Merge branch 'android-4.4@b834e92' into branch 'msm-4.4'

* refs/heads/tmp-b834e92
  Revert "USB: gadget: u_ether: Fix data stall issue in RNDIS tethering mode"
  Linux 4.4.63
  MIPS: fix Select HAVE_IRQ_EXIT_ON_IRQ_STACK patch.
  sctp: deny peeloff operation on asocs with threads sleeping on it
  net: ipv6: check route protocol when deleting routes
  tty/serial: atmel: RS485 half duplex w/DMA: enable RX after TX is done
  SUNRPC: fix refcounting problems with auth_gss messages.
  ibmveth: calculate gso_segs for large packets
  catc: Use heap buffer for memory size test
  catc: Combine failure cleanup code in catc_probe()
  rtl8150: Use heap buffers for all register access
  pegasus: Use heap buffers for all register access
  virtio-console: avoid DMA from stack
  dvb-usb-firmware: don't do DMA on stack
  dvb-usb: don't use stack for firmware load
  mm: Tighten x86 /dev/mem with zeroing reads
  rtc: tegra: Implement clock handling
  platform/x86: acer-wmi: setup accelerometer when machine has appropriate notify event
  ext4: fix inode checksum calculation problem if i_extra_size is small
  dvb-usb-v2: avoid use-after-free
  ath9k: fix NULL pointer dereference
  crypto: ahash - Fix EINPROGRESS notification callback
  powerpc: Disable HFSCR[TM] if TM is not supported
  zram: do not use copy_page with non-page aligned address
  kvm: fix page struct leak in handle_vmon
  Revert "MIPS: Lantiq: Fix cascaded IRQ setup"
  char: lack of bool string made CONFIG_DEVPORT always on
  char: Drop bogus dependency of DEVPORT on !M68K
  ftrace: Fix removing of second function probe
  irqchip/irq-imx-gpcv2: Fix spinlock initialization
  libnvdimm: fix reconfig_mutex, mmap_sem, and jbd2_handle lockdep splat
  xen, fbfront: fix connecting to backend
  scsi: sd: Fix capacity calculation with 32-bit sector_t
  scsi: sd: Consider max_xfer_blocks if opt_xfer_blocks is unusable
  scsi: sr: Sanity check returned mode data
  iscsi-target: Drop work-around for legacy GlobalSAN initiator
  iscsi-target: Fix TMR reference leak during session shutdown
  acpi, nfit, libnvdimm: fix interleave set cookie calculation (64-bit comparison)
  x86/vdso: Plug race between mapping and ELF header setup
  x86/vdso: Ensure vdso32_enabled gets set to valid values only
  perf/x86: Avoid exposing wrong/stale data in intel_pmu_lbr_read_32()
  Input: xpad - add support for Razer Wildcat gamepad
  CIFS: store results of cifs_reopen_file to avoid infinite wait
  drm/nouveau/mmu/nv4a: use nv04 mmu rather than the nv44 one
  drm/nouveau/mpeg: mthd returns true on success now
  thp: fix MADV_DONTNEED vs clear soft dirty race
  cgroup, kthread: close race window where new kthreads can be migrated to non-root cgroups
  ANDROID: uid_sys_stats: reduce update_io_stats overhead
  UPSTREAM: char: lack of bool string made CONFIG_DEVPORT always on
  UPSTREAM: char: Drop bogus dependency of DEVPORT on !M68K
  Revert "Android: sdcardfs: Don't do d_add for lower fs"
  ANDROID: usb: gadget: fix MTP enumeration issue under super speed mode
  Android: sdcardfs: Don't complain in fixup_lower_ownership
  Android: sdcardfs: Don't do d_add for lower fs
  ANDROID: sdcardfs: ->iget fixes
  Android: sdcardfs: Change cache GID value
  BACKPORT: [UPSTREAM] ext2: convert to mbcache2
  BACKPORT [UPSTREAM] ext4: convert to mbcache2
  BACKPORT: [UPSTREAM] mbcache2: reimplement mbcache
  Linux 4.4.62
  ibmveth: set correct gso_size and gso_type
  net/mlx4_core: Fix when to save some qp context flags for dynamic VST to VGT transitions
  net/mlx4_core: Fix racy CQ (Completion Queue) free
  net/mlx4_en: Fix bad WQE issue
  usb: hub: Wait for connection to be reestablished after port reset
  blk-mq: Avoid memory reclaim when remapping queues
  net/packet: fix overflow in check for priv area size
  crypto: caam - fix RNG deinstantiation error checking
  MIPS: IRQ Stack: Fix erroneous jal to plat_irq_dispatch
  MIPS: Select HAVE_IRQ_EXIT_ON_IRQ_STACK
  MIPS: Switch to the irq_stack in interrupts
  MIPS: Only change $28 to thread_info if coming from user mode
  MIPS: Stack unwinding while on IRQ stack
  MIPS: Introduce irq_stack
  mtd: bcm47xxpart: fix parsing first block after aligned TRX
  usb: dwc3: gadget: delay unmap of bounced requests
  drm/i915: Stop using RP_DOWN_EI on Baytrail
  drm/i915: Avoid tweaking evaluation thresholds on Baytrail v3
  UPSTREAM: net: socket: Make unnecessarily global sockfs_setattr() static
  UPSTREAM: net: ipv4: Don't crash if passing a null sk to ip_do_redirect.
  UPSTREAM: net/packet: fix overflow in check for priv area size
  Linux 4.4.61
  mm/mempolicy.c: fix error handling in set_mempolicy and mbind.
  MIPS: Flush wrong invalid FTLB entry for huge page
  MIPS: Lantiq: fix missing xbar kernel panic
  MIPS: End spinlocks with .insn
  MIPS: ralink: Fix typos in rt3883 pinctrl
  MIPS: Force o32 fp64 support on 32bit MIPS64r6 kernels
  s390/uaccess: get_user() should zero on failure (again)
  s390/decompressor: fix initrd corruption caused by bss clear
  nios2: reserve boot memory for device tree
  powerpc: Don't try to fix up misaligned load-with-reservation instructions
  powerpc/mm: Add missing global TLB invalidate if cxl is active
  metag/usercopy: Add missing fixups
  metag/usercopy: Fix src fixup in from user rapf loops
  metag/usercopy: Set flags before ADDZ
  metag/usercopy: Zero rest of buffer from copy_from_user
  metag/usercopy: Add early abort to copy_to_user
  metag/usercopy: Fix alignment error checking
  metag/usercopy: Drop unused macros
  ring-buffer: Fix return value check in test_ringbuffer()
  ptrace: fix PTRACE_LISTEN race corrupting task->state
  Reset TreeId to zero on SMB2 TREE_CONNECT
  iio: bmg160: reset chip when probing
  arm/arm64: KVM: Take mmap_sem in kvm_arch_prepare_memory_region
  arm/arm64: KVM: Take mmap_sem in stage2_unmap_vm
  staging: android: ashmem: lseek failed due to no FMODE_LSEEK.
  sysfs: be careful of error returns from ops->show()
  drm/vmwgfx: fix integer overflow in vmw_surface_define_ioctl()
  drm/vmwgfx: Remove getparam error message
  drm/ttm, drm/vmwgfx: Relax permission checking when opening surfaces
  drm/vmwgfx: avoid calling vzalloc with a 0 size in vmw_get_cap_3d_ioctl()
  drm/vmwgfx: NULL pointer dereference in vmw_surface_define_ioctl()
  drm/vmwgfx: Type-check lookups of fence objects
  Revert "Revert "Revert "CHROMIUM: android: binder: Fix potential scheduling-while-atomic"""
  ANDROID: sdcardfs: Directly pass lower file for mmap
  UPSTREAM: checkpatch: special audit for revert commit line
  UPSTREAM: PM / sleep: make PM notifiers called symmetrically
  Revert "Revert "CHROMIUM: android: binder: Fix potential scheduling-while-atomic""
  Linux 4.4.60
  padata: avoid race in reordering
  blk: Ensure users for current->bio_list can see the full list.
  blk: improve order of bio handling in generic_make_request()
  power: reset: at91-poweroff: timely shutdown LPDDR memories
  KVM: kvm_io_bus_unregister_dev() should never fail
  rtc: s35390a: improve irq handling
  rtc: s35390a: implement reset routine as suggested by the reference
  rtc: s35390a: make sure all members in the output are set
  rtc: s35390a: fix reading out alarm
  MIPS: Lantiq: Fix cascaded IRQ setup
  mm, hugetlb: use pte_present() instead of pmd_present() in follow_huge_pmd()
  drm/radeon: Override fpfn for all VRAM placements in radeon_evict_flags
  KVM: x86: clear bus pointer when destroyed
  USB: fix linked-list corruption in rh_call_control()
  tty/serial: atmel: fix TX path in atmel_console_write()
  tty/serial: atmel: fix race condition (TX+DMA)
  ACPI: Do not create a platform_device for IOAPIC/IOxAPIC
  ACPI: Fix incompatibility with mcount-based function graph tracing
  ASoC: atmel-classd: fix audio clock rate
  ALSA: hda - fix a problem for lineout on a Dell AIO machine
  ALSA: seq: Fix race during FIFO resize
  scsi: libsas: fix ata xfer length
  scsi: sg: check length passed to SG_NEXT_CMD_LEN
  scsi: mpt3sas: fix hang on ata passthrough commands
  xen/setup: Don't relocate p2m over existing one
  libceph: force GFP_NOIO for socket allocations
  Linux 4.4.59
  sched/rt: Add a missing rescheduling point
  fscrypt: remove broken support for detecting keyring key revocation
  metag/ptrace: Reject partial NT_METAG_RPIPE writes
  metag/ptrace: Provide default TXSTATUS for short NT_PRSTATUS
  metag/ptrace: Preserve previous registers for short regset write
  sparc/ptrace: Preserve previous registers for short regset write
  mips/ptrace: Preserve previous registers for short regset write
  h8300/ptrace: Fix incorrect register transfer count
  c6x/ptrace: Remove useless PTRACE_SETREGSET implementation
  pinctrl: qcom: Don't clear status bit on irq_unmask
  virtio_balloon: init 1st buffer in stats vq
  xfrm_user: validate XFRM_MSG_NEWAE incoming ESN size harder
  xfrm_user: validate XFRM_MSG_NEWAE XFRMA_REPLAY_ESN_VAL replay_window
  xfrm: policy: init locks early

Conflicts:
	drivers/scsi/sd.c
	drivers/usb/gadget/function/f_mtp.c
	drivers/usb/gadget/function/u_ether.c

Change-Id: I80501cf02d04204f8c0f3a7f5a036eaa4d54546e
Signed-off-by: Blagovest Kolenichev <bkolenichev@codeaurora.org>

20 files changed, 587 insertions, 233 deletions

diff --git a/fs/Makefile b/fs/Makefile
index 3b54070cd629..dee237540bc0 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -41,7 +41,7 @@ obj-$(CONFIG_COMPAT_BINFMT_ELF)	+= compat_binfmt_elf.o
 obj-$(CONFIG_BINFMT_ELF_FDPIC)	+= binfmt_elf_fdpic.o
 obj-$(CONFIG_BINFMT_FLAT)	+= binfmt_flat.o
 
-obj-$(CONFIG_FS_MBCACHE)	+= mbcache.o
+obj-$(CONFIG_FS_MBCACHE)	+= mbcache.o mbcache2.o
 obj-$(CONFIG_FS_POSIX_ACL)	+= posix_acl.o
 obj-$(CONFIG_NFS_COMMON)	+= nfs_common/
 obj-$(CONFIG_COREDUMP)		+= coredump.o
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 72f270d4bd17..a0c0a49b6620 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -2545,7 +2545,7 @@ cifs_write_from_iter(loff_t offset, size_t len, struct iov_iter *from,
 		wdata->credits = credits;
 
 		if (!wdata->cfile->invalidHandle ||
-		    !cifs_reopen_file(wdata->cfile, false))
+		    !(rc = cifs_reopen_file(wdata->cfile, false)))
 			rc = server->ops->async_writev(wdata,
 					cifs_uncached_writedata_release);
 		if (rc) {
@@ -2958,7 +2958,7 @@ cifs_send_async_read(loff_t offset, size_t len, struct cifsFileInfo *open_file,
 		rdata->credits = credits;
 
 		if (!rdata->cfile->invalidHandle ||
-		    !cifs_reopen_file(rdata->cfile, true))
+		    !(rc = cifs_reopen_file(rdata->cfile, true)))
 			rc = server->ops->async_readv(rdata);
 error:
 		if (rc) {
@@ -3544,7 +3544,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,
 		}
 
 		if (!rdata->cfile->invalidHandle ||
-		    !cifs_reopen_file(rdata->cfile, true))
+		    !(rc = cifs_reopen_file(rdata->cfile, true)))
 			rc = server->ops->async_readv(rdata);
 		if (rc) {
 			add_credits_and_wake_if(server, rdata->credits, 0);
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 2fa754c5fd62..6cb5c4b30e78 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -952,6 +952,10 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
 		return -EINVAL;
 	}
 
+	/* SMB2 TREE_CONNECT request must be called with TreeId == 0 */
+	if (tcon)
+		tcon->tid = 0;
+
 	rc = small_smb2_init(SMB2_TREE_CONNECT, tcon, (void **) &req);
 	if (rc) {
 		kfree(unc_path);
diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h
index 4c69c94cafd8..f98ce7e60a0f 100644
--- a/fs/ext2/ext2.h
+++ b/fs/ext2/ext2.h
@@ -61,6 +61,8 @@ struct ext2_block_alloc_info {
 #define rsv_start rsv_window._rsv_start
 #define rsv_end rsv_window._rsv_end
 
+struct mb2_cache;
+
 /*
  * second extended-fs super-block data in memory
  */
@@ -111,6 +113,7 @@ struct ext2_sb_info {
 	 * of the mount options.
 	 */
 	spinlock_t s_lock;
+	struct mb2_cache *s_mb_cache;
 };
 
 static inline spinlock_t *
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 748d35afc902..111a31761ffa 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -131,7 +131,10 @@ static void ext2_put_super (struct super_block * sb)
 
 	dquot_disable(sb, -1, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED);
 
-	ext2_xattr_put_super(sb);
+	if (sbi->s_mb_cache) {
+		ext2_xattr_destroy_cache(sbi->s_mb_cache);
+		sbi->s_mb_cache = NULL;
+	}
 	if (!(sb->s_flags & MS_RDONLY)) {
 		struct ext2_super_block *es = sbi->s_es;
 
@@ -1104,6 +1107,14 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 		ext2_msg(sb, KERN_ERR, "error: insufficient memory");
 		goto failed_mount3;
 	}
+
+#ifdef CONFIG_EXT2_FS_XATTR
+	sbi->s_mb_cache = ext2_xattr_create_cache();
+	if (!sbi->s_mb_cache) {
+		ext2_msg(sb, KERN_ERR, "Failed to create an mb_cache");
+		goto failed_mount3;
+	}
+#endif
 	/*
 	 * set up enough so that it can read an inode
 	 */
@@ -1149,6 +1160,8 @@ cantfind_ext2:
 			sb->s_id);
 	goto failed_mount;
 failed_mount3:
+	if (sbi->s_mb_cache)
+		ext2_xattr_destroy_cache(sbi->s_mb_cache);
 	percpu_counter_destroy(&sbi->s_freeblocks_counter);
 	percpu_counter_destroy(&sbi->s_freeinodes_counter);
 	percpu_counter_destroy(&sbi->s_dirs_counter);
@@ -1555,20 +1568,17 @@ MODULE_ALIAS_FS("ext2");
 
 static int __init init_ext2_fs(void)
 {
-	int err = init_ext2_xattr();
-	if (err)
-		return err;
+	int err;
+
 	err = init_inodecache();
 	if (err)
-		goto out1;
+		return err;
         err = register_filesystem(&ext2_fs_type);
 	if (err)
 		goto out;
 	return 0;
 out:
 	destroy_inodecache();
-out1:
-	exit_ext2_xattr();
 	return err;
 }
 
@@ -1576,7 +1586,6 @@ static void __exit exit_ext2_fs(void)
 {
 	unregister_filesystem(&ext2_fs_type);
 	destroy_inodecache();
-	exit_ext2_xattr();
 }
 
 MODULE_AUTHOR("Remy Card and others");
diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c
index fa70848afa8f..24736c8b3d51 100644
--- a/fs/ext2/xattr.c
+++ b/fs/ext2/xattr.c
@@ -56,7 +56,7 @@
 #include <linux/buffer_head.h>
 #include <linux/init.h>
 #include <linux/slab.h>
-#include <linux/mbcache.h>
+#include <linux/mbcache2.h>
 #include <linux/quotaops.h>
 #include <linux/rwsem.h>
 #include <linux/security.h>
@@ -92,14 +92,12 @@
 static int ext2_xattr_set2(struct inode *, struct buffer_head *,
 			   struct ext2_xattr_header *);
 
-static int ext2_xattr_cache_insert(struct buffer_head *);
+static int ext2_xattr_cache_insert(struct mb2_cache *, struct buffer_head *);
 static struct buffer_head *ext2_xattr_cache_find(struct inode *,
 						 struct ext2_xattr_header *);
 static void ext2_xattr_rehash(struct ext2_xattr_header *,
 			      struct ext2_xattr_entry *);
 
-static struct mb_cache *ext2_xattr_cache;
-
 static const struct xattr_handler *ext2_xattr_handler_map[] = {
 	[EXT2_XATTR_INDEX_USER]		     = &ext2_xattr_user_handler,
 #ifdef CONFIG_EXT2_FS_POSIX_ACL
@@ -154,6 +152,7 @@ ext2_xattr_get(struct inode *inode, int name_index, const char *name,
 	size_t name_len, size;
 	char *end;
 	int error;
+	struct mb2_cache *ext2_mb_cache = EXT2_SB(inode->i_sb)->s_mb_cache;
 
 	ea_idebug(inode, "name=%d.%s, buffer=%p, buffer_size=%ld",
 		  name_index, name, buffer, (long)buffer_size);
@@ -198,7 +197,7 @@ bad_block:	ext2_error(inode->i_sb, "ext2_xattr_get",
 			goto found;
 		entry = next;
 	}
-	if (ext2_xattr_cache_insert(bh))
+	if (ext2_xattr_cache_insert(ext2_mb_cache, bh))
 		ea_idebug(inode, "cache insert failed");
 	error = -ENODATA;
 	goto cleanup;
@@ -211,7 +210,7 @@ found:
 	    le16_to_cpu(entry->e_value_offs) + size > inode->i_sb->s_blocksize)
 		goto bad_block;
 
-	if (ext2_xattr_cache_insert(bh))
+	if (ext2_xattr_cache_insert(ext2_mb_cache, bh))
 		ea_idebug(inode, "cache insert failed");
 	if (buffer) {
 		error = -ERANGE;
@@ -249,6 +248,7 @@ ext2_xattr_list(struct dentry *dentry, char *buffer, size_t buffer_size)
 	char *end;
 	size_t rest = buffer_size;
 	int error;
+	struct mb2_cache *ext2_mb_cache = EXT2_SB(inode->i_sb)->s_mb_cache;
 
 	ea_idebug(inode, "buffer=%p, buffer_size=%ld",
 		  buffer, (long)buffer_size);
@@ -283,7 +283,7 @@ bad_block:	ext2_error(inode->i_sb, "ext2_xattr_list",
 			goto bad_block;
 		entry = next;
 	}
-	if (ext2_xattr_cache_insert(bh))
+	if (ext2_xattr_cache_insert(ext2_mb_cache, bh))
 		ea_idebug(inode, "cache insert failed");
 
 	/* list the attribute names */
@@ -480,22 +480,23 @@ bad_block:		ext2_error(sb, "ext2_xattr_set",
 	/* Here we know that we can set the new attribute. */
 
 	if (header) {
-		struct mb_cache_entry *ce;
-
 		/* assert(header == HDR(bh)); */
-		ce = mb_cache_entry_get(ext2_xattr_cache, bh->b_bdev,
-					bh->b_blocknr);
 		lock_buffer(bh);
 		if (header->h_refcount == cpu_to_le32(1)) {
+			__u32 hash = le32_to_cpu(header->h_hash);
+
 			ea_bdebug(bh, "modifying in-place");
-			if (ce)
-				mb_cache_entry_free(ce);
+			/*
+			 * This must happen under buffer lock for
+			 * ext2_xattr_set2() to reliably detect modified block
+			 */
+			mb2_cache_entry_delete_block(EXT2_SB(sb)->s_mb_cache,
+						     hash, bh->b_blocknr);
+
 			/* keep the buffer locked while modifying it. */
 		} else {
 			int offset;
 
-			if (ce)
-				mb_cache_entry_release(ce);
 			unlock_buffer(bh);
 			ea_bdebug(bh, "cloning");
 			header = kmalloc(bh->b_size, GFP_KERNEL);
@@ -623,6 +624,7 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh,
 	struct super_block *sb = inode->i_sb;
 	struct buffer_head *new_bh = NULL;
 	int error;
+	struct mb2_cache *ext2_mb_cache = EXT2_SB(sb)->s_mb_cache;
 
 	if (header) {
 		new_bh = ext2_xattr_cache_find(inode, header);
@@ -650,7 +652,7 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh,
 			   don't need to change the reference count. */
 			new_bh = old_bh;
 			get_bh(new_bh);
-			ext2_xattr_cache_insert(new_bh);
+			ext2_xattr_cache_insert(ext2_mb_cache, new_bh);
 		} else {
 			/* We need to allocate a new block */
 			ext2_fsblk_t goal = ext2_group_first_block_no(sb,
@@ -671,7 +673,7 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh,
 			memcpy(new_bh->b_data, header, new_bh->b_size);
 			set_buffer_uptodate(new_bh);
 			unlock_buffer(new_bh);
-			ext2_xattr_cache_insert(new_bh);
+			ext2_xattr_cache_insert(ext2_mb_cache, new_bh);
 			
 			ext2_xattr_update_super_block(sb);
 		}
@@ -704,19 +706,21 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh,
 
 	error = 0;
 	if (old_bh && old_bh != new_bh) {
-		struct mb_cache_entry *ce;
-
 		/*
 		 * If there was an old block and we are no longer using it,
 		 * release the old block.
 		 */
-		ce = mb_cache_entry_get(ext2_xattr_cache, old_bh->b_bdev,
-					old_bh->b_blocknr);
 		lock_buffer(old_bh);
 		if (HDR(old_bh)->h_refcount == cpu_to_le32(1)) {
+			__u32 hash = le32_to_cpu(HDR(old_bh)->h_hash);
+
+			/*
+			 * This must happen under buffer lock for
+			 * ext2_xattr_set2() to reliably detect freed block
+			 */
+			mb2_cache_entry_delete_block(ext2_mb_cache,
+						     hash, old_bh->b_blocknr);
 			/* Free the old block. */
-			if (ce)
-				mb_cache_entry_free(ce);
 			ea_bdebug(old_bh, "freeing");
 			ext2_free_blocks(inode, old_bh->b_blocknr, 1);
 			mark_inode_dirty(inode);
@@ -727,8 +731,6 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh,
 		} else {
 			/* Decrement the refcount only. */
 			le32_add_cpu(&HDR(old_bh)->h_refcount, -1);
-			if (ce)
-				mb_cache_entry_release(ce);
 			dquot_free_block_nodirty(inode, 1);
 			mark_inode_dirty(inode);
 			mark_buffer_dirty(old_bh);
@@ -754,7 +756,6 @@ void
 ext2_xattr_delete_inode(struct inode *inode)
 {
 	struct buffer_head *bh = NULL;
-	struct mb_cache_entry *ce;
 
 	down_write(&EXT2_I(inode)->xattr_sem);
 	if (!EXT2_I(inode)->i_file_acl)
@@ -774,19 +775,22 @@ ext2_xattr_delete_inode(struct inode *inode)
 			EXT2_I(inode)->i_file_acl);
 		goto cleanup;
 	}
-	ce = mb_cache_entry_get(ext2_xattr_cache, bh->b_bdev, bh->b_blocknr);
 	lock_buffer(bh);
 	if (HDR(bh)->h_refcount == cpu_to_le32(1)) {
-		if (ce)
-			mb_cache_entry_free(ce);
+		__u32 hash = le32_to_cpu(HDR(bh)->h_hash);
+
+		/*
+		 * This must happen under buffer lock for ext2_xattr_set2() to
+		 * reliably detect freed block
+		 */
+		mb2_cache_entry_delete_block(EXT2_SB(inode->i_sb)->s_mb_cache,
+					     hash, bh->b_blocknr);
 		ext2_free_blocks(inode, EXT2_I(inode)->i_file_acl, 1);
 		get_bh(bh);
 		bforget(bh);
 		unlock_buffer(bh);
 	} else {
 		le32_add_cpu(&HDR(bh)->h_refcount, -1);
-		if (ce)
-			mb_cache_entry_release(ce);
 		ea_bdebug(bh, "refcount now=%d",
 			le32_to_cpu(HDR(bh)->h_refcount));
 		unlock_buffer(bh);
@@ -803,18 +807,6 @@ cleanup:
 }
 
 /*
- * ext2_xattr_put_super()
- *
- * This is called when a file system is unmounted.
- */
-void
-ext2_xattr_put_super(struct super_block *sb)
-{
-	mb_cache_shrink(sb->s_bdev);
-}
-
-
-/*
  * ext2_xattr_cache_insert()
  *
  * Create a new entry in the extended attribute cache, and insert
@@ -823,28 +815,20 @@ ext2_xattr_put_super(struct super_block *sb)
  * Returns 0, or a negative error number on failure.
  */
 static int
-ext2_xattr_cache_insert(struct buffer_head *bh)
+ext2_xattr_cache_insert(struct mb2_cache *cache, struct buffer_head *bh)
 {
 	__u32 hash = le32_to_cpu(HDR(bh)->h_hash);
-	struct mb_cache_entry *ce;
 	int error;
 
-	ce = mb_cache_entry_alloc(ext2_xattr_cache, GFP_NOFS);
-	if (!ce)
-		return -ENOMEM;
-	error = mb_cache_entry_insert(ce, bh->b_bdev, bh->b_blocknr, hash);
+	error = mb2_cache_entry_create(cache, GFP_NOFS, hash, bh->b_blocknr);
 	if (error) {
-		mb_cache_entry_free(ce);
 		if (error == -EBUSY) {
 			ea_bdebug(bh, "already in cache (%d cache entries)",
 				atomic_read(&ext2_xattr_cache->c_entry_count));
 			error = 0;
 		}
-	} else {
-		ea_bdebug(bh, "inserting [%x] (%d cache entries)", (int)hash,
-			  atomic_read(&ext2_xattr_cache->c_entry_count));
-		mb_cache_entry_release(ce);
-	}
+	} else
+		ea_bdebug(bh, "inserting [%x]", (int)hash);
 	return error;
 }
 
@@ -900,23 +884,17 @@ static struct buffer_head *
 ext2_xattr_cache_find(struct inode *inode, struct ext2_xattr_header *header)
 {
 	__u32 hash = le32_to_cpu(header->h_hash);
-	struct mb_cache_entry *ce;
+	struct mb2_cache_entry *ce;
+	struct mb2_cache *ext2_mb_cache = EXT2_SB(inode->i_sb)->s_mb_cache;
 
 	if (!header->h_hash)
 		return NULL;  /* never share */
 	ea_idebug(inode, "looking for cached blocks [%x]", (int)hash);
 again:
-	ce = mb_cache_entry_find_first(ext2_xattr_cache, inode->i_sb->s_bdev,
-				       hash);
+	ce = mb2_cache_entry_find_first(ext2_mb_cache, hash);
 	while (ce) {
 		struct buffer_head *bh;
 
-		if (IS_ERR(ce)) {
-			if (PTR_ERR(ce) == -EAGAIN)
-				goto again;
-			break;
-		}
-
 		bh = sb_bread(inode->i_sb, ce->e_block);
 		if (!bh) {
 			ext2_error(inode->i_sb, "ext2_xattr_cache_find",
@@ -924,7 +902,21 @@ again:
 				inode->i_ino, (unsigned long) ce->e_block);
 		} else {
 			lock_buffer(bh);
-			if (le32_to_cpu(HDR(bh)->h_refcount) >
+			/*
+			 * We have to be careful about races with freeing or
+			 * rehashing of xattr block. Once we hold buffer lock
+			 * xattr block's state is stable so we can check
+			 * whether the block got freed / rehashed or not.
+			 * Since we unhash mbcache entry under buffer lock when
+			 * freeing / rehashing xattr block, checking whether
+			 * entry is still hashed is reliable.
+			 */
+			if (hlist_bl_unhashed(&ce->e_hash_list)) {
+				mb2_cache_entry_put(ext2_mb_cache, ce);
+				unlock_buffer(bh);
+				brelse(bh);
+				goto again;
+			} else if (le32_to_cpu(HDR(bh)->h_refcount) >
 				   EXT2_XATTR_REFCOUNT_MAX) {
 				ea_idebug(inode, "block %ld refcount %d>%d",
 					  (unsigned long) ce->e_block,
@@ -933,13 +925,14 @@ again:
 			} else if (!ext2_xattr_cmp(header, HDR(bh))) {
 				ea_bdebug(bh, "b_count=%d",
 					  atomic_read(&(bh->b_count)));
-				mb_cache_entry_release(ce);
+				mb2_cache_entry_touch(ext2_mb_cache, ce);
+				mb2_cache_entry_put(ext2_mb_cache, ce);
 				return bh;
 			}
 			unlock_buffer(bh);
 			brelse(bh);
 		}
-		ce = mb_cache_entry_find_next(ce, inode->i_sb->s_bdev, hash);
+		ce = mb2_cache_entry_find_next(ext2_mb_cache, ce);
 	}
 	return NULL;
 }
@@ -1012,17 +1005,15 @@ static void ext2_xattr_rehash(struct ext2_xattr_header *header,
 
 #undef BLOCK_HASH_SHIFT
 
-int __init
-init_ext2_xattr(void)
+#define HASH_BUCKET_BITS 10
+
+struct mb2_cache *ext2_xattr_create_cache(void)
 {
-	ext2_xattr_cache = mb_cache_create("ext2_xattr", 6);
-	if (!ext2_xattr_cache)
-		return -ENOMEM;
-	return 0;
+	return mb2_cache_create(HASH_BUCKET_BITS);
 }
 
-void
-exit_ext2_xattr(void)
+void ext2_xattr_destroy_cache(struct mb2_cache *cache)
 {
-	mb_cache_destroy(ext2_xattr_cache);
+	if (cache)
+		mb2_cache_destroy(cache);
 }
diff --git a/fs/ext2/xattr.h b/fs/ext2/xattr.h
index 60edf298644e..6ea38aa9563a 100644
--- a/fs/ext2/xattr.h
+++ b/fs/ext2/xattr.h
@@ -53,6 +53,8 @@ struct ext2_xattr_entry {
 #define EXT2_XATTR_SIZE(size) \
 	(((size) + EXT2_XATTR_ROUND) & ~EXT2_XATTR_ROUND)
 
+struct mb2_cache;
+
 # ifdef CONFIG_EXT2_FS_XATTR
 
 extern const struct xattr_handler ext2_xattr_user_handler;
@@ -65,10 +67,9 @@ extern int ext2_xattr_get(struct inode *, int, const char *, void *, size_t);
 extern int ext2_xattr_set(struct inode *, int, const char *, const void *, size_t, int);
 
 extern void ext2_xattr_delete_inode(struct inode *);
-extern void ext2_xattr_put_super(struct super_block *);
 
-extern int init_ext2_xattr(void);
-extern void exit_ext2_xattr(void);
+extern struct mb2_cache *ext2_xattr_create_cache(void);
+extern void ext2_xattr_destroy_cache(struct mb2_cache *cache);
 
 extern const struct xattr_handler *ext2_xattr_handlers[];
 
@@ -93,19 +94,7 @@ ext2_xattr_delete_inode(struct inode *inode)
 {
 }
 
-static inline void
-ext2_xattr_put_super(struct super_block *sb)
-{
-}
-
-static inline int
-init_ext2_xattr(void)
-{
-	return 0;
-}
-
-static inline void
-exit_ext2_xattr(void)
+static inline void ext2_xattr_destroy_cache(struct mb2_cache *cache)
 {
 }
 
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 482d1caee849..6c910f127f1f 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1443,7 +1443,7 @@ struct ext4_sb_info {
 	struct list_head s_es_list;	/* List of inodes with reclaimable extents */
 	long s_es_nr_inode;
 	struct ext4_es_stats s_es_stats;
-	struct mb_cache *s_mb_cache;
+	struct mb2_cache *s_mb_cache;
 	spinlock_t s_es_lock ____cacheline_aligned_in_smp;
 
 	/* Ratelimit ext4 messages. */
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 72b384931f66..4caa0c1f77d8 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -73,10 +73,9 @@ static __u32 ext4_inode_csum(struct inode *inode, struct ext4_inode *raw,
 			csum = ext4_chksum(sbi, csum, (__u8 *)&dummy_csum,
 					   csum_size);
 			offset += csum_size;
-			csum = ext4_chksum(sbi, csum, (__u8 *)raw + offset,
-					   EXT4_INODE_SIZE(inode->i_sb) -
-					   offset);
 		}
+		csum = ext4_chksum(sbi, csum, (__u8 *)raw + offset,
+				   EXT4_INODE_SIZE(inode->i_sb) - offset);
 	}
 
 	return csum;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 68345a9e59b8..bd8831bfbafe 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -816,7 +816,6 @@ static void ext4_put_super(struct super_block *sb)
 	ext4_release_system_zone(sb);
 	ext4_mb_release(sb);
 	ext4_ext_release(sb);
-	ext4_xattr_put_super(sb);
 
 	if (!(sb->s_flags & MS_RDONLY) && !aborted) {
 		ext4_clear_feature_journal_needs_recovery(sb);
@@ -3833,7 +3832,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 
 no_journal:
 	if (ext4_mballoc_ready) {
-		sbi->s_mb_cache = ext4_xattr_create_cache(sb->s_id);
+		sbi->s_mb_cache = ext4_xattr_create_cache();
 		if (!sbi->s_mb_cache) {
 			ext4_msg(sb, KERN_ERR, "Failed to create an mb_cache");
 			goto failed_mount_wq;
@@ -4065,6 +4064,10 @@ failed_mount4:
 	if (EXT4_SB(sb)->rsv_conversion_wq)
 		destroy_workqueue(EXT4_SB(sb)->rsv_conversion_wq);
 failed_mount_wq:
+	if (sbi->s_mb_cache) {
+		ext4_xattr_destroy_cache(sbi->s_mb_cache);
+		sbi->s_mb_cache = NULL;
+	}
 	if (sbi->s_journal) {
 		jbd2_journal_destroy(sbi->s_journal);
 		sbi->s_journal = NULL;
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 7c23363ecf19..b310ed81c10e 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -53,7 +53,7 @@
 #include <linux/init.h>
 #include <linux/fs.h>
 #include <linux/slab.h>
-#include <linux/mbcache.h>
+#include <linux/mbcache2.h>
 #include <linux/quotaops.h>
 #include "ext4_jbd2.h"
 #include "ext4.h"
@@ -80,10 +80,10 @@
 # define ea_bdebug(bh, fmt, ...)	no_printk(fmt, ##__VA_ARGS__)
 #endif
 
-static void ext4_xattr_cache_insert(struct mb_cache *, struct buffer_head *);
+static void ext4_xattr_cache_insert(struct mb2_cache *, struct buffer_head *);
 static struct buffer_head *ext4_xattr_cache_find(struct inode *,
 						 struct ext4_xattr_header *,
-						 struct mb_cache_entry **);
+						 struct mb2_cache_entry **);
 static void ext4_xattr_rehash(struct ext4_xattr_header *,
 			      struct ext4_xattr_entry *);
 static int ext4_xattr_list(struct dentry *dentry, char *buffer,
@@ -300,7 +300,7 @@ ext4_xattr_block_get(struct inode *inode, int name_index, const char *name,
 	struct ext4_xattr_entry *entry;
 	size_t size;
 	int error;
-	struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
+	struct mb2_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
 
 	ea_idebug(inode, "name=%d.%s, buffer=%p, buffer_size=%ld",
 		  name_index, name, buffer, (long)buffer_size);
@@ -447,7 +447,7 @@ ext4_xattr_block_list(struct dentry *dentry, char *buffer, size_t buffer_size)
 	struct inode *inode = d_inode(dentry);
 	struct buffer_head *bh = NULL;
 	int error;
-	struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
+	struct mb2_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
 
 	ea_idebug(inode, "buffer=%p, buffer_size=%ld",
 		  buffer, (long)buffer_size);
@@ -564,11 +564,8 @@ static void
 ext4_xattr_release_block(handle_t *handle, struct inode *inode,
 			 struct buffer_head *bh)
 {
-	struct mb_cache_entry *ce = NULL;
 	int error = 0;
-	struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
 
-	ce = mb_cache_entry_get(ext4_mb_cache, bh->b_bdev, bh->b_blocknr);
 	BUFFER_TRACE(bh, "get_write_access");
 	error = ext4_journal_get_write_access(handle, bh);
 	if (error)
@@ -576,9 +573,15 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode,
 
 	lock_buffer(bh);
 	if (BHDR(bh)->h_refcount == cpu_to_le32(1)) {
+		__u32 hash = le32_to_cpu(BHDR(bh)->h_hash);
+
 		ea_bdebug(bh, "refcount now=0; freeing");
-		if (ce)
-			mb_cache_entry_free(ce);
+		/*
+		 * This must happen under buffer lock for
+		 * ext4_xattr_block_set() to reliably detect freed block
+		 */
+		mb2_cache_entry_delete_block(EXT4_GET_MB_CACHE(inode), hash,
+					     bh->b_blocknr);
 		get_bh(bh);
 		unlock_buffer(bh);
 		ext4_free_blocks(handle, inode, bh, 0, 1,
@@ -586,8 +589,6 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode,
 				 EXT4_FREE_BLOCKS_FORGET);
 	} else {
 		le32_add_cpu(&BHDR(bh)->h_refcount, -1);
-		if (ce)
-			mb_cache_entry_release(ce);
 		/*
 		 * Beware of this ugliness: Releasing of xattr block references
 		 * from different inodes can race and so we have to protect
@@ -800,17 +801,15 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
 	struct super_block *sb = inode->i_sb;
 	struct buffer_head *new_bh = NULL;
 	struct ext4_xattr_search *s = &bs->s;
-	struct mb_cache_entry *ce = NULL;
+	struct mb2_cache_entry *ce = NULL;
 	int error = 0;
-	struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
+	struct mb2_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
 
 #define header(x) ((struct ext4_xattr_header *)(x))
 
 	if (i->value && i->value_len > sb->s_blocksize)
 		return -ENOSPC;
 	if (s->base) {
-		ce = mb_cache_entry_get(ext4_mb_cache, bs->bh->b_bdev,
-					bs->bh->b_blocknr);
 		BUFFER_TRACE(bs->bh, "get_write_access");
 		error = ext4_journal_get_write_access(handle, bs->bh);
 		if (error)
@@ -818,10 +817,15 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
 		lock_buffer(bs->bh);
 
 		if (header(s->base)->h_refcount == cpu_to_le32(1)) {
-			if (ce) {
-				mb_cache_entry_free(ce);
-				ce = NULL;
-			}
+			__u32 hash = le32_to_cpu(BHDR(bs->bh)->h_hash);
+
+			/*
+			 * This must happen under buffer lock for
+			 * ext4_xattr_block_set() to reliably detect modified
+			 * block
+			 */
+			mb2_cache_entry_delete_block(ext4_mb_cache, hash,
+						     bs->bh->b_blocknr);
 			ea_bdebug(bs->bh, "modifying in-place");
 			error = ext4_xattr_set_entry(i, s);
 			if (!error) {
@@ -845,10 +849,6 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
 			int offset = (char *)s->here - bs->bh->b_data;
 
 			unlock_buffer(bs->bh);
-			if (ce) {
-				mb_cache_entry_release(ce);
-				ce = NULL;
-			}
 			ea_bdebug(bs->bh, "cloning");
 			s->base = kmalloc(bs->bh->b_size, GFP_NOFS);
 			error = -ENOMEM;
@@ -903,6 +903,31 @@ inserted:
 				if (error)
 					goto cleanup_dquot;
 				lock_buffer(new_bh);
+				/*
+				 * We have to be careful about races with
+				 * freeing or rehashing of xattr block. Once we
+				 * hold buffer lock xattr block's state is
+				 * stable so we can check whether the block got
+				 * freed / rehashed or not.  Since we unhash
+				 * mbcache entry under buffer lock when freeing
+				 * / rehashing xattr block, checking whether
+				 * entry is still hashed is reliable.
+				 */
+				if (hlist_bl_unhashed(&ce->e_hash_list)) {
+					/*
+					 * Undo everything and check mbcache
+					 * again.
+					 */
+					unlock_buffer(new_bh);
+					dquot_free_block(inode,
+							 EXT4_C2B(EXT4_SB(sb),
+								  1));
+					brelse(new_bh);
+					mb2_cache_entry_put(ext4_mb_cache, ce);
+					ce = NULL;
+					new_bh = NULL;
+					goto inserted;
+				}
 				le32_add_cpu(&BHDR(new_bh)->h_refcount, 1);
 				ea_bdebug(new_bh, "reusing; refcount now=%d",
 					le32_to_cpu(BHDR(new_bh)->h_refcount));
@@ -913,7 +938,8 @@ inserted:
 				if (error)
 					goto cleanup_dquot;
 			}
-			mb_cache_entry_release(ce);
+			mb2_cache_entry_touch(ext4_mb_cache, ce);
+			mb2_cache_entry_put(ext4_mb_cache, ce);
 			ce = NULL;
 		} else if (bs->bh && s->base == bs->bh->b_data) {
 			/* We were modifying this block in-place. */
@@ -978,7 +1004,7 @@ getblk_failed:
 
 cleanup:
 	if (ce)
-		mb_cache_entry_release(ce);
+		mb2_cache_entry_put(ext4_mb_cache, ce);
 	brelse(new_bh);
 	if (!(bs->bh && s->base == bs->bh->b_data))
 		kfree(s->base);
@@ -1543,17 +1569,6 @@ cleanup:
 }
 
 /*
- * ext4_xattr_put_super()
- *
- * This is called when a file system is unmounted.
- */
-void
-ext4_xattr_put_super(struct super_block *sb)
-{
-	mb_cache_shrink(sb->s_bdev);
-}
-
-/*
  * ext4_xattr_cache_insert()
  *
  * Create a new entry in the extended attribute cache, and insert
@@ -1562,28 +1577,18 @@ ext4_xattr_put_super(struct super_block *sb)
  * Returns 0, or a negative error number on failure.
  */
 static void
-ext4_xattr_cache_insert(struct mb_cache *ext4_mb_cache, struct buffer_head *bh)
+ext4_xattr_cache_insert(struct mb2_cache *ext4_mb_cache, struct buffer_head *bh)
 {
 	__u32 hash = le32_to_cpu(BHDR(bh)->h_hash);
-	struct mb_cache_entry *ce;
 	int error;
 
-	ce = mb_cache_entry_alloc(ext4_mb_cache, GFP_NOFS);
-	if (!ce) {
-		ea_bdebug(bh, "out of memory");
-		return;
-	}
-	error = mb_cache_entry_insert(ce, bh->b_bdev, bh->b_blocknr, hash);
+	error = mb2_cache_entry_create(ext4_mb_cache, GFP_NOFS, hash,
+				       bh->b_blocknr);
 	if (error) {
-		mb_cache_entry_free(ce);
-		if (error == -EBUSY) {
+		if (error == -EBUSY)
 			ea_bdebug(bh, "already in cache");
-			error = 0;
-		}
-	} else {
+	} else
 		ea_bdebug(bh, "inserting [%x]", (int)hash);
-		mb_cache_entry_release(ce);
-	}
 }
 
 /*
@@ -1636,26 +1641,19 @@ ext4_xattr_cmp(struct ext4_xattr_header *header1,
  */
 static struct buffer_head *
 ext4_xattr_cache_find(struct inode *inode, struct ext4_xattr_header *header,
-		      struct mb_cache_entry **pce)
+		      struct mb2_cache_entry **pce)
 {
 	__u32 hash = le32_to_cpu(header->h_hash);
-	struct mb_cache_entry *ce;
-	struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
+	struct mb2_cache_entry *ce;
+	struct mb2_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
 
 	if (!header->h_hash)
 		return NULL;  /* never share */
 	ea_idebug(inode, "looking for cached blocks [%x]", (int)hash);
-again:
-	ce = mb_cache_entry_find_first(ext4_mb_cache, inode->i_sb->s_bdev,
-				       hash);
+	ce = mb2_cache_entry_find_first(ext4_mb_cache, hash);
 	while (ce) {
 		struct buffer_head *bh;
 
-		if (IS_ERR(ce)) {
-			if (PTR_ERR(ce) == -EAGAIN)
-				goto again;
-			break;
-		}
 		bh = sb_bread(inode->i_sb, ce->e_block);
 		if (!bh) {
 			EXT4_ERROR_INODE(inode, "block %lu read error",
@@ -1671,7 +1669,7 @@ again:
 			return bh;
 		}
 		brelse(bh);
-		ce = mb_cache_entry_find_next(ce, inode->i_sb->s_bdev, hash);
+		ce = mb2_cache_entry_find_next(ext4_mb_cache, ce);
 	}
 	return NULL;
 }
@@ -1746,15 +1744,15 @@ static void ext4_xattr_rehash(struct ext4_xattr_header *header,
 
 #define	HASH_BUCKET_BITS	10
 
-struct mb_cache *
-ext4_xattr_create_cache(char *name)
+struct mb2_cache *
+ext4_xattr_create_cache(void)
 {
-	return mb_cache_create(name, HASH_BUCKET_BITS);
+	return mb2_cache_create(HASH_BUCKET_BITS);
 }
 
-void ext4_xattr_destroy_cache(struct mb_cache *cache)
+void ext4_xattr_destroy_cache(struct mb2_cache *cache)
 {
 	if (cache)
-		mb_cache_destroy(cache);
+		mb2_cache_destroy(cache);
 }
 
diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h
index ddc0957760ba..10b0f7323ed6 100644
--- a/fs/ext4/xattr.h
+++ b/fs/ext4/xattr.h
@@ -108,7 +108,6 @@ extern int ext4_xattr_set(struct inode *, int, const char *, const void *, size_
 extern int ext4_xattr_set_handle(handle_t *, struct inode *, int, const char *, const void *, size_t, int);
 
 extern void ext4_xattr_delete_inode(handle_t *, struct inode *);
-extern void ext4_xattr_put_super(struct super_block *);
 
 extern int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize,
 			    struct ext4_inode *raw_inode, handle_t *handle);
@@ -124,8 +123,8 @@ extern int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode,
 				       struct ext4_xattr_info *i,
 				       struct ext4_xattr_ibody_find *is);
 
-extern struct mb_cache *ext4_xattr_create_cache(char *name);
-extern void ext4_xattr_destroy_cache(struct mb_cache *);
+extern struct mb2_cache *ext4_xattr_create_cache(void);
+extern void ext4_xattr_destroy_cache(struct mb2_cache *);
 
 #ifdef CONFIG_EXT4_FS_SECURITY
 extern int ext4_init_security(handle_t *handle, struct inode *inode,
diff --git a/fs/mbcache2.c b/fs/mbcache2.c
new file mode 100644
index 000000000000..5c3e1a8c38f6
--- /dev/null
+++ b/fs/mbcache2.c
@@ -0,0 +1,359 @@
+#include <linux/spinlock.h>
+#include <linux/slab.h>
+#include <linux/list.h>
+#include <linux/list_bl.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/mbcache2.h>
+
+/*
+ * Mbcache is a simple key-value store. Keys need not be unique, however
+ * key-value pairs are expected to be unique (we use this fact in
+ * mb2_cache_entry_delete_block()).
+ *
+ * Ext2 and ext4 use this cache for deduplication of extended attribute blocks.
+ * They use hash of a block contents as a key and block number as a value.
+ * That's why keys need not be unique (different xattr blocks may end up having
+ * the same hash). However block number always uniquely identifies a cache
+ * entry.
+ *
+ * We provide functions for creation and removal of entries, search by key,
+ * and a special "delete entry with given key-value pair" operation. Fixed
+ * size hash table is used for fast key lookups.
+ */
+
+struct mb2_cache {
+	/* Hash table of entries */
+	struct hlist_bl_head	*c_hash;
+	/* log2 of hash table size */
+	int			c_bucket_bits;
+	/* Protects c_lru_list, c_entry_count */
+	spinlock_t		c_lru_list_lock;
+	struct list_head	c_lru_list;
+	/* Number of entries in cache */
+	unsigned long		c_entry_count;
+	struct shrinker		c_shrink;
+};
+
+static struct kmem_cache *mb2_entry_cache;
+
+/*
+ * mb2_cache_entry_create - create entry in cache
+ * @cache - cache where the entry should be created
+ * @mask - gfp mask with which the entry should be allocated
+ * @key - key of the entry
+ * @block - block that contains data
+ *
+ * Creates entry in @cache with key @key and records that data is stored in
+ * block @block. The function returns -EBUSY if entry with the same key
+ * and for the same block already exists in cache. Otherwise 0 is returned.
+ */
+int mb2_cache_entry_create(struct mb2_cache *cache, gfp_t mask, u32 key,
+			   sector_t block)
+{
+	struct mb2_cache_entry *entry, *dup;
+	struct hlist_bl_node *dup_node;
+	struct hlist_bl_head *head;
+
+	entry = kmem_cache_alloc(mb2_entry_cache, mask);
+	if (!entry)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&entry->e_lru_list);
+	/* One ref for hash, one ref returned */
+	atomic_set(&entry->e_refcnt, 1);
+	entry->e_key = key;
+	entry->e_block = block;
+	head = &cache->c_hash[hash_32(key, cache->c_bucket_bits)];
+	entry->e_hash_list_head = head;
+	hlist_bl_lock(head);
+	hlist_bl_for_each_entry(dup, dup_node, head, e_hash_list) {
+		if (dup->e_key == key && dup->e_block == block) {
+			hlist_bl_unlock(head);
+			kmem_cache_free(mb2_entry_cache, entry);
+			return -EBUSY;
+		}
+	}
+	hlist_bl_add_head(&entry->e_hash_list, head);
+	hlist_bl_unlock(head);
+
+	spin_lock(&cache->c_lru_list_lock);
+	list_add_tail(&entry->e_lru_list, &cache->c_lru_list);
+	/* Grab ref for LRU list */
+	atomic_inc(&entry->e_refcnt);
+	cache->c_entry_count++;
+	spin_unlock(&cache->c_lru_list_lock);
+
+	return 0;
+}
+EXPORT_SYMBOL(mb2_cache_entry_create);
+
+void __mb2_cache_entry_free(struct mb2_cache_entry *entry)
+{
+	kmem_cache_free(mb2_entry_cache, entry);
+}
+EXPORT_SYMBOL(__mb2_cache_entry_free);
+
+static struct mb2_cache_entry *__entry_find(struct mb2_cache *cache,
+					    struct mb2_cache_entry *entry,
+					    u32 key)
+{
+	struct mb2_cache_entry *old_entry = entry;
+	struct hlist_bl_node *node;
+	struct hlist_bl_head *head;
+
+	if (entry)
+		head = entry->e_hash_list_head;
+	else
+		head = &cache->c_hash[hash_32(key, cache->c_bucket_bits)];
+	hlist_bl_lock(head);
+	if (entry && !hlist_bl_unhashed(&entry->e_hash_list))
+		node = entry->e_hash_list.next;
+	else
+		node = hlist_bl_first(head);
+	while (node) {
+		entry = hlist_bl_entry(node, struct mb2_cache_entry,
+				       e_hash_list);
+		if (entry->e_key == key) {
+			atomic_inc(&entry->e_refcnt);
+			goto out;
+		}
+		node = node->next;
+	}
+	entry = NULL;
+out:
+	hlist_bl_unlock(head);
+	if (old_entry)
+		mb2_cache_entry_put(cache, old_entry);
+
+	return entry;
+}
+
+/*
+ * mb2_cache_entry_find_first - find the first entry in cache with given key
+ * @cache: cache where we should search
+ * @key: key to look for
+ *
+ * Search in @cache for entry with key @key. Grabs reference to the first
+ * entry found and returns the entry.
+ */
+struct mb2_cache_entry *mb2_cache_entry_find_first(struct mb2_cache *cache,
+						   u32 key)
+{
+	return __entry_find(cache, NULL, key);
+}
+EXPORT_SYMBOL(mb2_cache_entry_find_first);
+
+/*
+ * mb2_cache_entry_find_next - find next entry in cache with the same
+ * @cache: cache where we should search
+ * @entry: entry to start search from
+ *
+ * Finds next entry in the hash chain which has the same key as @entry.
+ * If @entry is unhashed (which can happen when deletion of entry races
+ * with the search), finds the first entry in the hash chain. The function
+ * drops reference to @entry and returns with a reference to the found entry.
+ */
+struct mb2_cache_entry *mb2_cache_entry_find_next(struct mb2_cache *cache,
+						  struct mb2_cache_entry *entry)
+{
+	return __entry_find(cache, entry, entry->e_key);
+}
+EXPORT_SYMBOL(mb2_cache_entry_find_next);
+
+/* mb2_cache_entry_delete_block - remove information about block from cache
+ * @cache - cache we work with
+ * @key - key of the entry to remove
+ * @block - block containing data for @key
+ *
+ * Remove entry from cache @cache with key @key with data stored in @block.
+ */
+void mb2_cache_entry_delete_block(struct mb2_cache *cache, u32 key,
+				  sector_t block)
+{
+	struct hlist_bl_node *node;
+	struct hlist_bl_head *head;
+	struct mb2_cache_entry *entry;
+
+	head = &cache->c_hash[hash_32(key, cache->c_bucket_bits)];
+	hlist_bl_lock(head);
+	hlist_bl_for_each_entry(entry, node, head, e_hash_list) {
+		if (entry->e_key == key && entry->e_block == block) {
+			/* We keep hash list reference to keep entry alive */
+			hlist_bl_del_init(&entry->e_hash_list);
+			hlist_bl_unlock(head);
+			spin_lock(&cache->c_lru_list_lock);
+			if (!list_empty(&entry->e_lru_list)) {
+				list_del_init(&entry->e_lru_list);
+				cache->c_entry_count--;
+				atomic_dec(&entry->e_refcnt);
+			}
+			spin_unlock(&cache->c_lru_list_lock);
+			mb2_cache_entry_put(cache, entry);
+			return;
+		}
+	}
+	hlist_bl_unlock(head);
+}
+EXPORT_SYMBOL(mb2_cache_entry_delete_block);
+
+/* mb2_cache_entry_touch - cache entry got used
+ * @cache - cache the entry belongs to
+ * @entry - entry that got used
+ *
+ * Move entry in lru list to reflect the fact that it was used.
+ */
+void mb2_cache_entry_touch(struct mb2_cache *cache,
+			   struct mb2_cache_entry *entry)
+{
+	spin_lock(&cache->c_lru_list_lock);
+	if (!list_empty(&entry->e_lru_list))
+		list_move_tail(&cache->c_lru_list, &entry->e_lru_list);
+	spin_unlock(&cache->c_lru_list_lock);
+}
+EXPORT_SYMBOL(mb2_cache_entry_touch);
+
+static unsigned long mb2_cache_count(struct shrinker *shrink,
+				     struct shrink_control *sc)
+{
+	struct mb2_cache *cache = container_of(shrink, struct mb2_cache,
+					       c_shrink);
+
+	return cache->c_entry_count;
+}
+
+/* Shrink number of entries in cache */
+static unsigned long mb2_cache_scan(struct shrinker *shrink,
+				    struct shrink_control *sc)
+{
+	int nr_to_scan = sc->nr_to_scan;
+	struct mb2_cache *cache = container_of(shrink, struct mb2_cache,
+					      c_shrink);
+	struct mb2_cache_entry *entry;
+	struct hlist_bl_head *head;
+	unsigned int shrunk = 0;
+
+	spin_lock(&cache->c_lru_list_lock);
+	while (nr_to_scan-- && !list_empty(&cache->c_lru_list)) {
+		entry = list_first_entry(&cache->c_lru_list,
+					 struct mb2_cache_entry, e_lru_list);
+		list_del_init(&entry->e_lru_list);
+		cache->c_entry_count--;
+		/*
+		 * We keep LRU list reference so that entry doesn't go away
+		 * from under us.
+		 */
+		spin_unlock(&cache->c_lru_list_lock);
+		head = entry->e_hash_list_head;
+		hlist_bl_lock(head);
+		if (!hlist_bl_unhashed(&entry->e_hash_list)) {
+			hlist_bl_del_init(&entry->e_hash_list);
+			atomic_dec(&entry->e_refcnt);
+		}
+		hlist_bl_unlock(head);
+		if (mb2_cache_entry_put(cache, entry))
+			shrunk++;
+		cond_resched();
+		spin_lock(&cache->c_lru_list_lock);
+	}
+	spin_unlock(&cache->c_lru_list_lock);
+
+	return shrunk;
+}
+
+/*
+ * mb2_cache_create - create cache
+ * @bucket_bits: log2 of the hash table size
+ *
+ * Create cache for keys with 2^bucket_bits hash entries.
+ */
+struct mb2_cache *mb2_cache_create(int bucket_bits)
+{
+	struct mb2_cache *cache;
+	int bucket_count = 1 << bucket_bits;
+	int i;
+
+	if (!try_module_get(THIS_MODULE))
+		return NULL;
+
+	cache = kzalloc(sizeof(struct mb2_cache), GFP_KERNEL);
+	if (!cache)
+		goto err_out;
+	cache->c_bucket_bits = bucket_bits;
+	INIT_LIST_HEAD(&cache->c_lru_list);
+	spin_lock_init(&cache->c_lru_list_lock);
+	cache->c_hash = kmalloc(bucket_count * sizeof(struct hlist_bl_head),
+				GFP_KERNEL);
+	if (!cache->c_hash) {
+		kfree(cache);
+		goto err_out;
+	}
+	for (i = 0; i < bucket_count; i++)
+		INIT_HLIST_BL_HEAD(&cache->c_hash[i]);
+
+	cache->c_shrink.count_objects = mb2_cache_count;
+	cache->c_shrink.scan_objects = mb2_cache_scan;
+	cache->c_shrink.seeks = DEFAULT_SEEKS;
+	register_shrinker(&cache->c_shrink);
+
+	return cache;
+
+err_out:
+	module_put(THIS_MODULE);
+	return NULL;
+}
+EXPORT_SYMBOL(mb2_cache_create);
+
+/*
+ * mb2_cache_destroy - destroy cache
+ * @cache: the cache to destroy
+ *
+ * Free all entries in cache and cache itself. Caller must make sure nobody
+ * (except shrinker) can reach @cache when calling this.
+ */
+void mb2_cache_destroy(struct mb2_cache *cache)
+{
+	struct mb2_cache_entry *entry, *next;
+
+	unregister_shrinker(&cache->c_shrink);
+
+	/*
+	 * We don't bother with any locking. Cache must not be used at this
+	 * point.
+	 */
+	list_for_each_entry_safe(entry, next, &cache->c_lru_list, e_lru_list) {
+		if (!hlist_bl_unhashed(&entry->e_hash_list)) {
+			hlist_bl_del_init(&entry->e_hash_list);
+			atomic_dec(&entry->e_refcnt);
+		} else
+			WARN_ON(1);
+		list_del(&entry->e_lru_list);
+		WARN_ON(atomic_read(&entry->e_refcnt) != 1);
+		mb2_cache_entry_put(cache, entry);
+	}
+	kfree(cache->c_hash);
+	kfree(cache);
+	module_put(THIS_MODULE);
+}
+EXPORT_SYMBOL(mb2_cache_destroy);
+
+static int __init mb2cache_init(void)
+{
+	mb2_entry_cache = kmem_cache_create("mbcache",
+				sizeof(struct mb2_cache_entry), 0,
+				SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD, NULL);
+	BUG_ON(!mb2_entry_cache);
+	return 0;
+}
+
+static void __exit mb2cache_exit(void)
+{
+	kmem_cache_destroy(mb2_entry_cache);
+}
+
+module_init(mb2cache_init)
+module_exit(mb2cache_exit)
+
+MODULE_AUTHOR("Jan Kara <jack@suse.cz>");
+MODULE_DESCRIPTION("Meta block cache (for extended attributes)");
+MODULE_LICENSE("GPL");
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 6a44fb94228c..fc5243c331c4 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -867,7 +867,14 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma,
 static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma,
 		unsigned long addr, pmd_t *pmdp)
 {
-	pmd_t pmd = pmdp_huge_get_and_clear(vma->vm_mm, addr, pmdp);
+	pmd_t pmd = *pmdp;
+
+	/* See comment in change_huge_pmd() */
+	pmdp_invalidate(vma, addr, pmdp);
+	if (pmd_dirty(*pmdp))
+		pmd = pmd_mkdirty(pmd);
+	if (pmd_young(*pmdp))
+		pmd = pmd_mkyoung(pmd);
 
 	pmd = pmd_wrprotect(pmd);
 	pmd = pmd_clear_soft_dirty(pmd);
diff --git a/fs/sdcardfs/derived_perm.c b/fs/sdcardfs/derived_perm.c
index f82fedd29007..cddfc79ea365 100644
--- a/fs/sdcardfs/derived_perm.c
+++ b/fs/sdcardfs/derived_perm.c
@@ -222,7 +222,7 @@ void fixup_lower_ownership(struct dentry *dentry, const char *name)
 		break;
 	case PERM_ANDROID_PACKAGE_CACHE:
 		if (info->d_uid != 0)
-			gid = multiuser_get_cache_gid(info->d_uid);
+			gid = multiuser_get_ext_cache_gid(info->d_uid);
 		else
 			gid = multiuser_get_uid(info->userid, uid);
 		break;
@@ -252,7 +252,7 @@ retry_deleg:
 				goto retry_deleg;
 		}
 		if (error)
-			pr_err("sdcardfs: Failed to touch up lower fs gid/uid.\n");
+			pr_debug("sdcardfs: Failed to touch up lower fs gid/uid for %s\n", name);
 	}
 	sdcardfs_put_lower_path(dentry, &path);
 }
diff --git a/fs/sdcardfs/file.c b/fs/sdcardfs/file.c
index c0146e03fa2e..1f6921e2ffbf 100644
--- a/fs/sdcardfs/file.c
+++ b/fs/sdcardfs/file.c
@@ -192,6 +192,9 @@ static int sdcardfs_mmap(struct file *file, struct vm_area_struct *vma)
 	file->f_mapping->a_ops = &sdcardfs_aops; /* set our aops */
 	if (!SDCARDFS_F(file)->lower_vm_ops) /* save for our ->fault */
 		SDCARDFS_F(file)->lower_vm_ops = saved_vm_ops;
+	vma->vm_private_data = file;
+	get_file(lower_file);
+	vma->vm_file = lower_file;
 
 out:
 	return err;
diff --git a/fs/sdcardfs/lookup.c b/fs/sdcardfs/lookup.c
index f10f7752f514..a0f221501b4c 100644
--- a/fs/sdcardfs/lookup.c
+++ b/fs/sdcardfs/lookup.c
@@ -91,7 +91,9 @@ struct inode *sdcardfs_iget(struct super_block *sb, struct inode *lower_inode, u
 	struct sdcardfs_inode_info *info;
 	struct inode_data data;
 	struct inode *inode; /* the new inode to return */
-	int err;
+
+	if (!igrab(lower_inode))
+		return ERR_PTR(-ESTALE);
 
 	data.id = id;
 	data.lower_inode = lower_inode;
@@ -106,22 +108,19 @@ struct inode *sdcardfs_iget(struct super_block *sb, struct inode *lower_inode, u
 			     sdcardfs_inode_set, /* inode init function */
 			     &data); /* data passed to test+set fxns */
 	if (!inode) {
-		err = -EACCES;
 		iput(lower_inode);
-		return ERR_PTR(err);
+		return ERR_PTR(-ENOMEM);
 	}
-	/* if found a cached inode, then just return it */
-	if (!(inode->i_state & I_NEW))
+	/* if found a cached inode, then just return it (after iput) */
+	if (!(inode->i_state & I_NEW)) {
+		iput(lower_inode);
 		return inode;
+	}
 
 	/* initialize new inode */
 	info = SDCARDFS_I(inode);
 
 	inode->i_ino = lower_inode->i_ino;
-	if (!igrab(lower_inode)) {
-		err = -ESTALE;
-		return ERR_PTR(err);
-	}
 	sdcardfs_set_lower_inode(inode, lower_inode);
 
 	inode->i_version++;
diff --git a/fs/sdcardfs/mmap.c b/fs/sdcardfs/mmap.c
index 0d4089c62c3a..b61f82275e7d 100644
--- a/fs/sdcardfs/mmap.c
+++ b/fs/sdcardfs/mmap.c
@@ -23,60 +23,45 @@
 static int sdcardfs_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	int err;
-	struct file *file, *lower_file;
+	struct file *file;
 	const struct vm_operations_struct *lower_vm_ops;
-	struct vm_area_struct lower_vma;
 
-	memcpy(&lower_vma, vma, sizeof(struct vm_area_struct));
-	file = lower_vma.vm_file;
+	file = (struct file *)vma->vm_private_data;
 	lower_vm_ops = SDCARDFS_F(file)->lower_vm_ops;
 	BUG_ON(!lower_vm_ops);
 
-	lower_file = sdcardfs_lower_file(file);
-	/*
-	 * XXX: vm_ops->fault may be called in parallel.  Because we have to
-	 * resort to temporarily changing the vma->vm_file to point to the
-	 * lower file, a concurrent invocation of sdcardfs_fault could see a
-	 * different value.  In this workaround, we keep a different copy of
-	 * the vma structure in our stack, so we never expose a different
-	 * value of the vma->vm_file called to us, even temporarily.  A
-	 * better fix would be to change the calling semantics of ->fault to
-	 * take an explicit file pointer.
-	 */
-	lower_vma.vm_file = lower_file;
-	err = lower_vm_ops->fault(&lower_vma, vmf);
+	err = lower_vm_ops->fault(vma, vmf);
 	return err;
 }
 
+static void sdcardfs_vm_open(struct vm_area_struct *vma)
+{
+	struct file *file = (struct file *)vma->vm_private_data;
+
+	get_file(file);
+}
+
+static void sdcardfs_vm_close(struct vm_area_struct *vma)
+{
+	struct file *file = (struct file *)vma->vm_private_data;
+
+	fput(file);
+}
+
 static int sdcardfs_page_mkwrite(struct vm_area_struct *vma,
 			       struct vm_fault *vmf)
 {
 	int err = 0;
-	struct file *file, *lower_file;
+	struct file *file;
 	const struct vm_operations_struct *lower_vm_ops;
-	struct vm_area_struct lower_vma;
 
-	memcpy(&lower_vma, vma, sizeof(struct vm_area_struct));
-	file = lower_vma.vm_file;
+	file = (struct file *)vma->vm_private_data;
 	lower_vm_ops = SDCARDFS_F(file)->lower_vm_ops;
 	BUG_ON(!lower_vm_ops);
 	if (!lower_vm_ops->page_mkwrite)
 		goto out;
 
-	lower_file = sdcardfs_lower_file(file);
-	/*
-	 * XXX: vm_ops->page_mkwrite may be called in parallel.
-	 * Because we have to resort to temporarily changing the
-	 * vma->vm_file to point to the lower file, a concurrent
-	 * invocation of sdcardfs_page_mkwrite could see a different
-	 * value.  In this workaround, we keep a different copy of the
-	 * vma structure in our stack, so we never expose a different
-	 * value of the vma->vm_file called to us, even temporarily.
-	 * A better fix would be to change the calling semantics of
-	 * ->page_mkwrite to take an explicit file pointer.
-	 */
-	lower_vma.vm_file = lower_file;
-	err = lower_vm_ops->page_mkwrite(&lower_vma, vmf);
+	err = lower_vm_ops->page_mkwrite(vma, vmf);
 out:
 	return err;
 }
@@ -99,4 +84,6 @@ const struct address_space_operations sdcardfs_aops = {
 const struct vm_operations_struct sdcardfs_vm_ops = {
 	.fault		= sdcardfs_fault,
 	.page_mkwrite	= sdcardfs_page_mkwrite,
+	.open		= sdcardfs_vm_open,
+	.close		= sdcardfs_vm_close,
 };
diff --git a/fs/sdcardfs/multiuser.h b/fs/sdcardfs/multiuser.h
index 2e89b5872314..d0c925cda299 100644
--- a/fs/sdcardfs/multiuser.h
+++ b/fs/sdcardfs/multiuser.h
@@ -23,6 +23,8 @@
 #define AID_APP_END          19999 /* last app user */
 #define AID_CACHE_GID_START  20000 /* start of gids for apps to mark cached data */
 #define AID_EXT_GID_START    30000 /* start of gids for apps to mark external data */
+#define AID_EXT_CACHE_GID_START 40000 /* start of gids for apps to mark external cached data */
+#define AID_EXT_CACHE_GID_END 49999   /* end of gids for apps to mark external cached data */
 #define AID_SHARED_GID_START 50000 /* start of gids for apps in each user to share */
 
 typedef uid_t userid_t;
@@ -33,9 +35,9 @@ static inline uid_t multiuser_get_uid(userid_t user_id, appid_t app_id)
 	return (user_id * AID_USER_OFFSET) + (app_id % AID_USER_OFFSET);
 }
 
-static inline gid_t multiuser_get_cache_gid(uid_t uid)
+static inline gid_t multiuser_get_ext_cache_gid(uid_t uid)
 {
-	return uid - AID_APP_START + AID_CACHE_GID_START;
+	return uid - AID_APP_START + AID_EXT_CACHE_GID_START;
 }
 
 static inline gid_t multiuser_get_ext_gid(uid_t uid)
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index b803213d1307..39c75a86c67f 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -108,7 +108,7 @@ static ssize_t sysfs_kf_read(struct kernfs_open_file *of, char *buf,
 {
 	const struct sysfs_ops *ops = sysfs_file_ops(of->kn);
 	struct kobject *kobj = of->kn->parent->priv;
-	size_t len;
+	ssize_t len;
 
 	/*
 	 * If buf != of->prealloc_buf, we don't know how
@@ -117,13 +117,15 @@ static ssize_t sysfs_kf_read(struct kernfs_open_file *of, char *buf,
 	if (WARN_ON_ONCE(buf != of->prealloc_buf))
 		return 0;
 	len = ops->show(kobj, of->kn->priv, buf);
+	if (len < 0)
+		return len;
 	if (pos) {
 		if (len <= pos)
 			return 0;
 		len -= pos;
 		memmove(buf, buf + pos, len);
 	}
-	return min(count, len);
+	return min_t(ssize_t, count, len);
 }
 
 /* kernfs write callback for regular sysfs files */