Merge branch 'android-4.4@c71ad0f' into branch 'msm-4.4'

* refs/heads/tmp-c71ad0f:
  BACKPORT: arm64: dts: juno: fix cluster sleep state entry latency on all SoC versions
  staging: android: ashmem: lseek failed due to no FMODE_LSEEK.
  ANDROID: sdcardfs: update module info
  ANDROID: sdcardfs: use d_splice_alias
  ANDROID: sdcardfs: add read_iter/write_iter opeations
  ANDROID: sdcardfs: fix ->llseek to update upper and lower offset
  ANDROID: sdcardfs: copy lower inode attributes in ->ioctl
  ANDROID: sdcardfs: remove unnecessary call to do_munmap
  Merge 4.4.59 into android-4.4
  UPSTREAM: ipv6 addrconf: implement RFC7559 router solicitation backoff
  android: base-cfg: enable CONFIG_INET_DIAG_DESTROY
  ANDROID: android-base.cfg: add CONFIG_MODULES option
  ANDROID: android-base.cfg: add CONFIG_IKCONFIG option
  ANDROID: android-base.cfg: properly sort the file
  ANDROID: binder: add hwbinder,vndbinder to BINDER_DEVICES.
  ANDROID: sort android-recommended.cfg
  UPSTREAM: config/android: Remove CONFIG_IPV6_PRIVACY
  UPSTREAM: config: android: set SELinux as default security mode
  config: android: move device mapper options to recommended
  ANDROID: ARM64: Allow to choose appended kernel image
  UPSTREAM: arm64: vdso: constify vm_special_mapping used for aarch32 vectors page
  UPSTREAM: arm64: vdso: add __init section marker to alloc_vectors_page
  UPSTREAM: ARM: 8597/1: VDSO: put RO and RO after init objects into proper sections
  UPSTREAM: arm64: Add support for CLOCK_MONOTONIC_RAW in clock_gettime() vDSO
  UPSTREAM: arm64: Refactor vDSO time functions
  UPSTREAM: arm64: fix vdso-offsets.h dependency
  UPSTREAM: kbuild: drop FORCE from PHONY targets
  UPSTREAM: mm: add PHYS_PFN, use it in __phys_to_pfn()
  UPSTREAM: ARM: 8476/1: VDSO: use PTR_ERR_OR_ZERO for vma check
  Linux 4.4.58
  crypto: algif_hash - avoid zero-sized array
  fbcon: Fix vc attr at deinit
  serial: 8250_pci: Detach low-level driver during PCI error recovery
  ACPI / blacklist: Make Dell Latitude 3350 ethernet work
  ACPI / blacklist: add _REV quirks for Dell Precision 5520 and 3520
  uvcvideo: uvc_scan_fallback() for webcams with broken chain
  s390/zcrypt: Introduce CEX6 toleration
  block: allow WRITE_SAME commands with the SG_IO ioctl
  vfio/spapr: Postpone allocation of userspace version of TCE table
  PCI: Do any VF BAR updates before enabling the BARs
  PCI: Ignore BAR updates on virtual functions
  PCI: Update BARs using property bits appropriate for type
  PCI: Don't update VF BARs while VF memory space is enabled
  PCI: Decouple IORESOURCE_ROM_ENABLE and PCI_ROM_ADDRESS_ENABLE
  PCI: Add comments about ROM BAR updating
  PCI: Remove pci_resource_bar() and pci_iov_resource_bar()
  PCI: Separate VF BAR updates from standard BAR updates
  x86/hyperv: Handle unknown NMIs on one CPU when unknown_nmi_panic
  igb: add i211 to i210 PHY workaround
  igb: Workaround for igb i210 firmware issue
  xen: do not re-use pirq number cached in pci device msi msg data
  xfs: clear _XBF_PAGES from buffers when readahead page
  USB: usbtmc: add missing endpoint sanity check
  nl80211: fix dumpit error path RTNL deadlocks
  xfs: fix up xfs_swap_extent_forks inline extent handling
  xfs: don't allow di_size with high bit set
  libceph: don't set weight to IN when OSD is destroyed
  raid10: increment write counter after bio is split
  cpufreq: Restore policy min/max limits on CPU online
  ARM: dts: at91: sama5d2: add dma properties to UART nodes
  ARM: at91: pm: cpu_idle: switch DDR to power-down mode
  iommu/vt-d: Fix NULL pointer dereference in device_to_iommu
  xen/acpi: upload PM state from init-domain to Xen
  mmc: sdhci: Do not disable interrupts while waiting for clock
  ext4: mark inode dirty after converting inline directory
  parport: fix attempt to write duplicate procfiles
  iio: hid-sensor-trigger: Change get poll value function order to avoid sensor properties losing after resume from S3
  iio: adc: ti_am335x_adc: fix fifo overrun recovery
  mmc: ushc: fix NULL-deref at probe
  uwb: hwa-rc: fix NULL-deref at probe
  uwb: i1480-dfu: fix NULL-deref at probe
  usb: hub: Fix crash after failure to read BOS descriptor
  usb: musb: cppi41: don't check early-TX-interrupt for Isoch transfer
  USB: wusbcore: fix NULL-deref at probe
  USB: idmouse: fix NULL-deref at probe
  USB: lvtest: fix NULL-deref at probe
  USB: uss720: fix NULL-deref at probe
  usb-core: Add LINEAR_FRAME_INTR_BINTERVAL USB quirk
  usb: gadget: f_uvc: Fix SuperSpeed companion descriptor's wBytesPerInterval
  ACM gadget: fix endianness in notifications
  USB: serial: qcserial: add Dell DW5811e
  USB: serial: option: add Quectel UC15, UC20, EC21, and EC25 modems
  ALSA: hda - Adding a group of pin definition to fix headset problem
  ALSA: ctxfi: Fix the incorrect check of dma_set_mask() call
  ALSA: seq: Fix racy cell insertions during snd_seq_pool_done()
  Input: sur40 - validate number of endpoints before using them
  Input: kbtab - validate number of endpoints before using them
  Input: cm109 - validate number of endpoints before using them
  Input: yealink - validate number of endpoints before using them
  Input: hanwang - validate number of endpoints before using them
  Input: ims-pcu - validate number of endpoints before using them
  Input: iforce - validate number of endpoints before using them
  Input: i8042 - add noloop quirk for Dell Embedded Box PC 3000
  Input: elan_i2c - add ASUS EeeBook X205TA special touchpad fw
  tcp: initialize icsk_ack.lrcvtime at session start time
  socket, bpf: fix sk_filter use after free in sk_clone_lock
  ipv4: provide stronger user input validation in nl_fib_input()
  net: bcmgenet: remove bcmgenet_internal_phy_setup()
  net/mlx5e: Count LRO packets correctly
  net/mlx5: Increase number of max QPs in default profile
  net: unix: properly re-increment inflight counter of GC discarded candidates
  amd-xgbe: Fix jumbo MTU processing on newer hardware
  net: properly release sk_frag.page
  net: bcmgenet: Do not suspend PHY if Wake-on-LAN is enabled
  net/openvswitch: Set the ipv6 source tunnel key address attribute correctly
  Linux 4.4.57
  ext4: fix fencepost in s_first_meta_bg validation
  percpu: acquire pcpu_lock when updating pcpu_nr_empty_pop_pages
  gfs2: Avoid alignment hole in struct lm_lockname
  isdn/gigaset: fix NULL-deref at probe
  target: Fix VERIFY_16 handling in sbc_parse_cdb
  scsi: libiscsi: add lock around task lists to fix list corruption regression
  scsi: lpfc: Add shutdown method for kexec
  target/pscsi: Fix TYPE_TAPE + TYPE_MEDIMUM_CHANGER export
  md/raid1/10: fix potential deadlock
  powerpc/boot: Fix zImage TOC alignment
  cpufreq: Fix and clean up show_cpuinfo_cur_freq()
  perf/core: Fix event inheritance on fork()
  give up on gcc ilog2() constant optimizations
  kernek/fork.c: allocate idle task for a CPU always on its local node
  hv_netvsc: use skb_get_hash() instead of a homegrown implementation
  tpm_tis: Use devm_free_irq not free_irq
  drm/amdgpu: add missing irq.h include
  s390/pci: fix use after free in dma_init
  KVM: PPC: Book3S PR: Fix illegal opcode emulation
  xen/qspinlock: Don't kick CPU if IRQ is not initialized
  Drivers: hv: avoid vfree() on crash
  Drivers: hv: balloon: don't crash when memory is added in non-sorted order
  pinctrl: cherryview: Do not mask all interrupts in probe
  ACPI / video: skip evaluating _DOD when it does not exist
  cxlflash: Increase cmd_per_lun for better throughput
  crypto: mcryptd - Fix load failure
  crypto: cryptd - Assign statesize properly
  crypto: ghash-clmulni - Fix load failure
  USB: don't free bandwidth_mutex too early
  usb: core: hub: hub_port_init lock controller instead of bus
  ANDROID: sdcardfs: Fix style issues in macros
  ANDROID: sdcardfs: Use seq_puts over seq_printf
  ANDROID: sdcardfs: Use to kstrout
  ANDROID: sdcardfs: Use pr_[...] instead of printk
  ANDROID: sdcardfs: remove unneeded null check
  ANDROID: sdcardfs: Fix style issues with comments
  ANDROID: sdcardfs: Fix formatting
  ANDROID: sdcardfs: correct order of descriptors
  fix the deadlock in xt_qtaguid when enable DDEBUG
  net: ipv6: Add sysctl for minimum prefix len acceptable in RIOs.
  Linux 4.4.56
  futex: Add missing error handling to FUTEX_REQUEUE_PI
  futex: Fix potential use-after-free in FUTEX_REQUEUE_PI
  x86/perf: Fix CR4.PCE propagation to use active_mm instead of mm
  x86/kasan: Fix boot with KASAN=y and PROFILE_ANNOTATED_BRANCHES=y
  fscrypto: lock inode while setting encryption policy
  fscrypt: fix renaming and linking special files
  net sched actions: decrement module reference count after table flush.
  dccp: fix memory leak during tear-down of unsuccessful connection request
  dccp/tcp: fix routing redirect race
  bridge: drop netfilter fake rtable unconditionally
  ipv6: avoid write to a possibly cloned skb
  ipv6: make ECMP route replacement less greedy
  mpls: Send route delete notifications when router module is unloaded
  act_connmark: avoid crashing on malformed nlattrs with null parms
  uapi: fix linux/packet_diag.h userspace compilation error
  vrf: Fix use-after-free in vrf_xmit
  dccp: fix use-after-free in dccp_feat_activate_values
  net: fix socket refcounting in skb_complete_tx_timestamp()
  net: fix socket refcounting in skb_complete_wifi_ack()
  tcp: fix various issues for sockets morphing to listen state
  dccp: Unlock sock before calling sk_free()
  net: net_enable_timestamp() can be called from irq contexts
  net: don't call strlen() on the user buffer in packet_bind_spkt()
  l2tp: avoid use-after-free caused by l2tp_ip_backlog_recv
  ipv4: mask tos for input route
  vti6: return GRE_KEY for vti6
  vxlan: correctly validate VXLAN ID against VXLAN_N_VID
  netlink: remove mmapped netlink support
  ANDROID: mmc: core: export emmc revision
  BACKPORT: mmc: core: Export device lifetime information through sysfs
  ANDROID: android-verity: do not compile as independent module
  ANDROID: sched: fix duplicate sched_group_energy const specifiers
  config: disable CONFIG_USELIB and CONFIG_FHANDLE
  ANDROID: power: align wakeup_sources format
  ANDROID: dm: android-verity: allow disable dm-verity for Treble VTS
  uid_sys_stats: change to use rt_mutex
  ANDROID: vfs: user permission2 in notify_change2
  ANDROID: sdcardfs: Fix gid issue
  ANDROID: sdcardfs: Use tabs instead of spaces in multiuser.h
  ANDROID: sdcardfs: Remove uninformative prints
  ANDROID: sdcardfs: move path_put outside of spinlock
  ANDROID: sdcardfs: Use case insensitive hash function
  ANDROID: sdcardfs: declare MODULE_ALIAS_FS
  ANDROID: sdcardfs: Get the blocksize from the lower fs
  ANDROID: sdcardfs: Use d_invalidate instead of drop_recurisve
  ANDROID: sdcardfs: Switch to internal case insensitive compare
  ANDROID: sdcardfs: Use spin_lock_nested
  ANDROID: sdcardfs: Replace get/put with d_lock
  ANDROID: sdcardfs: rate limit warning print
  ANDROID: sdcardfs: Fix case insensitive lookup
  ANDROID: uid_sys_stats: account for fsync syscalls
  ANDROID: sched: add a counter to track fsync
  ANDROID: uid_sys_stats: fix negative write bytes.
  ANDROID: uid_sys_stats: allow writing same state
  ANDROID: uid_sys_stats: rename uid_cputime.c to uid_sys_stats.c
  ANDROID: uid_cputime: add per-uid IO usage accounting
  DTB: Add EAS compatible Juno Energy model to 'juno.dts'
  arm64: dts: juno: Add idle-states to device tree
  ANDROID: Replace spaces by '_' for some android filesystem tracepoints.
  usb: gadget: f_accessory: Fix for UsbAccessory clean unbind.
  android: binder: move global binder state into context struct.
  android: binder: add padding to binder_fd_array_object.
  binder: use group leader instead of open thread
  nf: IDLETIMER: Use fullsock when querying uid
  nf: IDLETIMER: Fix use after free condition during work
  ANDROID: dm: android-verity: fix table_make_digest() error handling
  ANDROID: usb: gadget: function: Fix commenting style
  cpufreq: interactive governor drops bits in time calculation
  ANDROID: sdcardfs: support direct-IO (DIO) operations
  ANDROID: sdcardfs: implement vm_ops->page_mkwrite
  ANDROID: sdcardfs: Don't bother deleting freelist
  ANDROID: sdcardfs: Add missing path_put
  ANDROID: sdcardfs: Fix incorrect hash
  ANDROID: ext4 crypto: Disables zeroing on truncation when there's no key
  ANDROID: ext4: add a non-reversible key derivation method
  ANDROID: ext4: allow encrypting filenames using HEH algorithm
  ANDROID: arm64/crypto: add ARMv8-CE optimized poly_hash algorithm
  ANDROID: crypto: heh - factor out poly_hash algorithm
  ANDROID: crypto: heh - Add Hash-Encrypt-Hash (HEH) algorithm
  ANDROID: crypto: gf128mul - Add ble multiplication functions
  ANDROID: crypto: gf128mul - Refactor gf128 overflow macros and tables
  UPSTREAM: crypto: gf128mul - Zero memory when freeing multiplication table
  ANDROID: crypto: shash - Add crypto_grab_shash() and crypto_spawn_shash_alg()
  ANDROID: crypto: allow blkcipher walks over ablkcipher data
  UPSTREAM: arm/arm64: crypto: assure that ECB modes don't require an IV
  ANDROID: Refactor fs readpage/write tracepoints.
  ANDROID: export security_path_chown
  Squashfs: optimize reading uncompressed data
  Squashfs: implement .readpages()
  Squashfs: replace buffer_head with BIO
  Squashfs: refactor page_actor
  Squashfs: remove the FILE_CACHE option
  ANDROID: android-recommended.cfg: CONFIG_CPU_SW_DOMAIN_PAN=y
  FROMLIST: 9p: fix a potential acl leak
  BACKPORT: posix_acl: Clear SGID bit when setting file permissions
  UPSTREAM: udp: properly support MSG_PEEK with truncated buffers
  UPSTREAM: arm64: Allow hw watchpoint of length 3,5,6 and 7
  BACKPORT: arm64: hw_breakpoint: Handle inexact watchpoint addresses
  UPSTREAM: arm64: Allow hw watchpoint at varied offset from base address
  BACKPORT: hw_breakpoint: Allow watchpoint of length 3,5,6 and 7
  ANDROID: sdcardfs: Switch strcasecmp for internal call
  ANDROID: sdcardfs: switch to full_name_hash and qstr
  ANDROID: sdcardfs: Add GID Derivation to sdcardfs
  ANDROID: sdcardfs: Remove redundant operation
  ANDROID: sdcardfs: add support for user permission isolation
  ANDROID: sdcardfs: Refactor configfs interface
  ANDROID: sdcardfs: Allow non-owners to touch
  ANDROID: binder: fix format specifier for type binder_size_t
  ANDROID: fs: Export vfs_rmdir2
  ANDROID: fs: Export free_fs_struct and set_fs_pwd
  BACKPORT: Input: xpad - validate USB endpoint count during probe
  BACKPORT: Input: xpad - fix oops when attaching an unknown Xbox One gamepad
  ANDROID: mnt: remount should propagate to slaves of slaves
  ANDROID: sdcardfs: Switch ->d_inode to d_inode()
  ANDROID: sdcardfs: Fix locking issue with permision fix up
  ANDROID: sdcardfs: Change magic value
  ANDROID: sdcardfs: Use per mount permissions
  ANDROID: sdcardfs: Add gid and mask to private mount data
  ANDROID: sdcardfs: User new permission2 functions
  ANDROID: vfs: Add setattr2 for filesystems with per mount permissions
  ANDROID: vfs: Add permission2 for filesystems with per mount permissions
  ANDROID: vfs: Allow filesystems to access their private mount data
  ANDROID: mnt: Add filesystem private data to mount points
  ANDROID: sdcardfs: Move directory unlock before touch
  ANDROID: sdcardfs: fix external storage exporting incorrect uid
  ANDROID: sdcardfs: Added top to sdcardfs_inode_info
  ANDROID: sdcardfs: Switch package list to RCU
  ANDROID: sdcardfs: Fix locking for permission fix up
  ANDROID: sdcardfs: Check for other cases on path lookup
  ANDROID: sdcardfs: override umask on mkdir and create
  arm64: kernel: Fix build warning
  DEBUG: sched/fair: Fix sched_load_avg_cpu events for task_groups
  DEBUG: sched/fair: Fix missing sched_load_avg_cpu events
  UPSTREAM: l2tp: fix racy SOCK_ZAPPED flag check in l2tp_ip{,6}_bind()
  UPSTREAM: packet: fix race condition in packet_set_ring
  UPSTREAM: netlink: Fix dump skb leak/double free
  UPSTREAM: net: avoid signed overflows for SO_{SND|RCV}BUFFORCE
  MIPS: Prevent "restoration" of MSA context in non-MSA kernels
  net: socket: don't set sk_uid to garbage value in ->setattr()
  ANDROID: configs: CONFIG_ARM64_SW_TTBR0_PAN=y
  UPSTREAM: arm64: Disable PAN on uaccess_enable()
  UPSTREAM: arm64: Enable CONFIG_ARM64_SW_TTBR0_PAN
  UPSTREAM: arm64: xen: Enable user access before a privcmd hvc call
  UPSTREAM: arm64: Handle faults caused by inadvertent user access with PAN enabled
  BACKPORT: arm64: Disable TTBR0_EL1 during normal kernel execution
  BACKPORT: arm64: Introduce uaccess_{disable,enable} functionality based on TTBR0_EL1
  BACKPORT: arm64: Factor out TTBR0_EL1 post-update workaround into a specific asm macro
  BACKPORT: arm64: Factor out PAN enabling/disabling into separate uaccess_* macros
  UPSTREAM: arm64: alternative: add auto-nop infrastructure
  UPSTREAM: arm64: barriers: introduce nops and __nops macros for NOP sequences
  Revert "FROMLIST: arm64: Factor out PAN enabling/disabling into separate uaccess_* macros"
  Revert "FROMLIST: arm64: Factor out TTBR0_EL1 post-update workaround into a specific asm macro"
  Revert "FROMLIST: arm64: Introduce uaccess_{disable,enable} functionality based on TTBR0_EL1"
  Revert "FROMLIST: arm64: Disable TTBR0_EL1 during normal kernel execution"
  Revert "FROMLIST: arm64: Handle faults caused by inadvertent user access with PAN enabled"
  Revert "FROMLIST: arm64: xen: Enable user access before a privcmd hvc call"
  Revert "FROMLIST: arm64: Enable CONFIG_ARM64_SW_TTBR0_PAN"
  ANDROID: sched/walt: fix build failure if FAIR_GROUP_SCHED=n
  ANDROID: trace: net: use %pK for kernel pointers
  ANDROID: android-base: Enable QUOTA related configs
  net: ipv4: Don't crash if passing a null sk to ip_rt_update_pmtu.
  net: inet: Support UID-based routing in IP protocols.
  net: core: add UID to flows, rules, and routes
  net: core: Add a UID field to struct sock.
  Revert "net: core: Support UID-based routing."
  UPSTREAM: efi/arm64: Don't apply MEMBLOCK_NOMAP to UEFI memory map mapping
  UPSTREAM: arm64: mm: always take dirty state from new pte in ptep_set_access_flags
  UPSTREAM: arm64: Implement pmdp_set_access_flags() for hardware AF/DBM
  UPSTREAM: arm64: Fix typo in the pmdp_huge_get_and_clear() definition
  UPSTREAM: arm64: enable CONFIG_DEBUG_RODATA by default
  goldfish: enable CONFIG_INET_DIAG_DESTROY
  sched/walt: kill {min,max}_capacity
  sched: fix wrong truncation of walt_avg
  build: fix build config kernel_dir
  ANDROID: dm verity: add minimum prefetch size
  build: add build server configs for goldfish
  usb: gadget: Fix compilation problem with tx_qlen field

Conflicts:
	android/configs/android-base.cfg
	arch/arm64/Makefile
	arch/arm64/include/asm/cpufeature.h
	arch/arm64/kernel/vdso/gettimeofday.S
	arch/arm64/mm/cache.S
	drivers/md/Kconfig
	drivers/misc/Makefile
	drivers/mmc/host/sdhci.c
	drivers/usb/core/hcd.c
	drivers/usb/gadget/function/u_ether.c
	fs/sdcardfs/derived_perm.c
	fs/sdcardfs/file.c
	fs/sdcardfs/inode.c
	fs/sdcardfs/lookup.c
	fs/sdcardfs/main.c
	fs/sdcardfs/multiuser.h
	fs/sdcardfs/packagelist.c
	fs/sdcardfs/sdcardfs.h
	fs/sdcardfs/super.c
	include/linux/mmc/card.h
	include/linux/mmc/mmc.h
	include/trace/events/android_fs.h
	include/trace/events/android_fs_template.h
	drivers/android/binder.c
	fs/exec.c
	fs/ext4/crypto_key.c
	fs/ext4/ext4.h
	fs/ext4/inline.c
	fs/ext4/inode.c
	fs/ext4/readpage.c
	fs/f2fs/data.c
	fs/f2fs/inline.c
	fs/mpage.c
	include/linux/dcache.h
	include/trace/events/sched.h
	include/uapi/linux/ipv6.h
	net/ipv4/tcp_ipv4.c
	net/netfilter/xt_IDLETIMER.c

Change-Id: Ie345db6a14869fe0aa794aef4b71b5d0d503690b
Signed-off-by: Blagovest Kolenichev <bkolenichev@codeaurora.org>

1 files changed, 403 insertions, 143 deletions

diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c
index 0cea9b9236d0..2eb66decc5ab 100644
--- a/fs/squashfs/block.c
+++ b/fs/squashfs/block.c
@@ -28,9 +28,12 @@
 
 #include <linux/fs.h>
 #include <linux/vfs.h>
+#include <linux/bio.h>
 #include <linux/slab.h>
 #include <linux/string.h>
+#include <linux/pagemap.h>
 #include <linux/buffer_head.h>
+#include <linux/workqueue.h>
 
 #include "squashfs_fs.h"
 #include "squashfs_fs_sb.h"
@@ -38,177 +41,434 @@
 #include "decompressor.h"
 #include "page_actor.h"
 
-/*
- * Read the metadata block length, this is stored in the first two
- * bytes of the metadata block.
- */
-static struct buffer_head *get_block_length(struct super_block *sb,
-			u64 *cur_index, int *offset, int *length)
+static struct workqueue_struct *squashfs_read_wq;
+
+struct squashfs_read_request {
+	struct super_block *sb;
+	u64 index;
+	int length;
+	int compressed;
+	int offset;
+	u64 read_end;
+	struct squashfs_page_actor *output;
+	enum {
+		SQUASHFS_COPY,
+		SQUASHFS_DECOMPRESS,
+		SQUASHFS_METADATA,
+	} data_processing;
+	bool synchronous;
+
+	/*
+	 * If the read is synchronous, it is possible to retrieve information
+	 * about the request by setting these pointers.
+	 */
+	int *res;
+	int *bytes_read;
+	int *bytes_uncompressed;
+
+	int nr_buffers;
+	struct buffer_head **bh;
+	struct work_struct offload;
+};
+
+struct squashfs_bio_request {
+	struct buffer_head **bh;
+	int nr_buffers;
+};
+
+static int squashfs_bio_submit(struct squashfs_read_request *req);
+
+int squashfs_init_read_wq(void)
 {
-	struct squashfs_sb_info *msblk = sb->s_fs_info;
-	struct buffer_head *bh;
+	squashfs_read_wq = create_workqueue("SquashFS read wq");
+	return !!squashfs_read_wq;
+}
+
+void squashfs_destroy_read_wq(void)
+{
+	flush_workqueue(squashfs_read_wq);
+	destroy_workqueue(squashfs_read_wq);
+}
+
+static void free_read_request(struct squashfs_read_request *req, int error)
+{
+	if (!req->synchronous)
+		squashfs_page_actor_free(req->output, error);
+	if (req->res)
+		*(req->res) = error;
+	kfree(req->bh);
+	kfree(req);
+}
+
+static void squashfs_process_blocks(struct squashfs_read_request *req)
+{
+	int error = 0;
+	int bytes, i, length;
+	struct squashfs_sb_info *msblk = req->sb->s_fs_info;
+	struct squashfs_page_actor *actor = req->output;
+	struct buffer_head **bh = req->bh;
+	int nr_buffers = req->nr_buffers;
+
+	for (i = 0; i < nr_buffers; ++i) {
+		if (!bh[i])
+			continue;
+		wait_on_buffer(bh[i]);
+		if (!buffer_uptodate(bh[i]))
+			error = -EIO;
+	}
+	if (error)
+		goto cleanup;
+
+	if (req->data_processing == SQUASHFS_METADATA) {
+		/* Extract the length of the metadata block */
+		if (req->offset != msblk->devblksize - 1)
+			length = *((u16 *)(bh[0]->b_data + req->offset));
+		else {
+			length = bh[0]->b_data[req->offset];
+			length |= bh[1]->b_data[0] << 8;
+		}
+		req->compressed = SQUASHFS_COMPRESSED(length);
+		req->data_processing = req->compressed ? SQUASHFS_DECOMPRESS
+						       : SQUASHFS_COPY;
+		length = SQUASHFS_COMPRESSED_SIZE(length);
+		if (req->index + length + 2 > req->read_end) {
+			for (i = 0; i < nr_buffers; ++i)
+				put_bh(bh[i]);
+			kfree(bh);
+			req->length = length;
+			req->index += 2;
+			squashfs_bio_submit(req);
+			return;
+		}
+		req->length = length;
+		req->offset = (req->offset + 2) % PAGE_SIZE;
+		if (req->offset < 2) {
+			put_bh(bh[0]);
+			++bh;
+			--nr_buffers;
+		}
+	}
+	if (req->bytes_read)
+		*(req->bytes_read) = req->length;
 
-	bh = sb_bread(sb, *cur_index);
-	if (bh == NULL)
-		return NULL;
-
-	if (msblk->devblksize - *offset == 1) {
-		*length = (unsigned char) bh->b_data[*offset];
-		put_bh(bh);
-		bh = sb_bread(sb, ++(*cur_index));
-		if (bh == NULL)
-			return NULL;
-		*length |= (unsigned char) bh->b_data[0] << 8;
-		*offset = 1;
-	} else {
-		*length = (unsigned char) bh->b_data[*offset] |
-			(unsigned char) bh->b_data[*offset + 1] << 8;
-		*offset += 2;
-
-		if (*offset == msblk->devblksize) {
-			put_bh(bh);
-			bh = sb_bread(sb, ++(*cur_index));
-			if (bh == NULL)
-				return NULL;
-			*offset = 0;
+	if (req->data_processing == SQUASHFS_COPY) {
+		squashfs_bh_to_actor(bh, nr_buffers, req->output, req->offset,
+			req->length, msblk->devblksize);
+	} else if (req->data_processing == SQUASHFS_DECOMPRESS) {
+		req->length = squashfs_decompress(msblk, bh, nr_buffers,
+			req->offset, req->length, actor);
+		if (req->length < 0) {
+			error = -EIO;
+			goto cleanup;
 		}
 	}
 
-	return bh;
+	/* Last page may have trailing bytes not filled */
+	bytes = req->length % PAGE_SIZE;
+	if (bytes && actor->page[actor->pages - 1])
+		zero_user_segment(actor->page[actor->pages - 1], bytes,
+				  PAGE_SIZE);
+
+cleanup:
+	if (req->bytes_uncompressed)
+		*(req->bytes_uncompressed) = req->length;
+	if (error) {
+		for (i = 0; i < nr_buffers; ++i)
+			if (bh[i])
+				put_bh(bh[i]);
+	}
+	free_read_request(req, error);
 }
 
+static void read_wq_handler(struct work_struct *work)
+{
+	squashfs_process_blocks(container_of(work,
+		    struct squashfs_read_request, offload));
+}
 
-/*
- * Read and decompress a metadata block or datablock.  Length is non-zero
- * if a datablock is being read (the size is stored elsewhere in the
- * filesystem), otherwise the length is obtained from the first two bytes of
- * the metadata block.  A bit in the length field indicates if the block
- * is stored uncompressed in the filesystem (usually because compression
- * generated a larger block - this does occasionally happen with compression
- * algorithms).
- */
-int squashfs_read_data(struct super_block *sb, u64 index, int length,
-		u64 *next_index, struct squashfs_page_actor *output)
+static void squashfs_bio_end_io(struct bio *bio)
 {
-	struct squashfs_sb_info *msblk = sb->s_fs_info;
-	struct buffer_head **bh;
-	int offset = index & ((1 << msblk->devblksize_log2) - 1);
-	u64 cur_index = index >> msblk->devblksize_log2;
-	int bytes, compressed, b = 0, k = 0, avail, i;
+	int i;
+	int error = bio->bi_error;
+	struct squashfs_bio_request *bio_req = bio->bi_private;
+
+	bio_put(bio);
+
+	for (i = 0; i < bio_req->nr_buffers; ++i) {
+		if (!bio_req->bh[i])
+			continue;
+		if (!error)
+			set_buffer_uptodate(bio_req->bh[i]);
+		else
+			clear_buffer_uptodate(bio_req->bh[i]);
+		unlock_buffer(bio_req->bh[i]);
+	}
+	kfree(bio_req);
+}
+
+static int bh_is_optional(struct squashfs_read_request *req, int idx)
+{
+	int start_idx, end_idx;
+	struct squashfs_sb_info *msblk = req->sb->s_fs_info;
 
-	bh = kcalloc(((output->length + msblk->devblksize - 1)
-		>> msblk->devblksize_log2) + 1, sizeof(*bh), GFP_KERNEL);
-	if (bh == NULL)
+	start_idx = (idx * msblk->devblksize - req->offset) / PAGE_CACHE_SIZE;
+	end_idx = ((idx + 1) * msblk->devblksize - req->offset + 1) / PAGE_CACHE_SIZE;
+	if (start_idx >= req->output->pages)
+		return 1;
+	if (start_idx < 0)
+		start_idx = end_idx;
+	if (end_idx >= req->output->pages)
+		end_idx = start_idx;
+	return !req->output->page[start_idx] && !req->output->page[end_idx];
+}
+
+static int actor_getblks(struct squashfs_read_request *req, u64 block)
+{
+	int i;
+
+	req->bh = kmalloc_array(req->nr_buffers, sizeof(*(req->bh)), GFP_NOIO);
+	if (!req->bh)
 		return -ENOMEM;
 
-	if (length) {
+	for (i = 0; i < req->nr_buffers; ++i) {
 		/*
-		 * Datablock.
+		 * When dealing with an uncompressed block, the actor may
+		 * contains NULL pages. There's no need to read the buffers
+		 * associated with these pages.
 		 */
-		bytes = -offset;
-		compressed = SQUASHFS_COMPRESSED_BLOCK(length);
-		length = SQUASHFS_COMPRESSED_SIZE_BLOCK(length);
-		if (next_index)
-			*next_index = index + length;
-
-		TRACE("Block @ 0x%llx, %scompressed size %d, src size %d\n",
-			index, compressed ? "" : "un", length, output->length);
-
-		if (length < 0 || length > output->length ||
-				(index + length) > msblk->bytes_used)
-			goto read_failure;
-
-		for (b = 0; bytes < length; b++, cur_index++) {
-			bh[b] = sb_getblk(sb, cur_index);
-			if (bh[b] == NULL)
-				goto block_release;
-			bytes += msblk->devblksize;
+		if (!req->compressed && bh_is_optional(req, i)) {
+			req->bh[i] = NULL;
+			continue;
 		}
-		ll_rw_block(READ, b, bh);
-	} else {
-		/*
-		 * Metadata block.
-		 */
-		if ((index + 2) > msblk->bytes_used)
-			goto read_failure;
+		req->bh[i] = sb_getblk(req->sb, block + i);
+		if (!req->bh[i]) {
+			while (--i) {
+				if (req->bh[i])
+					put_bh(req->bh[i]);
+			}
+			return -1;
+		}
+	}
+	return 0;
+}
 
-		bh[0] = get_block_length(sb, &cur_index, &offset, &length);
-		if (bh[0] == NULL)
-			goto read_failure;
-		b = 1;
+static int squashfs_bio_submit(struct squashfs_read_request *req)
+{
+	struct bio *bio = NULL;
+	struct buffer_head *bh;
+	struct squashfs_bio_request *bio_req = NULL;
+	int b = 0, prev_block = 0;
+	struct squashfs_sb_info *msblk = req->sb->s_fs_info;
 
-		bytes = msblk->devblksize - offset;
-		compressed = SQUASHFS_COMPRESSED(length);
-		length = SQUASHFS_COMPRESSED_SIZE(length);
-		if (next_index)
-			*next_index = index + length + 2;
+	u64 read_start = round_down(req->index, msblk->devblksize);
+	u64 read_end = round_up(req->index + req->length, msblk->devblksize);
+	sector_t block = read_start >> msblk->devblksize_log2;
+	sector_t block_end = read_end >> msblk->devblksize_log2;
+	int offset = read_start - round_down(req->index, PAGE_SIZE);
+	int nr_buffers = block_end - block;
+	int blksz = msblk->devblksize;
+	int bio_max_pages = nr_buffers > BIO_MAX_PAGES ? BIO_MAX_PAGES
+						       : nr_buffers;
 
-		TRACE("Block @ 0x%llx, %scompressed size %d\n", index,
-				compressed ? "" : "un", length);
+	/* Setup the request */
+	req->read_end = read_end;
+	req->offset = req->index - read_start;
+	req->nr_buffers = nr_buffers;
+	if (actor_getblks(req, block) < 0)
+		goto getblk_failed;
 
-		if (length < 0 || length > output->length ||
-					(index + length) > msblk->bytes_used)
-			goto block_release;
+	/* Create and submit the BIOs */
+	for (b = 0; b < nr_buffers; ++b, offset += blksz) {
+		bh = req->bh[b];
+		if (!bh || !trylock_buffer(bh))
+			continue;
+		if (buffer_uptodate(bh)) {
+			unlock_buffer(bh);
+			continue;
+		}
+		offset %= PAGE_SIZE;
 
-		for (; bytes < length; b++) {
-			bh[b] = sb_getblk(sb, ++cur_index);
-			if (bh[b] == NULL)
-				goto block_release;
-			bytes += msblk->devblksize;
+		/* Append the buffer to the current BIO if it is contiguous */
+		if (bio && bio_req && prev_block + 1 == b) {
+			if (bio_add_page(bio, bh->b_page, blksz, offset)) {
+				bio_req->nr_buffers += 1;
+				prev_block = b;
+				continue;
+			}
 		}
-		ll_rw_block(READ, b - 1, bh + 1);
+
+		/* Otherwise, submit the current BIO and create a new one */
+		if (bio)
+			submit_bio(READ, bio);
+		bio_req = kcalloc(1, sizeof(struct squashfs_bio_request),
+				  GFP_NOIO);
+		if (!bio_req)
+			goto req_alloc_failed;
+		bio_req->bh = &req->bh[b];
+		bio = bio_alloc(GFP_NOIO, bio_max_pages);
+		if (!bio)
+			goto bio_alloc_failed;
+		bio->bi_bdev = req->sb->s_bdev;
+		bio->bi_iter.bi_sector = (block + b)
+				       << (msblk->devblksize_log2 - 9);
+		bio->bi_private = bio_req;
+		bio->bi_end_io = squashfs_bio_end_io;
+
+		bio_add_page(bio, bh->b_page, blksz, offset);
+		bio_req->nr_buffers += 1;
+		prev_block = b;
 	}
+	if (bio)
+		submit_bio(READ, bio);
 
-	for (i = 0; i < b; i++) {
-		wait_on_buffer(bh[i]);
-		if (!buffer_uptodate(bh[i]))
-			goto block_release;
+	if (req->synchronous)
+		squashfs_process_blocks(req);
+	else {
+		INIT_WORK(&req->offload, read_wq_handler);
+		schedule_work(&req->offload);
 	}
+	return 0;
 
-	if (compressed) {
-		length = squashfs_decompress(msblk, bh, b, offset, length,
-			output);
-		if (length < 0)
-			goto read_failure;
-	} else {
-		/*
-		 * Block is uncompressed.
-		 */
-		int in, pg_offset = 0;
-		void *data = squashfs_first_page(output);
-
-		for (bytes = length; k < b; k++) {
-			in = min(bytes, msblk->devblksize - offset);
-			bytes -= in;
-			while (in) {
-				if (pg_offset == PAGE_CACHE_SIZE) {
-					data = squashfs_next_page(output);
-					pg_offset = 0;
-				}
-				avail = min_t(int, in, PAGE_CACHE_SIZE -
-						pg_offset);
-				memcpy(data + pg_offset, bh[k]->b_data + offset,
-						avail);
-				in -= avail;
-				pg_offset += avail;
-				offset += avail;
-			}
-			offset = 0;
-			put_bh(bh[k]);
-		}
-		squashfs_finish_page(output);
+bio_alloc_failed:
+	kfree(bio_req);
+req_alloc_failed:
+	unlock_buffer(bh);
+	while (--nr_buffers >= b)
+		if (req->bh[nr_buffers])
+			put_bh(req->bh[nr_buffers]);
+	while (--b >= 0)
+		if (req->bh[b])
+			wait_on_buffer(req->bh[b]);
+getblk_failed:
+	free_read_request(req, -ENOMEM);
+	return -ENOMEM;
+}
+
+static int read_metadata_block(struct squashfs_read_request *req,
+			       u64 *next_index)
+{
+	int ret, error, bytes_read = 0, bytes_uncompressed = 0;
+	struct squashfs_sb_info *msblk = req->sb->s_fs_info;
+
+	if (req->index + 2 > msblk->bytes_used) {
+		free_read_request(req, -EINVAL);
+		return -EINVAL;
+	}
+	req->length = 2;
+
+	/* Do not read beyond the end of the device */
+	if (req->index + req->length > msblk->bytes_used)
+		req->length = msblk->bytes_used - req->index;
+	req->data_processing = SQUASHFS_METADATA;
+
+	/*
+	 * Reading metadata is always synchronous because we don't know the
+	 * length in advance and the function is expected to update
+	 * 'next_index' and return the length.
+	 */
+	req->synchronous = true;
+	req->res = &error;
+	req->bytes_read = &bytes_read;
+	req->bytes_uncompressed = &bytes_uncompressed;
+
+	TRACE("Metadata block @ 0x%llx, %scompressed size %d, src size %d\n",
+	      req->index, req->compressed ? "" : "un", bytes_read,
+	      req->output->length);
+
+	ret = squashfs_bio_submit(req);
+	if (ret)
+		return ret;
+	if (error)
+		return error;
+	if (next_index)
+		*next_index += 2 + bytes_read;
+	return bytes_uncompressed;
+}
+
+static int read_data_block(struct squashfs_read_request *req, int length,
+			   u64 *next_index, bool synchronous)
+{
+	int ret, error = 0, bytes_uncompressed = 0, bytes_read = 0;
+
+	req->compressed = SQUASHFS_COMPRESSED_BLOCK(length);
+	req->length = length = SQUASHFS_COMPRESSED_SIZE_BLOCK(length);
+	req->data_processing = req->compressed ? SQUASHFS_DECOMPRESS
+					       : SQUASHFS_COPY;
+
+	req->synchronous = synchronous;
+	if (synchronous) {
+		req->res = &error;
+		req->bytes_read = &bytes_read;
+		req->bytes_uncompressed = &bytes_uncompressed;
+	}
+
+	TRACE("Data block @ 0x%llx, %scompressed size %d, src size %d\n",
+	      req->index, req->compressed ? "" : "un", req->length,
+	      req->output->length);
+
+	ret = squashfs_bio_submit(req);
+	if (ret)
+		return ret;
+	if (synchronous)
+		ret = error ? error : bytes_uncompressed;
+	if (next_index)
+		*next_index += length;
+	return ret;
+}
+
+/*
+ * Read and decompress a metadata block or datablock.  Length is non-zero
+ * if a datablock is being read (the size is stored elsewhere in the
+ * filesystem), otherwise the length is obtained from the first two bytes of
+ * the metadata block.  A bit in the length field indicates if the block
+ * is stored uncompressed in the filesystem (usually because compression
+ * generated a larger block - this does occasionally happen with compression
+ * algorithms).
+ */
+static int __squashfs_read_data(struct super_block *sb, u64 index, int length,
+	u64 *next_index, struct squashfs_page_actor *output, bool sync)
+{
+	struct squashfs_read_request *req;
+
+	req = kcalloc(1, sizeof(struct squashfs_read_request), GFP_KERNEL);
+	if (!req) {
+		if (!sync)
+			squashfs_page_actor_free(output, -ENOMEM);
+		return -ENOMEM;
+	}
+
+	req->sb = sb;
+	req->index = index;
+	req->output = output;
+
+	if (next_index)
+		*next_index = index;
+
+	if (length)
+		length = read_data_block(req, length, next_index, sync);
+	else
+		length = read_metadata_block(req, next_index);
+
+	if (length < 0) {
+		ERROR("squashfs_read_data failed to read block 0x%llx\n",
+		      (unsigned long long)index);
+		return -EIO;
 	}
 
-	kfree(bh);
 	return length;
+}
 
-block_release:
-	for (; k < b; k++)
-		put_bh(bh[k]);
+int squashfs_read_data(struct super_block *sb, u64 index, int length,
+	u64 *next_index, struct squashfs_page_actor *output)
+{
+	return __squashfs_read_data(sb, index, length, next_index, output,
+				    true);
+}
+
+int squashfs_read_data_async(struct super_block *sb, u64 index, int length,
+	u64 *next_index, struct squashfs_page_actor *output)
+{
 
-read_failure:
-	ERROR("squashfs_read_data failed to read block 0x%llx\n",
-					(unsigned long long) index);
-	kfree(bh);
-	return -EIO;
+	return __squashfs_read_data(sb, index, length, next_index, output,
+				    false);
 }