Merge branch 'for-4.13-part1' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "The core updates improve error handling (mostly related to bios), with
  the usual incremental work on the GFP_NOFS (mis)use removal,
  refactoring or cleanups. Except the two top patches, all have been in
  for-next for an extensive amount of time.

  User visible changes:

   - statx support

   - quota override tunable

   - improved compression thresholds

   - obsoleted mount option alloc_start

  Core updates:

   - bio-related updates:
       - faster bio cloning
       - no allocation failures
       - preallocated flush bios

   - more kvzalloc use, memalloc_nofs protections, GFP_NOFS updates

   - prep work for btree_inode removal

   - dir-item validation

   - qgoup fixes and updates

   - cleanups:
       - removed unused struct members, unused code, refactoring
       - argument refactoring (fs_info/root, caller -> callee sink)
       - SEARCH_TREE ioctl docs"

* 'for-4.13-part1' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (115 commits)
  btrfs: Remove false alert when fiemap range is smaller than on-disk extent
  btrfs: Don't clear SGID when inheriting ACLs
  btrfs: fix integer overflow in calc_reclaim_items_nr
  btrfs: scrub: fix target device intialization while setting up scrub context
  btrfs: qgroup: Fix qgroup reserved space underflow by only freeing reserved ranges
  btrfs: qgroup: Introduce extent changeset for qgroup reserve functions
  btrfs: qgroup: Fix qgroup reserved space underflow caused by buffered write and quotas being enabled
  btrfs: qgroup: Return actually freed bytes for qgroup release or free data
  btrfs: qgroup: Cleanup btrfs_qgroup_prepare_account_extents function
  btrfs: qgroup: Add quick exit for non-fs extents
  Btrfs: rework delayed ref total_bytes_pinned accounting
  Btrfs: return old and new total ref mods when adding delayed refs
  Btrfs: always account pinned bytes when dropping a tree block ref
  Btrfs: update total_bytes_pinned when pinning down extents
  Btrfs: make BUG_ON() in add_pinned_bytes() an ASSERT()
  Btrfs: make add_pinned_bytes() take an s64 num_bytes instead of u64
  btrfs: fix validation of XATTR_ITEM dir items
  btrfs: Verify dir_item in iterate_object_props
  btrfs: Check name_len before in btrfs_del_root_ref
  btrfs: Check name_len before reading btrfs_get_name
  ...

1 files changed, 21 insertions, 73 deletions

diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index a2fad39f79ba..2c0b7b57fcd5 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -32,6 +32,7 @@
 #include <linux/writeback.h>
 #include <linux/bit_spinlock.h>
 #include <linux/slab.h>
+#include <linux/sched/mm.h>
 #include "ctree.h"
 #include "disk-io.h"
 #include "transaction.h"
@@ -42,48 +43,7 @@
 #include "extent_io.h"
 #include "extent_map.h"
 
-struct compressed_bio {
-        /* number of bios pending for this compressed extent */
-        refcount_t pending_bios;
-
-        /* the pages with the compressed data on them */
-        struct page **compressed_pages;
-
-        /* inode that owns this data */
-        struct inode *inode;
-
-        /* starting offset in the inode for our pages */
-        u64 start;
-
-        /* number of bytes in the inode we're working on */
-        unsigned long len;
-
-        /* number of bytes on disk */
-        unsigned long compressed_len;
-
-        /* the compression algorithm for this bio */
-        int compress_type;
-
-        /* number of compressed pages in the array */
-        unsigned long nr_pages;
-
-        /* IO errors */
-        int errors;
-        int mirror_num;
-
-        /* for reads, this is the bio we are copying the data into */
-        struct bio *orig_bio;
-
-        /*
-         * the start of a variable length array of checksums only
-         * used by reads
-         */
-        u32 sums;
-};
-
-static int btrfs_decompress_bio(int type, struct page **pages_in,
-                                   u64 disk_start, struct bio *orig_bio,
-                                   size_t srclen);
+static int btrfs_decompress_bio(struct compressed_bio *cb);
 
 static inline int compressed_bio_size(struct btrfs_fs_info *fs_info,
                                       unsigned long disk_size)
@@ -94,12 +54,6 @@ static inline int compressed_bio_size(struct btrfs_fs_info *fs_info,
                 (DIV_ROUND_UP(disk_size, fs_info->sectorsize)) * csum_size;
 }
 
-static struct bio *compressed_bio_alloc(struct block_device *bdev,
-                                        u64 first_byte, gfp_t gfp_flags)
-{
-        return btrfs_bio_alloc(bdev, first_byte >> 9, BIO_MAX_PAGES, gfp_flags);
-}
-
 static int check_compressed_csum(struct btrfs_inode *inode,
                                  struct compressed_bio *cb,
                                  u64 disk_start)
@@ -173,11 +127,8 @@ static void end_compressed_bio_read(struct bio *bio)
         /* ok, we're the last bio for this extent, lets start
          * the decompression.
          */
-        ret = btrfs_decompress_bio(cb->compress_type,
-                                      cb->compressed_pages,
-                                      cb->start,
-                                      cb->orig_bio,
-                                      cb->compressed_len);
+        ret = btrfs_decompress_bio(cb);
+
 csum_failed:
         if (ret)
                 cb->errors = 1;
@@ -355,11 +306,7 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
 
         bdev = fs_info->fs_devices->latest_bdev;
 
-        bio = compressed_bio_alloc(bdev, first_byte, GFP_NOFS);
-        if (!bio) {
-                kfree(cb);
-                return BLK_STS_RESOURCE;
-        }
+        bio = btrfs_bio_alloc(bdev, first_byte);
         bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
         bio->bi_private = cb;
         bio->bi_end_io = end_compressed_bio_write;
@@ -406,8 +353,7 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
 
                         bio_put(bio);
 
-                        bio = compressed_bio_alloc(bdev, first_byte, GFP_NOFS);
-                        BUG_ON(!bio);
+                        bio = btrfs_bio_alloc(bdev, first_byte);
                         bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
                         bio->bi_private = cb;
                         bio->bi_end_io = end_compressed_bio_write;
@@ -650,9 +596,7 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
         /* include any pages we added in add_ra-bio_pages */
         cb->len = bio->bi_iter.bi_size;
 
-        comp_bio = compressed_bio_alloc(bdev, cur_disk_byte, GFP_NOFS);
-        if (!comp_bio)
-                goto fail2;
+        comp_bio = btrfs_bio_alloc(bdev, cur_disk_byte);
         bio_set_op_attrs (comp_bio, REQ_OP_READ, 0);
         comp_bio->bi_private = cb;
         comp_bio->bi_end_io = end_compressed_bio_read;
@@ -703,9 +647,7 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 
                         bio_put(comp_bio);
 
-                        comp_bio = compressed_bio_alloc(bdev, cur_disk_byte,
-                                                        GFP_NOFS);
-                        BUG_ON(!comp_bio);
+                        comp_bio = btrfs_bio_alloc(bdev, cur_disk_byte);
                         bio_set_op_attrs(comp_bio, REQ_OP_READ, 0);
                         comp_bio->bi_private = cb;
                         comp_bio->bi_end_io = end_compressed_bio_read;
@@ -801,6 +743,7 @@ static struct list_head *find_workspace(int type)
         struct list_head *workspace;
         int cpus = num_online_cpus();
         int idx = type - 1;
+        unsigned nofs_flag;
 
         struct list_head *idle_ws       = &btrfs_comp_ws[idx].idle_ws;
         spinlock_t *ws_lock             = &btrfs_comp_ws[idx].ws_lock;
@@ -830,7 +773,15 @@ again:
         atomic_inc(total_ws);
         spin_unlock(ws_lock);
 
+        /*
+         * Allocation helpers call vmalloc that can't use GFP_NOFS, so we have
+         * to turn it off here because we might get called from the restricted
+         * context of btrfs_compress_bio/btrfs_compress_pages
+         */
+        nofs_flag = memalloc_nofs_save();
         workspace = btrfs_compress_op[idx]->alloc_workspace();
+        memalloc_nofs_restore(nofs_flag);
+
         if (IS_ERR(workspace)) {
                 atomic_dec(total_ws);
                 wake_up(ws_wait);
@@ -961,19 +912,16 @@ int btrfs_compress_pages(int type, struct address_space *mapping,
  * be contiguous.  They all correspond to the range of bytes covered by
  * the compressed extent.
  */
-static int btrfs_decompress_bio(int type, struct page **pages_in,
-                                   u64 disk_start, struct bio *orig_bio,
-                                   size_t srclen)
+static int btrfs_decompress_bio(struct compressed_bio *cb)
 {
         struct list_head *workspace;
         int ret;
+        int type = cb->compress_type;
 
         workspace = find_workspace(type);
-
-        ret = btrfs_compress_op[type-1]->decompress_bio(workspace, pages_in,
-                                                         disk_start, orig_bio,
-                                                         srclen);
+        ret = btrfs_compress_op[type - 1]->decompress_bio(workspace, cb);
         free_workspace(type, workspace);
+
         return ret;
 }