From 96f3136e51580ed68a2952341c8b9e2d7f853472 Mon Sep 17 00:00:00 2001 From: Anand Jain Date: Fri, 14 Aug 2015 18:32:46 +0800 Subject: Btrfs: rename btrfs_sysfs_add_one to btrfs_sysfs_add_mounted Signed-off-by: Anand Jain Signed-off-by: David Sterba --- fs/btrfs/disk-io.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 295795aebe0b..4622d38fa56e 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2933,7 +2933,7 @@ retry_root_backup: goto fail_fsdev_sysfs; } - ret = btrfs_sysfs_add_one(fs_info); + ret = btrfs_sysfs_add_mounted(fs_info); if (ret) { pr_err("BTRFS: failed to init sysfs interface: %d\n", ret); goto fail_fsdev_sysfs; -- cgit v1.2.3 From 6618a59bfc0a0490f2a51df37c67878e23285670 Mon Sep 17 00:00:00 2001 From: Anand Jain Date: Fri, 14 Aug 2015 18:32:47 +0800 Subject: Btrfs: rename btrfs_sysfs_remove_one to btrfs_sysfs_remove_mounted Signed-off-by: Anand Jain Signed-off-by: David Sterba --- fs/btrfs/ctree.h | 2 +- fs/btrfs/disk-io.c | 4 ++-- fs/btrfs/sysfs.c | 4 ++-- 3 files changed, 5 insertions(+), 5 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index afce3069697a..448406307272 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -4005,7 +4005,7 @@ int btrfs_defrag_leaves(struct btrfs_trans_handle *trans, int btrfs_init_sysfs(void); void btrfs_exit_sysfs(void); int btrfs_sysfs_add_mounted(struct btrfs_fs_info *fs_info); -void btrfs_sysfs_remove_one(struct btrfs_fs_info *fs_info); +void btrfs_sysfs_remove_mounted(struct btrfs_fs_info *fs_info); /* xattr.c */ ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 4622d38fa56e..76734732eca6 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3113,7 +3113,7 @@ fail_cleaner: filemap_write_and_wait(fs_info->btree_inode->i_mapping); fail_sysfs: - btrfs_sysfs_remove_one(fs_info); + btrfs_sysfs_remove_mounted(fs_info); fail_fsdev_sysfs: btrfs_sysfs_remove_fsid(fs_info->fs_devices); @@ -3788,7 +3788,7 @@ void close_ctree(struct btrfs_root *root) percpu_counter_sum(&fs_info->delalloc_bytes)); } - btrfs_sysfs_remove_one(fs_info); + btrfs_sysfs_remove_mounted(fs_info); btrfs_sysfs_remove_fsid(fs_info->fs_devices); btrfs_free_fs_roots(fs_info); diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index cabf840f6b37..095a302417ef 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -545,7 +545,7 @@ void btrfs_sysfs_remove_fsid(struct btrfs_fs_devices *fs_devs) } } -void btrfs_sysfs_remove_one(struct btrfs_fs_info *fs_info) +void btrfs_sysfs_remove_mounted(struct btrfs_fs_info *fs_info) { btrfs_reset_fs_info_ptr(fs_info); @@ -776,7 +776,7 @@ int btrfs_sysfs_add_mounted(struct btrfs_fs_info *fs_info) return 0; failure: - btrfs_sysfs_remove_one(fs_info); + btrfs_sysfs_remove_mounted(fs_info); return error; } -- cgit v1.2.3 From 92fc03fbdcbe2523be3f7e6b8e95fee9563a10d2 Mon Sep 17 00:00:00 2001 From: Anand Jain Date: Fri, 14 Aug 2015 18:32:51 +0800 Subject: Btrfs: SB read failure should return EIO for __bread failure This will return EIO when __bread() fails to read SB, instead of EINVAL. Signed-off-by: Anand Jain Signed-off-by: David Sterba --- fs/btrfs/disk-io.c | 18 +++++++++++++++--- fs/btrfs/volumes.c | 8 ++++---- 2 files changed, 19 insertions(+), 7 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 76734732eca6..357d9f9c9968 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2653,8 +2653,8 @@ int open_ctree(struct super_block *sb, * Read super block and check the signature bytes only */ bh = btrfs_read_dev_super(fs_devices->latest_bdev); - if (!bh) { - err = -EINVAL; + if (IS_ERR(bh)) { + err = PTR_ERR(bh); goto fail_alloc; } @@ -3196,6 +3196,7 @@ struct buffer_head *btrfs_read_dev_super(struct block_device *bdev) int i; u64 transid = 0; u64 bytenr; + int ret = -EINVAL; /* we would like to check all the supers, but that would make * a btrfs mount succeed after a mkfs from a different FS. @@ -3209,13 +3210,20 @@ struct buffer_head *btrfs_read_dev_super(struct block_device *bdev) break; bh = __bread(bdev, bytenr / 4096, BTRFS_SUPER_INFO_SIZE); - if (!bh) + /* + * If we fail to read from the underlying devices, as of now + * the best option we have is to mark it EIO. + */ + if (!bh) { + ret = -EIO; continue; + } super = (struct btrfs_super_block *)bh->b_data; if (btrfs_super_bytenr(super) != bytenr || btrfs_super_magic(super) != BTRFS_MAGIC) { brelse(bh); + ret = -EINVAL; continue; } @@ -3227,6 +3235,10 @@ struct buffer_head *btrfs_read_dev_super(struct block_device *bdev) brelse(bh); } } + + if (!latest) + return ERR_PTR(ret); + return latest; } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 643879208f05..e8a618261218 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -211,8 +211,8 @@ btrfs_get_bdev_and_sb(const char *device_path, fmode_t flags, void *holder, } invalidate_bdev(*bdev); *bh = btrfs_read_dev_super(*bdev); - if (!*bh) { - ret = -EINVAL; + if (IS_ERR(*bh)) { + ret = PTR_ERR(*bh); blkdev_put(*bdev, flags); goto error; } @@ -6746,8 +6746,8 @@ int btrfs_scratch_superblock(struct btrfs_device *device) struct btrfs_super_block *disk_super; bh = btrfs_read_dev_super(device->bdev); - if (!bh) - return -EINVAL; + if (IS_ERR(bh)) + return PTR_ERR(bh); disk_super = (struct btrfs_super_block *)bh->b_data; memset(&disk_super->magic, 0, sizeof(disk_super->magic)); -- cgit v1.2.3 From a4553fefb59cb0336f543fa567170b47e90142a9 Mon Sep 17 00:00:00 2001 From: Anand Jain Date: Fri, 25 Sep 2015 14:43:01 +0800 Subject: Btrfs: consolidate btrfs_error() to btrfs_std_error() btrfs_error() and btrfs_std_error() does the same thing and calls _btrfs_std_error(), so consolidate them together. And the main motivation is that btrfs_error() is closely named with btrfs_err(), one handles error action the other is to log the error, so don't closely name them. Signed-off-by: Anand Jain Suggested-by: David Sterba Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/ctree.c | 6 +++--- fs/btrfs/ctree.h | 9 +-------- fs/btrfs/disk-io.c | 8 ++++---- fs/btrfs/extent-tree.c | 2 +- fs/btrfs/inode-item.c | 2 +- fs/btrfs/ioctl.c | 2 +- fs/btrfs/relocation.c | 2 +- fs/btrfs/root-tree.c | 4 ++-- fs/btrfs/transaction.c | 2 +- fs/btrfs/tree-log.c | 8 ++++---- fs/btrfs/volumes.c | 14 +++++++------- 11 files changed, 26 insertions(+), 33 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 5f745eadf77d..1063315fb387 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -1011,7 +1011,7 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans, return ret; if (refs == 0) { ret = -EROFS; - btrfs_std_error(root->fs_info, ret); + btrfs_std_error(root->fs_info, ret, NULL); return ret; } } else { @@ -1927,7 +1927,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, child = read_node_slot(root, mid, 0); if (!child) { ret = -EROFS; - btrfs_std_error(root->fs_info, ret); + btrfs_std_error(root->fs_info, ret, NULL); goto enospc; } @@ -2030,7 +2030,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, */ if (!left) { ret = -EROFS; - btrfs_std_error(root->fs_info, ret); + btrfs_std_error(root->fs_info, ret, NULL); goto enospc; } wret = balance_node_right(trans, root, mid, left); diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 448406307272..a86051e332ff 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -4127,14 +4127,7 @@ do { \ __LINE__, (errno)); \ } while (0) -#define btrfs_std_error(fs_info, errno) \ -do { \ - if ((errno)) \ - __btrfs_std_error((fs_info), __func__, \ - __LINE__, (errno), NULL); \ -} while (0) - -#define btrfs_error(fs_info, errno, fmt, args...) \ +#define btrfs_std_error(fs_info, errno, fmt, args...) \ do { \ __btrfs_std_error((fs_info), __func__, __LINE__, \ (errno), fmt, ##args); \ diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 357d9f9c9968..0f8e33f2bcea 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2377,7 +2377,7 @@ static int btrfs_replay_log(struct btrfs_fs_info *fs_info, /* returns with log_tree_root freed on success */ ret = btrfs_recover_log_trees(log_tree_root); if (ret) { - btrfs_error(tree_root->fs_info, ret, + btrfs_std_error(tree_root->fs_info, ret, "Failed to recover log tree"); free_extent_buffer(log_tree_root->node); kfree(log_tree_root); @@ -3556,7 +3556,7 @@ static int write_all_supers(struct btrfs_root *root, int max_mirrors) if (ret) { mutex_unlock( &root->fs_info->fs_devices->device_list_mutex); - btrfs_error(root->fs_info, ret, + btrfs_std_error(root->fs_info, ret, "errors while submitting device barriers."); return ret; } @@ -3596,7 +3596,7 @@ static int write_all_supers(struct btrfs_root *root, int max_mirrors) mutex_unlock(&root->fs_info->fs_devices->device_list_mutex); /* FUA is masked off if unsupported and can't be the reason */ - btrfs_error(root->fs_info, -EIO, + btrfs_std_error(root->fs_info, -EIO, "%d errors while writing supers", total_errors); return -EIO; } @@ -3614,7 +3614,7 @@ static int write_all_supers(struct btrfs_root *root, int max_mirrors) } mutex_unlock(&root->fs_info->fs_devices->device_list_mutex); if (total_errors > max_errors) { - btrfs_error(root->fs_info, -EIO, + btrfs_std_error(root->fs_info, -EIO, "%d errors while writing supers", total_errors); return -EIO; } diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 9f9604201333..5069f1b73395 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -8688,7 +8688,7 @@ out: if (!for_reloc && root_dropped == false) btrfs_add_dead_root(root); if (err && err != -EAGAIN) - btrfs_std_error(root->fs_info, err); + btrfs_std_error(root->fs_info, err, NULL); return err; } diff --git a/fs/btrfs/inode-item.c b/fs/btrfs/inode-item.c index 265e03c73f4d..be4d22a5022f 100644 --- a/fs/btrfs/inode-item.c +++ b/fs/btrfs/inode-item.c @@ -157,7 +157,7 @@ static int btrfs_del_inode_extref(struct btrfs_trans_handle *trans, */ if (!btrfs_find_name_in_ext_backref(path, ref_objectid, name, name_len, &extref)) { - btrfs_std_error(root->fs_info, -ENOENT); + btrfs_std_error(root->fs_info, -ENOENT, NULL); ret = -EROFS; goto out; } diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 0adf5422fce9..f704d1c79739 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -4806,7 +4806,7 @@ static long btrfs_ioctl_qgroup_assign(struct file *file, void __user *arg) /* update qgroup status and info */ err = btrfs_run_qgroups(trans, root->fs_info); if (err < 0) - btrfs_error(root->fs_info, ret, + btrfs_std_error(root->fs_info, ret, "failed to update qgroup status and info\n"); err = btrfs_end_transaction(trans, root); if (err && !ret) diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 303babeef505..58ede0a56456 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -2418,7 +2418,7 @@ again: } out: if (ret) { - btrfs_std_error(root->fs_info, ret); + btrfs_std_error(root->fs_info, ret, NULL); if (!list_empty(&reloc_roots)) free_reloc_roots(&reloc_roots); diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index 360a728a639f..6d90851af4f0 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -283,7 +283,7 @@ int btrfs_find_orphan_roots(struct btrfs_root *tree_root) trans = btrfs_join_transaction(tree_root); if (IS_ERR(trans)) { err = PTR_ERR(trans); - btrfs_error(tree_root->fs_info, err, + btrfs_std_error(tree_root->fs_info, err, "Failed to start trans to delete " "orphan item"); break; @@ -292,7 +292,7 @@ int btrfs_find_orphan_roots(struct btrfs_root *tree_root) root_key.objectid); btrfs_end_transaction(trans, tree_root); if (err) { - btrfs_error(tree_root->fs_info, err, + btrfs_std_error(tree_root->fs_info, err, "Failed to delete root orphan " "item"); break; diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 74bc3338418b..3482d9eeb62d 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -2135,7 +2135,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, ret = btrfs_write_and_wait_transaction(trans, root); if (ret) { - btrfs_error(root->fs_info, ret, + btrfs_std_error(root->fs_info, ret, "Error while writing out transaction"); mutex_unlock(&root->fs_info->tree_log_mutex); goto scrub_continue; diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 1bbaace73383..c3f9a9c71f28 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -5314,7 +5314,7 @@ int btrfs_recover_log_trees(struct btrfs_root *log_root_tree) ret = walk_log_tree(trans, log_root_tree, &wc); if (ret) { - btrfs_error(fs_info, ret, "Failed to pin buffers while " + btrfs_std_error(fs_info, ret, "Failed to pin buffers while " "recovering log root tree."); goto error; } @@ -5328,7 +5328,7 @@ again: ret = btrfs_search_slot(NULL, log_root_tree, &key, path, 0, 0); if (ret < 0) { - btrfs_error(fs_info, ret, + btrfs_std_error(fs_info, ret, "Couldn't find tree log root."); goto error; } @@ -5346,7 +5346,7 @@ again: log = btrfs_read_fs_root(log_root_tree, &found_key); if (IS_ERR(log)) { ret = PTR_ERR(log); - btrfs_error(fs_info, ret, + btrfs_std_error(fs_info, ret, "Couldn't read tree log root."); goto error; } @@ -5361,7 +5361,7 @@ again: free_extent_buffer(log->node); free_extent_buffer(log->commit_root); kfree(log); - btrfs_error(fs_info, ret, "Couldn't read target root " + btrfs_std_error(fs_info, ret, "Couldn't read target root " "for tree log recovery."); goto error; } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index e8a618261218..99f294cfdcc0 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1402,7 +1402,7 @@ again: extent = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_dev_extent); } else { - btrfs_error(root->fs_info, ret, "Slot search failed"); + btrfs_std_error(root->fs_info, ret, "Slot search failed"); goto out; } @@ -1410,7 +1410,7 @@ again: ret = btrfs_del_item(trans, root, path); if (ret) { - btrfs_error(root->fs_info, ret, + btrfs_std_error(root->fs_info, ret, "Failed to remove dev extent item"); } else { trans->transaction->have_free_bgs = 1; @@ -2368,7 +2368,7 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path) ret = btrfs_relocate_sys_chunks(root); if (ret < 0) - btrfs_error(root->fs_info, ret, + btrfs_std_error(root->fs_info, ret, "Failed to relocate sys chunks after " "device initialization. This can be fixed " "using the \"btrfs balance\" command."); @@ -2613,7 +2613,7 @@ static int btrfs_free_chunk(struct btrfs_trans_handle *trans, if (ret < 0) goto out; else if (ret > 0) { /* Logic error or corruption */ - btrfs_error(root->fs_info, -ENOENT, + btrfs_std_error(root->fs_info, -ENOENT, "Failed lookup while freeing chunk."); ret = -ENOENT; goto out; @@ -2621,7 +2621,7 @@ static int btrfs_free_chunk(struct btrfs_trans_handle *trans, ret = btrfs_del_item(trans, root, path); if (ret < 0) - btrfs_error(root->fs_info, ret, + btrfs_std_error(root->fs_info, ret, "Failed to delete chunk item."); out: btrfs_free_path(path); @@ -2806,7 +2806,7 @@ static int btrfs_relocate_chunk(struct btrfs_root *root, u64 chunk_offset) trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { ret = PTR_ERR(trans); - btrfs_std_error(root->fs_info, ret); + btrfs_std_error(root->fs_info, ret, NULL); return ret; } @@ -3461,7 +3461,7 @@ static void __cancel_balance(struct btrfs_fs_info *fs_info) unset_balance_control(fs_info); ret = del_balance_item(fs_info->tree_root); if (ret) - btrfs_std_error(fs_info, ret); + btrfs_std_error(fs_info, ret, NULL); atomic_set(&fs_info->mutually_exclusive_operation_running, 0); } -- cgit v1.2.3 From 29c36d72535deb3d8961b3fb4b6a565190a6c63b Mon Sep 17 00:00:00 2001 From: Anand Jain Date: Fri, 14 Aug 2015 18:32:58 +0800 Subject: Btrfs: add btrfs_read_dev_one_super() to read one specific SB This uses a chunk of code from btrfs_read_dev_super() and creates a function called btrfs_read_dev_one_super() so that next patch can use it for scratch superblock. Signed-off-by: Anand Jain [renamed bufhead to bh] Signed-off-by: David Sterba --- fs/btrfs/disk-io.c | 53 +++++++++++++++++++++++++++++++++-------------------- fs/btrfs/disk-io.h | 2 ++ 2 files changed, 35 insertions(+), 20 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 0f8e33f2bcea..c7c739f420b5 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3188,6 +3188,37 @@ static void btrfs_end_buffer_write_sync(struct buffer_head *bh, int uptodate) put_bh(bh); } +int btrfs_read_dev_one_super(struct block_device *bdev, int copy_num, + struct buffer_head **bh_ret) +{ + struct buffer_head *bh; + struct btrfs_super_block *super; + u64 bytenr; + + bytenr = btrfs_sb_offset(copy_num); + if (bytenr + BTRFS_SUPER_INFO_SIZE >= i_size_read(bdev->bd_inode)) + return -EINVAL; + + bh = __bread(bdev, bytenr / 4096, BTRFS_SUPER_INFO_SIZE); + /* + * If we fail to read from the underlying devices, as of now + * the best option we have is to mark it EIO. + */ + if (!bh) + return -EIO; + + super = (struct btrfs_super_block *)bh->b_data; + if (btrfs_super_bytenr(super) != bytenr || + btrfs_super_magic(super) != BTRFS_MAGIC) { + brelse(bh); + return -EINVAL; + } + + *bh_ret = bh; + return 0; +} + + struct buffer_head *btrfs_read_dev_super(struct block_device *bdev) { struct buffer_head *bh; @@ -3195,7 +3226,6 @@ struct buffer_head *btrfs_read_dev_super(struct block_device *bdev) struct btrfs_super_block *super; int i; u64 transid = 0; - u64 bytenr; int ret = -EINVAL; /* we would like to check all the supers, but that would make @@ -3204,28 +3234,11 @@ struct buffer_head *btrfs_read_dev_super(struct block_device *bdev) * later supers, using BTRFS_SUPER_MIRROR_MAX instead */ for (i = 0; i < 1; i++) { - bytenr = btrfs_sb_offset(i); - if (bytenr + BTRFS_SUPER_INFO_SIZE >= - i_size_read(bdev->bd_inode)) - break; - bh = __bread(bdev, bytenr / 4096, - BTRFS_SUPER_INFO_SIZE); - /* - * If we fail to read from the underlying devices, as of now - * the best option we have is to mark it EIO. - */ - if (!bh) { - ret = -EIO; + ret = btrfs_read_dev_one_super(bdev, i, &bh); + if (ret) continue; - } super = (struct btrfs_super_block *)bh->b_data; - if (btrfs_super_bytenr(super) != bytenr || - btrfs_super_magic(super) != BTRFS_MAGIC) { - brelse(bh); - ret = -EINVAL; - continue; - } if (!latest || btrfs_super_generation(super) > transid) { brelse(latest); diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index bdfb479ea859..adeb31830b9c 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -60,6 +60,8 @@ void close_ctree(struct btrfs_root *root); int write_ctree_super(struct btrfs_trans_handle *trans, struct btrfs_root *root, int max_mirrors); struct buffer_head *btrfs_read_dev_super(struct block_device *bdev); +int btrfs_read_dev_one_super(struct block_device *bdev, int copy_num, + struct buffer_head **bh_ret); int btrfs_commit_super(struct btrfs_root *root); struct extent_buffer *btrfs_find_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr); -- cgit v1.2.3 From b14af3b46f214c5e927dacf58a994fa3c4cb20dc Mon Sep 17 00:00:00 2001 From: David Sterba Date: Thu, 8 Oct 2015 10:43:10 +0200 Subject: btrfs: switch message printers to ratelimited _in_rcu variants Signed-off-by: David Sterba --- fs/btrfs/disk-io.c | 4 ++-- fs/btrfs/extent_io.c | 4 ++-- fs/btrfs/scrub.c | 20 ++++++++++---------- fs/btrfs/volumes.c | 4 ++-- 4 files changed, 16 insertions(+), 16 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 295795aebe0b..ba41faf623ce 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3175,8 +3175,8 @@ static void btrfs_end_buffer_write_sync(struct buffer_head *bh, int uptodate) struct btrfs_device *device = (struct btrfs_device *) bh->b_private; - printk_ratelimited_in_rcu(KERN_WARNING "BTRFS: lost page write due to " - "I/O error on %s\n", + btrfs_warn_rl_in_rcu(device->dev_root->fs_info, + "lost page write due to IO error on %s", rcu_str_deref(device->name)); /* note, we dont' set_buffer_write_io_error because we have * our own ways of dealing with the IO errors diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index e2357e31609a..58b9ccdfe2e9 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -2078,8 +2078,8 @@ int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical, return -EIO; } - printk_ratelimited_in_rcu(KERN_INFO - "BTRFS: read error corrected: ino %llu off %llu (dev %s sector %llu)\n", + btrfs_info_rl_in_rcu(fs_info, + "read error corrected: ino %llu off %llu (dev %s sector %llu)", btrfs_ino(inode), start, rcu_str_deref(dev->name), sector); bio_put(bio); diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 26cfbb0b867c..bce86f8772e1 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -850,8 +850,8 @@ out: btrfs_dev_replace_stats_inc( &sctx->dev_root->fs_info->dev_replace. num_uncorrectable_read_errors); - printk_ratelimited_in_rcu(KERN_ERR "BTRFS: " - "unable to fixup (nodatasum) error at logical %llu on dev %s\n", + btrfs_err_rl_in_rcu(sctx->dev_root->fs_info, + "unable to fixup (nodatasum) error at logical %llu on dev %s", fixup->logical, rcu_str_deref(fixup->dev->name)); } @@ -1230,8 +1230,8 @@ corrected_error: sctx->stat.corrected_errors++; sblock_to_check->data_corrected = 1; spin_unlock(&sctx->stat_lock); - printk_ratelimited_in_rcu(KERN_ERR - "BTRFS: fixed up error at logical %llu on dev %s\n", + btrfs_err_rl_in_rcu(fs_info, + "fixed up error at logical %llu on dev %s", logical, rcu_str_deref(dev->name)); } } else { @@ -1239,8 +1239,8 @@ did_not_correct_error: spin_lock(&sctx->stat_lock); sctx->stat.uncorrectable_errors++; spin_unlock(&sctx->stat_lock); - printk_ratelimited_in_rcu(KERN_ERR - "BTRFS: unable to fixup (regular) error at logical %llu on dev %s\n", + btrfs_err_rl_in_rcu(fs_info, + "unable to fixup (regular) error at logical %llu on dev %s", logical, rcu_str_deref(dev->name)); } @@ -2201,15 +2201,15 @@ static void scrub_missing_raid56_worker(struct btrfs_work *work) spin_lock(&sctx->stat_lock); sctx->stat.read_errors++; spin_unlock(&sctx->stat_lock); - printk_ratelimited_in_rcu(KERN_ERR - "BTRFS: I/O error rebulding logical %llu for dev %s\n", + btrfs_err_rl_in_rcu(fs_info, + "IO error rebuilding logical %llu for dev %s", logical, rcu_str_deref(dev->name)); } else if (sblock->header_error || sblock->checksum_error) { spin_lock(&sctx->stat_lock); sctx->stat.uncorrectable_errors++; spin_unlock(&sctx->stat_lock); - printk_ratelimited_in_rcu(KERN_ERR - "BTRFS: failed to rebuild valid logical %llu for dev %s\n", + btrfs_err_rl_in_rcu(fs_info, + "failed to rebuild valid logical %llu for dev %s", logical, rcu_str_deref(dev->name)); } else { scrub_write_block_to_dev_replace(sblock); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index b0dae14242e8..4f80986dbf3c 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -6675,8 +6675,8 @@ static void btrfs_dev_stat_print_on_error(struct btrfs_device *dev) { if (!dev->dev_stats_valid) return; - printk_ratelimited_in_rcu(KERN_ERR "BTRFS: " - "bdev %s errs: wr %u, rd %u, flush %u, corrupt %u, gen %u\n", + btrfs_err_rl_in_rcu(dev->dev_root->fs_info, + "bdev %s errs: wr %u, rd %u, flush %u, corrupt %u, gen %u", rcu_str_deref(dev->name), btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_WRITE_ERRS), btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_READ_ERRS), -- cgit v1.2.3 From 9464732266862f6044e4708dca6c4b2a83dd937b Mon Sep 17 00:00:00 2001 From: David Sterba Date: Thu, 8 Oct 2015 11:01:36 +0200 Subject: btrfs: switch message printers to ratelimited variants Signed-off-by: David Sterba --- fs/btrfs/disk-io.c | 21 ++++++++++----------- fs/btrfs/extent-tree.c | 14 ++++++++------ fs/btrfs/extent_io.c | 4 ++-- fs/btrfs/free-space-cache.c | 10 +++++----- fs/btrfs/inode.c | 7 ++----- fs/btrfs/scrub.c | 8 ++++---- 6 files changed, 31 insertions(+), 33 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index ba41faf623ce..72553cd9ed14 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -319,9 +319,9 @@ static int csum_tree_block(struct btrfs_fs_info *fs_info, memcpy(&found, result, csum_size); read_extent_buffer(buf, &val, 0, csum_size); - printk_ratelimited(KERN_WARNING - "BTRFS: %s checksum verify failed on %llu wanted %X found %X " - "level %d\n", + btrfs_warn_rl(fs_info, + "%s checksum verify failed on %llu wanted %X found %X " + "level %d", fs_info->sb->s_id, buf->start, val, found, btrfs_header_level(buf)); if (result != (char *)&inline_result) @@ -368,9 +368,9 @@ static int verify_parent_transid(struct extent_io_tree *io_tree, ret = 0; goto out; } - printk_ratelimited(KERN_ERR - "BTRFS (device %s): parent transid verify failed on %llu wanted %llu found %llu\n", - eb->fs_info->sb->s_id, eb->start, + btrfs_err_rl(eb->fs_info, + "parent transid verify failed on %llu wanted %llu found %llu", + eb->start, parent_transid, btrfs_header_generation(eb)); ret = 1; @@ -629,15 +629,14 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio, found_start = btrfs_header_bytenr(eb); if (found_start != eb->start) { - printk_ratelimited(KERN_ERR "BTRFS (device %s): bad tree block start " - "%llu %llu\n", - eb->fs_info->sb->s_id, found_start, eb->start); + btrfs_err_rl(eb->fs_info, "bad tree block start %llu %llu", + found_start, eb->start); ret = -EIO; goto err; } if (check_tree_block_fsid(root->fs_info, eb)) { - printk_ratelimited(KERN_ERR "BTRFS (device %s): bad fsid on block %llu\n", - eb->fs_info->sb->s_id, eb->start); + btrfs_err_rl(eb->fs_info, "bad fsid on block %llu", + eb->start); ret = -EIO; goto err; } diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 9f9604201333..913a5836e604 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -8271,10 +8271,11 @@ skip: ret = account_shared_subtree(trans, root, next, generation, level - 1); if (ret) { - printk_ratelimited(KERN_ERR "BTRFS: %s Error " + btrfs_err_rl(root->fs_info, + "Error " "%d accounting shared subtree. Quota " - "is out of sync, rescan required.\n", - root->fs_info->sb->s_id, ret); + "is out of sync, rescan required.", + ret); } } ret = btrfs_free_extent(trans, root, bytenr, blocksize, parent, @@ -8363,10 +8364,11 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans, BUG_ON(ret); /* -ENOMEM */ ret = account_leaf_items(trans, root, eb); if (ret) { - printk_ratelimited(KERN_ERR "BTRFS: %s Error " + btrfs_err_rl(root->fs_info, + "error " "%d accounting leaf items. Quota " - "is out of sync, rescan required.\n", - root->fs_info->sb->s_id, ret); + "is out of sync, rescan required.", + ret); } } /* make block locked assertion in clean_tree_block happy */ diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 58b9ccdfe2e9..bb318b4e5dd0 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -96,8 +96,8 @@ static inline void __btrfs_debug_check_extent_io_range(const char *caller, inode = tree->mapping->host; isize = i_size_read(inode); if (end >= PAGE_SIZE && (end % 2) == 0 && end != isize - 1) { - printk_ratelimited(KERN_DEBUG - "BTRFS: %s: ino %llu isize %llu odd range [%llu,%llu]\n", + btrfs_debug_rl(BTRFS_I(inode)->root->fs_info, + "%s: ino %llu isize %llu odd range [%llu,%llu]", caller, btrfs_ino(inode), isize, start, end); } } diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index abe3a66bd3ba..afc10725f1d1 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -450,9 +450,9 @@ static int io_ctl_check_generation(struct btrfs_io_ctl *io_ctl, u64 generation) gen = io_ctl->cur; if (le64_to_cpu(*gen) != generation) { - printk_ratelimited(KERN_ERR "BTRFS: space cache generation " - "(%Lu) does not match inode (%Lu)\n", *gen, - generation); + btrfs_err_rl(io_ctl->root->fs_info, + "space cache generation (%llu) does not match inode (%llu)", + *gen, generation); io_ctl_unmap_page(io_ctl); return -EIO; } @@ -506,8 +506,8 @@ static int io_ctl_check_crc(struct btrfs_io_ctl *io_ctl, int index) PAGE_CACHE_SIZE - offset); btrfs_csum_final(crc, (char *)&crc); if (val != crc) { - printk_ratelimited(KERN_ERR "BTRFS: csum mismatch on free " - "space cache\n"); + btrfs_err_rl(io_ctl->root->fs_info, + "csum mismatch on free space cache"); io_ctl_unmap_page(io_ctl); return -EIO; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 611b66d73e80..25eb814c302f 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3018,8 +3018,6 @@ static int __readpage_endio_check(struct inode *inode, char *kaddr; u32 csum_expected; u32 csum = ~(u32)0; - static DEFINE_RATELIMIT_STATE(_rs, DEFAULT_RATELIMIT_INTERVAL, - DEFAULT_RATELIMIT_BURST); csum_expected = *(((u32 *)io_bio->csum) + icsum); @@ -3032,9 +3030,8 @@ static int __readpage_endio_check(struct inode *inode, kunmap_atomic(kaddr); return 0; zeroit: - if (__ratelimit(&_rs)) - btrfs_warn(BTRFS_I(inode)->root->fs_info, - "csum failed ino %llu off %llu csum %u expected csum %u", + btrfs_warn_rl(BTRFS_I(inode)->root->fs_info, + "csum failed ino %llu off %llu csum %u expected csum %u", btrfs_ino(inode), start, csum, csum_expected); memset(kaddr + pgoff, 1, len); flush_dcache_page(page); diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index bce86f8772e1..550de89a8661 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -1626,9 +1626,9 @@ static int scrub_repair_page_from_good_copy(struct scrub_block *sblock_bad, int ret; if (!page_bad->dev->bdev) { - printk_ratelimited(KERN_WARNING "BTRFS: " + btrfs_warn_rl(sblock_bad->sctx->dev_root->fs_info, "scrub_repair_page_from_good_copy(bdev == NULL) " - "is unexpected!\n"); + "is unexpected"); return -EIO; } @@ -4375,8 +4375,8 @@ static int write_page_nocow(struct scrub_ctx *sctx, if (!dev) return -EIO; if (!dev->bdev) { - printk_ratelimited(KERN_WARNING - "BTRFS: scrub write_page_nocow(bdev == NULL) is unexpected!\n"); + btrfs_warn_rl(dev->dev_root->fs_info, + "scrub write_page_nocow(bdev == NULL) is unexpected"); return -EIO; } bio = btrfs_io_bio_alloc(GFP_NOFS, 1); -- cgit v1.2.3 From f14d104dbdb5044dac9acd0e983ffb60f706c746 Mon Sep 17 00:00:00 2001 From: David Sterba Date: Thu, 8 Oct 2015 11:37:06 +0200 Subject: btrfs: switch more printks to our helpers Convert the simple cases, not all functions provide a way to reach the fs_info. Also skipped debugging messages (print-tree, integrity checker and pr_debug) and messages that are printed from possibly unfinished mount. Signed-off-by: David Sterba --- fs/btrfs/disk-io.c | 12 ++++++------ fs/btrfs/extent_io.c | 18 ++++++++++-------- fs/btrfs/ioctl.c | 6 +++--- fs/btrfs/root-tree.c | 5 +++-- fs/btrfs/send.c | 2 +- fs/btrfs/volumes.c | 3 ++- 6 files changed, 25 insertions(+), 21 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 72553cd9ed14..5bc94d2d5699 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2347,8 +2347,7 @@ static int btrfs_replay_log(struct btrfs_fs_info *fs_info, u64 bytenr = btrfs_super_log_root(disk_super); if (fs_devices->rw_devices == 0) { - printk(KERN_WARNING "BTRFS: log replay required " - "on RO media\n"); + btrfs_warn(fs_info, "log replay required on RO media"); return -EIO; } @@ -2363,12 +2362,12 @@ static int btrfs_replay_log(struct btrfs_fs_info *fs_info, log_tree_root->node = read_tree_block(tree_root, bytenr, fs_info->generation + 1); if (IS_ERR(log_tree_root->node)) { - printk(KERN_ERR "BTRFS: failed to read log tree\n"); + btrfs_warn(fs_info, "failed to read log tree"); ret = PTR_ERR(log_tree_root->node); kfree(log_tree_root); return ret; } else if (!extent_buffer_uptodate(log_tree_root->node)) { - printk(KERN_ERR "BTRFS: failed to read log tree\n"); + btrfs_err(fs_info, "failed to read log tree"); free_extent_buffer(log_tree_root->node); kfree(log_tree_root); return -EIO; @@ -3294,8 +3293,9 @@ static int write_dev_supers(struct btrfs_device *device, bh = __getblk(device->bdev, bytenr / 4096, BTRFS_SUPER_INFO_SIZE); if (!bh) { - printk(KERN_ERR "BTRFS: couldn't get super " - "buffer head for bytenr %Lu\n", bytenr); + btrfs_err(device->dev_root->fs_info, + "couldn't get super buffer head for bytenr %llu", + bytenr); errors++; continue; } diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index bb318b4e5dd0..c7a33913188b 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -5563,13 +5563,15 @@ void memcpy_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset, unsigned long src_i; if (src_offset + len > dst->len) { - printk(KERN_ERR "BTRFS: memmove bogus src_offset %lu move " - "len %lu dst len %lu\n", src_offset, len, dst->len); + btrfs_err(dst->fs_info, + "memmove bogus src_offset %lu move " + "len %lu dst len %lu", src_offset, len, dst->len); BUG_ON(1); } if (dst_offset + len > dst->len) { - printk(KERN_ERR "BTRFS: memmove bogus dst_offset %lu move " - "len %lu dst len %lu\n", dst_offset, len, dst->len); + btrfs_err(dst->fs_info, + "memmove bogus dst_offset %lu move " + "len %lu dst len %lu", dst_offset, len, dst->len); BUG_ON(1); } @@ -5609,13 +5611,13 @@ void memmove_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset, unsigned long src_i; if (src_offset + len > dst->len) { - printk(KERN_ERR "BTRFS: memmove bogus src_offset %lu move " - "len %lu len %lu\n", src_offset, len, dst->len); + btrfs_err(dst->fs_info, "memmove bogus src_offset %lu move " + "len %lu len %lu", src_offset, len, dst->len); BUG_ON(1); } if (dst_offset + len > dst->len) { - printk(KERN_ERR "BTRFS: memmove bogus dst_offset %lu move " - "len %lu len %lu\n", dst_offset, len, dst->len); + btrfs_err(dst->fs_info, "memmove bogus dst_offset %lu move " + "len %lu len %lu", dst_offset, len, dst->len); BUG_ON(1); } if (dst_offset < src_offset) { diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 8e9105af723e..2e520c635709 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1342,7 +1342,7 @@ int btrfs_defrag_file(struct inode *inode, struct file *file, break; if (btrfs_defrag_cancelled(root->fs_info)) { - printk(KERN_DEBUG "BTRFS: defrag_file cancelled\n"); + btrfs_debug(root->fs_info, "defrag_file cancelled"); ret = -EAGAIN; break; } @@ -2081,7 +2081,7 @@ static noinline int search_ioctl(struct inode *inode, key.offset = (u64)-1; root = btrfs_read_fs_root_no_name(info, &key); if (IS_ERR(root)) { - printk(KERN_ERR "BTRFS: could not find root %llu\n", + btrfs_err(info, "could not find root %llu", sk->tree_id); btrfs_free_path(path); return -ENOENT; @@ -2221,7 +2221,7 @@ static noinline int btrfs_search_path_in_tree(struct btrfs_fs_info *info, key.offset = (u64)-1; root = btrfs_read_fs_root_no_name(info, &key); if (IS_ERR(root)) { - printk(KERN_ERR "BTRFS: could not find root %llu\n", tree_id); + btrfs_err(info, "could not find root %llu", tree_id); ret = -ENOENT; goto out; } diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index 360a728a639f..42267d37bb94 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -45,12 +45,13 @@ static void btrfs_read_root_item(struct extent_buffer *eb, int slot, if (!need_reset && btrfs_root_generation(item) != btrfs_root_generation_v2(item)) { if (btrfs_root_generation_v2(item) != 0) { - printk(KERN_WARNING "BTRFS: mismatching " + btrfs_warn(eb->fs_info, + "mismatching " "generation and generation_v2 " "found in root item. This root " "was probably mounted with an " "older kernel. Resetting all " - "new fields.\n"); + "new fields."); } need_reset = 1; } diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index aa72bfd28f7d..4ea07c8cd6c2 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -2562,7 +2562,7 @@ verbose_printk("btrfs: send_create_inode %llu\n", ino); } else if (S_ISSOCK(mode)) { cmd = BTRFS_SEND_C_MKSOCK; } else { - printk(KERN_WARNING "btrfs: unexpected inode type %o", + btrfs_warn(sctx->send_root->fs_info, "unexpected inode type %o", (int)(mode & S_IFMT)); ret = -ENOTSUPP; goto out; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 4f80986dbf3c..7ad310cc3efb 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -2352,7 +2352,8 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path) root->fs_info->fsid); if (kobject_rename(&root->fs_info->fs_devices->super_kobj, fsid_buf)) - pr_warn("BTRFS: sysfs: failed to create fsid for sprout\n"); + btrfs_warn(root->fs_info, + "sysfs: failed to create fsid for sprout"); } root->fs_info->num_tolerated_disk_barrier_failures = -- cgit v1.2.3 From ee86395458072760d62e66aad10a5e9e8902b8cf Mon Sep 17 00:00:00 2001 From: David Sterba Date: Mon, 16 Feb 2015 19:41:40 +0100 Subject: btrfs: comment the rest of implicit barriers before waitqueue_active There are atomic operations that imply the barrier for waitqueue_active mixed in an if-condition. Signed-off-by: David Sterba --- fs/btrfs/delayed-inode.c | 4 ++++ fs/btrfs/disk-io.c | 3 +++ fs/btrfs/inode.c | 3 +++ fs/btrfs/locking.c | 9 +++++++++ fs/btrfs/volumes.c | 3 +++ 5 files changed, 22 insertions(+) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index a2ae42720a6a..e0941fbb913c 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -463,6 +463,10 @@ static int __btrfs_add_delayed_deletion_item(struct btrfs_delayed_node *node, static void finish_one_item(struct btrfs_delayed_root *delayed_root) { int seq = atomic_inc_return(&delayed_root->items_seq); + + /* + * atomic_dec_return implies a barrier for waitqueue_active + */ if ((atomic_dec_return(&delayed_root->items) < BTRFS_DELAYED_BACKGROUND || seq % BTRFS_DELAYED_BATCH == 0) && waitqueue_active(&delayed_root->wait)) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 295795aebe0b..379526ffd84d 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -802,6 +802,9 @@ static void run_one_async_done(struct btrfs_work *work) limit = btrfs_async_submit_limit(fs_info); limit = limit * 2 / 3; + /* + * atomic_dec_return implies a barrier for waitqueue_active + */ if (atomic_dec_return(&fs_info->nr_async_submits) < limit && waitqueue_active(&fs_info->async_submit_wait)) wake_up(&fs_info->async_submit_wait); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 611b66d73e80..7be4abe25e06 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1096,6 +1096,9 @@ static noinline void async_cow_submit(struct btrfs_work *work) nr_pages = (async_cow->end - async_cow->start + PAGE_CACHE_SIZE) >> PAGE_CACHE_SHIFT; + /* + * atomic_sub_return implies a barrier for waitqueue_active + */ if (atomic_sub_return(nr_pages, &root->fs_info->async_delalloc_pages) < 5 * 1024 * 1024 && waitqueue_active(&root->fs_info->async_submit_wait)) diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c index 03f8630dbaf2..8077461fc56a 100644 --- a/fs/btrfs/locking.c +++ b/fs/btrfs/locking.c @@ -79,6 +79,9 @@ void btrfs_clear_lock_blocking_rw(struct extent_buffer *eb, int rw) write_lock(&eb->lock); WARN_ON(atomic_read(&eb->spinning_writers)); atomic_inc(&eb->spinning_writers); + /* + * atomic_dec_and_test implies a barrier for waitqueue_active + */ if (atomic_dec_and_test(&eb->blocking_writers) && waitqueue_active(&eb->write_lock_wq)) wake_up(&eb->write_lock_wq); @@ -86,6 +89,9 @@ void btrfs_clear_lock_blocking_rw(struct extent_buffer *eb, int rw) BUG_ON(atomic_read(&eb->blocking_readers) == 0); read_lock(&eb->lock); atomic_inc(&eb->spinning_readers); + /* + * atomic_dec_and_test implies a barrier for waitqueue_active + */ if (atomic_dec_and_test(&eb->blocking_readers) && waitqueue_active(&eb->read_lock_wq)) wake_up(&eb->read_lock_wq); @@ -229,6 +235,9 @@ void btrfs_tree_read_unlock_blocking(struct extent_buffer *eb) } btrfs_assert_tree_read_locked(eb); WARN_ON(atomic_read(&eb->blocking_readers) == 0); + /* + * atomic_dec_and_test implies a barrier for waitqueue_active + */ if (atomic_dec_and_test(&eb->blocking_readers) && waitqueue_active(&eb->read_lock_wq)) wake_up(&eb->read_lock_wq); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 6fc735869c18..ff3527192409 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -345,6 +345,9 @@ loop_lock: pending = pending->bi_next; cur->bi_next = NULL; + /* + * atomic_dec_return implies a barrier for waitqueue_active + */ if (atomic_dec_return(&fs_info->nr_async_bios) < limit && waitqueue_active(&fs_info->async_submit_wait)) wake_up(&fs_info->async_submit_wait); -- cgit v1.2.3 From 8789f4fe608922f484369382a8e507ca12df7f4e Mon Sep 17 00:00:00 2001 From: Zhao Lei Date: Tue, 15 Sep 2015 21:08:07 +0800 Subject: btrfs: use btrfs_raid_array for btrfs_get_num_tolerated_disk_barrier_failures() btrfs_raid_array[] is used to define all raid attributes, use it to get tolerated_failures in btrfs_get_num_tolerated_disk_barrier_failures(), instead of complex condition in function. It can make code simple and auto-support other possible raid-type in future. Reviewed-by: David Sterba Signed-off-by: Zhao Lei Signed-off-by: David Sterba --- fs/btrfs/disk-io.c | 35 ++++++++++++++++++++++------------- fs/btrfs/volumes.c | 7 +++++++ fs/btrfs/volumes.h | 1 + 3 files changed, 30 insertions(+), 13 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 1e60d00d4ea7..322fd6ded723 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3449,22 +3449,31 @@ static int barrier_all_devices(struct btrfs_fs_info *info) int btrfs_get_num_tolerated_disk_barrier_failures(u64 flags) { - if ((flags & (BTRFS_BLOCK_GROUP_DUP | - BTRFS_BLOCK_GROUP_RAID0 | - BTRFS_AVAIL_ALLOC_BIT_SINGLE)) || - ((flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) == 0)) - return 0; + int raid_type; + int min_tolerated = INT_MAX; - if (flags & (BTRFS_BLOCK_GROUP_RAID1 | - BTRFS_BLOCK_GROUP_RAID5 | - BTRFS_BLOCK_GROUP_RAID10)) - return 1; + if ((flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) == 0 || + (flags & BTRFS_AVAIL_ALLOC_BIT_SINGLE)) + min_tolerated = min(min_tolerated, + btrfs_raid_array[BTRFS_RAID_SINGLE]. + tolerated_failures); - if (flags & BTRFS_BLOCK_GROUP_RAID6) - return 2; + for (raid_type = 0; raid_type < BTRFS_NR_RAID_TYPES; raid_type++) { + if (raid_type == BTRFS_RAID_SINGLE) + continue; + if (!(flags & btrfs_raid_group[raid_type])) + continue; + min_tolerated = min(min_tolerated, + btrfs_raid_array[raid_type]. + tolerated_failures); + } - pr_warn("BTRFS: unknown raid type: %llu\n", flags); - return 0; + if (min_tolerated == INT_MAX) { + pr_warn("BTRFS: unknown raid flag: %llu\n", flags); + min_tolerated = 0; + } + + return min_tolerated; } int btrfs_calc_num_tolerated_disk_barrier_failures( diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 2a65d2d45410..7b533909d006 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -48,6 +48,7 @@ const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = { .dev_stripes = 1, .devs_max = 0, /* 0 == as many as possible */ .devs_min = 4, + .tolerated_failures = 1, .devs_increment = 2, .ncopies = 2, }, @@ -56,6 +57,7 @@ const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = { .dev_stripes = 1, .devs_max = 2, .devs_min = 2, + .tolerated_failures = 1, .devs_increment = 2, .ncopies = 2, }, @@ -64,6 +66,7 @@ const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = { .dev_stripes = 2, .devs_max = 1, .devs_min = 1, + .tolerated_failures = 0, .devs_increment = 1, .ncopies = 2, }, @@ -72,6 +75,7 @@ const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = { .dev_stripes = 1, .devs_max = 0, .devs_min = 2, + .tolerated_failures = 0, .devs_increment = 1, .ncopies = 1, }, @@ -80,6 +84,7 @@ const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = { .dev_stripes = 1, .devs_max = 1, .devs_min = 1, + .tolerated_failures = 0, .devs_increment = 1, .ncopies = 1, }, @@ -88,6 +93,7 @@ const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = { .dev_stripes = 1, .devs_max = 0, .devs_min = 2, + .tolerated_failures = 1, .devs_increment = 1, .ncopies = 2, }, @@ -96,6 +102,7 @@ const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = { .dev_stripes = 1, .devs_max = 0, .devs_min = 3, + .tolerated_failures = 2, .devs_increment = 1, .ncopies = 3, }, diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 75d6083d9b3b..04ff0efe2f58 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -334,6 +334,7 @@ struct btrfs_raid_attr { int dev_stripes; /* stripes per dev */ int devs_max; /* max devs to use */ int devs_min; /* min devs needed */ + int tolerated_failures; /* max tolerated fail devs */ int devs_increment; /* ndevs has to be a multiple of this */ int ncopies; /* how many copies to data has */ }; -- cgit v1.2.3 From 55eeaf0578038c40baaf3cf9408c23e42cd2a2b8 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Tue, 8 Sep 2015 17:08:38 +0800 Subject: btrfs: qgroup: Introduce new functions to reserve/free metadata Introduce new functions btrfs_qgroup_reserve/free_meta() to reserve/free metadata reserved space. Signed-off-by: Qu Wenruo Signed-off-by: Chris Mason --- fs/btrfs/ctree.h | 3 +++ fs/btrfs/disk-io.c | 1 + fs/btrfs/qgroup.c | 40 ++++++++++++++++++++++++++++++++++++++++ fs/btrfs/qgroup.h | 4 ++++ 4 files changed, 48 insertions(+) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 49bc792108b9..9df8f01de4df 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1943,6 +1943,9 @@ struct btrfs_root { int send_in_progress; struct btrfs_subvolume_writers *subv_writers; atomic_t will_be_snapshoted; + + /* For qgroup metadata space reserve */ + atomic_t qgroup_meta_rsv; }; struct btrfs_ioctl_defrag_range_args { diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index bcbb596d9695..0e0544e0e20b 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1267,6 +1267,7 @@ static void __setup_root(u32 nodesize, u32 sectorsize, u32 stripesize, atomic_set(&root->orphan_inodes, 0); atomic_set(&root->refs, 1); atomic_set(&root->will_be_snapshoted, 0); + atomic_set(&root->qgroup_meta_rsv, 0); root->log_transid = 0; root->log_transid_committed = -1; root->last_log_commit = 0; diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 75d8e584c3e5..897a49d71638 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -2594,3 +2594,43 @@ int btrfs_qgroup_release_data(struct inode *inode, u64 start, u64 len) { return __btrfs_qgroup_release_data(inode, start, len, 0); } + +int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes) +{ + int ret; + + if (!root->fs_info->quota_enabled || !is_fstree(root->objectid) || + num_bytes == 0) + return 0; + + BUG_ON(num_bytes != round_down(num_bytes, root->nodesize)); + ret = btrfs_qgroup_reserve(root, num_bytes); + if (ret < 0) + return ret; + atomic_add(num_bytes, &root->qgroup_meta_rsv); + return ret; +} + +void btrfs_qgroup_free_meta_all(struct btrfs_root *root) +{ + int reserved; + + if (!root->fs_info->quota_enabled || !is_fstree(root->objectid)) + return; + + reserved = atomic_xchg(&root->qgroup_meta_rsv, 0); + if (reserved == 0) + return; + btrfs_qgroup_free(root, reserved); +} + +void btrfs_qgroup_free_meta(struct btrfs_root *root, int num_bytes) +{ + if (!root->fs_info->quota_enabled || !is_fstree(root->objectid)) + return; + + BUG_ON(num_bytes != round_down(num_bytes, root->nodesize)); + WARN_ON(atomic_read(&root->qgroup_meta_rsv) < num_bytes); + atomic_sub(num_bytes, &root->qgroup_meta_rsv); + btrfs_qgroup_free(root, num_bytes); +} diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h index 80924aeceb09..7d1c87cd3c78 100644 --- a/fs/btrfs/qgroup.h +++ b/fs/btrfs/qgroup.h @@ -101,4 +101,8 @@ int btrfs_verify_qgroup_counts(struct btrfs_fs_info *fs_info, u64 qgroupid, int btrfs_qgroup_reserve_data(struct inode *inode, u64 start, u64 len); int btrfs_qgroup_release_data(struct inode *inode, u64 start, u64 len); int btrfs_qgroup_free_data(struct inode *inode, u64 start, u64 len); + +int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes); +void btrfs_qgroup_free_meta_all(struct btrfs_root *root); +void btrfs_qgroup_free_meta(struct btrfs_root *root, int num_bytes); #endif /* __BTRFS_QGROUP__ */ -- cgit v1.2.3 From 161c3549b45aeef05451b6822d8aaaf39c7bedce Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Thu, 24 Sep 2015 16:17:39 -0400 Subject: Btrfs: change how we wait for pending ordered extents We have a mechanism to make sure we don't lose updates for ordered extents that were logged in the transaction that is currently running. We add the ordered extent to a transaction list and then the transaction waits on all the ordered extents in that list. However are substantially large file systems this list can be extremely large, and can give us soft lockups, since the ordered extents don't remove themselves from the list when they do complete. To fix this we simply add a counter to the transaction that is incremented any time we have a logged extent that needs to be completed in the current transaction. Then when the ordered extent finally completes it decrements the per transaction counter and wakes up the transaction if we are the last ones. This will eliminate the softlockup. Thanks, Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/disk-io.c | 20 ---------------- fs/btrfs/ordered-data.c | 64 ++++++++++++++++++++++++++++++++++++++----------- fs/btrfs/ordered-data.h | 2 ++ fs/btrfs/transaction.c | 34 +++++--------------------- fs/btrfs/transaction.h | 4 ++-- 5 files changed, 60 insertions(+), 64 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index bcbb596d9695..dceabb13ddc4 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -4326,25 +4326,6 @@ again: return 0; } -static void btrfs_free_pending_ordered(struct btrfs_transaction *cur_trans, - struct btrfs_fs_info *fs_info) -{ - struct btrfs_ordered_extent *ordered; - - spin_lock(&fs_info->trans_lock); - while (!list_empty(&cur_trans->pending_ordered)) { - ordered = list_first_entry(&cur_trans->pending_ordered, - struct btrfs_ordered_extent, - trans_list); - list_del_init(&ordered->trans_list); - spin_unlock(&fs_info->trans_lock); - - btrfs_put_ordered_extent(ordered); - spin_lock(&fs_info->trans_lock); - } - spin_unlock(&fs_info->trans_lock); -} - void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans, struct btrfs_root *root) { @@ -4356,7 +4337,6 @@ void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans, cur_trans->state = TRANS_STATE_UNBLOCKED; wake_up(&root->fs_info->transaction_wait); - btrfs_free_pending_ordered(cur_trans, root->fs_info); btrfs_destroy_delayed_inodes(root); btrfs_assert_delayed_root_empty(root); diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 071005f008c1..8c27292ea9ea 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -490,15 +490,16 @@ void btrfs_wait_logged_extents(struct btrfs_trans_handle *trans, spin_lock_irq(&log->log_extents_lock[index]); while (!list_empty(&log->logged_list[index])) { + struct inode *inode; ordered = list_first_entry(&log->logged_list[index], struct btrfs_ordered_extent, log_list); list_del_init(&ordered->log_list); + inode = ordered->inode; spin_unlock_irq(&log->log_extents_lock[index]); if (!test_bit(BTRFS_ORDERED_IO_DONE, &ordered->flags) && !test_bit(BTRFS_ORDERED_DIRECT, &ordered->flags)) { - struct inode *inode = ordered->inode; u64 start = ordered->file_offset; u64 end = ordered->file_offset + ordered->len - 1; @@ -509,20 +510,25 @@ void btrfs_wait_logged_extents(struct btrfs_trans_handle *trans, &ordered->flags)); /* - * If our ordered extent completed it means it updated the - * fs/subvol and csum trees already, so no need to make the - * current transaction's commit wait for it, as we end up - * holding memory unnecessarily and delaying the inode's iput - * until the transaction commit (we schedule an iput for the - * inode when the ordered extent's refcount drops to 0), which - * prevents it from being evictable until the transaction - * commits. + * In order to keep us from losing our ordered extent + * information when committing the transaction we have to make + * sure that any logged extents are completed when we go to + * commit the transaction. To do this we simply increase the + * current transactions pending_ordered counter and decrement it + * when the ordered extent completes. */ - if (test_bit(BTRFS_ORDERED_COMPLETE, &ordered->flags)) - btrfs_put_ordered_extent(ordered); - else - list_add_tail(&ordered->trans_list, &trans->ordered); - + if (!test_bit(BTRFS_ORDERED_COMPLETE, &ordered->flags)) { + struct btrfs_ordered_inode_tree *tree; + + tree = &BTRFS_I(inode)->ordered_tree; + spin_lock_irq(&tree->lock); + if (!test_bit(BTRFS_ORDERED_COMPLETE, &ordered->flags)) { + set_bit(BTRFS_ORDERED_PENDING, &ordered->flags); + atomic_inc(&trans->transaction->pending_ordered); + } + spin_unlock_irq(&tree->lock); + } + btrfs_put_ordered_extent(ordered); spin_lock_irq(&log->log_extents_lock[index]); } spin_unlock_irq(&log->log_extents_lock[index]); @@ -584,6 +590,7 @@ void btrfs_remove_ordered_extent(struct inode *inode, struct btrfs_ordered_inode_tree *tree; struct btrfs_root *root = BTRFS_I(inode)->root; struct rb_node *node; + bool dec_pending_ordered = false; tree = &BTRFS_I(inode)->ordered_tree; spin_lock_irq(&tree->lock); @@ -593,8 +600,37 @@ void btrfs_remove_ordered_extent(struct inode *inode, if (tree->last == node) tree->last = NULL; set_bit(BTRFS_ORDERED_COMPLETE, &entry->flags); + if (test_and_clear_bit(BTRFS_ORDERED_PENDING, &entry->flags)) + dec_pending_ordered = true; spin_unlock_irq(&tree->lock); + /* + * The current running transaction is waiting on us, we need to let it + * know that we're complete and wake it up. + */ + if (dec_pending_ordered) { + struct btrfs_transaction *trans; + + /* + * The checks for trans are just a formality, it should be set, + * but if it isn't we don't want to deref/assert under the spin + * lock, so be nice and check if trans is set, but ASSERT() so + * if it isn't set a developer will notice. + */ + spin_lock(&root->fs_info->trans_lock); + trans = root->fs_info->running_transaction; + if (trans) + atomic_inc(&trans->use_count); + spin_unlock(&root->fs_info->trans_lock); + + ASSERT(trans); + if (trans) { + if (atomic_dec_and_test(&trans->pending_ordered)) + wake_up(&trans->pending_wait); + btrfs_put_transaction(trans); + } + } + spin_lock(&root->ordered_extent_lock); list_del_init(&entry->root_extent_list); root->nr_ordered_extents--; diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h index 7176cc0fe43f..23c96059cef2 100644 --- a/fs/btrfs/ordered-data.h +++ b/fs/btrfs/ordered-data.h @@ -73,6 +73,8 @@ struct btrfs_ordered_sum { #define BTRFS_ORDERED_LOGGED 10 /* Set when we've waited on this ordered extent * in the logging code. */ +#define BTRFS_ORDERED_PENDING 11 /* We are waiting for this ordered extent to + * complete in the current transaction. */ struct btrfs_ordered_extent { /* logical offset in the file */ u64 file_offset; diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 9354e7a1247f..68a56c3cc555 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -232,6 +232,7 @@ loop: extwriter_counter_init(cur_trans, type); init_waitqueue_head(&cur_trans->writer_wait); init_waitqueue_head(&cur_trans->commit_wait); + init_waitqueue_head(&cur_trans->pending_wait); cur_trans->state = TRANS_STATE_RUNNING; /* * One for this trans handle, one so it will live on until we @@ -239,6 +240,7 @@ loop: */ atomic_set(&cur_trans->use_count, 2); cur_trans->have_free_bgs = 0; + atomic_set(&cur_trans->pending_ordered, 0); cur_trans->start_time = get_seconds(); cur_trans->dirty_bg_run = 0; @@ -266,7 +268,6 @@ loop: INIT_LIST_HEAD(&cur_trans->pending_snapshots); INIT_LIST_HEAD(&cur_trans->pending_chunks); INIT_LIST_HEAD(&cur_trans->switch_commits); - INIT_LIST_HEAD(&cur_trans->pending_ordered); INIT_LIST_HEAD(&cur_trans->dirty_bgs); INIT_LIST_HEAD(&cur_trans->io_bgs); INIT_LIST_HEAD(&cur_trans->dropped_roots); @@ -551,7 +552,6 @@ again: h->can_flush_pending_bgs = true; INIT_LIST_HEAD(&h->qgroup_ref_list); INIT_LIST_HEAD(&h->new_bgs); - INIT_LIST_HEAD(&h->ordered); smp_mb(); if (cur_trans->state >= TRANS_STATE_BLOCKED && @@ -784,12 +784,6 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans, if (!list_empty(&trans->new_bgs)) btrfs_create_pending_block_groups(trans, root); - if (!list_empty(&trans->ordered)) { - spin_lock(&info->trans_lock); - list_splice_init(&trans->ordered, &cur_trans->pending_ordered); - spin_unlock(&info->trans_lock); - } - trans->delayed_ref_updates = 0; if (!trans->sync) { must_run_delayed_refs = @@ -1788,25 +1782,10 @@ static inline void btrfs_wait_delalloc_flush(struct btrfs_fs_info *fs_info) } static inline void -btrfs_wait_pending_ordered(struct btrfs_transaction *cur_trans, - struct btrfs_fs_info *fs_info) +btrfs_wait_pending_ordered(struct btrfs_transaction *cur_trans) { - struct btrfs_ordered_extent *ordered; - - spin_lock(&fs_info->trans_lock); - while (!list_empty(&cur_trans->pending_ordered)) { - ordered = list_first_entry(&cur_trans->pending_ordered, - struct btrfs_ordered_extent, - trans_list); - list_del_init(&ordered->trans_list); - spin_unlock(&fs_info->trans_lock); - - wait_event(ordered->wait, test_bit(BTRFS_ORDERED_COMPLETE, - &ordered->flags)); - btrfs_put_ordered_extent(ordered); - spin_lock(&fs_info->trans_lock); - } - spin_unlock(&fs_info->trans_lock); + wait_event(cur_trans->pending_wait, + atomic_read(&cur_trans->pending_ordered) == 0); } int btrfs_commit_transaction(struct btrfs_trans_handle *trans, @@ -1890,7 +1869,6 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, } spin_lock(&root->fs_info->trans_lock); - list_splice_init(&trans->ordered, &cur_trans->pending_ordered); if (cur_trans->state >= TRANS_STATE_COMMIT_START) { spin_unlock(&root->fs_info->trans_lock); atomic_inc(&cur_trans->use_count); @@ -1949,7 +1927,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, btrfs_wait_delalloc_flush(root->fs_info); - btrfs_wait_pending_ordered(cur_trans, root->fs_info); + btrfs_wait_pending_ordered(cur_trans); btrfs_scrub_pause(root); /* diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index db6bfd92f0ea..bf7b1ddf5993 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -46,6 +46,7 @@ struct btrfs_transaction { */ atomic_t num_writers; atomic_t use_count; + atomic_t pending_ordered; /* * true if there is free bgs operations in this transaction @@ -59,9 +60,9 @@ struct btrfs_transaction { unsigned long start_time; wait_queue_head_t writer_wait; wait_queue_head_t commit_wait; + wait_queue_head_t pending_wait; struct list_head pending_snapshots; struct list_head pending_chunks; - struct list_head pending_ordered; struct list_head switch_commits; struct list_head dirty_bgs; struct list_head io_bgs; @@ -129,7 +130,6 @@ struct btrfs_trans_handle { */ struct btrfs_root *root; struct seq_list delayed_ref_elem; - struct list_head ordered; struct list_head qgroup_ref_list; struct list_head new_bgs; }; -- cgit v1.2.3 From 696249132158014d594896df3a81390616069c5c Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Mon, 26 Oct 2015 15:06:19 +0900 Subject: btrfs: clear PF_NOFREEZE in cleaner_kthread() cleaner_kthread() kthread calls try_to_freeze() at the beginning of every cleanup attempt. This operation can't ever succeed though, as the kthread hasn't marked itself as freezable. Before (hopefully eventually) kthread freezing gets converted to fileystem freezing, we'd rather mark cleaner_kthread() freezable (as my understanding is that it can generate filesystem I/O during suspend). Signed-off-by: Jiri Kosina Signed-off-by: Chris Mason --- fs/btrfs/disk-io.c | 1 + 1 file changed, 1 insertion(+) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 86a11a902fcf..2d4667594681 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1762,6 +1762,7 @@ static int cleaner_kthread(void *arg) int again; struct btrfs_trans_handle *trans; + set_freezable(); do { again = 0; -- cgit v1.2.3 From 7343dd61fd1b57c40cc06a5b5b5386df7f73c3ac Mon Sep 17 00:00:00 2001 From: Justin Maggard Date: Wed, 4 Nov 2015 15:56:16 -0800 Subject: btrfs: qgroup: exit the rescan worker during umount I was hitting a consistent NULL pointer dereference during shutdown that showed the trace running through end_workqueue_bio(). I traced it back to the endio_meta_workers workqueue being poked after it had already been destroyed. Eventually I found that the root cause was a qgroup rescan that was still in progress while we were stopping all the btrfs workers. Currently we explicitly pause balance and scrub operations in close_ctree(), but we do nothing to stop the qgroup rescan. We should probably be doing the same for qgroup rescan, but that's a much larger change. This small change is good enough to allow me to unmount without crashing. Signed-off-by: Justin Maggard Reviewed-by: Filipe Manana --- fs/btrfs/disk-io.c | 3 +++ fs/btrfs/qgroup.c | 9 ++++++--- 2 files changed, 9 insertions(+), 3 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 2d4667594681..1eb08393bff0 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3780,6 +3780,9 @@ void close_ctree(struct btrfs_root *root) fs_info->closing = 1; smp_mb(); + /* wait for the qgroup rescan worker to stop */ + btrfs_qgroup_wait_for_completion(fs_info); + /* wait for the uuid_scan task to finish */ down(&fs_info->uuid_tree_rescan_sem); /* avoid complains from lockdep et al., set sem back to initial state */ diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 46476c226395..75c0249702df 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -2286,7 +2286,7 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work) goto out; err = 0; - while (!err) { + while (!err && !btrfs_fs_closing(fs_info)) { trans = btrfs_start_transaction(fs_info->fs_root, 0); if (IS_ERR(trans)) { err = PTR_ERR(trans); @@ -2307,7 +2307,8 @@ out: btrfs_free_path(path); mutex_lock(&fs_info->qgroup_rescan_lock); - fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_RESCAN; + if (!btrfs_fs_closing(fs_info)) + fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_RESCAN; if (err > 0 && fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT) { @@ -2336,7 +2337,9 @@ out: } btrfs_end_transaction(trans, fs_info->quota_root); - if (err >= 0) { + if (btrfs_fs_closing(fs_info)) { + btrfs_info(fs_info, "qgroup scan paused"); + } else if (err >= 0) { btrfs_info(fs_info, "qgroup scan completed%s", err > 0 ? " (inconsistency flag cleared)" : ""); } else { -- cgit v1.2.3 From d0164adc89f6bb374d304ffcc375c6d2652fe67d Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Fri, 6 Nov 2015 16:28:21 -0800 Subject: mm, page_alloc: distinguish between being unable to sleep, unwilling to sleep and avoiding waking kswapd __GFP_WAIT has been used to identify atomic context in callers that hold spinlocks or are in interrupts. They are expected to be high priority and have access one of two watermarks lower than "min" which can be referred to as the "atomic reserve". __GFP_HIGH users get access to the first lower watermark and can be called the "high priority reserve". Over time, callers had a requirement to not block when fallback options were available. Some have abused __GFP_WAIT leading to a situation where an optimisitic allocation with a fallback option can access atomic reserves. This patch uses __GFP_ATOMIC to identify callers that are truely atomic, cannot sleep and have no alternative. High priority users continue to use __GFP_HIGH. __GFP_DIRECT_RECLAIM identifies callers that can sleep and are willing to enter direct reclaim. __GFP_KSWAPD_RECLAIM to identify callers that want to wake kswapd for background reclaim. __GFP_WAIT is redefined as a caller that is willing to enter direct reclaim and wake kswapd for background reclaim. This patch then converts a number of sites o __GFP_ATOMIC is used by callers that are high priority and have memory pools for those requests. GFP_ATOMIC uses this flag. o Callers that have a limited mempool to guarantee forward progress clear __GFP_DIRECT_RECLAIM but keep __GFP_KSWAPD_RECLAIM. bio allocations fall into this category where kswapd will still be woken but atomic reserves are not used as there is a one-entry mempool to guarantee progress. o Callers that are checking if they are non-blocking should use the helper gfpflags_allow_blocking() where possible. This is because checking for __GFP_WAIT as was done historically now can trigger false positives. Some exceptions like dm-crypt.c exist where the code intent is clearer if __GFP_DIRECT_RECLAIM is used instead of the helper due to flag manipulations. o Callers that built their own GFP flags instead of starting with GFP_KERNEL and friends now also need to specify __GFP_KSWAPD_RECLAIM. The first key hazard to watch out for is callers that removed __GFP_WAIT and was depending on access to atomic reserves for inconspicuous reasons. In some cases it may be appropriate for them to use __GFP_HIGH. The second key hazard is callers that assembled their own combination of GFP flags instead of starting with something like GFP_KERNEL. They may now wish to specify __GFP_KSWAPD_RECLAIM. It's almost certainly harmless if it's missed in most cases as other activity will wake kswapd. Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Acked-by: Michal Hocko Acked-by: Johannes Weiner Cc: Christoph Lameter Cc: David Rientjes Cc: Vitaly Wool Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/vm/balance | 14 ++++--- arch/arm/mm/dma-mapping.c | 6 +-- arch/arm/xen/mm.c | 2 +- arch/arm64/mm/dma-mapping.c | 4 +- arch/x86/kernel/pci-dma.c | 2 +- block/bio.c | 26 ++++++------ block/blk-core.c | 16 ++++---- block/blk-ioc.c | 2 +- block/blk-mq-tag.c | 2 +- block/blk-mq.c | 6 +-- drivers/block/drbd/drbd_receiver.c | 3 +- drivers/block/osdblk.c | 2 +- drivers/connector/connector.c | 3 +- drivers/firewire/core-cdev.c | 2 +- drivers/gpu/drm/i915/i915_gem.c | 2 +- drivers/infiniband/core/sa_query.c | 2 +- drivers/iommu/amd_iommu.c | 2 +- drivers/iommu/intel-iommu.c | 2 +- drivers/md/dm-crypt.c | 6 +-- drivers/md/dm-kcopyd.c | 2 +- drivers/media/pci/solo6x10/solo6x10-v4l2-enc.c | 2 +- drivers/media/pci/solo6x10/solo6x10-v4l2.c | 2 +- drivers/media/pci/tw68/tw68-video.c | 2 +- drivers/mtd/mtdcore.c | 3 +- drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c | 2 +- drivers/staging/android/ion/ion_system_heap.c | 2 +- .../lustre/include/linux/libcfs/libcfs_private.h | 2 +- drivers/usb/host/u132-hcd.c | 2 +- drivers/video/fbdev/vermilion/vermilion.c | 2 +- fs/btrfs/disk-io.c | 2 +- fs/btrfs/extent_io.c | 14 +++---- fs/btrfs/volumes.c | 4 +- fs/ext4/super.c | 2 +- fs/fscache/cookie.c | 2 +- fs/fscache/page.c | 6 +-- fs/jbd2/transaction.c | 4 +- fs/nfs/file.c | 6 +-- fs/xfs/xfs_qm.c | 2 +- include/linux/gfp.h | 46 ++++++++++++++++------ include/linux/skbuff.h | 6 +-- include/net/sock.h | 2 +- include/trace/events/gfpflags.h | 5 ++- kernel/audit.c | 6 +-- kernel/cgroup.c | 2 +- kernel/locking/lockdep.c | 2 +- kernel/power/snapshot.c | 2 +- kernel/smp.c | 2 +- lib/idr.c | 4 +- lib/radix-tree.c | 10 ++--- mm/backing-dev.c | 2 +- mm/dmapool.c | 2 +- mm/memcontrol.c | 6 +-- mm/mempool.c | 10 ++--- mm/migrate.c | 2 +- mm/page_alloc.c | 43 ++++++++++++-------- mm/slab.c | 18 ++++----- mm/slub.c | 10 ++--- mm/vmalloc.c | 2 +- mm/vmscan.c | 4 +- mm/zswap.c | 5 ++- net/core/skbuff.c | 8 ++-- net/core/sock.c | 6 ++- net/netlink/af_netlink.c | 2 +- net/rds/ib_recv.c | 4 +- net/rxrpc/ar-connection.c | 2 +- net/sctp/associola.c | 2 +- 66 files changed, 210 insertions(+), 172 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/Documentation/vm/balance b/Documentation/vm/balance index c46e68cf9344..964595481af6 100644 --- a/Documentation/vm/balance +++ b/Documentation/vm/balance @@ -1,12 +1,14 @@ Started Jan 2000 by Kanoj Sarcar -Memory balancing is needed for non __GFP_WAIT as well as for non -__GFP_IO allocations. +Memory balancing is needed for !__GFP_ATOMIC and !__GFP_KSWAPD_RECLAIM as +well as for non __GFP_IO allocations. -There are two reasons to be requesting non __GFP_WAIT allocations: -the caller can not sleep (typically intr context), or does not want -to incur cost overheads of page stealing and possible swap io for -whatever reasons. +The first reason why a caller may avoid reclaim is that the caller can not +sleep due to holding a spinlock or is in interrupt context. The second may +be that the caller is willing to fail the allocation without incurring the +overhead of page reclaim. This may happen for opportunistic high-order +allocation requests that have order-0 fallback options. In such cases, +the caller may also wish to avoid waking kswapd. __GFP_IO allocation requests are made to prevent file system deadlocks. diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index ad4eb2d26e16..e62400e5fb99 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -651,12 +651,12 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, if (nommu()) addr = __alloc_simple_buffer(dev, size, gfp, &page); - else if (dev_get_cma_area(dev) && (gfp & __GFP_WAIT)) + else if (dev_get_cma_area(dev) && (gfp & __GFP_DIRECT_RECLAIM)) addr = __alloc_from_contiguous(dev, size, prot, &page, caller, want_vaddr); else if (is_coherent) addr = __alloc_simple_buffer(dev, size, gfp, &page); - else if (!(gfp & __GFP_WAIT)) + else if (!gfpflags_allow_blocking(gfp)) addr = __alloc_from_pool(size, &page); else addr = __alloc_remap_buffer(dev, size, gfp, prot, &page, @@ -1363,7 +1363,7 @@ static void *arm_iommu_alloc_attrs(struct device *dev, size_t size, *handle = DMA_ERROR_CODE; size = PAGE_ALIGN(size); - if (!(gfp & __GFP_WAIT)) + if (!gfpflags_allow_blocking(gfp)) return __iommu_alloc_atomic(dev, size, handle); /* diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c index 7c34f7126b04..c5f9a9e3d1f3 100644 --- a/arch/arm/xen/mm.c +++ b/arch/arm/xen/mm.c @@ -25,7 +25,7 @@ unsigned long xen_get_swiotlb_free_pages(unsigned int order) { struct memblock_region *reg; - gfp_t flags = __GFP_NOWARN; + gfp_t flags = __GFP_NOWARN|__GFP_KSWAPD_RECLAIM; for_each_memblock(memory, reg) { if (reg->base < (phys_addr_t)0xffffffff) { diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 6320361d8d4c..bb4bf6a06ad6 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -100,7 +100,7 @@ static void *__dma_alloc_coherent(struct device *dev, size_t size, if (IS_ENABLED(CONFIG_ZONE_DMA) && dev->coherent_dma_mask <= DMA_BIT_MASK(32)) flags |= GFP_DMA; - if (dev_get_cma_area(dev) && (flags & __GFP_WAIT)) { + if (dev_get_cma_area(dev) && gfpflags_allow_blocking(flags)) { struct page *page; void *addr; @@ -148,7 +148,7 @@ static void *__dma_alloc(struct device *dev, size_t size, size = PAGE_ALIGN(size); - if (!coherent && !(flags & __GFP_WAIT)) { + if (!coherent && !gfpflags_allow_blocking(flags)) { struct page *page = NULL; void *addr = __alloc_from_pool(size, &page, flags); diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index cd99433b8ba1..6ba014c61d62 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -90,7 +90,7 @@ void *dma_generic_alloc_coherent(struct device *dev, size_t size, again: page = NULL; /* CMA can be used only in the context which permits sleeping */ - if (flag & __GFP_WAIT) { + if (gfpflags_allow_blocking(flag)) { page = dma_alloc_from_contiguous(dev, count, get_order(size)); if (page && page_to_phys(page) + size > dma_mask) { dma_release_from_contiguous(dev, page, count); diff --git a/block/bio.c b/block/bio.c index ad3f276d74bc..4f184d938942 100644 --- a/block/bio.c +++ b/block/bio.c @@ -211,7 +211,7 @@ fallback: bvl = mempool_alloc(pool, gfp_mask); } else { struct biovec_slab *bvs = bvec_slabs + *idx; - gfp_t __gfp_mask = gfp_mask & ~(__GFP_WAIT | __GFP_IO); + gfp_t __gfp_mask = gfp_mask & ~(__GFP_DIRECT_RECLAIM | __GFP_IO); /* * Make this allocation restricted and don't dump info on @@ -221,11 +221,11 @@ fallback: __gfp_mask |= __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN; /* - * Try a slab allocation. If this fails and __GFP_WAIT + * Try a slab allocation. If this fails and __GFP_DIRECT_RECLAIM * is set, retry with the 1-entry mempool */ bvl = kmem_cache_alloc(bvs->slab, __gfp_mask); - if (unlikely(!bvl && (gfp_mask & __GFP_WAIT))) { + if (unlikely(!bvl && (gfp_mask & __GFP_DIRECT_RECLAIM))) { *idx = BIOVEC_MAX_IDX; goto fallback; } @@ -395,12 +395,12 @@ static void punt_bios_to_rescuer(struct bio_set *bs) * If @bs is NULL, uses kmalloc() to allocate the bio; else the allocation is * backed by the @bs's mempool. * - * When @bs is not NULL, if %__GFP_WAIT is set then bio_alloc will always be - * able to allocate a bio. This is due to the mempool guarantees. To make this - * work, callers must never allocate more than 1 bio at a time from this pool. - * Callers that need to allocate more than 1 bio must always submit the - * previously allocated bio for IO before attempting to allocate a new one. - * Failure to do so can cause deadlocks under memory pressure. + * When @bs is not NULL, if %__GFP_DIRECT_RECLAIM is set then bio_alloc will + * always be able to allocate a bio. This is due to the mempool guarantees. + * To make this work, callers must never allocate more than 1 bio at a time + * from this pool. Callers that need to allocate more than 1 bio must always + * submit the previously allocated bio for IO before attempting to allocate + * a new one. Failure to do so can cause deadlocks under memory pressure. * * Note that when running under generic_make_request() (i.e. any block * driver), bios are not submitted until after you return - see the code in @@ -459,13 +459,13 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs) * We solve this, and guarantee forward progress, with a rescuer * workqueue per bio_set. If we go to allocate and there are * bios on current->bio_list, we first try the allocation - * without __GFP_WAIT; if that fails, we punt those bios we - * would be blocking to the rescuer workqueue before we retry - * with the original gfp_flags. + * without __GFP_DIRECT_RECLAIM; if that fails, we punt those + * bios we would be blocking to the rescuer workqueue before + * we retry with the original gfp_flags. */ if (current->bio_list && !bio_list_empty(current->bio_list)) - gfp_mask &= ~__GFP_WAIT; + gfp_mask &= ~__GFP_DIRECT_RECLAIM; p = mempool_alloc(bs->bio_pool, gfp_mask); if (!p && gfp_mask != saved_gfp) { diff --git a/block/blk-core.c b/block/blk-core.c index 89eec7965870..9e32f0868e36 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1206,8 +1206,8 @@ rq_starved: * @bio: bio to allocate request for (can be %NULL) * @gfp_mask: allocation mask * - * Get a free request from @q. If %__GFP_WAIT is set in @gfp_mask, this - * function keeps retrying under memory pressure and fails iff @q is dead. + * Get a free request from @q. If %__GFP_DIRECT_RECLAIM is set in @gfp_mask, + * this function keeps retrying under memory pressure and fails iff @q is dead. * * Must be called with @q->queue_lock held and, * Returns ERR_PTR on failure, with @q->queue_lock held. @@ -1227,7 +1227,7 @@ retry: if (!IS_ERR(rq)) return rq; - if (!(gfp_mask & __GFP_WAIT) || unlikely(blk_queue_dying(q))) { + if (!gfpflags_allow_blocking(gfp_mask) || unlikely(blk_queue_dying(q))) { blk_put_rl(rl); return rq; } @@ -1305,11 +1305,11 @@ EXPORT_SYMBOL(blk_get_request); * BUG. * * WARNING: When allocating/cloning a bio-chain, careful consideration should be - * given to how you allocate bios. In particular, you cannot use __GFP_WAIT for - * anything but the first bio in the chain. Otherwise you risk waiting for IO - * completion of a bio that hasn't been submitted yet, thus resulting in a - * deadlock. Alternatively bios should be allocated using bio_kmalloc() instead - * of bio_alloc(), as that avoids the mempool deadlock. + * given to how you allocate bios. In particular, you cannot use + * __GFP_DIRECT_RECLAIM for anything but the first bio in the chain. Otherwise + * you risk waiting for IO completion of a bio that hasn't been submitted yet, + * thus resulting in a deadlock. Alternatively bios should be allocated using + * bio_kmalloc() instead of bio_alloc(), as that avoids the mempool deadlock. * If possible a big IO should be split into smaller parts when allocation * fails. Partial allocation should not be an error, or you risk a live-lock. */ diff --git a/block/blk-ioc.c b/block/blk-ioc.c index 1a27f45ec776..381cb50a673c 100644 --- a/block/blk-ioc.c +++ b/block/blk-ioc.c @@ -289,7 +289,7 @@ struct io_context *get_task_io_context(struct task_struct *task, { struct io_context *ioc; - might_sleep_if(gfp_flags & __GFP_WAIT); + might_sleep_if(gfpflags_allow_blocking(gfp_flags)); do { task_lock(task); diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index 60ac684c8b8c..a07ca3488d96 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -268,7 +268,7 @@ static int bt_get(struct blk_mq_alloc_data *data, if (tag != -1) return tag; - if (!(data->gfp & __GFP_WAIT)) + if (!gfpflags_allow_blocking(data->gfp)) return -1; bs = bt_wait_ptr(bt, hctx); diff --git a/block/blk-mq.c b/block/blk-mq.c index 1c27b3eaef64..68c0a3416b34 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -244,11 +244,11 @@ struct request *blk_mq_alloc_request(struct request_queue *q, int rw, gfp_t gfp, ctx = blk_mq_get_ctx(q); hctx = q->mq_ops->map_queue(q, ctx->cpu); - blk_mq_set_alloc_data(&alloc_data, q, gfp & ~__GFP_WAIT, + blk_mq_set_alloc_data(&alloc_data, q, gfp & ~__GFP_DIRECT_RECLAIM, reserved, ctx, hctx); rq = __blk_mq_alloc_request(&alloc_data, rw); - if (!rq && (gfp & __GFP_WAIT)) { + if (!rq && (gfp & __GFP_DIRECT_RECLAIM)) { __blk_mq_run_hw_queue(hctx); blk_mq_put_ctx(ctx); @@ -1186,7 +1186,7 @@ static struct request *blk_mq_map_request(struct request_queue *q, ctx = blk_mq_get_ctx(q); hctx = q->mq_ops->map_queue(q, ctx->cpu); blk_mq_set_alloc_data(&alloc_data, q, - __GFP_WAIT|GFP_ATOMIC, false, ctx, hctx); + __GFP_WAIT|__GFP_HIGH, false, ctx, hctx); rq = __blk_mq_alloc_request(&alloc_data, rw); ctx = alloc_data.ctx; hctx = alloc_data.hctx; diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index c097909c589c..b4b5680ac6ad 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -357,7 +357,8 @@ drbd_alloc_peer_req(struct drbd_peer_device *peer_device, u64 id, sector_t secto } if (has_payload && data_size) { - page = drbd_alloc_pages(peer_device, nr_pages, (gfp_mask & __GFP_WAIT)); + page = drbd_alloc_pages(peer_device, nr_pages, + gfpflags_allow_blocking(gfp_mask)); if (!page) goto fail; } diff --git a/drivers/block/osdblk.c b/drivers/block/osdblk.c index e22942596207..1b709a4e3b5e 100644 --- a/drivers/block/osdblk.c +++ b/drivers/block/osdblk.c @@ -271,7 +271,7 @@ static struct bio *bio_chain_clone(struct bio *old_chain, gfp_t gfpmask) goto err_out; tmp->bi_bdev = NULL; - gfpmask &= ~__GFP_WAIT; + gfpmask &= ~__GFP_DIRECT_RECLAIM; tmp->bi_next = NULL; if (!new_chain) diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c index 30f522848c73..d7373ca69c99 100644 --- a/drivers/connector/connector.c +++ b/drivers/connector/connector.c @@ -124,7 +124,8 @@ int cn_netlink_send_mult(struct cn_msg *msg, u16 len, u32 portid, u32 __group, if (group) return netlink_broadcast(dev->nls, skb, portid, group, gfp_mask); - return netlink_unicast(dev->nls, skb, portid, !(gfp_mask&__GFP_WAIT)); + return netlink_unicast(dev->nls, skb, portid, + !gfpflags_allow_blocking(gfp_mask)); } EXPORT_SYMBOL_GPL(cn_netlink_send_mult); diff --git a/drivers/firewire/core-cdev.c b/drivers/firewire/core-cdev.c index 2a3973a7c441..36a7c2d89a01 100644 --- a/drivers/firewire/core-cdev.c +++ b/drivers/firewire/core-cdev.c @@ -486,7 +486,7 @@ static int ioctl_get_info(struct client *client, union ioctl_arg *arg) static int add_client_resource(struct client *client, struct client_resource *resource, gfp_t gfp_mask) { - bool preload = !!(gfp_mask & __GFP_WAIT); + bool preload = gfpflags_allow_blocking(gfp_mask); unsigned long flags; int ret; diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 4d631a946481..d58cb9e034fe 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -2215,7 +2215,7 @@ i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj) */ mapping = file_inode(obj->base.filp)->i_mapping; gfp = mapping_gfp_mask(mapping); - gfp |= __GFP_NORETRY | __GFP_NOWARN | __GFP_NO_KSWAPD; + gfp |= __GFP_NORETRY | __GFP_NOWARN; gfp &= ~(__GFP_IO | __GFP_WAIT); sg = st->sgl; st->nents = 0; diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c index 8c014b33d8e0..59ab264c99c4 100644 --- a/drivers/infiniband/core/sa_query.c +++ b/drivers/infiniband/core/sa_query.c @@ -1083,7 +1083,7 @@ static void init_mad(struct ib_sa_mad *mad, struct ib_mad_agent *agent) static int send_mad(struct ib_sa_query *query, int timeout_ms, gfp_t gfp_mask) { - bool preload = !!(gfp_mask & __GFP_WAIT); + bool preload = gfpflags_allow_blocking(gfp_mask); unsigned long flags; int ret, id; diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 0d533bba4ad1..8b2be1e7714f 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -2668,7 +2668,7 @@ static void *alloc_coherent(struct device *dev, size_t size, page = alloc_pages(flag | __GFP_NOWARN, get_order(size)); if (!page) { - if (!(flag & __GFP_WAIT)) + if (!gfpflags_allow_blocking(flag)) return NULL; page = dma_alloc_from_contiguous(dev, size >> PAGE_SHIFT, diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 7cf80c1a8a16..f1042daef9ad 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -3647,7 +3647,7 @@ static void *intel_alloc_coherent(struct device *dev, size_t size, flags |= GFP_DMA32; } - if (flags & __GFP_WAIT) { + if (gfpflags_allow_blocking(flags)) { unsigned int count = size >> PAGE_SHIFT; page = dma_alloc_from_contiguous(dev, count, order); diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 3729b394432c..917d47e290ae 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -994,7 +994,7 @@ static struct bio *crypt_alloc_buffer(struct dm_crypt_io *io, unsigned size) struct bio_vec *bvec; retry: - if (unlikely(gfp_mask & __GFP_WAIT)) + if (unlikely(gfp_mask & __GFP_DIRECT_RECLAIM)) mutex_lock(&cc->bio_alloc_lock); clone = bio_alloc_bioset(GFP_NOIO, nr_iovecs, cc->bs); @@ -1010,7 +1010,7 @@ retry: if (!page) { crypt_free_buffer_pages(cc, clone); bio_put(clone); - gfp_mask |= __GFP_WAIT; + gfp_mask |= __GFP_DIRECT_RECLAIM; goto retry; } @@ -1027,7 +1027,7 @@ retry: } return_clone: - if (unlikely(gfp_mask & __GFP_WAIT)) + if (unlikely(gfp_mask & __GFP_DIRECT_RECLAIM)) mutex_unlock(&cc->bio_alloc_lock); return clone; diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c index 3a7cade5e27d..1452ed9aacb4 100644 --- a/drivers/md/dm-kcopyd.c +++ b/drivers/md/dm-kcopyd.c @@ -244,7 +244,7 @@ static int kcopyd_get_pages(struct dm_kcopyd_client *kc, *pages = NULL; do { - pl = alloc_pl(__GFP_NOWARN | __GFP_NORETRY); + pl = alloc_pl(__GFP_NOWARN | __GFP_NORETRY | __GFP_KSWAPD_RECLAIM); if (unlikely(!pl)) { /* Use reserved pages */ pl = kc->pages; diff --git a/drivers/media/pci/solo6x10/solo6x10-v4l2-enc.c b/drivers/media/pci/solo6x10/solo6x10-v4l2-enc.c index 1bd2fd47421f..4432fd69b7cb 100644 --- a/drivers/media/pci/solo6x10/solo6x10-v4l2-enc.c +++ b/drivers/media/pci/solo6x10/solo6x10-v4l2-enc.c @@ -1297,7 +1297,7 @@ static struct solo_enc_dev *solo_enc_alloc(struct solo_dev *solo_dev, solo_enc->vidq.ops = &solo_enc_video_qops; solo_enc->vidq.mem_ops = &vb2_dma_sg_memops; solo_enc->vidq.drv_priv = solo_enc; - solo_enc->vidq.gfp_flags = __GFP_DMA32; + solo_enc->vidq.gfp_flags = __GFP_DMA32 | __GFP_KSWAPD_RECLAIM; solo_enc->vidq.timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC; solo_enc->vidq.buf_struct_size = sizeof(struct solo_vb2_buf); solo_enc->vidq.lock = &solo_enc->lock; diff --git a/drivers/media/pci/solo6x10/solo6x10-v4l2.c b/drivers/media/pci/solo6x10/solo6x10-v4l2.c index 26df903585d7..f7ce493b1fee 100644 --- a/drivers/media/pci/solo6x10/solo6x10-v4l2.c +++ b/drivers/media/pci/solo6x10/solo6x10-v4l2.c @@ -678,7 +678,7 @@ int solo_v4l2_init(struct solo_dev *solo_dev, unsigned nr) solo_dev->vidq.mem_ops = &vb2_dma_contig_memops; solo_dev->vidq.drv_priv = solo_dev; solo_dev->vidq.timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC; - solo_dev->vidq.gfp_flags = __GFP_DMA32; + solo_dev->vidq.gfp_flags = __GFP_DMA32 | __GFP_KSWAPD_RECLAIM; solo_dev->vidq.buf_struct_size = sizeof(struct solo_vb2_buf); solo_dev->vidq.lock = &solo_dev->lock; ret = vb2_queue_init(&solo_dev->vidq); diff --git a/drivers/media/pci/tw68/tw68-video.c b/drivers/media/pci/tw68/tw68-video.c index 4c3293dcddbc..46642ef9151b 100644 --- a/drivers/media/pci/tw68/tw68-video.c +++ b/drivers/media/pci/tw68/tw68-video.c @@ -979,7 +979,7 @@ int tw68_video_init2(struct tw68_dev *dev, int video_nr) dev->vidq.ops = &tw68_video_qops; dev->vidq.mem_ops = &vb2_dma_sg_memops; dev->vidq.drv_priv = dev; - dev->vidq.gfp_flags = __GFP_DMA32; + dev->vidq.gfp_flags = __GFP_DMA32 | __GFP_KSWAPD_RECLAIM; dev->vidq.buf_struct_size = sizeof(struct tw68_buf); dev->vidq.lock = &dev->lock; dev->vidq.min_buffers_needed = 2; diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c index 8bbbb751bf45..2dfb291a47c6 100644 --- a/drivers/mtd/mtdcore.c +++ b/drivers/mtd/mtdcore.c @@ -1188,8 +1188,7 @@ EXPORT_SYMBOL_GPL(mtd_writev); */ void *mtd_kmalloc_up_to(const struct mtd_info *mtd, size_t *size) { - gfp_t flags = __GFP_NOWARN | __GFP_WAIT | - __GFP_NORETRY | __GFP_NO_KSWAPD; + gfp_t flags = __GFP_NOWARN | __GFP_DIRECT_RECLAIM | __GFP_NORETRY; size_t min_alloc = max_t(size_t, mtd->writesize, PAGE_SIZE); void *kbuf; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index 44173be5cbf0..f8d7a2f06950 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -691,7 +691,7 @@ static void *bnx2x_frag_alloc(const struct bnx2x_fastpath *fp, gfp_t gfp_mask) { if (fp->rx_frag_size) { /* GFP_KERNEL allocations are used only during initialization */ - if (unlikely(gfp_mask & __GFP_WAIT)) + if (unlikely(gfpflags_allow_blocking(gfp_mask))) return (void *)__get_free_page(gfp_mask); return netdev_alloc_frag(fp->rx_frag_size); diff --git a/drivers/staging/android/ion/ion_system_heap.c b/drivers/staging/android/ion/ion_system_heap.c index ada724aab3d5..d4c3e5512dd5 100644 --- a/drivers/staging/android/ion/ion_system_heap.c +++ b/drivers/staging/android/ion/ion_system_heap.c @@ -27,7 +27,7 @@ #include "ion_priv.h" static gfp_t high_order_gfp_flags = (GFP_HIGHUSER | __GFP_ZERO | __GFP_NOWARN | - __GFP_NORETRY) & ~__GFP_WAIT; + __GFP_NORETRY) & ~__GFP_DIRECT_RECLAIM; static gfp_t low_order_gfp_flags = (GFP_HIGHUSER | __GFP_ZERO | __GFP_NOWARN); static const unsigned int orders[] = {8, 4, 0}; static const int num_orders = ARRAY_SIZE(orders); diff --git a/drivers/staging/lustre/include/linux/libcfs/libcfs_private.h b/drivers/staging/lustre/include/linux/libcfs/libcfs_private.h index 6af733de69ca..f0b0423a716b 100644 --- a/drivers/staging/lustre/include/linux/libcfs/libcfs_private.h +++ b/drivers/staging/lustre/include/linux/libcfs/libcfs_private.h @@ -95,7 +95,7 @@ do { \ do { \ LASSERT(!in_interrupt() || \ ((size) <= LIBCFS_VMALLOC_SIZE && \ - ((mask) & __GFP_WAIT) == 0)); \ + !gfpflags_allow_blocking(mask))); \ } while (0) #define LIBCFS_ALLOC_POST(ptr, size) \ diff --git a/drivers/usb/host/u132-hcd.c b/drivers/usb/host/u132-hcd.c index 0a94895a358d..692ccc69345e 100644 --- a/drivers/usb/host/u132-hcd.c +++ b/drivers/usb/host/u132-hcd.c @@ -2244,7 +2244,7 @@ static int u132_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, { struct u132 *u132 = hcd_to_u132(hcd); if (irqs_disabled()) { - if (__GFP_WAIT & mem_flags) { + if (gfpflags_allow_blocking(mem_flags)) { printk(KERN_ERR "invalid context for function that might sleep\n"); return -EINVAL; } diff --git a/drivers/video/fbdev/vermilion/vermilion.c b/drivers/video/fbdev/vermilion/vermilion.c index 6b70d7f62b2f..1c1e95a0b8fa 100644 --- a/drivers/video/fbdev/vermilion/vermilion.c +++ b/drivers/video/fbdev/vermilion/vermilion.c @@ -99,7 +99,7 @@ static int vmlfb_alloc_vram_area(struct vram_area *va, unsigned max_order, * below the first 16MB. */ - flags = __GFP_DMA | __GFP_HIGH; + flags = __GFP_DMA | __GFP_HIGH | __GFP_KSWAPD_RECLAIM; va->logical = __get_free_pages(flags, --max_order); } while (va->logical == 0 && max_order > min_order); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 1e60d00d4ea7..c339d561e596 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2572,7 +2572,7 @@ int open_ctree(struct super_block *sb, fs_info->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL; fs_info->avg_delayed_ref_runtime = NSEC_PER_SEC >> 6; /* div by 64 */ /* readahead state */ - INIT_RADIX_TREE(&fs_info->reada_tree, GFP_NOFS & ~__GFP_WAIT); + INIT_RADIX_TREE(&fs_info->reada_tree, GFP_NOFS & ~__GFP_DIRECT_RECLAIM); spin_lock_init(&fs_info->reada_lock); fs_info->thread_pool_size = min_t(unsigned long, diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 3915c9473e94..032abfbebe76 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -594,7 +594,7 @@ int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, if (bits & (EXTENT_IOBITS | EXTENT_BOUNDARY)) clear = 1; again: - if (!prealloc && (mask & __GFP_WAIT)) { + if (!prealloc && gfpflags_allow_blocking(mask)) { /* * Don't care for allocation failure here because we might end * up not needing the pre-allocated extent state at all, which @@ -718,7 +718,7 @@ search_again: if (start > end) goto out; spin_unlock(&tree->lock); - if (mask & __GFP_WAIT) + if (gfpflags_allow_blocking(mask)) cond_resched(); goto again; } @@ -850,7 +850,7 @@ __set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, bits |= EXTENT_FIRST_DELALLOC; again: - if (!prealloc && (mask & __GFP_WAIT)) { + if (!prealloc && gfpflags_allow_blocking(mask)) { prealloc = alloc_extent_state(mask); BUG_ON(!prealloc); } @@ -1028,7 +1028,7 @@ search_again: if (start > end) goto out; spin_unlock(&tree->lock); - if (mask & __GFP_WAIT) + if (gfpflags_allow_blocking(mask)) cond_resched(); goto again; } @@ -1076,7 +1076,7 @@ int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, btrfs_debug_check_extent_io_range(tree, start, end); again: - if (!prealloc && (mask & __GFP_WAIT)) { + if (!prealloc && gfpflags_allow_blocking(mask)) { /* * Best effort, don't worry if extent state allocation fails * here for the first iteration. We might have a cached state @@ -1253,7 +1253,7 @@ search_again: if (start > end) goto out; spin_unlock(&tree->lock); - if (mask & __GFP_WAIT) + if (gfpflags_allow_blocking(mask)) cond_resched(); first_iteration = false; goto again; @@ -4319,7 +4319,7 @@ int try_release_extent_mapping(struct extent_map_tree *map, u64 start = page_offset(page); u64 end = start + PAGE_CACHE_SIZE - 1; - if ((mask & __GFP_WAIT) && + if (gfpflags_allow_blocking(mask) && page->mapping->host->i_size > 16 * 1024 * 1024) { u64 len; while (start <= end) { diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 6fc735869c18..e023919b4470 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -156,8 +156,8 @@ static struct btrfs_device *__alloc_device(void) spin_lock_init(&dev->reada_lock); atomic_set(&dev->reada_in_flight, 0); atomic_set(&dev->dev_stats_ccnt, 0); - INIT_RADIX_TREE(&dev->reada_zones, GFP_NOFS & ~__GFP_WAIT); - INIT_RADIX_TREE(&dev->reada_extents, GFP_NOFS & ~__GFP_WAIT); + INIT_RADIX_TREE(&dev->reada_zones, GFP_NOFS & ~__GFP_DIRECT_RECLAIM); + INIT_RADIX_TREE(&dev->reada_extents, GFP_NOFS & ~__GFP_DIRECT_RECLAIM); return dev; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index a63c7b0a10cf..49f6c78ee3af 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1058,7 +1058,7 @@ static int bdev_try_to_free_page(struct super_block *sb, struct page *page, return 0; if (journal) return jbd2_journal_try_to_free_buffers(journal, page, - wait & ~__GFP_WAIT); + wait & ~__GFP_DIRECT_RECLAIM); return try_to_free_buffers(page); } diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index d403c69bee08..4304072161aa 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -111,7 +111,7 @@ struct fscache_cookie *__fscache_acquire_cookie( /* radix tree insertion won't use the preallocation pool unless it's * told it may not wait */ - INIT_RADIX_TREE(&cookie->stores, GFP_NOFS & ~__GFP_WAIT); + INIT_RADIX_TREE(&cookie->stores, GFP_NOFS & ~__GFP_DIRECT_RECLAIM); switch (cookie->def->type) { case FSCACHE_COOKIE_TYPE_INDEX: diff --git a/fs/fscache/page.c b/fs/fscache/page.c index 483bbc613bf0..79483b3d8c6f 100644 --- a/fs/fscache/page.c +++ b/fs/fscache/page.c @@ -58,7 +58,7 @@ bool release_page_wait_timeout(struct fscache_cookie *cookie, struct page *page) /* * decide whether a page can be released, possibly by cancelling a store to it - * - we're allowed to sleep if __GFP_WAIT is flagged + * - we're allowed to sleep if __GFP_DIRECT_RECLAIM is flagged */ bool __fscache_maybe_release_page(struct fscache_cookie *cookie, struct page *page, @@ -122,7 +122,7 @@ page_busy: * allocator as the work threads writing to the cache may all end up * sleeping on memory allocation, so we may need to impose a timeout * too. */ - if (!(gfp & __GFP_WAIT) || !(gfp & __GFP_FS)) { + if (!(gfp & __GFP_DIRECT_RECLAIM) || !(gfp & __GFP_FS)) { fscache_stat(&fscache_n_store_vmscan_busy); return false; } @@ -132,7 +132,7 @@ page_busy: _debug("fscache writeout timeout page: %p{%lx}", page, page->index); - gfp &= ~__GFP_WAIT; + gfp &= ~__GFP_DIRECT_RECLAIM; goto try_again; } EXPORT_SYMBOL(__fscache_maybe_release_page); diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 6b8338ec2464..89463eee6791 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -1937,8 +1937,8 @@ out: * @journal: journal for operation * @page: to try and free * @gfp_mask: we use the mask to detect how hard should we try to release - * buffers. If __GFP_WAIT and __GFP_FS is set, we wait for commit code to - * release the buffers. + * buffers. If __GFP_DIRECT_RECLAIM and __GFP_FS is set, we wait for commit + * code to release the buffers. * * * For all the buffers on this page, diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 37f639d50af5..93e236429c5d 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -473,8 +473,8 @@ static int nfs_release_page(struct page *page, gfp_t gfp) dfprintk(PAGECACHE, "NFS: release_page(%p)\n", page); /* Always try to initiate a 'commit' if relevant, but only - * wait for it if __GFP_WAIT is set. Even then, only wait 1 - * second and only if the 'bdi' is not congested. + * wait for it if the caller allows blocking. Even then, + * only wait 1 second and only if the 'bdi' is not congested. * Waiting indefinitely can cause deadlocks when the NFS * server is on this machine, when a new TCP connection is * needed and in other rare cases. There is no particular @@ -484,7 +484,7 @@ static int nfs_release_page(struct page *page, gfp_t gfp) if (mapping) { struct nfs_server *nfss = NFS_SERVER(mapping->host); nfs_commit_inode(mapping->host, 0); - if ((gfp & __GFP_WAIT) && + if (gfpflags_allow_blocking(gfp) && !bdi_write_congested(&nfss->backing_dev_info)) { wait_on_page_bit_killable_timeout(page, PG_private, HZ); diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index eac9549efd52..587174fd4f2c 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -525,7 +525,7 @@ xfs_qm_shrink_scan( unsigned long freed; int error; - if ((sc->gfp_mask & (__GFP_FS|__GFP_WAIT)) != (__GFP_FS|__GFP_WAIT)) + if ((sc->gfp_mask & (__GFP_FS|__GFP_DIRECT_RECLAIM)) != (__GFP_FS|__GFP_DIRECT_RECLAIM)) return 0; INIT_LIST_HEAD(&isol.buffers); diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 440fca3e7e5d..b56e811b6f7c 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -29,12 +29,13 @@ struct vm_area_struct; #define ___GFP_NOMEMALLOC 0x10000u #define ___GFP_HARDWALL 0x20000u #define ___GFP_THISNODE 0x40000u -#define ___GFP_WAIT 0x80000u +#define ___GFP_ATOMIC 0x80000u #define ___GFP_NOACCOUNT 0x100000u #define ___GFP_NOTRACK 0x200000u -#define ___GFP_NO_KSWAPD 0x400000u +#define ___GFP_DIRECT_RECLAIM 0x400000u #define ___GFP_OTHER_NODE 0x800000u #define ___GFP_WRITE 0x1000000u +#define ___GFP_KSWAPD_RECLAIM 0x2000000u /* If the above are modified, __GFP_BITS_SHIFT may need updating */ /* @@ -71,7 +72,7 @@ struct vm_area_struct; * __GFP_MOVABLE: Flag that this page will be movable by the page migration * mechanism or reclaimed */ -#define __GFP_WAIT ((__force gfp_t)___GFP_WAIT) /* Can wait and reschedule? */ +#define __GFP_ATOMIC ((__force gfp_t)___GFP_ATOMIC) /* Caller cannot wait or reschedule */ #define __GFP_HIGH ((__force gfp_t)___GFP_HIGH) /* Should access emergency pools? */ #define __GFP_IO ((__force gfp_t)___GFP_IO) /* Can start physical IO? */ #define __GFP_FS ((__force gfp_t)___GFP_FS) /* Can call down to low-level FS? */ @@ -94,23 +95,37 @@ struct vm_area_struct; #define __GFP_NOACCOUNT ((__force gfp_t)___GFP_NOACCOUNT) /* Don't account to kmemcg */ #define __GFP_NOTRACK ((__force gfp_t)___GFP_NOTRACK) /* Don't track with kmemcheck */ -#define __GFP_NO_KSWAPD ((__force gfp_t)___GFP_NO_KSWAPD) #define __GFP_OTHER_NODE ((__force gfp_t)___GFP_OTHER_NODE) /* On behalf of other node */ #define __GFP_WRITE ((__force gfp_t)___GFP_WRITE) /* Allocator intends to dirty page */ +/* + * A caller that is willing to wait may enter direct reclaim and will + * wake kswapd to reclaim pages in the background until the high + * watermark is met. A caller may wish to clear __GFP_DIRECT_RECLAIM to + * avoid unnecessary delays when a fallback option is available but + * still allow kswapd to reclaim in the background. The kswapd flag + * can be cleared when the reclaiming of pages would cause unnecessary + * disruption. + */ +#define __GFP_WAIT ((__force gfp_t)(___GFP_DIRECT_RECLAIM|___GFP_KSWAPD_RECLAIM)) +#define __GFP_DIRECT_RECLAIM ((__force gfp_t)___GFP_DIRECT_RECLAIM) /* Caller can reclaim */ +#define __GFP_KSWAPD_RECLAIM ((__force gfp_t)___GFP_KSWAPD_RECLAIM) /* kswapd can wake */ + /* * This may seem redundant, but it's a way of annotating false positives vs. * allocations that simply cannot be supported (e.g. page tables). */ #define __GFP_NOTRACK_FALSE_POSITIVE (__GFP_NOTRACK) -#define __GFP_BITS_SHIFT 25 /* Room for N __GFP_FOO bits */ +#define __GFP_BITS_SHIFT 26 /* Room for N __GFP_FOO bits */ #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) -/* This equals 0, but use constants in case they ever change */ -#define GFP_NOWAIT (GFP_ATOMIC & ~__GFP_HIGH) -/* GFP_ATOMIC means both !wait (__GFP_WAIT not set) and use emergency pool */ -#define GFP_ATOMIC (__GFP_HIGH) +/* + * GFP_ATOMIC callers can not sleep, need the allocation to succeed. + * A lower watermark is applied to allow access to "atomic reserves" + */ +#define GFP_ATOMIC (__GFP_HIGH|__GFP_ATOMIC|__GFP_KSWAPD_RECLAIM) +#define GFP_NOWAIT (__GFP_KSWAPD_RECLAIM) #define GFP_NOIO (__GFP_WAIT) #define GFP_NOFS (__GFP_WAIT | __GFP_IO) #define GFP_KERNEL (__GFP_WAIT | __GFP_IO | __GFP_FS) @@ -119,10 +134,10 @@ struct vm_area_struct; #define GFP_USER (__GFP_WAIT | __GFP_IO | __GFP_FS | __GFP_HARDWALL) #define GFP_HIGHUSER (GFP_USER | __GFP_HIGHMEM) #define GFP_HIGHUSER_MOVABLE (GFP_HIGHUSER | __GFP_MOVABLE) -#define GFP_IOFS (__GFP_IO | __GFP_FS) -#define GFP_TRANSHUGE (GFP_HIGHUSER_MOVABLE | __GFP_COMP | \ - __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN | \ - __GFP_NO_KSWAPD) +#define GFP_IOFS (__GFP_IO | __GFP_FS | __GFP_KSWAPD_RECLAIM) +#define GFP_TRANSHUGE ((GFP_HIGHUSER_MOVABLE | __GFP_COMP | \ + __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN) & \ + ~__GFP_KSWAPD_RECLAIM) /* This mask makes up all the page movable related flags */ #define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE) @@ -164,6 +179,11 @@ static inline int gfpflags_to_migratetype(const gfp_t gfp_flags) return (gfp_flags & GFP_MOVABLE_MASK) >> GFP_MOVABLE_SHIFT; } +static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags) +{ + return gfp_flags & __GFP_DIRECT_RECLAIM; +} + #ifdef CONFIG_HIGHMEM #define OPT_ZONE_HIGHMEM ZONE_HIGHMEM #else diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 24f4dfd94c51..4355129fff91 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1224,7 +1224,7 @@ static inline int skb_cloned(const struct sk_buff *skb) static inline int skb_unclone(struct sk_buff *skb, gfp_t pri) { - might_sleep_if(pri & __GFP_WAIT); + might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_cloned(skb)) return pskb_expand_head(skb, 0, 0, pri); @@ -1308,7 +1308,7 @@ static inline int skb_shared(const struct sk_buff *skb) */ static inline struct sk_buff *skb_share_check(struct sk_buff *skb, gfp_t pri) { - might_sleep_if(pri & __GFP_WAIT); + might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_shared(skb)) { struct sk_buff *nskb = skb_clone(skb, pri); @@ -1344,7 +1344,7 @@ static inline struct sk_buff *skb_share_check(struct sk_buff *skb, gfp_t pri) static inline struct sk_buff *skb_unshare(struct sk_buff *skb, gfp_t pri) { - might_sleep_if(pri & __GFP_WAIT); + might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_cloned(skb)) { struct sk_buff *nskb = skb_copy(skb, pri); diff --git a/include/net/sock.h b/include/net/sock.h index f570e75e3da9..bbf7c2cf15b4 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2041,7 +2041,7 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp, */ static inline struct page_frag *sk_page_frag(struct sock *sk) { - if (sk->sk_allocation & __GFP_WAIT) + if (gfpflags_allow_blocking(sk->sk_allocation)) return ¤t->task_frag; return &sk->sk_frag; diff --git a/include/trace/events/gfpflags.h b/include/trace/events/gfpflags.h index d6fd8e5b14b7..dde6bf092c8a 100644 --- a/include/trace/events/gfpflags.h +++ b/include/trace/events/gfpflags.h @@ -20,7 +20,7 @@ {(unsigned long)GFP_ATOMIC, "GFP_ATOMIC"}, \ {(unsigned long)GFP_NOIO, "GFP_NOIO"}, \ {(unsigned long)__GFP_HIGH, "GFP_HIGH"}, \ - {(unsigned long)__GFP_WAIT, "GFP_WAIT"}, \ + {(unsigned long)__GFP_ATOMIC, "GFP_ATOMIC"}, \ {(unsigned long)__GFP_IO, "GFP_IO"}, \ {(unsigned long)__GFP_COLD, "GFP_COLD"}, \ {(unsigned long)__GFP_NOWARN, "GFP_NOWARN"}, \ @@ -36,7 +36,8 @@ {(unsigned long)__GFP_RECLAIMABLE, "GFP_RECLAIMABLE"}, \ {(unsigned long)__GFP_MOVABLE, "GFP_MOVABLE"}, \ {(unsigned long)__GFP_NOTRACK, "GFP_NOTRACK"}, \ - {(unsigned long)__GFP_NO_KSWAPD, "GFP_NO_KSWAPD"}, \ + {(unsigned long)__GFP_DIRECT_RECLAIM, "GFP_DIRECT_RECLAIM"}, \ + {(unsigned long)__GFP_KSWAPD_RECLAIM, "GFP_KSWAPD_RECLAIM"}, \ {(unsigned long)__GFP_OTHER_NODE, "GFP_OTHER_NODE"} \ ) : "GFP_NOWAIT" diff --git a/kernel/audit.c b/kernel/audit.c index 8a056a32ded7..5ffcbd354a52 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -1371,16 +1371,16 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, if (unlikely(audit_filter_type(type))) return NULL; - if (gfp_mask & __GFP_WAIT) { + if (gfp_mask & __GFP_DIRECT_RECLAIM) { if (audit_pid && audit_pid == current->pid) - gfp_mask &= ~__GFP_WAIT; + gfp_mask &= ~__GFP_DIRECT_RECLAIM; else reserve = 0; } while (audit_backlog_limit && skb_queue_len(&audit_skb_queue) > audit_backlog_limit + reserve) { - if (gfp_mask & __GFP_WAIT && audit_backlog_wait_time) { + if (gfp_mask & __GFP_DIRECT_RECLAIM && audit_backlog_wait_time) { long sleep_time; sleep_time = timeout_start + audit_backlog_wait_time - jiffies; diff --git a/kernel/cgroup.c b/kernel/cgroup.c index b9d0cce3f9ce..f1603c153890 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -299,7 +299,7 @@ static int cgroup_idr_alloc(struct idr *idr, void *ptr, int start, int end, idr_preload(gfp_mask); spin_lock_bh(&cgroup_idr_lock); - ret = idr_alloc(idr, ptr, start, end, gfp_mask & ~__GFP_WAIT); + ret = idr_alloc(idr, ptr, start, end, gfp_mask & ~__GFP_DIRECT_RECLAIM); spin_unlock_bh(&cgroup_idr_lock); idr_preload_end(); return ret; diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 4e49cc4c9952..deae3907ac1e 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -2738,7 +2738,7 @@ static void __lockdep_trace_alloc(gfp_t gfp_mask, unsigned long flags) return; /* no reclaim without waiting on it */ - if (!(gfp_mask & __GFP_WAIT)) + if (!(gfp_mask & __GFP_DIRECT_RECLAIM)) return; /* this guy won't enter reclaim */ diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 5235dd4e1e2f..3a970604308f 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -1779,7 +1779,7 @@ alloc_highmem_pages(struct memory_bitmap *bm, unsigned int nr_highmem) while (to_alloc-- > 0) { struct page *page; - page = alloc_image_page(__GFP_HIGHMEM); + page = alloc_image_page(__GFP_HIGHMEM|__GFP_KSWAPD_RECLAIM); memory_bm_set_bit(bm, page_to_pfn(page)); } return nr_highmem; diff --git a/kernel/smp.c b/kernel/smp.c index 07854477c164..d903c02223af 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -669,7 +669,7 @@ void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info), cpumask_var_t cpus; int cpu, ret; - might_sleep_if(gfp_flags & __GFP_WAIT); + might_sleep_if(gfpflags_allow_blocking(gfp_flags)); if (likely(zalloc_cpumask_var(&cpus, (gfp_flags|__GFP_NOWARN)))) { preempt_disable(); diff --git a/lib/idr.c b/lib/idr.c index 5335c43adf46..6098336df267 100644 --- a/lib/idr.c +++ b/lib/idr.c @@ -399,7 +399,7 @@ void idr_preload(gfp_t gfp_mask) * allocation guarantee. Disallow usage from those contexts. */ WARN_ON_ONCE(in_interrupt()); - might_sleep_if(gfp_mask & __GFP_WAIT); + might_sleep_if(gfpflags_allow_blocking(gfp_mask)); preempt_disable(); @@ -453,7 +453,7 @@ int idr_alloc(struct idr *idr, void *ptr, int start, int end, gfp_t gfp_mask) struct idr_layer *pa[MAX_IDR_LEVEL + 1]; int id; - might_sleep_if(gfp_mask & __GFP_WAIT); + might_sleep_if(gfpflags_allow_blocking(gfp_mask)); /* sanity checks */ if (WARN_ON_ONCE(start < 0)) diff --git a/lib/radix-tree.c b/lib/radix-tree.c index f9ebe1c82060..fcf5d98574ce 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -188,7 +188,7 @@ radix_tree_node_alloc(struct radix_tree_root *root) * preloading in the interrupt anyway as all the allocations have to * be atomic. So just do normal allocation when in interrupt. */ - if (!(gfp_mask & __GFP_WAIT) && !in_interrupt()) { + if (!gfpflags_allow_blocking(gfp_mask) && !in_interrupt()) { struct radix_tree_preload *rtp; /* @@ -249,7 +249,7 @@ radix_tree_node_free(struct radix_tree_node *node) * with preemption not disabled. * * To make use of this facility, the radix tree must be initialised without - * __GFP_WAIT being passed to INIT_RADIX_TREE(). + * __GFP_DIRECT_RECLAIM being passed to INIT_RADIX_TREE(). */ static int __radix_tree_preload(gfp_t gfp_mask) { @@ -286,12 +286,12 @@ out: * with preemption not disabled. * * To make use of this facility, the radix tree must be initialised without - * __GFP_WAIT being passed to INIT_RADIX_TREE(). + * __GFP_DIRECT_RECLAIM being passed to INIT_RADIX_TREE(). */ int radix_tree_preload(gfp_t gfp_mask) { /* Warn on non-sensical use... */ - WARN_ON_ONCE(!(gfp_mask & __GFP_WAIT)); + WARN_ON_ONCE(!gfpflags_allow_blocking(gfp_mask)); return __radix_tree_preload(gfp_mask); } EXPORT_SYMBOL(radix_tree_preload); @@ -303,7 +303,7 @@ EXPORT_SYMBOL(radix_tree_preload); */ int radix_tree_maybe_preload(gfp_t gfp_mask) { - if (gfp_mask & __GFP_WAIT) + if (gfpflags_allow_blocking(gfp_mask)) return __radix_tree_preload(gfp_mask); /* Preloading doesn't help anything with this gfp mask, skip it */ preempt_disable(); diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 619984fc07ec..8ed2ffd963c5 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -637,7 +637,7 @@ struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi, { struct bdi_writeback *wb; - might_sleep_if(gfp & __GFP_WAIT); + might_sleep_if(gfpflags_allow_blocking(gfp)); if (!memcg_css->parent) return &bdi->wb; diff --git a/mm/dmapool.c b/mm/dmapool.c index 312a716fa14c..57312b5d6e12 100644 --- a/mm/dmapool.c +++ b/mm/dmapool.c @@ -326,7 +326,7 @@ void *dma_pool_alloc(struct dma_pool *pool, gfp_t mem_flags, size_t offset; void *retval; - might_sleep_if(mem_flags & __GFP_WAIT); + might_sleep_if(gfpflags_allow_blocking(mem_flags)); spin_lock_irqsave(&pool->lock, flags); list_for_each_entry(page, &pool->page_list, page_list) { diff --git a/mm/memcontrol.c b/mm/memcontrol.c index bc502e590366..05374f09339c 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2046,7 +2046,7 @@ retry: if (unlikely(task_in_memcg_oom(current))) goto nomem; - if (!(gfp_mask & __GFP_WAIT)) + if (!gfpflags_allow_blocking(gfp_mask)) goto nomem; mem_cgroup_events(mem_over_limit, MEMCG_MAX, 1); @@ -4364,8 +4364,8 @@ static int mem_cgroup_do_precharge(unsigned long count) { int ret; - /* Try a single bulk charge without reclaim first */ - ret = try_charge(mc.to, GFP_KERNEL & ~__GFP_WAIT, count); + /* Try a single bulk charge without reclaim first, kswapd may wake */ + ret = try_charge(mc.to, GFP_KERNEL & ~__GFP_DIRECT_RECLAIM, count); if (!ret) { mc.precharge += count; return ret; diff --git a/mm/mempool.c b/mm/mempool.c index 4c533bc51d73..004d42b1dfaf 100644 --- a/mm/mempool.c +++ b/mm/mempool.c @@ -320,13 +320,13 @@ void * mempool_alloc(mempool_t *pool, gfp_t gfp_mask) gfp_t gfp_temp; VM_WARN_ON_ONCE(gfp_mask & __GFP_ZERO); - might_sleep_if(gfp_mask & __GFP_WAIT); + might_sleep_if(gfp_mask & __GFP_DIRECT_RECLAIM); gfp_mask |= __GFP_NOMEMALLOC; /* don't allocate emergency reserves */ gfp_mask |= __GFP_NORETRY; /* don't loop in __alloc_pages */ gfp_mask |= __GFP_NOWARN; /* failures are OK */ - gfp_temp = gfp_mask & ~(__GFP_WAIT|__GFP_IO); + gfp_temp = gfp_mask & ~(__GFP_DIRECT_RECLAIM|__GFP_IO); repeat_alloc: @@ -349,7 +349,7 @@ repeat_alloc: } /* - * We use gfp mask w/o __GFP_WAIT or IO for the first round. If + * We use gfp mask w/o direct reclaim or IO for the first round. If * alloc failed with that and @pool was empty, retry immediately. */ if (gfp_temp != gfp_mask) { @@ -358,8 +358,8 @@ repeat_alloc: goto repeat_alloc; } - /* We must not sleep if !__GFP_WAIT */ - if (!(gfp_mask & __GFP_WAIT)) { + /* We must not sleep if !__GFP_DIRECT_RECLAIM */ + if (!(gfp_mask & __GFP_DIRECT_RECLAIM)) { spin_unlock_irqrestore(&pool->lock, flags); return NULL; } diff --git a/mm/migrate.c b/mm/migrate.c index 2834faba719a..e60379eb23f8 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1578,7 +1578,7 @@ static struct page *alloc_misplaced_dst_page(struct page *page, (GFP_HIGHUSER_MOVABLE | __GFP_THISNODE | __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN) & - ~GFP_IOFS, 0); + ~(__GFP_IO | __GFP_FS), 0); return newpage; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 67390988881a..70461f3e3378 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -169,12 +169,12 @@ void pm_restrict_gfp_mask(void) WARN_ON(!mutex_is_locked(&pm_mutex)); WARN_ON(saved_gfp_mask); saved_gfp_mask = gfp_allowed_mask; - gfp_allowed_mask &= ~GFP_IOFS; + gfp_allowed_mask &= ~(__GFP_IO | __GFP_FS); } bool pm_suspended_storage(void) { - if ((gfp_allowed_mask & GFP_IOFS) == GFP_IOFS) + if ((gfp_allowed_mask & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS)) return false; return true; } @@ -2183,7 +2183,7 @@ static bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) return false; if (fail_page_alloc.ignore_gfp_highmem && (gfp_mask & __GFP_HIGHMEM)) return false; - if (fail_page_alloc.ignore_gfp_wait && (gfp_mask & __GFP_WAIT)) + if (fail_page_alloc.ignore_gfp_wait && (gfp_mask & __GFP_DIRECT_RECLAIM)) return false; return should_fail(&fail_page_alloc.attr, 1 << order); @@ -2685,7 +2685,7 @@ void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...) if (test_thread_flag(TIF_MEMDIE) || (current->flags & (PF_MEMALLOC | PF_EXITING))) filter &= ~SHOW_MEM_FILTER_NODES; - if (in_interrupt() || !(gfp_mask & __GFP_WAIT)) + if (in_interrupt() || !(gfp_mask & __GFP_DIRECT_RECLAIM)) filter &= ~SHOW_MEM_FILTER_NODES; if (fmt) { @@ -2945,7 +2945,6 @@ static inline int gfp_to_alloc_flags(gfp_t gfp_mask) { int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET; - const bool atomic = !(gfp_mask & (__GFP_WAIT | __GFP_NO_KSWAPD)); /* __GFP_HIGH is assumed to be the same as ALLOC_HIGH to save a branch. */ BUILD_BUG_ON(__GFP_HIGH != (__force gfp_t) ALLOC_HIGH); @@ -2954,11 +2953,11 @@ gfp_to_alloc_flags(gfp_t gfp_mask) * The caller may dip into page reserves a bit more if the caller * cannot run direct reclaim, or if the caller has realtime scheduling * policy or is asking for __GFP_HIGH memory. GFP_ATOMIC requests will - * set both ALLOC_HARDER (atomic == true) and ALLOC_HIGH (__GFP_HIGH). + * set both ALLOC_HARDER (__GFP_ATOMIC) and ALLOC_HIGH (__GFP_HIGH). */ alloc_flags |= (__force int) (gfp_mask & __GFP_HIGH); - if (atomic) { + if (gfp_mask & __GFP_ATOMIC) { /* * Not worth trying to allocate harder for __GFP_NOMEMALLOC even * if it can't schedule. @@ -2995,11 +2994,16 @@ bool gfp_pfmemalloc_allowed(gfp_t gfp_mask) return !!(gfp_to_alloc_flags(gfp_mask) & ALLOC_NO_WATERMARKS); } +static inline bool is_thp_gfp_mask(gfp_t gfp_mask) +{ + return (gfp_mask & (GFP_TRANSHUGE | __GFP_KSWAPD_RECLAIM)) == GFP_TRANSHUGE; +} + static inline struct page * __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, struct alloc_context *ac) { - const gfp_t wait = gfp_mask & __GFP_WAIT; + bool can_direct_reclaim = gfp_mask & __GFP_DIRECT_RECLAIM; struct page *page = NULL; int alloc_flags; unsigned long pages_reclaimed = 0; @@ -3019,16 +3023,24 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, return NULL; } + /* + * We also sanity check to catch abuse of atomic reserves being used by + * callers that are not in atomic context. + */ + if (WARN_ON_ONCE((gfp_mask & (__GFP_ATOMIC|__GFP_DIRECT_RECLAIM)) == + (__GFP_ATOMIC|__GFP_DIRECT_RECLAIM))) + gfp_mask &= ~__GFP_ATOMIC; + /* * If this allocation cannot block and it is for a specific node, then * fail early. There's no need to wakeup kswapd or retry for a * speculative node-specific allocation. */ - if (IS_ENABLED(CONFIG_NUMA) && (gfp_mask & __GFP_THISNODE) && !wait) + if (IS_ENABLED(CONFIG_NUMA) && (gfp_mask & __GFP_THISNODE) && !can_direct_reclaim) goto nopage; retry: - if (!(gfp_mask & __GFP_NO_KSWAPD)) + if (gfp_mask & __GFP_KSWAPD_RECLAIM) wake_all_kswapds(order, ac); /* @@ -3071,8 +3083,8 @@ retry: } } - /* Atomic allocations - we can't balance anything */ - if (!wait) { + /* Caller is not willing to reclaim, we can't balance anything */ + if (!can_direct_reclaim) { /* * All existing users of the deprecated __GFP_NOFAIL are * blockable, so warn of any new users that actually allow this @@ -3102,7 +3114,7 @@ retry: goto got_pg; /* Checks for THP-specific high-order allocations */ - if ((gfp_mask & GFP_TRANSHUGE) == GFP_TRANSHUGE) { + if (is_thp_gfp_mask(gfp_mask)) { /* * If compaction is deferred for high-order allocations, it is * because sync compaction recently failed. If this is the case @@ -3137,8 +3149,7 @@ retry: * fault, so use asynchronous memory compaction for THP unless it is * khugepaged trying to collapse. */ - if ((gfp_mask & GFP_TRANSHUGE) != GFP_TRANSHUGE || - (current->flags & PF_KTHREAD)) + if (!is_thp_gfp_mask(gfp_mask) || (current->flags & PF_KTHREAD)) migration_mode = MIGRATE_SYNC_LIGHT; /* Try direct reclaim and then allocating */ @@ -3209,7 +3220,7 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, lockdep_trace_alloc(gfp_mask); - might_sleep_if(gfp_mask & __GFP_WAIT); + might_sleep_if(gfp_mask & __GFP_DIRECT_RECLAIM); if (should_fail_alloc_page(gfp_mask, order)) return NULL; diff --git a/mm/slab.c b/mm/slab.c index 272e809404d5..a9ef77d19a9a 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -1031,12 +1031,12 @@ static inline int cache_free_alien(struct kmem_cache *cachep, void *objp) } /* - * Construct gfp mask to allocate from a specific node but do not invoke reclaim - * or warn about failures. + * Construct gfp mask to allocate from a specific node but do not direct reclaim + * or warn about failures. kswapd may still wake to reclaim in the background. */ static inline gfp_t gfp_exact_node(gfp_t flags) { - return (flags | __GFP_THISNODE | __GFP_NOWARN) & ~__GFP_WAIT; + return (flags | __GFP_THISNODE | __GFP_NOWARN) & ~__GFP_DIRECT_RECLAIM; } #endif @@ -2633,7 +2633,7 @@ static int cache_grow(struct kmem_cache *cachep, offset *= cachep->colour_off; - if (local_flags & __GFP_WAIT) + if (gfpflags_allow_blocking(local_flags)) local_irq_enable(); /* @@ -2663,7 +2663,7 @@ static int cache_grow(struct kmem_cache *cachep, cache_init_objs(cachep, page); - if (local_flags & __GFP_WAIT) + if (gfpflags_allow_blocking(local_flags)) local_irq_disable(); check_irq_off(); spin_lock(&n->list_lock); @@ -2677,7 +2677,7 @@ static int cache_grow(struct kmem_cache *cachep, opps1: kmem_freepages(cachep, page); failed: - if (local_flags & __GFP_WAIT) + if (gfpflags_allow_blocking(local_flags)) local_irq_disable(); return 0; } @@ -2869,7 +2869,7 @@ force_grow: static inline void cache_alloc_debugcheck_before(struct kmem_cache *cachep, gfp_t flags) { - might_sleep_if(flags & __GFP_WAIT); + might_sleep_if(gfpflags_allow_blocking(flags)); #if DEBUG kmem_flagcheck(cachep, flags); #endif @@ -3057,11 +3057,11 @@ retry: */ struct page *page; - if (local_flags & __GFP_WAIT) + if (gfpflags_allow_blocking(local_flags)) local_irq_enable(); kmem_flagcheck(cache, flags); page = kmem_getpages(cache, local_flags, numa_mem_id()); - if (local_flags & __GFP_WAIT) + if (gfpflags_allow_blocking(local_flags)) local_irq_disable(); if (page) { /* diff --git a/mm/slub.c b/mm/slub.c index 75a5fa92ac2a..97695622a858 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1265,7 +1265,7 @@ static inline struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s, { flags &= gfp_allowed_mask; lockdep_trace_alloc(flags); - might_sleep_if(flags & __GFP_WAIT); + might_sleep_if(gfpflags_allow_blocking(flags)); if (should_failslab(s->object_size, flags, s->flags)) return NULL; @@ -1353,7 +1353,7 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) flags &= gfp_allowed_mask; - if (flags & __GFP_WAIT) + if (gfpflags_allow_blocking(flags)) local_irq_enable(); flags |= s->allocflags; @@ -1363,8 +1363,8 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) * so we fall-back to the minimum order allocation. */ alloc_gfp = (flags | __GFP_NOWARN | __GFP_NORETRY) & ~__GFP_NOFAIL; - if ((alloc_gfp & __GFP_WAIT) && oo_order(oo) > oo_order(s->min)) - alloc_gfp = (alloc_gfp | __GFP_NOMEMALLOC) & ~__GFP_WAIT; + if ((alloc_gfp & __GFP_DIRECT_RECLAIM) && oo_order(oo) > oo_order(s->min)) + alloc_gfp = (alloc_gfp | __GFP_NOMEMALLOC) & ~__GFP_DIRECT_RECLAIM; page = alloc_slab_page(s, alloc_gfp, node, oo); if (unlikely(!page)) { @@ -1424,7 +1424,7 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) page->frozen = 1; out: - if (flags & __GFP_WAIT) + if (gfpflags_allow_blocking(flags)) local_irq_disable(); if (!page) return NULL; diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 9db9ef5e8481..7ee94dc10000 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1617,7 +1617,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, goto fail; } area->pages[i] = page; - if (gfp_mask & __GFP_WAIT) + if (gfpflags_allow_blocking(gfp_mask)) cond_resched(); } diff --git a/mm/vmscan.c b/mm/vmscan.c index e0cd7eed4e38..2aec4241b42a 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1476,7 +1476,7 @@ static int too_many_isolated(struct zone *zone, int file, * won't get blocked by normal direct-reclaimers, forming a circular * deadlock. */ - if ((sc->gfp_mask & GFP_IOFS) == GFP_IOFS) + if ((sc->gfp_mask & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS)) inactive >>= 3; return isolated > inactive; @@ -3791,7 +3791,7 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order) /* * Do not scan if the allocation should not be delayed. */ - if (!(gfp_mask & __GFP_WAIT) || (current->flags & PF_MEMALLOC)) + if (!gfpflags_allow_blocking(gfp_mask) || (current->flags & PF_MEMALLOC)) return ZONE_RECLAIM_NOSCAN; /* diff --git a/mm/zswap.c b/mm/zswap.c index 4043df7c672f..e54166d3732e 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -571,7 +571,7 @@ static struct zswap_pool *zswap_pool_find_get(char *type, char *compressor) static struct zswap_pool *zswap_pool_create(char *type, char *compressor) { struct zswap_pool *pool; - gfp_t gfp = __GFP_NORETRY | __GFP_NOWARN; + gfp_t gfp = __GFP_NORETRY | __GFP_NOWARN | __GFP_KSWAPD_RECLAIM; pool = kzalloc(sizeof(*pool), GFP_KERNEL); if (!pool) { @@ -1011,7 +1011,8 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset, /* store */ len = dlen + sizeof(struct zswap_header); ret = zpool_malloc(entry->pool->zpool, len, - __GFP_NORETRY | __GFP_NOWARN, &handle); + __GFP_NORETRY | __GFP_NOWARN | __GFP_KSWAPD_RECLAIM, + &handle); if (ret == -ENOSPC) { zswap_reject_compress_poor++; goto put_dstmem; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index fab4599ba8b2..aa41e6dd6429 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -414,7 +414,7 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len, len += NET_SKB_PAD; if ((len > SKB_WITH_OVERHEAD(PAGE_SIZE)) || - (gfp_mask & (__GFP_WAIT | GFP_DMA))) { + (gfp_mask & (__GFP_DIRECT_RECLAIM | GFP_DMA))) { skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX, NUMA_NO_NODE); if (!skb) goto skb_fail; @@ -481,7 +481,7 @@ struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len, len += NET_SKB_PAD + NET_IP_ALIGN; if ((len > SKB_WITH_OVERHEAD(PAGE_SIZE)) || - (gfp_mask & (__GFP_WAIT | GFP_DMA))) { + (gfp_mask & (__GFP_DIRECT_RECLAIM | GFP_DMA))) { skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX, NUMA_NO_NODE); if (!skb) goto skb_fail; @@ -4452,7 +4452,7 @@ struct sk_buff *alloc_skb_with_frags(unsigned long header_len, return NULL; gfp_head = gfp_mask; - if (gfp_head & __GFP_WAIT) + if (gfp_head & __GFP_DIRECT_RECLAIM) gfp_head |= __GFP_REPEAT; *errcode = -ENOBUFS; @@ -4467,7 +4467,7 @@ struct sk_buff *alloc_skb_with_frags(unsigned long header_len, while (order) { if (npages >= 1 << order) { - page = alloc_pages((gfp_mask & ~__GFP_WAIT) | + page = alloc_pages((gfp_mask & ~__GFP_DIRECT_RECLAIM) | __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY, diff --git a/net/core/sock.c b/net/core/sock.c index 7529eb9463be..1e4dd54bfb5a 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1944,8 +1944,10 @@ bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t gfp) pfrag->offset = 0; if (SKB_FRAG_PAGE_ORDER) { - pfrag->page = alloc_pages((gfp & ~__GFP_WAIT) | __GFP_COMP | - __GFP_NOWARN | __GFP_NORETRY, + /* Avoid direct reclaim but allow kswapd to wake */ + pfrag->page = alloc_pages((gfp & ~__GFP_DIRECT_RECLAIM) | + __GFP_COMP | __GFP_NOWARN | + __GFP_NORETRY, SKB_FRAG_PAGE_ORDER); if (likely(pfrag->page)) { pfrag->size = PAGE_SIZE << SKB_FRAG_PAGE_ORDER; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index fafe33bdb619..59651af8cc27 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2116,7 +2116,7 @@ int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb, u32 portid consume_skb(info.skb2); if (info.delivered) { - if (info.congested && (allocation & __GFP_WAIT)) + if (info.congested && gfpflags_allow_blocking(allocation)) yield(); return 0; } diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c index 96744b75db93..977fb86065b7 100644 --- a/net/rds/ib_recv.c +++ b/net/rds/ib_recv.c @@ -305,7 +305,7 @@ static int rds_ib_recv_refill_one(struct rds_connection *conn, gfp_t slab_mask = GFP_NOWAIT; gfp_t page_mask = GFP_NOWAIT; - if (gfp & __GFP_WAIT) { + if (gfp & __GFP_DIRECT_RECLAIM) { slab_mask = GFP_KERNEL; page_mask = GFP_HIGHUSER; } @@ -379,7 +379,7 @@ void rds_ib_recv_refill(struct rds_connection *conn, int prefill, gfp_t gfp) struct ib_recv_wr *failed_wr; unsigned int posted = 0; int ret = 0; - bool can_wait = !!(gfp & __GFP_WAIT); + bool can_wait = !!(gfp & __GFP_DIRECT_RECLAIM); u32 pos; /* the goal here is to just make sure that someone, somewhere diff --git a/net/rxrpc/ar-connection.c b/net/rxrpc/ar-connection.c index 692b3e67fb54..6c71ed1caf16 100644 --- a/net/rxrpc/ar-connection.c +++ b/net/rxrpc/ar-connection.c @@ -500,7 +500,7 @@ int rxrpc_connect_call(struct rxrpc_sock *rx, if (bundle->num_conns >= 20) { _debug("too many conns"); - if (!(gfp & __GFP_WAIT)) { + if (!gfpflags_allow_blocking(gfp)) { _leave(" = -EAGAIN"); return -EAGAIN; } diff --git a/net/sctp/associola.c b/net/sctp/associola.c index b00f1f9611d6..559afd0ee7de 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -1590,7 +1590,7 @@ int sctp_assoc_lookup_laddr(struct sctp_association *asoc, /* Set an association id for a given association */ int sctp_assoc_set_id(struct sctp_association *asoc, gfp_t gfp) { - bool preload = !!(gfp & __GFP_WAIT); + bool preload = gfpflags_allow_blocking(gfp); int ret; /* If the id is already assigned, keep it. */ -- cgit v1.2.3