- Linux-stable-mirror - lists.linaro.org

FAILED: patch "[PATCH] btrfs: return error pointer from alloc_test_extent_buffer" failed to apply to 4.14-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.14-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 b6293c821ea8fa2a631a2112cd86cd435effeb8b Mon Sep 17 00:00:00 2001 From: Dan Carpenter <dan.carpenter(a)oracle.com> Date: Tue, 3 Dec 2019 14:24:58 +0300 Subject: [PATCH] btrfs: return error pointer from alloc_test_extent_buffer Callers of alloc_test_extent_buffer have not correctly interpreted the return value as error pointer, as alloc_test_extent_buffer should behave as alloc_extent_buffer. The self-tests were unaffected but btrfs_find_create_tree_block could call both functions and that would cause problems up in the call chain. Fixes: faa2dbf004e8 ("Btrfs: add sanity tests for new qgroup accounting code") CC: stable(a)vger.kernel.org # 4.4+ Signed-off-by: Dan Carpenter <dan.carpenter(a)oracle.com> Reviewed-by: David Sterba <dsterba(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index eb8bd0258360..2f4802f405a2 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -5074,12 +5074,14 @@ struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info, return eb; eb = alloc_dummy_extent_buffer(fs_info, start); if (!eb) - return NULL; + return ERR_PTR(-ENOMEM); eb->fs_info = fs_info; again: ret = radix_tree_preload(GFP_NOFS); - if (ret) + if (ret) { + exists = ERR_PTR(ret); goto free_eb; + } spin_lock(&fs_info->buffer_lock); ret = radix_tree_insert(&fs_info->buffer_radix, start >> PAGE_SHIFT, eb); diff --git a/fs/btrfs/tests/free-space-tree-tests.c b/fs/btrfs/tests/free-space-tree-tests.c index 1a846bf6e197..914eea5ba6a7 100644 --- a/fs/btrfs/tests/free-space-tree-tests.c +++ b/fs/btrfs/tests/free-space-tree-tests.c @@ -452,9 +452,9 @@ static int run_test(test_func_t test_func, int bitmaps, u32 sectorsize, root->fs_info->tree_root = root; root->node = alloc_test_extent_buffer(root->fs_info, nodesize); - if (!root->node) { + if (IS_ERR(root->node)) { test_std_err(TEST_ALLOC_EXTENT_BUFFER); - ret = -ENOMEM; + ret = PTR_ERR(root->node); goto out; } btrfs_set_header_level(root->node, 0); diff --git a/fs/btrfs/tests/qgroup-tests.c b/fs/btrfs/tests/qgroup-tests.c index 09aaca1efd62..ac035a6fa003 100644 --- a/fs/btrfs/tests/qgroup-tests.c +++ b/fs/btrfs/tests/qgroup-tests.c @@ -484,9 +484,9 @@ int btrfs_test_qgroups(u32 sectorsize, u32 nodesize) * *cough*backref walking code*cough* */ root->node = alloc_test_extent_buffer(root->fs_info, nodesize); - if (!root->node) { + if (IS_ERR(root->node)) { test_err("couldn't allocate dummy buffer"); - ret = -ENOMEM; + ret = PTR_ERR(root->node); goto out; } btrfs_set_header_level(root->node, 0);

5 years, 10 months

1
0
0 0

FAILED: patch "[PATCH] btrfs: return error pointer from alloc_test_extent_buffer" failed to apply to 4.9-stable tree

by gregkh＠linuxfoundation.org

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 b6293c821ea8fa2a631a2112cd86cd435effeb8b Mon Sep 17 00:00:00 2001 From: Dan Carpenter <dan.carpenter(a)oracle.com> Date: Tue, 3 Dec 2019 14:24:58 +0300 Subject: [PATCH] btrfs: return error pointer from alloc_test_extent_buffer Callers of alloc_test_extent_buffer have not correctly interpreted the return value as error pointer, as alloc_test_extent_buffer should behave as alloc_extent_buffer. The self-tests were unaffected but btrfs_find_create_tree_block could call both functions and that would cause problems up in the call chain. Fixes: faa2dbf004e8 ("Btrfs: add sanity tests for new qgroup accounting code") CC: stable(a)vger.kernel.org # 4.4+ Signed-off-by: Dan Carpenter <dan.carpenter(a)oracle.com> Reviewed-by: David Sterba <dsterba(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index eb8bd0258360..2f4802f405a2 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -5074,12 +5074,14 @@ struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info, return eb; eb = alloc_dummy_extent_buffer(fs_info, start); if (!eb) - return NULL; + return ERR_PTR(-ENOMEM); eb->fs_info = fs_info; again: ret = radix_tree_preload(GFP_NOFS); - if (ret) + if (ret) { + exists = ERR_PTR(ret); goto free_eb; + } spin_lock(&fs_info->buffer_lock); ret = radix_tree_insert(&fs_info->buffer_radix, start >> PAGE_SHIFT, eb); diff --git a/fs/btrfs/tests/free-space-tree-tests.c b/fs/btrfs/tests/free-space-tree-tests.c index 1a846bf6e197..914eea5ba6a7 100644 --- a/fs/btrfs/tests/free-space-tree-tests.c +++ b/fs/btrfs/tests/free-space-tree-tests.c @@ -452,9 +452,9 @@ static int run_test(test_func_t test_func, int bitmaps, u32 sectorsize, root->fs_info->tree_root = root; root->node = alloc_test_extent_buffer(root->fs_info, nodesize); - if (!root->node) { + if (IS_ERR(root->node)) { test_std_err(TEST_ALLOC_EXTENT_BUFFER); - ret = -ENOMEM; + ret = PTR_ERR(root->node); goto out; } btrfs_set_header_level(root->node, 0); diff --git a/fs/btrfs/tests/qgroup-tests.c b/fs/btrfs/tests/qgroup-tests.c index 09aaca1efd62..ac035a6fa003 100644 --- a/fs/btrfs/tests/qgroup-tests.c +++ b/fs/btrfs/tests/qgroup-tests.c @@ -484,9 +484,9 @@ int btrfs_test_qgroups(u32 sectorsize, u32 nodesize) * *cough*backref walking code*cough* */ root->node = alloc_test_extent_buffer(root->fs_info, nodesize); - if (!root->node) { + if (IS_ERR(root->node)) { test_err("couldn't allocate dummy buffer"); - ret = -ENOMEM; + ret = PTR_ERR(root->node); goto out; } btrfs_set_header_level(root->node, 0);

5 years, 10 months

1
0
0 0

FAILED: patch "[PATCH] btrfs: return error pointer from alloc_test_extent_buffer" failed to apply to 4.4-stable tree

by gregkh＠linuxfoundation.org

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 b6293c821ea8fa2a631a2112cd86cd435effeb8b Mon Sep 17 00:00:00 2001 From: Dan Carpenter <dan.carpenter(a)oracle.com> Date: Tue, 3 Dec 2019 14:24:58 +0300 Subject: [PATCH] btrfs: return error pointer from alloc_test_extent_buffer Callers of alloc_test_extent_buffer have not correctly interpreted the return value as error pointer, as alloc_test_extent_buffer should behave as alloc_extent_buffer. The self-tests were unaffected but btrfs_find_create_tree_block could call both functions and that would cause problems up in the call chain. Fixes: faa2dbf004e8 ("Btrfs: add sanity tests for new qgroup accounting code") CC: stable(a)vger.kernel.org # 4.4+ Signed-off-by: Dan Carpenter <dan.carpenter(a)oracle.com> Reviewed-by: David Sterba <dsterba(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index eb8bd0258360..2f4802f405a2 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -5074,12 +5074,14 @@ struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info, return eb; eb = alloc_dummy_extent_buffer(fs_info, start); if (!eb) - return NULL; + return ERR_PTR(-ENOMEM); eb->fs_info = fs_info; again: ret = radix_tree_preload(GFP_NOFS); - if (ret) + if (ret) { + exists = ERR_PTR(ret); goto free_eb; + } spin_lock(&fs_info->buffer_lock); ret = radix_tree_insert(&fs_info->buffer_radix, start >> PAGE_SHIFT, eb); diff --git a/fs/btrfs/tests/free-space-tree-tests.c b/fs/btrfs/tests/free-space-tree-tests.c index 1a846bf6e197..914eea5ba6a7 100644 --- a/fs/btrfs/tests/free-space-tree-tests.c +++ b/fs/btrfs/tests/free-space-tree-tests.c @@ -452,9 +452,9 @@ static int run_test(test_func_t test_func, int bitmaps, u32 sectorsize, root->fs_info->tree_root = root; root->node = alloc_test_extent_buffer(root->fs_info, nodesize); - if (!root->node) { + if (IS_ERR(root->node)) { test_std_err(TEST_ALLOC_EXTENT_BUFFER); - ret = -ENOMEM; + ret = PTR_ERR(root->node); goto out; } btrfs_set_header_level(root->node, 0); diff --git a/fs/btrfs/tests/qgroup-tests.c b/fs/btrfs/tests/qgroup-tests.c index 09aaca1efd62..ac035a6fa003 100644 --- a/fs/btrfs/tests/qgroup-tests.c +++ b/fs/btrfs/tests/qgroup-tests.c @@ -484,9 +484,9 @@ int btrfs_test_qgroups(u32 sectorsize, u32 nodesize) * *cough*backref walking code*cough* */ root->node = alloc_test_extent_buffer(root->fs_info, nodesize); - if (!root->node) { + if (IS_ERR(root->node)) { test_err("couldn't allocate dummy buffer"); - ret = -ENOMEM; + ret = PTR_ERR(root->node); goto out; } btrfs_set_header_level(root->node, 0);

5 years, 10 months

1
0
0 0

FAILED: patch "[PATCH] Btrfs: make tree checker detect checksum items with" failed to apply to 4.4-stable tree

by gregkh＠linuxfoundation.org

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 ad1d8c439978ede77cbf73cbdd11bafe810421a5 Mon Sep 17 00:00:00 2001 From: Filipe Manana <fdmanana(a)suse.com> Date: Mon, 2 Dec 2019 11:01:03 +0000 Subject: [PATCH] Btrfs: make tree checker detect checksum items with overlapping ranges Having checksum items, either on the checksums tree or in a log tree, that represent ranges that overlap each other is a sign of a corruption. Such case confuses the checksum lookup code and can result in not being able to find checksums or find stale checksums. So add a check for such case. This is motivated by a recent fix for a case where a log tree had checksum items covering ranges that overlap each other due to extent cloning, and resulted in missing checksums after replaying the log tree. It also helps detect past issues such as stale and outdated checksums due to overlapping, commit 27b9a8122ff71a ("Btrfs: fix csum tree corruption, duplicate and outdated checksums"). CC: stable(a)vger.kernel.org # 4.4+ Signed-off-by: Filipe Manana <fdmanana(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 092b8ece36d7..97f3520b8d98 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -332,7 +332,7 @@ static int check_extent_data_item(struct extent_buffer *leaf, } static int check_csum_item(struct extent_buffer *leaf, struct btrfs_key *key, - int slot) + int slot, struct btrfs_key *prev_key) { struct btrfs_fs_info *fs_info = leaf->fs_info; u32 sectorsize = fs_info->sectorsize; @@ -356,6 +356,20 @@ static int check_csum_item(struct extent_buffer *leaf, struct btrfs_key *key, btrfs_item_size_nr(leaf, slot), csumsize); return -EUCLEAN; } + if (slot > 0 && prev_key->type == BTRFS_EXTENT_CSUM_KEY) { + u64 prev_csum_end; + u32 prev_item_size; + + prev_item_size = btrfs_item_size_nr(leaf, slot - 1); + prev_csum_end = (prev_item_size / csumsize) * sectorsize; + prev_csum_end += prev_key->offset; + if (prev_csum_end > key->offset) { + generic_err(leaf, slot - 1, +"csum end range (%llu) goes beyond the start range (%llu) of the next csum item", + prev_csum_end, key->offset); + return -EUCLEAN; + } + } return 0; } @@ -1355,7 +1369,7 @@ static int check_leaf_item(struct extent_buffer *leaf, ret = check_extent_data_item(leaf, key, slot, prev_key); break; case BTRFS_EXTENT_CSUM_KEY: - ret = check_csum_item(leaf, key, slot); + ret = check_csum_item(leaf, key, slot, prev_key); break; case BTRFS_DIR_ITEM_KEY: case BTRFS_DIR_INDEX_KEY:

5 years, 10 months

1
0
0 0

FAILED: patch "[PATCH] Btrfs: make tree checker detect checksum items with" failed to apply to 4.9-stable tree

by gregkh＠linuxfoundation.org

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 ad1d8c439978ede77cbf73cbdd11bafe810421a5 Mon Sep 17 00:00:00 2001 From: Filipe Manana <fdmanana(a)suse.com> Date: Mon, 2 Dec 2019 11:01:03 +0000 Subject: [PATCH] Btrfs: make tree checker detect checksum items with overlapping ranges Having checksum items, either on the checksums tree or in a log tree, that represent ranges that overlap each other is a sign of a corruption. Such case confuses the checksum lookup code and can result in not being able to find checksums or find stale checksums. So add a check for such case. This is motivated by a recent fix for a case where a log tree had checksum items covering ranges that overlap each other due to extent cloning, and resulted in missing checksums after replaying the log tree. It also helps detect past issues such as stale and outdated checksums due to overlapping, commit 27b9a8122ff71a ("Btrfs: fix csum tree corruption, duplicate and outdated checksums"). CC: stable(a)vger.kernel.org # 4.4+ Signed-off-by: Filipe Manana <fdmanana(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 092b8ece36d7..97f3520b8d98 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -332,7 +332,7 @@ static int check_extent_data_item(struct extent_buffer *leaf, } static int check_csum_item(struct extent_buffer *leaf, struct btrfs_key *key, - int slot) + int slot, struct btrfs_key *prev_key) { struct btrfs_fs_info *fs_info = leaf->fs_info; u32 sectorsize = fs_info->sectorsize; @@ -356,6 +356,20 @@ static int check_csum_item(struct extent_buffer *leaf, struct btrfs_key *key, btrfs_item_size_nr(leaf, slot), csumsize); return -EUCLEAN; } + if (slot > 0 && prev_key->type == BTRFS_EXTENT_CSUM_KEY) { + u64 prev_csum_end; + u32 prev_item_size; + + prev_item_size = btrfs_item_size_nr(leaf, slot - 1); + prev_csum_end = (prev_item_size / csumsize) * sectorsize; + prev_csum_end += prev_key->offset; + if (prev_csum_end > key->offset) { + generic_err(leaf, slot - 1, +"csum end range (%llu) goes beyond the start range (%llu) of the next csum item", + prev_csum_end, key->offset); + return -EUCLEAN; + } + } return 0; } @@ -1355,7 +1369,7 @@ static int check_leaf_item(struct extent_buffer *leaf, ret = check_extent_data_item(leaf, key, slot, prev_key); break; case BTRFS_EXTENT_CSUM_KEY: - ret = check_csum_item(leaf, key, slot); + ret = check_csum_item(leaf, key, slot, prev_key); break; case BTRFS_DIR_ITEM_KEY: case BTRFS_DIR_INDEX_KEY:

5 years, 10 months

1
0
0 0

FAILED: patch "[PATCH] Btrfs: make tree checker detect checksum items with" failed to apply to 4.14-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.14-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 ad1d8c439978ede77cbf73cbdd11bafe810421a5 Mon Sep 17 00:00:00 2001 From: Filipe Manana <fdmanana(a)suse.com> Date: Mon, 2 Dec 2019 11:01:03 +0000 Subject: [PATCH] Btrfs: make tree checker detect checksum items with overlapping ranges Having checksum items, either on the checksums tree or in a log tree, that represent ranges that overlap each other is a sign of a corruption. Such case confuses the checksum lookup code and can result in not being able to find checksums or find stale checksums. So add a check for such case. This is motivated by a recent fix for a case where a log tree had checksum items covering ranges that overlap each other due to extent cloning, and resulted in missing checksums after replaying the log tree. It also helps detect past issues such as stale and outdated checksums due to overlapping, commit 27b9a8122ff71a ("Btrfs: fix csum tree corruption, duplicate and outdated checksums"). CC: stable(a)vger.kernel.org # 4.4+ Signed-off-by: Filipe Manana <fdmanana(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 092b8ece36d7..97f3520b8d98 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -332,7 +332,7 @@ static int check_extent_data_item(struct extent_buffer *leaf, } static int check_csum_item(struct extent_buffer *leaf, struct btrfs_key *key, - int slot) + int slot, struct btrfs_key *prev_key) { struct btrfs_fs_info *fs_info = leaf->fs_info; u32 sectorsize = fs_info->sectorsize; @@ -356,6 +356,20 @@ static int check_csum_item(struct extent_buffer *leaf, struct btrfs_key *key, btrfs_item_size_nr(leaf, slot), csumsize); return -EUCLEAN; } + if (slot > 0 && prev_key->type == BTRFS_EXTENT_CSUM_KEY) { + u64 prev_csum_end; + u32 prev_item_size; + + prev_item_size = btrfs_item_size_nr(leaf, slot - 1); + prev_csum_end = (prev_item_size / csumsize) * sectorsize; + prev_csum_end += prev_key->offset; + if (prev_csum_end > key->offset) { + generic_err(leaf, slot - 1, +"csum end range (%llu) goes beyond the start range (%llu) of the next csum item", + prev_csum_end, key->offset); + return -EUCLEAN; + } + } return 0; } @@ -1355,7 +1369,7 @@ static int check_leaf_item(struct extent_buffer *leaf, ret = check_extent_data_item(leaf, key, slot, prev_key); break; case BTRFS_EXTENT_CSUM_KEY: - ret = check_csum_item(leaf, key, slot); + ret = check_csum_item(leaf, key, slot, prev_key); break; case BTRFS_DIR_ITEM_KEY: case BTRFS_DIR_INDEX_KEY:

5 years, 10 months

1
0
0 0

FAILED: patch "[PATCH] Btrfs: make tree checker detect checksum items with" failed to apply to 4.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.19-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 ad1d8c439978ede77cbf73cbdd11bafe810421a5 Mon Sep 17 00:00:00 2001 From: Filipe Manana <fdmanana(a)suse.com> Date: Mon, 2 Dec 2019 11:01:03 +0000 Subject: [PATCH] Btrfs: make tree checker detect checksum items with overlapping ranges Having checksum items, either on the checksums tree or in a log tree, that represent ranges that overlap each other is a sign of a corruption. Such case confuses the checksum lookup code and can result in not being able to find checksums or find stale checksums. So add a check for such case. This is motivated by a recent fix for a case where a log tree had checksum items covering ranges that overlap each other due to extent cloning, and resulted in missing checksums after replaying the log tree. It also helps detect past issues such as stale and outdated checksums due to overlapping, commit 27b9a8122ff71a ("Btrfs: fix csum tree corruption, duplicate and outdated checksums"). CC: stable(a)vger.kernel.org # 4.4+ Signed-off-by: Filipe Manana <fdmanana(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 092b8ece36d7..97f3520b8d98 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -332,7 +332,7 @@ static int check_extent_data_item(struct extent_buffer *leaf, } static int check_csum_item(struct extent_buffer *leaf, struct btrfs_key *key, - int slot) + int slot, struct btrfs_key *prev_key) { struct btrfs_fs_info *fs_info = leaf->fs_info; u32 sectorsize = fs_info->sectorsize; @@ -356,6 +356,20 @@ static int check_csum_item(struct extent_buffer *leaf, struct btrfs_key *key, btrfs_item_size_nr(leaf, slot), csumsize); return -EUCLEAN; } + if (slot > 0 && prev_key->type == BTRFS_EXTENT_CSUM_KEY) { + u64 prev_csum_end; + u32 prev_item_size; + + prev_item_size = btrfs_item_size_nr(leaf, slot - 1); + prev_csum_end = (prev_item_size / csumsize) * sectorsize; + prev_csum_end += prev_key->offset; + if (prev_csum_end > key->offset) { + generic_err(leaf, slot - 1, +"csum end range (%llu) goes beyond the start range (%llu) of the next csum item", + prev_csum_end, key->offset); + return -EUCLEAN; + } + } return 0; } @@ -1355,7 +1369,7 @@ static int check_leaf_item(struct extent_buffer *leaf, ret = check_extent_data_item(leaf, key, slot, prev_key); break; case BTRFS_EXTENT_CSUM_KEY: - ret = check_csum_item(leaf, key, slot); + ret = check_csum_item(leaf, key, slot, prev_key); break; case BTRFS_DIR_ITEM_KEY: case BTRFS_DIR_INDEX_KEY:

5 years, 10 months

1
0
0 0

FAILED: patch "[PATCH] btrfs: do not call synchronize_srcu() in inode_tree_del" failed to apply to 4.4-stable tree

by gregkh＠linuxfoundation.org

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 f72ff01df9cf5db25c76674cac16605992d15467 Mon Sep 17 00:00:00 2001 From: Josef Bacik <josef(a)toxicpanda.com> Date: Tue, 19 Nov 2019 13:59:35 -0500 Subject: [PATCH] btrfs: do not call synchronize_srcu() in inode_tree_del Testing with the new fsstress uncovered a pretty nasty deadlock with lookup and snapshot deletion. Process A unlink -> final iput -> inode_tree_del -> synchronize_srcu(subvol_srcu) Process B btrfs_lookup <- srcu_read_lock() acquired here -> btrfs_iget -> find inode that has I_FREEING set -> __wait_on_freeing_inode() We're holding the srcu_read_lock() while doing the iget in order to make sure our fs root doesn't go away, and then we are waiting for the inode to finish freeing. However because the free'ing process is doing a synchronize_srcu() we deadlock. Fix this by dropping the synchronize_srcu() in inode_tree_del(). We don't need people to stop accessing the fs root at this point, we're only adding our empty root to the dead roots list. A larger much more invasive fix is forthcoming to address how we deal with fs roots, but this fixes the immediate problem. Fixes: 76dda93c6ae2 ("Btrfs: add snapshot/subvolume destroy ioctl") CC: stable(a)vger.kernel.org # 4.4+ Signed-off-by: Josef Bacik <josef(a)toxicpanda.com> Reviewed-by: David Sterba <dsterba(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 56032c518b26..5766c2d19896 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -5728,7 +5728,6 @@ static void inode_tree_add(struct inode *inode) static void inode_tree_del(struct inode *inode) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_root *root = BTRFS_I(inode)->root; int empty = 0; @@ -5741,7 +5740,6 @@ static void inode_tree_del(struct inode *inode) spin_unlock(&root->inode_lock); if (empty && btrfs_root_refs(&root->root_item) == 0) { - synchronize_srcu(&fs_info->subvol_srcu); spin_lock(&root->inode_lock); empty = RB_EMPTY_ROOT(&root->inode_tree); spin_unlock(&root->inode_lock);

5 years, 10 months

1
0
0 0

FAILED: patch "[PATCH] btrfs: don't double lock the subvol_sem for rename exchange" failed to apply to 4.4-stable tree

by gregkh＠linuxfoundation.org

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 943eb3bf25f4a7b745dd799e031be276aa104d82 Mon Sep 17 00:00:00 2001 From: Josef Bacik <josef(a)toxicpanda.com> Date: Tue, 19 Nov 2019 13:59:20 -0500 Subject: [PATCH] btrfs: don't double lock the subvol_sem for rename exchange If we're rename exchanging two subvols we'll try to lock this lock twice, which is bad. Just lock once if either of the ino's are subvols. Fixes: cdd1fedf8261 ("btrfs: add support for RENAME_EXCHANGE and RENAME_WHITEOUT") CC: stable(a)vger.kernel.org # 4.4+ Signed-off-by: Josef Bacik <josef(a)toxicpanda.com> Reviewed-by: David Sterba <dsterba(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 5766c2d19896..e3c76645cad7 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -9554,9 +9554,8 @@ static int btrfs_rename_exchange(struct inode *old_dir, btrfs_init_log_ctx(&ctx_dest, new_inode); /* close the race window with snapshot create/destroy ioctl */ - if (old_ino == BTRFS_FIRST_FREE_OBJECTID) - down_read(&fs_info->subvol_sem); - if (new_ino == BTRFS_FIRST_FREE_OBJECTID) + if (old_ino == BTRFS_FIRST_FREE_OBJECTID || + new_ino == BTRFS_FIRST_FREE_OBJECTID) down_read(&fs_info->subvol_sem); /* @@ -9790,9 +9789,8 @@ static int btrfs_rename_exchange(struct inode *old_dir, ret = ret ? ret : ret2; } out_notrans: - if (new_ino == BTRFS_FIRST_FREE_OBJECTID) - up_read(&fs_info->subvol_sem); - if (old_ino == BTRFS_FIRST_FREE_OBJECTID) + if (new_ino == BTRFS_FIRST_FREE_OBJECTID || + old_ino == BTRFS_FIRST_FREE_OBJECTID) up_read(&fs_info->subvol_sem); ASSERT(list_empty(&ctx_root.list));

5 years, 10 months

1
0
0 0

[PATCH v2] mm: memcg/slab: fix percpu slab vmstats flushing

by Roman Gushchin

Currently slab percpu vmstats are flushed twice: during the memcg offlining and just before freeing the memcg structure. Each time percpu counters are summed, added to the atomic counterparts and propagated up by the cgroup tree. The second flushing is required due to how recursive vmstats are implemented: counters are batched in percpu variables on a local level, and once a percpu value is crossing some predefined threshold, it spills over to atomic values on the local and each ascendant levels. It means that without flushing some numbers cached in percpu variables will be dropped on floor each time a cgroup is destroyed. And with uptime the error on upper levels might become noticeable. The first flushing aims to make counters on ancestor levels more precise. Dying cgroups may resume in the dying state for a long time. After kmem_cache reparenting which is performed during the offlining slab counters of the dying cgroup don't have any chances to be updated, because any slab operations will be performed on the parent level. It means that the inaccuracy caused by percpu batching will not decrease up to the final destruction of the cgroup. By the original idea flushing slab counters during the offlining should minimize the visible inaccuracy of slab counters on the parent level. The problem is that percpu counters are not zeroed after the first flushing. So every cached percpu value is summed twice. It creates a small error (up to 32 pages per cpu, but usually less) which accumulates on parent cgroup level. After creating and destroying of thousands of child cgroups, slab counter on parent level can be way off the real value. For now, let's just stop flushing slab counters on memcg offlining. It can't be done correctly without scheduling a work on each cpu: reading and zeroing it during css offlining can race with an asynchronous update, which doesn't expect values to be changed underneath. With this change, slab counters on parent level will become eventually consistent. Once all dying children are gone, values are correct. And if not, the error is capped by 32 * NR_CPUS pages per dying cgroup. It's not perfect, as slab are reparented, so any updates after the reparenting will happen on the parent level. It means that if a slab page was allocated, a counter on child level was bumped, then the page was reparented and freed, the annihilation of positive and negative counter values will not happen until the child cgroup is released. It makes slab counters different from others, and it might want us to implement flushing in a correct form again. But it's also a question of performance: scheduling a work on each cpu isn't free, and it's an open question if the benefit of having more accurate counters is worth it. We might also consider flushing all counters on offlining, not only slab counters. So let's fix the main problem now: make the slab counters eventually consistent, so at least the error won't grow with uptime (or more precisely the number of created and destroyed cgroups). And think about the accuracy of counters separately. v2: added a note to the changelog, asked by Johannes. Thanks! Signed-off-by: Roman Gushchin <guro(a)fb.com> Fixes: bee07b33db78 ("mm: memcontrol: flush percpu slab vmstats on kmem offlining") Cc: stable(a)vger.kernel.org Acked-by: Johannes Weiner <hannes(a)cmpxchg.org> --- include/linux/mmzone.h | 5 ++--- mm/memcontrol.c | 37 +++++++++---------------------------- 2 files changed, 11 insertions(+), 31 deletions(-) diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 89d8ff06c9ce..5334ad8fc7bd 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -215,9 +215,8 @@ enum node_stat_item { NR_INACTIVE_FILE, /* " " " " " */ NR_ACTIVE_FILE, /* " " " " " */ NR_UNEVICTABLE, /* " " " " " */ - NR_SLAB_RECLAIMABLE, /* Please do not reorder this item */ - NR_SLAB_UNRECLAIMABLE, /* and this one without looking at - * memcg_flush_percpu_vmstats() first. */ + NR_SLAB_RECLAIMABLE, + NR_SLAB_UNRECLAIMABLE, NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */ NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */ WORKINGSET_NODES, diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 601405b207fb..3165db39827a 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3287,49 +3287,34 @@ static u64 mem_cgroup_read_u64(struct cgroup_subsys_state *css, } } -static void memcg_flush_percpu_vmstats(struct mem_cgroup *memcg, bool slab_only) +static void memcg_flush_percpu_vmstats(struct mem_cgroup *memcg) { - unsigned long stat[MEMCG_NR_STAT]; + unsigned long stat[MEMCG_NR_STAT] = {0}; struct mem_cgroup *mi; int node, cpu, i; - int min_idx, max_idx; - - if (slab_only) { - min_idx = NR_SLAB_RECLAIMABLE; - max_idx = NR_SLAB_UNRECLAIMABLE; - } else { - min_idx = 0; - max_idx = MEMCG_NR_STAT; - } - - for (i = min_idx; i < max_idx; i++) - stat[i] = 0; for_each_online_cpu(cpu) - for (i = min_idx; i < max_idx; i++) + for (i = 0; i < MEMCG_NR_STAT; i++) stat[i] += per_cpu(memcg->vmstats_percpu->stat[i], cpu); for (mi = memcg; mi; mi = parent_mem_cgroup(mi)) - for (i = min_idx; i < max_idx; i++) + for (i = 0; i < MEMCG_NR_STAT; i++) atomic_long_add(stat[i], &mi->vmstats[i]); - if (!slab_only) - max_idx = NR_VM_NODE_STAT_ITEMS; - for_each_node(node) { struct mem_cgroup_per_node *pn = memcg->nodeinfo[node]; struct mem_cgroup_per_node *pi; - for (i = min_idx; i < max_idx; i++) + for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) stat[i] = 0; for_each_online_cpu(cpu) - for (i = min_idx; i < max_idx; i++) + for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) stat[i] += per_cpu( pn->lruvec_stat_cpu->count[i], cpu); for (pi = pn; pi; pi = parent_nodeinfo(pi, node)) - for (i = min_idx; i < max_idx; i++) + for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) atomic_long_add(stat[i], &pi->lruvec_stat[i]); } } @@ -3403,13 +3388,9 @@ static void memcg_offline_kmem(struct mem_cgroup *memcg) parent = root_mem_cgroup; /* - * Deactivate and reparent kmem_caches. Then flush percpu - * slab statistics to have precise values at the parent and - * all ancestor levels. It's required to keep slab stats - * accurate after the reparenting of kmem_caches. + * Deactivate and reparent kmem_caches. */ memcg_deactivate_kmem_caches(memcg, parent); - memcg_flush_percpu_vmstats(memcg, true); kmemcg_id = memcg->kmemcg_id; BUG_ON(kmemcg_id < 0); @@ -4913,7 +4894,7 @@ static void mem_cgroup_free(struct mem_cgroup *memcg) * Flush percpu vmstats and vmevents to guarantee the value correctness * on parent's and all ancestor levels. */ - memcg_flush_percpu_vmstats(memcg, false); + memcg_flush_percpu_vmstats(memcg); memcg_flush_percpu_vmevents(memcg); __mem_cgroup_free(memcg); } -- 2.17.1

5 years, 10 months

2
2
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror