* Linux 4.4.172
@ 2019-01-26 9:29 Greg KH
2019-01-26 9:29 ` Greg KH
0 siblings, 1 reply; 2+ messages in thread
From: Greg KH @ 2019-01-26 9:29 UTC (permalink / raw)
To: linux-kernel, Andrew Morton, torvalds, stable; +Cc: lwn, Jiri Slaby
[-- Attachment #1: Type: text/plain, Size: 12942 bytes --]
I'm announcing the release of the 4.4.172 kernel.
All users of the 4.4 kernel series must upgrade.
The updated 4.4.y git tree can be found at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable.git linux-4.4.y
and can be browsed at the normal kernel.org git web browser:
http://git.kernel.org/?p=linux/kernel/git/stable/linux-stable.git;a=summary
thanks,
greg k-h
------------
Documentation/filesystems/proc.txt | 4
Makefile | 2
arch/arm64/include/asm/kvm_arm.h | 3
arch/arm64/kernel/head.S | 3
arch/arm64/kernel/perf_event.c | 1
arch/arm64/kvm/hyp.S | 2
arch/mips/Kconfig | 4
arch/mips/pci/msi-octeon.c | 4
arch/mips/sibyte/common/Makefile | 1
arch/mips/sibyte/common/dma.c | 14 +
crypto/authenc.c | 14 +
crypto/authencesn.c | 2
drivers/base/bus.c | 7
drivers/block/loop.c | 79 +++++-----
drivers/block/loop.h | 1
drivers/char/ipmi/ipmi_ssif.c | 25 ++-
drivers/clk/imx/clk-imx6q.c | 6
drivers/cpuidle/cpuidle-pseries.c | 8 -
drivers/gpu/drm/drm_fb_helper.c | 7
drivers/md/dm-kcopyd.c | 19 +-
drivers/md/dm-snap.c | 22 +++
drivers/media/firewire/firedtv-avc.c | 6
drivers/media/firewire/firedtv.h | 6
drivers/media/platform/vivid/vivid-kthread-cap.c | 5
drivers/media/platform/vivid/vivid-kthread-out.c | 5
drivers/media/platform/vivid/vivid-vid-common.c | 2
drivers/media/usb/em28xx/em28xx-video.c | 4
drivers/media/v4l2-core/videobuf2-core.c | 14 +
drivers/mfd/tps6586x.c | 24 +++
drivers/mmc/host/atmel-mci.c | 3
drivers/net/ethernet/intel/e1000e/ptp.c | 13 +
drivers/net/ethernet/realtek/r8169.c | 2
drivers/platform/x86/asus-wmi.c | 3
drivers/scsi/megaraid/megaraid_sas_fp.c | 2
drivers/scsi/megaraid/megaraid_sas_fusion.c | 2
drivers/scsi/sd.c | 6
drivers/target/target_core_spc.c | 17 +-
drivers/tty/tty_ldsem.c | 10 +
drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c | 2
fs/btrfs/disk-io.c | 8 +
fs/f2fs/checkpoint.c | 168 ++++++++++++-----------
fs/f2fs/data.c | 118 +++++++++-------
fs/f2fs/dir.c | 87 ++++++-----
fs/f2fs/f2fs.h | 77 ++++++++--
fs/f2fs/file.c | 21 ++
fs/f2fs/inline.c | 115 +++++++++++++++
fs/f2fs/inode.c | 68 ++++++++-
fs/f2fs/node.c | 103 ++++++++------
fs/f2fs/node.h | 77 ++++++----
fs/f2fs/recovery.c | 165 +++++++++++-----------
fs/f2fs/segment.c | 93 ++++++------
fs/f2fs/segment.h | 48 +++++-
fs/f2fs/super.c | 134 +++++++++++++++---
fs/jffs2/super.c | 3
fs/ocfs2/localalloc.c | 9 -
fs/proc/array.c | 2
fs/pstore/ram_core.c | 5
fs/xfs/libxfs/xfs_attr.c | 9 +
include/linux/backing-dev-defs.h | 8 +
include/linux/f2fs_fs.h | 3
mm/page-writeback.c | 35 ++--
net/bridge/br_netfilter_hooks.c | 2
net/can/gw.c | 30 +++-
net/core/skbuff.c | 11 -
net/core/sock.c | 1
net/ipv4/ip_sockglue.c | 12 -
net/ipv6/af_inet6.c | 14 +
net/ipv6/datagram.c | 11 -
net/packet/af_packet.c | 4
net/sctp/ipv6.c | 5
net/sctp/protocol.c | 4
net/sunrpc/rpcb_clnt.c | 8 +
net/tipc/netlink_compat.c | 50 ++++++
scripts/kconfig/zconf.l | 4
security/security.c | 7
security/selinux/ss/policydb.c | 3
security/yama/yama_lsm.c | 4
sound/firewire/bebob/bebob.c | 2
tools/perf/arch/x86/util/intel-pt.c | 11 +
tools/perf/util/parse-events.c | 2
tools/perf/util/svghelper.c | 2
81 files changed, 1334 insertions(+), 563 deletions(-)
Adrian Hunter (1):
perf intel-pt: Fix error with config term "pt=0"
Anders Roxell (2):
writeback: don't decrement wb->refcnt if !wb->bdi
arm64: perf: set suppress_bind_attrs flag to true
Arnaldo Carvalho de Melo (2):
perf svghelper: Fix unchecked usage of strncpy()
perf parse-events: Fix unchecked usage of strncpy()
Arnd Bergmann (1):
mips: fix n32 compat_ipc_parse_version
Ben Hutchings (2):
f2fs: Add sanity_check_inode() function
media: em28xx: Fix misplaced reset of dev->v4l::field_count
Breno Leitao (1):
powerpc/pseries/cpuidle: Fix preempt warning
Brian Foster (1):
mm/page-writeback.c: don't break integrity writeback on ->writepage() error
Chao Yu (17):
f2fs: clean up argument of recover_data
f2fs: fix to convert inline directory correctly
f2fs: factor out fsync inode entry operations
f2fs: fix inode cache leak
f2fs: fix to avoid reading out encrypted data in page cache
f2fs: avoid unneeded loop in build_sit_entries
f2fs: fix race condition in between free nid allocator/initializer
f2fs: clean up with is_valid_blkaddr()
f2fs: introduce and spread verify_blkaddr
f2fs: fix to do sanity check with secs_per_zone
f2fs: fix to do sanity check with user_block_count
f2fs: fix to do sanity check with node footer and iblocks
f2fs: fix to do sanity check with reserved blkaddr of inline inode
f2fs: fix to do sanity check with block address in main area
f2fs: fix to do sanity check with block address in main area v2
f2fs: fix to do sanity check with cp_pack_start_sum
f2fs: fix invalid memory access
Corey Minyard (1):
ipmi:ssif: Fix handling of multi-part return messages
Daniel Santos (1):
jffs2: Fix use of uninitialized delayed_work, lockdep breakage
Daniel Vetter (1):
sysfs: Disable lockdep for driver bind/unbind files
Darrick J. Wong (1):
xfs: don't fail when converting shortform attr to long form during ATTR_REPLACE
David Ahern (2):
ipv6: Consider sk_bound_dev_if when binding a socket to a v4 mapped address
ipv6: Take rcu_read_lock in __inet6_bind for mapped addresses
David Disseldorp (1):
scsi: target: use consistent left-aligned ASCII INQUIRY data
Dmitry Safonov (1):
tty/ldsem: Wake up readers after timed out down_write()
Eric Biggers (1):
crypto: authenc - fix parsing key with misaligned rta_len
Eric Dumazet (2):
ipv6: fix kernel-infoleak in ipv6_local_error()
net: speed up skb_rbtree_purge()
Greg Kroah-Hartman (1):
Linux 4.4.172
Gwendal Grignou (1):
proc: Remove empty line in /proc/self/status
Hans Verkuil (3):
media: vivid: fix error handling of kthread_run
media: vivid: set min width/height to a value > 0
media: vb2: vb2_mmap: move lock up
Harsh Jain (1):
crypto: authencesn - Avoid twice completion call in decrypt path
Ivan Mironov (2):
scsi: sd: Fix cache_type_store()
drm/fb-helper: Ignore the value of fb_var_screeninfo.pixclock
J. Bruce Fields (1):
sunrpc: handle ENOMEM in rpcb_getport_async
Jaegeuk Kim (12):
f2fs: cover more area with nat_tree_lock
f2fs: give -EINVAL for norecovery and rw mount
f2fs: remove an obsolete variable
f2fs: use crc and cp version to determine roll-forward recovery
f2fs: put directory inodes before checkpoint in roll-forward recovery
f2fs: fix to determine start_cp_addr by sbi->cur_cp_pack
f2fs: detect wrong layout
f2fs: free meta pages if sanity check for ckpt is failed
f2fs: return error during fill_super
f2fs: sanity check on sit entry
f2fs: enhance sanity_check_raw_super() to avoid potential overflow
f2fs: fix missing up_read
James Morris (1):
LSM: Check for NULL cred-security on free
Jan Kara (2):
loop: Fold __loop_release into loop_release
loop: Get rid of loop_index_mutex
Jason Gunthorpe (1):
packet: Do not leak dev refcounts on error exit
JianJhen Chen (1):
net: bridge: fix a bug on using a neighbour cache entry without checking its state
Joel Fernandes (Google) (1):
pstore/ram: Do not treat empty buffers as valid
Jonas Danielsson (1):
mmc: atmel-mci: do not assume idle after atmci_request_end
Jonathan Hunter (1):
mfd: tps6586x: Handle interrupts on suspend
Josef Bacik (1):
btrfs: wait on ordered extents on abort cleanup
João Paulo Rechi Vita (1):
platform/x86: asus-wmi: Tell the EC the OS will handle the display off hotkey
Junxiao Bi (1):
ocfs2: fix panic due to unrecovered local alloc
Kai-Heng Feng (1):
r8169: Add support for new Realtek Ethernet
Kees Cook (1):
Yama: Check for pid death before checking ancestry
Lucas Stach (1):
clk: imx6q: reset exclusive gates on init
Maciej W. Rozycki (1):
MIPS: SiByte: Enable swiotlb for SWARM, LittleSur and BigSur
Mark Rutland (2):
arm64/kvm: consistently handle host HCR_EL2 flags
arm64: Don't trap host pointer auth use to EL2
Martin Blumenstingl (1):
f2fs: fix validation of the block count in sanity_check_raw_super
Masahiro Yamada (2):
kconfig: fix file name and line number of warn_ignored_character()
kconfig: fix memory leak when EOF is encountered in quotation
Mauro Carvalho Chehab (1):
media: vb2: be sure to unlock mutex on errors
Michal Hocko (1):
mm, proc: be more verbose about unstable VMA flags in /proc/<pid>/smaps
Miroslav Lichvar (1):
e1000e: allow non-monotonic SYSTIM readings
Nathan Chancellor (1):
media: firewire: Fix app_info parameter type in avc_ca{,_app}_info
Nikos Tsironis (2):
dm kcopyd: Fix bug causing workqueue stalls
dm snapshot: Fix excessive memory usage and workqueue stalls
Oliver Hartkopp (1):
can: gw: ensure DLC boundaries after CAN frame modification
Qian Cai (1):
scsi: megaraid: fix out-of-bound array accesses
Shawn Lin (1):
f2fs: move sanity checking of cp into get_valid_checkpoint
Stephen Smalley (1):
selinux: fix GPF on invalid policy
Takashi Sakamoto (1):
ALSA: bebob: fix model-id of unit for Apogee Ensemble
Tetsuo Handa (2):
block/loop: Use global lock for ioctl() operation.
loop: Fix double mutex_unlock(&loop_ctl_mutex) in loop_control_ioctl()
Tiezhu Yang (1):
f2fs: introduce get_checkpoint_version for cleanup
Vlad Tsyrklevich (1):
omap2fb: Fix stack memory disclosure
Willem de Bruijn (1):
ip: on queued skb use skb_header_pointer instead of pskb_may_pull
Xin Long (1):
sctp: allocate sctp_sockaddr_entry with kzalloc
Ying Xue (5):
tipc: fix uninit-value in tipc_nl_compat_link_reset_stats
tipc: fix uninit-value in tipc_nl_compat_bearer_enable
tipc: fix uninit-value in tipc_nl_compat_link_set
tipc: fix uninit-value in tipc_nl_compat_name_table_dump
tipc: fix uninit-value in tipc_nl_compat_doit
YunQiang Su (1):
Disable MSI also when pcie-octeon.pcie_disable on
Yunlei He (2):
f2fs: not allow to write illegal blkaddr
f2fs: check blkaddr more accuratly before issue a bio
yupeng (1):
net: call sk_dst_reset when set SO_DONTROUTE
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]
^ permalink raw reply [flat|nested] 2+ messages in thread
* Re: Linux 4.4.172
2019-01-26 9:29 Linux 4.4.172 Greg KH
@ 2019-01-26 9:29 ` Greg KH
0 siblings, 0 replies; 2+ messages in thread
From: Greg KH @ 2019-01-26 9:29 UTC (permalink / raw)
To: linux-kernel, Andrew Morton, torvalds, stable; +Cc: lwn, Jiri Slaby
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index 6d2689ebf824..5b87946a53a3 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -466,7 +466,9 @@ manner. The codes are the following:
Note that there is no guarantee that every flag and associated mnemonic will
be present in all further kernel releases. Things get changed, the flags may
-be vanished or the reverse -- new added.
+be vanished or the reverse -- new added. Interpretation of their meaning
+might change in future as well. So each consumer of these flags has to
+follow each specific kernel version for the exact semantic.
This file is only present if the CONFIG_MMU kernel configuration option is
enabled.
diff --git a/Makefile b/Makefile
index c6b680faedd8..2aa8db459a74 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
VERSION = 4
PATCHLEVEL = 4
-SUBLEVEL = 171
+SUBLEVEL = 172
EXTRAVERSION =
NAME = Blurry Fish Butt
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index ef8e13d379cb..d7e7cf56e8d6 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -23,6 +23,8 @@
#include <asm/types.h>
/* Hyp Configuration Register (HCR) bits */
+#define HCR_API (UL(1) << 41)
+#define HCR_APK (UL(1) << 40)
#define HCR_ID (UL(1) << 33)
#define HCR_CD (UL(1) << 32)
#define HCR_RW_SHIFT 31
@@ -81,6 +83,7 @@
HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW)
#define HCR_VIRT_EXCP_MASK (HCR_VA | HCR_VI | HCR_VF)
#define HCR_INT_OVERRIDE (HCR_FMO | HCR_IMO)
+#define HCR_HOST_NVHE_FLAGS (HCR_RW | HCR_API | HCR_APK)
/* Hyp System Control Register (SCTLR_EL2) bits */
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index d019c3a58cc2..0382eba4bf7b 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -30,6 +30,7 @@
#include <asm/cache.h>
#include <asm/cputype.h>
#include <asm/kernel-pgtable.h>
+#include <asm/kvm_arm.h>
#include <asm/memory.h>
#include <asm/pgtable-hwdef.h>
#include <asm/pgtable.h>
@@ -464,7 +465,7 @@ CPU_LE( bic x0, x0, #(3 << 24) ) // Clear the EE and E0E bits for EL1
ret
/* Hyp configuration. */
-2: mov x0, #(1 << 31) // 64-bit EL1
+2: mov_q x0, HCR_HOST_NVHE_FLAGS
msr hcr_el2, x0
/* Generic timers. */
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 62d3dc60ca09..e99a0ed7e66b 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -670,6 +670,7 @@ static struct platform_driver armv8_pmu_driver = {
.driver = {
.name = "armv8-pmu",
.of_match_table = armv8_pmu_of_device_ids,
+ .suppress_bind_attrs = true,
},
.probe = armv8_pmu_device_probe,
};
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index 86c289832272..8d3da858c257 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -494,7 +494,7 @@
.endm
.macro deactivate_traps
- mov x2, #HCR_RW
+ mov_q x2, HCR_HOST_NVHE_FLAGS
msr hcr_el2, x2
msr hstr_el2, xzr
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 8b0424abc84c..333ea0389adb 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -760,6 +760,7 @@ config SIBYTE_SWARM
select SYS_SUPPORTS_HIGHMEM
select SYS_SUPPORTS_LITTLE_ENDIAN
select ZONE_DMA32 if 64BIT
+ select SWIOTLB if ARCH_DMA_ADDR_T_64BIT && PCI
config SIBYTE_LITTLESUR
bool "Sibyte BCM91250C2-LittleSur"
@@ -782,6 +783,7 @@ config SIBYTE_SENTOSA
select SYS_HAS_CPU_SB1
select SYS_SUPPORTS_BIG_ENDIAN
select SYS_SUPPORTS_LITTLE_ENDIAN
+ select SWIOTLB if ARCH_DMA_ADDR_T_64BIT && PCI
config SIBYTE_BIGSUR
bool "Sibyte BCM91480B-BigSur"
@@ -795,6 +797,7 @@ config SIBYTE_BIGSUR
select SYS_SUPPORTS_HIGHMEM
select SYS_SUPPORTS_LITTLE_ENDIAN
select ZONE_DMA32 if 64BIT
+ select SWIOTLB if ARCH_DMA_ADDR_T_64BIT && PCI
config SNI_RM
bool "SNI RM200/300/400"
@@ -2972,6 +2975,7 @@ config MIPS32_O32
config MIPS32_N32
bool "Kernel support for n32 binaries"
depends on 64BIT
+ select ARCH_WANT_COMPAT_IPC_PARSE_VERSION
select COMPAT
select MIPS32_COMPAT
select SYSVIPC_COMPAT if SYSVIPC
diff --git a/arch/mips/pci/msi-octeon.c b/arch/mips/pci/msi-octeon.c
index 2a5bb849b10e..288b58b00dc8 100644
--- a/arch/mips/pci/msi-octeon.c
+++ b/arch/mips/pci/msi-octeon.c
@@ -369,7 +369,9 @@ int __init octeon_msi_initialize(void)
int irq;
struct irq_chip *msi;
- if (octeon_dma_bar_type == OCTEON_DMA_BAR_TYPE_PCIE) {
+ if (octeon_dma_bar_type == OCTEON_DMA_BAR_TYPE_INVALID) {
+ return 0;
+ } else if (octeon_dma_bar_type == OCTEON_DMA_BAR_TYPE_PCIE) {
msi_rcv_reg[0] = CVMX_PEXP_NPEI_MSI_RCV0;
msi_rcv_reg[1] = CVMX_PEXP_NPEI_MSI_RCV1;
msi_rcv_reg[2] = CVMX_PEXP_NPEI_MSI_RCV2;
diff --git a/arch/mips/sibyte/common/Makefile b/arch/mips/sibyte/common/Makefile
index b3d6bf23a662..3ef3fb658136 100644
--- a/arch/mips/sibyte/common/Makefile
+++ b/arch/mips/sibyte/common/Makefile
@@ -1,4 +1,5 @@
obj-y := cfe.o
+obj-$(CONFIG_SWIOTLB) += dma.o
obj-$(CONFIG_SIBYTE_BUS_WATCHER) += bus_watcher.o
obj-$(CONFIG_SIBYTE_CFE_CONSOLE) += cfe_console.o
obj-$(CONFIG_SIBYTE_TBPROF) += sb_tbprof.o
diff --git a/arch/mips/sibyte/common/dma.c b/arch/mips/sibyte/common/dma.c
new file mode 100644
index 000000000000..eb47a94f3583
--- /dev/null
+++ b/arch/mips/sibyte/common/dma.c
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * DMA support for Broadcom SiByte platforms.
+ *
+ * Copyright (c) 2018 Maciej W. Rozycki
+ */
+
+#include <linux/swiotlb.h>
+#include <asm/bootinfo.h>
+
+void __init plat_swiotlb_setup(void)
+{
+ swiotlb_init(1);
+}
diff --git a/crypto/authenc.c b/crypto/authenc.c
index b7290c5b1eaa..5c25005ff398 100644
--- a/crypto/authenc.c
+++ b/crypto/authenc.c
@@ -58,14 +58,22 @@ int crypto_authenc_extractkeys(struct crypto_authenc_keys *keys, const u8 *key,
return -EINVAL;
if (rta->rta_type != CRYPTO_AUTHENC_KEYA_PARAM)
return -EINVAL;
- if (RTA_PAYLOAD(rta) < sizeof(*param))
+
+ /*
+ * RTA_OK() didn't align the rtattr's payload when validating that it
+ * fits in the buffer. Yet, the keys should start on the next 4-byte
+ * aligned boundary. To avoid confusion, require that the rtattr
+ * payload be exactly the param struct, which has a 4-byte aligned size.
+ */
+ if (RTA_PAYLOAD(rta) != sizeof(*param))
return -EINVAL;
+ BUILD_BUG_ON(sizeof(*param) % RTA_ALIGNTO);
param = RTA_DATA(rta);
keys->enckeylen = be32_to_cpu(param->enckeylen);
- key += RTA_ALIGN(rta->rta_len);
- keylen -= RTA_ALIGN(rta->rta_len);
+ key += rta->rta_len;
+ keylen -= rta->rta_len;
if (keylen < keys->enckeylen)
return -EINVAL;
diff --git a/crypto/authencesn.c b/crypto/authencesn.c
index fa0c4567f697..5fdf3e532310 100644
--- a/crypto/authencesn.c
+++ b/crypto/authencesn.c
@@ -276,7 +276,7 @@ static void authenc_esn_verify_ahash_done(struct crypto_async_request *areq,
struct aead_request *req = areq->data;
err = err ?: crypto_authenc_esn_decrypt_tail(req, 0);
- aead_request_complete(req, err);
+ authenc_esn_request_complete(req, err);
}
static int crypto_authenc_esn_decrypt(struct aead_request *req)
diff --git a/drivers/base/bus.c b/drivers/base/bus.c
index 0346e46e2871..ecca4ae248e0 100644
--- a/drivers/base/bus.c
+++ b/drivers/base/bus.c
@@ -33,6 +33,9 @@ static struct kset *system_kset;
#define to_drv_attr(_attr) container_of(_attr, struct driver_attribute, attr)
+#define DRIVER_ATTR_IGNORE_LOCKDEP(_name, _mode, _show, _store) \
+ struct driver_attribute driver_attr_##_name = \
+ __ATTR_IGNORE_LOCKDEP(_name, _mode, _show, _store)
static int __must_check bus_rescan_devices_helper(struct device *dev,
void *data);
@@ -198,7 +201,7 @@ static ssize_t unbind_store(struct device_driver *drv, const char *buf,
bus_put(bus);
return err;
}
-static DRIVER_ATTR_WO(unbind);
+static DRIVER_ATTR_IGNORE_LOCKDEP(unbind, S_IWUSR, NULL, unbind_store);
/*
* Manually attach a device to a driver.
@@ -234,7 +237,7 @@ static ssize_t bind_store(struct device_driver *drv, const char *buf,
bus_put(bus);
return err;
}
-static DRIVER_ATTR_WO(bind);
+static DRIVER_ATTR_IGNORE_LOCKDEP(bind, S_IWUSR, NULL, bind_store);
static ssize_t show_drivers_autoprobe(struct bus_type *bus, char *buf)
{
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index da3902ac16c8..b1cf891cb3d9 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -81,7 +81,7 @@
#include <asm/uaccess.h>
static DEFINE_IDR(loop_index_idr);
-static DEFINE_MUTEX(loop_index_mutex);
+static DEFINE_MUTEX(loop_ctl_mutex);
static int max_part;
static int part_shift;
@@ -1044,7 +1044,7 @@ static int loop_clr_fd(struct loop_device *lo)
*/
if (atomic_read(&lo->lo_refcnt) > 1) {
lo->lo_flags |= LO_FLAGS_AUTOCLEAR;
- mutex_unlock(&lo->lo_ctl_mutex);
+ mutex_unlock(&loop_ctl_mutex);
return 0;
}
@@ -1093,12 +1093,12 @@ static int loop_clr_fd(struct loop_device *lo)
if (!part_shift)
lo->lo_disk->flags |= GENHD_FL_NO_PART_SCAN;
loop_unprepare_queue(lo);
- mutex_unlock(&lo->lo_ctl_mutex);
+ mutex_unlock(&loop_ctl_mutex);
/*
- * Need not hold lo_ctl_mutex to fput backing file.
- * Calling fput holding lo_ctl_mutex triggers a circular
+ * Need not hold loop_ctl_mutex to fput backing file.
+ * Calling fput holding loop_ctl_mutex triggers a circular
* lock dependency possibility warning as fput can take
- * bd_mutex which is usually taken before lo_ctl_mutex.
+ * bd_mutex which is usually taken before loop_ctl_mutex.
*/
fput(filp);
return 0;
@@ -1361,7 +1361,7 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode,
struct loop_device *lo = bdev->bd_disk->private_data;
int err;
- mutex_lock_nested(&lo->lo_ctl_mutex, 1);
+ mutex_lock_nested(&loop_ctl_mutex, 1);
switch (cmd) {
case LOOP_SET_FD:
err = loop_set_fd(lo, mode, bdev, arg);
@@ -1370,7 +1370,7 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode,
err = loop_change_fd(lo, bdev, arg);
break;
case LOOP_CLR_FD:
- /* loop_clr_fd would have unlocked lo_ctl_mutex on success */
+ /* loop_clr_fd would have unlocked loop_ctl_mutex on success */
err = loop_clr_fd(lo);
if (!err)
goto out_unlocked;
@@ -1406,7 +1406,7 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode,
default:
err = lo->ioctl ? lo->ioctl(lo, cmd, arg) : -EINVAL;
}
- mutex_unlock(&lo->lo_ctl_mutex);
+ mutex_unlock(&loop_ctl_mutex);
out_unlocked:
return err;
@@ -1539,16 +1539,16 @@ static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode,
switch(cmd) {
case LOOP_SET_STATUS:
- mutex_lock(&lo->lo_ctl_mutex);
+ mutex_lock(&loop_ctl_mutex);
err = loop_set_status_compat(
lo, (const struct compat_loop_info __user *) arg);
- mutex_unlock(&lo->lo_ctl_mutex);
+ mutex_unlock(&loop_ctl_mutex);
break;
case LOOP_GET_STATUS:
- mutex_lock(&lo->lo_ctl_mutex);
+ mutex_lock(&loop_ctl_mutex);
err = loop_get_status_compat(
lo, (struct compat_loop_info __user *) arg);
- mutex_unlock(&lo->lo_ctl_mutex);
+ mutex_unlock(&loop_ctl_mutex);
break;
case LOOP_SET_CAPACITY:
case LOOP_CLR_FD:
@@ -1570,9 +1570,11 @@ static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode,
static int lo_open(struct block_device *bdev, fmode_t mode)
{
struct loop_device *lo;
- int err = 0;
+ int err;
- mutex_lock(&loop_index_mutex);
+ err = mutex_lock_killable(&loop_ctl_mutex);
+ if (err)
+ return err;
lo = bdev->bd_disk->private_data;
if (!lo) {
err = -ENXIO;
@@ -1581,18 +1583,20 @@ static int lo_open(struct block_device *bdev, fmode_t mode)
atomic_inc(&lo->lo_refcnt);
out:
- mutex_unlock(&loop_index_mutex);
+ mutex_unlock(&loop_ctl_mutex);
return err;
}
-static void __lo_release(struct loop_device *lo)
+static void lo_release(struct gendisk *disk, fmode_t mode)
{
+ struct loop_device *lo;
int err;
+ mutex_lock(&loop_ctl_mutex);
+ lo = disk->private_data;
if (atomic_dec_return(&lo->lo_refcnt))
- return;
+ goto out_unlock;
- mutex_lock(&lo->lo_ctl_mutex);
if (lo->lo_flags & LO_FLAGS_AUTOCLEAR) {
/*
* In autoclear mode, stop the loop thread
@@ -1609,14 +1613,8 @@ static void __lo_release(struct loop_device *lo)
loop_flush(lo);
}
- mutex_unlock(&lo->lo_ctl_mutex);
-}
-
-static void lo_release(struct gendisk *disk, fmode_t mode)
-{
- mutex_lock(&loop_index_mutex);
- __lo_release(disk->private_data);
- mutex_unlock(&loop_index_mutex);
+out_unlock:
+ mutex_unlock(&loop_ctl_mutex);
}
static const struct block_device_operations lo_fops = {
@@ -1655,10 +1653,10 @@ static int unregister_transfer_cb(int id, void *ptr, void *data)
struct loop_device *lo = ptr;
struct loop_func_table *xfer = data;
- mutex_lock(&lo->lo_ctl_mutex);
+ mutex_lock(&loop_ctl_mutex);
if (lo->lo_encryption == xfer)
loop_release_xfer(lo);
- mutex_unlock(&lo->lo_ctl_mutex);
+ mutex_unlock(&loop_ctl_mutex);
return 0;
}
@@ -1820,7 +1818,6 @@ static int loop_add(struct loop_device **l, int i)
if (!part_shift)
disk->flags |= GENHD_FL_NO_PART_SCAN;
disk->flags |= GENHD_FL_EXT_DEVT;
- mutex_init(&lo->lo_ctl_mutex);
atomic_set(&lo->lo_refcnt, 0);
lo->lo_number = i;
spin_lock_init(&lo->lo_lock);
@@ -1899,7 +1896,7 @@ static struct kobject *loop_probe(dev_t dev, int *part, void *data)
struct kobject *kobj;
int err;
- mutex_lock(&loop_index_mutex);
+ mutex_lock(&loop_ctl_mutex);
err = loop_lookup(&lo, MINOR(dev) >> part_shift);
if (err < 0)
err = loop_add(&lo, MINOR(dev) >> part_shift);
@@ -1907,7 +1904,7 @@ static struct kobject *loop_probe(dev_t dev, int *part, void *data)
kobj = NULL;
else
kobj = get_disk(lo->lo_disk);
- mutex_unlock(&loop_index_mutex);
+ mutex_unlock(&loop_ctl_mutex);
*part = 0;
return kobj;
@@ -1917,9 +1914,13 @@ static long loop_control_ioctl(struct file *file, unsigned int cmd,
unsigned long parm)
{
struct loop_device *lo;
- int ret = -ENOSYS;
+ int ret;
+
+ ret = mutex_lock_killable(&loop_ctl_mutex);
+ if (ret)
+ return ret;
- mutex_lock(&loop_index_mutex);
+ ret = -ENOSYS;
switch (cmd) {
case LOOP_CTL_ADD:
ret = loop_lookup(&lo, parm);
@@ -1933,19 +1934,15 @@ static long loop_control_ioctl(struct file *file, unsigned int cmd,
ret = loop_lookup(&lo, parm);
if (ret < 0)
break;
- mutex_lock(&lo->lo_ctl_mutex);
if (lo->lo_state != Lo_unbound) {
ret = -EBUSY;
- mutex_unlock(&lo->lo_ctl_mutex);
break;
}
if (atomic_read(&lo->lo_refcnt) > 0) {
ret = -EBUSY;
- mutex_unlock(&lo->lo_ctl_mutex);
break;
}
lo->lo_disk->private_data = NULL;
- mutex_unlock(&lo->lo_ctl_mutex);
idr_remove(&loop_index_idr, lo->lo_number);
loop_remove(lo);
break;
@@ -1955,7 +1952,7 @@ static long loop_control_ioctl(struct file *file, unsigned int cmd,
break;
ret = loop_add(&lo, -1);
}
- mutex_unlock(&loop_index_mutex);
+ mutex_unlock(&loop_ctl_mutex);
return ret;
}
@@ -2038,10 +2035,10 @@ static int __init loop_init(void)
THIS_MODULE, loop_probe, NULL, NULL);
/* pre-create number of devices given by config or max_loop */
- mutex_lock(&loop_index_mutex);
+ mutex_lock(&loop_ctl_mutex);
for (i = 0; i < nr; i++)
loop_add(&lo, i);
- mutex_unlock(&loop_index_mutex);
+ mutex_unlock(&loop_ctl_mutex);
printk(KERN_INFO "loop: module loaded\n");
return 0;
diff --git a/drivers/block/loop.h b/drivers/block/loop.h
index 60f0fd2c0c65..a923e74495ce 100644
--- a/drivers/block/loop.h
+++ b/drivers/block/loop.h
@@ -55,7 +55,6 @@ struct loop_device {
spinlock_t lo_lock;
int lo_state;
- struct mutex lo_ctl_mutex;
struct kthread_worker worker;
struct task_struct *worker_task;
bool use_dio;
diff --git a/drivers/char/ipmi/ipmi_ssif.c b/drivers/char/ipmi/ipmi_ssif.c
index 7a2e23d6bfdd..b2da2382d544 100644
--- a/drivers/char/ipmi/ipmi_ssif.c
+++ b/drivers/char/ipmi/ipmi_ssif.c
@@ -637,8 +637,9 @@ static void msg_done_handler(struct ssif_info *ssif_info, int result,
/* Remove the multi-part read marker. */
len -= 2;
+ data += 2;
for (i = 0; i < len; i++)
- ssif_info->data[i] = data[i+2];
+ ssif_info->data[i] = data[i];
ssif_info->multi_len = len;
ssif_info->multi_pos = 1;
@@ -666,8 +667,19 @@ static void msg_done_handler(struct ssif_info *ssif_info, int result,
}
blocknum = data[0];
+ len--;
+ data++;
+
+ if (blocknum != 0xff && len != 31) {
+ /* All blocks but the last must have 31 data bytes. */
+ result = -EIO;
+ if (ssif_info->ssif_debug & SSIF_DEBUG_MSG)
+ pr_info("Received middle message <31\n");
- if (ssif_info->multi_len + len - 1 > IPMI_MAX_MSG_LENGTH) {
+ goto continue_op;
+ }
+
+ if (ssif_info->multi_len + len > IPMI_MAX_MSG_LENGTH) {
/* Received message too big, abort the operation. */
result = -E2BIG;
if (ssif_info->ssif_debug & SSIF_DEBUG_MSG)
@@ -676,16 +688,14 @@ static void msg_done_handler(struct ssif_info *ssif_info, int result,
goto continue_op;
}
- /* Remove the blocknum from the data. */
- len--;
for (i = 0; i < len; i++)
- ssif_info->data[i + ssif_info->multi_len] = data[i + 1];
+ ssif_info->data[i + ssif_info->multi_len] = data[i];
ssif_info->multi_len += len;
if (blocknum == 0xff) {
/* End of read */
len = ssif_info->multi_len;
data = ssif_info->data;
- } else if (blocknum + 1 != ssif_info->multi_pos) {
+ } else if (blocknum != ssif_info->multi_pos) {
/*
* Out of sequence block, just abort. Block
* numbers start at zero for the second block,
@@ -713,6 +723,7 @@ static void msg_done_handler(struct ssif_info *ssif_info, int result,
}
}
+ continue_op:
if (result < 0) {
ssif_inc_stat(ssif_info, receive_errors);
} else {
@@ -720,8 +731,6 @@ static void msg_done_handler(struct ssif_info *ssif_info, int result,
ssif_inc_stat(ssif_info, received_message_parts);
}
-
- continue_op:
if (ssif_info->ssif_debug & SSIF_DEBUG_STATE)
pr_info(PFX "DONE 1: state = %d, result=%d.\n",
ssif_info->ssif_state, result);
diff --git a/drivers/clk/imx/clk-imx6q.c b/drivers/clk/imx/clk-imx6q.c
index a0df83e6b84b..46c05c9a9354 100644
--- a/drivers/clk/imx/clk-imx6q.c
+++ b/drivers/clk/imx/clk-imx6q.c
@@ -239,8 +239,12 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node)
* lvds1_gate and lvds2_gate are pseudo-gates. Both can be
* independently configured as clock inputs or outputs. We treat
* the "output_enable" bit as a gate, even though it's really just
- * enabling clock output.
+ * enabling clock output. Initially the gate bits are cleared, as
+ * otherwise the exclusive configuration gets locked in the setup done
+ * by software running before the clock driver, with no way to change
+ * it.
*/
+ writel(readl(base + 0x160) & ~0x3c00, base + 0x160);
clk[IMX6QDL_CLK_LVDS1_GATE] = imx_clk_gate_exclusive("lvds1_gate", "lvds1_sel", base + 0x160, 10, BIT(12));
clk[IMX6QDL_CLK_LVDS2_GATE] = imx_clk_gate_exclusive("lvds2_gate", "lvds2_sel", base + 0x160, 11, BIT(13));
diff --git a/drivers/cpuidle/cpuidle-pseries.c b/drivers/cpuidle/cpuidle-pseries.c
index 07135e009d8b..601a6c3acc7f 100644
--- a/drivers/cpuidle/cpuidle-pseries.c
+++ b/drivers/cpuidle/cpuidle-pseries.c
@@ -240,7 +240,13 @@ static int pseries_idle_probe(void)
return -ENODEV;
if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
- if (lppaca_shared_proc(get_lppaca())) {
+ /*
+ * Use local_paca instead of get_lppaca() since
+ * preemption is not disabled, and it is not required in
+ * fact, since lppaca_ptr does not need to be the value
+ * associated to the current CPU, it can be from any CPU.
+ */
+ if (lppaca_shared_proc(local_paca->lppaca_ptr)) {
cpuidle_state_table = shared_states;
max_idle_state = ARRAY_SIZE(shared_states);
} else {
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index 5ad036741b99..e449f22c8f29 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -1109,9 +1109,14 @@ int drm_fb_helper_check_var(struct fb_var_screeninfo *var,
struct drm_framebuffer *fb = fb_helper->fb;
int depth;
- if (var->pixclock != 0 || in_dbg_master())
+ if (in_dbg_master())
return -EINVAL;
+ if (var->pixclock != 0) {
+ DRM_DEBUG("fbdev emulation doesn't support changing the pixel clock, value of pixclock is ignored\n");
+ var->pixclock = 0;
+ }
+
/* Need to resize the fb object !!! */
if (var->bits_per_pixel > fb->bits_per_pixel ||
var->xres > fb->width || var->yres > fb->height ||
diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c
index 54c308e6704f..04248394843e 100644
--- a/drivers/md/dm-kcopyd.c
+++ b/drivers/md/dm-kcopyd.c
@@ -55,15 +55,17 @@ struct dm_kcopyd_client {
struct dm_kcopyd_throttle *throttle;
/*
- * We maintain three lists of jobs:
+ * We maintain four lists of jobs:
*
* i) jobs waiting for pages
* ii) jobs that have pages, and are waiting for the io to be issued.
- * iii) jobs that have completed.
+ * iii) jobs that don't need to do any IO and just run a callback
+ * iv) jobs that have completed.
*
- * All three of these are protected by job_lock.
+ * All four of these are protected by job_lock.
*/
spinlock_t job_lock;
+ struct list_head callback_jobs;
struct list_head complete_jobs;
struct list_head io_jobs;
struct list_head pages_jobs;
@@ -583,6 +585,7 @@ static void do_work(struct work_struct *work)
struct dm_kcopyd_client *kc = container_of(work,
struct dm_kcopyd_client, kcopyd_work);
struct blk_plug plug;
+ unsigned long flags;
/*
* The order that these are called is *very* important.
@@ -591,6 +594,10 @@ static void do_work(struct work_struct *work)
* list. io jobs call wake when they complete and it all
* starts again.
*/
+ spin_lock_irqsave(&kc->job_lock, flags);
+ list_splice_tail_init(&kc->callback_jobs, &kc->complete_jobs);
+ spin_unlock_irqrestore(&kc->job_lock, flags);
+
blk_start_plug(&plug);
process_jobs(&kc->complete_jobs, kc, run_complete_job);
process_jobs(&kc->pages_jobs, kc, run_pages_job);
@@ -608,7 +615,7 @@ static void dispatch_job(struct kcopyd_job *job)
struct dm_kcopyd_client *kc = job->kc;
atomic_inc(&kc->nr_jobs);
if (unlikely(!job->source.count))
- push(&kc->complete_jobs, job);
+ push(&kc->callback_jobs, job);
else if (job->pages == &zero_page_list)
push(&kc->io_jobs, job);
else
@@ -795,7 +802,7 @@ void dm_kcopyd_do_callback(void *j, int read_err, unsigned long write_err)
job->read_err = read_err;
job->write_err = write_err;
- push(&kc->complete_jobs, job);
+ push(&kc->callback_jobs, job);
wake(kc);
}
EXPORT_SYMBOL(dm_kcopyd_do_callback);
@@ -825,6 +832,7 @@ struct dm_kcopyd_client *dm_kcopyd_client_create(struct dm_kcopyd_throttle *thro
return ERR_PTR(-ENOMEM);
spin_lock_init(&kc->job_lock);
+ INIT_LIST_HEAD(&kc->callback_jobs);
INIT_LIST_HEAD(&kc->complete_jobs);
INIT_LIST_HEAD(&kc->io_jobs);
INIT_LIST_HEAD(&kc->pages_jobs);
@@ -874,6 +882,7 @@ void dm_kcopyd_client_destroy(struct dm_kcopyd_client *kc)
/* Wait for completion of all jobs submitted by this client. */
wait_event(kc->destroyq, !atomic_read(&kc->nr_jobs));
+ BUG_ON(!list_empty(&kc->callback_jobs));
BUG_ON(!list_empty(&kc->complete_jobs));
BUG_ON(!list_empty(&kc->io_jobs));
BUG_ON(!list_empty(&kc->pages_jobs));
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index e108deebbaaa..5d3797728b9c 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -19,6 +19,7 @@
#include <linux/vmalloc.h>
#include <linux/log2.h>
#include <linux/dm-kcopyd.h>
+#include <linux/semaphore.h>
#include "dm.h"
@@ -105,6 +106,9 @@ struct dm_snapshot {
/* The on disk metadata handler */
struct dm_exception_store *store;
+ /* Maximum number of in-flight COW jobs. */
+ struct semaphore cow_count;
+
struct dm_kcopyd_client *kcopyd_client;
/* Wait for events based on state_bits */
@@ -145,6 +149,19 @@ struct dm_snapshot {
#define RUNNING_MERGE 0
#define SHUTDOWN_MERGE 1
+/*
+ * Maximum number of chunks being copied on write.
+ *
+ * The value was decided experimentally as a trade-off between memory
+ * consumption, stalling the kernel's workqueues and maintaining a high enough
+ * throughput.
+ */
+#define DEFAULT_COW_THRESHOLD 2048
+
+static int cow_threshold = DEFAULT_COW_THRESHOLD;
+module_param_named(snapshot_cow_threshold, cow_threshold, int, 0644);
+MODULE_PARM_DESC(snapshot_cow_threshold, "Maximum number of chunks being copied on write");
+
DECLARE_DM_KCOPYD_THROTTLE_WITH_MODULE_PARM(snapshot_copy_throttle,
"A percentage of time allocated for copy on write");
@@ -1190,6 +1207,8 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv)
goto bad_hash_tables;
}
+ sema_init(&s->cow_count, (cow_threshold > 0) ? cow_threshold : INT_MAX);
+
s->kcopyd_client = dm_kcopyd_client_create(&dm_kcopyd_throttle);
if (IS_ERR(s->kcopyd_client)) {
r = PTR_ERR(s->kcopyd_client);
@@ -1563,6 +1582,7 @@ static void copy_callback(int read_err, unsigned long write_err, void *context)
}
list_add(&pe->out_of_order_entry, lh);
}
+ up(&s->cow_count);
}
/*
@@ -1586,6 +1606,7 @@ static void start_copy(struct dm_snap_pending_exception *pe)
dest.count = src.count;
/* Hand over to kcopyd */
+ down(&s->cow_count);
dm_kcopyd_copy(s->kcopyd_client, &src, 1, &dest, 0, copy_callback, pe);
}
@@ -1606,6 +1627,7 @@ static void start_full_bio(struct dm_snap_pending_exception *pe,
pe->full_bio_end_io = bio->bi_end_io;
pe->full_bio_private = bio->bi_private;
+ down(&s->cow_count);
callback_data = dm_kcopyd_prepare_callback(s->kcopyd_client,
copy_callback, pe);
diff --git a/drivers/media/firewire/firedtv-avc.c b/drivers/media/firewire/firedtv-avc.c
index 251a556112a9..280b5ffea592 100644
--- a/drivers/media/firewire/firedtv-avc.c
+++ b/drivers/media/firewire/firedtv-avc.c
@@ -968,7 +968,8 @@ static int get_ca_object_length(struct avc_response_frame *r)
return r->operand[7];
}
-int avc_ca_app_info(struct firedtv *fdtv, char *app_info, unsigned int *len)
+int avc_ca_app_info(struct firedtv *fdtv, unsigned char *app_info,
+ unsigned int *len)
{
struct avc_command_frame *c = (void *)fdtv->avc_data;
struct avc_response_frame *r = (void *)fdtv->avc_data;
@@ -1009,7 +1010,8 @@ out:
return ret;
}
-int avc_ca_info(struct firedtv *fdtv, char *app_info, unsigned int *len)
+int avc_ca_info(struct firedtv *fdtv, unsigned char *app_info,
+ unsigned int *len)
{
struct avc_command_frame *c = (void *)fdtv->avc_data;
struct avc_response_frame *r = (void *)fdtv->avc_data;
diff --git a/drivers/media/firewire/firedtv.h b/drivers/media/firewire/firedtv.h
index 345d1eda8c05..5b18a08c6285 100644
--- a/drivers/media/firewire/firedtv.h
+++ b/drivers/media/firewire/firedtv.h
@@ -124,8 +124,10 @@ int avc_lnb_control(struct firedtv *fdtv, char voltage, char burst,
struct dvb_diseqc_master_cmd *diseqcmd);
void avc_remote_ctrl_work(struct work_struct *work);
int avc_register_remote_control(struct firedtv *fdtv);
-int avc_ca_app_info(struct firedtv *fdtv, char *app_info, unsigned int *len);
-int avc_ca_info(struct firedtv *fdtv, char *app_info, unsigned int *len);
+int avc_ca_app_info(struct firedtv *fdtv, unsigned char *app_info,
+ unsigned int *len);
+int avc_ca_info(struct firedtv *fdtv, unsigned char *app_info,
+ unsigned int *len);
int avc_ca_reset(struct firedtv *fdtv);
int avc_ca_pmt(struct firedtv *fdtv, char *app_info, int length);
int avc_ca_get_time_date(struct firedtv *fdtv, int *interval);
diff --git a/drivers/media/platform/vivid/vivid-kthread-cap.c b/drivers/media/platform/vivid/vivid-kthread-cap.c
index 83cc6d3b4784..81ba454a6d95 100644
--- a/drivers/media/platform/vivid/vivid-kthread-cap.c
+++ b/drivers/media/platform/vivid/vivid-kthread-cap.c
@@ -863,8 +863,11 @@ int vivid_start_generating_vid_cap(struct vivid_dev *dev, bool *pstreaming)
"%s-vid-cap", dev->v4l2_dev.name);
if (IS_ERR(dev->kthread_vid_cap)) {
+ int err = PTR_ERR(dev->kthread_vid_cap);
+
+ dev->kthread_vid_cap = NULL;
v4l2_err(&dev->v4l2_dev, "kernel_thread() failed\n");
- return PTR_ERR(dev->kthread_vid_cap);
+ return err;
}
*pstreaming = true;
vivid_grab_controls(dev, true);
diff --git a/drivers/media/platform/vivid/vivid-kthread-out.c b/drivers/media/platform/vivid/vivid-kthread-out.c
index c2c46dcdbe95..2c5dbdcb576a 100644
--- a/drivers/media/platform/vivid/vivid-kthread-out.c
+++ b/drivers/media/platform/vivid/vivid-kthread-out.c
@@ -248,8 +248,11 @@ int vivid_start_generating_vid_out(struct vivid_dev *dev, bool *pstreaming)
"%s-vid-out", dev->v4l2_dev.name);
if (IS_ERR(dev->kthread_vid_out)) {
+ int err = PTR_ERR(dev->kthread_vid_out);
+
+ dev->kthread_vid_out = NULL;
v4l2_err(&dev->v4l2_dev, "kernel_thread() failed\n");
- return PTR_ERR(dev->kthread_vid_out);
+ return err;
}
*pstreaming = true;
vivid_grab_controls(dev, true);
diff --git a/drivers/media/platform/vivid/vivid-vid-common.c b/drivers/media/platform/vivid/vivid-vid-common.c
index 1678b730dba2..2e82f520a869 100644
--- a/drivers/media/platform/vivid/vivid-vid-common.c
+++ b/drivers/media/platform/vivid/vivid-vid-common.c
@@ -33,7 +33,7 @@ const struct v4l2_dv_timings_cap vivid_dv_timings_cap = {
.type = V4L2_DV_BT_656_1120,
/* keep this initialization for compatibility with GCC < 4.4.6 */
.reserved = { 0 },
- V4L2_INIT_BT_TIMINGS(0, MAX_WIDTH, 0, MAX_HEIGHT, 14000000, 775000000,
+ V4L2_INIT_BT_TIMINGS(16, MAX_WIDTH, 16, MAX_HEIGHT, 14000000, 775000000,
V4L2_DV_BT_STD_CEA861 | V4L2_DV_BT_STD_DMT |
V4L2_DV_BT_STD_CVT | V4L2_DV_BT_STD_GTF,
V4L2_DV_BT_CAP_PROGRESSIVE | V4L2_DV_BT_CAP_INTERLACED)
diff --git a/drivers/media/usb/em28xx/em28xx-video.c b/drivers/media/usb/em28xx/em28xx-video.c
index 6cfcdcea27e0..873948e429e8 100644
--- a/drivers/media/usb/em28xx/em28xx-video.c
+++ b/drivers/media/usb/em28xx/em28xx-video.c
@@ -930,6 +930,8 @@ int em28xx_start_analog_streaming(struct vb2_queue *vq, unsigned int count)
em28xx_videodbg("%s\n", __func__);
+ dev->v4l2->field_count = 0;
+
/* Make sure streaming is not already in progress for this type
of filehandle (e.g. video, vbi) */
rc = res_get(dev, vq->type);
@@ -1149,8 +1151,6 @@ static void em28xx_ctrl_notify(struct v4l2_ctrl *ctrl, void *priv)
{
struct em28xx *dev = priv;
- dev->v4l2->field_count = 0;
-
/*
* In the case of non-AC97 volume controls, we still need
* to do some setups at em28xx, in order to mute/unmute
diff --git a/drivers/media/v4l2-core/videobuf2-core.c b/drivers/media/v4l2-core/videobuf2-core.c
index 8ce9c63dfc59..e0041fcfa783 100644
--- a/drivers/media/v4l2-core/videobuf2-core.c
+++ b/drivers/media/v4l2-core/videobuf2-core.c
@@ -1976,9 +1976,13 @@ int vb2_mmap(struct vb2_queue *q, struct vm_area_struct *vma)
return -EINVAL;
}
}
+
+ mutex_lock(&q->mmap_lock);
+
if (vb2_fileio_is_active(q)) {
dprintk(1, "mmap: file io in progress\n");
- return -EBUSY;
+ ret = -EBUSY;
+ goto unlock;
}
/*
@@ -1986,7 +1990,7 @@ int vb2_mmap(struct vb2_queue *q, struct vm_area_struct *vma)
*/
ret = __find_plane_by_offset(q, off, &buffer, &plane);
if (ret)
- return ret;
+ goto unlock;
vb = q->bufs[buffer];
@@ -1999,11 +2003,13 @@ int vb2_mmap(struct vb2_queue *q, struct vm_area_struct *vma)
if (length < (vma->vm_end - vma->vm_start)) {
dprintk(1,
"MMAP invalid, as it would overflow buffer length\n");
- return -EINVAL;
+ ret = -EINVAL;
+ goto unlock;
}
- mutex_lock(&q->mmap_lock);
ret = call_memop(vb, mmap, vb->planes[plane].mem_priv, vma);
+
+unlock:
mutex_unlock(&q->mmap_lock);
if (ret)
return ret;
diff --git a/drivers/mfd/tps6586x.c b/drivers/mfd/tps6586x.c
index 5628a6b5b19b..c5c320efc7b4 100644
--- a/drivers/mfd/tps6586x.c
+++ b/drivers/mfd/tps6586x.c
@@ -594,6 +594,29 @@ static int tps6586x_i2c_remove(struct i2c_client *client)
return 0;
}
+static int __maybe_unused tps6586x_i2c_suspend(struct device *dev)
+{
+ struct tps6586x *tps6586x = dev_get_drvdata(dev);
+
+ if (tps6586x->client->irq)
+ disable_irq(tps6586x->client->irq);
+
+ return 0;
+}
+
+static int __maybe_unused tps6586x_i2c_resume(struct device *dev)
+{
+ struct tps6586x *tps6586x = dev_get_drvdata(dev);
+
+ if (tps6586x->client->irq)
+ enable_irq(tps6586x->client->irq);
+
+ return 0;
+}
+
+static SIMPLE_DEV_PM_OPS(tps6586x_pm_ops, tps6586x_i2c_suspend,
+ tps6586x_i2c_resume);
+
static const struct i2c_device_id tps6586x_id_table[] = {
{ "tps6586x", 0 },
{ },
@@ -604,6 +627,7 @@ static struct i2c_driver tps6586x_driver = {
.driver = {
.name = "tps6586x",
.of_match_table = of_match_ptr(tps6586x_of_match),
+ .pm = &tps6586x_pm_ops,
},
.probe = tps6586x_i2c_probe,
.remove = tps6586x_i2c_remove,
diff --git a/drivers/mmc/host/atmel-mci.c b/drivers/mmc/host/atmel-mci.c
index bf62e429f7fc..98be9eb3184b 100644
--- a/drivers/mmc/host/atmel-mci.c
+++ b/drivers/mmc/host/atmel-mci.c
@@ -1840,13 +1840,14 @@ static void atmci_tasklet_func(unsigned long priv)
}
atmci_request_end(host, host->mrq);
- state = STATE_IDLE;
+ goto unlock; /* atmci_request_end() sets host->state */
break;
}
} while (state != prev_state);
host->state = state;
+unlock:
spin_unlock(&host->lock);
}
diff --git a/drivers/net/ethernet/intel/e1000e/ptp.c b/drivers/net/ethernet/intel/e1000e/ptp.c
index 25a0ad5102d6..855cf8c15c8a 100644
--- a/drivers/net/ethernet/intel/e1000e/ptp.c
+++ b/drivers/net/ethernet/intel/e1000e/ptp.c
@@ -111,10 +111,14 @@ static int e1000e_phc_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts)
struct e1000_adapter *adapter = container_of(ptp, struct e1000_adapter,
ptp_clock_info);
unsigned long flags;
- u64 ns;
+ u64 cycles, ns;
spin_lock_irqsave(&adapter->systim_lock, flags);
- ns = timecounter_read(&adapter->tc);
+
+ /* Use timecounter_cyc2time() to allow non-monotonic SYSTIM readings */
+ cycles = adapter->cc.read(&adapter->cc);
+ ns = timecounter_cyc2time(&adapter->tc, cycles);
+
spin_unlock_irqrestore(&adapter->systim_lock, flags);
*ts = ns_to_timespec64(ns);
@@ -170,9 +174,12 @@ static void e1000e_systim_overflow_work(struct work_struct *work)
systim_overflow_work.work);
struct e1000_hw *hw = &adapter->hw;
struct timespec64 ts;
+ u64 ns;
- adapter->ptp_clock_info.gettime64(&adapter->ptp_clock_info, &ts);
+ /* Update the timecounter */
+ ns = timecounter_read(&adapter->tc);
+ ts = ns_to_timespec64(ns);
e_dbg("SYSTIM overflow check at %lld.%09lu\n",
(long long) ts.tv_sec, ts.tv_nsec);
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 93543e176829..8f40e121f7d4 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -324,6 +324,8 @@ enum cfg_version {
};
static const struct pci_device_id rtl8169_pci_tbl[] = {
+ { PCI_VDEVICE(REALTEK, 0x2502), RTL_CFG_1 },
+ { PCI_VDEVICE(REALTEK, 0x2600), RTL_CFG_1 },
{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK, 0x8129), 0, 0, RTL_CFG_0 },
{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK, 0x8136), 0, 0, RTL_CFG_2 },
{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK, 0x8161), 0, 0, RTL_CFG_1 },
diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c
index f96f7b865267..7c1defaef3f5 100644
--- a/drivers/platform/x86/asus-wmi.c
+++ b/drivers/platform/x86/asus-wmi.c
@@ -2084,7 +2084,8 @@ static int asus_wmi_add(struct platform_device *pdev)
err = asus_wmi_backlight_init(asus);
if (err && err != -ENODEV)
goto fail_backlight;
- }
+ } else
+ err = asus_wmi_set_devstate(ASUS_WMI_DEVID_BACKLIGHT, 2, NULL);
status = wmi_install_notify_handler(asus->driver->event_guid,
asus_wmi_notify, asus);
diff --git a/drivers/scsi/megaraid/megaraid_sas_fp.c b/drivers/scsi/megaraid/megaraid_sas_fp.c
index 741509b35617..14f32c114c55 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fp.c
+++ b/drivers/scsi/megaraid/megaraid_sas_fp.c
@@ -1273,7 +1273,7 @@ void mr_update_load_balance_params(struct MR_DRV_RAID_MAP_ALL *drv_map,
for (ldCount = 0; ldCount < MAX_LOGICAL_DRIVES_EXT; ldCount++) {
ld = MR_TargetIdToLdGet(ldCount, drv_map);
- if (ld >= MAX_LOGICAL_DRIVES_EXT) {
+ if (ld >= MAX_LOGICAL_DRIVES_EXT - 1) {
lbInfo[ldCount].loadBalanceFlag = 0;
continue;
}
diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c
index 213944ed64d9..3d3bfa814093 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fusion.c
+++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c
@@ -1758,7 +1758,7 @@ static void megasas_build_ld_nonrw_fusion(struct megasas_instance *instance,
device_id < instance->fw_supported_vd_count)) {
ld = MR_TargetIdToLdGet(device_id, local_map_ptr);
- if (ld >= instance->fw_supported_vd_count)
+ if (ld >= instance->fw_supported_vd_count - 1)
fp_possible = 0;
raid = MR_LdRaidGet(ld, local_map_ptr);
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 6fffb73766de..ec80a0077ace 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -207,6 +207,12 @@ cache_type_store(struct device *dev, struct device_attribute *attr,
sp = buffer_data[0] & 0x80 ? 1 : 0;
buffer_data[0] &= ~0x80;
+ /*
+ * Ensure WP, DPOFUA, and RESERVED fields are cleared in
+ * received mode parameter buffer before doing MODE SELECT.
+ */
+ data.device_specific = 0;
+
if (scsi_mode_select(sdp, 1, sp, 8, buffer_data, len, SD_TIMEOUT,
SD_MAX_RETRIES, &data, &sshdr)) {
if (scsi_sense_valid(&sshdr))
diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c
index 9413e1a949e5..5af4d6a03d6e 100644
--- a/drivers/target/target_core_spc.c
+++ b/drivers/target/target_core_spc.c
@@ -108,12 +108,17 @@ spc_emulate_inquiry_std(struct se_cmd *cmd, unsigned char *buf)
buf[7] = 0x2; /* CmdQue=1 */
- memcpy(&buf[8], "LIO-ORG ", 8);
- memset(&buf[16], 0x20, 16);
+ /*
+ * ASCII data fields described as being left-aligned shall have any
+ * unused bytes at the end of the field (i.e., highest offset) and the
+ * unused bytes shall be filled with ASCII space characters (20h).
+ */
+ memset(&buf[8], 0x20, 8 + 16 + 4);
+ memcpy(&buf[8], "LIO-ORG", sizeof("LIO-ORG") - 1);
memcpy(&buf[16], dev->t10_wwn.model,
- min_t(size_t, strlen(dev->t10_wwn.model), 16));
+ strnlen(dev->t10_wwn.model, 16));
memcpy(&buf[32], dev->t10_wwn.revision,
- min_t(size_t, strlen(dev->t10_wwn.revision), 4));
+ strnlen(dev->t10_wwn.revision, 4));
buf[4] = 31; /* Set additional length to 31 */
return 0;
@@ -251,7 +256,9 @@ check_t10_vend_desc:
buf[off] = 0x2; /* ASCII */
buf[off+1] = 0x1; /* T10 Vendor ID */
buf[off+2] = 0x0;
- memcpy(&buf[off+4], "LIO-ORG", 8);
+ /* left align Vendor ID and pad with spaces */
+ memset(&buf[off+4], 0x20, 8);
+ memcpy(&buf[off+4], "LIO-ORG", sizeof("LIO-ORG") - 1);
/* Extra Byte for NULL Terminator */
id_len++;
/* Identifier Length */
diff --git a/drivers/tty/tty_ldsem.c b/drivers/tty/tty_ldsem.c
index ad7eba5ca380..34234c233851 100644
--- a/drivers/tty/tty_ldsem.c
+++ b/drivers/tty/tty_ldsem.c
@@ -307,6 +307,16 @@ down_write_failed(struct ld_semaphore *sem, long count, long timeout)
if (!locked)
ldsem_atomic_update(-LDSEM_WAIT_BIAS, sem);
list_del(&waiter.list);
+
+ /*
+ * In case of timeout, wake up every reader who gave the right of way
+ * to writer. Prevent separation readers into two groups:
+ * one that helds semaphore and another that sleeps.
+ * (in case of no contention with a writer)
+ */
+ if (!locked && list_empty(&sem->write_wait))
+ __ldsem_wake_readers(sem);
+
raw_spin_unlock_irq(&sem->wait_lock);
__set_task_state(tsk, TASK_RUNNING);
diff --git a/drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c b/drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c
index 34ab4f950f0a..0c1c34ff40a9 100644
--- a/drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c
+++ b/drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c
@@ -609,6 +609,8 @@ int omapfb_ioctl(struct fb_info *fbi, unsigned int cmd, unsigned long arg)
int r = 0;
+ memset(&p, 0, sizeof(p));
+
switch (cmd) {
case OMAPFB_SYNC_GFX:
DBG("ioctl SYNC_GFX\n");
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index f80a0af68736..78722aaffecd 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -4111,6 +4111,14 @@ static void btrfs_destroy_all_ordered_extents(struct btrfs_fs_info *fs_info)
spin_lock(&fs_info->ordered_root_lock);
}
spin_unlock(&fs_info->ordered_root_lock);
+
+ /*
+ * We need this here because if we've been flipped read-only we won't
+ * get sync() from the umount, so we need to make sure any ordered
+ * extents that haven't had their dirty pages IO start writeout yet
+ * actually get run and error out properly.
+ */
+ btrfs_wait_ordered_roots(fs_info, -1);
}
static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index f661d80474be..4b2f609f376d 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -58,6 +58,7 @@ static struct page *__get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index,
.rw = READ_SYNC | REQ_META | REQ_PRIO,
.blk_addr = index,
.encrypted_page = NULL,
+ .is_meta = is_meta,
};
if (unlikely(!is_meta))
@@ -74,8 +75,10 @@ repeat:
fio.page = page;
if (f2fs_submit_page_bio(&fio)) {
- f2fs_put_page(page, 1);
- goto repeat;
+ memset(page_address(page), 0, PAGE_SIZE);
+ f2fs_stop_checkpoint(sbi);
+ f2fs_bug_on(sbi, 1);
+ return page;
}
lock_page(page);
@@ -106,7 +109,8 @@ struct page *get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index)
return __get_meta_page(sbi, index, false);
}
-bool is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type)
+bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
+ block_t blkaddr, int type)
{
switch (type) {
case META_NAT:
@@ -126,8 +130,20 @@ bool is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type)
return false;
break;
case META_POR:
+ case DATA_GENERIC:
if (unlikely(blkaddr >= MAX_BLKADDR(sbi) ||
- blkaddr < MAIN_BLKADDR(sbi)))
+ blkaddr < MAIN_BLKADDR(sbi))) {
+ if (type == DATA_GENERIC) {
+ f2fs_msg(sbi->sb, KERN_WARNING,
+ "access invalid blkaddr:%u", blkaddr);
+ WARN_ON(1);
+ }
+ return false;
+ }
+ break;
+ case META_GENERIC:
+ if (unlikely(blkaddr < SEG0_BLKADDR(sbi) ||
+ blkaddr >= MAIN_BLKADDR(sbi)))
return false;
break;
default:
@@ -151,6 +167,7 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
.type = META,
.rw = sync ? (READ_SYNC | REQ_META | REQ_PRIO) : READA,
.encrypted_page = NULL,
+ .is_meta = (type != META_POR),
};
if (unlikely(type == META_POR))
@@ -158,7 +175,7 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
for (; nrpages-- > 0; blkno++) {
- if (!is_valid_blkaddr(sbi, blkno, type))
+ if (!f2fs_is_valid_blkaddr(sbi, blkno, type))
goto out;
switch (type) {
@@ -601,54 +618,73 @@ static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk)
}
}
-static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
- block_t cp_addr, unsigned long long *version)
+static int get_checkpoint_version(struct f2fs_sb_info *sbi, block_t cp_addr,
+ struct f2fs_checkpoint **cp_block, struct page **cp_page,
+ unsigned long long *version)
{
- struct page *cp_page_1, *cp_page_2 = NULL;
unsigned long blk_size = sbi->blocksize;
- struct f2fs_checkpoint *cp_block;
- unsigned long long cur_version = 0, pre_version = 0;
- size_t crc_offset;
+ size_t crc_offset = 0;
__u32 crc = 0;
- /* Read the 1st cp block in this CP pack */
- cp_page_1 = get_meta_page(sbi, cp_addr);
+ *cp_page = get_meta_page(sbi, cp_addr);
+ *cp_block = (struct f2fs_checkpoint *)page_address(*cp_page);
- /* get the version number */
- cp_block = (struct f2fs_checkpoint *)page_address(cp_page_1);
- crc_offset = le32_to_cpu(cp_block->checksum_offset);
- if (crc_offset >= blk_size)
- goto invalid_cp1;
-
- crc = le32_to_cpu(*((__le32 *)((unsigned char *)cp_block + crc_offset)));
- if (!f2fs_crc_valid(crc, cp_block, crc_offset))
- goto invalid_cp1;
+ crc_offset = le32_to_cpu((*cp_block)->checksum_offset);
+ if (crc_offset >= blk_size) {
+ f2fs_put_page(*cp_page, 1);
+ f2fs_msg(sbi->sb, KERN_WARNING,
+ "invalid crc_offset: %zu", crc_offset);
+ return -EINVAL;
+ }
- pre_version = cur_cp_version(cp_block);
+ crc = le32_to_cpu(*((__le32 *)((unsigned char *)*cp_block
+ + crc_offset)));
+ if (!f2fs_crc_valid(crc, *cp_block, crc_offset)) {
+ f2fs_put_page(*cp_page, 1);
+ f2fs_msg(sbi->sb, KERN_WARNING, "invalid crc value");
+ return -EINVAL;
+ }
- /* Read the 2nd cp block in this CP pack */
- cp_addr += le32_to_cpu(cp_block->cp_pack_total_block_count) - 1;
- cp_page_2 = get_meta_page(sbi, cp_addr);
+ *version = cur_cp_version(*cp_block);
+ return 0;
+}
- cp_block = (struct f2fs_checkpoint *)page_address(cp_page_2);
- crc_offset = le32_to_cpu(cp_block->checksum_offset);
- if (crc_offset >= blk_size)
- goto invalid_cp2;
+static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
+ block_t cp_addr, unsigned long long *version)
+{
+ struct page *cp_page_1 = NULL, *cp_page_2 = NULL;
+ struct f2fs_checkpoint *cp_block = NULL;
+ unsigned long long cur_version = 0, pre_version = 0;
+ int err;
- crc = le32_to_cpu(*((__le32 *)((unsigned char *)cp_block + crc_offset)));
- if (!f2fs_crc_valid(crc, cp_block, crc_offset))
- goto invalid_cp2;
+ err = get_checkpoint_version(sbi, cp_addr, &cp_block,
+ &cp_page_1, version);
+ if (err)
+ return NULL;
+
+ if (le32_to_cpu(cp_block->cp_pack_total_block_count) >
+ sbi->blocks_per_seg) {
+ f2fs_msg(sbi->sb, KERN_WARNING,
+ "invalid cp_pack_total_block_count:%u",
+ le32_to_cpu(cp_block->cp_pack_total_block_count));
+ goto invalid_cp;
+ }
+ pre_version = *version;
- cur_version = cur_cp_version(cp_block);
+ cp_addr += le32_to_cpu(cp_block->cp_pack_total_block_count) - 1;
+ err = get_checkpoint_version(sbi, cp_addr, &cp_block,
+ &cp_page_2, version);
+ if (err)
+ goto invalid_cp;
+ cur_version = *version;
if (cur_version == pre_version) {
*version = cur_version;
f2fs_put_page(cp_page_2, 1);
return cp_page_1;
}
-invalid_cp2:
f2fs_put_page(cp_page_2, 1);
-invalid_cp1:
+invalid_cp:
f2fs_put_page(cp_page_1, 1);
return NULL;
}
@@ -696,6 +732,15 @@ int get_valid_checkpoint(struct f2fs_sb_info *sbi)
cp_block = (struct f2fs_checkpoint *)page_address(cur_page);
memcpy(sbi->ckpt, cp_block, blk_size);
+ if (cur_page == cp1)
+ sbi->cur_cp_pack = 1;
+ else
+ sbi->cur_cp_pack = 2;
+
+ /* Sanity checking of checkpoint */
+ if (sanity_check_ckpt(sbi))
+ goto free_fail_no_cp;
+
if (cp_blks <= 1)
goto done;
@@ -717,6 +762,9 @@ done:
f2fs_put_page(cp2, 1);
return 0;
+free_fail_no_cp:
+ f2fs_put_page(cp1, 1);
+ f2fs_put_page(cp2, 1);
fail_no_cp:
kfree(sbi->ckpt);
return -EINVAL;
@@ -767,24 +815,6 @@ out:
f2fs_trace_pid(page);
}
-void add_dirty_dir_inode(struct inode *inode)
-{
- struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- struct inode_entry *new =
- f2fs_kmem_cache_alloc(inode_entry_slab, GFP_NOFS);
- int ret = 0;
-
- new->inode = inode;
- INIT_LIST_HEAD(&new->list);
-
- spin_lock(&sbi->dir_inode_lock);
- ret = __add_dirty_inode(inode, new);
- spin_unlock(&sbi->dir_inode_lock);
-
- if (ret)
- kmem_cache_free(inode_entry_slab, new);
-}
-
void remove_dirty_dir_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
@@ -807,12 +837,6 @@ void remove_dirty_dir_inode(struct inode *inode)
stat_dec_dirty_dir(sbi);
spin_unlock(&sbi->dir_inode_lock);
kmem_cache_free(inode_entry_slab, entry);
-
- /* Only from the recovery routine */
- if (is_inode_flag_set(F2FS_I(inode), FI_DELAY_IPUT)) {
- clear_inode_flag(F2FS_I(inode), FI_DELAY_IPUT);
- iput(inode);
- }
}
void sync_dirty_dir_inodes(struct f2fs_sb_info *sbi)
@@ -922,7 +946,6 @@ static void wait_on_all_pages_writeback(struct f2fs_sb_info *sbi)
static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
{
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
- struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
struct f2fs_nm_info *nm_i = NM_I(sbi);
unsigned long orphan_num = sbi->im[ORPHAN_INO].ino_num;
nid_t last_nid = nm_i->next_scan_nid;
@@ -931,15 +954,6 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
__u32 crc32 = 0;
int i;
int cp_payload_blks = __cp_payload(sbi);
- block_t discard_blk = NEXT_FREE_BLKADDR(sbi, curseg);
- bool invalidate = false;
-
- /*
- * This avoids to conduct wrong roll-forward operations and uses
- * metapages, so should be called prior to sync_meta_pages below.
- */
- if (discard_next_dnode(sbi, discard_blk))
- invalidate = true;
/* Flush all the NAT/SIT pages */
while (get_pages(sbi, F2FS_DIRTY_META)) {
@@ -1016,6 +1030,9 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
if (is_sbi_flag_set(sbi, SBI_NEED_FSCK))
set_ckpt_flags(ckpt, CP_FSCK_FLAG);
+ /* set this flag to activate crc|cp_ver for recovery */
+ set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG);
+
/* update SIT/NAT bitmap */
get_sit_bitmap(sbi, __bitmap_ptr(sbi, SIT_BITMAP));
get_nat_bitmap(sbi, __bitmap_ptr(sbi, NAT_BITMAP));
@@ -1025,7 +1042,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
le32_to_cpu(ckpt->checksum_offset)))
= cpu_to_le32(crc32);
- start_blk = __start_cp_addr(sbi);
+ start_blk = __start_cp_next_addr(sbi);
/* need to wait for end_io results */
wait_on_all_pages_writeback(sbi);
@@ -1073,14 +1090,6 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
/* wait for previous submitted meta pages writeback */
wait_on_all_pages_writeback(sbi);
- /*
- * invalidate meta page which is used temporarily for zeroing out
- * block at the end of warm node chain.
- */
- if (invalidate)
- invalidate_mapping_pages(META_MAPPING(sbi), discard_blk,
- discard_blk);
-
release_dirty_inode(sbi);
if (unlikely(f2fs_cp_error(sbi)))
@@ -1088,6 +1097,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
clear_prefree_segments(sbi, cpc);
clear_sbi_flag(sbi, SBI_IS_DIRTY);
+ __set_cp_next_pack(sbi);
}
/*
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index f6ccb21f286b..2b0b671484bd 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -147,6 +147,10 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio)
struct bio *bio;
struct page *page = fio->encrypted_page ? fio->encrypted_page : fio->page;
+ if (!f2fs_is_valid_blkaddr(fio->sbi, fio->blk_addr,
+ __is_meta_io(fio) ? META_GENERIC : DATA_GENERIC))
+ return -EFAULT;
+
trace_f2fs_submit_page_bio(page, fio);
f2fs_trace_ios(fio, 0);
@@ -172,7 +176,7 @@ void f2fs_submit_page_mbio(struct f2fs_io_info *fio)
io = is_read ? &sbi->read_io : &sbi->write_io[btype];
- verify_block_addr(sbi, fio->blk_addr);
+ verify_block_addr(fio, fio->blk_addr);
down_write(&io->io_rwsem);
@@ -603,7 +607,13 @@ static int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
goto unlock_out;
}
- if (dn.data_blkaddr == NEW_ADDR || dn.data_blkaddr == NULL_ADDR) {
+ if (__is_valid_data_blkaddr(dn.data_blkaddr) &&
+ !f2fs_is_valid_blkaddr(sbi, dn.data_blkaddr, DATA_GENERIC)) {
+ err = -EFAULT;
+ goto sync_out;
+ }
+
+ if (!is_valid_data_blkaddr(sbi, dn.data_blkaddr)) {
if (create) {
if (unlikely(f2fs_cp_error(sbi))) {
err = -EIO;
@@ -866,6 +876,40 @@ out:
return ret;
}
+struct bio *f2fs_grab_bio(struct inode *inode, block_t blkaddr,
+ unsigned nr_pages)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct f2fs_crypto_ctx *ctx = NULL;
+ struct block_device *bdev = sbi->sb->s_bdev;
+ struct bio *bio;
+
+ if (!f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC))
+ return ERR_PTR(-EFAULT);
+
+ if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) {
+ ctx = f2fs_get_crypto_ctx(inode);
+ if (IS_ERR(ctx))
+ return ERR_CAST(ctx);
+
+ /* wait the page to be moved by cleaning */
+ f2fs_wait_on_encrypted_page_writeback(sbi, blkaddr);
+ }
+
+ bio = bio_alloc(GFP_KERNEL, min_t(int, nr_pages, BIO_MAX_PAGES));
+ if (!bio) {
+ if (ctx)
+ f2fs_release_crypto_ctx(ctx);
+ return ERR_PTR(-ENOMEM);
+ }
+ bio->bi_bdev = bdev;
+ bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(blkaddr);
+ bio->bi_end_io = f2fs_read_end_io;
+ bio->bi_private = ctx;
+
+ return bio;
+}
+
/*
* This function was originally taken from fs/mpage.c, and customized for f2fs.
* Major change was from block_size == page_size in f2fs by default.
@@ -884,7 +928,6 @@ static int f2fs_mpage_readpages(struct address_space *mapping,
sector_t last_block;
sector_t last_block_in_file;
sector_t block_nr;
- struct block_device *bdev = inode->i_sb->s_bdev;
struct f2fs_map_blocks map;
map.m_pblk = 0;
@@ -941,6 +984,10 @@ got_it:
SetPageUptodate(page);
goto confused;
}
+
+ if (!f2fs_is_valid_blkaddr(F2FS_I_SB(inode), block_nr,
+ DATA_GENERIC))
+ goto set_error_page;
} else {
zero_user_segment(page, 0, PAGE_CACHE_SIZE);
SetPageUptodate(page);
@@ -958,31 +1005,9 @@ submit_and_realloc:
bio = NULL;
}
if (bio == NULL) {
- struct f2fs_crypto_ctx *ctx = NULL;
-
- if (f2fs_encrypted_inode(inode) &&
- S_ISREG(inode->i_mode)) {
-
- ctx = f2fs_get_crypto_ctx(inode);
- if (IS_ERR(ctx))
- goto set_error_page;
-
- /* wait the page to be moved by cleaning */
- f2fs_wait_on_encrypted_page_writeback(
- F2FS_I_SB(inode), block_nr);
- }
-
- bio = bio_alloc(GFP_KERNEL,
- min_t(int, nr_pages, BIO_MAX_PAGES));
- if (!bio) {
- if (ctx)
- f2fs_release_crypto_ctx(ctx);
+ bio = f2fs_grab_bio(inode, block_nr, nr_pages);
+ if (IS_ERR(bio))
goto set_error_page;
- }
- bio->bi_bdev = bdev;
- bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(block_nr);
- bio->bi_end_io = f2fs_read_end_io;
- bio->bi_private = ctx;
}
if (bio_add_page(bio, page, blocksize, 0) < blocksize)
@@ -1077,11 +1102,17 @@ int do_write_data_page(struct f2fs_io_info *fio)
set_page_writeback(page);
+ if (__is_valid_data_blkaddr(fio->blk_addr) &&
+ !f2fs_is_valid_blkaddr(fio->sbi, fio->blk_addr,
+ DATA_GENERIC)) {
+ err = -EFAULT;
+ goto out_writepage;
+ }
/*
* If current allocation needs SSR,
* it had better in-place writes for updated data.
*/
- if (unlikely(fio->blk_addr != NEW_ADDR &&
+ if (unlikely(is_valid_data_blkaddr(fio->sbi, fio->blk_addr) &&
!is_cold_data(page) &&
need_inplace_update(inode))) {
rewrite_data_page(fio);
@@ -1482,17 +1513,21 @@ put_next:
if (dn.data_blkaddr == NEW_ADDR) {
zero_user_segment(page, 0, PAGE_CACHE_SIZE);
} else {
- struct f2fs_io_info fio = {
- .sbi = sbi,
- .type = DATA,
- .rw = READ_SYNC,
- .blk_addr = dn.data_blkaddr,
- .page = page,
- .encrypted_page = NULL,
- };
- err = f2fs_submit_page_bio(&fio);
- if (err)
+ struct bio *bio;
+
+ bio = f2fs_grab_bio(inode, dn.data_blkaddr, 1);
+ if (IS_ERR(bio)) {
+ err = PTR_ERR(bio);
goto fail;
+ }
+
+ if (bio_add_page(bio, page, PAGE_CACHE_SIZE, 0) < PAGE_CACHE_SIZE) {
+ bio_put(bio);
+ err = -EFAULT;
+ goto fail;
+ }
+
+ submit_bio(READ_SYNC, bio);
lock_page(page);
if (unlikely(!PageUptodate(page))) {
@@ -1503,13 +1538,6 @@ put_next:
f2fs_put_page(page, 1);
goto repeat;
}
-
- /* avoid symlink page */
- if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) {
- err = f2fs_decrypt_one(inode, page);
- if (err)
- goto fail;
- }
}
out_update:
SetPageUptodate(page);
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 60972a559685..92a240616f52 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -48,7 +48,6 @@ unsigned char f2fs_filetype_table[F2FS_FT_MAX] = {
[F2FS_FT_SYMLINK] = DT_LNK,
};
-#define S_SHIFT 12
static unsigned char f2fs_type_by_mode[S_IFMT >> S_SHIFT] = {
[S_IFREG >> S_SHIFT] = F2FS_FT_REG_FILE,
[S_IFDIR >> S_SHIFT] = F2FS_FT_DIR,
@@ -64,6 +63,13 @@ void set_de_type(struct f2fs_dir_entry *de, umode_t mode)
de->file_type = f2fs_type_by_mode[(mode & S_IFMT) >> S_SHIFT];
}
+unsigned char get_de_type(struct f2fs_dir_entry *de)
+{
+ if (de->file_type < F2FS_FT_MAX)
+ return f2fs_filetype_table[de->file_type];
+ return DT_UNKNOWN;
+}
+
static unsigned long dir_block_index(unsigned int level,
int dir_level, unsigned int idx)
{
@@ -519,11 +525,7 @@ void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *d,
test_and_set_bit_le(bit_pos + i, (void *)d->bitmap);
}
-/*
- * Caller should grab and release a rwsem by calling f2fs_lock_op() and
- * f2fs_unlock_op().
- */
-int __f2fs_add_link(struct inode *dir, const struct qstr *name,
+int f2fs_add_regular_entry(struct inode *dir, const struct qstr *new_name,
struct inode *inode, nid_t ino, umode_t mode)
{
unsigned int bit_pos;
@@ -536,28 +538,11 @@ int __f2fs_add_link(struct inode *dir, const struct qstr *name,
struct f2fs_dentry_block *dentry_blk = NULL;
struct f2fs_dentry_ptr d;
struct page *page = NULL;
- struct f2fs_filename fname;
- struct qstr new_name;
- int slots, err;
-
- err = f2fs_fname_setup_filename(dir, name, 0, &fname);
- if (err)
- return err;
-
- new_name.name = fname_name(&fname);
- new_name.len = fname_len(&fname);
-
- if (f2fs_has_inline_dentry(dir)) {
- err = f2fs_add_inline_entry(dir, &new_name, inode, ino, mode);
- if (!err || err != -EAGAIN)
- goto out;
- else
- err = 0;
- }
+ int slots, err = 0;
level = 0;
- slots = GET_DENTRY_SLOTS(new_name.len);
- dentry_hash = f2fs_dentry_hash(&new_name, NULL);
+ slots = GET_DENTRY_SLOTS(new_name->len);
+ dentry_hash = f2fs_dentry_hash(new_name, NULL);
current_depth = F2FS_I(dir)->i_current_depth;
if (F2FS_I(dir)->chash == dentry_hash) {
@@ -566,10 +551,8 @@ int __f2fs_add_link(struct inode *dir, const struct qstr *name,
}
start:
- if (unlikely(current_depth == MAX_DIR_HASH_DEPTH)) {
- err = -ENOSPC;
- goto out;
- }
+ if (unlikely(current_depth == MAX_DIR_HASH_DEPTH))
+ return -ENOSPC;
/* Increase the depth, if required */
if (level == current_depth)
@@ -583,10 +566,8 @@ start:
for (block = bidx; block <= (bidx + nblock - 1); block++) {
dentry_page = get_new_data_page(dir, NULL, block, true);
- if (IS_ERR(dentry_page)) {
- err = PTR_ERR(dentry_page);
- goto out;
- }
+ if (IS_ERR(dentry_page))
+ return PTR_ERR(dentry_page);
dentry_blk = kmap(dentry_page);
bit_pos = room_for_filename(&dentry_blk->dentry_bitmap,
@@ -606,7 +587,7 @@ add_dentry:
if (inode) {
down_write(&F2FS_I(inode)->i_sem);
- page = init_inode_metadata(inode, dir, &new_name, NULL);
+ page = init_inode_metadata(inode, dir, new_name, NULL);
if (IS_ERR(page)) {
err = PTR_ERR(page);
goto fail;
@@ -616,7 +597,7 @@ add_dentry:
}
make_dentry_ptr(NULL, &d, (void *)dentry_blk, 1);
- f2fs_update_dentry(ino, mode, &d, &new_name, dentry_hash, bit_pos);
+ f2fs_update_dentry(ino, mode, &d, new_name, dentry_hash, bit_pos);
set_page_dirty(dentry_page);
@@ -638,7 +619,34 @@ fail:
}
kunmap(dentry_page);
f2fs_put_page(dentry_page, 1);
-out:
+
+ return err;
+}
+
+/*
+ * Caller should grab and release a rwsem by calling f2fs_lock_op() and
+ * f2fs_unlock_op().
+ */
+int __f2fs_add_link(struct inode *dir, const struct qstr *name,
+ struct inode *inode, nid_t ino, umode_t mode)
+{
+ struct f2fs_filename fname;
+ struct qstr new_name;
+ int err;
+
+ err = f2fs_fname_setup_filename(dir, name, 0, &fname);
+ if (err)
+ return err;
+
+ new_name.name = fname_name(&fname);
+ new_name.len = fname_len(&fname);
+
+ err = -EAGAIN;
+ if (f2fs_has_inline_dentry(dir))
+ err = f2fs_add_inline_entry(dir, &new_name, inode, ino, mode);
+ if (err == -EAGAIN)
+ err = f2fs_add_regular_entry(dir, &new_name, inode, ino, mode);
+
f2fs_fname_free_filename(&fname);
return err;
}
@@ -792,10 +800,7 @@ bool f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
break;
de = &d->dentry[bit_pos];
- if (de->file_type < F2FS_FT_MAX)
- d_type = f2fs_filetype_table[de->file_type];
- else
- d_type = DT_UNKNOWN;
+ d_type = get_de_type(de);
de_name.name = d->filename[bit_pos];
de_name.len = le16_to_cpu(de->name_len);
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 2871576fbca4..2bfce887dce2 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -135,7 +135,7 @@ struct cp_control {
};
/*
- * For CP/NAT/SIT/SSA readahead
+ * indicate meta/data type
*/
enum {
META_CP,
@@ -143,6 +143,8 @@ enum {
META_SIT,
META_SSA,
META_POR,
+ DATA_GENERIC,
+ META_GENERIC,
};
/* for the list of ino */
@@ -684,6 +686,7 @@ struct f2fs_io_info {
block_t blk_addr; /* block address to be written */
struct page *page; /* page to be written */
struct page *encrypted_page; /* encrypted page */
+ bool is_meta; /* indicate borrow meta inode mapping or not */
};
#define is_read_io(rw) (((rw) & 1) == READ)
@@ -731,6 +734,7 @@ struct f2fs_sb_info {
/* for checkpoint */
struct f2fs_checkpoint *ckpt; /* raw checkpoint pointer */
+ int cur_cp_pack; /* remain current cp pack */
struct inode *meta_inode; /* cache meta blocks */
struct mutex cp_mutex; /* checkpoint procedure lock */
struct rw_semaphore cp_rwsem; /* blocking FS operations */
@@ -1140,22 +1144,27 @@ static inline void *__bitmap_ptr(struct f2fs_sb_info *sbi, int flag)
static inline block_t __start_cp_addr(struct f2fs_sb_info *sbi)
{
- block_t start_addr;
- struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
- unsigned long long ckpt_version = cur_cp_version(ckpt);
-
- start_addr = le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_blkaddr);
+ block_t start_addr = le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_blkaddr);
- /*
- * odd numbered checkpoint should at cp segment 0
- * and even segment must be at cp segment 1
- */
- if (!(ckpt_version & 1))
+ if (sbi->cur_cp_pack == 2)
start_addr += sbi->blocks_per_seg;
+ return start_addr;
+}
+
+static inline block_t __start_cp_next_addr(struct f2fs_sb_info *sbi)
+{
+ block_t start_addr = le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_blkaddr);
+ if (sbi->cur_cp_pack == 1)
+ start_addr += sbi->blocks_per_seg;
return start_addr;
}
+static inline void __set_cp_next_pack(struct f2fs_sb_info *sbi)
+{
+ sbi->cur_cp_pack = (sbi->cur_cp_pack == 1) ? 2 : 1;
+}
+
static inline block_t __start_sum_addr(struct f2fs_sb_info *sbi)
{
return le32_to_cpu(F2FS_CKPT(sbi)->cp_pack_start_sum);
@@ -1402,7 +1411,6 @@ enum {
FI_NO_ALLOC, /* should not allocate any blocks */
FI_FREE_NID, /* free allocated nide */
FI_UPDATE_DIR, /* should update inode block for consistency */
- FI_DELAY_IPUT, /* used for the recovery */
FI_NO_EXTENT, /* not to use the extent cache */
FI_INLINE_XATTR, /* used for inline xattr */
FI_INLINE_DATA, /* used for inline data*/
@@ -1641,6 +1649,39 @@ static inline void *f2fs_kvzalloc(size_t size, gfp_t flags)
(pgofs - ADDRS_PER_INODE(fi) + ADDRS_PER_BLOCK) / \
ADDRS_PER_BLOCK * ADDRS_PER_BLOCK + ADDRS_PER_INODE(fi))
+#define __is_meta_io(fio) (PAGE_TYPE_OF_BIO(fio->type) == META && \
+ (!is_read_io(fio->rw) || fio->is_meta))
+
+bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
+ block_t blkaddr, int type);
+void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...);
+static inline void verify_blkaddr(struct f2fs_sb_info *sbi,
+ block_t blkaddr, int type)
+{
+ if (!f2fs_is_valid_blkaddr(sbi, blkaddr, type)) {
+ f2fs_msg(sbi->sb, KERN_ERR,
+ "invalid blkaddr: %u, type: %d, run fsck to fix.",
+ blkaddr, type);
+ f2fs_bug_on(sbi, 1);
+ }
+}
+
+static inline bool __is_valid_data_blkaddr(block_t blkaddr)
+{
+ if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR)
+ return false;
+ return true;
+}
+
+static inline bool is_valid_data_blkaddr(struct f2fs_sb_info *sbi,
+ block_t blkaddr)
+{
+ if (!__is_valid_data_blkaddr(blkaddr))
+ return false;
+ verify_blkaddr(sbi, blkaddr, DATA_GENERIC);
+ return true;
+}
+
/*
* file.c
*/
@@ -1677,7 +1718,7 @@ struct dentry *f2fs_get_parent(struct dentry *child);
*/
extern unsigned char f2fs_filetype_table[F2FS_FT_MAX];
void set_de_type(struct f2fs_dir_entry *, umode_t);
-
+unsigned char get_de_type(struct f2fs_dir_entry *);
struct f2fs_dir_entry *find_target_dentry(struct f2fs_filename *,
f2fs_hash_t, int *, struct f2fs_dentry_ptr *);
bool f2fs_fill_dentries(struct dir_context *, struct f2fs_dentry_ptr *,
@@ -1698,6 +1739,8 @@ void f2fs_set_link(struct inode *, struct f2fs_dir_entry *,
int update_dent_inode(struct inode *, struct inode *, const struct qstr *);
void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *,
const struct qstr *, f2fs_hash_t , unsigned int);
+int f2fs_add_regular_entry(struct inode *, const struct qstr *,
+ struct inode *, nid_t, umode_t);
int __f2fs_add_link(struct inode *, const struct qstr *, struct inode *, nid_t,
umode_t);
void f2fs_delete_entry(struct f2fs_dir_entry *, struct page *, struct inode *,
@@ -1718,6 +1761,7 @@ int f2fs_commit_super(struct f2fs_sb_info *, bool);
int f2fs_sync_fs(struct super_block *, int);
extern __printf(3, 4)
void f2fs_msg(struct super_block *, const char *, const char *, ...);
+int sanity_check_ckpt(struct f2fs_sb_info *sbi);
/*
* hash.c
@@ -1778,7 +1822,6 @@ bool is_checkpointed_data(struct f2fs_sb_info *, block_t);
void refresh_sit_entry(struct f2fs_sb_info *, block_t, block_t);
void clear_prefree_segments(struct f2fs_sb_info *, struct cp_control *);
void release_discard_addrs(struct f2fs_sb_info *);
-bool discard_next_dnode(struct f2fs_sb_info *, block_t);
int npages_for_summary_flush(struct f2fs_sb_info *, bool);
void allocate_new_segments(struct f2fs_sb_info *);
int f2fs_trim_fs(struct f2fs_sb_info *, struct fstrim_range *);
@@ -1810,7 +1853,8 @@ void destroy_segment_manager_caches(void);
struct page *grab_meta_page(struct f2fs_sb_info *, pgoff_t);
struct page *get_meta_page(struct f2fs_sb_info *, pgoff_t);
struct page *get_tmp_page(struct f2fs_sb_info *, pgoff_t);
-bool is_valid_blkaddr(struct f2fs_sb_info *, block_t, int);
+bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
+ block_t blkaddr, int type);
int ra_meta_pages(struct f2fs_sb_info *, block_t, int, int, bool);
void ra_meta_pages_cond(struct f2fs_sb_info *, pgoff_t);
long sync_meta_pages(struct f2fs_sb_info *, enum page_type, long);
@@ -1825,7 +1869,6 @@ void remove_orphan_inode(struct f2fs_sb_info *, nid_t);
int recover_orphan_inodes(struct f2fs_sb_info *);
int get_valid_checkpoint(struct f2fs_sb_info *);
void update_dirty_page(struct inode *, struct page *);
-void add_dirty_dir_inode(struct inode *);
void remove_dirty_dir_inode(struct inode *);
void sync_dirty_dir_inodes(struct f2fs_sb_info *);
void write_checkpoint(struct f2fs_sb_info *, struct cp_control *);
@@ -1864,7 +1907,7 @@ void build_gc_manager(struct f2fs_sb_info *);
/*
* recovery.c
*/
-int recover_fsync_data(struct f2fs_sb_info *);
+int recover_fsync_data(struct f2fs_sb_info *, bool);
bool space_for_roll_forward(struct f2fs_sb_info *);
/*
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 01eed94b01ea..96bfd9f0ea02 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -305,13 +305,13 @@ static pgoff_t __get_first_dirty_index(struct address_space *mapping,
return pgofs;
}
-static bool __found_offset(block_t blkaddr, pgoff_t dirty, pgoff_t pgofs,
- int whence)
+static bool __found_offset(struct f2fs_sb_info *sbi, block_t blkaddr,
+ pgoff_t dirty, pgoff_t pgofs, int whence)
{
switch (whence) {
case SEEK_DATA:
if ((blkaddr == NEW_ADDR && dirty == pgofs) ||
- (blkaddr != NEW_ADDR && blkaddr != NULL_ADDR))
+ is_valid_data_blkaddr(sbi, blkaddr))
return true;
break;
case SEEK_HOLE:
@@ -374,7 +374,15 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence)
block_t blkaddr;
blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
- if (__found_offset(blkaddr, dirty, pgofs, whence)) {
+ if (__is_valid_data_blkaddr(blkaddr) &&
+ !f2fs_is_valid_blkaddr(F2FS_I_SB(inode),
+ blkaddr, DATA_GENERIC)) {
+ f2fs_put_dnode(&dn);
+ goto fail;
+ }
+
+ if (__found_offset(F2FS_I_SB(inode), blkaddr, dirty,
+ pgofs, whence)) {
f2fs_put_dnode(&dn);
goto found;
}
@@ -466,6 +474,11 @@ int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
dn->data_blkaddr = NULL_ADDR;
set_data_blkaddr(dn);
+
+ if (__is_valid_data_blkaddr(blkaddr) &&
+ !f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC))
+ continue;
+
invalidate_blocks(sbi, blkaddr);
if (dn->ofs_in_node == 0 && IS_INODE(dn->node_page))
clear_inode_flag(F2FS_I(dn->inode),
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index ad80f916b64d..00685a8b1418 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -127,6 +127,16 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
if (err)
return err;
+ if (unlikely(dn->data_blkaddr != NEW_ADDR)) {
+ f2fs_put_dnode(dn);
+ set_sbi_flag(fio.sbi, SBI_NEED_FSCK);
+ f2fs_msg(fio.sbi->sb, KERN_WARNING,
+ "%s: corrupted inline inode ino=%lx, i_addr[0]:0x%x, "
+ "run fsck to fix.",
+ __func__, dn->inode->i_ino, dn->data_blkaddr);
+ return -EINVAL;
+ }
+
f2fs_wait_on_page_writeback(page, DATA);
if (PageUptodate(page))
@@ -367,7 +377,7 @@ int make_empty_inline_dir(struct inode *inode, struct inode *parent,
* NOTE: ipage is grabbed by caller, but if any error occurs, we should
* release ipage in this function.
*/
-static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage,
+static int f2fs_move_inline_dirents(struct inode *dir, struct page *ipage,
struct f2fs_inline_dentry *inline_dentry)
{
struct page *page;
@@ -386,6 +396,17 @@ static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage,
if (err)
goto out;
+ if (unlikely(dn.data_blkaddr != NEW_ADDR)) {
+ f2fs_put_dnode(&dn);
+ set_sbi_flag(F2FS_P_SB(page), SBI_NEED_FSCK);
+ f2fs_msg(F2FS_P_SB(page)->sb, KERN_WARNING,
+ "%s: corrupted inline inode ino=%lx, i_addr[0]:0x%x, "
+ "run fsck to fix.",
+ __func__, dir->i_ino, dn.data_blkaddr);
+ err = -EINVAL;
+ goto out;
+ }
+
f2fs_wait_on_page_writeback(page, DATA);
zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_SIZE);
@@ -428,6 +449,98 @@ out:
return err;
}
+static int f2fs_add_inline_entries(struct inode *dir,
+ struct f2fs_inline_dentry *inline_dentry)
+{
+ struct f2fs_dentry_ptr d;
+ unsigned long bit_pos = 0;
+ int err = 0;
+
+ make_dentry_ptr(NULL, &d, (void *)inline_dentry, 2);
+
+ while (bit_pos < d.max) {
+ struct f2fs_dir_entry *de;
+ struct qstr new_name;
+ nid_t ino;
+ umode_t fake_mode;
+
+ if (!test_bit_le(bit_pos, d.bitmap)) {
+ bit_pos++;
+ continue;
+ }
+
+ de = &d.dentry[bit_pos];
+ new_name.name = d.filename[bit_pos];
+ new_name.len = de->name_len;
+
+ ino = le32_to_cpu(de->ino);
+ fake_mode = get_de_type(de) << S_SHIFT;
+
+ err = f2fs_add_regular_entry(dir, &new_name, NULL,
+ ino, fake_mode);
+ if (err)
+ goto punch_dentry_pages;
+
+ if (unlikely(!de->name_len))
+ d.max = -1;
+
+ bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len));
+ }
+ return 0;
+punch_dentry_pages:
+ truncate_inode_pages(&dir->i_data, 0);
+ truncate_blocks(dir, 0, false);
+ remove_dirty_dir_inode(dir);
+ return err;
+}
+
+static int f2fs_move_rehashed_dirents(struct inode *dir, struct page *ipage,
+ struct f2fs_inline_dentry *inline_dentry)
+{
+ struct f2fs_inline_dentry *backup_dentry;
+ int err;
+
+ backup_dentry = kmalloc(sizeof(struct f2fs_inline_dentry),
+ GFP_F2FS_ZERO);
+ if (!backup_dentry)
+ return -ENOMEM;
+
+ memcpy(backup_dentry, inline_dentry, MAX_INLINE_DATA);
+ truncate_inline_inode(ipage, 0);
+
+ unlock_page(ipage);
+
+ err = f2fs_add_inline_entries(dir, backup_dentry);
+ if (err)
+ goto recover;
+
+ lock_page(ipage);
+
+ stat_dec_inline_dir(dir);
+ clear_inode_flag(F2FS_I(dir), FI_INLINE_DENTRY);
+ update_inode(dir, ipage);
+ kfree(backup_dentry);
+ return 0;
+recover:
+ lock_page(ipage);
+ memcpy(inline_dentry, backup_dentry, MAX_INLINE_DATA);
+ i_size_write(dir, MAX_INLINE_DATA);
+ update_inode(dir, ipage);
+ f2fs_put_page(ipage, 1);
+
+ kfree(backup_dentry);
+ return err;
+}
+
+static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage,
+ struct f2fs_inline_dentry *inline_dentry)
+{
+ if (!F2FS_I(dir)->i_dir_level)
+ return f2fs_move_inline_dirents(dir, ipage, inline_dentry);
+ else
+ return f2fs_move_rehashed_dirents(dir, ipage, inline_dentry);
+}
+
int f2fs_add_inline_entry(struct inode *dir, const struct qstr *name,
struct inode *inode, nid_t ino, umode_t mode)
{
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index 5528801a5baf..89bf8dd7758c 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -50,13 +50,16 @@ static void __get_inode_rdev(struct inode *inode, struct f2fs_inode *ri)
}
}
-static bool __written_first_block(struct f2fs_inode *ri)
+static int __written_first_block(struct f2fs_sb_info *sbi,
+ struct f2fs_inode *ri)
{
block_t addr = le32_to_cpu(ri->i_addr[0]);
- if (addr != NEW_ADDR && addr != NULL_ADDR)
- return true;
- return false;
+ if (!__is_valid_data_blkaddr(addr))
+ return 1;
+ if (!f2fs_is_valid_blkaddr(sbi, addr, DATA_GENERIC))
+ return -EFAULT;
+ return 0;
}
static void __set_inode_rdev(struct inode *inode, struct f2fs_inode *ri)
@@ -94,12 +97,57 @@ static void __recover_inline_status(struct inode *inode, struct page *ipage)
return;
}
+static bool sanity_check_inode(struct inode *inode, struct page *node_page)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ unsigned long long iblocks;
+
+ iblocks = le64_to_cpu(F2FS_INODE(node_page)->i_blocks);
+ if (!iblocks) {
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ f2fs_msg(sbi->sb, KERN_WARNING,
+ "%s: corrupted inode i_blocks i_ino=%lx iblocks=%llu, "
+ "run fsck to fix.",
+ __func__, inode->i_ino, iblocks);
+ return false;
+ }
+
+ if (ino_of_node(node_page) != nid_of_node(node_page)) {
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ f2fs_msg(sbi->sb, KERN_WARNING,
+ "%s: corrupted inode footer i_ino=%lx, ino,nid: "
+ "[%u, %u] run fsck to fix.",
+ __func__, inode->i_ino,
+ ino_of_node(node_page), nid_of_node(node_page));
+ return false;
+ }
+
+ if (F2FS_I(inode)->extent_tree) {
+ struct extent_info *ei = &F2FS_I(inode)->extent_tree->largest;
+
+ if (ei->len &&
+ (!f2fs_is_valid_blkaddr(sbi, ei->blk, DATA_GENERIC) ||
+ !f2fs_is_valid_blkaddr(sbi, ei->blk + ei->len - 1,
+ DATA_GENERIC))) {
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ f2fs_msg(sbi->sb, KERN_WARNING,
+ "%s: inode (ino=%lx) extent info [%u, %u, %u] "
+ "is incorrect, run fsck to fix",
+ __func__, inode->i_ino,
+ ei->blk, ei->fofs, ei->len);
+ return false;
+ }
+ }
+ return true;
+}
+
static int do_read_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_inode_info *fi = F2FS_I(inode);
struct page *node_page;
struct f2fs_inode *ri;
+ int err;
/* Check if ino is within scope */
if (check_nid_range(sbi, inode->i_ino)) {
@@ -142,6 +190,11 @@ static int do_read_inode(struct inode *inode)
get_inline_info(fi, ri);
+ if (!sanity_check_inode(inode, node_page)) {
+ f2fs_put_page(node_page, 1);
+ return -EINVAL;
+ }
+
/* check data exist */
if (f2fs_has_inline_data(inode) && !f2fs_exist_data(inode))
__recover_inline_status(inode, node_page);
@@ -149,7 +202,12 @@ static int do_read_inode(struct inode *inode)
/* get rdev by using inline_info */
__get_inode_rdev(inode, ri);
- if (__written_first_block(ri))
+ err = __written_first_block(sbi, ri);
+ if (err < 0) {
+ f2fs_put_page(node_page, 1);
+ return err;
+ }
+ if (!err)
set_inode_flag(F2FS_I(inode), FI_FIRST_BLOCK_WRITTEN);
f2fs_put_page(node_page, 1);
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 7bcbc6e9c40d..3685fea62333 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -261,13 +261,11 @@ static void cache_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid,
{
struct nat_entry *e;
- down_write(&nm_i->nat_tree_lock);
e = __lookup_nat_cache(nm_i, nid);
if (!e) {
e = grab_nat_entry(nm_i, nid);
node_info_from_raw_nat(&e->ni, ne);
}
- up_write(&nm_i->nat_tree_lock);
}
static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni,
@@ -298,8 +296,7 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni,
new_blkaddr == NULL_ADDR);
f2fs_bug_on(sbi, nat_get_blkaddr(e) == NEW_ADDR &&
new_blkaddr == NEW_ADDR);
- f2fs_bug_on(sbi, nat_get_blkaddr(e) != NEW_ADDR &&
- nat_get_blkaddr(e) != NULL_ADDR &&
+ f2fs_bug_on(sbi, is_valid_data_blkaddr(sbi, nat_get_blkaddr(e)) &&
new_blkaddr == NEW_ADDR);
/* increment version no as node is removed */
@@ -314,7 +311,7 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni,
/* change address */
nat_set_blkaddr(e, new_blkaddr);
- if (new_blkaddr == NEW_ADDR || new_blkaddr == NULL_ADDR)
+ if (!is_valid_data_blkaddr(sbi, new_blkaddr))
set_nat_flag(e, IS_CHECKPOINTED, false);
__set_nat_cache_dirty(nm_i, e);
@@ -379,6 +376,8 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni)
memset(&ne, 0, sizeof(struct f2fs_nat_entry));
+ down_write(&nm_i->nat_tree_lock);
+
/* Check current segment summary */
mutex_lock(&curseg->curseg_mutex);
i = lookup_journal_in_cursum(sum, NAT_JOURNAL, nid, 0);
@@ -399,6 +398,7 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni)
cache:
/* cache nat entry */
cache_nat_entry(NM_I(sbi), nid, &ne);
+ up_write(&nm_i->nat_tree_lock);
}
/*
@@ -1341,6 +1341,12 @@ static int f2fs_write_node_page(struct page *page,
return 0;
}
+ if (__is_valid_data_blkaddr(ni.blk_addr) &&
+ !f2fs_is_valid_blkaddr(sbi, ni.blk_addr, DATA_GENERIC)) {
+ up_read(&sbi->node_write);
+ goto redirty_out;
+ }
+
set_page_writeback(page);
fio.blk_addr = ni.blk_addr;
write_node_page(nid, &fio);
@@ -1427,9 +1433,9 @@ static void __del_from_free_nid_list(struct f2fs_nm_info *nm_i,
static int add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
- struct free_nid *i;
+ struct free_nid *i, *e;
struct nat_entry *ne;
- bool allocated = false;
+ int err = -EINVAL;
if (!available_free_memory(sbi, FREE_NIDS))
return -1;
@@ -1438,40 +1444,58 @@ static int add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build)
if (unlikely(nid == 0))
return 0;
- if (build) {
- /* do not add allocated nids */
- down_read(&nm_i->nat_tree_lock);
- ne = __lookup_nat_cache(nm_i, nid);
- if (ne &&
- (!get_nat_flag(ne, IS_CHECKPOINTED) ||
- nat_get_blkaddr(ne) != NULL_ADDR))
- allocated = true;
- up_read(&nm_i->nat_tree_lock);
- if (allocated)
- return 0;
- }
-
i = f2fs_kmem_cache_alloc(free_nid_slab, GFP_NOFS);
i->nid = nid;
i->state = NID_NEW;
- if (radix_tree_preload(GFP_NOFS)) {
- kmem_cache_free(free_nid_slab, i);
- return 0;
- }
+ if (radix_tree_preload(GFP_NOFS))
+ goto err;
spin_lock(&nm_i->free_nid_list_lock);
- if (radix_tree_insert(&nm_i->free_nid_root, i->nid, i)) {
- spin_unlock(&nm_i->free_nid_list_lock);
- radix_tree_preload_end();
- kmem_cache_free(free_nid_slab, i);
- return 0;
+
+ if (build) {
+ /*
+ * Thread A Thread B
+ * - f2fs_create
+ * - f2fs_new_inode
+ * - alloc_nid
+ * - __insert_nid_to_list(ALLOC_NID_LIST)
+ * - f2fs_balance_fs_bg
+ * - build_free_nids
+ * - __build_free_nids
+ * - scan_nat_page
+ * - add_free_nid
+ * - __lookup_nat_cache
+ * - f2fs_add_link
+ * - init_inode_metadata
+ * - new_inode_page
+ * - new_node_page
+ * - set_node_addr
+ * - alloc_nid_done
+ * - __remove_nid_from_list(ALLOC_NID_LIST)
+ * - __insert_nid_to_list(FREE_NID_LIST)
+ */
+ ne = __lookup_nat_cache(nm_i, nid);
+ if (ne && (!get_nat_flag(ne, IS_CHECKPOINTED) ||
+ nat_get_blkaddr(ne) != NULL_ADDR))
+ goto err_out;
+
+ e = __lookup_free_nid_list(nm_i, nid);
+ if (e)
+ goto err_out;
}
+ if (radix_tree_insert(&nm_i->free_nid_root, i->nid, i))
+ goto err_out;
+ err = 0;
list_add_tail(&i->list, &nm_i->free_nid_list);
nm_i->fcnt++;
+err_out:
spin_unlock(&nm_i->free_nid_list_lock);
radix_tree_preload_end();
- return 1;
+err:
+ if (err)
+ kmem_cache_free(free_nid_slab, i);
+ return !err;
}
static void remove_free_nid(struct f2fs_nm_info *nm_i, nid_t nid)
@@ -1532,6 +1556,8 @@ static void build_free_nids(struct f2fs_sb_info *sbi)
ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), FREE_NID_PAGES,
META_NAT, true);
+ down_read(&nm_i->nat_tree_lock);
+
while (1) {
struct page *page = get_current_nat_page(sbi, nid);
@@ -1560,6 +1586,7 @@ static void build_free_nids(struct f2fs_sb_info *sbi)
remove_free_nid(nm_i, nid);
}
mutex_unlock(&curseg->curseg_mutex);
+ up_read(&nm_i->nat_tree_lock);
ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nm_i->next_scan_nid),
nm_i->ra_nid_pages, META_NAT, false);
@@ -1842,14 +1869,12 @@ static void remove_nats_in_journal(struct f2fs_sb_info *sbi)
raw_ne = nat_in_journal(sum, i);
- down_write(&nm_i->nat_tree_lock);
ne = __lookup_nat_cache(nm_i, nid);
if (!ne) {
ne = grab_nat_entry(nm_i, nid);
node_info_from_raw_nat(&ne->ni, &raw_ne);
}
__set_nat_cache_dirty(nm_i, ne);
- up_write(&nm_i->nat_tree_lock);
}
update_nats_in_cursum(sum, -i);
mutex_unlock(&curseg->curseg_mutex);
@@ -1883,7 +1908,6 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi,
struct f2fs_nat_block *nat_blk;
struct nat_entry *ne, *cur;
struct page *page = NULL;
- struct f2fs_nm_info *nm_i = NM_I(sbi);
/*
* there are two steps to flush nat entries:
@@ -1920,12 +1944,8 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi,
raw_ne = &nat_blk->entries[nid - start_nid];
}
raw_nat_from_node_info(raw_ne, &ne->ni);
-
- down_write(&NM_I(sbi)->nat_tree_lock);
nat_reset_flag(ne);
__clear_nat_cache_dirty(NM_I(sbi), ne);
- up_write(&NM_I(sbi)->nat_tree_lock);
-
if (nat_get_blkaddr(ne) == NULL_ADDR)
add_free_nid(sbi, nid, false);
}
@@ -1937,9 +1957,7 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi,
f2fs_bug_on(sbi, set->entry_cnt);
- down_write(&nm_i->nat_tree_lock);
radix_tree_delete(&NM_I(sbi)->nat_set_root, set->set);
- up_write(&nm_i->nat_tree_lock);
kmem_cache_free(nat_entry_set_slab, set);
}
@@ -1959,6 +1977,9 @@ void flush_nat_entries(struct f2fs_sb_info *sbi)
if (!nm_i->dirty_nat_cnt)
return;
+
+ down_write(&nm_i->nat_tree_lock);
+
/*
* if there are no enough space in journal to store dirty nat
* entries, remove all entries from journal and merge them
@@ -1967,7 +1988,6 @@ void flush_nat_entries(struct f2fs_sb_info *sbi)
if (!__has_cursum_space(sum, nm_i->dirty_nat_cnt, NAT_JOURNAL))
remove_nats_in_journal(sbi);
- down_write(&nm_i->nat_tree_lock);
while ((found = __gang_lookup_nat_set(nm_i,
set_idx, SETVEC_SIZE, setvec))) {
unsigned idx;
@@ -1976,12 +1996,13 @@ void flush_nat_entries(struct f2fs_sb_info *sbi)
__adjust_nat_entry_set(setvec[idx], &sets,
MAX_NAT_JENTRIES(sum));
}
- up_write(&nm_i->nat_tree_lock);
/* flush dirty nats in nat entry set */
list_for_each_entry_safe(set, tmp, &sets, set_list)
__flush_nat_entry_set(sbi, set);
+ up_write(&nm_i->nat_tree_lock);
+
f2fs_bug_on(sbi, nm_i->dirty_nat_cnt);
}
diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h
index e4fffd2d98c4..0d6f0e3dc655 100644
--- a/fs/f2fs/node.h
+++ b/fs/f2fs/node.h
@@ -212,6 +212,37 @@ static inline void set_to_next_nat(struct f2fs_nm_info *nm_i, nid_t start_nid)
f2fs_change_bit(block_off, nm_i->nat_bitmap);
}
+static inline nid_t ino_of_node(struct page *node_page)
+{
+ struct f2fs_node *rn = F2FS_NODE(node_page);
+ return le32_to_cpu(rn->footer.ino);
+}
+
+static inline nid_t nid_of_node(struct page *node_page)
+{
+ struct f2fs_node *rn = F2FS_NODE(node_page);
+ return le32_to_cpu(rn->footer.nid);
+}
+
+static inline unsigned int ofs_of_node(struct page *node_page)
+{
+ struct f2fs_node *rn = F2FS_NODE(node_page);
+ unsigned flag = le32_to_cpu(rn->footer.flag);
+ return flag >> OFFSET_BIT_SHIFT;
+}
+
+static inline __u64 cpver_of_node(struct page *node_page)
+{
+ struct f2fs_node *rn = F2FS_NODE(node_page);
+ return le64_to_cpu(rn->footer.cp_ver);
+}
+
+static inline block_t next_blkaddr_of_node(struct page *node_page)
+{
+ struct f2fs_node *rn = F2FS_NODE(node_page);
+ return le32_to_cpu(rn->footer.next_blkaddr);
+}
+
static inline void fill_node_footer(struct page *page, nid_t nid,
nid_t ino, unsigned int ofs, bool reset)
{
@@ -242,40 +273,30 @@ static inline void fill_node_footer_blkaddr(struct page *page, block_t blkaddr)
{
struct f2fs_checkpoint *ckpt = F2FS_CKPT(F2FS_P_SB(page));
struct f2fs_node *rn = F2FS_NODE(page);
+ size_t crc_offset = le32_to_cpu(ckpt->checksum_offset);
+ __u64 cp_ver = le64_to_cpu(ckpt->checkpoint_ver);
- rn->footer.cp_ver = ckpt->checkpoint_ver;
+ if (is_set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG)) {
+ __u64 crc = le32_to_cpu(*((__le32 *)
+ ((unsigned char *)ckpt + crc_offset)));
+ cp_ver |= (crc << 32);
+ }
+ rn->footer.cp_ver = cpu_to_le64(cp_ver);
rn->footer.next_blkaddr = cpu_to_le32(blkaddr);
}
-static inline nid_t ino_of_node(struct page *node_page)
-{
- struct f2fs_node *rn = F2FS_NODE(node_page);
- return le32_to_cpu(rn->footer.ino);
-}
-
-static inline nid_t nid_of_node(struct page *node_page)
+static inline bool is_recoverable_dnode(struct page *page)
{
- struct f2fs_node *rn = F2FS_NODE(node_page);
- return le32_to_cpu(rn->footer.nid);
-}
-
-static inline unsigned int ofs_of_node(struct page *node_page)
-{
- struct f2fs_node *rn = F2FS_NODE(node_page);
- unsigned flag = le32_to_cpu(rn->footer.flag);
- return flag >> OFFSET_BIT_SHIFT;
-}
-
-static inline unsigned long long cpver_of_node(struct page *node_page)
-{
- struct f2fs_node *rn = F2FS_NODE(node_page);
- return le64_to_cpu(rn->footer.cp_ver);
-}
+ struct f2fs_checkpoint *ckpt = F2FS_CKPT(F2FS_P_SB(page));
+ size_t crc_offset = le32_to_cpu(ckpt->checksum_offset);
+ __u64 cp_ver = cur_cp_version(ckpt);
-static inline block_t next_blkaddr_of_node(struct page *node_page)
-{
- struct f2fs_node *rn = F2FS_NODE(node_page);
- return le32_to_cpu(rn->footer.next_blkaddr);
+ if (is_set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG)) {
+ __u64 crc = le32_to_cpu(*((__le32 *)
+ ((unsigned char *)ckpt + crc_offset)));
+ cp_ver |= (crc << 32);
+ }
+ return cpu_to_le64(cp_ver) == cpver_of_node(page);
}
/*
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index e32f349f341b..2878be3e448f 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -67,7 +67,30 @@ static struct fsync_inode_entry *get_fsync_inode(struct list_head *head,
return NULL;
}
-static int recover_dentry(struct inode *inode, struct page *ipage)
+static struct fsync_inode_entry *add_fsync_inode(struct list_head *head,
+ struct inode *inode)
+{
+ struct fsync_inode_entry *entry;
+
+ entry = kmem_cache_alloc(fsync_entry_slab, GFP_F2FS_ZERO);
+ if (!entry)
+ return NULL;
+
+ entry->inode = inode;
+ list_add_tail(&entry->list, head);
+
+ return entry;
+}
+
+static void del_fsync_inode(struct fsync_inode_entry *entry)
+{
+ iput(entry->inode);
+ list_del(&entry->list);
+ kmem_cache_free(fsync_entry_slab, entry);
+}
+
+static int recover_dentry(struct inode *inode, struct page *ipage,
+ struct list_head *dir_list)
{
struct f2fs_inode *raw_inode = F2FS_INODE(ipage);
nid_t pino = le32_to_cpu(raw_inode->i_pino);
@@ -75,18 +98,29 @@ static int recover_dentry(struct inode *inode, struct page *ipage)
struct qstr name;
struct page *page;
struct inode *dir, *einode;
+ struct fsync_inode_entry *entry;
int err = 0;
- dir = f2fs_iget(inode->i_sb, pino);
- if (IS_ERR(dir)) {
- err = PTR_ERR(dir);
- goto out;
+ entry = get_fsync_inode(dir_list, pino);
+ if (!entry) {
+ dir = f2fs_iget(inode->i_sb, pino);
+ if (IS_ERR(dir)) {
+ err = PTR_ERR(dir);
+ goto out;
+ }
+
+ entry = add_fsync_inode(dir_list, dir);
+ if (!entry) {
+ err = -ENOMEM;
+ iput(dir);
+ goto out;
+ }
}
- if (file_enc_name(inode)) {
- iput(dir);
+ dir = entry->inode;
+
+ if (file_enc_name(inode))
return 0;
- }
name.len = le32_to_cpu(raw_inode->i_namelen);
name.name = raw_inode->i_name;
@@ -94,7 +128,7 @@ static int recover_dentry(struct inode *inode, struct page *ipage)
if (unlikely(name.len > F2FS_NAME_LEN)) {
WARN_ON(1);
err = -ENAMETOOLONG;
- goto out_err;
+ goto out;
}
retry:
de = f2fs_find_entry(dir, &name, &page);
@@ -120,23 +154,12 @@ retry:
goto retry;
}
err = __f2fs_add_link(dir, &name, inode, inode->i_ino, inode->i_mode);
- if (err)
- goto out_err;
-
- if (is_inode_flag_set(F2FS_I(dir), FI_DELAY_IPUT)) {
- iput(dir);
- } else {
- add_dirty_dir_inode(dir);
- set_inode_flag(F2FS_I(dir), FI_DELAY_IPUT);
- }
goto out;
out_unmap_put:
f2fs_dentry_kunmap(dir, page);
f2fs_put_page(page, 0);
-out_err:
- iput(dir);
out:
f2fs_msg(inode->i_sb, KERN_NOTICE,
"%s: ino = %x, name = %s, dir = %lx, err = %d",
@@ -170,8 +193,8 @@ static void recover_inode(struct inode *inode, struct page *page)
static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
{
- unsigned long long cp_ver = cur_cp_version(F2FS_CKPT(sbi));
struct curseg_info *curseg;
+ struct inode *inode;
struct page *page = NULL;
block_t blkaddr;
int err = 0;
@@ -185,12 +208,12 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
while (1) {
struct fsync_inode_entry *entry;
- if (!is_valid_blkaddr(sbi, blkaddr, META_POR))
+ if (!f2fs_is_valid_blkaddr(sbi, blkaddr, META_POR))
return 0;
page = get_tmp_page(sbi, blkaddr);
- if (cp_ver != cpver_of_node(page))
+ if (!is_recoverable_dnode(page))
break;
if (!is_fsync_dnode(page))
@@ -204,27 +227,27 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
break;
}
- /* add this fsync inode to the list */
- entry = kmem_cache_alloc(fsync_entry_slab, GFP_F2FS_ZERO);
- if (!entry) {
- err = -ENOMEM;
- break;
- }
/*
* CP | dnode(F) | inode(DF)
* For this case, we should not give up now.
*/
- entry->inode = f2fs_iget(sbi->sb, ino_of_node(page));
- if (IS_ERR(entry->inode)) {
- err = PTR_ERR(entry->inode);
- kmem_cache_free(fsync_entry_slab, entry);
+ inode = f2fs_iget(sbi->sb, ino_of_node(page));
+ if (IS_ERR(inode)) {
+ err = PTR_ERR(inode);
if (err == -ENOENT) {
err = 0;
goto next;
}
break;
}
- list_add_tail(&entry->list, head);
+
+ /* add this fsync inode to the list */
+ entry = add_fsync_inode(head, inode);
+ if (!entry) {
+ err = -ENOMEM;
+ iput(inode);
+ break;
+ }
}
entry->blkaddr = blkaddr;
@@ -248,11 +271,8 @@ static void destroy_fsync_dnodes(struct list_head *head)
{
struct fsync_inode_entry *entry, *tmp;
- list_for_each_entry_safe(entry, tmp, head, list) {
- iput(entry->inode);
- list_del(&entry->list);
- kmem_cache_free(fsync_entry_slab, entry);
- }
+ list_for_each_entry_safe(entry, tmp, head, list)
+ del_fsync_inode(entry);
}
static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi,
@@ -423,7 +443,7 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
}
/* dest is valid block, try to recover from src to dest */
- if (is_valid_blkaddr(sbi, dest, META_POR)) {
+ if (f2fs_is_valid_blkaddr(sbi, dest, META_POR)) {
if (src == NULL_ADDR) {
err = reserve_new_block(&dn);
@@ -459,35 +479,34 @@ out:
return err;
}
-static int recover_data(struct f2fs_sb_info *sbi,
- struct list_head *head, int type)
+static int recover_data(struct f2fs_sb_info *sbi, struct list_head *inode_list,
+ struct list_head *dir_list)
{
- unsigned long long cp_ver = cur_cp_version(F2FS_CKPT(sbi));
struct curseg_info *curseg;
struct page *page = NULL;
int err = 0;
block_t blkaddr;
/* get node pages in the current segment */
- curseg = CURSEG_I(sbi, type);
+ curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
while (1) {
struct fsync_inode_entry *entry;
- if (!is_valid_blkaddr(sbi, blkaddr, META_POR))
+ if (!f2fs_is_valid_blkaddr(sbi, blkaddr, META_POR))
break;
ra_meta_pages_cond(sbi, blkaddr);
page = get_tmp_page(sbi, blkaddr);
- if (cp_ver != cpver_of_node(page)) {
+ if (!is_recoverable_dnode(page)) {
f2fs_put_page(page, 1);
break;
}
- entry = get_fsync_inode(head, ino_of_node(page));
+ entry = get_fsync_inode(inode_list, ino_of_node(page));
if (!entry)
goto next;
/*
@@ -498,7 +517,7 @@ static int recover_data(struct f2fs_sb_info *sbi,
if (entry->last_inode == blkaddr)
recover_inode(entry->inode, page);
if (entry->last_dentry == blkaddr) {
- err = recover_dentry(entry->inode, page);
+ err = recover_dentry(entry->inode, page, dir_list);
if (err) {
f2fs_put_page(page, 1);
break;
@@ -510,11 +529,8 @@ static int recover_data(struct f2fs_sb_info *sbi,
break;
}
- if (entry->blkaddr == blkaddr) {
- iput(entry->inode);
- list_del(&entry->list);
- kmem_cache_free(fsync_entry_slab, entry);
- }
+ if (entry->blkaddr == blkaddr)
+ del_fsync_inode(entry);
next:
/* check next segment */
blkaddr = next_blkaddr_of_node(page);
@@ -525,12 +541,14 @@ next:
return err;
}
-int recover_fsync_data(struct f2fs_sb_info *sbi)
+int recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
{
struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
struct list_head inode_list;
+ struct list_head dir_list;
block_t blkaddr;
int err;
+ int ret = 0;
bool need_writecp = false;
fsync_entry_slab = f2fs_kmem_cache_create("f2fs_fsync_inode_entry",
@@ -539,6 +557,7 @@ int recover_fsync_data(struct f2fs_sb_info *sbi)
return -ENOMEM;
INIT_LIST_HEAD(&inode_list);
+ INIT_LIST_HEAD(&dir_list);
/* prevent checkpoint */
mutex_lock(&sbi->cp_mutex);
@@ -547,21 +566,22 @@ int recover_fsync_data(struct f2fs_sb_info *sbi)
/* step #1: find fsynced inode numbers */
err = find_fsync_dnodes(sbi, &inode_list);
- if (err)
+ if (err || list_empty(&inode_list))
goto out;
- if (list_empty(&inode_list))
+ if (check_only) {
+ ret = 1;
goto out;
+ }
need_writecp = true;
/* step #2: recover data */
- err = recover_data(sbi, &inode_list, CURSEG_WARM_NODE);
+ err = recover_data(sbi, &inode_list, &dir_list);
if (!err)
f2fs_bug_on(sbi, !list_empty(&inode_list));
out:
destroy_fsync_dnodes(&inode_list);
- kmem_cache_destroy(fsync_entry_slab);
/* truncate meta pages to be used by the recovery */
truncate_inode_pages_range(META_MAPPING(sbi),
@@ -573,31 +593,20 @@ out:
}
clear_sbi_flag(sbi, SBI_POR_DOING);
- if (err) {
- bool invalidate = false;
-
- if (discard_next_dnode(sbi, blkaddr))
- invalidate = true;
-
- /* Flush all the NAT/SIT pages */
- while (get_pages(sbi, F2FS_DIRTY_META))
- sync_meta_pages(sbi, META, LONG_MAX);
+ if (err)
+ set_ckpt_flags(sbi->ckpt, CP_ERROR_FLAG);
+ mutex_unlock(&sbi->cp_mutex);
- /* invalidate temporary meta page */
- if (invalidate)
- invalidate_mapping_pages(META_MAPPING(sbi),
- blkaddr, blkaddr);
+ /* let's drop all the directory inodes for clean checkpoint */
+ destroy_fsync_dnodes(&dir_list);
- set_ckpt_flags(sbi->ckpt, CP_ERROR_FLAG);
- mutex_unlock(&sbi->cp_mutex);
- } else if (need_writecp) {
+ if (!err && need_writecp) {
struct cp_control cpc = {
.reason = CP_RECOVERY,
};
- mutex_unlock(&sbi->cp_mutex);
write_checkpoint(sbi, &cpc);
- } else {
- mutex_unlock(&sbi->cp_mutex);
}
- return err;
+
+ kmem_cache_destroy(fsync_entry_slab);
+ return ret ? ret: err;
}
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 39ec9da08bb5..6802cd754eda 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -519,28 +519,6 @@ static int f2fs_issue_discard(struct f2fs_sb_info *sbi,
return blkdev_issue_discard(sbi->sb->s_bdev, start, len, GFP_NOFS, 0);
}
-bool discard_next_dnode(struct f2fs_sb_info *sbi, block_t blkaddr)
-{
- int err = -ENOTSUPP;
-
- if (test_opt(sbi, DISCARD)) {
- struct seg_entry *se = get_seg_entry(sbi,
- GET_SEGNO(sbi, blkaddr));
- unsigned int offset = GET_BLKOFF_FROM_SEG0(sbi, blkaddr);
-
- if (f2fs_test_bit(offset, se->discard_map))
- return false;
-
- err = f2fs_issue_discard(sbi, blkaddr, 1);
- }
-
- if (err) {
- update_meta_page(sbi, NULL, blkaddr);
- return true;
- }
- return false;
-}
-
static void __add_discard_entry(struct f2fs_sb_info *sbi,
struct cp_control *cpc, struct seg_entry *se,
unsigned int start, unsigned int end)
@@ -774,7 +752,7 @@ bool is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr)
struct seg_entry *se;
bool is_cp = false;
- if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR)
+ if (!is_valid_data_blkaddr(sbi, blkaddr))
return true;
mutex_lock(&sit_i->sentry_lock);
@@ -1488,7 +1466,7 @@ void f2fs_wait_on_encrypted_page_writeback(struct f2fs_sb_info *sbi,
{
struct page *cpage;
- if (blkaddr == NEW_ADDR)
+ if (!is_valid_data_blkaddr(sbi, blkaddr))
return;
f2fs_bug_on(sbi, blkaddr == NULL_ADDR);
@@ -2123,7 +2101,7 @@ static int build_curseg(struct f2fs_sb_info *sbi)
return restore_curseg_summaries(sbi);
}
-static void build_sit_entries(struct f2fs_sb_info *sbi)
+static int build_sit_entries(struct f2fs_sb_info *sbi)
{
struct sit_info *sit_i = SIT_I(sbi);
struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_COLD_DATA);
@@ -2132,6 +2110,7 @@ static void build_sit_entries(struct f2fs_sb_info *sbi)
unsigned int i, start, end;
unsigned int readed, start_blk = 0;
int nrpages = MAX_BIO_BLOCKS(sbi);
+ int err = 0;
do {
readed = ra_meta_pages(sbi, start_blk, nrpages, META_SIT, true);
@@ -2145,36 +2124,62 @@ static void build_sit_entries(struct f2fs_sb_info *sbi)
struct f2fs_sit_entry sit;
struct page *page;
- mutex_lock(&curseg->curseg_mutex);
- for (i = 0; i < sits_in_cursum(sum); i++) {
- if (le32_to_cpu(segno_in_journal(sum, i))
- == start) {
- sit = sit_in_journal(sum, i);
- mutex_unlock(&curseg->curseg_mutex);
- goto got_it;
- }
- }
- mutex_unlock(&curseg->curseg_mutex);
-
page = get_current_sit_page(sbi, start);
sit_blk = (struct f2fs_sit_block *)page_address(page);
sit = sit_blk->entries[SIT_ENTRY_OFFSET(sit_i, start)];
f2fs_put_page(page, 1);
-got_it:
- check_block_count(sbi, start, &sit);
+
+ err = check_block_count(sbi, start, &sit);
+ if (err)
+ return err;
seg_info_from_raw_sit(se, &sit);
/* build discard map only one time */
memcpy(se->discard_map, se->cur_valid_map, SIT_VBLOCK_MAP_SIZE);
sbi->discard_blks += sbi->blocks_per_seg - se->valid_blocks;
- if (sbi->segs_per_sec > 1) {
- struct sec_entry *e = get_sec_entry(sbi, start);
- e->valid_blocks += se->valid_blocks;
- }
+ if (sbi->segs_per_sec > 1)
+ get_sec_entry(sbi, start)->valid_blocks +=
+ se->valid_blocks;
}
start_blk += readed;
} while (start_blk < sit_blk_cnt);
+
+ mutex_lock(&curseg->curseg_mutex);
+ for (i = 0; i < sits_in_cursum(sum); i++) {
+ struct f2fs_sit_entry sit;
+ struct seg_entry *se;
+ unsigned int old_valid_blocks;
+
+ start = le32_to_cpu(segno_in_journal(sum, i));
+ if (start >= MAIN_SEGS(sbi)) {
+ f2fs_msg(sbi->sb, KERN_ERR,
+ "Wrong journal entry on segno %u",
+ start);
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ err = -EINVAL;
+ break;
+ }
+
+ se = &sit_i->sentries[start];
+ sit = sit_in_journal(sum, i);
+
+ old_valid_blocks = se->valid_blocks;
+
+ err = check_block_count(sbi, start, &sit);
+ if (err)
+ break;
+ seg_info_from_raw_sit(se, &sit);
+
+ memcpy(se->discard_map, se->cur_valid_map, SIT_VBLOCK_MAP_SIZE);
+ sbi->discard_blks += old_valid_blocks - se->valid_blocks;
+
+ if (sbi->segs_per_sec > 1)
+ get_sec_entry(sbi, start)->valid_blocks +=
+ se->valid_blocks - old_valid_blocks;
+ }
+ mutex_unlock(&curseg->curseg_mutex);
+ return err;
}
static void init_free_segmap(struct f2fs_sb_info *sbi)
@@ -2336,7 +2341,9 @@ int build_segment_manager(struct f2fs_sb_info *sbi)
return err;
/* reinit free segmap based on SIT */
- build_sit_entries(sbi);
+ err = build_sit_entries(sbi);
+ if (err)
+ return err;
init_free_segmap(sbi);
err = build_dirty_segmap(sbi);
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index bfa1d31f79aa..08b08ae6ba9d 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -17,6 +17,8 @@
#define DEF_RECLAIM_PREFREE_SEGMENTS 5 /* 5% over total segments */
+#define F2FS_MIN_SEGMENTS 9 /* SB + 2 (CP + SIT + NAT) + SSA + MAIN */
+
/* L: Logical segment # in volume, R: Relative segment # in main area */
#define GET_L2R_SEGNO(free_i, segno) (segno - free_i->start_segno)
#define GET_R2L_SEGNO(free_i, segno) (segno + free_i->start_segno)
@@ -46,13 +48,19 @@
(secno == CURSEG_I(sbi, CURSEG_COLD_NODE)->segno / \
sbi->segs_per_sec)) \
-#define MAIN_BLKADDR(sbi) (SM_I(sbi)->main_blkaddr)
-#define SEG0_BLKADDR(sbi) (SM_I(sbi)->seg0_blkaddr)
+#define MAIN_BLKADDR(sbi) \
+ (SM_I(sbi) ? SM_I(sbi)->main_blkaddr : \
+ le32_to_cpu(F2FS_RAW_SUPER(sbi)->main_blkaddr))
+#define SEG0_BLKADDR(sbi) \
+ (SM_I(sbi) ? SM_I(sbi)->seg0_blkaddr : \
+ le32_to_cpu(F2FS_RAW_SUPER(sbi)->segment0_blkaddr))
#define MAIN_SEGS(sbi) (SM_I(sbi)->main_segments)
#define MAIN_SECS(sbi) (sbi->total_sections)
-#define TOTAL_SEGS(sbi) (SM_I(sbi)->segment_count)
+#define TOTAL_SEGS(sbi) \
+ (SM_I(sbi) ? SM_I(sbi)->segment_count : \
+ le32_to_cpu(F2FS_RAW_SUPER(sbi)->segment_count))
#define TOTAL_BLKS(sbi) (TOTAL_SEGS(sbi) << sbi->log_blocks_per_seg)
#define MAX_BLKADDR(sbi) (SEG0_BLKADDR(sbi) + TOTAL_BLKS(sbi))
@@ -72,7 +80,7 @@
(GET_SEGOFF_FROM_SEG0(sbi, blk_addr) & (sbi->blocks_per_seg - 1))
#define GET_SEGNO(sbi, blk_addr) \
- (((blk_addr == NULL_ADDR) || (blk_addr == NEW_ADDR)) ? \
+ ((!is_valid_data_blkaddr(sbi, blk_addr)) ? \
NULL_SEGNO : GET_L2R_SEGNO(FREE_I(sbi), \
GET_SEGNO_FROM_SEG0(sbi, blk_addr)))
#define GET_SECNO(sbi, segno) \
@@ -574,16 +582,20 @@ static inline void check_seg_range(struct f2fs_sb_info *sbi, unsigned int segno)
f2fs_bug_on(sbi, segno > TOTAL_SEGS(sbi) - 1);
}
-static inline void verify_block_addr(struct f2fs_sb_info *sbi, block_t blk_addr)
+static inline void verify_block_addr(struct f2fs_io_info *fio, block_t blk_addr)
{
- f2fs_bug_on(sbi, blk_addr < SEG0_BLKADDR(sbi)
- || blk_addr >= MAX_BLKADDR(sbi));
+ struct f2fs_sb_info *sbi = fio->sbi;
+
+ if (__is_meta_io(fio))
+ verify_blkaddr(sbi, blk_addr, META_GENERIC);
+ else
+ verify_blkaddr(sbi, blk_addr, DATA_GENERIC);
}
/*
* Summary block is always treated as an invalid block
*/
-static inline void check_block_count(struct f2fs_sb_info *sbi,
+static inline int check_block_count(struct f2fs_sb_info *sbi,
int segno, struct f2fs_sit_entry *raw_sit)
{
#ifdef CONFIG_F2FS_CHECK_FS
@@ -605,11 +617,25 @@ static inline void check_block_count(struct f2fs_sb_info *sbi,
cur_pos = next_pos;
is_valid = !is_valid;
} while (cur_pos < sbi->blocks_per_seg);
- BUG_ON(GET_SIT_VBLOCKS(raw_sit) != valid_blocks);
+
+ if (unlikely(GET_SIT_VBLOCKS(raw_sit) != valid_blocks)) {
+ f2fs_msg(sbi->sb, KERN_ERR,
+ "Mismatch valid blocks %d vs. %d",
+ GET_SIT_VBLOCKS(raw_sit), valid_blocks);
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ return -EINVAL;
+ }
#endif
/* check segment usage, and check boundary of a given segment number */
- f2fs_bug_on(sbi, GET_SIT_VBLOCKS(raw_sit) > sbi->blocks_per_seg
- || segno > TOTAL_SEGS(sbi) - 1);
+ if (unlikely(GET_SIT_VBLOCKS(raw_sit) > sbi->blocks_per_seg
+ || segno > TOTAL_SEGS(sbi) - 1)) {
+ f2fs_msg(sbi->sb, KERN_ERR,
+ "Wrong valid blocks %d or segno %u",
+ GET_SIT_VBLOCKS(raw_sit), segno);
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ return -EINVAL;
+ }
+ return 0;
}
static inline pgoff_t current_sit_addr(struct f2fs_sb_info *sbi,
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 2ffc53d0c9c7..dbd7adff8b5a 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -994,6 +994,8 @@ static inline bool sanity_check_area_boundary(struct super_block *sb,
static int sanity_check_raw_super(struct super_block *sb,
struct f2fs_super_block *raw_super)
{
+ block_t segment_count, segs_per_sec, secs_per_zone;
+ block_t total_sections, blocks_per_seg;
unsigned int blocksize;
if (F2FS_SUPER_MAGIC != le32_to_cpu(raw_super->magic)) {
@@ -1047,6 +1049,68 @@ static int sanity_check_raw_super(struct super_block *sb,
return 1;
}
+ segment_count = le32_to_cpu(raw_super->segment_count);
+ segs_per_sec = le32_to_cpu(raw_super->segs_per_sec);
+ secs_per_zone = le32_to_cpu(raw_super->secs_per_zone);
+ total_sections = le32_to_cpu(raw_super->section_count);
+
+ /* blocks_per_seg should be 512, given the above check */
+ blocks_per_seg = 1 << le32_to_cpu(raw_super->log_blocks_per_seg);
+
+ if (segment_count > F2FS_MAX_SEGMENT ||
+ segment_count < F2FS_MIN_SEGMENTS) {
+ f2fs_msg(sb, KERN_INFO,
+ "Invalid segment count (%u)",
+ segment_count);
+ return 1;
+ }
+
+ if (total_sections > segment_count ||
+ total_sections < F2FS_MIN_SEGMENTS ||
+ segs_per_sec > segment_count || !segs_per_sec) {
+ f2fs_msg(sb, KERN_INFO,
+ "Invalid segment/section count (%u, %u x %u)",
+ segment_count, total_sections, segs_per_sec);
+ return 1;
+ }
+
+ if ((segment_count / segs_per_sec) < total_sections) {
+ f2fs_msg(sb, KERN_INFO,
+ "Small segment_count (%u < %u * %u)",
+ segment_count, segs_per_sec, total_sections);
+ return 1;
+ }
+
+ if (segment_count > (le64_to_cpu(raw_super->block_count) >> 9)) {
+ f2fs_msg(sb, KERN_INFO,
+ "Wrong segment_count / block_count (%u > %llu)",
+ segment_count, le64_to_cpu(raw_super->block_count));
+ return 1;
+ }
+
+ if (secs_per_zone > total_sections || !secs_per_zone) {
+ f2fs_msg(sb, KERN_INFO,
+ "Wrong secs_per_zone / total_sections (%u, %u)",
+ secs_per_zone, total_sections);
+ return 1;
+ }
+ if (le32_to_cpu(raw_super->extension_count) > F2FS_MAX_EXTENSION) {
+ f2fs_msg(sb, KERN_INFO,
+ "Corrupted extension count (%u > %u)",
+ le32_to_cpu(raw_super->extension_count),
+ F2FS_MAX_EXTENSION);
+ return 1;
+ }
+
+ if (le32_to_cpu(raw_super->cp_payload) >
+ (blocks_per_seg - F2FS_CP_PACKS)) {
+ f2fs_msg(sb, KERN_INFO,
+ "Insane cp_payload (%u > %u)",
+ le32_to_cpu(raw_super->cp_payload),
+ blocks_per_seg - F2FS_CP_PACKS);
+ return 1;
+ }
+
/* check reserved ino info */
if (le32_to_cpu(raw_super->node_ino) != 1 ||
le32_to_cpu(raw_super->meta_ino) != 2 ||
@@ -1059,13 +1123,6 @@ static int sanity_check_raw_super(struct super_block *sb,
return 1;
}
- if (le32_to_cpu(raw_super->segment_count) > F2FS_MAX_SEGMENT) {
- f2fs_msg(sb, KERN_INFO,
- "Invalid segment count (%u)",
- le32_to_cpu(raw_super->segment_count));
- return 1;
- }
-
/* check CP/SIT/NAT/SSA/MAIN_AREA area boundary */
if (sanity_check_area_boundary(sb, raw_super))
return 1;
@@ -1073,15 +1130,19 @@ static int sanity_check_raw_super(struct super_block *sb,
return 0;
}
-static int sanity_check_ckpt(struct f2fs_sb_info *sbi)
+int sanity_check_ckpt(struct f2fs_sb_info *sbi)
{
unsigned int total, fsmeta;
struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
+ unsigned int ovp_segments, reserved_segments;
unsigned int main_segs, blocks_per_seg;
unsigned int sit_segs, nat_segs;
unsigned int sit_bitmap_size, nat_bitmap_size;
unsigned int log_blocks_per_seg;
+ unsigned int segment_count_main;
+ unsigned int cp_pack_start_sum, cp_payload;
+ block_t user_block_count;
int i;
total = le32_to_cpu(raw_super->segment_count);
@@ -1096,6 +1157,26 @@ static int sanity_check_ckpt(struct f2fs_sb_info *sbi)
if (unlikely(fsmeta >= total))
return 1;
+ ovp_segments = le32_to_cpu(ckpt->overprov_segment_count);
+ reserved_segments = le32_to_cpu(ckpt->rsvd_segment_count);
+
+ if (unlikely(fsmeta < F2FS_MIN_SEGMENTS ||
+ ovp_segments == 0 || reserved_segments == 0)) {
+ f2fs_msg(sbi->sb, KERN_ERR,
+ "Wrong layout: check mkfs.f2fs version");
+ return 1;
+ }
+
+ user_block_count = le64_to_cpu(ckpt->user_block_count);
+ segment_count_main = le32_to_cpu(raw_super->segment_count_main);
+ log_blocks_per_seg = le32_to_cpu(raw_super->log_blocks_per_seg);
+ if (!user_block_count || user_block_count >=
+ segment_count_main << log_blocks_per_seg) {
+ f2fs_msg(sbi->sb, KERN_ERR,
+ "Wrong user_block_count: %u", user_block_count);
+ return 1;
+ }
+
main_segs = le32_to_cpu(raw_super->segment_count_main);
blocks_per_seg = sbi->blocks_per_seg;
@@ -1112,7 +1193,6 @@ static int sanity_check_ckpt(struct f2fs_sb_info *sbi)
sit_bitmap_size = le32_to_cpu(ckpt->sit_ver_bitmap_bytesize);
nat_bitmap_size = le32_to_cpu(ckpt->nat_ver_bitmap_bytesize);
- log_blocks_per_seg = le32_to_cpu(raw_super->log_blocks_per_seg);
if (sit_bitmap_size != ((sit_segs / 2) << log_blocks_per_seg) / 8 ||
nat_bitmap_size != ((nat_segs / 2) << log_blocks_per_seg) / 8) {
@@ -1122,6 +1202,17 @@ static int sanity_check_ckpt(struct f2fs_sb_info *sbi)
return 1;
}
+ cp_pack_start_sum = __start_sum_addr(sbi);
+ cp_payload = __cp_payload(sbi);
+ if (cp_pack_start_sum < cp_payload + 1 ||
+ cp_pack_start_sum > blocks_per_seg - 1 -
+ NR_CURSEG_TYPE) {
+ f2fs_msg(sbi->sb, KERN_ERR,
+ "Wrong cp_pack_start_sum: %u",
+ cp_pack_start_sum);
+ return 1;
+ }
+
if (unlikely(f2fs_cp_error(sbi))) {
f2fs_msg(sbi->sb, KERN_ERR, "A bug case: need to run fsck");
return 1;
@@ -1358,13 +1449,6 @@ try_onemore:
goto free_meta_inode;
}
- /* sanity checking of checkpoint */
- err = -EINVAL;
- if (sanity_check_ckpt(sbi)) {
- f2fs_msg(sb, KERN_ERR, "Invalid F2FS checkpoint");
- goto free_cp;
- }
-
sbi->total_valid_node_count =
le32_to_cpu(sbi->ckpt->valid_node_count);
sbi->total_valid_inode_count =
@@ -1464,14 +1548,27 @@ try_onemore:
if (need_fsck)
set_sbi_flag(sbi, SBI_NEED_FSCK);
- err = recover_fsync_data(sbi);
- if (err) {
+ if (!retry)
+ goto skip_recovery;
+
+ err = recover_fsync_data(sbi, false);
+ if (err < 0) {
need_fsck = true;
f2fs_msg(sb, KERN_ERR,
"Cannot recover all fsync data errno=%ld", err);
goto free_kobj;
}
+ } else {
+ err = recover_fsync_data(sbi, true);
+
+ if (!f2fs_readonly(sb) && err > 0) {
+ err = -EINVAL;
+ f2fs_msg(sb, KERN_ERR,
+ "Need to recover fsync data");
+ goto free_kobj;
+ }
}
+skip_recovery:
/* recover_fsync_data() cleared this already */
clear_sbi_flag(sbi, SBI_POR_DOING);
@@ -1517,7 +1614,6 @@ free_nm:
destroy_node_manager(sbi);
free_sm:
destroy_segment_manager(sbi);
-free_cp:
kfree(sbi->ckpt);
free_meta_inode:
make_bad_inode(sbi->meta_inode);
diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c
index 1544f530ccd0..023e7f32ee1b 100644
--- a/fs/jffs2/super.c
+++ b/fs/jffs2/super.c
@@ -101,7 +101,8 @@ static int jffs2_sync_fs(struct super_block *sb, int wait)
struct jffs2_sb_info *c = JFFS2_SB_INFO(sb);
#ifdef CONFIG_JFFS2_FS_WRITEBUFFER
- cancel_delayed_work_sync(&c->wbuf_dwork);
+ if (jffs2_is_writebuffered(c))
+ cancel_delayed_work_sync(&c->wbuf_dwork);
#endif
mutex_lock(&c->alloc_sem);
diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c
index 0a4457fb0711..85111d740c9d 100644
--- a/fs/ocfs2/localalloc.c
+++ b/fs/ocfs2/localalloc.c
@@ -345,13 +345,18 @@ int ocfs2_load_local_alloc(struct ocfs2_super *osb)
if (num_used
|| alloc->id1.bitmap1.i_used
|| alloc->id1.bitmap1.i_total
- || la->la_bm_off)
- mlog(ML_ERROR, "Local alloc hasn't been recovered!\n"
+ || la->la_bm_off) {
+ mlog(ML_ERROR, "inconsistent detected, clean journal with"
+ " unrecovered local alloc, please run fsck.ocfs2!\n"
"found = %u, set = %u, taken = %u, off = %u\n",
num_used, le32_to_cpu(alloc->id1.bitmap1.i_used),
le32_to_cpu(alloc->id1.bitmap1.i_total),
OCFS2_LOCAL_ALLOC(alloc)->la_bm_off);
+ status = -EINVAL;
+ goto bail;
+ }
+
osb->local_alloc_bh = alloc_bh;
osb->local_alloc_state = OCFS2_LA_ENABLED;
diff --git a/fs/proc/array.c b/fs/proc/array.c
index cb71cbae606d..60cbaa821164 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -333,7 +333,7 @@ static inline void task_seccomp(struct seq_file *m, struct task_struct *p)
#ifdef CONFIG_SECCOMP
seq_printf(m, "Seccomp:\t%d\n", p->seccomp.mode);
#endif
- seq_printf(m, "\nSpeculation_Store_Bypass:\t");
+ seq_printf(m, "Speculation_Store_Bypass:\t");
switch (arch_prctl_spec_ctrl_get(p, PR_SPEC_STORE_BYPASS)) {
case -EINVAL:
seq_printf(m, "unknown");
diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c
index bd21795ce657..679d75a864d0 100644
--- a/fs/pstore/ram_core.c
+++ b/fs/pstore/ram_core.c
@@ -445,6 +445,11 @@ static int persistent_ram_post_init(struct persistent_ram_zone *prz, u32 sig,
sig ^= PERSISTENT_RAM_SIG;
if (prz->buffer->sig == sig) {
+ if (buffer_size(prz) == 0) {
+ pr_debug("found existing empty buffer\n");
+ return 0;
+ }
+
if (buffer_size(prz) > prz->buffer_size ||
buffer_start(prz) > buffer_size(prz))
pr_info("found existing invalid buffer, size %zu, start %zu\n",
diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index fb9636cc927c..5d8d12746e6e 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -528,7 +528,14 @@ xfs_attr_shortform_addname(xfs_da_args_t *args)
if (args->flags & ATTR_CREATE)
return retval;
retval = xfs_attr_shortform_remove(args);
- ASSERT(retval == 0);
+ if (retval)
+ return retval;
+ /*
+ * Since we have removed the old attr, clear ATTR_REPLACE so
+ * that the leaf format add routine won't trip over the attr
+ * not being around.
+ */
+ args->flags &= ~ATTR_REPLACE;
}
if (args->namelen >= XFS_ATTR_SF_ENTSIZE_MAX ||
diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h
index a307c37c2e6c..072501a0ac86 100644
--- a/include/linux/backing-dev-defs.h
+++ b/include/linux/backing-dev-defs.h
@@ -225,6 +225,14 @@ static inline void wb_get(struct bdi_writeback *wb)
*/
static inline void wb_put(struct bdi_writeback *wb)
{
+ if (WARN_ON_ONCE(!wb->bdi)) {
+ /*
+ * A driver bug might cause a file to be removed before bdi was
+ * initialized.
+ */
+ return;
+ }
+
if (wb != &wb->bdi->wb)
percpu_ref_put(&wb->refcnt);
}
diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h
index 3d6e6ce44c5c..520fd854e7b3 100644
--- a/include/linux/f2fs_fs.h
+++ b/include/linux/f2fs_fs.h
@@ -99,6 +99,7 @@ struct f2fs_super_block {
/*
* For checkpoint
*/
+#define CP_CRC_RECOVERY_FLAG 0x00000040
#define CP_FASTBOOT_FLAG 0x00000020
#define CP_FSCK_FLAG 0x00000010
#define CP_ERROR_FLAG 0x00000008
@@ -497,4 +498,6 @@ enum {
F2FS_FT_MAX
};
+#define S_SHIFT 12
+
#endif /* _LINUX_F2FS_FS_H */
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 3309dbda7ffa..0bc7fa21db85 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2151,6 +2151,7 @@ int write_cache_pages(struct address_space *mapping,
{
int ret = 0;
int done = 0;
+ int error;
struct pagevec pvec;
int nr_pages;
pgoff_t uninitialized_var(writeback_index);
@@ -2247,25 +2248,31 @@ continue_unlock:
goto continue_unlock;
trace_wbc_writepage(wbc, inode_to_bdi(mapping->host));
- ret = (*writepage)(page, wbc, data);
- if (unlikely(ret)) {
- if (ret == AOP_WRITEPAGE_ACTIVATE) {
+ error = (*writepage)(page, wbc, data);
+ if (unlikely(error)) {
+ /*
+ * Handle errors according to the type of
+ * writeback. There's no need to continue for
+ * background writeback. Just push done_index
+ * past this page so media errors won't choke
+ * writeout for the entire file. For integrity
+ * writeback, we must process the entire dirty
+ * set regardless of errors because the fs may
+ * still have state to clear for each page. In
+ * that case we continue processing and return
+ * the first error.
+ */
+ if (error == AOP_WRITEPAGE_ACTIVATE) {
unlock_page(page);
- ret = 0;
- } else {
- /*
- * done_index is set past this page,
- * so media errors will not choke
- * background writeout for the entire
- * file. This has consequences for
- * range_cyclic semantics (ie. it may
- * not be suitable for data integrity
- * writeout).
- */
+ error = 0;
+ } else if (wbc->sync_mode != WB_SYNC_ALL) {
+ ret = error;
done_index = page->index + 1;
done = 1;
break;
}
+ if (!ret)
+ ret = error;
}
/*
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index 55dcb2b20b59..6def85d75b1d 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -267,7 +267,7 @@ int br_nf_pre_routing_finish_bridge(struct net *net, struct sock *sk, struct sk_
struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
int ret;
- if (neigh->hh.hh_len) {
+ if ((neigh->nud_state & NUD_CONNECTED) && neigh->hh.hh_len) {
neigh_hh_bridge(&neigh->hh, skb);
skb->dev = nf_bridge->physindev;
ret = br_handle_frame_finish(net, sk, skb);
diff --git a/net/can/gw.c b/net/can/gw.c
index 77c8af4047ef..81650affa3fa 100644
--- a/net/can/gw.c
+++ b/net/can/gw.c
@@ -418,13 +418,29 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data)
while (modidx < MAX_MODFUNCTIONS && gwj->mod.modfunc[modidx])
(*gwj->mod.modfunc[modidx++])(cf, &gwj->mod);
- /* check for checksum updates when the CAN frame has been modified */
+ /* Has the CAN frame been modified? */
if (modidx) {
- if (gwj->mod.csumfunc.crc8)
+ /* get available space for the processed CAN frame type */
+ int max_len = nskb->len - offsetof(struct can_frame, data);
+
+ /* dlc may have changed, make sure it fits to the CAN frame */
+ if (cf->can_dlc > max_len)
+ goto out_delete;
+
+ /* check for checksum updates in classic CAN length only */
+ if (gwj->mod.csumfunc.crc8) {
+ if (cf->can_dlc > 8)
+ goto out_delete;
+
(*gwj->mod.csumfunc.crc8)(cf, &gwj->mod.csum.crc8);
+ }
+
+ if (gwj->mod.csumfunc.xor) {
+ if (cf->can_dlc > 8)
+ goto out_delete;
- if (gwj->mod.csumfunc.xor)
(*gwj->mod.csumfunc.xor)(cf, &gwj->mod.csum.xor);
+ }
}
/* clear the skb timestamp if not configured the other way */
@@ -436,6 +452,14 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data)
gwj->dropped_frames++;
else
gwj->handled_frames++;
+
+ return;
+
+ out_delete:
+ /* delete frame due to misconfiguration */
+ gwj->deleted_frames++;
+ kfree_skb(nskb);
+ return;
}
static inline int cgw_register_filter(struct cgw_job *gwj)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 9703924ed071..8a57bbaf7452 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2388,12 +2388,15 @@ EXPORT_SYMBOL(skb_queue_purge);
*/
void skb_rbtree_purge(struct rb_root *root)
{
- struct sk_buff *skb, *next;
+ struct rb_node *p = rb_first(root);
- rbtree_postorder_for_each_entry_safe(skb, next, root, rbnode)
- kfree_skb(skb);
+ while (p) {
+ struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode);
- *root = RB_ROOT;
+ p = rb_next(p);
+ rb_erase(&skb->rbnode, root);
+ kfree_skb(skb);
+ }
}
/**
diff --git a/net/core/sock.c b/net/core/sock.c
index 9fb1c073d0c4..8aa4a5f89572 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -732,6 +732,7 @@ int sock_setsockopt(struct socket *sock, int level, int optname,
break;
case SO_DONTROUTE:
sock_valbool_flag(sk, SOCK_LOCALROUTE, valbool);
+ sk_dst_reset(sk);
break;
case SO_BROADCAST:
sock_valbool_flag(sk, SOCK_BROADCAST, valbool);
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 3f8caf7d19b8..1ea36bf778e6 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -133,19 +133,17 @@ static void ip_cmsg_recv_security(struct msghdr *msg, struct sk_buff *skb)
static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb)
{
+ __be16 _ports[2], *ports;
struct sockaddr_in sin;
- __be16 *ports;
- int end;
-
- end = skb_transport_offset(skb) + 4;
- if (end > 0 && !pskb_may_pull(skb, end))
- return;
/* All current transport protocols have the port numbers in the
* first four bytes of the transport header and this function is
* written with this assumption in mind.
*/
- ports = (__be16 *)skb_transport_header(skb);
+ ports = skb_header_pointer(skb, skb_transport_offset(skb),
+ sizeof(_ports), &_ports);
+ if (!ports)
+ return;
sin.sin_family = AF_INET;
sin.sin_addr.s_addr = ip_hdr(skb)->daddr;
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 637a0e41b0aa..d6f2dab28d14 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -292,6 +292,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
/* Check if the address belongs to the host. */
if (addr_type == IPV6_ADDR_MAPPED) {
+ struct net_device *dev = NULL;
int chk_addr_ret;
/* Binding to v4-mapped address on a v6-only socket
@@ -302,9 +303,20 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
goto out;
}
+ rcu_read_lock();
+ if (sk->sk_bound_dev_if) {
+ dev = dev_get_by_index_rcu(net, sk->sk_bound_dev_if);
+ if (!dev) {
+ err = -ENODEV;
+ goto out_unlock;
+ }
+ }
+
/* Reproduce AF_INET checks to make the bindings consistent */
v4addr = addr->sin6_addr.s6_addr32[3];
- chk_addr_ret = inet_addr_type(net, v4addr);
+ chk_addr_ret = inet_addr_type_dev_table(net, dev, v4addr);
+ rcu_read_unlock();
+
if (!net->ipv4.sysctl_ip_nonlocal_bind &&
!(inet->freebind || inet->transparent) &&
v4addr != htonl(INADDR_ANY) &&
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 9f6e57ded338..27cdf543c539 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -290,6 +290,7 @@ void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info)
skb_reset_network_header(skb);
iph = ipv6_hdr(skb);
iph->daddr = fl6->daddr;
+ ip6_flow_hdr(iph, 0, 0);
serr = SKB_EXT_ERR(skb);
serr->ee.ee_errno = err;
@@ -657,17 +658,15 @@ void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg,
}
if (np->rxopt.bits.rxorigdstaddr) {
struct sockaddr_in6 sin6;
- __be16 *ports;
- int end;
+ __be16 _ports[2], *ports;
- end = skb_transport_offset(skb) + 4;
- if (end <= 0 || pskb_may_pull(skb, end)) {
+ ports = skb_header_pointer(skb, skb_transport_offset(skb),
+ sizeof(_ports), &_ports);
+ if (ports) {
/* All current transport protocols have the port numbers in the
* first four bytes of the transport header and this function is
* written with this assumption in mind.
*/
- ports = (__be16 *)skb_transport_header(skb);
-
sin6.sin6_family = AF_INET6;
sin6.sin6_addr = ipv6_hdr(skb)->daddr;
sin6.sin6_port = ports[1];
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 0f50977ed53b..753b2837318d 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2514,7 +2514,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
addr = saddr->sll_halen ? saddr->sll_addr : NULL;
dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex);
if (addr && dev && saddr->sll_halen < dev->addr_len)
- goto out;
+ goto out_put;
}
err = -ENXIO;
@@ -2683,7 +2683,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
addr = saddr->sll_halen ? saddr->sll_addr : NULL;
dev = dev_get_by_index(sock_net(sk), saddr->sll_ifindex);
if (addr && dev && saddr->sll_halen < dev->addr_len)
- goto out;
+ goto out_unlock;
}
err = -ENXIO;
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 7dffc97a953c..9fa0b0dc3868 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -97,11 +97,9 @@ static int sctp_inet6addr_event(struct notifier_block *this, unsigned long ev,
switch (ev) {
case NETDEV_UP:
- addr = kmalloc(sizeof(struct sctp_sockaddr_entry), GFP_ATOMIC);
+ addr = kzalloc(sizeof(*addr), GFP_ATOMIC);
if (addr) {
addr->a.v6.sin6_family = AF_INET6;
- addr->a.v6.sin6_port = 0;
- addr->a.v6.sin6_flowinfo = 0;
addr->a.v6.sin6_addr = ifa->addr;
addr->a.v6.sin6_scope_id = ifa->idev->dev->ifindex;
addr->valid = 1;
@@ -412,7 +410,6 @@ static void sctp_v6_copy_addrlist(struct list_head *addrlist,
addr = kzalloc(sizeof(*addr), GFP_ATOMIC);
if (addr) {
addr->a.v6.sin6_family = AF_INET6;
- addr->a.v6.sin6_port = 0;
addr->a.v6.sin6_addr = ifp->addr;
addr->a.v6.sin6_scope_id = dev->ifindex;
addr->valid = 1;
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index dc030efa4447..9f2f3c48b7b6 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -151,7 +151,6 @@ static void sctp_v4_copy_addrlist(struct list_head *addrlist,
addr = kzalloc(sizeof(*addr), GFP_ATOMIC);
if (addr) {
addr->a.v4.sin_family = AF_INET;
- addr->a.v4.sin_port = 0;
addr->a.v4.sin_addr.s_addr = ifa->ifa_local;
addr->valid = 1;
INIT_LIST_HEAD(&addr->list);
@@ -775,10 +774,9 @@ static int sctp_inetaddr_event(struct notifier_block *this, unsigned long ev,
switch (ev) {
case NETDEV_UP:
- addr = kmalloc(sizeof(struct sctp_sockaddr_entry), GFP_ATOMIC);
+ addr = kzalloc(sizeof(*addr), GFP_ATOMIC);
if (addr) {
addr->a.v4.sin_family = AF_INET;
- addr->a.v4.sin_port = 0;
addr->a.v4.sin_addr.s_addr = ifa->ifa_local;
addr->valid = 1;
spin_lock_bh(&net->sctp.local_addr_lock);
diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c
index cf5770d8f49a..c89626b2afff 100644
--- a/net/sunrpc/rpcb_clnt.c
+++ b/net/sunrpc/rpcb_clnt.c
@@ -772,6 +772,12 @@ void rpcb_getport_async(struct rpc_task *task)
case RPCBVERS_3:
map->r_netid = xprt->address_strings[RPC_DISPLAY_NETID];
map->r_addr = rpc_sockaddr2uaddr(sap, GFP_ATOMIC);
+ if (!map->r_addr) {
+ status = -ENOMEM;
+ dprintk("RPC: %5u %s: no memory available\n",
+ task->tk_pid, __func__);
+ goto bailout_free_args;
+ }
map->r_owner = "";
break;
case RPCBVERS_2:
@@ -794,6 +800,8 @@ void rpcb_getport_async(struct rpc_task *task)
rpc_put_task(child);
return;
+bailout_free_args:
+ kfree(map);
bailout_release_client:
rpc_release_client(rpcb_clnt);
bailout_nofree:
diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index f86c6555a539..e9653c42cdd1 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -87,6 +87,11 @@ static int tipc_skb_tailroom(struct sk_buff *skb)
return limit;
}
+static inline int TLV_GET_DATA_LEN(struct tlv_desc *tlv)
+{
+ return TLV_GET_LEN(tlv) - TLV_SPACE(0);
+}
+
static int tipc_add_tlv(struct sk_buff *skb, u16 type, void *data, u16 len)
{
struct tlv_desc *tlv = (struct tlv_desc *)skb_tail_pointer(skb);
@@ -166,6 +171,11 @@ static struct sk_buff *tipc_get_err_tlv(char *str)
return buf;
}
+static inline bool string_is_valid(char *s, int len)
+{
+ return memchr(s, '\0', len) ? true : false;
+}
+
static int __tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd,
struct tipc_nl_compat_msg *msg,
struct sk_buff *arg)
@@ -364,6 +374,7 @@ static int tipc_nl_compat_bearer_enable(struct tipc_nl_compat_cmd_doit *cmd,
struct nlattr *prop;
struct nlattr *bearer;
struct tipc_bearer_config *b;
+ int len;
b = (struct tipc_bearer_config *)TLV_DATA(msg->req);
@@ -371,6 +382,10 @@ static int tipc_nl_compat_bearer_enable(struct tipc_nl_compat_cmd_doit *cmd,
if (!bearer)
return -EMSGSIZE;
+ len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_BEARER_NAME);
+ if (!string_is_valid(b->name, len))
+ return -EINVAL;
+
if (nla_put_string(skb, TIPC_NLA_BEARER_NAME, b->name))
return -EMSGSIZE;
@@ -396,6 +411,7 @@ static int tipc_nl_compat_bearer_disable(struct tipc_nl_compat_cmd_doit *cmd,
{
char *name;
struct nlattr *bearer;
+ int len;
name = (char *)TLV_DATA(msg->req);
@@ -403,6 +419,10 @@ static int tipc_nl_compat_bearer_disable(struct tipc_nl_compat_cmd_doit *cmd,
if (!bearer)
return -EMSGSIZE;
+ len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_BEARER_NAME);
+ if (!string_is_valid(name, len))
+ return -EINVAL;
+
if (nla_put_string(skb, TIPC_NLA_BEARER_NAME, name))
return -EMSGSIZE;
@@ -462,6 +482,7 @@ static int tipc_nl_compat_link_stat_dump(struct tipc_nl_compat_msg *msg,
struct nlattr *link[TIPC_NLA_LINK_MAX + 1];
struct nlattr *prop[TIPC_NLA_PROP_MAX + 1];
struct nlattr *stats[TIPC_NLA_STATS_MAX + 1];
+ int len;
nla_parse_nested(link, TIPC_NLA_LINK_MAX, attrs[TIPC_NLA_LINK], NULL);
@@ -472,6 +493,11 @@ static int tipc_nl_compat_link_stat_dump(struct tipc_nl_compat_msg *msg,
NULL);
name = (char *)TLV_DATA(msg->req);
+
+ len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_LINK_NAME);
+ if (!string_is_valid(name, len))
+ return -EINVAL;
+
if (strcmp(name, nla_data(link[TIPC_NLA_LINK_NAME])) != 0)
return 0;
@@ -605,6 +631,7 @@ static int tipc_nl_compat_media_set(struct sk_buff *skb,
struct nlattr *prop;
struct nlattr *media;
struct tipc_link_config *lc;
+ int len;
lc = (struct tipc_link_config *)TLV_DATA(msg->req);
@@ -612,6 +639,10 @@ static int tipc_nl_compat_media_set(struct sk_buff *skb,
if (!media)
return -EMSGSIZE;
+ len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_MEDIA_NAME);
+ if (!string_is_valid(lc->name, len))
+ return -EINVAL;
+
if (nla_put_string(skb, TIPC_NLA_MEDIA_NAME, lc->name))
return -EMSGSIZE;
@@ -632,6 +663,7 @@ static int tipc_nl_compat_bearer_set(struct sk_buff *skb,
struct nlattr *prop;
struct nlattr *bearer;
struct tipc_link_config *lc;
+ int len;
lc = (struct tipc_link_config *)TLV_DATA(msg->req);
@@ -639,6 +671,10 @@ static int tipc_nl_compat_bearer_set(struct sk_buff *skb,
if (!bearer)
return -EMSGSIZE;
+ len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_MEDIA_NAME);
+ if (!string_is_valid(lc->name, len))
+ return -EINVAL;
+
if (nla_put_string(skb, TIPC_NLA_BEARER_NAME, lc->name))
return -EMSGSIZE;
@@ -687,9 +723,14 @@ static int tipc_nl_compat_link_set(struct tipc_nl_compat_cmd_doit *cmd,
struct tipc_link_config *lc;
struct tipc_bearer *bearer;
struct tipc_media *media;
+ int len;
lc = (struct tipc_link_config *)TLV_DATA(msg->req);
+ len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_LINK_NAME);
+ if (!string_is_valid(lc->name, len))
+ return -EINVAL;
+
media = tipc_media_find(lc->name);
if (media) {
cmd->doit = &tipc_nl_media_set;
@@ -711,6 +752,7 @@ static int tipc_nl_compat_link_reset_stats(struct tipc_nl_compat_cmd_doit *cmd,
{
char *name;
struct nlattr *link;
+ int len;
name = (char *)TLV_DATA(msg->req);
@@ -718,6 +760,10 @@ static int tipc_nl_compat_link_reset_stats(struct tipc_nl_compat_cmd_doit *cmd,
if (!link)
return -EMSGSIZE;
+ len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_LINK_NAME);
+ if (!string_is_valid(name, len))
+ return -EINVAL;
+
if (nla_put_string(skb, TIPC_NLA_LINK_NAME, name))
return -EMSGSIZE;
@@ -739,6 +785,8 @@ static int tipc_nl_compat_name_table_dump_header(struct tipc_nl_compat_msg *msg)
};
ntq = (struct tipc_name_table_query *)TLV_DATA(msg->req);
+ if (TLV_GET_DATA_LEN(msg->req) < sizeof(struct tipc_name_table_query))
+ return -EINVAL;
depth = ntohl(ntq->depth);
@@ -1117,7 +1165,7 @@ static int tipc_nl_compat_recv(struct sk_buff *skb, struct genl_info *info)
}
len = nlmsg_attrlen(req_nlh, GENL_HDRLEN + TIPC_GENL_HDRLEN);
- if (len && !TLV_OK(msg.req, len)) {
+ if (!len || !TLV_OK(msg.req, len)) {
msg.rep = tipc_get_err_tlv(TIPC_CFG_NOT_SUPPORTED);
err = -EOPNOTSUPP;
goto send;
diff --git a/scripts/kconfig/zconf.l b/scripts/kconfig/zconf.l
index c410d257da06..0c7800112ff5 100644
--- a/scripts/kconfig/zconf.l
+++ b/scripts/kconfig/zconf.l
@@ -71,7 +71,7 @@ static void warn_ignored_character(char chr)
{
fprintf(stderr,
"%s:%d:warning: ignoring unsupported character '%c'\n",
- zconf_curname(), zconf_lineno(), chr);
+ current_file->name, yylineno, chr);
}
%}
@@ -191,6 +191,8 @@ n [A-Za-z0-9_-]
}
<<EOF>> {
BEGIN(INITIAL);
+ yylval.string = text;
+ return T_WORD_QUOTE;
}
}
diff --git a/security/security.c b/security/security.c
index 46f405ce6b0f..0dde287db5c5 100644
--- a/security/security.c
+++ b/security/security.c
@@ -861,6 +861,13 @@ int security_cred_alloc_blank(struct cred *cred, gfp_t gfp)
void security_cred_free(struct cred *cred)
{
+ /*
+ * There is a failure case in prepare_creds() that
+ * may result in a call here with ->security being NULL.
+ */
+ if (unlikely(cred->security == NULL))
+ return;
+
call_void_hook(cred_free, cred);
}
diff --git a/security/selinux/ss/policydb.c b/security/selinux/ss/policydb.c
index 992a31530825..965a55eacaba 100644
--- a/security/selinux/ss/policydb.c
+++ b/security/selinux/ss/policydb.c
@@ -726,7 +726,8 @@ static int sens_destroy(void *key, void *datum, void *p)
kfree(key);
if (datum) {
levdatum = datum;
- ebitmap_destroy(&levdatum->level->cat);
+ if (levdatum->level)
+ ebitmap_destroy(&levdatum->level->cat);
kfree(levdatum->level);
}
kfree(datum);
diff --git a/security/yama/yama_lsm.c b/security/yama/yama_lsm.c
index cb6ed10816d4..0a8808954bd8 100644
--- a/security/yama/yama_lsm.c
+++ b/security/yama/yama_lsm.c
@@ -288,7 +288,9 @@ static int yama_ptrace_access_check(struct task_struct *child,
break;
case YAMA_SCOPE_RELATIONAL:
rcu_read_lock();
- if (!task_is_descendant(current, child) &&
+ if (!pid_alive(child))
+ rc = -EPERM;
+ if (!rc && !task_is_descendant(current, child) &&
!ptracer_exception_found(current, child) &&
!ns_capable(__task_cred(child)->user_ns, CAP_SYS_PTRACE))
rc = -EPERM;
diff --git a/sound/firewire/bebob/bebob.c b/sound/firewire/bebob/bebob.c
index 091290d1f3ea..1898fa4228ad 100644
--- a/sound/firewire/bebob/bebob.c
+++ b/sound/firewire/bebob/bebob.c
@@ -382,7 +382,7 @@ static const struct ieee1394_device_id bebob_id_table[] = {
/* Apogee Electronics, DA/AD/DD-16X (X-FireWire card) */
SND_BEBOB_DEV_ENTRY(VEN_APOGEE, 0x00010048, &spec_normal),
/* Apogee Electronics, Ensemble */
- SND_BEBOB_DEV_ENTRY(VEN_APOGEE, 0x00001eee, &spec_normal),
+ SND_BEBOB_DEV_ENTRY(VEN_APOGEE, 0x01eeee, &spec_normal),
/* ESI, Quatafire610 */
SND_BEBOB_DEV_ENTRY(VEN_ESI, 0x00010064, &spec_normal),
/* AcousticReality, eARMasterOne */
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index c53f78767568..df21da796fa7 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -471,10 +471,21 @@ static int intel_pt_validate_config(struct perf_pmu *intel_pt_pmu,
struct perf_evsel *evsel)
{
int err;
+ char c;
if (!evsel)
return 0;
+ /*
+ * If supported, force pass-through config term (pt=1) even if user
+ * sets pt=0, which avoids senseless kernel errors.
+ */
+ if (perf_pmu__scan_file(intel_pt_pmu, "format/pt", "%c", &c) == 1 &&
+ !(evsel->attr.config & 1)) {
+ pr_warning("pt=0 doesn't make sense, forcing pt=1\n");
+ evsel->attr.config |= 1;
+ }
+
err = intel_pt_val_config_term(intel_pt_pmu, "caps/cycle_thresholds",
"cyc_thresh", "caps/psb_cyc",
evsel->attr.config);
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index e81dfb2e239c..9351738df703 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1903,7 +1903,7 @@ restart:
if (!name_only && strlen(syms->alias))
snprintf(name, MAX_NAME_LEN, "%s OR %s", syms->symbol, syms->alias);
else
- strncpy(name, syms->symbol, MAX_NAME_LEN);
+ strlcpy(name, syms->symbol, MAX_NAME_LEN);
evt_list[evt_i] = strdup(name);
if (evt_list[evt_i] == NULL)
diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c
index eec6c1149f44..132878d4847a 100644
--- a/tools/perf/util/svghelper.c
+++ b/tools/perf/util/svghelper.c
@@ -333,7 +333,7 @@ static char *cpu_model(void)
if (file) {
while (fgets(buf, 255, file)) {
if (strstr(buf, "model name")) {
- strncpy(cpu_m, &buf[13], 255);
+ strlcpy(cpu_m, &buf[13], 255);
break;
}
}
^ permalink raw reply related [flat|nested] 2+ messages in thread
end of thread, other threads:[~2019-01-26 9:30 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2019-01-26 9:29 Linux 4.4.172 Greg KH
2019-01-26 9:29 ` Greg KH
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).