = get_user_pages_fast(vaddr, 1, !!(prot & IOMMU_WRITE),
- page);
+ ret = get_user_pages_longterm(vaddr, 1, !!(prot & IOMMU_WRITE),
+ page, vmas);
} else {
unsigned int flags = 0;
@@ -351,7 +352,18 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr,
down_read(&mm->mmap_sem);
ret = get_user_pages_remote(NULL, mm, vaddr, 1, flags, page,
- NULL, NULL);
+ vmas, NULL);
+ /*
+ * The lifetime of a vaddr_get_pfn() page pin is
+ * userspace-controlled. In the fs-dax case this could
+ * lead to indefinite stalls in filesystem operations.
+ * Disallow attempts to pin fs-dax pages via this
+ * interface.
+ */
+ if (ret > 0 && vma_is_fsdax(vmas[0])) {
+ ret = -EOPNOTSUPP;
+ put_page(page[0]);
+ }
up_read(&mm->mmap_sem);
}
The patch below does not apply to the 4.9-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From 94db151dc89262bfa82922c44e8320cea2334667 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams(a)intel.com>
Date: Sun, 4 Feb 2018 10:34:02 -0800
Subject: [PATCH] vfio: disable filesystem-dax page pinning
Filesystem-DAX is incompatible with 'longterm' page pinning. Without
page cache indirection a DAX mapping maps filesystem blocks directly.
This means that the filesystem must not modify a file's block map while
any page in a mapping is pinned. In order to prevent the situation of
userspace holding of filesystem operations indefinitely, disallow
'longterm' Filesystem-DAX mappings.
RDMA has the same conflict and the plan there is to add a 'with lease'
mechanism to allow the kernel to notify userspace that the mapping is
being torn down for block-map maintenance. Perhaps something similar can
be put in place for vfio.
Note that xfs and ext4 still report:
"DAX enabled. Warning: EXPERIMENTAL, use at your own risk"
...at mount time, and resolving the dax-dma-vs-truncate problem is one
of the last hurdles to remove that designation.
Acked-by: Alex Williamson <alex.williamson(a)redhat.com>
Cc: Michal Hocko <mhocko(a)suse.com>
Cc: kvm(a)vger.kernel.org
Cc: <stable(a)vger.kernel.org>
Reported-by: Haozhong Zhang <haozhong.zhang(a)intel.com>
Tested-by: Haozhong Zhang <haozhong.zhang(a)intel.com>
Fixes: d475c6346a38 ("dax,ext2: replace XIP read and write with DAX I/O")
Reviewed-by: Christoph Hellwig <hch(a)lst.de>
Signed-off-by: Dan Williams <dan.j.williams(a)intel.com>
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index e30e29ae4819..45657e2b1ff7 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -338,11 +338,12 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr,
{
struct page *page[1];
struct vm_area_struct *vma;
+ struct vm_area_struct *vmas[1];
int ret;
if (mm == current->mm) {
- ret = get_user_pages_fast(vaddr, 1, !!(prot & IOMMU_WRITE),
- page);
+ ret = get_user_pages_longterm(vaddr, 1, !!(prot & IOMMU_WRITE),
+ page, vmas);
} else {
unsigned int flags = 0;
@@ -351,7 +352,18 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr,
down_read(&mm->mmap_sem);
ret = get_user_pages_remote(NULL, mm, vaddr, 1, flags, page,
- NULL, NULL);
+ vmas, NULL);
+ /*
+ * The lifetime of a vaddr_get_pfn() page pin is
+ * userspace-controlled. In the fs-dax case this could
+ * lead to indefinite stalls in filesystem operations.
+ * Disallow attempts to pin fs-dax pages via this
+ * interface.
+ */
+ if (ret > 0 && vma_is_fsdax(vmas[0])) {
+ ret = -EOPNOTSUPP;
+ put_page(page[0]);
+ }
up_read(&mm->mmap_sem);
}
The patch below does not apply to the 3.18-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From 3c181c12c431fe33b669410d663beb9cceefcd1b Mon Sep 17 00:00:00 2001
From: Anand Jain <anand.jain(a)oracle.com>
Date: Thu, 22 Feb 2018 21:58:42 +0800
Subject: [PATCH] btrfs: use proper endianness accessors for super_copy
The fs_info::super_copy is a byte copy of the on-disk structure and all
members must use the accessor macros/functions to obtain the right
value. This was missing in update_super_roots and in sysfs readers.
Moving between opposite endianness hosts will report bogus numbers in
sysfs, and mount may fail as the root will not be restored correctly. If
the filesystem is always used on a same endian host, this will not be a
problem.
Fix this by using the btrfs_set_super...() functions to set
fs_info::super_copy values, and for the sysfs, use the cached
fs_info::nodesize/sectorsize values.
CC: stable(a)vger.kernel.org
Fixes: df93589a17378 ("btrfs: export more from FS_INFO to sysfs")
Signed-off-by: Anand Jain <anand.jain(a)oracle.com>
Reviewed-by: Liu Bo <bo.li.liu(a)oracle.com>
Reviewed-by: David Sterba <dsterba(a)suse.com>
[ update changelog ]
Signed-off-by: David Sterba <dsterba(a)suse.com>
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index a8bafed931f4..d11c70bff5a9 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -423,7 +423,7 @@ static ssize_t btrfs_nodesize_show(struct kobject *kobj,
{
struct btrfs_fs_info *fs_info = to_fs_info(kobj);
- return snprintf(buf, PAGE_SIZE, "%u\n", fs_info->super_copy->nodesize);
+ return snprintf(buf, PAGE_SIZE, "%u\n", fs_info->nodesize);
}
BTRFS_ATTR(, nodesize, btrfs_nodesize_show);
@@ -433,8 +433,7 @@ static ssize_t btrfs_sectorsize_show(struct kobject *kobj,
{
struct btrfs_fs_info *fs_info = to_fs_info(kobj);
- return snprintf(buf, PAGE_SIZE, "%u\n",
- fs_info->super_copy->sectorsize);
+ return snprintf(buf, PAGE_SIZE, "%u\n", fs_info->sectorsize);
}
BTRFS_ATTR(, sectorsize, btrfs_sectorsize_show);
@@ -444,8 +443,7 @@ static ssize_t btrfs_clone_alignment_show(struct kobject *kobj,
{
struct btrfs_fs_info *fs_info = to_fs_info(kobj);
- return snprintf(buf, PAGE_SIZE, "%u\n",
- fs_info->super_copy->sectorsize);
+ return snprintf(buf, PAGE_SIZE, "%u\n", fs_info->sectorsize);
}
BTRFS_ATTR(, clone_alignment, btrfs_clone_alignment_show);
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 04f07144b45c..9220f004001c 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -1722,19 +1722,23 @@ static void update_super_roots(struct btrfs_fs_info *fs_info)
super = fs_info->super_copy;
+ /* update latest btrfs_super_block::chunk_root refs */
root_item = &fs_info->chunk_root->root_item;
- super->chunk_root = root_item->bytenr;
- super->chunk_root_generation = root_item->generation;
- super->chunk_root_level = root_item->level;
+ btrfs_set_super_chunk_root(super, root_item->bytenr);
+ btrfs_set_super_chunk_root_generation(super, root_item->generation);
+ btrfs_set_super_chunk_root_level(super, root_item->level);
+ /* update latest btrfs_super_block::root refs */
root_item = &fs_info->tree_root->root_item;
- super->root = root_item->bytenr;
- super->generation = root_item->generation;
- super->root_level = root_item->level;
+ btrfs_set_super_root(super, root_item->bytenr);
+ btrfs_set_super_generation(super, root_item->generation);
+ btrfs_set_super_root_level(super, root_item->level);
+
if (btrfs_test_opt(fs_info, SPACE_CACHE))
- super->cache_generation = root_item->generation;
+ btrfs_set_super_cache_generation(super, root_item->generation);
if (test_bit(BTRFS_FS_UPDATE_UUID_TREE_GEN, &fs_info->flags))
- super->uuid_tree_generation = root_item->generation;
+ btrfs_set_super_uuid_tree_generation(super,
+ root_item->generation);
}
int btrfs_transaction_in_commit(struct btrfs_fs_info *info)
The patch below does not apply to the 4.4-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From 3c181c12c431fe33b669410d663beb9cceefcd1b Mon Sep 17 00:00:00 2001
From: Anand Jain <anand.jain(a)oracle.com>
Date: Thu, 22 Feb 2018 21:58:42 +0800
Subject: [PATCH] btrfs: use proper endianness accessors for super_copy
The fs_info::super_copy is a byte copy of the on-disk structure and all
members must use the accessor macros/functions to obtain the right
value. This was missing in update_super_roots and in sysfs readers.
Moving between opposite endianness hosts will report bogus numbers in
sysfs, and mount may fail as the root will not be restored correctly. If
the filesystem is always used on a same endian host, this will not be a
problem.
Fix this by using the btrfs_set_super...() functions to set
fs_info::super_copy values, and for the sysfs, use the cached
fs_info::nodesize/sectorsize values.
CC: stable(a)vger.kernel.org
Fixes: df93589a17378 ("btrfs: export more from FS_INFO to sysfs")
Signed-off-by: Anand Jain <anand.jain(a)oracle.com>
Reviewed-by: Liu Bo <bo.li.liu(a)oracle.com>
Reviewed-by: David Sterba <dsterba(a)suse.com>
[ update changelog ]
Signed-off-by: David Sterba <dsterba(a)suse.com>
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index a8bafed931f4..d11c70bff5a9 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -423,7 +423,7 @@ static ssize_t btrfs_nodesize_show(struct kobject *kobj,
{
struct btrfs_fs_info *fs_info = to_fs_info(kobj);
- return snprintf(buf, PAGE_SIZE, "%u\n", fs_info->super_copy->nodesize);
+ return snprintf(buf, PAGE_SIZE, "%u\n", fs_info->nodesize);
}
BTRFS_ATTR(, nodesize, btrfs_nodesize_show);
@@ -433,8 +433,7 @@ static ssize_t btrfs_sectorsize_show(struct kobject *kobj,
{
struct btrfs_fs_info *fs_info = to_fs_info(kobj);
- return snprintf(buf, PAGE_SIZE, "%u\n",
- fs_info->super_copy->sectorsize);
+ return snprintf(buf, PAGE_SIZE, "%u\n", fs_info->sectorsize);
}
BTRFS_ATTR(, sectorsize, btrfs_sectorsize_show);
@@ -444,8 +443,7 @@ static ssize_t btrfs_clone_alignment_show(struct kobject *kobj,
{
struct btrfs_fs_info *fs_info = to_fs_info(kobj);
- return snprintf(buf, PAGE_SIZE, "%u\n",
- fs_info->super_copy->sectorsize);
+ return snprintf(buf, PAGE_SIZE, "%u\n", fs_info->sectorsize);
}
BTRFS_ATTR(, clone_alignment, btrfs_clone_alignment_show);
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 04f07144b45c..9220f004001c 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -1722,19 +1722,23 @@ static void update_super_roots(struct btrfs_fs_info *fs_info)
super = fs_info->super_copy;
+ /* update latest btrfs_super_block::chunk_root refs */
root_item = &fs_info->chunk_root->root_item;
- super->chunk_root = root_item->bytenr;
- super->chunk_root_generation = root_item->generation;
- super->chunk_root_level = root_item->level;
+ btrfs_set_super_chunk_root(super, root_item->bytenr);
+ btrfs_set_super_chunk_root_generation(super, root_item->generation);
+ btrfs_set_super_chunk_root_level(super, root_item->level);
+ /* update latest btrfs_super_block::root refs */
root_item = &fs_info->tree_root->root_item;
- super->root = root_item->bytenr;
- super->generation = root_item->generation;
- super->root_level = root_item->level;
+ btrfs_set_super_root(super, root_item->bytenr);
+ btrfs_set_super_generation(super, root_item->generation);
+ btrfs_set_super_root_level(super, root_item->level);
+
if (btrfs_test_opt(fs_info, SPACE_CACHE))
- super->cache_generation = root_item->generation;
+ btrfs_set_super_cache_generation(super, root_item->generation);
if (test_bit(BTRFS_FS_UPDATE_UUID_TREE_GEN, &fs_info->flags))
- super->uuid_tree_generation = root_item->generation;
+ btrfs_set_super_uuid_tree_generation(super,
+ root_item->generation);
}
int btrfs_transaction_in_commit(struct btrfs_fs_info *info)
The patch below does not apply to the 4.9-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From 3c181c12c431fe33b669410d663beb9cceefcd1b Mon Sep 17 00:00:00 2001
From: Anand Jain <anand.jain(a)oracle.com>
Date: Thu, 22 Feb 2018 21:58:42 +0800
Subject: [PATCH] btrfs: use proper endianness accessors for super_copy
The fs_info::super_copy is a byte copy of the on-disk structure and all
members must use the accessor macros/functions to obtain the right
value. This was missing in update_super_roots and in sysfs readers.
Moving between opposite endianness hosts will report bogus numbers in
sysfs, and mount may fail as the root will not be restored correctly. If
the filesystem is always used on a same endian host, this will not be a
problem.
Fix this by using the btrfs_set_super...() functions to set
fs_info::super_copy values, and for the sysfs, use the cached
fs_info::nodesize/sectorsize values.
CC: stable(a)vger.kernel.org
Fixes: df93589a17378 ("btrfs: export more from FS_INFO to sysfs")
Signed-off-by: Anand Jain <anand.jain(a)oracle.com>
Reviewed-by: Liu Bo <bo.li.liu(a)oracle.com>
Reviewed-by: David Sterba <dsterba(a)suse.com>
[ update changelog ]
Signed-off-by: David Sterba <dsterba(a)suse.com>
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index a8bafed931f4..d11c70bff5a9 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -423,7 +423,7 @@ static ssize_t btrfs_nodesize_show(struct kobject *kobj,
{
struct btrfs_fs_info *fs_info = to_fs_info(kobj);
- return snprintf(buf, PAGE_SIZE, "%u\n", fs_info->super_copy->nodesize);
+ return snprintf(buf, PAGE_SIZE, "%u\n", fs_info->nodesize);
}
BTRFS_ATTR(, nodesize, btrfs_nodesize_show);
@@ -433,8 +433,7 @@ static ssize_t btrfs_sectorsize_show(struct kobject *kobj,
{
struct btrfs_fs_info *fs_info = to_fs_info(kobj);
- return snprintf(buf, PAGE_SIZE, "%u\n",
- fs_info->super_copy->sectorsize);
+ return snprintf(buf, PAGE_SIZE, "%u\n", fs_info->sectorsize);
}
BTRFS_ATTR(, sectorsize, btrfs_sectorsize_show);
@@ -444,8 +443,7 @@ static ssize_t btrfs_clone_alignment_show(struct kobject *kobj,
{
struct btrfs_fs_info *fs_info = to_fs_info(kobj);
- return snprintf(buf, PAGE_SIZE, "%u\n",
- fs_info->super_copy->sectorsize);
+ return snprintf(buf, PAGE_SIZE, "%u\n", fs_info->sectorsize);
}
BTRFS_ATTR(, clone_alignment, btrfs_clone_alignment_show);
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 04f07144b45c..9220f004001c 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -1722,19 +1722,23 @@ static void update_super_roots(struct btrfs_fs_info *fs_info)
super = fs_info->super_copy;
+ /* update latest btrfs_super_block::chunk_root refs */
root_item = &fs_info->chunk_root->root_item;
- super->chunk_root = root_item->bytenr;
- super->chunk_root_generation = root_item->generation;
- super->chunk_root_level = root_item->level;
+ btrfs_set_super_chunk_root(super, root_item->bytenr);
+ btrfs_set_super_chunk_root_generation(super, root_item->generation);
+ btrfs_set_super_chunk_root_level(super, root_item->level);
+ /* update latest btrfs_super_block::root refs */
root_item = &fs_info->tree_root->root_item;
- super->root = root_item->bytenr;
- super->generation = root_item->generation;
- super->root_level = root_item->level;
+ btrfs_set_super_root(super, root_item->bytenr);
+ btrfs_set_super_generation(super, root_item->generation);
+ btrfs_set_super_root_level(super, root_item->level);
+
if (btrfs_test_opt(fs_info, SPACE_CACHE))
- super->cache_generation = root_item->generation;
+ btrfs_set_super_cache_generation(super, root_item->generation);
if (test_bit(BTRFS_FS_UPDATE_UUID_TREE_GEN, &fs_info->flags))
- super->uuid_tree_generation = root_item->generation;
+ btrfs_set_super_uuid_tree_generation(super,
+ root_item->generation);
}
int btrfs_transaction_in_commit(struct btrfs_fs_info *info)