diff options
111 files changed, 9495 insertions, 5212 deletions
diff --git a/Documentation/filesystems/f2fs.txt b/Documentation/filesystems/f2fs.txt index b102b436563e..753dd4f96afe 100644 --- a/Documentation/filesystems/f2fs.txt +++ b/Documentation/filesystems/f2fs.txt @@ -102,14 +102,16 @@ background_gc=%s Turn on/off cleaning operations, namely garbage collection, triggered in background when I/O subsystem is idle. If background_gc=on, it will turn on the garbage collection and if background_gc=off, garbage collection - will be truned off. If background_gc=sync, it will turn + will be turned off. If background_gc=sync, it will turn on synchronous garbage collection running in background. Default value for this option is on. So garbage collection is on by default. disable_roll_forward Disable the roll-forward recovery routine norecovery Disable the roll-forward recovery routine, mounted read- only (i.e., -o ro,disable_roll_forward) -discard Issue discard/TRIM commands when a segment is cleaned. +discard/nodiscard Enable/disable real-time discard in f2fs, if discard is + enabled, f2fs will issue discard/TRIM commands when a + segment is cleaned. no_heap Disable heap-style segment allocation which finds free segments for data from the beginning of main area, while for node from the end of main area. @@ -129,6 +131,7 @@ inline_dentry Enable the inline dir feature: data in new created directory entries can be written into inode block. The space of inode block which is used to store inline dentries is limited to ~3.4k. +noinline_dentry Diable the inline dentry feature. flush_merge Merge concurrent cache_flush commands as much as possible to eliminate redundant command issues. If the underlying device handles the cache_flush command relatively slowly, @@ -145,10 +148,15 @@ extent_cache Enable an extent cache based on rb-tree, it can cache as many as extent which map between contiguous logical address and physical address per inode, resulting in increasing the cache hit ratio. Set by default. -noextent_cache Diable an extent cache based on rb-tree explicitly, see +noextent_cache Disable an extent cache based on rb-tree explicitly, see the above extent_cache mount option. noinline_data Disable the inline data feature, inline data feature is enabled by default. +data_flush Enable data flushing before checkpoint in order to + persist data of regular and symlink. +mode=%s Control block allocation mode which supports "adaptive" + and "lfs". In "lfs" mode, there should be no random + writes towards main area. ================================================================================ DEBUGFS ENTRIES @@ -192,7 +200,7 @@ Files in /sys/fs/f2fs/<devname> policy for garbage collection. Setting gc_idle = 0 (default) will disable this option. Setting gc_idle = 1 will select the Cost Benefit approach - & setting gc_idle = 2 will select the greedy aproach. + & setting gc_idle = 2 will select the greedy approach. reclaim_segments This parameter controls the number of prefree segments to be reclaimed. If the number of prefree @@ -298,7 +306,7 @@ The dump.f2fs shows the information of specific inode and dumps SSA and SIT to file. Each file is dump_ssa and dump_sit. The dump.f2fs is used to debug on-disk data structures of the f2fs filesystem. -It shows on-disk inode information reconized by a given inode number, and is +It shows on-disk inode information recognized by a given inode number, and is able to dump all the SSA and SIT entries into predefined files, ./dump_ssa and ./dump_sit respectively. @@ -1,6 +1,6 @@ VERSION = 4 PATCHLEVEL = 4 -SUBLEVEL = 88 +SUBLEVEL = 89 EXTRAVERSION = NAME = Blurry Fish Butt diff --git a/android/configs/README b/android/configs/README deleted file mode 100644 index 8798731f8904..000000000000 --- a/android/configs/README +++ /dev/null @@ -1,15 +0,0 @@ -The files in this directory are meant to be used as a base for an Android -kernel config. All devices should have the options in android-base.cfg enabled. -While not mandatory, the options in android-recommended.cfg enable advanced -Android features. - -Assuming you already have a minimalist defconfig for your device, a possible -way to enable these options would be: - - ARCH=<arch> scripts/kconfig/merge_config.sh <path_to>/<device>_defconfig android/configs/android-base.cfg android/configs/android-recommended.cfg - -This will generate a .config that can then be used to save a new defconfig or -compile a new kernel with Android features enabled. - -Because there is no tool to consistently generate these config fragments, -lets keep them alphabetically sorted instead of random. diff --git a/android/configs/android-base-arm64.cfg b/android/configs/android-base-arm64.cfg deleted file mode 100644 index 43f23d6b5391..000000000000 --- a/android/configs/android-base-arm64.cfg +++ /dev/null @@ -1,5 +0,0 @@ -# KEEP ALPHABETICALLY SORTED -CONFIG_ARMV8_DEPRECATED=y -CONFIG_CP15_BARRIER_EMULATION=y -CONFIG_SETEND_EMULATION=y -CONFIG_SWP_EMULATION=y diff --git a/android/configs/android-base.cfg b/android/configs/android-base.cfg deleted file mode 100644 index d354338540bd..000000000000 --- a/android/configs/android-base.cfg +++ /dev/null @@ -1,165 +0,0 @@ -# KEEP ALPHABETICALLY SORTED -# CONFIG_DEVKMEM is not set -# CONFIG_DEVMEM is not set -# CONFIG_FHANDLE is not set -# CONFIG_INET_LRO is not set -# CONFIG_NFSD is not set -# CONFIG_NFS_FS is not set -# CONFIG_OABI_COMPAT is not set -# CONFIG_SYSVIPC is not set -# CONFIG_USELIB is not set -CONFIG_ANDROID=y -CONFIG_ANDROID_BINDER_IPC=y -CONFIG_ANDROID_BINDER_DEVICES=binder,hwbinder,vndbinder -CONFIG_ANDROID_LOW_MEMORY_KILLER=y -CONFIG_ASHMEM=y -CONFIG_AUDIT=y -CONFIG_BLK_DEV_INITRD=y -CONFIG_CGROUPS=y -CONFIG_CGROUP_CPUACCT=y -CONFIG_CGROUP_FREEZER=y -CONFIG_CGROUP_SCHED=y -CONFIG_DEFAULT_SECURITY_SELINUX=y -CONFIG_EMBEDDED=y -CONFIG_FB=y -CONFIG_HARDENED_USERCOPY=y -CONFIG_HIGH_RES_TIMERS=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_INET6_AH=y -CONFIG_INET6_ESP=y -CONFIG_INET6_IPCOMP=y -CONFIG_INET=y -CONFIG_INET_DIAG_DESTROY=y -CONFIG_INET_ESP=y -CONFIG_INET_XFRM_MODE_TUNNEL=y -CONFIG_IP6_NF_FILTER=y -CONFIG_IP6_NF_IPTABLES=y -CONFIG_IP6_NF_MANGLE=y -CONFIG_IP6_NF_MATCH_RPFILTER=y -CONFIG_IP6_NF_RAW=y -CONFIG_IP6_NF_TARGET_REJECT=y -CONFIG_IPV6=y -CONFIG_IPV6_MIP6=y -CONFIG_IPV6_MULTIPLE_TABLES=y -CONFIG_IPV6_OPTIMISTIC_DAD=y -CONFIG_IPV6_ROUTER_PREF=y -CONFIG_IPV6_ROUTE_INFO=y -CONFIG_IP_ADVANCED_ROUTER=y -CONFIG_IP_MULTICAST=y -CONFIG_IP_MULTIPLE_TABLES=y -CONFIG_IP_NF_ARPFILTER=y -CONFIG_IP_NF_ARPTABLES=y -CONFIG_IP_NF_ARP_MANGLE=y -CONFIG_IP_NF_FILTER=y -CONFIG_IP_NF_IPTABLES=y -CONFIG_IP_NF_MANGLE=y -CONFIG_IP_NF_MATCH_AH=y -CONFIG_IP_NF_MATCH_ECN=y -CONFIG_IP_NF_MATCH_TTL=y -CONFIG_IP_NF_NAT=y -CONFIG_IP_NF_RAW=y -CONFIG_IP_NF_SECURITY=y -CONFIG_IP_NF_TARGET_MASQUERADE=y -CONFIG_IP_NF_TARGET_NETMAP=y -CONFIG_IP_NF_TARGET_REDIRECT=y -CONFIG_IP_NF_TARGET_REJECT=y -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -CONFIG_MODVERSIONS=y -CONFIG_NET=y -CONFIG_NETDEVICES=y -CONFIG_NETFILTER=y -CONFIG_NETFILTER_XT_MATCH_COMMENT=y -CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=y -CONFIG_NETFILTER_XT_MATCH_CONNMARK=y -CONFIG_NETFILTER_XT_MATCH_CONNTRACK=y -CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=y -CONFIG_NETFILTER_XT_MATCH_HELPER=y -CONFIG_NETFILTER_XT_MATCH_IPRANGE=y -CONFIG_NETFILTER_XT_MATCH_LENGTH=y -CONFIG_NETFILTER_XT_MATCH_LIMIT=y -CONFIG_NETFILTER_XT_MATCH_MAC=y -CONFIG_NETFILTER_XT_MATCH_MARK=y -CONFIG_NETFILTER_XT_MATCH_PKTTYPE=y -CONFIG_NETFILTER_XT_MATCH_POLICY=y -CONFIG_NETFILTER_XT_MATCH_QTAGUID=y -CONFIG_NETFILTER_XT_MATCH_QUOTA2=y -CONFIG_NETFILTER_XT_MATCH_QUOTA=y -CONFIG_NETFILTER_XT_MATCH_SOCKET=y -CONFIG_NETFILTER_XT_MATCH_STATE=y -CONFIG_NETFILTER_XT_MATCH_STATISTIC=y -CONFIG_NETFILTER_XT_MATCH_STRING=y -CONFIG_NETFILTER_XT_MATCH_TIME=y -CONFIG_NETFILTER_XT_MATCH_U32=y -CONFIG_NETFILTER_XT_TARGET_CLASSIFY=y -CONFIG_NETFILTER_XT_TARGET_CONNMARK=y -CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=y -CONFIG_NETFILTER_XT_TARGET_IDLETIMER=y -CONFIG_NETFILTER_XT_TARGET_MARK=y -CONFIG_NETFILTER_XT_TARGET_NFLOG=y -CONFIG_NETFILTER_XT_TARGET_NFQUEUE=y -CONFIG_NETFILTER_XT_TARGET_SECMARK=y -CONFIG_NETFILTER_XT_TARGET_TCPMSS=y -CONFIG_NETFILTER_XT_TARGET_TPROXY=y -CONFIG_NETFILTER_XT_TARGET_TRACE=y -CONFIG_NET_CLS_ACT=y -CONFIG_NET_CLS_U32=y -CONFIG_NET_EMATCH=y -CONFIG_NET_EMATCH_U32=y -CONFIG_NET_KEY=y -CONFIG_NET_SCHED=y -CONFIG_NET_SCH_HTB=y -CONFIG_NF_CONNTRACK=y -CONFIG_NF_CONNTRACK_AMANDA=y -CONFIG_NF_CONNTRACK_EVENTS=y -CONFIG_NF_CONNTRACK_FTP=y -CONFIG_NF_CONNTRACK_H323=y -CONFIG_NF_CONNTRACK_IPV4=y -CONFIG_NF_CONNTRACK_IPV6=y -CONFIG_NF_CONNTRACK_IRC=y -CONFIG_NF_CONNTRACK_NETBIOS_NS=y -CONFIG_NF_CONNTRACK_PPTP=y -CONFIG_NF_CONNTRACK_SANE=y -CONFIG_NF_CONNTRACK_SECMARK=y -CONFIG_NF_CONNTRACK_TFTP=y -CONFIG_NF_CT_NETLINK=y -CONFIG_NF_CT_PROTO_DCCP=y -CONFIG_NF_CT_PROTO_SCTP=y -CONFIG_NF_CT_PROTO_UDPLITE=y -CONFIG_NF_NAT=y -CONFIG_NO_HZ=y -CONFIG_PACKET=y -CONFIG_PM_AUTOSLEEP=y -CONFIG_PM_WAKELOCKS=y -CONFIG_PPP=y -CONFIG_PPPOLAC=y -CONFIG_PPPOPNS=y -CONFIG_PPP_BSDCOMP=y -CONFIG_PPP_DEFLATE=y -CONFIG_PPP_MPPE=y -CONFIG_PREEMPT=y -CONFIG_PROFILING=y -CONFIG_RANDOMIZE_BASE=y -CONFIG_RTC_CLASS=y -CONFIG_RT_GROUP_SCHED=y -CONFIG_SECCOMP=y -CONFIG_SECURITY=y -CONFIG_SECURITY_NETWORK=y -CONFIG_SECURITY_PERF_EVENTS_RESTRICT=y -CONFIG_SECURITY_SELINUX=y -CONFIG_STAGING=y -CONFIG_SYNC=y -CONFIG_TUN=y -CONFIG_UID_SYS_STATS=y -CONFIG_UNIX=y -CONFIG_USB_CONFIGFS=y -CONFIG_USB_CONFIGFS_F_ACC=y -CONFIG_USB_CONFIGFS_F_AUDIO_SRC=y -CONFIG_USB_CONFIGFS_F_FS=y -CONFIG_USB_CONFIGFS_F_MIDI=y -CONFIG_USB_CONFIGFS_F_MTP=y -CONFIG_USB_CONFIGFS_F_PTP=y -CONFIG_USB_CONFIGFS_UEVENT=y -CONFIG_USB_GADGET=y -CONFIG_XFRM_USER=y diff --git a/android/configs/android-recommended.cfg b/android/configs/android-recommended.cfg deleted file mode 100644 index 6550d0423f50..000000000000 --- a/android/configs/android-recommended.cfg +++ /dev/null @@ -1,140 +0,0 @@ -# KEEP ALPHABETICALLY SORTED -# CONFIG_AIO is not set -# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set -# CONFIG_INPUT_MOUSE is not set -# CONFIG_LEGACY_PTYS is not set -# CONFIG_NF_CONNTRACK_SIP is not set -# CONFIG_PM_WAKELOCKS_GC is not set -# CONFIG_VT is not set -CONFIG_ANDROID_TIMED_GPIO=y -CONFIG_ARM64_SW_TTBR0_PAN=y -CONFIG_ARM_KERNMEM_PERMS=y -CONFIG_ARM64_SW_TTBR0_PAN=y -CONFIG_BACKLIGHT_LCD_SUPPORT=y -CONFIG_BLK_DEV_DM=y -CONFIG_BLK_DEV_LOOP=y -CONFIG_BLK_DEV_RAM=y -CONFIG_BLK_DEV_RAM_SIZE=8192 -CONFIG_CC_STACKPROTECTOR_STRONG=y -CONFIG_COMPACTION=y -CONFIG_CPU_SW_DOMAIN_PAN=y -CONFIG_DEBUG_RODATA=y -CONFIG_DM_CRYPT=y -CONFIG_DM_UEVENT=y -CONFIG_DM_VERITY=y -CONFIG_DM_VERITY_FEC=y -CONFIG_DRAGONRISE_FF=y -CONFIG_ENABLE_DEFAULT_TRACERS=y -CONFIG_EXT4_FS=y -CONFIG_EXT4_FS_SECURITY=y -CONFIG_FUSE_FS=y -CONFIG_GREENASIA_FF=y -CONFIG_HIDRAW=y -CONFIG_HID_A4TECH=y -CONFIG_HID_ACRUX=y -CONFIG_HID_ACRUX_FF=y -CONFIG_HID_APPLE=y -CONFIG_HID_BELKIN=y -CONFIG_HID_CHERRY=y -CONFIG_HID_CHICONY=y -CONFIG_HID_CYPRESS=y -CONFIG_HID_DRAGONRISE=y -CONFIG_HID_ELECOM=y -CONFIG_HID_EMS_FF=y -CONFIG_HID_EZKEY=y -CONFIG_HID_GREENASIA=y -CONFIG_HID_GYRATION=y -CONFIG_HID_HOLTEK=y -CONFIG_HID_KENSINGTON=y -CONFIG_HID_KEYTOUCH=y -CONFIG_HID_KYE=y -CONFIG_HID_LCPOWER=y -CONFIG_HID_LOGITECH=y -CONFIG_HID_LOGITECH_DJ=y -CONFIG_HID_MAGICMOUSE=y -CONFIG_HID_MICROSOFT=y -CONFIG_HID_MONTEREY=y -CONFIG_HID_MULTITOUCH=y -CONFIG_HID_NTRIG=y -CONFIG_HID_ORTEK=y -CONFIG_HID_PANTHERLORD=y -CONFIG_HID_PETALYNX=y -CONFIG_HID_PICOLCD=y -CONFIG_HID_PRIMAX=y -CONFIG_HID_PRODIKEYS=y -CONFIG_HID_ROCCAT=y -CONFIG_HID_SAITEK=y -CONFIG_HID_SAMSUNG=y -CONFIG_HID_SMARTJOYPLUS=y -CONFIG_HID_SONY=y -CONFIG_HID_SPEEDLINK=y -CONFIG_HID_SUNPLUS=y -CONFIG_HID_THRUSTMASTER=y -CONFIG_HID_TIVO=y -CONFIG_HID_TOPSEED=y -CONFIG_HID_TWINHAN=y -CONFIG_HID_UCLOGIC=y -CONFIG_HID_WACOM=y -CONFIG_HID_WALTOP=y -CONFIG_HID_WIIMOTE=y -CONFIG_HID_ZEROPLUS=y -CONFIG_HID_ZYDACRON=y -CONFIG_INPUT_EVDEV=y -CONFIG_INPUT_GPIO=y -CONFIG_INPUT_JOYSTICK=y -CONFIG_INPUT_KEYCHORD=y -CONFIG_INPUT_KEYRESET=y -CONFIG_INPUT_MISC=y -CONFIG_INPUT_TABLET=y -CONFIG_INPUT_UINPUT=y -CONFIG_ION=y -CONFIG_JOYSTICK_XPAD=y -CONFIG_JOYSTICK_XPAD_FF=y -CONFIG_JOYSTICK_XPAD_LEDS=y -CONFIG_KALLSYMS_ALL=y -CONFIG_KSM=y -CONFIG_LOGIG940_FF=y -CONFIG_LOGIRUMBLEPAD2_FF=y -CONFIG_LOGITECH_FF=y -CONFIG_MD=y -CONFIG_MEDIA_SUPPORT=y -CONFIG_MEMORY_STATE_TIME=y -CONFIG_MSDOS_FS=y -CONFIG_PANIC_TIMEOUT=5 -CONFIG_PANTHERLORD_FF=y -CONFIG_PERF_EVENTS=y -CONFIG_PM_DEBUG=y -CONFIG_PM_RUNTIME=y -CONFIG_PM_WAKELOCKS_LIMIT=0 -CONFIG_POWER_SUPPLY=y -CONFIG_PSTORE=y -CONFIG_PSTORE_CONSOLE=y -CONFIG_PSTORE_RAM=y -CONFIG_QFMT_V2=y -CONFIG_QUOTA=y -CONFIG_QUOTACTL=y -CONFIG_QUOTA_NETLINK_INTERFACE=y -CONFIG_QUOTA_TREE=y -CONFIG_SCHEDSTATS=y -CONFIG_SMARTJOYPLUS_FF=y -CONFIG_SND=y -CONFIG_SOUND=y -CONFIG_SUSPEND_TIME=y -CONFIG_TABLET_USB_ACECAD=y -CONFIG_TABLET_USB_AIPTEK=y -CONFIG_TABLET_USB_GTCO=y -CONFIG_TABLET_USB_HANWANG=y -CONFIG_TABLET_USB_KBTAB=y -CONFIG_TASKSTATS=y -CONFIG_TASK_DELAY_ACCT=y -CONFIG_TASK_IO_ACCOUNTING=y -CONFIG_TASK_XACCT=y -CONFIG_TIMER_STATS=y -CONFIG_TMPFS=y -CONFIG_TMPFS_POSIX_ACL=y -CONFIG_UHID=y -CONFIG_USB_ANNOUNCE_NEW_DEVICES=y -CONFIG_USB_EHCI_HCD=y -CONFIG_USB_HIDDEV=y -CONFIG_USB_USBNET=y -CONFIG_VFAT_FS=y diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S index 2efb0625331d..db1eee5fe502 100644 --- a/arch/arc/kernel/entry.S +++ b/arch/arc/kernel/entry.S @@ -104,6 +104,12 @@ ENTRY(EV_MachineCheck) lr r0, [efa] mov r1, sp + ; hardware auto-disables MMU, re-enable it to allow kernel vaddr + ; access for say stack unwinding of modules for crash dumps + lr r3, [ARC_REG_PID] + or r3, r3, MMU_ENABLE + sr r3, [ARC_REG_PID] + lsr r3, r2, 8 bmsk r3, r3, 7 brne r3, ECR_C_MCHK_DUP_TLB, 1f diff --git a/arch/arc/mm/tlb.c b/arch/arc/mm/tlb.c index daf2bf52b984..97e9582dcf99 100644 --- a/arch/arc/mm/tlb.c +++ b/arch/arc/mm/tlb.c @@ -885,9 +885,6 @@ void do_tlb_overlap_fault(unsigned long cause, unsigned long address, local_irq_save(flags); - /* re-enable the MMU */ - write_aux_reg(ARC_REG_PID, MMU_ENABLE | read_aux_reg(ARC_REG_PID)); - /* loop thru all sets of TLB */ for (set = 0; set < mmu->sets; set++) { diff --git a/arch/mips/math-emu/dp_fmax.c b/arch/mips/math-emu/dp_fmax.c index fd71b8daaaf2..5bec64f2884e 100644 --- a/arch/mips/math-emu/dp_fmax.c +++ b/arch/mips/math-emu/dp_fmax.c @@ -47,14 +47,26 @@ union ieee754dp ieee754dp_fmax(union ieee754dp x, union ieee754dp y) case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF): return ieee754dp_nanxcpt(x); - /* numbers are preferred to NaNs */ + /* + * Quiet NaN handling + */ + + /* + * The case of both inputs quiet NaNs + */ + case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN): + return x; + + /* + * The cases of exactly one input quiet NaN (numbers + * are here preferred as returned values to NaNs) + */ case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN): return x; - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM): @@ -80,9 +92,7 @@ union ieee754dp ieee754dp_fmax(union ieee754dp x, union ieee754dp y) return ys ? x : y; case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO): - if (xs == ys) - return x; - return ieee754dp_zero(1); + return ieee754dp_zero(xs & ys); case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): DPDNORMX; @@ -106,16 +116,32 @@ union ieee754dp ieee754dp_fmax(union ieee754dp x, union ieee754dp y) else if (xs < ys) return x; - /* Compare exponent */ - if (xe > ye) - return x; - else if (xe < ye) - return y; + /* Signs of inputs are equal, let's compare exponents */ + if (xs == 0) { + /* Inputs are both positive */ + if (xe > ye) + return x; + else if (xe < ye) + return y; + } else { + /* Inputs are both negative */ + if (xe > ye) + return y; + else if (xe < ye) + return x; + } - /* Compare mantissa */ + /* Signs and exponents of inputs are equal, let's compare mantissas */ + if (xs == 0) { + /* Inputs are both positive, with equal signs and exponents */ + if (xm <= ym) + return y; + return x; + } + /* Inputs are both negative, with equal signs and exponents */ if (xm <= ym) - return y; - return x; + return x; + return y; } union ieee754dp ieee754dp_fmaxa(union ieee754dp x, union ieee754dp y) @@ -147,14 +173,26 @@ union ieee754dp ieee754dp_fmaxa(union ieee754dp x, union ieee754dp y) case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF): return ieee754dp_nanxcpt(x); - /* numbers are preferred to NaNs */ + /* + * Quiet NaN handling + */ + + /* + * The case of both inputs quiet NaNs + */ + case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN): + return x; + + /* + * The cases of exactly one input quiet NaN (numbers + * are here preferred as returned values to NaNs) + */ case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN): return x; - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM): @@ -164,6 +202,9 @@ union ieee754dp ieee754dp_fmaxa(union ieee754dp x, union ieee754dp y) /* * Infinity and zero handling */ + case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF): + return ieee754dp_inf(xs & ys); + case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO): case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM): case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM): @@ -171,7 +212,6 @@ union ieee754dp ieee754dp_fmaxa(union ieee754dp x, union ieee754dp y) case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO): return x; - case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF): case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF): case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF): case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF): @@ -180,9 +220,7 @@ union ieee754dp ieee754dp_fmaxa(union ieee754dp x, union ieee754dp y) return y; case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO): - if (xs == ys) - return x; - return ieee754dp_zero(1); + return ieee754dp_zero(xs & ys); case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): DPDNORMX; @@ -207,7 +245,11 @@ union ieee754dp ieee754dp_fmaxa(union ieee754dp x, union ieee754dp y) return y; /* Compare mantissa */ - if (xm <= ym) + if (xm < ym) return y; - return x; + else if (xm > ym) + return x; + else if (xs == 0) + return x; + return y; } diff --git a/arch/mips/math-emu/dp_fmin.c b/arch/mips/math-emu/dp_fmin.c index c1072b0dfb95..a287b23818d8 100644 --- a/arch/mips/math-emu/dp_fmin.c +++ b/arch/mips/math-emu/dp_fmin.c @@ -47,14 +47,26 @@ union ieee754dp ieee754dp_fmin(union ieee754dp x, union ieee754dp y) case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF): return ieee754dp_nanxcpt(x); - /* numbers are preferred to NaNs */ + /* + * Quiet NaN handling + */ + + /* + * The case of both inputs quiet NaNs + */ + case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN): + return x; + + /* + * The cases of exactly one input quiet NaN (numbers + * are here preferred as returned values to NaNs) + */ case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN): return x; - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM): @@ -80,9 +92,7 @@ union ieee754dp ieee754dp_fmin(union ieee754dp x, union ieee754dp y) return ys ? y : x; case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO): - if (xs == ys) - return x; - return ieee754dp_zero(1); + return ieee754dp_zero(xs | ys); case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): DPDNORMX; @@ -106,16 +116,32 @@ union ieee754dp ieee754dp_fmin(union ieee754dp x, union ieee754dp y) else if (xs < ys) return y; - /* Compare exponent */ - if (xe > ye) - return y; - else if (xe < ye) - return x; + /* Signs of inputs are the same, let's compare exponents */ + if (xs == 0) { + /* Inputs are both positive */ + if (xe > ye) + return y; + else if (xe < ye) + return x; + } else { + /* Inputs are both negative */ + if (xe > ye) + return x; + else if (xe < ye) + return y; + } - /* Compare mantissa */ + /* Signs and exponents of inputs are equal, let's compare mantissas */ + if (xs == 0) { + /* Inputs are both positive, with equal signs and exponents */ + if (xm <= ym) + return x; + return y; + } + /* Inputs are both negative, with equal signs and exponents */ if (xm <= ym) - return x; - return y; + return y; + return x; } union ieee754dp ieee754dp_fmina(union ieee754dp x, union ieee754dp y) @@ -147,14 +173,26 @@ union ieee754dp ieee754dp_fmina(union ieee754dp x, union ieee754dp y) case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF): return ieee754dp_nanxcpt(x); - /* numbers are preferred to NaNs */ + /* + * Quiet NaN handling + */ + + /* + * The case of both inputs quiet NaNs + */ + case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN): + return x; + + /* + * The cases of exactly one input quiet NaN (numbers + * are here preferred as returned values to NaNs) + */ case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN): return x; - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM): @@ -164,25 +202,25 @@ union ieee754dp ieee754dp_fmina(union ieee754dp x, union ieee754dp y) /* * Infinity and zero handling */ + case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF): + return ieee754dp_inf(xs | ys); + case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO): case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM): case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM): case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_ZERO): case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO): - return x; + return y; - case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF): case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF): case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF): case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF): case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM): case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_DNORM): - return y; + return x; case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO): - if (xs == ys) - return x; - return ieee754dp_zero(1); + return ieee754dp_zero(xs | ys); case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): DPDNORMX; @@ -207,7 +245,11 @@ union ieee754dp ieee754dp_fmina(union ieee754dp x, union ieee754dp y) return x; /* Compare mantissa */ - if (xm <= ym) + if (xm < ym) + return x; + else if (xm > ym) + return y; + else if (xs == 1) return x; return y; } diff --git a/arch/mips/math-emu/sp_fmax.c b/arch/mips/math-emu/sp_fmax.c index 4d000844e48e..74a5a00d2f22 100644 --- a/arch/mips/math-emu/sp_fmax.c +++ b/arch/mips/math-emu/sp_fmax.c @@ -47,14 +47,26 @@ union ieee754sp ieee754sp_fmax(union ieee754sp x, union ieee754sp y) case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF): return ieee754sp_nanxcpt(x); - /* numbers are preferred to NaNs */ + /* + * Quiet NaN handling + */ + + /* + * The case of both inputs quiet NaNs + */ + case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN): + return x; + + /* + * The cases of exactly one input quiet NaN (numbers + * are here preferred as returned values to NaNs) + */ case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN): return x; - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM): @@ -80,9 +92,7 @@ union ieee754sp ieee754sp_fmax(union ieee754sp x, union ieee754sp y) return ys ? x : y; case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO): - if (xs == ys) - return x; - return ieee754sp_zero(1); + return ieee754sp_zero(xs & ys); case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): SPDNORMX; @@ -106,16 +116,32 @@ union ieee754sp ieee754sp_fmax(union ieee754sp x, union ieee754sp y) else if (xs < ys) return x; - /* Compare exponent */ - if (xe > ye) - return x; - else if (xe < ye) - return y; + /* Signs of inputs are equal, let's compare exponents */ + if (xs == 0) { + /* Inputs are both positive */ + if (xe > ye) + return x; + else if (xe < ye) + return y; + } else { + /* Inputs are both negative */ + if (xe > ye) + return y; + else if (xe < ye) + return x; + } - /* Compare mantissa */ + /* Signs and exponents of inputs are equal, let's compare mantissas */ + if (xs == 0) { + /* Inputs are both positive, with equal signs and exponents */ + if (xm <= ym) + return y; + return x; + } + /* Inputs are both negative, with equal signs and exponents */ if (xm <= ym) - return y; - return x; + return x; + return y; } union ieee754sp ieee754sp_fmaxa(union ieee754sp x, union ieee754sp y) @@ -147,14 +173,26 @@ union ieee754sp ieee754sp_fmaxa(union ieee754sp x, union ieee754sp y) case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF): return ieee754sp_nanxcpt(x); - /* numbers are preferred to NaNs */ + /* + * Quiet NaN handling + */ + + /* + * The case of both inputs quiet NaNs + */ + case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN): + return x; + + /* + * The cases of exactly one input quiet NaN (numbers + * are here preferred as returned values to NaNs) + */ case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN): return x; - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM): @@ -164,6 +202,9 @@ union ieee754sp ieee754sp_fmaxa(union ieee754sp x, union ieee754sp y) /* * Infinity and zero handling */ + case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF): + return ieee754sp_inf(xs & ys); + case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO): case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM): case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM): @@ -171,7 +212,6 @@ union ieee754sp ieee754sp_fmaxa(union ieee754sp x, union ieee754sp y) case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO): return x; - case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF): case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF): case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF): case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF): @@ -180,9 +220,7 @@ union ieee754sp ieee754sp_fmaxa(union ieee754sp x, union ieee754sp y) return y; case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO): - if (xs == ys) - return x; - return ieee754sp_zero(1); + return ieee754sp_zero(xs & ys); case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): SPDNORMX; @@ -207,7 +245,11 @@ union ieee754sp ieee754sp_fmaxa(union ieee754sp x, union ieee754sp y) return y; /* Compare mantissa */ - if (xm <= ym) + if (xm < ym) return y; - return x; + else if (xm > ym) + return x; + else if (xs == 0) + return x; + return y; } diff --git a/arch/mips/math-emu/sp_fmin.c b/arch/mips/math-emu/sp_fmin.c index 4eb1bb9e9dec..c51385f46b09 100644 --- a/arch/mips/math-emu/sp_fmin.c +++ b/arch/mips/math-emu/sp_fmin.c @@ -47,14 +47,26 @@ union ieee754sp ieee754sp_fmin(union ieee754sp x, union ieee754sp y) case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF): return ieee754sp_nanxcpt(x); - /* numbers are preferred to NaNs */ + /* + * Quiet NaN handling + */ + + /* + * The case of both inputs quiet NaNs + */ + case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN): + return x; + + /* + * The cases of exactly one input quiet NaN (numbers + * are here preferred as returned values to NaNs) + */ case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN): return x; - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM): @@ -80,9 +92,7 @@ union ieee754sp ieee754sp_fmin(union ieee754sp x, union ieee754sp y) return ys ? y : x; case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO): - if (xs == ys) - return x; - return ieee754sp_zero(1); + return ieee754sp_zero(xs | ys); case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): SPDNORMX; @@ -106,16 +116,32 @@ union ieee754sp ieee754sp_fmin(union ieee754sp x, union ieee754sp y) else if (xs < ys) return y; - /* Compare exponent */ - if (xe > ye) - return y; - else if (xe < ye) - return x; + /* Signs of inputs are the same, let's compare exponents */ + if (xs == 0) { + /* Inputs are both positive */ + if (xe > ye) + return y; + else if (xe < ye) + return x; + } else { + /* Inputs are both negative */ + if (xe > ye) + return x; + else if (xe < ye) + return y; + } - /* Compare mantissa */ + /* Signs and exponents of inputs are equal, let's compare mantissas */ + if (xs == 0) { + /* Inputs are both positive, with equal signs and exponents */ + if (xm <= ym) + return x; + return y; + } + /* Inputs are both negative, with equal signs and exponents */ if (xm <= ym) - return x; - return y; + return y; + return x; } union ieee754sp ieee754sp_fmina(union ieee754sp x, union ieee754sp y) @@ -147,14 +173,26 @@ union ieee754sp ieee754sp_fmina(union ieee754sp x, union ieee754sp y) case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF): return ieee754sp_nanxcpt(x); - /* numbers are preferred to NaNs */ + /* + * Quiet NaN handling + */ + + /* + * The case of both inputs quiet NaNs + */ + case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN): + return x; + + /* + * The cases of exactly one input quiet NaN (numbers + * are here preferred as returned values to NaNs) + */ case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN): return x; - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM): @@ -164,25 +202,25 @@ union ieee754sp ieee754sp_fmina(union ieee754sp x, union ieee754sp y) /* * Infinity and zero handling */ + case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF): + return ieee754sp_inf(xs | ys); + case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO): case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM): case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM): case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_ZERO): case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO): - return x; + return y; - case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF): case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF): case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF): case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF): case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM): case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_DNORM): - return y; + return x; case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO): - if (xs == ys) - return x; - return ieee754sp_zero(1); + return ieee754sp_zero(xs | ys); case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): SPDNORMX; @@ -207,7 +245,11 @@ union ieee754sp ieee754sp_fmina(union ieee754sp x, union ieee754sp y) return x; /* Compare mantissa */ - if (xm <= ym) + if (xm < ym) + return x; + else if (xm > ym) + return y; + else if (xs == 1) return x; return y; } diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c index 91e5c1758b5c..64e016abb2a5 100644 --- a/arch/powerpc/kernel/align.c +++ b/arch/powerpc/kernel/align.c @@ -236,6 +236,28 @@ static int emulate_dcbz(struct pt_regs *regs, unsigned char __user *addr) #define SWIZ_PTR(p) ((unsigned char __user *)((p) ^ swiz)) +#define __get_user_or_set_dar(_regs, _dest, _addr) \ + ({ \ + int rc = 0; \ + typeof(_addr) __addr = (_addr); \ + if (__get_user_inatomic(_dest, __addr)) { \ + _regs->dar = (unsigned long)__addr; \ + rc = -EFAULT; \ + } \ + rc; \ + }) + +#define __put_user_or_set_dar(_regs, _src, _addr) \ + ({ \ + int rc = 0; \ + typeof(_addr) __addr = (_addr); \ + if (__put_user_inatomic(_src, __addr)) { \ + _regs->dar = (unsigned long)__addr; \ + rc = -EFAULT; \ + } \ + rc; \ + }) + static int emulate_multiple(struct pt_regs *regs, unsigned char __user *addr, unsigned int reg, unsigned int nb, unsigned int flags, unsigned int instr, @@ -264,9 +286,10 @@ static int emulate_multiple(struct pt_regs *regs, unsigned char __user *addr, } else { unsigned long pc = regs->nip ^ (swiz & 4); - if (__get_user_inatomic(instr, - (unsigned int __user *)pc)) + if (__get_user_or_set_dar(regs, instr, + (unsigned int __user *)pc)) return -EFAULT; + if (swiz == 0 && (flags & SW)) instr = cpu_to_le32(instr); nb = (instr >> 11) & 0x1f; @@ -310,31 +333,31 @@ static int emulate_multiple(struct pt_regs *regs, unsigned char __user *addr, ((nb0 + 3) / 4) * sizeof(unsigned long)); for (i = 0; i < nb; ++i, ++p) - if (__get_user_inatomic(REG_BYTE(rptr, i ^ bswiz), - SWIZ_PTR(p))) + if (__get_user_or_set_dar(regs, REG_BYTE(rptr, i ^ bswiz), + SWIZ_PTR(p))) return -EFAULT; if (nb0 > 0) { rptr = ®s->gpr[0]; addr += nb; for (i = 0; i < nb0; ++i, ++p) - if (__get_user_inatomic(REG_BYTE(rptr, - i ^ bswiz), - SWIZ_PTR(p))) + if (__get_user_or_set_dar(regs, + REG_BYTE(rptr, i ^ bswiz), + SWIZ_PTR(p))) return -EFAULT; } } else { for (i = 0; i < nb; ++i, ++p) - if (__put_user_inatomic(REG_BYTE(rptr, i ^ bswiz), - SWIZ_PTR(p))) + if (__put_user_or_set_dar(regs, REG_BYTE(rptr, i ^ bswiz), + SWIZ_PTR(p))) return -EFAULT; if (nb0 > 0) { rptr = ®s->gpr[0]; addr += nb; for (i = 0; i < nb0; ++i, ++p) - if (__put_user_inatomic(REG_BYTE(rptr, - i ^ bswiz), - SWIZ_PTR(p))) + if (__put_user_or_set_dar(regs, + REG_BYTE(rptr, i ^ bswiz), + SWIZ_PTR(p))) return -EFAULT; } } @@ -346,29 +369,32 @@ static int emulate_multiple(struct pt_regs *regs, unsigned char __user *addr, * Only POWER6 has these instructions, and it does true little-endian, * so we don't need the address swizzling. */ -static int emulate_fp_pair(unsigned char __user *addr, unsigned int reg, - unsigned int flags) +static int emulate_fp_pair(struct pt_regs *regs, unsigned char __user *addr, + unsigned int reg, unsigned int flags) { char *ptr0 = (char *) ¤t->thread.TS_FPR(reg); char *ptr1 = (char *) ¤t->thread.TS_FPR(reg+1); - int i, ret, sw = 0; + int i, sw = 0; if (reg & 1) return 0; /* invalid form: FRS/FRT must be even */ if (flags & SW) sw = 7; - ret = 0; + for (i = 0; i < 8; ++i) { if (!(flags & ST)) { - ret |= __get_user(ptr0[i^sw], addr + i); - ret |= __get_user(ptr1[i^sw], addr + i + 8); + if (__get_user_or_set_dar(regs, ptr0[i^sw], addr + i)) + return -EFAULT; + if (__get_user_or_set_dar(regs, ptr1[i^sw], addr + i + 8)) + return -EFAULT; } else { - ret |= __put_user(ptr0[i^sw], addr + i); - ret |= __put_user(ptr1[i^sw], addr + i + 8); + if (__put_user_or_set_dar(regs, ptr0[i^sw], addr + i)) + return -EFAULT; + if (__put_user_or_set_dar(regs, ptr1[i^sw], addr + i + 8)) + return -EFAULT; } } - if (ret) - return -EFAULT; + return 1; /* exception handled and fixed up */ } @@ -378,24 +404,27 @@ static int emulate_lq_stq(struct pt_regs *regs, unsigned char __user *addr, { char *ptr0 = (char *)®s->gpr[reg]; char *ptr1 = (char *)®s->gpr[reg+1]; - int i, ret, sw = 0; + int i, sw = 0; if (reg & 1) return 0; /* invalid form: GPR must be even */ if (flags & SW) sw = 7; - ret = 0; + for (i = 0; i < 8; ++i) { if (!(flags & ST)) { - ret |= __get_user(ptr0[i^sw], addr + i); - ret |= __get_user(ptr1[i^sw], addr + i + 8); + if (__get_user_or_set_dar(regs, ptr0[i^sw], addr + i)) + return -EFAULT; + if (__get_user_or_set_dar(regs, ptr1[i^sw], addr + i + 8)) + return -EFAULT; } else { - ret |= __put_user(ptr0[i^sw], addr + i); - ret |= __put_user(ptr1[i^sw], addr + i + 8); + if (__put_user_or_set_dar(regs, ptr0[i^sw], addr + i)) + return -EFAULT; + if (__put_user_or_set_dar(regs, ptr1[i^sw], addr + i + 8)) + return -EFAULT; } } - if (ret) - return -EFAULT; + return 1; /* exception handled and fixed up */ } #endif /* CONFIG_PPC64 */ @@ -688,9 +717,14 @@ static int emulate_vsx(unsigned char __user *addr, unsigned int reg, for (j = 0; j < length; j += elsize) { for (i = 0; i < elsize; ++i) { if (flags & ST) - ret |= __put_user(ptr[i^sw], addr + i); + ret = __put_user_or_set_dar(regs, ptr[i^sw], + addr + i); else - ret |= __get_user(ptr[i^sw], addr + i); + ret = __get_user_or_set_dar(regs, ptr[i^sw], + addr + i); + + if (ret) + return ret; } ptr += elsize; #ifdef __LITTLE_ENDIAN__ @@ -740,7 +774,7 @@ int fix_alignment(struct pt_regs *regs) unsigned int dsisr; unsigned char __user *addr; unsigned long p, swiz; - int ret, i; + int i; union data { u64 ll; double dd; @@ -923,7 +957,7 @@ int fix_alignment(struct pt_regs *regs) if (flags & F) { /* Special case for 16-byte FP loads and stores */ PPC_WARN_ALIGNMENT(fp_pair, regs); - return emulate_fp_pair(addr, reg, flags); + return emulate_fp_pair(regs, addr, reg, flags); } else { #ifdef CONFIG_PPC64 /* Special case for 16-byte loads and stores */ @@ -953,15 +987,12 @@ int fix_alignment(struct pt_regs *regs) } data.ll = 0; - ret = 0; p = (unsigned long)addr; for (i = 0; i < nb; i++) - ret |= __get_user_inatomic(data.v[start + i], - SWIZ_PTR(p++)); - - if (unlikely(ret)) - return -EFAULT; + if (__get_user_or_set_dar(regs, data.v[start + i], + SWIZ_PTR(p++))) + return -EFAULT; } else if (flags & F) { data.ll = current->thread.TS_FPR(reg); @@ -1031,15 +1062,13 @@ int fix_alignment(struct pt_regs *regs) break; } - ret = 0; p = (unsigned long)addr; for (i = 0; i < nb; i++) - ret |= __put_user_inatomic(data.v[start + i], - SWIZ_PTR(p++)); + if (__put_user_or_set_dar(regs, data.v[start + i], + SWIZ_PTR(p++))) + return -EFAULT; - if (unlikely(ret)) - return -EFAULT; } else if (flags & F) current->thread.TS_FPR(reg) = data.ll; else diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index bcd3d6199464..bb16a58cf7e4 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -204,6 +204,7 @@ void set_personality_ia32(bool); #define ELF_CORE_COPY_REGS(pr_reg, regs) \ do { \ + unsigned long base; \ unsigned v; \ (pr_reg)[0] = (regs)->r15; \ (pr_reg)[1] = (regs)->r14; \ @@ -226,8 +227,8 @@ do { \ (pr_reg)[18] = (regs)->flags; \ (pr_reg)[19] = (regs)->sp; \ (pr_reg)[20] = (regs)->ss; \ - (pr_reg)[21] = current->thread.fs; \ - (pr_reg)[22] = current->thread.gs; \ + rdmsrl(MSR_FS_BASE, base); (pr_reg)[21] = base; \ + rdmsrl(MSR_KERNEL_GS_BASE, base); (pr_reg)[22] = base; \ asm("movl %%ds,%0" : "=r" (v)); (pr_reg)[23] = v; \ asm("movl %%es,%0" : "=r" (v)); (pr_reg)[24] = v; \ asm("movl %%fs,%0" : "=r" (v)); (pr_reg)[25] = v; \ diff --git a/block/blk-core.c b/block/blk-core.c index 3115494c4cb2..1bc9f212b3a2 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -247,7 +247,7 @@ EXPORT_SYMBOL(blk_start_queue_async); **/ void blk_start_queue(struct request_queue *q) { - WARN_ON(!irqs_disabled()); + WARN_ON(!in_interrupt() && !irqs_disabled()); queue_flag_clear(QUEUE_FLAG_STOPPED, q); __blk_run_queue(q); diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c index b3b0004ea8ac..d12782dc9683 100644 --- a/crypto/algif_skcipher.c +++ b/crypto/algif_skcipher.c @@ -143,8 +143,10 @@ static int skcipher_alloc_sgl(struct sock *sk) sg_init_table(sgl->sg, MAX_SGL_ENTS + 1); sgl->cur = 0; - if (sg) + if (sg) { sg_chain(sg, MAX_SGL_ENTS + 1, sgl->sg); + sg_unmark_end(sg + (MAX_SGL_ENTS - 1)); + } list_add_tail(&sgl->list, &ctx->tsgl); } diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c index 1c1a7d9c86ed..b95da16fd938 100644 --- a/drivers/android/binder_alloc.c +++ b/drivers/android/binder_alloc.c @@ -186,12 +186,12 @@ struct binder_buffer *binder_alloc_prepare_to_free(struct binder_alloc *alloc, } static int binder_update_page_range(struct binder_alloc *alloc, int allocate, - void *start, void *end, - struct vm_area_struct *vma) + void *start, void *end) { void *page_addr; unsigned long user_page_addr; struct binder_lru_page *page; + struct vm_area_struct *vma = NULL; struct mm_struct *mm = NULL; bool need_mm = false; @@ -215,17 +215,13 @@ static int binder_update_page_range(struct binder_alloc *alloc, int allocate, } } - if (!vma && need_mm) - mm = get_task_mm(alloc->tsk); + /* Same as mmget_not_zero() in later kernel versions */ + if (need_mm && atomic_inc_not_zero(&alloc->vma_vm_mm->mm_users)) + mm = alloc->vma_vm_mm; if (mm) { down_write(&mm->mmap_sem); vma = alloc->vma; - if (vma && mm != alloc->vma_vm_mm) { - pr_err("%d: vma mm and task mm mismatch\n", - alloc->pid); - vma = NULL; - } } if (!vma && need_mm) { @@ -442,7 +438,7 @@ struct binder_buffer *binder_alloc_new_buf_locked(struct binder_alloc *alloc, if (end_page_addr > has_page_addr) end_page_addr = has_page_addr; ret = binder_update_page_range(alloc, 1, - (void *)PAGE_ALIGN((uintptr_t)buffer->data), end_page_addr, NULL); + (void *)PAGE_ALIGN((uintptr_t)buffer->data), end_page_addr); if (ret) return ERR_PTR(ret); @@ -483,7 +479,7 @@ struct binder_buffer *binder_alloc_new_buf_locked(struct binder_alloc *alloc, err_alloc_buf_struct_failed: binder_update_page_range(alloc, 0, (void *)PAGE_ALIGN((uintptr_t)buffer->data), - end_page_addr, NULL); + end_page_addr); return ERR_PTR(-ENOMEM); } @@ -567,8 +563,7 @@ static void binder_delete_free_buffer(struct binder_alloc *alloc, alloc->pid, buffer->data, prev->data, next->data); binder_update_page_range(alloc, 0, buffer_start_page(buffer), - buffer_start_page(buffer) + PAGE_SIZE, - NULL); + buffer_start_page(buffer) + PAGE_SIZE); } list_del(&buffer->entry); kfree(buffer); @@ -605,8 +600,7 @@ static void binder_free_buf_locked(struct binder_alloc *alloc, binder_update_page_range(alloc, 0, (void *)PAGE_ALIGN((uintptr_t)buffer->data), - (void *)(((uintptr_t)buffer->data + buffer_size) & PAGE_MASK), - NULL); + (void *)(((uintptr_t)buffer->data + buffer_size) & PAGE_MASK)); rb_erase(&buffer->rb_node, &alloc->allocated_buffers); buffer->free = 1; @@ -720,6 +714,8 @@ int binder_alloc_mmap_handler(struct binder_alloc *alloc, barrier(); alloc->vma = vma; alloc->vma_vm_mm = vma->vm_mm; + /* Same as mmgrab() in later kernel versions */ + atomic_inc(&alloc->vma_vm_mm->mm_count); return 0; @@ -795,6 +791,8 @@ void binder_alloc_deferred_release(struct binder_alloc *alloc) vfree(alloc->buffer); } mutex_unlock(&alloc->mutex); + if (alloc->vma_vm_mm) + mmdrop(alloc->vma_vm_mm); binder_alloc_debug(BINDER_DEBUG_OPEN_CLOSE, "%s: %d buffers %d, pages %d\n", @@ -889,7 +887,6 @@ int binder_alloc_get_allocated_count(struct binder_alloc *alloc) void binder_alloc_vma_close(struct binder_alloc *alloc) { WRITE_ONCE(alloc->vma, NULL); - WRITE_ONCE(alloc->vma_vm_mm, NULL); } /** @@ -913,6 +910,7 @@ enum lru_status binder_alloc_free_page(struct list_head *item, struct binder_alloc *alloc; uintptr_t page_addr; size_t index; + struct vm_area_struct *vma; alloc = page->alloc; if (!mutex_trylock(&alloc->mutex)) @@ -923,16 +921,23 @@ enum lru_status binder_alloc_free_page(struct list_head *item, index = page - alloc->pages; page_addr = (uintptr_t)alloc->buffer + index * PAGE_SIZE; - if (alloc->vma) { - mm = get_task_mm(alloc->tsk); - if (!mm) - goto err_get_task_mm_failed; + vma = alloc->vma; + if (vma) { + /* Same as mmget_not_zero() in later kernel versions */ + if (!atomic_inc_not_zero(&alloc->vma_vm_mm->mm_users)) + goto err_mmget; + mm = alloc->vma_vm_mm; if (!down_write_trylock(&mm->mmap_sem)) goto err_down_write_mmap_sem_failed; + } + + list_lru_isolate(lru, item); + spin_unlock(lock); + if (vma) { trace_binder_unmap_user_start(alloc, index); - zap_page_range(alloc->vma, + zap_page_range(vma, page_addr + alloc->user_buffer_offset, PAGE_SIZE, NULL); @@ -951,14 +956,13 @@ enum lru_status binder_alloc_free_page(struct list_head *item, trace_binder_unmap_kernel_end(alloc, index); - list_lru_isolate(lru, item); - + spin_lock(lock); mutex_unlock(&alloc->mutex); - return LRU_REMOVED; + return LRU_REMOVED_RETRY; err_down_write_mmap_sem_failed: - mmput(mm); -err_get_task_mm_failed: + mmput_async(mm); +err_mmget: err_page_already_freed: mutex_unlock(&alloc->mutex); err_get_alloc_mutex_failed: @@ -997,7 +1001,6 @@ struct shrinker binder_shrinker = { */ void binder_alloc_init(struct binder_alloc *alloc) { - alloc->tsk = current->group_leader; alloc->pid = current->group_leader->pid; mutex_init(&alloc->mutex); INIT_LIST_HEAD(&alloc->buffers); diff --git a/drivers/android/binder_alloc.h b/drivers/android/binder_alloc.h index a3a3602c689c..2dd33b6df104 100644 --- a/drivers/android/binder_alloc.h +++ b/drivers/android/binder_alloc.h @@ -100,7 +100,6 @@ struct binder_lru_page { */ struct binder_alloc { struct mutex mutex; - struct task_struct *tsk; struct vm_area_struct *vma; struct mm_struct *vma_vm_mm; void *buffer; diff --git a/drivers/block/skd_main.c b/drivers/block/skd_main.c index 586f9168ffa4..47d1e834f3f4 100644 --- a/drivers/block/skd_main.c +++ b/drivers/block/skd_main.c @@ -2214,6 +2214,9 @@ static void skd_send_fitmsg(struct skd_device *skdev, */ qcmd |= FIT_QCMD_MSGSIZE_64; + /* Make sure skd_msg_buf is written before the doorbell is triggered. */ + smp_wmb(); + SKD_WRITEQ(skdev, qcmd, FIT_Q_COMMAND); } @@ -2260,6 +2263,9 @@ static void skd_send_special_fitmsg(struct skd_device *skdev, qcmd = skspcl->mb_dma_address; qcmd |= FIT_QCMD_QID_NORMAL + FIT_QCMD_MSGSIZE_128; + /* Make sure skd_msg_buf is written before the doorbell is triggered. */ + smp_wmb(); + SKD_WRITEQ(skdev, qcmd, FIT_Q_COMMAND); } @@ -4679,15 +4685,16 @@ static void skd_free_disk(struct skd_device *skdev) { struct gendisk *disk = skdev->disk; - if (disk != NULL) { - struct request_queue *q = disk->queue; + if (disk && (disk->flags & GENHD_FL_UP)) + del_gendisk(disk); - if (disk->flags & GENHD_FL_UP) - del_gendisk(disk); - if (q) - blk_cleanup_queue(q); - put_disk(disk); + if (skdev->queue) { + blk_cleanup_queue(skdev->queue); + skdev->queue = NULL; + disk->queue = NULL; } + + put_disk(disk); skdev->disk = NULL; } diff --git a/drivers/cpufreq/cpufreq_interactive.c b/drivers/cpufreq/cpufreq_interactive.c index abbee61c99c8..ae65fbc3ceac 100644 --- a/drivers/cpufreq/cpufreq_interactive.c +++ b/drivers/cpufreq/cpufreq_interactive.c @@ -1825,6 +1825,7 @@ struct cpufreq_governor cpufreq_gov_interactive = { static int __init cpufreq_interactive_init(void) { struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 }; + int ret = 0; spin_lock_init(&speedchange_cpumask_lock); mutex_init(&gov_lock); @@ -1841,7 +1842,12 @@ static int __init cpufreq_interactive_init(void) /* NB: wake up so the thread does not look hung to the freezer */ wake_up_process_no_notif(speedchange_task); - return cpufreq_register_governor(&cpufreq_gov_interactive); + ret = cpufreq_register_governor(&cpufreq_gov_interactive); + if (ret) { + kthread_stop(speedchange_task); + put_task_struct(speedchange_task); + } + return ret; } #ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_INTERACTIVE diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h index 5be14ad29d46..dbf09836ff30 100644 --- a/drivers/input/serio/i8042-x86ia64io.h +++ b/drivers/input/serio/i8042-x86ia64io.h @@ -905,6 +905,13 @@ static const struct dmi_system_id __initconst i8042_dmi_kbdreset_table[] = { }, }, { + /* Gigabyte P57 - Elantech touchpad */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"), + DMI_MATCH(DMI_PRODUCT_NAME, "P57"), + }, + }, + { /* Schenker XMG C504 - Elantech touchpad */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "XMG"), diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index c3ea03c9a1a8..02619cabda8b 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -333,6 +333,7 @@ struct cached_dev { /* Limit number of writeback bios in flight */ struct semaphore in_flight; struct task_struct *writeback_thread; + struct workqueue_struct *writeback_write_wq; struct keybuf writeback_keys; diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index 2410df1c2a05..6c4c7caea693 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -196,12 +196,12 @@ static void bch_data_insert_start(struct closure *cl) struct data_insert_op *op = container_of(cl, struct data_insert_op, cl); struct bio *bio = op->bio, *n; - if (atomic_sub_return(bio_sectors(bio), &op->c->sectors_to_gc) < 0) - wake_up_gc(op->c); - if (op->bypass) return bch_data_invalidate(cl); + if (atomic_sub_return(bio_sectors(bio), &op->c->sectors_to_gc) < 0) + wake_up_gc(op->c); + /* * Journal writes are marked REQ_FLUSH; if the original write was a * flush, it'll wait on the journal write. diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 7b5880b8874c..c5ceea9222ff 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -1023,7 +1023,7 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c) } if (BDEV_STATE(&dc->sb) == BDEV_STATE_DIRTY) { - bch_sectors_dirty_init(dc); + bch_sectors_dirty_init(&dc->disk); atomic_set(&dc->has_dirty, 1); atomic_inc(&dc->count); bch_writeback_queue(dc); @@ -1056,6 +1056,8 @@ static void cached_dev_free(struct closure *cl) cancel_delayed_work_sync(&dc->writeback_rate_update); if (!IS_ERR_OR_NULL(dc->writeback_thread)) kthread_stop(dc->writeback_thread); + if (dc->writeback_write_wq) + destroy_workqueue(dc->writeback_write_wq); mutex_lock(&bch_register_lock); @@ -1227,6 +1229,7 @@ static int flash_dev_run(struct cache_set *c, struct uuid_entry *u) goto err; bcache_device_attach(d, c, u - c->uuids); + bch_sectors_dirty_init(d); bch_flash_dev_request_init(d); add_disk(d->disk); @@ -1959,6 +1962,8 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr, else err = "device busy"; mutex_unlock(&bch_register_lock); + if (!IS_ERR(bdev)) + bdput(bdev); if (attr == &ksysfs_register_quiet) goto out; } diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c index b3ff57d61dde..4fbb5532f24c 100644 --- a/drivers/md/bcache/sysfs.c +++ b/drivers/md/bcache/sysfs.c @@ -191,7 +191,7 @@ STORE(__cached_dev) { struct cached_dev *dc = container_of(kobj, struct cached_dev, disk.kobj); - unsigned v = size; + ssize_t v = size; struct cache_set *c; struct kobj_uevent_env *env; @@ -226,7 +226,7 @@ STORE(__cached_dev) bch_cached_dev_run(dc); if (attr == &sysfs_cache_mode) { - ssize_t v = bch_read_string_list(buf, bch_cache_modes + 1); + v = bch_read_string_list(buf, bch_cache_modes + 1); if (v < 0) return v; diff --git a/drivers/md/bcache/util.c b/drivers/md/bcache/util.c index db3ae4c2b223..6c18e3ec3e48 100644 --- a/drivers/md/bcache/util.c +++ b/drivers/md/bcache/util.c @@ -73,24 +73,44 @@ STRTO_H(strtouint, unsigned int) STRTO_H(strtoll, long long) STRTO_H(strtoull, unsigned long long) +/** + * bch_hprint() - formats @v to human readable string for sysfs. + * + * @v - signed 64 bit integer + * @buf - the (at least 8 byte) buffer to format the result into. + * + * Returns the number of bytes used by format. + */ ssize_t bch_hprint(char *buf, int64_t v) { static const char units[] = "?kMGTPEZY"; - char dec[4] = ""; - int u, t = 0; - - for (u = 0; v >= 1024 || v <= -1024; u++) { - t = v & ~(~0 << 10); - v >>= 10; - } - - if (!u) - return sprintf(buf, "%llu", v); - - if (v < 100 && v > -100) - snprintf(dec, sizeof(dec), ".%i", t / 100); - - return sprintf(buf, "%lli%s%c", v, dec, units[u]); + int u = 0, t; + + uint64_t q; + + if (v < 0) + q = -v; + else + q = v; + + /* For as long as the number is more than 3 digits, but at least + * once, shift right / divide by 1024. Keep the remainder for + * a digit after the decimal point. + */ + do { + u++; + + t = q & ~(~0 << 10); + q >>= 10; + } while (q >= 1000); + + if (v < 0) + /* '-', up to 3 digits, '.', 1 digit, 1 character, null; + * yields 8 bytes. + */ + return sprintf(buf, "-%llu.%i%c", q, t * 10 / 1024, units[u]); + else + return sprintf(buf, "%llu.%i%c", q, t * 10 / 1024, units[u]); } ssize_t bch_snprint_string_list(char *buf, size_t size, const char * const list[], diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c index b9346cd9cda1..bbb1dc9e1639 100644 --- a/drivers/md/bcache/writeback.c +++ b/drivers/md/bcache/writeback.c @@ -21,7 +21,8 @@ static void __update_writeback_rate(struct cached_dev *dc) { struct cache_set *c = dc->disk.c; - uint64_t cache_sectors = c->nbuckets * c->sb.bucket_size; + uint64_t cache_sectors = c->nbuckets * c->sb.bucket_size - + bcache_flash_devs_sectors_dirty(c); uint64_t cache_dirty_target = div_u64(cache_sectors * dc->writeback_percent, 100); @@ -190,7 +191,7 @@ static void write_dirty(struct closure *cl) closure_bio_submit(&io->bio, cl); - continue_at(cl, write_dirty_finish, system_wq); + continue_at(cl, write_dirty_finish, io->dc->writeback_write_wq); } static void read_dirty_endio(struct bio *bio) @@ -210,7 +211,7 @@ static void read_dirty_submit(struct closure *cl) closure_bio_submit(&io->bio, cl); - continue_at(cl, write_dirty, system_wq); + continue_at(cl, write_dirty, io->dc->writeback_write_wq); } static void read_dirty(struct cached_dev *dc) @@ -488,17 +489,17 @@ static int sectors_dirty_init_fn(struct btree_op *_op, struct btree *b, return MAP_CONTINUE; } -void bch_sectors_dirty_init(struct cached_dev *dc) +void bch_sectors_dirty_init(struct bcache_device *d) { struct sectors_dirty_init op; bch_btree_op_init(&op.op, -1); - op.inode = dc->disk.id; + op.inode = d->id; - bch_btree_map_keys(&op.op, dc->disk.c, &KEY(op.inode, 0, 0), + bch_btree_map_keys(&op.op, d->c, &KEY(op.inode, 0, 0), sectors_dirty_init_fn, 0); - dc->disk.sectors_dirty_last = bcache_dev_sectors_dirty(&dc->disk); + d->sectors_dirty_last = bcache_dev_sectors_dirty(d); } void bch_cached_dev_writeback_init(struct cached_dev *dc) @@ -522,6 +523,11 @@ void bch_cached_dev_writeback_init(struct cached_dev *dc) int bch_cached_dev_writeback_start(struct cached_dev *dc) { + dc->writeback_write_wq = alloc_workqueue("bcache_writeback_wq", + WQ_MEM_RECLAIM, 0); + if (!dc->writeback_write_wq) + return -ENOMEM; + dc->writeback_thread = kthread_create(bch_writeback_thread, dc, "bcache_writeback"); if (IS_ERR(dc->writeback_thread)) diff --git a/drivers/md/bcache/writeback.h b/drivers/md/bcache/writeback.h index 073a042aed24..daec4fd782ea 100644 --- a/drivers/md/bcache/writeback.h +++ b/drivers/md/bcache/writeback.h @@ -14,6 +14,25 @@ static inline uint64_t bcache_dev_sectors_dirty(struct bcache_device *d) return ret; } +static inline uint64_t bcache_flash_devs_sectors_dirty(struct cache_set *c) +{ + uint64_t i, ret = 0; + + mutex_lock(&bch_register_lock); + + for (i = 0; i < c->nr_uuids; i++) { + struct bcache_device *d = c->devices[i]; + + if (!d || !UUID_FLASH_ONLY(&c->uuids[i])) + continue; + ret += bcache_dev_sectors_dirty(d); + } + + mutex_unlock(&bch_register_lock); + + return ret; +} + static inline unsigned offset_to_stripe(struct bcache_device *d, uint64_t offset) { @@ -85,7 +104,7 @@ static inline void bch_writeback_add(struct cached_dev *dc) void bcache_dev_sectors_dirty_add(struct cache_set *, unsigned, uint64_t, int); -void bch_sectors_dirty_init(struct cached_dev *dc); +void bch_sectors_dirty_init(struct bcache_device *); void bch_cached_dev_writeback_init(struct cached_dev *); int bch_cached_dev_writeback_start(struct cached_dev *); diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c index 4f22e919787a..7a50728b9389 100644 --- a/drivers/md/bitmap.c +++ b/drivers/md/bitmap.c @@ -1960,6 +1960,11 @@ int bitmap_resize(struct bitmap *bitmap, sector_t blocks, long pages; struct bitmap_page *new_bp; + if (bitmap->storage.file && !init) { + pr_info("md: cannot resize file-based bitmap\n"); + return -EINVAL; + } + if (chunksize == 0) { /* If there is enough space, leave the chunk size unchanged, * else increase by factor of two until there is enough space. diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 8f60520c8392..5eac08ffc697 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -5822,6 +5822,8 @@ static void raid5_do_work(struct work_struct *work) spin_unlock_irq(&conf->device_lock); + r5l_flush_stripe_to_raid(conf->log); + async_tx_issue_pending_all(); blk_finish_plug(&plug); diff --git a/drivers/media/usb/uvc/uvc_ctrl.c b/drivers/media/usb/uvc/uvc_ctrl.c index 57d2f89350d2..9532235b07de 100644 --- a/drivers/media/usb/uvc/uvc_ctrl.c +++ b/drivers/media/usb/uvc/uvc_ctrl.c @@ -2004,6 +2004,13 @@ int uvc_ctrl_add_mapping(struct uvc_video_chain *chain, goto done; } + /* Validate the user-provided bit-size and offset */ + if (mapping->size > 32 || + mapping->offset + mapping->size > ctrl->info.size * 8) { + ret = -EINVAL; + goto done; + } + list_for_each_entry(map, &ctrl->info.mappings, list) { if (mapping->id == map->id) { uvc_trace(UVC_TRACE_CONTROL, "Can't add mapping '%s', " diff --git a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c index 2f1c03783414..bee17d21ee49 100644 --- a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c +++ b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c @@ -788,7 +788,8 @@ static int put_v4l2_event32(struct v4l2_event *kp, struct v4l2_event32 __user *u copy_to_user(&up->u, &kp->u, sizeof(kp->u)) || put_user(kp->pending, &up->pending) || put_user(kp->sequence, &up->sequence) || - compat_put_timespec(&kp->timestamp, &up->timestamp) || + put_user(kp->timestamp.tv_sec, &up->timestamp.tv_sec) || + put_user(kp->timestamp.tv_nsec, &up->timestamp.tv_nsec) || put_user(kp->id, &up->id) || copy_to_user(up->reserved, kp->reserved, 8 * sizeof(__u32))) return -EFAULT; diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index 4cd2a7d0124f..7923bfdc9b30 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -3676,7 +3676,7 @@ static noinline void gfar_update_link_state(struct gfar_private *priv) u32 tempval1 = gfar_read(®s->maccfg1); u32 tempval = gfar_read(®s->maccfg2); u32 ecntrl = gfar_read(®s->ecntrl); - u32 tx_flow_oldval = (tempval & MACCFG1_TX_FLOW); + u32 tx_flow_oldval = (tempval1 & MACCFG1_TX_FLOW); if (phydev->duplex != priv->oldduplex) { if (!(phydev->duplex)) diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_dbg.c b/drivers/net/ethernet/qlogic/qlge/qlge_dbg.c index 829be21f97b2..be258d90de9e 100644 --- a/drivers/net/ethernet/qlogic/qlge/qlge_dbg.c +++ b/drivers/net/ethernet/qlogic/qlge/qlge_dbg.c @@ -724,7 +724,7 @@ static void ql_build_coredump_seg_header( seg_hdr->cookie = MPI_COREDUMP_COOKIE; seg_hdr->segNum = seg_number; seg_hdr->segSize = seg_size; - memcpy(seg_hdr->description, desc, (sizeof(seg_hdr->description)) - 1); + strncpy(seg_hdr->description, desc, (sizeof(seg_hdr->description)) - 1); } /* diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 49d9f0a789fe..7d0690433ee0 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -541,9 +541,6 @@ void phy_stop_machine(struct phy_device *phydev) if (phydev->state > PHY_UP && phydev->state != PHY_HALTED) phydev->state = PHY_UP; mutex_unlock(&phydev->lock); - - /* Now we can run the state machine synchronously */ - phy_state_machine(&phydev->state_queue.work); } /** diff --git a/drivers/pci/hotplug/shpchp_hpc.c b/drivers/pci/hotplug/shpchp_hpc.c index 7d223e9080ef..77dddee2753a 100644 --- a/drivers/pci/hotplug/shpchp_hpc.c +++ b/drivers/pci/hotplug/shpchp_hpc.c @@ -1062,6 +1062,8 @@ int shpc_init(struct controller *ctrl, struct pci_dev *pdev) if (rc) { ctrl_info(ctrl, "Can't get msi for the hotplug controller\n"); ctrl_info(ctrl, "Use INTx for the hotplug controller\n"); + } else { + pci_set_master(pdev); } rc = request_irq(ctrl->pci_dev->irq, shpc_isr, IRQF_SHARED, diff --git a/drivers/s390/scsi/zfcp_dbf.c b/drivers/s390/scsi/zfcp_dbf.c index d5bf36ec8a75..34367d172961 100644 --- a/drivers/s390/scsi/zfcp_dbf.c +++ b/drivers/s390/scsi/zfcp_dbf.c @@ -3,7 +3,7 @@ * * Debug traces for zfcp. * - * Copyright IBM Corp. 2002, 2016 + * Copyright IBM Corp. 2002, 2017 */ #define KMSG_COMPONENT "zfcp" @@ -447,6 +447,7 @@ static u16 zfcp_dbf_san_res_cap_len_if_gpn_ft(char *tag, struct fc_ct_hdr *reqh = sg_virt(ct_els->req); struct fc_ns_gid_ft *reqn = (struct fc_ns_gid_ft *)(reqh + 1); struct scatterlist *resp_entry = ct_els->resp; + struct fc_ct_hdr *resph; struct fc_gpn_ft_resp *acc; int max_entries, x, last = 0; @@ -473,6 +474,13 @@ static u16 zfcp_dbf_san_res_cap_len_if_gpn_ft(char *tag, return len; /* not GPN_FT response so do not cap */ acc = sg_virt(resp_entry); + + /* cap all but accept CT responses to at least the CT header */ + resph = (struct fc_ct_hdr *)acc; + if ((ct_els->status) || + (resph->ct_cmd != cpu_to_be16(FC_FS_ACC))) + return max(FC_CT_HDR_LEN, ZFCP_DBF_SAN_MAX_PAYLOAD); + max_entries = (reqh->ct_mr_size * 4 / sizeof(struct fc_gpn_ft_resp)) + 1 /* zfcp_fc_scan_ports: bytes correct, entries off-by-one * to account for header as 1st pseudo "entry" */; @@ -555,8 +563,8 @@ void zfcp_dbf_scsi(char *tag, int level, struct scsi_cmnd *sc, rec->scsi_retries = sc->retries; rec->scsi_allowed = sc->allowed; rec->scsi_id = sc->device->id; - /* struct zfcp_dbf_scsi needs to be updated to handle 64bit LUNs */ rec->scsi_lun = (u32)sc->device->lun; + rec->scsi_lun_64_hi = (u32)(sc->device->lun >> 32); rec->host_scribble = (unsigned long)sc->host_scribble; memcpy(rec->scsi_opcode, sc->cmnd, @@ -564,19 +572,32 @@ void zfcp_dbf_scsi(char *tag, int level, struct scsi_cmnd *sc, if (fsf) { rec->fsf_req_id = fsf->req_id; + rec->pl_len = FCP_RESP_WITH_EXT; fcp_rsp = (struct fcp_resp_with_ext *) &(fsf->qtcb->bottom.io.fcp_rsp); + /* mandatory parts of FCP_RSP IU in this SCSI record */ memcpy(&rec->fcp_rsp, fcp_rsp, FCP_RESP_WITH_EXT); if (fcp_rsp->resp.fr_flags & FCP_RSP_LEN_VAL) { fcp_rsp_info = (struct fcp_resp_rsp_info *) &fcp_rsp[1]; rec->fcp_rsp_info = fcp_rsp_info->rsp_code; + rec->pl_len += be32_to_cpu(fcp_rsp->ext.fr_rsp_len); } if (fcp_rsp->resp.fr_flags & FCP_SNS_LEN_VAL) { - rec->pl_len = min((u16)SCSI_SENSE_BUFFERSIZE, - (u16)ZFCP_DBF_PAY_MAX_REC); - zfcp_dbf_pl_write(dbf, sc->sense_buffer, rec->pl_len, - "fcp_sns", fsf->req_id); + rec->pl_len += be32_to_cpu(fcp_rsp->ext.fr_sns_len); } + /* complete FCP_RSP IU in associated PAYload record + * but only if there are optional parts + */ + if (fcp_rsp->resp.fr_flags != 0) + zfcp_dbf_pl_write( + dbf, fcp_rsp, + /* at least one full PAY record + * but not beyond hardware response field + */ + min_t(u16, max_t(u16, rec->pl_len, + ZFCP_DBF_PAY_MAX_REC), + FSF_FCP_RSP_SIZE), + "fcp_riu", fsf->req_id); } debug_event(dbf->scsi, level, rec, sizeof(*rec)); diff --git a/drivers/s390/scsi/zfcp_dbf.h b/drivers/s390/scsi/zfcp_dbf.h index db186d44cfaf..b60667c145fd 100644 --- a/drivers/s390/scsi/zfcp_dbf.h +++ b/drivers/s390/scsi/zfcp_dbf.h @@ -2,7 +2,7 @@ * zfcp device driver * debug feature declarations * - * Copyright IBM Corp. 2008, 2016 + * Copyright IBM Corp. 2008, 2017 */ #ifndef ZFCP_DBF_H @@ -204,7 +204,7 @@ enum zfcp_dbf_scsi_id { * @id: unique number of recovery record type * @tag: identifier string specifying the location of initiation * @scsi_id: scsi device id - * @scsi_lun: scsi device logical unit number + * @scsi_lun: scsi device logical unit number, low part of 64 bit, old 32 bit * @scsi_result: scsi result * @scsi_retries: current retry number of scsi request * @scsi_allowed: allowed retries @@ -214,6 +214,7 @@ enum zfcp_dbf_scsi_id { * @host_scribble: LLD specific data attached to SCSI request * @pl_len: length of paload stored as zfcp_dbf_pay * @fsf_rsp: response for fsf request + * @scsi_lun_64_hi: scsi device logical unit number, high part of 64 bit */ struct zfcp_dbf_scsi { u8 id; @@ -230,6 +231,7 @@ struct zfcp_dbf_scsi { u64 host_scribble; u16 pl_len; struct fcp_resp_with_ext fcp_rsp; + u32 scsi_lun_64_hi; } __packed; /** @@ -323,7 +325,11 @@ void zfcp_dbf_hba_fsf_response(struct zfcp_fsf_req *req) { struct fsf_qtcb *qtcb = req->qtcb; - if ((qtcb->prefix.prot_status != FSF_PROT_GOOD) && + if (unlikely(req->status & (ZFCP_STATUS_FSFREQ_DISMISSED | + ZFCP_STATUS_FSFREQ_ERROR))) { + zfcp_dbf_hba_fsf_resp("fs_rerr", 3, req); + + } else if ((qtcb->prefix.prot_status != FSF_PROT_GOOD) && (qtcb->prefix.prot_status != FSF_PROT_FSF_STATUS_PRESENTED)) { zfcp_dbf_hba_fsf_resp("fs_perr", 1, req); @@ -401,7 +407,8 @@ void zfcp_dbf_scsi_abort(char *tag, struct scsi_cmnd *scmd, * @flag: indicates type of reset (Target Reset, Logical Unit Reset) */ static inline -void zfcp_dbf_scsi_devreset(char *tag, struct scsi_cmnd *scmnd, u8 flag) +void zfcp_dbf_scsi_devreset(char *tag, struct scsi_cmnd *scmnd, u8 flag, + struct zfcp_fsf_req *fsf_req) { char tmp_tag[ZFCP_DBF_TAG_LEN]; @@ -411,7 +418,7 @@ void zfcp_dbf_scsi_devreset(char *tag, struct scsi_cmnd *scmnd, u8 flag) memcpy(tmp_tag, "lr_", 3); memcpy(&tmp_tag[3], tag, 4); - _zfcp_dbf_scsi(tmp_tag, 1, scmnd, NULL); + _zfcp_dbf_scsi(tmp_tag, 1, scmnd, fsf_req); } /** diff --git a/drivers/s390/scsi/zfcp_fc.h b/drivers/s390/scsi/zfcp_fc.h index df2b541c8287..a2275825186f 100644 --- a/drivers/s390/scsi/zfcp_fc.h +++ b/drivers/s390/scsi/zfcp_fc.h @@ -4,7 +4,7 @@ * Fibre Channel related definitions and inline functions for the zfcp * device driver * - * Copyright IBM Corp. 2009 + * Copyright IBM Corp. 2009, 2017 */ #ifndef ZFCP_FC_H @@ -279,6 +279,10 @@ void zfcp_fc_eval_fcp_rsp(struct fcp_resp_with_ext *fcp_rsp, !(rsp_flags & FCP_SNS_LEN_VAL) && fcp_rsp->resp.fr_status == SAM_STAT_GOOD) set_host_byte(scsi, DID_ERROR); + } else if (unlikely(rsp_flags & FCP_RESID_OVER)) { + /* FCP_DL was not sufficient for SCSI data length */ + if (fcp_rsp->resp.fr_status == SAM_STAT_GOOD) + set_host_byte(scsi, DID_ERROR); } } diff --git a/drivers/s390/scsi/zfcp_fsf.c b/drivers/s390/scsi/zfcp_fsf.c index 27ff38f839fc..1964391db904 100644 --- a/drivers/s390/scsi/zfcp_fsf.c +++ b/drivers/s390/scsi/zfcp_fsf.c @@ -928,8 +928,8 @@ static void zfcp_fsf_send_ct_handler(struct zfcp_fsf_req *req) switch (header->fsf_status) { case FSF_GOOD: - zfcp_dbf_san_res("fsscth2", req); ct->status = 0; + zfcp_dbf_san_res("fsscth2", req); break; case FSF_SERVICE_CLASS_NOT_SUPPORTED: zfcp_fsf_class_not_supp(req); @@ -1109,8 +1109,8 @@ static void zfcp_fsf_send_els_handler(struct zfcp_fsf_req *req) switch (header->fsf_status) { case FSF_GOOD: - zfcp_dbf_san_res("fsselh1", req); send_els->status = 0; + zfcp_dbf_san_res("fsselh1", req); break; case FSF_SERVICE_CLASS_NOT_SUPPORTED: zfcp_fsf_class_not_supp(req); @@ -2258,7 +2258,8 @@ int zfcp_fsf_fcp_cmnd(struct scsi_cmnd *scsi_cmnd) fcp_cmnd = (struct fcp_cmnd *) &req->qtcb->bottom.io.fcp_cmnd; zfcp_fc_scsi_to_fcp(fcp_cmnd, scsi_cmnd, 0); - if (scsi_prot_sg_count(scsi_cmnd)) { + if ((scsi_get_prot_op(scsi_cmnd) != SCSI_PROT_NORMAL) && + scsi_prot_sg_count(scsi_cmnd)) { zfcp_qdio_set_data_div(qdio, &req->qdio_req, scsi_prot_sg_count(scsi_cmnd)); retval = zfcp_qdio_sbals_from_sg(qdio, &req->qdio_req, diff --git a/drivers/s390/scsi/zfcp_scsi.c b/drivers/s390/scsi/zfcp_scsi.c index 07ffdbb5107f..9bd9b9a29dfc 100644 --- a/drivers/s390/scsi/zfcp_scsi.c +++ b/drivers/s390/scsi/zfcp_scsi.c @@ -3,7 +3,7 @@ * * Interface to Linux SCSI midlayer. * - * Copyright IBM Corp. 2002, 2016 + * Copyright IBM Corp. 2002, 2017 */ #define KMSG_COMPONENT "zfcp" @@ -273,25 +273,29 @@ static int zfcp_task_mgmt_function(struct scsi_cmnd *scpnt, u8 tm_flags) zfcp_erp_wait(adapter); ret = fc_block_scsi_eh(scpnt); - if (ret) + if (ret) { + zfcp_dbf_scsi_devreset("fiof", scpnt, tm_flags, NULL); return ret; + } if (!(atomic_read(&adapter->status) & ZFCP_STATUS_COMMON_RUNNING)) { - zfcp_dbf_scsi_devreset("nres", scpnt, tm_flags); + zfcp_dbf_scsi_devreset("nres", scpnt, tm_flags, NULL); return SUCCESS; } } - if (!fsf_req) + if (!fsf_req) { + zfcp_dbf_scsi_devreset("reqf", scpnt, tm_flags, NULL); return FAILED; + } wait_for_completion(&fsf_req->completion); if (fsf_req->status & ZFCP_STATUS_FSFREQ_TMFUNCFAILED) { - zfcp_dbf_scsi_devreset("fail", scpnt, tm_flags); + zfcp_dbf_scsi_devreset("fail", scpnt, tm_flags, fsf_req); retval = FAILED; } else { - zfcp_dbf_scsi_devreset("okay", scpnt, tm_flags); + zfcp_dbf_scsi_devreset("okay", scpnt, tm_flags, fsf_req); zfcp_scsi_forget_cmnds(zfcp_sdev, tm_flags); } diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index 17c440b9d086..6835bae33ec4 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -1824,9 +1824,12 @@ static void megasas_complete_outstanding_ioctls(struct megasas_instance *instanc if (cmd_fusion->sync_cmd_idx != (u32)ULONG_MAX) { cmd_mfi = instance->cmd_list[cmd_fusion->sync_cmd_idx]; if (cmd_mfi->sync_cmd && - cmd_mfi->frame->hdr.cmd != MFI_CMD_ABORT) + (cmd_mfi->frame->hdr.cmd != MFI_CMD_ABORT)) { + cmd_mfi->frame->hdr.cmd_status = + MFI_STAT_WRONG_STATE; megasas_complete_cmd(instance, cmd_mfi, DID_OK); + } } } } else { @@ -5094,6 +5097,14 @@ megasas_register_aen(struct megasas_instance *instance, u32 seq_num, prev_aen.word = le32_to_cpu(instance->aen_cmd->frame->dcmd.mbox.w[1]); + if ((curr_aen.members.class < MFI_EVT_CLASS_DEBUG) || + (curr_aen.members.class > MFI_EVT_CLASS_DEAD)) { + dev_info(&instance->pdev->dev, + "%s %d out of range class %d send by application\n", + __func__, __LINE__, curr_aen.members.class); + return 0; + } + /* * A class whose enum value is smaller is inclusive of all * higher values. If a PROGRESS (= -1) was previously diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c index 1ed85dfc008d..ac12ee844bfc 100644 --- a/drivers/scsi/qla2xxx/qla_attr.c +++ b/drivers/scsi/qla2xxx/qla_attr.c @@ -404,6 +404,8 @@ qla2x00_sysfs_write_optrom_ctl(struct file *filp, struct kobject *kobj, return -EINVAL; if (start > ha->optrom_size) return -EINVAL; + if (size > ha->optrom_size - start) + size = ha->optrom_size - start; mutex_lock(&ha->optrom_mutex); switch (val) { @@ -429,8 +431,7 @@ qla2x00_sysfs_write_optrom_ctl(struct file *filp, struct kobject *kobj, } ha->optrom_region_start = start; - ha->optrom_region_size = start + size > ha->optrom_size ? - ha->optrom_size - start : size; + ha->optrom_region_size = start + size; ha->optrom_state = QLA_SREADING; ha->optrom_buffer = vmalloc(ha->optrom_region_size); @@ -503,8 +504,7 @@ qla2x00_sysfs_write_optrom_ctl(struct file *filp, struct kobject *kobj, } ha->optrom_region_start = start; - ha->optrom_region_size = start + size > ha->optrom_size ? - ha->optrom_size - start : size; + ha->optrom_region_size = start + size; ha->optrom_state = QLA_SWRITING; ha->optrom_buffer = vmalloc(ha->optrom_region_size); diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 06bef0fc43c7..b0e2e292e3cb 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -133,7 +133,7 @@ struct sg_device; /* forward declarations */ struct sg_fd; typedef struct sg_request { /* SG_MAX_QUEUE requests outstanding per file */ - struct sg_request *nextrp; /* NULL -> tail request (slist) */ + struct list_head entry; /* list entry */ struct sg_fd *parentfp; /* NULL -> not in use */ Sg_scatter_hold data; /* hold buffer, perhaps scatter list */ sg_io_hdr_t header; /* scsi command+info, see <scsi/sg.h> */ @@ -157,8 +157,7 @@ typedef struct sg_fd { /* holds the state of a file descriptor */ int timeout; /* defaults to SG_DEFAULT_TIMEOUT */ int timeout_user; /* defaults to SG_DEFAULT_TIMEOUT_USER */ Sg_scatter_hold reserve; /* buffer held for this file descriptor */ - unsigned save_scat_len; /* original length of trunc. scat. element */ - Sg_request *headrp; /* head of request slist, NULL->empty */ + struct list_head rq_list; /* head of request list */ struct fasync_struct *async_qp; /* used by asynchronous notification */ Sg_request req_arr[SG_MAX_QUEUE]; /* used as singly-linked list */ char low_dma; /* as in parent but possibly overridden to 1 */ @@ -840,6 +839,39 @@ static int max_sectors_bytes(struct request_queue *q) return max_sectors << 9; } +static void +sg_fill_request_table(Sg_fd *sfp, sg_req_info_t *rinfo) +{ + Sg_request *srp; + int val; + unsigned int ms; + + val = 0; + list_for_each_entry(srp, &sfp->rq_list, entry) { + if (val > SG_MAX_QUEUE) + break; + rinfo[val].req_state = srp->done + 1; + rinfo[val].problem = + srp->header.masked_status & + srp->header.host_status & + srp->header.driver_status; + if (srp->done) + rinfo[val].duration = + srp->header.duration; + else { + ms = jiffies_to_msecs(jiffies); + rinfo[val].duration = + (ms > srp->header.duration) ? + (ms - srp->header.duration) : 0; + } + rinfo[val].orphan = srp->orphan; + rinfo[val].sg_io_owned = srp->sg_io_owned; + rinfo[val].pack_id = srp->header.pack_id; + rinfo[val].usr_ptr = srp->header.usr_ptr; + val++; + } +} + static long sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg) { @@ -951,7 +983,7 @@ sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg) if (!access_ok(VERIFY_WRITE, ip, sizeof (int))) return -EFAULT; read_lock_irqsave(&sfp->rq_list_lock, iflags); - for (srp = sfp->headrp; srp; srp = srp->nextrp) { + list_for_each_entry(srp, &sfp->rq_list, entry) { if ((1 == srp->done) && (!srp->sg_io_owned)) { read_unlock_irqrestore(&sfp->rq_list_lock, iflags); @@ -964,7 +996,8 @@ sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg) return 0; case SG_GET_NUM_WAITING: read_lock_irqsave(&sfp->rq_list_lock, iflags); - for (val = 0, srp = sfp->headrp; srp; srp = srp->nextrp) { + val = 0; + list_for_each_entry(srp, &sfp->rq_list, entry) { if ((1 == srp->done) && (!srp->sg_io_owned)) ++val; } @@ -1032,42 +1065,15 @@ sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg) return -EFAULT; else { sg_req_info_t *rinfo; - unsigned int ms; - rinfo = kmalloc(SZ_SG_REQ_INFO * SG_MAX_QUEUE, - GFP_KERNEL); + rinfo = kzalloc(SZ_SG_REQ_INFO * SG_MAX_QUEUE, + GFP_KERNEL); if (!rinfo) return -ENOMEM; read_lock_irqsave(&sfp->rq_list_lock, iflags); - for (srp = sfp->headrp, val = 0; val < SG_MAX_QUEUE; - ++val, srp = srp ? srp->nextrp : srp) { - memset(&rinfo[val], 0, SZ_SG_REQ_INFO); - if (srp) { - rinfo[val].req_state = srp->done + 1; - rinfo[val].problem = - srp->header.masked_status & - srp->header.host_status & - srp->header.driver_status; - if (srp->done) - rinfo[val].duration = - srp->header.duration; - else { - ms = jiffies_to_msecs(jiffies); - rinfo[val].duration = - (ms > srp->header.duration) ? - (ms - srp->header.duration) : 0; - } - rinfo[val].orphan = srp->orphan; - rinfo[val].sg_io_owned = - srp->sg_io_owned; - rinfo[val].pack_id = - srp->header.pack_id; - rinfo[val].usr_ptr = - srp->header.usr_ptr; - } - } + sg_fill_request_table(sfp, rinfo); read_unlock_irqrestore(&sfp->rq_list_lock, iflags); - result = __copy_to_user(p, rinfo, + result = __copy_to_user(p, rinfo, SZ_SG_REQ_INFO * SG_MAX_QUEUE); result = result ? -EFAULT : 0; kfree(rinfo); @@ -1173,7 +1179,7 @@ sg_poll(struct file *filp, poll_table * wait) return POLLERR; poll_wait(filp, &sfp->read_wait, wait); read_lock_irqsave(&sfp->rq_list_lock, iflags); - for (srp = sfp->headrp; srp; srp = srp->nextrp) { + list_for_each_entry(srp, &sfp->rq_list, entry) { /* if any read waiting, flag it */ if ((0 == res) && (1 == srp->done) && (!srp->sg_io_owned)) res = POLLIN | POLLRDNORM; @@ -2056,7 +2062,6 @@ sg_unlink_reserve(Sg_fd * sfp, Sg_request * srp) req_schp->pages = NULL; req_schp->page_order = 0; req_schp->sglist_len = 0; - sfp->save_scat_len = 0; srp->res_used = 0; /* Called without mutex lock to avoid deadlock */ sfp->res_in_use = 0; @@ -2069,7 +2074,7 @@ sg_get_rq_mark(Sg_fd * sfp, int pack_id) unsigned long iflags; write_lock_irqsave(&sfp->rq_list_lock, iflags); - for (resp = sfp->headrp; resp; resp = resp->nextrp) { + list_for_each_entry(resp, &sfp->rq_list, entry) { /* look for requests that are ready + not SG_IO owned */ if ((1 == resp->done) && (!resp->sg_io_owned) && ((-1 == pack_id) || (resp->header.pack_id == pack_id))) { @@ -2087,70 +2092,45 @@ sg_add_request(Sg_fd * sfp) { int k; unsigned long iflags; - Sg_request *resp; Sg_request *rp = sfp->req_arr; write_lock_irqsave(&sfp->rq_list_lock, iflags); - resp = sfp->headrp; - if (!resp) { - memset(rp, 0, sizeof (Sg_request)); - rp->parentfp = sfp; - resp = rp; - sfp->headrp = resp; - } else { - if (0 == sfp->cmd_q) - resp = NULL; /* command queuing disallowed */ - else { - for (k = 0; k < SG_MAX_QUEUE; ++k, ++rp) { - if (!rp->parentfp) - break; - } - if (k < SG_MAX_QUEUE) { - memset(rp, 0, sizeof (Sg_request)); - rp->parentfp = sfp; - while (resp->nextrp) - resp = resp->nextrp; - resp->nextrp = rp; - resp = rp; - } else - resp = NULL; + if (!list_empty(&sfp->rq_list)) { + if (!sfp->cmd_q) + goto out_unlock; + + for (k = 0; k < SG_MAX_QUEUE; ++k, ++rp) { + if (!rp->parentfp) + break; } + if (k >= SG_MAX_QUEUE) + goto out_unlock; } - if (resp) { - resp->nextrp = NULL; - resp->header.duration = jiffies_to_msecs(jiffies); - } + memset(rp, 0, sizeof (Sg_request)); + rp->parentfp = sfp; + rp->header.duration = jiffies_to_msecs(jiffies); + list_add_tail(&rp->entry, &sfp->rq_list); write_unlock_irqrestore(&sfp->rq_list_lock, iflags); - return resp; + return rp; +out_unlock: + write_unlock_irqrestore(&sfp->rq_list_lock, iflags); + return NULL; } /* Return of 1 for found; 0 for not found */ static int sg_remove_request(Sg_fd * sfp, Sg_request * srp) { - Sg_request *prev_rp; - Sg_request *rp; unsigned long iflags; int res = 0; - if ((!sfp) || (!srp) || (!sfp->headrp)) + if (!sfp || !srp || list_empty(&sfp->rq_list)) return res; write_lock_irqsave(&sfp->rq_list_lock, iflags); - prev_rp = sfp->headrp; - if (srp == prev_rp) { - sfp->headrp = prev_rp->nextrp; - prev_rp->parentfp = NULL; + if (!list_empty(&srp->entry)) { + list_del(&srp->entry); + srp->parentfp = NULL; res = 1; - } else { - while ((rp = prev_rp->nextrp)) { - if (srp == rp) { - prev_rp->nextrp = rp->nextrp; - rp->parentfp = NULL; - res = 1; - break; - } - prev_rp = rp; - } } write_unlock_irqrestore(&sfp->rq_list_lock, iflags); return res; @@ -2169,7 +2149,7 @@ sg_add_sfp(Sg_device * sdp) init_waitqueue_head(&sfp->read_wait); rwlock_init(&sfp->rq_list_lock); - + INIT_LIST_HEAD(&sfp->rq_list); kref_init(&sfp->f_ref); mutex_init(&sfp->f_mutex); sfp->timeout = SG_DEFAULT_TIMEOUT; @@ -2210,10 +2190,13 @@ sg_remove_sfp_usercontext(struct work_struct *work) { struct sg_fd *sfp = container_of(work, struct sg_fd, ew.work); struct sg_device *sdp = sfp->parentdp; + Sg_request *srp; /* Cleanup any responses which were never read(). */ - while (sfp->headrp) - sg_finish_rem_req(sfp->headrp); + while (!list_empty(&sfp->rq_list)) { + srp = list_first_entry(&sfp->rq_list, Sg_request, entry); + sg_finish_rem_req(srp); + } if (sfp->reserve.bufflen > 0) { SCSI_LOG_TIMEOUT(6, sg_printk(KERN_INFO, sdp, @@ -2616,7 +2599,7 @@ static int sg_proc_seq_show_devstrs(struct seq_file *s, void *v) /* must be called while holding sg_index_lock */ static void sg_proc_debug_helper(struct seq_file *s, Sg_device * sdp) { - int k, m, new_interface, blen, usg; + int k, new_interface, blen, usg; Sg_request *srp; Sg_fd *fp; const sg_io_hdr_t *hp; @@ -2636,13 +2619,11 @@ static void sg_proc_debug_helper(struct seq_file *s, Sg_device * sdp) seq_printf(s, " cmd_q=%d f_packid=%d k_orphan=%d closed=0\n", (int) fp->cmd_q, (int) fp->force_packid, (int) fp->keep_orphan); - for (m = 0, srp = fp->headrp; - srp != NULL; - ++m, srp = srp->nextrp) { + list_for_each_entry(srp, &fp->rq_list, entry) { hp = &srp->header; new_interface = (hp->interface_id == '\0') ? 0 : 1; if (srp->res_used) { - if (new_interface && + if (new_interface && (SG_FLAG_MMAP_IO & hp->flags)) cp = " mmap>> "; else @@ -2673,7 +2654,7 @@ static void sg_proc_debug_helper(struct seq_file *s, Sg_device * sdp) seq_printf(s, "ms sgat=%d op=0x%02x\n", usg, (int) srp->data.cmd_opcode); } - if (0 == m) + if (list_empty(&fp->rq_list)) seq_puts(s, " No requests active\n"); read_unlock(&fp->rq_list_lock); } diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index cd5c1c060481..6df2841cb7f9 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1511,6 +1511,8 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd) ret = storvsc_do_io(dev, cmd_request); if (ret == -EAGAIN) { + if (payload_sz > sizeof(cmd_request->mpb)) + kfree(payload); /* no more space */ return SCSI_MLQUEUE_DEVICE_BUSY; } diff --git a/drivers/tty/tty_buffer.c b/drivers/tty/tty_buffer.c index fb31eecb708d..8f3566cde3eb 100644 --- a/drivers/tty/tty_buffer.c +++ b/drivers/tty/tty_buffer.c @@ -362,6 +362,32 @@ int tty_insert_flip_string_flags(struct tty_port *port, EXPORT_SYMBOL(tty_insert_flip_string_flags); /** + * __tty_insert_flip_char - Add one character to the tty buffer + * @port: tty port + * @ch: character + * @flag: flag byte + * + * Queue a single byte to the tty buffering, with an optional flag. + * This is the slow path of tty_insert_flip_char. + */ +int __tty_insert_flip_char(struct tty_port *port, unsigned char ch, char flag) +{ + struct tty_buffer *tb; + int flags = (flag == TTY_NORMAL) ? TTYB_NORMAL : 0; + + if (!__tty_buffer_request_room(port, 1, flags)) + return 0; + + tb = port->buf.tail; + if (~tb->flags & TTYB_NORMAL) + *flag_buf_ptr(tb, tb->used) = flag; + *char_buf_ptr(tb, tb->used++) = ch; + + return 1; +} +EXPORT_SYMBOL(__tty_insert_flip_char); + +/** * tty_schedule_flip - push characters to ldisc * @port: tty port to push from * diff --git a/fs/Kconfig b/fs/Kconfig index 4adb93ec85ea..89ddd182f568 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -73,6 +73,8 @@ config FILE_LOCKING for filesystems like NFS and for the flock() system call. Disabling this option saves about 11k. +source "fs/crypto/Kconfig" + source "fs/notify/Kconfig" source "fs/quota/Kconfig" diff --git a/fs/Makefile b/fs/Makefile index dee237540bc0..4644db462ba9 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -30,6 +30,7 @@ obj-$(CONFIG_EVENTFD) += eventfd.o obj-$(CONFIG_USERFAULTFD) += userfaultfd.o obj-$(CONFIG_AIO) += aio.o obj-$(CONFIG_FS_DAX) += dax.o +obj-$(CONFIG_FS_ENCRYPTION) += crypto/ obj-$(CONFIG_FILE_LOCKING) += locks.o obj-$(CONFIG_COMPAT) += compat.o compat_ioctl.o obj-$(CONFIG_BINFMT_AOUT) += binfmt_aout.o diff --git a/fs/crypto/Kconfig b/fs/crypto/Kconfig new file mode 100644 index 000000000000..92348faf9865 --- /dev/null +++ b/fs/crypto/Kconfig @@ -0,0 +1,18 @@ +config FS_ENCRYPTION + tristate "FS Encryption (Per-file encryption)" + depends on BLOCK + select CRYPTO + select CRYPTO_AES + select CRYPTO_CBC + select CRYPTO_ECB + select CRYPTO_XTS + select CRYPTO_CTS + select CRYPTO_CTR + select CRYPTO_SHA256 + select KEYS + select ENCRYPTED_KEYS + help + Enable encryption of files and directories. This + feature is similar to ecryptfs, but it is more memory + efficient since it avoids caching the encrypted and + decrypted pages in the page cache. diff --git a/fs/crypto/Makefile b/fs/crypto/Makefile new file mode 100644 index 000000000000..f17684c48739 --- /dev/null +++ b/fs/crypto/Makefile @@ -0,0 +1,3 @@ +obj-$(CONFIG_FS_ENCRYPTION) += fscrypto.o + +fscrypto-y := crypto.o fname.o policy.o keyinfo.o diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c new file mode 100644 index 000000000000..2d40ab9edc9f --- /dev/null +++ b/fs/crypto/crypto.c @@ -0,0 +1,568 @@ +/* + * This contains encryption functions for per-file encryption. + * + * Copyright (C) 2015, Google, Inc. + * Copyright (C) 2015, Motorola Mobility + * + * Written by Michael Halcrow, 2014. + * + * Filename encryption additions + * Uday Savagaonkar, 2014 + * Encryption policy handling additions + * Ildar Muslukhov, 2014 + * Add fscrypt_pullback_bio_page() + * Jaegeuk Kim, 2015. + * + * This has not yet undergone a rigorous security audit. + * + * The usage of AES-XTS should conform to recommendations in NIST + * Special Publication 800-38E and IEEE P1619/D16. + */ + +#include <linux/pagemap.h> +#include <linux/mempool.h> +#include <linux/module.h> +#include <linux/scatterlist.h> +#include <linux/ratelimit.h> +#include <linux/bio.h> +#include <linux/dcache.h> +#include <linux/namei.h> +#include <linux/fscrypto.h> + +static unsigned int num_prealloc_crypto_pages = 32; +static unsigned int num_prealloc_crypto_ctxs = 128; + +module_param(num_prealloc_crypto_pages, uint, 0444); +MODULE_PARM_DESC(num_prealloc_crypto_pages, + "Number of crypto pages to preallocate"); +module_param(num_prealloc_crypto_ctxs, uint, 0444); +MODULE_PARM_DESC(num_prealloc_crypto_ctxs, + "Number of crypto contexts to preallocate"); + +static mempool_t *fscrypt_bounce_page_pool = NULL; + +static LIST_HEAD(fscrypt_free_ctxs); +static DEFINE_SPINLOCK(fscrypt_ctx_lock); + +static struct workqueue_struct *fscrypt_read_workqueue; +static DEFINE_MUTEX(fscrypt_init_mutex); + +static struct kmem_cache *fscrypt_ctx_cachep; +struct kmem_cache *fscrypt_info_cachep; + +/** + * fscrypt_release_ctx() - Releases an encryption context + * @ctx: The encryption context to release. + * + * If the encryption context was allocated from the pre-allocated pool, returns + * it to that pool. Else, frees it. + * + * If there's a bounce page in the context, this frees that. + */ +void fscrypt_release_ctx(struct fscrypt_ctx *ctx) +{ + unsigned long flags; + + if (ctx->flags & FS_WRITE_PATH_FL && ctx->w.bounce_page) { + mempool_free(ctx->w.bounce_page, fscrypt_bounce_page_pool); + ctx->w.bounce_page = NULL; + } + ctx->w.control_page = NULL; + if (ctx->flags & FS_CTX_REQUIRES_FREE_ENCRYPT_FL) { + kmem_cache_free(fscrypt_ctx_cachep, ctx); + } else { + spin_lock_irqsave(&fscrypt_ctx_lock, flags); + list_add(&ctx->free_list, &fscrypt_free_ctxs); + spin_unlock_irqrestore(&fscrypt_ctx_lock, flags); + } +} +EXPORT_SYMBOL(fscrypt_release_ctx); + +/** + * fscrypt_get_ctx() - Gets an encryption context + * @inode: The inode for which we are doing the crypto + * @gfp_flags: The gfp flag for memory allocation + * + * Allocates and initializes an encryption context. + * + * Return: An allocated and initialized encryption context on success; error + * value or NULL otherwise. + */ +struct fscrypt_ctx *fscrypt_get_ctx(struct inode *inode, gfp_t gfp_flags) +{ + struct fscrypt_ctx *ctx = NULL; + struct fscrypt_info *ci = inode->i_crypt_info; + unsigned long flags; + + if (ci == NULL) + return ERR_PTR(-ENOKEY); + + /* + * We first try getting the ctx from a free list because in + * the common case the ctx will have an allocated and + * initialized crypto tfm, so it's probably a worthwhile + * optimization. For the bounce page, we first try getting it + * from the kernel allocator because that's just about as fast + * as getting it from a list and because a cache of free pages + * should generally be a "last resort" option for a filesystem + * to be able to do its job. + */ + spin_lock_irqsave(&fscrypt_ctx_lock, flags); + ctx = list_first_entry_or_null(&fscrypt_free_ctxs, + struct fscrypt_ctx, free_list); + if (ctx) + list_del(&ctx->free_list); + spin_unlock_irqrestore(&fscrypt_ctx_lock, flags); + if (!ctx) { + ctx = kmem_cache_zalloc(fscrypt_ctx_cachep, gfp_flags); + if (!ctx) + return ERR_PTR(-ENOMEM); + ctx->flags |= FS_CTX_REQUIRES_FREE_ENCRYPT_FL; + } else { + ctx->flags &= ~FS_CTX_REQUIRES_FREE_ENCRYPT_FL; + } + ctx->flags &= ~FS_WRITE_PATH_FL; + return ctx; +} +EXPORT_SYMBOL(fscrypt_get_ctx); + +/** + * page_crypt_complete() - completion callback for page crypto + * @req: The asynchronous cipher request context + * @res: The result of the cipher operation + */ +static void page_crypt_complete(struct crypto_async_request *req, int res) +{ + struct fscrypt_completion_result *ecr = req->data; + + if (res == -EINPROGRESS) + return; + ecr->res = res; + complete(&ecr->completion); +} + +typedef enum { + FS_DECRYPT = 0, + FS_ENCRYPT, +} fscrypt_direction_t; + +static int do_page_crypto(struct inode *inode, + fscrypt_direction_t rw, pgoff_t index, + struct page *src_page, struct page *dest_page, + gfp_t gfp_flags) +{ + struct { + __le64 index; + u8 padding[FS_XTS_TWEAK_SIZE - sizeof(__le64)]; + } xts_tweak; + struct skcipher_request *req = NULL; + DECLARE_FS_COMPLETION_RESULT(ecr); + struct scatterlist dst, src; + struct fscrypt_info *ci = inode->i_crypt_info; + struct crypto_skcipher *tfm = ci->ci_ctfm; + int res = 0; + + req = skcipher_request_alloc(tfm, gfp_flags); + if (!req) { + printk_ratelimited(KERN_ERR + "%s: crypto_request_alloc() failed\n", + __func__); + return -ENOMEM; + } + + skcipher_request_set_callback( + req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, + page_crypt_complete, &ecr); + + BUILD_BUG_ON(sizeof(xts_tweak) != FS_XTS_TWEAK_SIZE); + xts_tweak.index = cpu_to_le64(index); + memset(xts_tweak.padding, 0, sizeof(xts_tweak.padding)); + + sg_init_table(&dst, 1); + sg_set_page(&dst, dest_page, PAGE_SIZE, 0); + sg_init_table(&src, 1); + sg_set_page(&src, src_page, PAGE_SIZE, 0); + skcipher_request_set_crypt(req, &src, &dst, PAGE_SIZE, &xts_tweak); + if (rw == FS_DECRYPT) + res = crypto_skcipher_decrypt(req); + else + res = crypto_skcipher_encrypt(req); + if (res == -EINPROGRESS || res == -EBUSY) { + BUG_ON(req->base.data != &ecr); + wait_for_completion(&ecr.completion); + res = ecr.res; + } + skcipher_request_free(req); + if (res) { + printk_ratelimited(KERN_ERR + "%s: crypto_skcipher_encrypt() returned %d\n", + __func__, res); + return res; + } + return 0; +} + +static struct page *alloc_bounce_page(struct fscrypt_ctx *ctx, gfp_t gfp_flags) +{ + ctx->w.bounce_page = mempool_alloc(fscrypt_bounce_page_pool, gfp_flags); + if (ctx->w.bounce_page == NULL) + return ERR_PTR(-ENOMEM); + ctx->flags |= FS_WRITE_PATH_FL; + return ctx->w.bounce_page; +} + +/** + * fscypt_encrypt_page() - Encrypts a page + * @inode: The inode for which the encryption should take place + * @plaintext_page: The page to encrypt. Must be locked. + * @gfp_flags: The gfp flag for memory allocation + * + * Allocates a ciphertext page and encrypts plaintext_page into it using the ctx + * encryption context. + * + * Called on the page write path. The caller must call + * fscrypt_restore_control_page() on the returned ciphertext page to + * release the bounce buffer and the encryption context. + * + * Return: An allocated page with the encrypted content on success. Else, an + * error value or NULL. + */ +struct page *fscrypt_encrypt_page(struct inode *inode, + struct page *plaintext_page, gfp_t gfp_flags) +{ + struct fscrypt_ctx *ctx; + struct page *ciphertext_page = NULL; + int err; + + BUG_ON(!PageLocked(plaintext_page)); + + ctx = fscrypt_get_ctx(inode, gfp_flags); + if (IS_ERR(ctx)) + return (struct page *)ctx; + + /* The encryption operation will require a bounce page. */ + ciphertext_page = alloc_bounce_page(ctx, gfp_flags); + if (IS_ERR(ciphertext_page)) + goto errout; + + ctx->w.control_page = plaintext_page; + err = do_page_crypto(inode, FS_ENCRYPT, plaintext_page->index, + plaintext_page, ciphertext_page, + gfp_flags); + if (err) { + ciphertext_page = ERR_PTR(err); + goto errout; + } + SetPagePrivate(ciphertext_page); + set_page_private(ciphertext_page, (unsigned long)ctx); + lock_page(ciphertext_page); + return ciphertext_page; + +errout: + fscrypt_release_ctx(ctx); + return ciphertext_page; +} +EXPORT_SYMBOL(fscrypt_encrypt_page); + +/** + * f2crypt_decrypt_page() - Decrypts a page in-place + * @page: The page to decrypt. Must be locked. + * + * Decrypts page in-place using the ctx encryption context. + * + * Called from the read completion callback. + * + * Return: Zero on success, non-zero otherwise. + */ +int fscrypt_decrypt_page(struct page *page) +{ + BUG_ON(!PageLocked(page)); + + return do_page_crypto(page->mapping->host, + FS_DECRYPT, page->index, page, page, GFP_NOFS); +} +EXPORT_SYMBOL(fscrypt_decrypt_page); + +int fscrypt_zeroout_range(struct inode *inode, pgoff_t lblk, + sector_t pblk, unsigned int len) +{ + struct fscrypt_ctx *ctx; + struct page *ciphertext_page = NULL; + struct bio *bio; + int ret, err = 0; + + BUG_ON(inode->i_sb->s_blocksize != PAGE_SIZE); + + ctx = fscrypt_get_ctx(inode, GFP_NOFS); + if (IS_ERR(ctx)) + return PTR_ERR(ctx); + + ciphertext_page = alloc_bounce_page(ctx, GFP_NOWAIT); + if (IS_ERR(ciphertext_page)) { + err = PTR_ERR(ciphertext_page); + goto errout; + } + + while (len--) { + err = do_page_crypto(inode, FS_ENCRYPT, lblk, + ZERO_PAGE(0), ciphertext_page, + GFP_NOFS); + if (err) + goto errout; + + bio = bio_alloc(GFP_NOWAIT, 1); + if (!bio) { + err = -ENOMEM; + goto errout; + } + bio->bi_bdev = inode->i_sb->s_bdev; + bio->bi_iter.bi_sector = + pblk << (inode->i_sb->s_blocksize_bits - 9); + ret = bio_add_page(bio, ciphertext_page, + inode->i_sb->s_blocksize, 0); + if (ret != inode->i_sb->s_blocksize) { + /* should never happen! */ + WARN_ON(1); + bio_put(bio); + err = -EIO; + goto errout; + } + err = submit_bio_wait(WRITE, bio); + if ((err == 0) && bio->bi_error) + err = -EIO; + bio_put(bio); + if (err) + goto errout; + lblk++; + pblk++; + } + err = 0; +errout: + fscrypt_release_ctx(ctx); + return err; +} +EXPORT_SYMBOL(fscrypt_zeroout_range); + +/* + * Validate dentries for encrypted directories to make sure we aren't + * potentially caching stale data after a key has been added or + * removed. + */ +static int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags) +{ + struct dentry *dir; + struct fscrypt_info *ci; + int dir_has_key, cached_with_key; + + if (flags & LOOKUP_RCU) + return -ECHILD; + + dir = dget_parent(dentry); + if (!d_inode(dir)->i_sb->s_cop->is_encrypted(d_inode(dir))) { + dput(dir); + return 0; + } + + ci = d_inode(dir)->i_crypt_info; + if (ci && ci->ci_keyring_key && + (ci->ci_keyring_key->flags & ((1 << KEY_FLAG_INVALIDATED) | + (1 << KEY_FLAG_REVOKED) | + (1 << KEY_FLAG_DEAD)))) + ci = NULL; + + /* this should eventually be an flag in d_flags */ + spin_lock(&dentry->d_lock); + cached_with_key = dentry->d_flags & DCACHE_ENCRYPTED_WITH_KEY; + spin_unlock(&dentry->d_lock); + dir_has_key = (ci != NULL); + dput(dir); + + /* + * If the dentry was cached without the key, and it is a + * negative dentry, it might be a valid name. We can't check + * if the key has since been made available due to locking + * reasons, so we fail the validation so ext4_lookup() can do + * this check. + * + * We also fail the validation if the dentry was created with + * the key present, but we no longer have the key, or vice versa. + */ + if ((!cached_with_key && d_is_negative(dentry)) || + (!cached_with_key && dir_has_key) || + (cached_with_key && !dir_has_key)) + return 0; + return 1; +} + +const struct dentry_operations fscrypt_d_ops = { + .d_revalidate = fscrypt_d_revalidate, +}; +EXPORT_SYMBOL(fscrypt_d_ops); + +/* + * Call fscrypt_decrypt_page on every single page, reusing the encryption + * context. + */ +static void completion_pages(struct work_struct *work) +{ + struct fscrypt_ctx *ctx = + container_of(work, struct fscrypt_ctx, r.work); + struct bio *bio = ctx->r.bio; + struct bio_vec *bv; + int i; + + bio_for_each_segment_all(bv, bio, i) { + struct page *page = bv->bv_page; + int ret = fscrypt_decrypt_page(page); + + if (ret) { + WARN_ON_ONCE(1); + SetPageError(page); + } else { + SetPageUptodate(page); + } + unlock_page(page); + } + fscrypt_release_ctx(ctx); + bio_put(bio); +} + +void fscrypt_decrypt_bio_pages(struct fscrypt_ctx *ctx, struct bio *bio) +{ + INIT_WORK(&ctx->r.work, completion_pages); + ctx->r.bio = bio; + queue_work(fscrypt_read_workqueue, &ctx->r.work); +} +EXPORT_SYMBOL(fscrypt_decrypt_bio_pages); + +void fscrypt_pullback_bio_page(struct page **page, bool restore) +{ + struct fscrypt_ctx *ctx; + struct page *bounce_page; + + /* The bounce data pages are unmapped. */ + if ((*page)->mapping) + return; + + /* The bounce data page is unmapped. */ + bounce_page = *page; + ctx = (struct fscrypt_ctx *)page_private(bounce_page); + + /* restore control page */ + *page = ctx->w.control_page; + + if (restore) + fscrypt_restore_control_page(bounce_page); +} +EXPORT_SYMBOL(fscrypt_pullback_bio_page); + +void fscrypt_restore_control_page(struct page *page) +{ + struct fscrypt_ctx *ctx; + + ctx = (struct fscrypt_ctx *)page_private(page); + set_page_private(page, (unsigned long)NULL); + ClearPagePrivate(page); + unlock_page(page); + fscrypt_release_ctx(ctx); +} +EXPORT_SYMBOL(fscrypt_restore_control_page); + +static void fscrypt_destroy(void) +{ + struct fscrypt_ctx *pos, *n; + + list_for_each_entry_safe(pos, n, &fscrypt_free_ctxs, free_list) + kmem_cache_free(fscrypt_ctx_cachep, pos); + INIT_LIST_HEAD(&fscrypt_free_ctxs); + mempool_destroy(fscrypt_bounce_page_pool); + fscrypt_bounce_page_pool = NULL; +} + +/** + * fscrypt_initialize() - allocate major buffers for fs encryption. + * + * We only call this when we start accessing encrypted files, since it + * results in memory getting allocated that wouldn't otherwise be used. + * + * Return: Zero on success, non-zero otherwise. + */ +int fscrypt_initialize(void) +{ + int i, res = -ENOMEM; + + if (fscrypt_bounce_page_pool) + return 0; + + mutex_lock(&fscrypt_init_mutex); + if (fscrypt_bounce_page_pool) + goto already_initialized; + + for (i = 0; i < num_prealloc_crypto_ctxs; i++) { + struct fscrypt_ctx *ctx; + + ctx = kmem_cache_zalloc(fscrypt_ctx_cachep, GFP_NOFS); + if (!ctx) + goto fail; + list_add(&ctx->free_list, &fscrypt_free_ctxs); + } + + fscrypt_bounce_page_pool = + mempool_create_page_pool(num_prealloc_crypto_pages, 0); + if (!fscrypt_bounce_page_pool) + goto fail; + +already_initialized: + mutex_unlock(&fscrypt_init_mutex); + return 0; +fail: + fscrypt_destroy(); + mutex_unlock(&fscrypt_init_mutex); + return res; +} +EXPORT_SYMBOL(fscrypt_initialize); + +/** + * fscrypt_init() - Set up for fs encryption. + */ +static int __init fscrypt_init(void) +{ + fscrypt_read_workqueue = alloc_workqueue("fscrypt_read_queue", + WQ_HIGHPRI, 0); + if (!fscrypt_read_workqueue) + goto fail; + + fscrypt_ctx_cachep = KMEM_CACHE(fscrypt_ctx, SLAB_RECLAIM_ACCOUNT); + if (!fscrypt_ctx_cachep) + goto fail_free_queue; + + fscrypt_info_cachep = KMEM_CACHE(fscrypt_info, SLAB_RECLAIM_ACCOUNT); + if (!fscrypt_info_cachep) + goto fail_free_ctx; + + return 0; + +fail_free_ctx: + kmem_cache_destroy(fscrypt_ctx_cachep); +fail_free_queue: + destroy_workqueue(fscrypt_read_workqueue); +fail: + return -ENOMEM; +} +module_init(fscrypt_init) + +/** + * fscrypt_exit() - Shutdown the fs encryption system + */ +static void __exit fscrypt_exit(void) +{ + fscrypt_destroy(); + + if (fscrypt_read_workqueue) + destroy_workqueue(fscrypt_read_workqueue); + kmem_cache_destroy(fscrypt_ctx_cachep); + kmem_cache_destroy(fscrypt_info_cachep); +} +module_exit(fscrypt_exit); + +MODULE_LICENSE("GPL"); diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c new file mode 100644 index 000000000000..9b774f4b50c8 --- /dev/null +++ b/fs/crypto/fname.c @@ -0,0 +1,414 @@ +/* + * This contains functions for filename crypto management + * + * Copyright (C) 2015, Google, Inc. + * Copyright (C) 2015, Motorola Mobility + * + * Written by Uday Savagaonkar, 2014. + * Modified by Jaegeuk Kim, 2015. + * + * This has not yet undergone a rigorous security audit. + */ + +#include <linux/scatterlist.h> +#include <linux/ratelimit.h> +#include <linux/fscrypto.h> + +/** + * fname_crypt_complete() - completion callback for filename crypto + * @req: The asynchronous cipher request context + * @res: The result of the cipher operation + */ +static void fname_crypt_complete(struct crypto_async_request *req, int res) +{ + struct fscrypt_completion_result *ecr = req->data; + + if (res == -EINPROGRESS) + return; + ecr->res = res; + complete(&ecr->completion); +} + +/** + * fname_encrypt() - encrypt a filename + * + * The caller must have allocated sufficient memory for the @oname string. + * + * Return: 0 on success, -errno on failure + */ +static int fname_encrypt(struct inode *inode, + const struct qstr *iname, struct fscrypt_str *oname) +{ + struct skcipher_request *req = NULL; + DECLARE_FS_COMPLETION_RESULT(ecr); + struct fscrypt_info *ci = inode->i_crypt_info; + struct crypto_skcipher *tfm = ci->ci_ctfm; + int res = 0; + char iv[FS_CRYPTO_BLOCK_SIZE]; + struct scatterlist sg; + int padding = 4 << (ci->ci_flags & FS_POLICY_FLAGS_PAD_MASK); + unsigned int lim; + unsigned int cryptlen; + + lim = inode->i_sb->s_cop->max_namelen(inode); + if (iname->len <= 0 || iname->len > lim) + return -EIO; + + /* + * Copy the filename to the output buffer for encrypting in-place and + * pad it with the needed number of NUL bytes. + */ + cryptlen = max_t(unsigned int, iname->len, FS_CRYPTO_BLOCK_SIZE); + cryptlen = round_up(cryptlen, padding); + cryptlen = min(cryptlen, lim); + memcpy(oname->name, iname->name, iname->len); + memset(oname->name + iname->len, 0, cryptlen - iname->len); + + /* Initialize the IV */ + memset(iv, 0, FS_CRYPTO_BLOCK_SIZE); + + /* Set up the encryption request */ + req = skcipher_request_alloc(tfm, GFP_NOFS); + if (!req) { + printk_ratelimited(KERN_ERR + "%s: skcipher_request_alloc() failed\n", __func__); + return -ENOMEM; + } + skcipher_request_set_callback(req, + CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, + fname_crypt_complete, &ecr); + sg_init_one(&sg, oname->name, cryptlen); + skcipher_request_set_crypt(req, &sg, &sg, cryptlen, iv); + + /* Do the encryption */ + res = crypto_skcipher_encrypt(req); + if (res == -EINPROGRESS || res == -EBUSY) { + /* Request is being completed asynchronously; wait for it */ + wait_for_completion(&ecr.completion); + res = ecr.res; + } + skcipher_request_free(req); + if (res < 0) { + printk_ratelimited(KERN_ERR + "%s: Error (error code %d)\n", __func__, res); + return res; + } + + oname->len = cryptlen; + return 0; +} + +/** + * fname_decrypt() - decrypt a filename + * + * The caller must have allocated sufficient memory for the @oname string. + * + * Return: 0 on success, -errno on failure + */ +static int fname_decrypt(struct inode *inode, + const struct fscrypt_str *iname, + struct fscrypt_str *oname) +{ + struct skcipher_request *req = NULL; + DECLARE_FS_COMPLETION_RESULT(ecr); + struct scatterlist src_sg, dst_sg; + struct fscrypt_info *ci = inode->i_crypt_info; + struct crypto_skcipher *tfm = ci->ci_ctfm; + int res = 0; + char iv[FS_CRYPTO_BLOCK_SIZE]; + unsigned lim; + + lim = inode->i_sb->s_cop->max_namelen(inode); + if (iname->len <= 0 || iname->len > lim) + return -EIO; + + /* Allocate request */ + req = skcipher_request_alloc(tfm, GFP_NOFS); + if (!req) { + printk_ratelimited(KERN_ERR + "%s: crypto_request_alloc() failed\n", __func__); + return -ENOMEM; + } + skcipher_request_set_callback(req, + CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, + fname_crypt_complete, &ecr); + + /* Initialize IV */ + memset(iv, 0, FS_CRYPTO_BLOCK_SIZE); + + /* Create decryption request */ + sg_init_one(&src_sg, iname->name, iname->len); + sg_init_one(&dst_sg, oname->name, oname->len); + skcipher_request_set_crypt(req, &src_sg, &dst_sg, iname->len, iv); + res = crypto_skcipher_decrypt(req); + if (res == -EINPROGRESS || res == -EBUSY) { + wait_for_completion(&ecr.completion); + res = ecr.res; + } + skcipher_request_free(req); + if (res < 0) { + printk_ratelimited(KERN_ERR + "%s: Error (error code %d)\n", __func__, res); + return res; + } + + oname->len = strnlen(oname->name, iname->len); + return 0; +} + +static const char *lookup_table = + "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+,"; + +/** + * digest_encode() - + * + * Encodes the input digest using characters from the set [a-zA-Z0-9_+]. + * The encoded string is roughly 4/3 times the size of the input string. + */ +static int digest_encode(const char *src, int len, char *dst) +{ + int i = 0, bits = 0, ac = 0; + char *cp = dst; + + while (i < len) { + ac += (((unsigned char) src[i]) << bits); + bits += 8; + do { + *cp++ = lookup_table[ac & 0x3f]; + ac >>= 6; + bits -= 6; + } while (bits >= 6); + i++; + } + if (bits) + *cp++ = lookup_table[ac & 0x3f]; + return cp - dst; +} + +static int digest_decode(const char *src, int len, char *dst) +{ + int i = 0, bits = 0, ac = 0; + const char *p; + char *cp = dst; + + while (i < len) { + p = strchr(lookup_table, src[i]); + if (p == NULL || src[i] == 0) + return -2; + ac += (p - lookup_table) << bits; + bits += 6; + if (bits >= 8) { + *cp++ = ac & 0xff; + ac >>= 8; + bits -= 8; + } + i++; + } + if (ac) + return -1; + return cp - dst; +} + +u32 fscrypt_fname_encrypted_size(struct inode *inode, u32 ilen) +{ + int padding = 32; + struct fscrypt_info *ci = inode->i_crypt_info; + + if (ci) + padding = 4 << (ci->ci_flags & FS_POLICY_FLAGS_PAD_MASK); + ilen = max(ilen, (u32)FS_CRYPTO_BLOCK_SIZE); + return round_up(ilen, padding); +} +EXPORT_SYMBOL(fscrypt_fname_encrypted_size); + +/** + * fscrypt_fname_crypto_alloc_obuff() - + * + * Allocates an output buffer that is sufficient for the crypto operation + * specified by the context and the direction. + */ +int fscrypt_fname_alloc_buffer(struct inode *inode, + u32 ilen, struct fscrypt_str *crypto_str) +{ + unsigned int olen = fscrypt_fname_encrypted_size(inode, ilen); + + crypto_str->len = olen; + if (olen < FS_FNAME_CRYPTO_DIGEST_SIZE * 2) + olen = FS_FNAME_CRYPTO_DIGEST_SIZE * 2; + /* + * Allocated buffer can hold one more character to null-terminate the + * string + */ + crypto_str->name = kmalloc(olen + 1, GFP_NOFS); + if (!(crypto_str->name)) + return -ENOMEM; + return 0; +} +EXPORT_SYMBOL(fscrypt_fname_alloc_buffer); + +/** + * fscrypt_fname_crypto_free_buffer() - + * + * Frees the buffer allocated for crypto operation. + */ +void fscrypt_fname_free_buffer(struct fscrypt_str *crypto_str) +{ + if (!crypto_str) + return; + kfree(crypto_str->name); + crypto_str->name = NULL; +} +EXPORT_SYMBOL(fscrypt_fname_free_buffer); + +/** + * fscrypt_fname_disk_to_usr() - converts a filename from disk space to user + * space + * + * The caller must have allocated sufficient memory for the @oname string. + * + * Return: 0 on success, -errno on failure + */ +int fscrypt_fname_disk_to_usr(struct inode *inode, + u32 hash, u32 minor_hash, + const struct fscrypt_str *iname, + struct fscrypt_str *oname) +{ + const struct qstr qname = FSTR_TO_QSTR(iname); + char buf[24]; + + if (fscrypt_is_dot_dotdot(&qname)) { + oname->name[0] = '.'; + oname->name[iname->len - 1] = '.'; + oname->len = iname->len; + return 0; + } + + if (iname->len < FS_CRYPTO_BLOCK_SIZE) + return -EUCLEAN; + + if (inode->i_crypt_info) + return fname_decrypt(inode, iname, oname); + + if (iname->len <= FS_FNAME_CRYPTO_DIGEST_SIZE) { + oname->len = digest_encode(iname->name, iname->len, + oname->name); + return 0; + } + if (hash) { + memcpy(buf, &hash, 4); + memcpy(buf + 4, &minor_hash, 4); + } else { + memset(buf, 0, 8); + } + memcpy(buf + 8, iname->name + iname->len - 16, 16); + oname->name[0] = '_'; + oname->len = 1 + digest_encode(buf, 24, oname->name + 1); + return 0; +} +EXPORT_SYMBOL(fscrypt_fname_disk_to_usr); + +/** + * fscrypt_fname_usr_to_disk() - converts a filename from user space to disk + * space + * + * The caller must have allocated sufficient memory for the @oname string. + * + * Return: 0 on success, -errno on failure + */ +int fscrypt_fname_usr_to_disk(struct inode *inode, + const struct qstr *iname, + struct fscrypt_str *oname) +{ + if (fscrypt_is_dot_dotdot(iname)) { + oname->name[0] = '.'; + oname->name[iname->len - 1] = '.'; + oname->len = iname->len; + return 0; + } + if (inode->i_crypt_info) + return fname_encrypt(inode, iname, oname); + /* + * Without a proper key, a user is not allowed to modify the filenames + * in a directory. Consequently, a user space name cannot be mapped to + * a disk-space name + */ + return -EACCES; +} +EXPORT_SYMBOL(fscrypt_fname_usr_to_disk); + +int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname, + int lookup, struct fscrypt_name *fname) +{ + int ret = 0, bigname = 0; + + memset(fname, 0, sizeof(struct fscrypt_name)); + fname->usr_fname = iname; + + if (!dir->i_sb->s_cop->is_encrypted(dir) || + fscrypt_is_dot_dotdot(iname)) { + fname->disk_name.name = (unsigned char *)iname->name; + fname->disk_name.len = iname->len; + return 0; + } + ret = get_crypt_info(dir); + if (ret && ret != -EOPNOTSUPP) + return ret; + + if (dir->i_crypt_info) { + ret = fscrypt_fname_alloc_buffer(dir, iname->len, + &fname->crypto_buf); + if (ret) + return ret; + ret = fname_encrypt(dir, iname, &fname->crypto_buf); + if (ret) + goto errout; + fname->disk_name.name = fname->crypto_buf.name; + fname->disk_name.len = fname->crypto_buf.len; + return 0; + } + if (!lookup) + return -EACCES; + + /* + * We don't have the key and we are doing a lookup; decode the + * user-supplied name + */ + if (iname->name[0] == '_') + bigname = 1; + if ((bigname && (iname->len != 33)) || (!bigname && (iname->len > 43))) + return -ENOENT; + + fname->crypto_buf.name = kmalloc(32, GFP_KERNEL); + if (fname->crypto_buf.name == NULL) + return -ENOMEM; + + ret = digest_decode(iname->name + bigname, iname->len - bigname, + fname->crypto_buf.name); + if (ret < 0) { + ret = -ENOENT; + goto errout; + } + fname->crypto_buf.len = ret; + if (bigname) { + memcpy(&fname->hash, fname->crypto_buf.name, 4); + memcpy(&fname->minor_hash, fname->crypto_buf.name + 4, 4); + } else { + fname->disk_name.name = fname->crypto_buf.name; + fname->disk_name.len = fname->crypto_buf.len; + } + return 0; + +errout: + fscrypt_fname_free_buffer(&fname->crypto_buf); + return ret; +} +EXPORT_SYMBOL(fscrypt_setup_filename); + +void fscrypt_free_filename(struct fscrypt_name *fname) +{ + kfree(fname->crypto_buf.name); + fname->crypto_buf.name = NULL; + fname->usr_fname = NULL; + fname->disk_name.name = NULL; +} +EXPORT_SYMBOL(fscrypt_free_filename); diff --git a/fs/crypto/keyinfo.c b/fs/crypto/keyinfo.c new file mode 100644 index 000000000000..67fb6d8876d0 --- /dev/null +++ b/fs/crypto/keyinfo.c @@ -0,0 +1,333 @@ +/* + * key management facility for FS encryption support. + * + * Copyright (C) 2015, Google, Inc. + * + * This contains encryption key functions. + * + * Written by Michael Halcrow, Ildar Muslukhov, and Uday Savagaonkar, 2015. + */ + +#include <keys/user-type.h> +#include <linux/scatterlist.h> +#include <linux/fscrypto.h> + +static void derive_crypt_complete(struct crypto_async_request *req, int rc) +{ + struct fscrypt_completion_result *ecr = req->data; + + if (rc == -EINPROGRESS) + return; + + ecr->res = rc; + complete(&ecr->completion); +} + +/** + * derive_key_aes() - Derive a key using AES-128-ECB + * @deriving_key: Encryption key used for derivation. + * @source_key: Source key to which to apply derivation. + * @derived_key: Derived key. + * + * Return: Zero on success; non-zero otherwise. + */ +static int derive_key_aes(u8 deriving_key[FS_AES_128_ECB_KEY_SIZE], + u8 source_key[FS_AES_256_XTS_KEY_SIZE], + u8 derived_key[FS_AES_256_XTS_KEY_SIZE]) +{ + int res = 0; + struct skcipher_request *req = NULL; + DECLARE_FS_COMPLETION_RESULT(ecr); + struct scatterlist src_sg, dst_sg; + struct crypto_skcipher *tfm = crypto_alloc_skcipher("ecb(aes)", 0, 0); + + if (IS_ERR(tfm)) { + res = PTR_ERR(tfm); + tfm = NULL; + goto out; + } + crypto_skcipher_set_flags(tfm, CRYPTO_TFM_REQ_WEAK_KEY); + req = skcipher_request_alloc(tfm, GFP_NOFS); + if (!req) { + res = -ENOMEM; + goto out; + } + skcipher_request_set_callback(req, + CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, + derive_crypt_complete, &ecr); + res = crypto_skcipher_setkey(tfm, deriving_key, + FS_AES_128_ECB_KEY_SIZE); + if (res < 0) + goto out; + + sg_init_one(&src_sg, source_key, FS_AES_256_XTS_KEY_SIZE); + sg_init_one(&dst_sg, derived_key, FS_AES_256_XTS_KEY_SIZE); + skcipher_request_set_crypt(req, &src_sg, &dst_sg, + FS_AES_256_XTS_KEY_SIZE, NULL); + res = crypto_skcipher_encrypt(req); + if (res == -EINPROGRESS || res == -EBUSY) { + wait_for_completion(&ecr.completion); + res = ecr.res; + } +out: + skcipher_request_free(req); + crypto_free_skcipher(tfm); + return res; +} + +static int validate_user_key(struct fscrypt_info *crypt_info, + struct fscrypt_context *ctx, u8 *raw_key, + u8 *prefix, int prefix_size) +{ + u8 *full_key_descriptor; + struct key *keyring_key; + struct fscrypt_key *master_key; + const struct user_key_payload *ukp; + int full_key_len = prefix_size + (FS_KEY_DESCRIPTOR_SIZE * 2) + 1; + int res; + + full_key_descriptor = kmalloc(full_key_len, GFP_NOFS); + if (!full_key_descriptor) + return -ENOMEM; + + memcpy(full_key_descriptor, prefix, prefix_size); + sprintf(full_key_descriptor + prefix_size, + "%*phN", FS_KEY_DESCRIPTOR_SIZE, + ctx->master_key_descriptor); + full_key_descriptor[full_key_len - 1] = '\0'; + keyring_key = request_key(&key_type_logon, full_key_descriptor, NULL); + kfree(full_key_descriptor); + if (IS_ERR(keyring_key)) + return PTR_ERR(keyring_key); + + if (keyring_key->type != &key_type_logon) { + printk_once(KERN_WARNING + "%s: key type must be logon\n", __func__); + res = -ENOKEY; + goto out; + } + down_read(&keyring_key->sem); + ukp = user_key_payload(keyring_key); + if (ukp->datalen != sizeof(struct fscrypt_key)) { + res = -EINVAL; + up_read(&keyring_key->sem); + goto out; + } + master_key = (struct fscrypt_key *)ukp->data; + BUILD_BUG_ON(FS_AES_128_ECB_KEY_SIZE != FS_KEY_DERIVATION_NONCE_SIZE); + + if (master_key->size != FS_AES_256_XTS_KEY_SIZE) { + printk_once(KERN_WARNING + "%s: key size incorrect: %d\n", + __func__, master_key->size); + res = -ENOKEY; + up_read(&keyring_key->sem); + goto out; + } + res = derive_key_aes(ctx->nonce, master_key->raw, raw_key); + up_read(&keyring_key->sem); + if (res) + goto out; + + crypt_info->ci_keyring_key = keyring_key; + return 0; +out: + key_put(keyring_key); + return res; +} + +static int determine_cipher_type(struct fscrypt_info *ci, struct inode *inode, + const char **cipher_str_ret, int *keysize_ret) +{ + if (S_ISREG(inode->i_mode)) { + if (ci->ci_data_mode == FS_ENCRYPTION_MODE_AES_256_XTS) { + *cipher_str_ret = "xts(aes)"; + *keysize_ret = FS_AES_256_XTS_KEY_SIZE; + return 0; + } + pr_warn_once("fscrypto: unsupported contents encryption mode " + "%d for inode %lu\n", + ci->ci_data_mode, inode->i_ino); + return -ENOKEY; + } + + if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) { + if (ci->ci_filename_mode == FS_ENCRYPTION_MODE_AES_256_CTS) { + *cipher_str_ret = "cts(cbc(aes))"; + *keysize_ret = FS_AES_256_CTS_KEY_SIZE; + return 0; + } + pr_warn_once("fscrypto: unsupported filenames encryption mode " + "%d for inode %lu\n", + ci->ci_filename_mode, inode->i_ino); + return -ENOKEY; + } + + pr_warn_once("fscrypto: unsupported file type %d for inode %lu\n", + (inode->i_mode & S_IFMT), inode->i_ino); + return -ENOKEY; +} + +static void put_crypt_info(struct fscrypt_info *ci) +{ + if (!ci) + return; + + key_put(ci->ci_keyring_key); + crypto_free_skcipher(ci->ci_ctfm); + kmem_cache_free(fscrypt_info_cachep, ci); +} + +int get_crypt_info(struct inode *inode) +{ + struct fscrypt_info *crypt_info; + struct fscrypt_context ctx; + struct crypto_skcipher *ctfm; + const char *cipher_str; + int keysize; + u8 *raw_key = NULL; + int res; + + res = fscrypt_initialize(); + if (res) + return res; + + if (!inode->i_sb->s_cop->get_context) + return -EOPNOTSUPP; +retry: + crypt_info = ACCESS_ONCE(inode->i_crypt_info); + if (crypt_info) { + if (!crypt_info->ci_keyring_key || + key_validate(crypt_info->ci_keyring_key) == 0) + return 0; + fscrypt_put_encryption_info(inode, crypt_info); + goto retry; + } + + res = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx)); + if (res < 0) { + if (!fscrypt_dummy_context_enabled(inode)) + return res; + ctx.format = FS_ENCRYPTION_CONTEXT_FORMAT_V1; + ctx.contents_encryption_mode = FS_ENCRYPTION_MODE_AES_256_XTS; + ctx.filenames_encryption_mode = FS_ENCRYPTION_MODE_AES_256_CTS; + ctx.flags = 0; + } else if (res != sizeof(ctx)) { + return -EINVAL; + } + + if (ctx.format != FS_ENCRYPTION_CONTEXT_FORMAT_V1) + return -EINVAL; + + if (ctx.flags & ~FS_POLICY_FLAGS_VALID) + return -EINVAL; + + crypt_info = kmem_cache_alloc(fscrypt_info_cachep, GFP_NOFS); + if (!crypt_info) + return -ENOMEM; + + crypt_info->ci_flags = ctx.flags; + crypt_info->ci_data_mode = ctx.contents_encryption_mode; + crypt_info->ci_filename_mode = ctx.filenames_encryption_mode; + crypt_info->ci_ctfm = NULL; + crypt_info->ci_keyring_key = NULL; + memcpy(crypt_info->ci_master_key, ctx.master_key_descriptor, + sizeof(crypt_info->ci_master_key)); + + res = determine_cipher_type(crypt_info, inode, &cipher_str, &keysize); + if (res) + goto out; + + /* + * This cannot be a stack buffer because it is passed to the scatterlist + * crypto API as part of key derivation. + */ + res = -ENOMEM; + raw_key = kmalloc(FS_MAX_KEY_SIZE, GFP_NOFS); + if (!raw_key) + goto out; + + if (fscrypt_dummy_context_enabled(inode)) { + memset(raw_key, 0x42, FS_AES_256_XTS_KEY_SIZE); + goto got_key; + } + + res = validate_user_key(crypt_info, &ctx, raw_key, + FS_KEY_DESC_PREFIX, FS_KEY_DESC_PREFIX_SIZE); + if (res && inode->i_sb->s_cop->key_prefix) { + u8 *prefix = NULL; + int prefix_size, res2; + + prefix_size = inode->i_sb->s_cop->key_prefix(inode, &prefix); + res2 = validate_user_key(crypt_info, &ctx, raw_key, + prefix, prefix_size); + if (res2) { + if (res2 == -ENOKEY) + res = -ENOKEY; + goto out; + } + } else if (res) { + goto out; + } +got_key: + ctfm = crypto_alloc_skcipher(cipher_str, 0, 0); + if (!ctfm || IS_ERR(ctfm)) { + res = ctfm ? PTR_ERR(ctfm) : -ENOMEM; + printk(KERN_DEBUG + "%s: error %d (inode %u) allocating crypto tfm\n", + __func__, res, (unsigned) inode->i_ino); + goto out; + } + crypt_info->ci_ctfm = ctfm; + crypto_skcipher_clear_flags(ctfm, ~0); + crypto_skcipher_set_flags(ctfm, CRYPTO_TFM_REQ_WEAK_KEY); + res = crypto_skcipher_setkey(ctfm, raw_key, keysize); + if (res) + goto out; + + kzfree(raw_key); + raw_key = NULL; + if (cmpxchg(&inode->i_crypt_info, NULL, crypt_info) != NULL) { + put_crypt_info(crypt_info); + goto retry; + } + return 0; + +out: + if (res == -ENOKEY) + res = 0; + put_crypt_info(crypt_info); + kzfree(raw_key); + return res; +} + +void fscrypt_put_encryption_info(struct inode *inode, struct fscrypt_info *ci) +{ + struct fscrypt_info *prev; + + if (ci == NULL) + ci = ACCESS_ONCE(inode->i_crypt_info); + if (ci == NULL) + return; + + prev = cmpxchg(&inode->i_crypt_info, ci, NULL); + if (prev != ci) + return; + + put_crypt_info(ci); +} +EXPORT_SYMBOL(fscrypt_put_encryption_info); + +int fscrypt_get_encryption_info(struct inode *inode) +{ + struct fscrypt_info *ci = inode->i_crypt_info; + + if (!ci || + (ci->ci_keyring_key && + (ci->ci_keyring_key->flags & ((1 << KEY_FLAG_INVALIDATED) | + (1 << KEY_FLAG_REVOKED) | + (1 << KEY_FLAG_DEAD))))) + return get_crypt_info(inode); + return 0; +} +EXPORT_SYMBOL(fscrypt_get_encryption_info); diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c new file mode 100644 index 000000000000..6865663aac69 --- /dev/null +++ b/fs/crypto/policy.c @@ -0,0 +1,250 @@ +/* + * Encryption policy functions for per-file encryption support. + * + * Copyright (C) 2015, Google, Inc. + * Copyright (C) 2015, Motorola Mobility. + * + * Written by Michael Halcrow, 2015. + * Modified by Jaegeuk Kim, 2015. + */ + +#include <linux/random.h> +#include <linux/string.h> +#include <linux/fscrypto.h> +#include <linux/mount.h> + +static int inode_has_encryption_context(struct inode *inode) +{ + if (!inode->i_sb->s_cop->get_context) + return 0; + return (inode->i_sb->s_cop->get_context(inode, NULL, 0L) > 0); +} + +/* + * check whether the policy is consistent with the encryption context + * for the inode + */ +static int is_encryption_context_consistent_with_policy(struct inode *inode, + const struct fscrypt_policy *policy) +{ + struct fscrypt_context ctx; + int res; + + if (!inode->i_sb->s_cop->get_context) + return 0; + + res = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx)); + if (res != sizeof(ctx)) + return 0; + + return (memcmp(ctx.master_key_descriptor, policy->master_key_descriptor, + FS_KEY_DESCRIPTOR_SIZE) == 0 && + (ctx.flags == policy->flags) && + (ctx.contents_encryption_mode == + policy->contents_encryption_mode) && + (ctx.filenames_encryption_mode == + policy->filenames_encryption_mode)); +} + +static int create_encryption_context_from_policy(struct inode *inode, + const struct fscrypt_policy *policy) +{ + struct fscrypt_context ctx; + int res; + + if (!inode->i_sb->s_cop->set_context) + return -EOPNOTSUPP; + + if (inode->i_sb->s_cop->prepare_context) { + res = inode->i_sb->s_cop->prepare_context(inode); + if (res) + return res; + } + + ctx.format = FS_ENCRYPTION_CONTEXT_FORMAT_V1; + memcpy(ctx.master_key_descriptor, policy->master_key_descriptor, + FS_KEY_DESCRIPTOR_SIZE); + + if (!fscrypt_valid_contents_enc_mode( + policy->contents_encryption_mode)) { + printk(KERN_WARNING + "%s: Invalid contents encryption mode %d\n", __func__, + policy->contents_encryption_mode); + return -EINVAL; + } + + if (!fscrypt_valid_filenames_enc_mode( + policy->filenames_encryption_mode)) { + printk(KERN_WARNING + "%s: Invalid filenames encryption mode %d\n", __func__, + policy->filenames_encryption_mode); + return -EINVAL; + } + + if (policy->flags & ~FS_POLICY_FLAGS_VALID) + return -EINVAL; + + ctx.contents_encryption_mode = policy->contents_encryption_mode; + ctx.filenames_encryption_mode = policy->filenames_encryption_mode; + ctx.flags = policy->flags; + BUILD_BUG_ON(sizeof(ctx.nonce) != FS_KEY_DERIVATION_NONCE_SIZE); + get_random_bytes(ctx.nonce, FS_KEY_DERIVATION_NONCE_SIZE); + + return inode->i_sb->s_cop->set_context(inode, &ctx, sizeof(ctx), NULL); +} + +int fscrypt_process_policy(struct file *filp, + const struct fscrypt_policy *policy) +{ + struct inode *inode = file_inode(filp); + int ret; + + if (!inode_owner_or_capable(inode)) + return -EACCES; + + if (policy->version != 0) + return -EINVAL; + + ret = mnt_want_write_file(filp); + if (ret) + return ret; + + inode_lock(inode); + + if (!inode_has_encryption_context(inode)) { + if (!S_ISDIR(inode->i_mode)) + ret = -EINVAL; + else if (!inode->i_sb->s_cop->empty_dir) + ret = -EOPNOTSUPP; + else if (!inode->i_sb->s_cop->empty_dir(inode)) + ret = -ENOTEMPTY; + else + ret = create_encryption_context_from_policy(inode, + policy); + } else if (!is_encryption_context_consistent_with_policy(inode, + policy)) { + printk(KERN_WARNING + "%s: Policy inconsistent with encryption context\n", + __func__); + ret = -EINVAL; + } + + inode_unlock(inode); + + mnt_drop_write_file(filp); + return ret; +} +EXPORT_SYMBOL(fscrypt_process_policy); + +int fscrypt_get_policy(struct inode *inode, struct fscrypt_policy *policy) +{ + struct fscrypt_context ctx; + int res; + + if (!inode->i_sb->s_cop->get_context || + !inode->i_sb->s_cop->is_encrypted(inode)) + return -ENODATA; + + res = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx)); + if (res != sizeof(ctx)) + return -ENODATA; + if (ctx.format != FS_ENCRYPTION_CONTEXT_FORMAT_V1) + return -EINVAL; + + policy->version = 0; + policy->contents_encryption_mode = ctx.contents_encryption_mode; + policy->filenames_encryption_mode = ctx.filenames_encryption_mode; + policy->flags = ctx.flags; + memcpy(&policy->master_key_descriptor, ctx.master_key_descriptor, + FS_KEY_DESCRIPTOR_SIZE); + return 0; +} +EXPORT_SYMBOL(fscrypt_get_policy); + +int fscrypt_has_permitted_context(struct inode *parent, struct inode *child) +{ + struct fscrypt_info *parent_ci, *child_ci; + int res; + + if ((parent == NULL) || (child == NULL)) { + printk(KERN_ERR "parent %p child %p\n", parent, child); + BUG_ON(1); + } + + /* no restrictions if the parent directory is not encrypted */ + if (!parent->i_sb->s_cop->is_encrypted(parent)) + return 1; + /* if the child directory is not encrypted, this is always a problem */ + if (!parent->i_sb->s_cop->is_encrypted(child)) + return 0; + res = fscrypt_get_encryption_info(parent); + if (res) + return 0; + res = fscrypt_get_encryption_info(child); + if (res) + return 0; + parent_ci = parent->i_crypt_info; + child_ci = child->i_crypt_info; + if (!parent_ci && !child_ci) + return 1; + if (!parent_ci || !child_ci) + return 0; + + return (memcmp(parent_ci->ci_master_key, + child_ci->ci_master_key, + FS_KEY_DESCRIPTOR_SIZE) == 0 && + (parent_ci->ci_data_mode == child_ci->ci_data_mode) && + (parent_ci->ci_filename_mode == child_ci->ci_filename_mode) && + (parent_ci->ci_flags == child_ci->ci_flags)); +} +EXPORT_SYMBOL(fscrypt_has_permitted_context); + +/** + * fscrypt_inherit_context() - Sets a child context from its parent + * @parent: Parent inode from which the context is inherited. + * @child: Child inode that inherits the context from @parent. + * @fs_data: private data given by FS. + * @preload: preload child i_crypt_info + * + * Return: Zero on success, non-zero otherwise + */ +int fscrypt_inherit_context(struct inode *parent, struct inode *child, + void *fs_data, bool preload) +{ + struct fscrypt_context ctx; + struct fscrypt_info *ci; + int res; + + if (!parent->i_sb->s_cop->set_context) + return -EOPNOTSUPP; + + res = fscrypt_get_encryption_info(parent); + if (res < 0) + return res; + + ci = parent->i_crypt_info; + if (ci == NULL) + return -ENOKEY; + + ctx.format = FS_ENCRYPTION_CONTEXT_FORMAT_V1; + if (fscrypt_dummy_context_enabled(parent)) { + ctx.contents_encryption_mode = FS_ENCRYPTION_MODE_AES_256_XTS; + ctx.filenames_encryption_mode = FS_ENCRYPTION_MODE_AES_256_CTS; + ctx.flags = 0; + memset(ctx.master_key_descriptor, 0x42, FS_KEY_DESCRIPTOR_SIZE); + res = 0; + } else { + ctx.contents_encryption_mode = ci->ci_data_mode; + ctx.filenames_encryption_mode = ci->ci_filename_mode; + ctx.flags = ci->ci_flags; + memcpy(ctx.master_key_descriptor, ci->ci_master_key, + FS_KEY_DESCRIPTOR_SIZE); + } + get_random_bytes(ctx.nonce, FS_KEY_DERIVATION_NONCE_SIZE); + res = parent->i_sb->s_cop->set_context(child, &ctx, + sizeof(ctx), fs_data); + if (res) + return res; + return preload ? fscrypt_get_encryption_info(child): 0; +} +EXPORT_SYMBOL(fscrypt_inherit_context); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index bd8831bfbafe..83a72da67df7 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2204,6 +2204,7 @@ static void ext4_orphan_cleanup(struct super_block *sb, unsigned int s_flags = sb->s_flags; int nr_orphans = 0, nr_truncates = 0; #ifdef CONFIG_QUOTA + int quota_update = 0; int i; #endif if (!es->s_last_orphan) { @@ -2242,14 +2243,32 @@ static void ext4_orphan_cleanup(struct super_block *sb, #ifdef CONFIG_QUOTA /* Needed for iput() to work correctly and not trash data */ sb->s_flags |= MS_ACTIVE; - /* Turn on quotas so that they are updated correctly */ + + /* + * Turn on quotas which were not enabled for read-only mounts if + * filesystem has quota feature, so that they are updated correctly. + */ + if (ext4_has_feature_quota(sb) && (s_flags & MS_RDONLY)) { + int ret = ext4_enable_quotas(sb); + + if (!ret) + quota_update = 1; + else + ext4_msg(sb, KERN_ERR, + "Cannot turn on quotas: error %d", ret); + } + + /* Turn on journaled quotas used for old sytle */ for (i = 0; i < EXT4_MAXQUOTAS; i++) { if (EXT4_SB(sb)->s_qf_names[i]) { int ret = ext4_quota_on_mount(sb, i); - if (ret < 0) + + if (!ret) + quota_update = 1; + else ext4_msg(sb, KERN_ERR, "Cannot turn on journaled " - "quota: error %d", ret); + "quota: type %d: error %d", i, ret); } } #endif @@ -2308,10 +2327,12 @@ static void ext4_orphan_cleanup(struct super_block *sb, ext4_msg(sb, KERN_INFO, "%d truncate%s cleaned up", PLURAL(nr_truncates)); #ifdef CONFIG_QUOTA - /* Turn quotas off */ - for (i = 0; i < EXT4_MAXQUOTAS; i++) { - if (sb_dqopt(sb)->files[i]) - dquot_quota_off(sb, i); + /* Turn off quotas if they were enabled for orphan cleanup */ + if (quota_update) { + for (i = 0; i < EXT4_MAXQUOTAS; i++) { + if (sb_dqopt(sb)->files[i]) + dquot_quota_off(sb, i); + } } #endif sb->s_flags = s_flags; /* Restore MS_RDONLY status */ @@ -5123,6 +5144,9 @@ static int ext4_enable_quotas(struct super_block *sb) err = ext4_quota_enable(sb, type, QFMT_VFS_V1, DQUOT_USAGE_ENABLED); if (err) { + for (type--; type >= 0; type--) + dquot_quota_off(sb, type); + ext4_warning(sb, "Failed to enable quota tracking " "(type=%d, err=%d). Please run " diff --git a/fs/f2fs/Kconfig b/fs/f2fs/Kconfig index b0a9dc929f88..1852d99df97b 100644 --- a/fs/f2fs/Kconfig +++ b/fs/f2fs/Kconfig @@ -1,6 +1,9 @@ config F2FS_FS tristate "F2FS filesystem support" depends on BLOCK + select CRYPTO + select KEYS + select CRYPTO_CRC32 help F2FS is based on Log-structured File System (LFS), which supports versatile "flash-friendly" features. The design has been focused on @@ -76,15 +79,7 @@ config F2FS_FS_ENCRYPTION bool "F2FS Encryption" depends on F2FS_FS depends on F2FS_FS_XATTR - select CRYPTO_AES - select CRYPTO_CBC - select CRYPTO_ECB - select CRYPTO_XTS - select CRYPTO_CTS - select CRYPTO_CTR - select CRYPTO_SHA256 - select KEYS - select ENCRYPTED_KEYS + select FS_ENCRYPTION help Enable encryption of f2fs files and directories. This feature is similar to ecryptfs, but it is more memory @@ -100,3 +95,11 @@ config F2FS_IO_TRACE information and block IO patterns in the filesystem level. If unsure, say N. + +config F2FS_FAULT_INJECTION + bool "F2FS fault injection facility" + depends on F2FS_FS + help + Test F2FS to inject faults such as ENOMEM, ENOSPC, and so on. + + If unsure, say N. diff --git a/fs/f2fs/Makefile b/fs/f2fs/Makefile index 08e101ed914c..ca949ea7c02f 100644 --- a/fs/f2fs/Makefile +++ b/fs/f2fs/Makefile @@ -7,5 +7,3 @@ f2fs-$(CONFIG_F2FS_STAT_FS) += debug.o f2fs-$(CONFIG_F2FS_FS_XATTR) += xattr.o f2fs-$(CONFIG_F2FS_FS_POSIX_ACL) += acl.o f2fs-$(CONFIG_F2FS_IO_TRACE) += trace.o -f2fs-$(CONFIG_F2FS_FS_ENCRYPTION) += crypto_policy.o crypto.o \ - crypto_key.o crypto_fname.o diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c index 83dcf7bfd7b8..a45d1f4b7b0f 100644 --- a/fs/f2fs/acl.c +++ b/fs/f2fs/acl.c @@ -109,14 +109,16 @@ fail: return ERR_PTR(-EINVAL); } -static void *f2fs_acl_to_disk(const struct posix_acl *acl, size_t *size) +static void *f2fs_acl_to_disk(struct f2fs_sb_info *sbi, + const struct posix_acl *acl, size_t *size) { struct f2fs_acl_header *f2fs_acl; struct f2fs_acl_entry *entry; int i; - f2fs_acl = kmalloc(sizeof(struct f2fs_acl_header) + acl->a_count * - sizeof(struct f2fs_acl_entry), GFP_NOFS); + f2fs_acl = f2fs_kmalloc(sbi, sizeof(struct f2fs_acl_header) + + acl->a_count * sizeof(struct f2fs_acl_entry), + GFP_NOFS); if (!f2fs_acl) return ERR_PTR(-ENOMEM); @@ -175,7 +177,7 @@ static struct posix_acl *__f2fs_get_acl(struct inode *inode, int type, retval = f2fs_getxattr(inode, name_index, "", NULL, 0, dpage); if (retval > 0) { - value = kmalloc(retval, GFP_F2FS_ZERO); + value = f2fs_kmalloc(F2FS_I_SB(inode), retval, GFP_F2FS_ZERO); if (!value) return ERR_PTR(-ENOMEM); retval = f2fs_getxattr(inode, name_index, "", value, @@ -204,7 +206,6 @@ struct posix_acl *f2fs_get_acl(struct inode *inode, int type) static int __f2fs_set_acl(struct inode *inode, int type, struct posix_acl *acl, struct page *ipage) { - struct f2fs_inode_info *fi = F2FS_I(inode); int name_index; void *value = NULL; size_t size = 0; @@ -213,11 +214,11 @@ static int __f2fs_set_acl(struct inode *inode, int type, switch (type) { case ACL_TYPE_ACCESS: name_index = F2FS_XATTR_INDEX_POSIX_ACL_ACCESS; - if (acl && !ipage) { + if (acl) { error = posix_acl_update_mode(inode, &inode->i_mode, &acl); if (error) return error; - set_acl_inode(fi, inode->i_mode); + set_acl_inode(inode, inode->i_mode); } break; @@ -232,9 +233,9 @@ static int __f2fs_set_acl(struct inode *inode, int type, } if (acl) { - value = f2fs_acl_to_disk(acl, &size); + value = f2fs_acl_to_disk(F2FS_I_SB(inode), acl, &size); if (IS_ERR(value)) { - clear_inode_flag(fi, FI_ACL_MODE); + clear_inode_flag(inode, FI_ACL_MODE); return (int)PTR_ERR(value); } } @@ -245,7 +246,7 @@ static int __f2fs_set_acl(struct inode *inode, int type, if (!error) set_cached_acl(inode, type, acl); - clear_inode_flag(fi, FI_ACL_MODE); + clear_inode_flag(inode, FI_ACL_MODE); return error; } @@ -386,6 +387,8 @@ int f2fs_init_acl(struct inode *inode, struct inode *dir, struct page *ipage, if (error) return error; + f2fs_mark_inode_dirty_sync(inode, true); + if (default_acl) { error = __f2fs_set_acl(inode, ACL_TYPE_DEFAULT, default_acl, ipage); diff --git a/fs/f2fs/acl.h b/fs/f2fs/acl.h index 997ca8edb6cb..2c685185c24d 100644 --- a/fs/f2fs/acl.h +++ b/fs/f2fs/acl.h @@ -37,11 +37,10 @@ struct f2fs_acl_header { #ifdef CONFIG_F2FS_FS_POSIX_ACL extern struct posix_acl *f2fs_get_acl(struct inode *, int); -extern int f2fs_set_acl(struct inode *inode, struct posix_acl *acl, int type); +extern int f2fs_set_acl(struct inode *, struct posix_acl *, int); extern int f2fs_init_acl(struct inode *, struct inode *, struct page *, struct page *); #else -#define f2fs_check_acl NULL #define f2fs_get_acl NULL #define f2fs_set_acl NULL diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index f661d80474be..640f28576e88 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -26,6 +26,14 @@ static struct kmem_cache *ino_entry_slab; struct kmem_cache *inode_entry_slab; +void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io) +{ + set_ckpt_flags(sbi, CP_ERROR_FLAG); + sbi->sb->s_flags |= MS_RDONLY; + if (!end_io) + f2fs_flush_merged_bios(sbi); +} + /* * We guarantee no failure on the returned page. */ @@ -34,13 +42,14 @@ struct page *grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index) struct address_space *mapping = META_MAPPING(sbi); struct page *page = NULL; repeat: - page = grab_cache_page(mapping, index); + page = f2fs_grab_cache_page(mapping, index, false); if (!page) { cond_resched(); goto repeat; } - f2fs_wait_on_page_writeback(page, META); - SetPageUptodate(page); + f2fs_wait_on_page_writeback(page, META, true); + if (!PageUptodate(page)) + SetPageUptodate(page); return page; } @@ -56,14 +65,15 @@ static struct page *__get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index, .sbi = sbi, .type = META, .rw = READ_SYNC | REQ_META | REQ_PRIO, - .blk_addr = index, + .old_blkaddr = index, + .new_blkaddr = index, .encrypted_page = NULL, }; if (unlikely(!is_meta)) fio.rw &= ~REQ_META; repeat: - page = grab_cache_page(mapping, index); + page = f2fs_grab_cache_page(mapping, index, false); if (!page) { cond_resched(); goto repeat; @@ -90,7 +100,7 @@ repeat: * meta page. */ if (unlikely(!PageUptodate(page))) - f2fs_stop_checkpoint(sbi); + f2fs_stop_checkpoint(sbi, false); out: return page; } @@ -143,7 +153,6 @@ bool is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type) int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, int type, bool sync) { - block_t prev_blk_addr = 0; struct page *page; block_t blkno = start; struct f2fs_io_info fio = { @@ -152,10 +161,12 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, .rw = sync ? (READ_SYNC | REQ_META | REQ_PRIO) : READA, .encrypted_page = NULL, }; + struct blk_plug plug; if (unlikely(type == META_POR)) fio.rw &= ~REQ_META; + blk_start_plug(&plug); for (; nrpages-- > 0; blkno++) { if (!is_valid_blkaddr(sbi, blkno, type)) @@ -167,27 +178,25 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, NAT_BLOCK_OFFSET(NM_I(sbi)->max_nid))) blkno = 0; /* get nat block addr */ - fio.blk_addr = current_nat_addr(sbi, + fio.new_blkaddr = current_nat_addr(sbi, blkno * NAT_ENTRY_PER_BLOCK); break; case META_SIT: /* get sit block addr */ - fio.blk_addr = current_sit_addr(sbi, + fio.new_blkaddr = current_sit_addr(sbi, blkno * SIT_ENTRY_PER_BLOCK); - if (blkno != start && prev_blk_addr + 1 != fio.blk_addr) - goto out; - prev_blk_addr = fio.blk_addr; break; case META_SSA: case META_CP: case META_POR: - fio.blk_addr = blkno; + fio.new_blkaddr = blkno; break; default: BUG(); } - page = grab_cache_page(META_MAPPING(sbi), fio.blk_addr); + page = f2fs_grab_cache_page(META_MAPPING(sbi), + fio.new_blkaddr, false); if (!page) continue; if (PageUptodate(page)) { @@ -196,11 +205,13 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, } fio.page = page; + fio.old_blkaddr = fio.new_blkaddr; f2fs_submit_page_mbio(&fio); f2fs_put_page(page, 0); } out: f2fs_submit_merged_bio(sbi, META, READ); + blk_finish_plug(&plug); return blkno - start; } @@ -210,12 +221,12 @@ void ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index) bool readahead = false; page = find_get_page(META_MAPPING(sbi), index); - if (!page || (page && !PageUptodate(page))) + if (!page || !PageUptodate(page)) readahead = true; f2fs_put_page(page, 0); if (readahead) - ra_meta_pages(sbi, index, MAX_BIO_BLOCKS(sbi), META_POR, true); + ra_meta_pages(sbi, index, BIO_MAX_PAGES, META_POR, true); } static int f2fs_write_meta_page(struct page *page, @@ -232,13 +243,17 @@ static int f2fs_write_meta_page(struct page *page, if (unlikely(f2fs_cp_error(sbi))) goto redirty_out; - f2fs_wait_on_page_writeback(page, META); write_meta_page(sbi, page); dec_page_count(sbi, F2FS_DIRTY_META); - unlock_page(page); if (wbc->for_reclaim) + f2fs_submit_merged_bio_cond(sbi, NULL, page, 0, META, WRITE); + + unlock_page(page); + + if (unlikely(f2fs_cp_error(sbi))) f2fs_submit_merged_bio(sbi, META, WRITE); + return 0; redirty_out: @@ -252,13 +267,13 @@ static int f2fs_write_meta_pages(struct address_space *mapping, struct f2fs_sb_info *sbi = F2FS_M_SB(mapping); long diff, written; - trace_f2fs_writepages(mapping->host, wbc, META); - /* collect a number of dirty meta pages and write together */ if (wbc->for_kupdate || get_pages(sbi, F2FS_DIRTY_META) < nr_pages_to_skip(sbi, META)) goto skip_write; + trace_f2fs_writepages(mapping->host, wbc, META); + /* if mounting is failed, skip writing node pages */ mutex_lock(&sbi->cp_mutex); diff = nr_pages_to_write(sbi, META, wbc); @@ -269,6 +284,7 @@ static int f2fs_write_meta_pages(struct address_space *mapping, skip_write: wbc->pages_skipped += get_pages(sbi, F2FS_DIRTY_META); + trace_f2fs_writepages(mapping->host, wbc, META); return 0; } @@ -276,15 +292,18 @@ long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type, long nr_to_write) { struct address_space *mapping = META_MAPPING(sbi); - pgoff_t index = 0, end = LONG_MAX, prev = LONG_MAX; + pgoff_t index = 0, end = ULONG_MAX, prev = ULONG_MAX; struct pagevec pvec; long nwritten = 0; struct writeback_control wbc = { .for_reclaim = 0, }; + struct blk_plug plug; pagevec_init(&pvec, 0); + blk_start_plug(&plug); + while (index <= end) { int i, nr_pages; nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, @@ -296,7 +315,7 @@ long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type, for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; - if (prev == LONG_MAX) + if (prev == ULONG_MAX) prev = page->index - 1; if (nr_to_write != LONG_MAX && page->index != prev + 1) { pagevec_release(&pvec); @@ -315,6 +334,9 @@ continue_unlock: goto continue_unlock; } + f2fs_wait_on_page_writeback(page, META, true); + + BUG_ON(PageWriteback(page)); if (!clear_page_dirty_for_io(page)) goto continue_unlock; @@ -334,6 +356,8 @@ stop: if (nwritten) f2fs_submit_merged_bio(sbi, type, WRITE); + blk_finish_plug(&plug); + return nwritten; } @@ -341,9 +365,10 @@ static int f2fs_set_meta_page_dirty(struct page *page) { trace_f2fs_set_page_dirty(page, META); - SetPageUptodate(page); + if (!PageUptodate(page)) + SetPageUptodate(page); if (!PageDirty(page)) { - __set_page_dirty_nobuffers(page); + f2fs_set_page_dirty_nobuffers(page); inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_META); SetPagePrivate(page); f2fs_trace_pid(page); @@ -358,6 +383,9 @@ const struct address_space_operations f2fs_meta_aops = { .set_page_dirty = f2fs_set_meta_page_dirty, .invalidatepage = f2fs_invalidate_page, .releasepage = f2fs_release_page, +#ifdef CONFIG_MIGRATION + .migratepage = f2fs_migrate_page, +#endif }; static void __add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type) @@ -410,13 +438,13 @@ static void __remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type) spin_unlock(&im->ino_lock); } -void add_dirty_inode(struct f2fs_sb_info *sbi, nid_t ino, int type) +void add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type) { /* add new dirty ino entry into list */ __add_ino_entry(sbi, ino, type); } -void remove_dirty_inode(struct f2fs_sb_info *sbi, nid_t ino, int type) +void remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type) { /* remove dirty ino entry from list */ __remove_ino_entry(sbi, ino, type); @@ -434,12 +462,12 @@ bool exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode) return e ? true : false; } -void release_dirty_inode(struct f2fs_sb_info *sbi) +void release_ino_entry(struct f2fs_sb_info *sbi, bool all) { struct ino_entry *e, *tmp; int i; - for (i = APPEND_INO; i <= UPDATE_INO; i++) { + for (i = all ? ORPHAN_INO: APPEND_INO; i <= UPDATE_INO; i++) { struct inode_management *im = &sbi->im[i]; spin_lock(&im->ino_lock); @@ -459,6 +487,13 @@ int acquire_orphan_inode(struct f2fs_sb_info *sbi) int err = 0; spin_lock(&im->ino_lock); + +#ifdef CONFIG_F2FS_FAULT_INJECTION + if (time_to_inject(sbi, FAULT_ORPHAN)) { + spin_unlock(&im->ino_lock); + return -ENOSPC; + } +#endif if (unlikely(im->ino_num >= sbi->max_orphans)) err = -ENOSPC; else @@ -478,10 +513,11 @@ void release_orphan_inode(struct f2fs_sb_info *sbi) spin_unlock(&im->ino_lock); } -void add_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino) +void add_orphan_inode(struct inode *inode) { /* add new orphan ino entry into list */ - __add_ino_entry(sbi, ino, ORPHAN_INO); + __add_ino_entry(F2FS_I_SB(inode), inode->i_ino, ORPHAN_INO); + update_inode_page(inode); } void remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino) @@ -493,8 +529,20 @@ void remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino) static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino) { struct inode *inode; + struct node_info ni; + int err = acquire_orphan_inode(sbi); + + if (err) { + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_msg(sbi->sb, KERN_WARNING, + "%s: orphan failed (ino=%x), run fsck to fix.", + __func__, ino); + return err; + } - inode = f2fs_iget(sbi->sb, ino); + __add_ino_entry(sbi, ino, ORPHAN_INO); + + inode = f2fs_iget_retry(sbi->sb, ino); if (IS_ERR(inode)) { /* * there should be a bug that we can't find the entry @@ -508,6 +556,18 @@ static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino) /* truncate all the data during iput */ iput(inode); + + get_node_info(sbi, ino, &ni); + + /* ENOMEM was fully retried in f2fs_evict_inode. */ + if (ni.blk_addr != NULL_ADDR) { + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_msg(sbi->sb, KERN_WARNING, + "%s: orphan failed (ino=%x), run fsck to fix.", + __func__, ino); + return -EIO; + } + __remove_ino_entry(sbi, ino, ORPHAN_INO); return 0; } @@ -516,7 +576,7 @@ int recover_orphan_inodes(struct f2fs_sb_info *sbi) block_t start_blk, orphan_blocks, i, j; int err; - if (!is_set_ckpt_flags(F2FS_CKPT(sbi), CP_ORPHAN_PRESENT_FLAG)) + if (!is_set_ckpt_flags(sbi, CP_ORPHAN_PRESENT_FLAG)) return 0; start_blk = __start_cp_addr(sbi) + 1 + __cp_payload(sbi); @@ -540,7 +600,7 @@ int recover_orphan_inodes(struct f2fs_sb_info *sbi) f2fs_put_page(page, 1); } /* clear Orphan Flag */ - clear_ckpt_flags(F2FS_CKPT(sbi), CP_ORPHAN_PRESENT_FLAG); + clear_ckpt_flags(sbi, CP_ORPHAN_PRESENT_FLAG); return 0; } @@ -601,45 +661,55 @@ 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_offset = le32_to_cpu((*cp_block)->checksum_offset); + if (crc_offset >= blk_size) { + f2fs_msg(sbi->sb, KERN_WARNING, + "invalid crc_offset: %zu", crc_offset); + return -EINVAL; + } - crc = le32_to_cpu(*((__le32 *)((unsigned char *)cp_block + crc_offset))); - if (!f2fs_crc_valid(crc, cp_block, crc_offset)) - goto invalid_cp1; + crc = le32_to_cpu(*((__le32 *)((unsigned char *)*cp_block + + crc_offset))); + if (!f2fs_crc_valid(sbi, crc, *cp_block, crc_offset)) { + f2fs_msg(sbi->sb, KERN_WARNING, "invalid crc value"); + return -EINVAL; + } - pre_version = cur_cp_version(cp_block); + *version = cur_cp_version(*cp_block); + return 0; +} - /* 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); +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; - 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; + err = get_checkpoint_version(sbi, cp_addr, &cp_block, + &cp_page_1, version); + if (err) + goto invalid_cp1; + pre_version = *version; - crc = le32_to_cpu(*((__le32 *)((unsigned char *)cp_block + crc_offset))); - if (!f2fs_crc_valid(crc, cp_block, crc_offset)) + 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_cp2; - - cur_version = cur_cp_version(cp_block); + cur_version = *version; if (cur_version == pre_version) { *version = cur_version; @@ -696,6 +766,15 @@ 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); + /* Sanity checking of checkpoint */ + if (sanity_check_ckpt(sbi)) + goto free_fail_no_cp; + + if (cur_page == cp1) + sbi->cur_cp_pack = 1; + else + sbi->cur_cp_pack = 2; + if (cp_blks <= 1) goto done; @@ -717,123 +796,102 @@ 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; } -static int __add_dirty_inode(struct inode *inode, struct inode_entry *new) +static void __add_dirty_inode(struct inode *inode, enum inode_type type) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + int flag = (type == DIR_INODE) ? FI_DIRTY_DIR : FI_DIRTY_FILE; - if (is_inode_flag_set(F2FS_I(inode), FI_DIRTY_DIR)) - return -EEXIST; + if (is_inode_flag_set(inode, flag)) + return; - set_inode_flag(F2FS_I(inode), FI_DIRTY_DIR); - F2FS_I(inode)->dirty_dir = new; - list_add_tail(&new->list, &sbi->dir_inode_list); - stat_inc_dirty_dir(sbi); - return 0; + set_inode_flag(inode, flag); + list_add_tail(&F2FS_I(inode)->dirty_list, &sbi->inode_list[type]); + stat_inc_dirty_inode(sbi, type); +} + +static void __remove_dirty_inode(struct inode *inode, enum inode_type type) +{ + int flag = (type == DIR_INODE) ? FI_DIRTY_DIR : FI_DIRTY_FILE; + + if (get_dirty_pages(inode) || !is_inode_flag_set(inode, flag)) + return; + + list_del_init(&F2FS_I(inode)->dirty_list); + clear_inode_flag(inode, flag); + stat_dec_dirty_inode(F2FS_I_SB(inode), type); } void update_dirty_page(struct inode *inode, struct page *page) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct inode_entry *new; - int ret = 0; + enum inode_type type = S_ISDIR(inode->i_mode) ? DIR_INODE : FILE_INODE; if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode) && !S_ISLNK(inode->i_mode)) return; - if (!S_ISDIR(inode->i_mode)) { - inode_inc_dirty_pages(inode); - goto out; - } - - new = f2fs_kmem_cache_alloc(inode_entry_slab, GFP_NOFS); - new->inode = inode; - INIT_LIST_HEAD(&new->list); - - spin_lock(&sbi->dir_inode_lock); - ret = __add_dirty_inode(inode, new); + spin_lock(&sbi->inode_lock[type]); + if (type != FILE_INODE || test_opt(sbi, DATA_FLUSH)) + __add_dirty_inode(inode, type); inode_inc_dirty_pages(inode); - spin_unlock(&sbi->dir_inode_lock); + spin_unlock(&sbi->inode_lock[type]); - if (ret) - kmem_cache_free(inode_entry_slab, new); -out: SetPagePrivate(page); f2fs_trace_pid(page); } -void add_dirty_dir_inode(struct inode *inode) +void remove_dirty_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; + enum inode_type type = S_ISDIR(inode->i_mode) ? DIR_INODE : FILE_INODE; - 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); - struct inode_entry *entry; - - if (!S_ISDIR(inode->i_mode)) + if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode) && + !S_ISLNK(inode->i_mode)) return; - spin_lock(&sbi->dir_inode_lock); - if (get_dirty_pages(inode) || - !is_inode_flag_set(F2FS_I(inode), FI_DIRTY_DIR)) { - spin_unlock(&sbi->dir_inode_lock); + if (type == FILE_INODE && !test_opt(sbi, DATA_FLUSH)) return; - } - entry = F2FS_I(inode)->dirty_dir; - list_del(&entry->list); - F2FS_I(inode)->dirty_dir = NULL; - clear_inode_flag(F2FS_I(inode), FI_DIRTY_DIR); - 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); - } + spin_lock(&sbi->inode_lock[type]); + __remove_dirty_inode(inode, type); + spin_unlock(&sbi->inode_lock[type]); } -void sync_dirty_dir_inodes(struct f2fs_sb_info *sbi) +int sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type) { struct list_head *head; - struct inode_entry *entry; struct inode *inode; + struct f2fs_inode_info *fi; + bool is_dir = (type == DIR_INODE); + + trace_f2fs_sync_dirty_inodes_enter(sbi->sb, is_dir, + get_pages(sbi, is_dir ? + F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA)); retry: if (unlikely(f2fs_cp_error(sbi))) - return; + return -EIO; - spin_lock(&sbi->dir_inode_lock); + spin_lock(&sbi->inode_lock[type]); - head = &sbi->dir_inode_list; + head = &sbi->inode_list[type]; if (list_empty(head)) { - spin_unlock(&sbi->dir_inode_lock); - return; + spin_unlock(&sbi->inode_lock[type]); + trace_f2fs_sync_dirty_inodes_exit(sbi->sb, is_dir, + get_pages(sbi, is_dir ? + F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA)); + return 0; } - entry = list_entry(head->next, struct inode_entry, list); - inode = igrab(entry->inode); - spin_unlock(&sbi->dir_inode_lock); + fi = list_entry(head->next, struct f2fs_inode_info, dirty_list); + inode = igrab(&fi->vfs_inode); + spin_unlock(&sbi->inode_lock[type]); if (inode) { filemap_fdatawrite(inode->i_mapping); iput(inode); @@ -848,6 +906,38 @@ retry: goto retry; } +int f2fs_sync_inode_meta(struct f2fs_sb_info *sbi) +{ + struct list_head *head = &sbi->inode_list[DIRTY_META]; + struct inode *inode; + struct f2fs_inode_info *fi; + s64 total = get_pages(sbi, F2FS_DIRTY_IMETA); + + while (total--) { + if (unlikely(f2fs_cp_error(sbi))) + return -EIO; + + spin_lock(&sbi->inode_lock[DIRTY_META]); + if (list_empty(head)) { + spin_unlock(&sbi->inode_lock[DIRTY_META]); + return 0; + } + fi = list_entry(head->next, struct f2fs_inode_info, + gdirty_list); + inode = igrab(&fi->vfs_inode); + spin_unlock(&sbi->inode_lock[DIRTY_META]); + if (inode) { + sync_inode_metadata(inode, 0); + + /* it's on eviction */ + if (is_inode_flag_set(inode, FI_DIRTY_INODE)) + update_inode_page(inode); + iput(inode); + } + }; + return 0; +} + /* * Freeze all the FS-operations for checkpoint. */ @@ -868,11 +958,17 @@ retry_flush_dents: /* write all the dirty dentry pages */ if (get_pages(sbi, F2FS_DIRTY_DENTS)) { f2fs_unlock_all(sbi); - sync_dirty_dir_inodes(sbi); - if (unlikely(f2fs_cp_error(sbi))) { - err = -EIO; + err = sync_dirty_inodes(sbi, DIR_INODE); + if (err) + goto out; + goto retry_flush_dents; + } + + if (get_pages(sbi, F2FS_DIRTY_IMETA)) { + f2fs_unlock_all(sbi); + err = f2fs_sync_inode_meta(sbi); + if (err) goto out; - } goto retry_flush_dents; } @@ -885,10 +981,9 @@ retry_flush_nodes: if (get_pages(sbi, F2FS_DIRTY_NODES)) { up_write(&sbi->node_write); - sync_node_pages(sbi, 0, &wbc); - if (unlikely(f2fs_cp_error(sbi))) { + err = sync_node_pages(sbi, &wbc); + if (err) { f2fs_unlock_all(sbi); - err = -EIO; goto out; } goto retry_flush_nodes; @@ -901,6 +996,8 @@ out: static void unblock_operations(struct f2fs_sb_info *sbi) { up_write(&sbi->node_write); + + build_free_nids(sbi, false); f2fs_unlock_all(sbi); } @@ -911,18 +1008,48 @@ static void wait_on_all_pages_writeback(struct f2fs_sb_info *sbi) for (;;) { prepare_to_wait(&sbi->cp_wait, &wait, TASK_UNINTERRUPTIBLE); - if (!get_pages(sbi, F2FS_WRITEBACK)) + if (!get_pages(sbi, F2FS_WB_CP_DATA)) break; - io_schedule(); + io_schedule_timeout(5*HZ); } finish_wait(&sbi->cp_wait, &wait); } -static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) +static void update_ckpt_flags(struct f2fs_sb_info *sbi, struct cp_control *cpc) +{ + unsigned long orphan_num = sbi->im[ORPHAN_INO].ino_num; + struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); + + spin_lock(&sbi->cp_lock); + + if (cpc->reason == CP_UMOUNT) + __set_ckpt_flags(ckpt, CP_UMOUNT_FLAG); + else + __clear_ckpt_flags(ckpt, CP_UMOUNT_FLAG); + + if (cpc->reason == CP_FASTBOOT) + __set_ckpt_flags(ckpt, CP_FASTBOOT_FLAG); + else + __clear_ckpt_flags(ckpt, CP_FASTBOOT_FLAG); + + if (orphan_num) + __set_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG); + else + __clear_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG); + + 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); + + spin_unlock(&sbi->cp_lock); +} + +static int 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; @@ -931,21 +1058,15 @@ 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; + struct super_block *sb = sbi->sb; + struct curseg_info *seg_i = CURSEG_I(sbi, CURSEG_HOT_NODE); + u64 kbytes_written; /* Flush all the NAT/SIT pages */ while (get_pages(sbi, F2FS_DIRTY_META)) { sync_meta_pages(sbi, META, LONG_MAX); if (unlikely(f2fs_cp_error(sbi))) - return; + return -EIO; } next_free_nid(sbi, &last_nid); @@ -980,10 +1101,12 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) /* 2 cp + n data seg summary + orphan inode blocks */ data_sum_blocks = npages_for_summary_flush(sbi, false); + spin_lock(&sbi->cp_lock); if (data_sum_blocks < NR_CURSEG_DATA_TYPE) - set_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG); + __set_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG); else - clear_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG); + __clear_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG); + spin_unlock(&sbi->cp_lock); orphan_blocks = GET_ORPHAN_BLOCKS(orphan_num); ckpt->cp_pack_start_sum = cpu_to_le32(1 + cp_payload_blks + @@ -998,39 +1121,24 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) cp_payload_blks + data_sum_blocks + orphan_blocks); - if (cpc->reason == CP_UMOUNT) - set_ckpt_flags(ckpt, CP_UMOUNT_FLAG); - else - clear_ckpt_flags(ckpt, CP_UMOUNT_FLAG); - - if (cpc->reason == CP_FASTBOOT) - set_ckpt_flags(ckpt, CP_FASTBOOT_FLAG); - else - clear_ckpt_flags(ckpt, CP_FASTBOOT_FLAG); - - if (orphan_num) - set_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG); - else - clear_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG); - - if (is_sbi_flag_set(sbi, SBI_NEED_FSCK)) - set_ckpt_flags(ckpt, CP_FSCK_FLAG); + /* update ckpt flag for checkpoint */ + update_ckpt_flags(sbi, cpc); /* update SIT/NAT bitmap */ get_sit_bitmap(sbi, __bitmap_ptr(sbi, SIT_BITMAP)); get_nat_bitmap(sbi, __bitmap_ptr(sbi, NAT_BITMAP)); - crc32 = f2fs_crc32(ckpt, le32_to_cpu(ckpt->checksum_offset)); + crc32 = f2fs_crc32(sbi, ckpt, le32_to_cpu(ckpt->checksum_offset)); *((__le32 *)((unsigned char *)ckpt + 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); if (unlikely(f2fs_cp_error(sbi))) - return; + return -EIO; /* write out checkpoint buffer at block 0 */ update_meta_page(sbi, ckpt, start_blk++); @@ -1046,6 +1154,14 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) write_data_summaries(sbi, start_blk); start_blk += data_sum_blocks; + + /* Record write statistics in the hot node summary */ + kbytes_written = sbi->kbytes_written; + if (sb->s_bdev->bd_part) + kbytes_written += BD_PART_WRITTEN(sbi); + + seg_i->journal->info.kbytes_written = cpu_to_le64(kbytes_written); + if (__remain_node_summaries(cpc->reason)) { write_node_summaries(sbi, start_blk); start_blk += NR_CURSEG_NODE_TYPE; @@ -1058,14 +1174,14 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) wait_on_all_pages_writeback(sbi); if (unlikely(f2fs_cp_error(sbi))) - return; + return -EIO; - filemap_fdatawait_range(NODE_MAPPING(sbi), 0, LONG_MAX); - filemap_fdatawait_range(META_MAPPING(sbi), 0, LONG_MAX); + filemap_fdatawait_range(NODE_MAPPING(sbi), 0, LLONG_MAX); + filemap_fdatawait_range(META_MAPPING(sbi), 0, LLONG_MAX); /* update user_block_counts */ sbi->last_valid_block_count = sbi->total_valid_block_count; - sbi->alloc_valid_block_count = 0; + percpu_counter_set(&sbi->alloc_valid_block_count, 0); /* Here, we only have one bio having CP pack */ sync_meta_pages(sbi, META_FLUSH, LONG_MAX); @@ -1073,30 +1189,36 @@ 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); + release_ino_entry(sbi, false); if (unlikely(f2fs_cp_error(sbi))) - return; + return -EIO; - clear_prefree_segments(sbi, cpc); clear_sbi_flag(sbi, SBI_IS_DIRTY); + clear_sbi_flag(sbi, SBI_NEED_CP); + __set_cp_next_pack(sbi); + + /* + * redirty superblock if metadata like node page or inode cache is + * updated during writing checkpoint. + */ + if (get_pages(sbi, F2FS_DIRTY_NODES) || + get_pages(sbi, F2FS_DIRTY_IMETA)) + set_sbi_flag(sbi, SBI_IS_DIRTY); + + f2fs_bug_on(sbi, get_pages(sbi, F2FS_DIRTY_DENTS)); + + return 0; } /* * We guarantee that this checkpoint procedure will not fail. */ -void write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) +int write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) { struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); unsigned long long ckpt_ver; + int err = 0; mutex_lock(&sbi->cp_mutex); @@ -1104,21 +1226,35 @@ void write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) (cpc->reason == CP_FASTBOOT || cpc->reason == CP_SYNC || (cpc->reason == CP_DISCARD && !sbi->discard_blks))) goto out; - if (unlikely(f2fs_cp_error(sbi))) + if (unlikely(f2fs_cp_error(sbi))) { + err = -EIO; goto out; - if (f2fs_readonly(sbi->sb)) + } + if (f2fs_readonly(sbi->sb)) { + err = -EROFS; goto out; + } trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "start block_ops"); - if (block_operations(sbi)) + err = block_operations(sbi); + if (err) goto out; trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish block_ops"); - f2fs_submit_merged_bio(sbi, DATA, WRITE); - f2fs_submit_merged_bio(sbi, NODE, WRITE); - f2fs_submit_merged_bio(sbi, META, WRITE); + f2fs_flush_merged_bios(sbi); + + /* this is the case of multiple fstrims without any changes */ + if (cpc->reason == CP_DISCARD && !is_sbi_flag_set(sbi, SBI_IS_DIRTY)) { + f2fs_bug_on(sbi, NM_I(sbi)->dirty_nat_cnt); + f2fs_bug_on(sbi, SIT_I(sbi)->dirty_sentries); + f2fs_bug_on(sbi, prefree_segments(sbi)); + flush_sit_entries(sbi, cpc); + clear_prefree_segments(sbi, cpc); + unblock_operations(sbi); + goto out; + } /* * update checkpoint pack index @@ -1133,7 +1269,11 @@ void write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) flush_sit_entries(sbi, cpc); /* unlock all the fs_lock[] in do_checkpoint() */ - do_checkpoint(sbi, cpc); + err = do_checkpoint(sbi, cpc); + if (err) + release_discard_addrs(sbi); + else + clear_prefree_segments(sbi, cpc); unblock_operations(sbi); stat_inc_cp_count(sbi->stat_info); @@ -1143,10 +1283,11 @@ void write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) "checkpoint: version = %llx", ckpt_ver); /* do checkpoint periodically */ - sbi->cp_expires = round_jiffies_up(jiffies + HZ * sbi->cp_interval); + f2fs_update_time(sbi, CP_TIME); + trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish checkpoint"); out: mutex_unlock(&sbi->cp_mutex); - trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish checkpoint"); + return err; } void init_ino_entry_info(struct f2fs_sb_info *sbi) diff --git a/fs/f2fs/crypto.c b/fs/f2fs/crypto.c deleted file mode 100644 index 4a62ef14e932..000000000000 --- a/fs/f2fs/crypto.c +++ /dev/null @@ -1,491 +0,0 @@ -/* - * linux/fs/f2fs/crypto.c - * - * Copied from linux/fs/ext4/crypto.c - * - * Copyright (C) 2015, Google, Inc. - * Copyright (C) 2015, Motorola Mobility - * - * This contains encryption functions for f2fs - * - * Written by Michael Halcrow, 2014. - * - * Filename encryption additions - * Uday Savagaonkar, 2014 - * Encryption policy handling additions - * Ildar Muslukhov, 2014 - * Remove ext4_encrypted_zeroout(), - * add f2fs_restore_and_release_control_page() - * Jaegeuk Kim, 2015. - * - * This has not yet undergone a rigorous security audit. - * - * The usage of AES-XTS should conform to recommendations in NIST - * Special Publication 800-38E and IEEE P1619/D16. - */ -#include <crypto/hash.h> -#include <crypto/sha.h> -#include <keys/user-type.h> -#include <keys/encrypted-type.h> -#include <linux/crypto.h> -#include <linux/ecryptfs.h> -#include <linux/gfp.h> -#include <linux/kernel.h> -#include <linux/key.h> -#include <linux/list.h> -#include <linux/mempool.h> -#include <linux/module.h> -#include <linux/mutex.h> -#include <linux/random.h> -#include <linux/scatterlist.h> -#include <linux/spinlock_types.h> -#include <linux/f2fs_fs.h> -#include <linux/ratelimit.h> -#include <linux/bio.h> - -#include "f2fs.h" -#include "xattr.h" - -/* Encryption added and removed here! (L: */ - -static unsigned int num_prealloc_crypto_pages = 32; -static unsigned int num_prealloc_crypto_ctxs = 128; - -module_param(num_prealloc_crypto_pages, uint, 0444); -MODULE_PARM_DESC(num_prealloc_crypto_pages, - "Number of crypto pages to preallocate"); -module_param(num_prealloc_crypto_ctxs, uint, 0444); -MODULE_PARM_DESC(num_prealloc_crypto_ctxs, - "Number of crypto contexts to preallocate"); - -static mempool_t *f2fs_bounce_page_pool; - -static LIST_HEAD(f2fs_free_crypto_ctxs); -static DEFINE_SPINLOCK(f2fs_crypto_ctx_lock); - -static struct workqueue_struct *f2fs_read_workqueue; -static DEFINE_MUTEX(crypto_init); - -static struct kmem_cache *f2fs_crypto_ctx_cachep; -struct kmem_cache *f2fs_crypt_info_cachep; - -/** - * f2fs_release_crypto_ctx() - Releases an encryption context - * @ctx: The encryption context to release. - * - * If the encryption context was allocated from the pre-allocated pool, returns - * it to that pool. Else, frees it. - * - * If there's a bounce page in the context, this frees that. - */ -void f2fs_release_crypto_ctx(struct f2fs_crypto_ctx *ctx) -{ - unsigned long flags; - - if (ctx->flags & F2FS_WRITE_PATH_FL && ctx->w.bounce_page) { - mempool_free(ctx->w.bounce_page, f2fs_bounce_page_pool); - ctx->w.bounce_page = NULL; - } - ctx->w.control_page = NULL; - if (ctx->flags & F2FS_CTX_REQUIRES_FREE_ENCRYPT_FL) { - kmem_cache_free(f2fs_crypto_ctx_cachep, ctx); - } else { - spin_lock_irqsave(&f2fs_crypto_ctx_lock, flags); - list_add(&ctx->free_list, &f2fs_free_crypto_ctxs); - spin_unlock_irqrestore(&f2fs_crypto_ctx_lock, flags); - } -} - -/** - * f2fs_get_crypto_ctx() - Gets an encryption context - * @inode: The inode for which we are doing the crypto - * - * Allocates and initializes an encryption context. - * - * Return: An allocated and initialized encryption context on success; error - * value or NULL otherwise. - */ -struct f2fs_crypto_ctx *f2fs_get_crypto_ctx(struct inode *inode) -{ - struct f2fs_crypto_ctx *ctx = NULL; - unsigned long flags; - struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info; - - if (ci == NULL) - return ERR_PTR(-ENOKEY); - - /* - * We first try getting the ctx from a free list because in - * the common case the ctx will have an allocated and - * initialized crypto tfm, so it's probably a worthwhile - * optimization. For the bounce page, we first try getting it - * from the kernel allocator because that's just about as fast - * as getting it from a list and because a cache of free pages - * should generally be a "last resort" option for a filesystem - * to be able to do its job. - */ - spin_lock_irqsave(&f2fs_crypto_ctx_lock, flags); - ctx = list_first_entry_or_null(&f2fs_free_crypto_ctxs, - struct f2fs_crypto_ctx, free_list); - if (ctx) - list_del(&ctx->free_list); - spin_unlock_irqrestore(&f2fs_crypto_ctx_lock, flags); - if (!ctx) { - ctx = kmem_cache_zalloc(f2fs_crypto_ctx_cachep, GFP_NOFS); - if (!ctx) - return ERR_PTR(-ENOMEM); - ctx->flags |= F2FS_CTX_REQUIRES_FREE_ENCRYPT_FL; - } else { - ctx->flags &= ~F2FS_CTX_REQUIRES_FREE_ENCRYPT_FL; - } - ctx->flags &= ~F2FS_WRITE_PATH_FL; - return ctx; -} - -/* - * Call f2fs_decrypt on every single page, reusing the encryption - * context. - */ -static void completion_pages(struct work_struct *work) -{ - struct f2fs_crypto_ctx *ctx = - container_of(work, struct f2fs_crypto_ctx, r.work); - struct bio *bio = ctx->r.bio; - struct bio_vec *bv; - int i; - - bio_for_each_segment_all(bv, bio, i) { - struct page *page = bv->bv_page; - int ret = f2fs_decrypt(ctx, page); - - if (ret) { - WARN_ON_ONCE(1); - SetPageError(page); - } else - SetPageUptodate(page); - unlock_page(page); - } - f2fs_release_crypto_ctx(ctx); - bio_put(bio); -} - -void f2fs_end_io_crypto_work(struct f2fs_crypto_ctx *ctx, struct bio *bio) -{ - INIT_WORK(&ctx->r.work, completion_pages); - ctx->r.bio = bio; - queue_work(f2fs_read_workqueue, &ctx->r.work); -} - -static void f2fs_crypto_destroy(void) -{ - struct f2fs_crypto_ctx *pos, *n; - - list_for_each_entry_safe(pos, n, &f2fs_free_crypto_ctxs, free_list) - kmem_cache_free(f2fs_crypto_ctx_cachep, pos); - INIT_LIST_HEAD(&f2fs_free_crypto_ctxs); - if (f2fs_bounce_page_pool) - mempool_destroy(f2fs_bounce_page_pool); - f2fs_bounce_page_pool = NULL; -} - -/** - * f2fs_crypto_initialize() - Set up for f2fs encryption. - * - * We only call this when we start accessing encrypted files, since it - * results in memory getting allocated that wouldn't otherwise be used. - * - * Return: Zero on success, non-zero otherwise. - */ -int f2fs_crypto_initialize(void) -{ - int i, res = -ENOMEM; - - if (f2fs_bounce_page_pool) - return 0; - - mutex_lock(&crypto_init); - if (f2fs_bounce_page_pool) - goto already_initialized; - - for (i = 0; i < num_prealloc_crypto_ctxs; i++) { - struct f2fs_crypto_ctx *ctx; - - ctx = kmem_cache_zalloc(f2fs_crypto_ctx_cachep, GFP_KERNEL); - if (!ctx) - goto fail; - list_add(&ctx->free_list, &f2fs_free_crypto_ctxs); - } - - /* must be allocated at the last step to avoid race condition above */ - f2fs_bounce_page_pool = - mempool_create_page_pool(num_prealloc_crypto_pages, 0); - if (!f2fs_bounce_page_pool) - goto fail; - -already_initialized: - mutex_unlock(&crypto_init); - return 0; -fail: - f2fs_crypto_destroy(); - mutex_unlock(&crypto_init); - return res; -} - -/** - * f2fs_exit_crypto() - Shutdown the f2fs encryption system - */ -void f2fs_exit_crypto(void) -{ - f2fs_crypto_destroy(); - - if (f2fs_read_workqueue) - destroy_workqueue(f2fs_read_workqueue); - if (f2fs_crypto_ctx_cachep) - kmem_cache_destroy(f2fs_crypto_ctx_cachep); - if (f2fs_crypt_info_cachep) - kmem_cache_destroy(f2fs_crypt_info_cachep); -} - -int __init f2fs_init_crypto(void) -{ - int res = -ENOMEM; - - f2fs_read_workqueue = alloc_workqueue("f2fs_crypto", WQ_HIGHPRI, 0); - if (!f2fs_read_workqueue) - goto fail; - - f2fs_crypto_ctx_cachep = KMEM_CACHE(f2fs_crypto_ctx, - SLAB_RECLAIM_ACCOUNT); - if (!f2fs_crypto_ctx_cachep) - goto fail; - - f2fs_crypt_info_cachep = KMEM_CACHE(f2fs_crypt_info, - SLAB_RECLAIM_ACCOUNT); - if (!f2fs_crypt_info_cachep) - goto fail; - - return 0; -fail: - f2fs_exit_crypto(); - return res; -} - -void f2fs_restore_and_release_control_page(struct page **page) -{ - struct f2fs_crypto_ctx *ctx; - struct page *bounce_page; - - /* The bounce data pages are unmapped. */ - if ((*page)->mapping) - return; - - /* The bounce data page is unmapped. */ - bounce_page = *page; - ctx = (struct f2fs_crypto_ctx *)page_private(bounce_page); - - /* restore control page */ - *page = ctx->w.control_page; - - f2fs_restore_control_page(bounce_page); -} - -void f2fs_restore_control_page(struct page *data_page) -{ - struct f2fs_crypto_ctx *ctx = - (struct f2fs_crypto_ctx *)page_private(data_page); - - set_page_private(data_page, (unsigned long)NULL); - ClearPagePrivate(data_page); - unlock_page(data_page); - f2fs_release_crypto_ctx(ctx); -} - -/** - * f2fs_crypt_complete() - The completion callback for page encryption - * @req: The asynchronous encryption request context - * @res: The result of the encryption operation - */ -static void f2fs_crypt_complete(struct crypto_async_request *req, int res) -{ - struct f2fs_completion_result *ecr = req->data; - - if (res == -EINPROGRESS) - return; - ecr->res = res; - complete(&ecr->completion); -} - -typedef enum { - F2FS_DECRYPT = 0, - F2FS_ENCRYPT, -} f2fs_direction_t; - -static int f2fs_page_crypto(struct f2fs_crypto_ctx *ctx, - struct inode *inode, - f2fs_direction_t rw, - pgoff_t index, - struct page *src_page, - struct page *dest_page) -{ - u8 xts_tweak[F2FS_XTS_TWEAK_SIZE]; - struct ablkcipher_request *req = NULL; - DECLARE_F2FS_COMPLETION_RESULT(ecr); - struct scatterlist dst, src; - struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info; - struct crypto_ablkcipher *tfm = ci->ci_ctfm; - int res = 0; - - req = ablkcipher_request_alloc(tfm, GFP_NOFS); - if (!req) { - printk_ratelimited(KERN_ERR - "%s: crypto_request_alloc() failed\n", - __func__); - return -ENOMEM; - } - ablkcipher_request_set_callback( - req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, - f2fs_crypt_complete, &ecr); - - BUILD_BUG_ON(F2FS_XTS_TWEAK_SIZE < sizeof(index)); - memcpy(xts_tweak, &index, sizeof(index)); - memset(&xts_tweak[sizeof(index)], 0, - F2FS_XTS_TWEAK_SIZE - sizeof(index)); - - sg_init_table(&dst, 1); - sg_set_page(&dst, dest_page, PAGE_CACHE_SIZE, 0); - sg_init_table(&src, 1); - sg_set_page(&src, src_page, PAGE_CACHE_SIZE, 0); - ablkcipher_request_set_crypt(req, &src, &dst, PAGE_CACHE_SIZE, - xts_tweak); - if (rw == F2FS_DECRYPT) - res = crypto_ablkcipher_decrypt(req); - else - res = crypto_ablkcipher_encrypt(req); - if (res == -EINPROGRESS || res == -EBUSY) { - BUG_ON(req->base.data != &ecr); - wait_for_completion(&ecr.completion); - res = ecr.res; - } - ablkcipher_request_free(req); - if (res) { - printk_ratelimited(KERN_ERR - "%s: crypto_ablkcipher_encrypt() returned %d\n", - __func__, res); - return res; - } - return 0; -} - -static struct page *alloc_bounce_page(struct f2fs_crypto_ctx *ctx) -{ - ctx->w.bounce_page = mempool_alloc(f2fs_bounce_page_pool, GFP_NOWAIT); - if (ctx->w.bounce_page == NULL) - return ERR_PTR(-ENOMEM); - ctx->flags |= F2FS_WRITE_PATH_FL; - return ctx->w.bounce_page; -} - -/** - * f2fs_encrypt() - Encrypts a page - * @inode: The inode for which the encryption should take place - * @plaintext_page: The page to encrypt. Must be locked. - * - * Allocates a ciphertext page and encrypts plaintext_page into it using the ctx - * encryption context. - * - * Called on the page write path. The caller must call - * f2fs_restore_control_page() on the returned ciphertext page to - * release the bounce buffer and the encryption context. - * - * Return: An allocated page with the encrypted content on success. Else, an - * error value or NULL. - */ -struct page *f2fs_encrypt(struct inode *inode, - struct page *plaintext_page) -{ - struct f2fs_crypto_ctx *ctx; - struct page *ciphertext_page = NULL; - int err; - - BUG_ON(!PageLocked(plaintext_page)); - - ctx = f2fs_get_crypto_ctx(inode); - if (IS_ERR(ctx)) - return (struct page *)ctx; - - /* The encryption operation will require a bounce page. */ - ciphertext_page = alloc_bounce_page(ctx); - if (IS_ERR(ciphertext_page)) - goto err_out; - - ctx->w.control_page = plaintext_page; - err = f2fs_page_crypto(ctx, inode, F2FS_ENCRYPT, plaintext_page->index, - plaintext_page, ciphertext_page); - if (err) { - ciphertext_page = ERR_PTR(err); - goto err_out; - } - - SetPagePrivate(ciphertext_page); - set_page_private(ciphertext_page, (unsigned long)ctx); - lock_page(ciphertext_page); - return ciphertext_page; - -err_out: - f2fs_release_crypto_ctx(ctx); - return ciphertext_page; -} - -/** - * f2fs_decrypt() - Decrypts a page in-place - * @ctx: The encryption context. - * @page: The page to decrypt. Must be locked. - * - * Decrypts page in-place using the ctx encryption context. - * - * Called from the read completion callback. - * - * Return: Zero on success, non-zero otherwise. - */ -int f2fs_decrypt(struct f2fs_crypto_ctx *ctx, struct page *page) -{ - BUG_ON(!PageLocked(page)); - - return f2fs_page_crypto(ctx, page->mapping->host, - F2FS_DECRYPT, page->index, page, page); -} - -/* - * Convenience function which takes care of allocating and - * deallocating the encryption context - */ -int f2fs_decrypt_one(struct inode *inode, struct page *page) -{ - struct f2fs_crypto_ctx *ctx = f2fs_get_crypto_ctx(inode); - int ret; - - if (IS_ERR(ctx)) - return PTR_ERR(ctx); - ret = f2fs_decrypt(ctx, page); - f2fs_release_crypto_ctx(ctx); - return ret; -} - -bool f2fs_valid_contents_enc_mode(uint32_t mode) -{ - return (mode == F2FS_ENCRYPTION_MODE_AES_256_XTS); -} - -/** - * f2fs_validate_encryption_key_size() - Validate the encryption key size - * @mode: The key mode. - * @size: The key size to validate. - * - * Return: The validated key size for @mode. Zero if invalid. - */ -uint32_t f2fs_validate_encryption_key_size(uint32_t mode, uint32_t size) -{ - if (size == f2fs_encryption_key_size(mode)) - return size; - return 0; -} diff --git a/fs/f2fs/crypto_fname.c b/fs/f2fs/crypto_fname.c deleted file mode 100644 index 38349ed5ea51..000000000000 --- a/fs/f2fs/crypto_fname.c +++ /dev/null @@ -1,440 +0,0 @@ -/* - * linux/fs/f2fs/crypto_fname.c - * - * Copied from linux/fs/ext4/crypto.c - * - * Copyright (C) 2015, Google, Inc. - * Copyright (C) 2015, Motorola Mobility - * - * This contains functions for filename crypto management in f2fs - * - * Written by Uday Savagaonkar, 2014. - * - * Adjust f2fs dentry structure - * Jaegeuk Kim, 2015. - * - * This has not yet undergone a rigorous security audit. - */ -#include <crypto/hash.h> -#include <crypto/sha.h> -#include <keys/encrypted-type.h> -#include <keys/user-type.h> -#include <linux/crypto.h> -#include <linux/gfp.h> -#include <linux/kernel.h> -#include <linux/key.h> -#include <linux/list.h> -#include <linux/mempool.h> -#include <linux/random.h> -#include <linux/scatterlist.h> -#include <linux/spinlock_types.h> -#include <linux/f2fs_fs.h> -#include <linux/ratelimit.h> - -#include "f2fs.h" -#include "f2fs_crypto.h" -#include "xattr.h" - -/** - * f2fs_dir_crypt_complete() - - */ -static void f2fs_dir_crypt_complete(struct crypto_async_request *req, int res) -{ - struct f2fs_completion_result *ecr = req->data; - - if (res == -EINPROGRESS) - return; - ecr->res = res; - complete(&ecr->completion); -} - -bool f2fs_valid_filenames_enc_mode(uint32_t mode) -{ - return (mode == F2FS_ENCRYPTION_MODE_AES_256_CTS); -} - -static unsigned max_name_len(struct inode *inode) -{ - return S_ISLNK(inode->i_mode) ? inode->i_sb->s_blocksize : - F2FS_NAME_LEN; -} - -/** - * f2fs_fname_encrypt() - - * - * This function encrypts the input filename, and returns the length of the - * ciphertext. Errors are returned as negative numbers. We trust the caller to - * allocate sufficient memory to oname string. - */ -static int f2fs_fname_encrypt(struct inode *inode, - const struct qstr *iname, struct f2fs_str *oname) -{ - u32 ciphertext_len; - struct ablkcipher_request *req = NULL; - DECLARE_F2FS_COMPLETION_RESULT(ecr); - struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info; - struct crypto_ablkcipher *tfm = ci->ci_ctfm; - int res = 0; - char iv[F2FS_CRYPTO_BLOCK_SIZE]; - struct scatterlist src_sg, dst_sg; - int padding = 4 << (ci->ci_flags & F2FS_POLICY_FLAGS_PAD_MASK); - char *workbuf, buf[32], *alloc_buf = NULL; - unsigned lim = max_name_len(inode); - - if (iname->len <= 0 || iname->len > lim) - return -EIO; - - ciphertext_len = (iname->len < F2FS_CRYPTO_BLOCK_SIZE) ? - F2FS_CRYPTO_BLOCK_SIZE : iname->len; - ciphertext_len = f2fs_fname_crypto_round_up(ciphertext_len, padding); - ciphertext_len = (ciphertext_len > lim) ? lim : ciphertext_len; - - if (ciphertext_len <= sizeof(buf)) { - workbuf = buf; - } else { - alloc_buf = kmalloc(ciphertext_len, GFP_NOFS); - if (!alloc_buf) - return -ENOMEM; - workbuf = alloc_buf; - } - - /* Allocate request */ - req = ablkcipher_request_alloc(tfm, GFP_NOFS); - if (!req) { - printk_ratelimited(KERN_ERR - "%s: crypto_request_alloc() failed\n", __func__); - kfree(alloc_buf); - return -ENOMEM; - } - ablkcipher_request_set_callback(req, - CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, - f2fs_dir_crypt_complete, &ecr); - - /* Copy the input */ - memcpy(workbuf, iname->name, iname->len); - if (iname->len < ciphertext_len) - memset(workbuf + iname->len, 0, ciphertext_len - iname->len); - - /* Initialize IV */ - memset(iv, 0, F2FS_CRYPTO_BLOCK_SIZE); - - /* Create encryption request */ - sg_init_one(&src_sg, workbuf, ciphertext_len); - sg_init_one(&dst_sg, oname->name, ciphertext_len); - ablkcipher_request_set_crypt(req, &src_sg, &dst_sg, ciphertext_len, iv); - res = crypto_ablkcipher_encrypt(req); - if (res == -EINPROGRESS || res == -EBUSY) { - BUG_ON(req->base.data != &ecr); - wait_for_completion(&ecr.completion); - res = ecr.res; - } - kfree(alloc_buf); - ablkcipher_request_free(req); - if (res < 0) { - printk_ratelimited(KERN_ERR - "%s: Error (error code %d)\n", __func__, res); - } - oname->len = ciphertext_len; - return res; -} - -/* - * f2fs_fname_decrypt() - * This function decrypts the input filename, and returns - * the length of the plaintext. - * Errors are returned as negative numbers. - * We trust the caller to allocate sufficient memory to oname string. - */ -static int f2fs_fname_decrypt(struct inode *inode, - const struct f2fs_str *iname, struct f2fs_str *oname) -{ - struct ablkcipher_request *req = NULL; - DECLARE_F2FS_COMPLETION_RESULT(ecr); - struct scatterlist src_sg, dst_sg; - struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info; - struct crypto_ablkcipher *tfm = ci->ci_ctfm; - int res = 0; - char iv[F2FS_CRYPTO_BLOCK_SIZE]; - unsigned lim = max_name_len(inode); - - if (iname->len <= 0 || iname->len > lim) - return -EIO; - - /* Allocate request */ - req = ablkcipher_request_alloc(tfm, GFP_NOFS); - if (!req) { - printk_ratelimited(KERN_ERR - "%s: crypto_request_alloc() failed\n", __func__); - return -ENOMEM; - } - ablkcipher_request_set_callback(req, - CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, - f2fs_dir_crypt_complete, &ecr); - - /* Initialize IV */ - memset(iv, 0, F2FS_CRYPTO_BLOCK_SIZE); - - /* Create decryption request */ - sg_init_one(&src_sg, iname->name, iname->len); - sg_init_one(&dst_sg, oname->name, oname->len); - ablkcipher_request_set_crypt(req, &src_sg, &dst_sg, iname->len, iv); - res = crypto_ablkcipher_decrypt(req); - if (res == -EINPROGRESS || res == -EBUSY) { - BUG_ON(req->base.data != &ecr); - wait_for_completion(&ecr.completion); - res = ecr.res; - } - ablkcipher_request_free(req); - if (res < 0) { - printk_ratelimited(KERN_ERR - "%s: Error in f2fs_fname_decrypt (error code %d)\n", - __func__, res); - return res; - } - - oname->len = strnlen(oname->name, iname->len); - return oname->len; -} - -static const char *lookup_table = - "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+,"; - -/** - * f2fs_fname_encode_digest() - - * - * Encodes the input digest using characters from the set [a-zA-Z0-9_+]. - * The encoded string is roughly 4/3 times the size of the input string. - */ -static int digest_encode(const char *src, int len, char *dst) -{ - int i = 0, bits = 0, ac = 0; - char *cp = dst; - - while (i < len) { - ac += (((unsigned char) src[i]) << bits); - bits += 8; - do { - *cp++ = lookup_table[ac & 0x3f]; - ac >>= 6; - bits -= 6; - } while (bits >= 6); - i++; - } - if (bits) - *cp++ = lookup_table[ac & 0x3f]; - return cp - dst; -} - -static int digest_decode(const char *src, int len, char *dst) -{ - int i = 0, bits = 0, ac = 0; - const char *p; - char *cp = dst; - - while (i < len) { - p = strchr(lookup_table, src[i]); - if (p == NULL || src[i] == 0) - return -2; - ac += (p - lookup_table) << bits; - bits += 6; - if (bits >= 8) { - *cp++ = ac & 0xff; - ac >>= 8; - bits -= 8; - } - i++; - } - if (ac) - return -1; - return cp - dst; -} - -/** - * f2fs_fname_crypto_round_up() - - * - * Return: The next multiple of block size - */ -u32 f2fs_fname_crypto_round_up(u32 size, u32 blksize) -{ - return ((size + blksize - 1) / blksize) * blksize; -} - -/** - * f2fs_fname_crypto_alloc_obuff() - - * - * Allocates an output buffer that is sufficient for the crypto operation - * specified by the context and the direction. - */ -int f2fs_fname_crypto_alloc_buffer(struct inode *inode, - u32 ilen, struct f2fs_str *crypto_str) -{ - unsigned int olen; - int padding = 16; - struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info; - - if (ci) - padding = 4 << (ci->ci_flags & F2FS_POLICY_FLAGS_PAD_MASK); - if (padding < F2FS_CRYPTO_BLOCK_SIZE) - padding = F2FS_CRYPTO_BLOCK_SIZE; - olen = f2fs_fname_crypto_round_up(ilen, padding); - crypto_str->len = olen; - if (olen < F2FS_FNAME_CRYPTO_DIGEST_SIZE * 2) - olen = F2FS_FNAME_CRYPTO_DIGEST_SIZE * 2; - /* Allocated buffer can hold one more character to null-terminate the - * string */ - crypto_str->name = kmalloc(olen + 1, GFP_NOFS); - if (!(crypto_str->name)) - return -ENOMEM; - return 0; -} - -/** - * f2fs_fname_crypto_free_buffer() - - * - * Frees the buffer allocated for crypto operation. - */ -void f2fs_fname_crypto_free_buffer(struct f2fs_str *crypto_str) -{ - if (!crypto_str) - return; - kfree(crypto_str->name); - crypto_str->name = NULL; -} - -/** - * f2fs_fname_disk_to_usr() - converts a filename from disk space to user space - */ -int f2fs_fname_disk_to_usr(struct inode *inode, - f2fs_hash_t *hash, - const struct f2fs_str *iname, - struct f2fs_str *oname) -{ - const struct qstr qname = FSTR_TO_QSTR(iname); - char buf[24]; - int ret; - - if (is_dot_dotdot(&qname)) { - oname->name[0] = '.'; - oname->name[iname->len - 1] = '.'; - oname->len = iname->len; - return oname->len; - } - - if (F2FS_I(inode)->i_crypt_info) - return f2fs_fname_decrypt(inode, iname, oname); - - if (iname->len <= F2FS_FNAME_CRYPTO_DIGEST_SIZE) { - ret = digest_encode(iname->name, iname->len, oname->name); - oname->len = ret; - return ret; - } - if (hash) { - memcpy(buf, hash, 4); - memset(buf + 4, 0, 4); - } else - memset(buf, 0, 8); - memcpy(buf + 8, iname->name + ((iname->len - 17) & ~15), 16); - oname->name[0] = '_'; - ret = digest_encode(buf, 24, oname->name + 1); - oname->len = ret + 1; - return ret + 1; -} - -/** - * f2fs_fname_usr_to_disk() - converts a filename from user space to disk space - */ -int f2fs_fname_usr_to_disk(struct inode *inode, - const struct qstr *iname, - struct f2fs_str *oname) -{ - int res; - struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info; - - if (is_dot_dotdot(iname)) { - oname->name[0] = '.'; - oname->name[iname->len - 1] = '.'; - oname->len = iname->len; - return oname->len; - } - - if (ci) { - res = f2fs_fname_encrypt(inode, iname, oname); - return res; - } - /* Without a proper key, a user is not allowed to modify the filenames - * in a directory. Consequently, a user space name cannot be mapped to - * a disk-space name */ - return -EACCES; -} - -int f2fs_fname_setup_filename(struct inode *dir, const struct qstr *iname, - int lookup, struct f2fs_filename *fname) -{ - struct f2fs_crypt_info *ci; - int ret = 0, bigname = 0; - - memset(fname, 0, sizeof(struct f2fs_filename)); - fname->usr_fname = iname; - - if (!f2fs_encrypted_inode(dir) || is_dot_dotdot(iname)) { - fname->disk_name.name = (unsigned char *)iname->name; - fname->disk_name.len = iname->len; - return 0; - } - ret = f2fs_get_encryption_info(dir); - if (ret) - return ret; - ci = F2FS_I(dir)->i_crypt_info; - if (ci) { - ret = f2fs_fname_crypto_alloc_buffer(dir, iname->len, - &fname->crypto_buf); - if (ret < 0) - return ret; - ret = f2fs_fname_encrypt(dir, iname, &fname->crypto_buf); - if (ret < 0) - goto errout; - fname->disk_name.name = fname->crypto_buf.name; - fname->disk_name.len = fname->crypto_buf.len; - return 0; - } - if (!lookup) - return -EACCES; - - /* We don't have the key and we are doing a lookup; decode the - * user-supplied name - */ - if (iname->name[0] == '_') - bigname = 1; - if ((bigname && (iname->len != 33)) || - (!bigname && (iname->len > 43))) - return -ENOENT; - - fname->crypto_buf.name = kmalloc(32, GFP_KERNEL); - if (fname->crypto_buf.name == NULL) - return -ENOMEM; - ret = digest_decode(iname->name + bigname, iname->len - bigname, - fname->crypto_buf.name); - if (ret < 0) { - ret = -ENOENT; - goto errout; - } - fname->crypto_buf.len = ret; - if (bigname) { - memcpy(&fname->hash, fname->crypto_buf.name, 4); - } else { - fname->disk_name.name = fname->crypto_buf.name; - fname->disk_name.len = fname->crypto_buf.len; - } - return 0; -errout: - f2fs_fname_crypto_free_buffer(&fname->crypto_buf); - return ret; -} - -void f2fs_fname_free_filename(struct f2fs_filename *fname) -{ - kfree(fname->crypto_buf.name); - fname->crypto_buf.name = NULL; - fname->usr_fname = NULL; - fname->disk_name.name = NULL; -} diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 4fb5709256fd..283fc9de4762 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -19,6 +19,8 @@ #include <linux/bio.h> #include <linux/prefetch.h> #include <linux/uio.h> +#include <linux/mm.h> +#include <linux/memcontrol.h> #include <linux/cleancache.h> #include "f2fs.h" @@ -28,16 +30,41 @@ #include <trace/events/f2fs.h> #include <trace/events/android_fs.h> +static bool __is_cp_guaranteed(struct page *page) +{ + struct address_space *mapping = page->mapping; + struct inode *inode; + struct f2fs_sb_info *sbi; + + if (!mapping) + return false; + + inode = mapping->host; + sbi = F2FS_I_SB(inode); + + if (inode->i_ino == F2FS_META_INO(sbi) || + inode->i_ino == F2FS_NODE_INO(sbi) || + S_ISDIR(inode->i_mode) || + is_cold_data(page)) + return true; + return false; +} + static void f2fs_read_end_io(struct bio *bio) { struct bio_vec *bvec; int i; +#ifdef CONFIG_F2FS_FAULT_INJECTION + if (time_to_inject(F2FS_P_SB(bio->bi_io_vec->bv_page), FAULT_IO)) + bio->bi_error = -EIO; +#endif + if (f2fs_bio_encrypted(bio)) { if (bio->bi_error) { - f2fs_release_crypto_ctx(bio->bi_private); + fscrypt_release_ctx(bio->bi_private); } else { - f2fs_end_io_crypto_work(bio->bi_private, bio); + fscrypt_decrypt_bio_pages(bio->bi_private, bio); return; } } @@ -46,7 +73,8 @@ static void f2fs_read_end_io(struct bio *bio) struct page *page = bvec->bv_page; if (!bio->bi_error) { - SetPageUptodate(page); + if (!PageUptodate(page)) + SetPageUptodate(page); } else { ClearPageUptodate(page); SetPageError(page); @@ -64,26 +92,66 @@ static void f2fs_write_end_io(struct bio *bio) bio_for_each_segment_all(bvec, bio, i) { struct page *page = bvec->bv_page; + enum count_type type = WB_DATA_TYPE(page); - f2fs_restore_and_release_control_page(&page); + fscrypt_pullback_bio_page(&page, true); if (unlikely(bio->bi_error)) { - set_page_dirty(page); set_bit(AS_EIO, &page->mapping->flags); - f2fs_stop_checkpoint(sbi); + f2fs_stop_checkpoint(sbi, true); } + dec_page_count(sbi, type); + clear_cold_data(page); end_page_writeback(page); - dec_page_count(sbi, F2FS_WRITEBACK); } - - if (!get_pages(sbi, F2FS_WRITEBACK) && - !list_empty(&sbi->cp_wait.task_list)) + if (!get_pages(sbi, F2FS_WB_CP_DATA) && + wq_has_sleeper(&sbi->cp_wait)) wake_up(&sbi->cp_wait); bio_put(bio); } /* + * Return true, if pre_bio's bdev is same as its target device. + */ +struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi, + block_t blk_addr, struct bio *bio) +{ + struct block_device *bdev = sbi->sb->s_bdev; + int i; + + for (i = 0; i < sbi->s_ndevs; i++) { + if (FDEV(i).start_blk <= blk_addr && + FDEV(i).end_blk >= blk_addr) { + blk_addr -= FDEV(i).start_blk; + bdev = FDEV(i).bdev; + break; + } + } + if (bio) { + bio->bi_bdev = bdev; + bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(blk_addr); + } + return bdev; +} + +int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr) +{ + int i; + + for (i = 0; i < sbi->s_ndevs; i++) + if (FDEV(i).start_blk <= blkaddr && FDEV(i).end_blk >= blkaddr) + return i; + return 0; +} + +static bool __same_bdev(struct f2fs_sb_info *sbi, + block_t blk_addr, struct bio *bio) +{ + return f2fs_target_device(sbi, blk_addr, NULL) == bio->bi_bdev; +} + +/* * Low-level block read/write IO operations. */ static struct bio *__bio_alloc(struct f2fs_sb_info *sbi, block_t blk_addr, @@ -93,14 +161,24 @@ static struct bio *__bio_alloc(struct f2fs_sb_info *sbi, block_t blk_addr, bio = f2fs_bio_alloc(npages); - bio->bi_bdev = sbi->sb->s_bdev; - bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(blk_addr); + f2fs_target_device(sbi, blk_addr, bio); bio->bi_end_io = is_read ? f2fs_read_end_io : f2fs_write_end_io; bio->bi_private = is_read ? NULL : sbi; return bio; } +static inline void __submit_bio(struct f2fs_sb_info *sbi, int rw, + struct bio *bio, enum page_type type) +{ + if (!is_read_io(rw)) { + if (f2fs_sb_mounted_blkzoned(sbi->sb) && + current->plug && (type == DATA || type == NODE)) + blk_finish_plug(current->plug); + } + submit_bio(rw, bio); +} + static void __submit_merged_bio(struct f2fs_bio_info *io) { struct f2fs_io_info *fio = &io->fio; @@ -113,12 +191,58 @@ static void __submit_merged_bio(struct f2fs_bio_info *io) else trace_f2fs_submit_write_bio(io->sbi->sb, fio, io->bio); - submit_bio(fio->rw, io->bio); + __submit_bio(io->sbi, fio->rw, io->bio, fio->type); io->bio = NULL; } -void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi, - enum page_type type, int rw) +static bool __has_merged_page(struct f2fs_bio_info *io, struct inode *inode, + struct page *page, nid_t ino) +{ + struct bio_vec *bvec; + struct page *target; + int i; + + if (!io->bio) + return false; + + if (!inode && !page && !ino) + return true; + + bio_for_each_segment_all(bvec, io->bio, i) { + + if (bvec->bv_page->mapping) + target = bvec->bv_page; + else + target = fscrypt_control_page(bvec->bv_page); + + if (inode && inode == target->mapping->host) + return true; + if (page && page == target) + return true; + if (ino && ino == ino_of_node(target)) + return true; + } + + return false; +} + +static bool has_merged_page(struct f2fs_sb_info *sbi, struct inode *inode, + struct page *page, nid_t ino, + enum page_type type) +{ + enum page_type btype = PAGE_TYPE_OF_BIO(type); + struct f2fs_bio_info *io = &sbi->write_io[btype]; + bool ret; + + down_read(&io->io_rwsem); + ret = __has_merged_page(io, inode, page, ino); + up_read(&io->io_rwsem); + return ret; +} + +static void __f2fs_submit_merged_bio(struct f2fs_sb_info *sbi, + struct inode *inode, struct page *page, + nid_t ino, enum page_type type, int rw) { enum page_type btype = PAGE_TYPE_OF_BIO(type); struct f2fs_bio_info *io; @@ -127,6 +251,9 @@ void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi, down_write(&io->io_rwsem); + if (!__has_merged_page(io, inode, page, ino)) + goto out; + /* change META to META_FLUSH in the checkpoint procedure */ if (type >= META_FLUSH) { io->fio.type = META_FLUSH; @@ -136,9 +263,31 @@ void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi, io->fio.rw = WRITE_FLUSH_FUA | REQ_META | REQ_PRIO; } __submit_merged_bio(io); +out: up_write(&io->io_rwsem); } +void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi, enum page_type type, + int rw) +{ + __f2fs_submit_merged_bio(sbi, NULL, NULL, 0, type, rw); +} + +void f2fs_submit_merged_bio_cond(struct f2fs_sb_info *sbi, + struct inode *inode, struct page *page, + nid_t ino, enum page_type type, int rw) +{ + if (has_merged_page(sbi, inode, page, ino, type)) + __f2fs_submit_merged_bio(sbi, inode, page, ino, type, rw); +} + +void f2fs_flush_merged_bios(struct f2fs_sb_info *sbi) +{ + f2fs_submit_merged_bio(sbi, DATA, WRITE); + f2fs_submit_merged_bio(sbi, NODE, WRITE); + f2fs_submit_merged_bio(sbi, META, WRITE); +} + /* * Fill the locked page with data located in the block address. * Return unlocked page. @@ -146,20 +295,21 @@ void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi, int f2fs_submit_page_bio(struct f2fs_io_info *fio) { struct bio *bio; - struct page *page = fio->encrypted_page ? fio->encrypted_page : fio->page; + struct page *page = fio->encrypted_page ? + fio->encrypted_page : fio->page; trace_f2fs_submit_page_bio(page, fio); f2fs_trace_ios(fio, 0); /* Allocate a new bio */ - bio = __bio_alloc(fio->sbi, fio->blk_addr, 1, is_read_io(fio->rw)); + bio = __bio_alloc(fio->sbi, fio->new_blkaddr, 1, is_read_io(fio->rw)); - if (bio_add_page(bio, page, PAGE_CACHE_SIZE, 0) < PAGE_CACHE_SIZE) { + if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) { bio_put(bio); return -EFAULT; } - submit_bio(fio->rw, bio); + __submit_bio(fio->sbi, fio->rw, bio, fio->type); return 0; } @@ -173,39 +323,51 @@ 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); + if (fio->old_blkaddr != NEW_ADDR) + verify_block_addr(sbi, fio->old_blkaddr); + verify_block_addr(sbi, fio->new_blkaddr); - down_write(&io->io_rwsem); + bio_page = fio->encrypted_page ? fio->encrypted_page : fio->page; if (!is_read) - inc_page_count(sbi, F2FS_WRITEBACK); + inc_page_count(sbi, WB_DATA_TYPE(bio_page)); - if (io->bio && (io->last_block_in_bio != fio->blk_addr - 1 || - io->fio.rw != fio->rw)) + down_write(&io->io_rwsem); + + if (io->bio && (io->last_block_in_bio != fio->new_blkaddr - 1 || + (io->fio.rw != fio->rw) || + !__same_bdev(sbi, fio->new_blkaddr, io->bio))) __submit_merged_bio(io); alloc_new: if (io->bio == NULL) { - int bio_blocks = MAX_BIO_BLOCKS(sbi); - - io->bio = __bio_alloc(sbi, fio->blk_addr, bio_blocks, is_read); + io->bio = __bio_alloc(sbi, fio->new_blkaddr, + BIO_MAX_PAGES, is_read); io->fio = *fio; } - bio_page = fio->encrypted_page ? fio->encrypted_page : fio->page; - - if (bio_add_page(io->bio, bio_page, PAGE_CACHE_SIZE, 0) < - PAGE_CACHE_SIZE) { + if (bio_add_page(io->bio, bio_page, PAGE_SIZE, 0) < + PAGE_SIZE) { __submit_merged_bio(io); goto alloc_new; } - io->last_block_in_bio = fio->blk_addr; + io->last_block_in_bio = fio->new_blkaddr; f2fs_trace_ios(fio, 0); up_write(&io->io_rwsem); trace_f2fs_submit_page_mbio(fio->page, fio); } +static void __set_data_blkaddr(struct dnode_of_data *dn) +{ + struct f2fs_node *rn = F2FS_NODE(dn->node_page); + __le32 *addr_array; + + /* Get physical address of data block */ + addr_array = blkaddr_in_node(rn); + addr_array[dn->ofs_in_node] = cpu_to_le32(dn->data_blkaddr); +} + /* * Lock ordering for the change of data block address: * ->data_page @@ -214,39 +376,63 @@ alloc_new: */ void set_data_blkaddr(struct dnode_of_data *dn) { - struct f2fs_node *rn; - __le32 *addr_array; - struct page *node_page = dn->node_page; - unsigned int ofs_in_node = dn->ofs_in_node; - - f2fs_wait_on_page_writeback(node_page, NODE); - - rn = F2FS_NODE(node_page); + f2fs_wait_on_page_writeback(dn->node_page, NODE, true); + __set_data_blkaddr(dn); + if (set_page_dirty(dn->node_page)) + dn->node_changed = true; +} - /* Get physical address of data block */ - addr_array = blkaddr_in_node(rn); - addr_array[ofs_in_node] = cpu_to_le32(dn->data_blkaddr); - set_page_dirty(node_page); +void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr) +{ + dn->data_blkaddr = blkaddr; + set_data_blkaddr(dn); + f2fs_update_extent_cache(dn); } -int reserve_new_block(struct dnode_of_data *dn) +/* dn->ofs_in_node will be returned with up-to-date last block pointer */ +int reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count) { struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); - if (unlikely(is_inode_flag_set(F2FS_I(dn->inode), FI_NO_ALLOC))) + if (!count) + return 0; + + if (unlikely(is_inode_flag_set(dn->inode, FI_NO_ALLOC))) return -EPERM; - if (unlikely(!inc_valid_block_count(sbi, dn->inode, 1))) + if (unlikely(!inc_valid_block_count(sbi, dn->inode, &count))) return -ENOSPC; - trace_f2fs_reserve_new_block(dn->inode, dn->nid, dn->ofs_in_node); + trace_f2fs_reserve_new_blocks(dn->inode, dn->nid, + dn->ofs_in_node, count); - dn->data_blkaddr = NEW_ADDR; - set_data_blkaddr(dn); - mark_inode_dirty(dn->inode); - sync_inode_page(dn); + f2fs_wait_on_page_writeback(dn->node_page, NODE, true); + + for (; count > 0; dn->ofs_in_node++) { + block_t blkaddr = + datablock_addr(dn->node_page, dn->ofs_in_node); + if (blkaddr == NULL_ADDR) { + dn->data_blkaddr = NEW_ADDR; + __set_data_blkaddr(dn); + count--; + } + } + + if (set_page_dirty(dn->node_page)) + dn->node_changed = true; return 0; } +/* Should keep dn->ofs_in_node unchanged */ +int reserve_new_block(struct dnode_of_data *dn) +{ + unsigned int ofs_in_node = dn->ofs_in_node; + int ret; + + ret = reserve_new_blocks(dn, 1); + dn->ofs_in_node = ofs_in_node; + return ret; +} + int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index) { bool need_put = dn->inode_page ? false : true; @@ -326,13 +512,14 @@ got_it: * see, f2fs_add_link -> get_new_data_page -> init_inode_metadata. */ if (dn.data_blkaddr == NEW_ADDR) { - zero_user_segment(page, 0, PAGE_CACHE_SIZE); - SetPageUptodate(page); + zero_user_segment(page, 0, PAGE_SIZE); + if (!PageUptodate(page)) + SetPageUptodate(page); unlock_page(page); return page; } - fio.blk_addr = dn.data_blkaddr; + fio.new_blkaddr = fio.old_blkaddr = dn.data_blkaddr; fio.page = page; err = f2fs_submit_page_bio(&fio); if (err) @@ -386,14 +573,14 @@ repeat: /* wait for read completion */ lock_page(page); - if (unlikely(!PageUptodate(page))) { - f2fs_put_page(page, 1); - return ERR_PTR(-EIO); - } if (unlikely(page->mapping != mapping)) { f2fs_put_page(page, 1); goto repeat; } + if (unlikely(!PageUptodate(page))) { + f2fs_put_page(page, 1); + return ERR_PTR(-EIO); + } return page; } @@ -413,7 +600,7 @@ struct page *get_new_data_page(struct inode *inode, struct page *page; struct dnode_of_data dn; int err; -repeat: + page = f2fs_grab_cache_page(mapping, index, true); if (!page) { /* @@ -437,125 +624,99 @@ repeat: goto got_it; if (dn.data_blkaddr == NEW_ADDR) { - zero_user_segment(page, 0, PAGE_CACHE_SIZE); - SetPageUptodate(page); + zero_user_segment(page, 0, PAGE_SIZE); + if (!PageUptodate(page)) + SetPageUptodate(page); } else { f2fs_put_page(page, 1); - page = get_read_data_page(inode, index, READ_SYNC, true); + /* if ipage exists, blkaddr should be NEW_ADDR */ + f2fs_bug_on(F2FS_I_SB(inode), ipage); + page = get_lock_data_page(inode, index, true); if (IS_ERR(page)) - goto repeat; - - /* wait for read completion */ - lock_page(page); + return page; } got_it: if (new_i_size && i_size_read(inode) < - ((loff_t)(index + 1) << PAGE_CACHE_SHIFT)) { - i_size_write(inode, ((loff_t)(index + 1) << PAGE_CACHE_SHIFT)); - /* Only the directory inode sets new_i_size */ - set_inode_flag(F2FS_I(inode), FI_UPDATE_DIR); - } + ((loff_t)(index + 1) << PAGE_SHIFT)) + f2fs_i_size_write(inode, ((loff_t)(index + 1) << PAGE_SHIFT)); return page; } static int __allocate_data_block(struct dnode_of_data *dn) { struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); - struct f2fs_inode_info *fi = F2FS_I(dn->inode); struct f2fs_summary sum; struct node_info ni; - int seg = CURSEG_WARM_DATA; pgoff_t fofs; + blkcnt_t count = 1; - if (unlikely(is_inode_flag_set(F2FS_I(dn->inode), FI_NO_ALLOC))) + if (unlikely(is_inode_flag_set(dn->inode, FI_NO_ALLOC))) return -EPERM; dn->data_blkaddr = datablock_addr(dn->node_page, dn->ofs_in_node); if (dn->data_blkaddr == NEW_ADDR) goto alloc; - if (unlikely(!inc_valid_block_count(sbi, dn->inode, 1))) + if (unlikely(!inc_valid_block_count(sbi, dn->inode, &count))) return -ENOSPC; alloc: get_node_info(sbi, dn->nid, &ni); set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version); - if (dn->ofs_in_node == 0 && dn->inode_page == dn->node_page) - seg = CURSEG_DIRECT_IO; - allocate_data_block(sbi, NULL, dn->data_blkaddr, &dn->data_blkaddr, - &sum, seg); + &sum, CURSEG_WARM_DATA); set_data_blkaddr(dn); /* update i_size */ - fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) + + fofs = start_bidx_of_node(ofs_of_node(dn->node_page), dn->inode) + dn->ofs_in_node; - if (i_size_read(dn->inode) < ((loff_t)(fofs + 1) << PAGE_CACHE_SHIFT)) - i_size_write(dn->inode, - ((loff_t)(fofs + 1) << PAGE_CACHE_SHIFT)); - - /* direct IO doesn't use extent cache to maximize the performance */ - f2fs_drop_largest_extent(dn->inode, fofs); - + if (i_size_read(dn->inode) < ((loff_t)(fofs + 1) << PAGE_SHIFT)) + f2fs_i_size_write(dn->inode, + ((loff_t)(fofs + 1) << PAGE_SHIFT)); return 0; } -static void __allocate_data_blocks(struct inode *inode, loff_t offset, - size_t count) +static inline bool __force_buffered_io(struct inode *inode, int rw) { - struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct dnode_of_data dn; - u64 start = F2FS_BYTES_TO_BLK(offset); - u64 len = F2FS_BYTES_TO_BLK(count); - bool allocated; - u64 end_offset; - - while (len) { - f2fs_balance_fs(sbi); - f2fs_lock_op(sbi); - - /* When reading holes, we need its node page */ - set_new_dnode(&dn, inode, NULL, NULL, 0); - if (get_dnode_of_data(&dn, start, ALLOC_NODE)) - goto out; - - allocated = false; - end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode)); - - while (dn.ofs_in_node < end_offset && len) { - block_t blkaddr; + return ((f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) || + (rw == WRITE && test_opt(F2FS_I_SB(inode), LFS)) || + F2FS_I_SB(inode)->s_ndevs); +} - if (unlikely(f2fs_cp_error(sbi))) - goto sync_out; +int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from) +{ + struct inode *inode = file_inode(iocb->ki_filp); + struct f2fs_map_blocks map; + int err = 0; - blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node); - if (blkaddr == NULL_ADDR || blkaddr == NEW_ADDR) { - if (__allocate_data_block(&dn)) - goto sync_out; - allocated = true; - } - len--; - start++; - dn.ofs_in_node++; - } + map.m_lblk = F2FS_BLK_ALIGN(iocb->ki_pos); + map.m_len = F2FS_BYTES_TO_BLK(iocb->ki_pos + iov_iter_count(from)); + if (map.m_len > map.m_lblk) + map.m_len -= map.m_lblk; + else + map.m_len = 0; - if (allocated) - sync_inode_page(&dn); + map.m_next_pgofs = NULL; - f2fs_put_dnode(&dn); - f2fs_unlock_op(sbi); + if (iocb->ki_flags & IOCB_DIRECT) { + err = f2fs_convert_inline_inode(inode); + if (err) + return err; + return f2fs_map_blocks(inode, &map, 1, + __force_buffered_io(inode, WRITE) ? + F2FS_GET_BLOCK_PRE_AIO : + F2FS_GET_BLOCK_PRE_DIO); } - return; - -sync_out: - if (allocated) - sync_inode_page(&dn); - f2fs_put_dnode(&dn); -out: - f2fs_unlock_op(sbi); - return; + if (iocb->ki_pos + iov_iter_count(from) > MAX_INLINE_DATA) { + err = f2fs_convert_inline_inode(inode); + if (err) + return err; + } + if (!f2fs_has_inline_data(inode)) + return f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_AIO); + return err; } /* @@ -567,188 +728,210 @@ out: * b. do not use extent cache for better performance * c. give the block addresses to blockdev */ -static int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, +int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, int create, int flag) { unsigned int maxblocks = map->m_len; struct dnode_of_data dn; struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - int mode = create ? ALLOC_NODE : LOOKUP_NODE_RA; - pgoff_t pgofs, end_offset; + int mode = create ? ALLOC_NODE : LOOKUP_NODE; + pgoff_t pgofs, end_offset, end; int err = 0, ofs = 1; + unsigned int ofs_in_node, last_ofs_in_node; + blkcnt_t prealloc; struct extent_info ei; - bool allocated = false; + block_t blkaddr; + + if (!maxblocks) + return 0; map->m_len = 0; map->m_flags = 0; /* it only supports block size == page size */ pgofs = (pgoff_t)map->m_lblk; + end = pgofs + maxblocks; - if (f2fs_lookup_extent_cache(inode, pgofs, &ei)) { + if (!create && f2fs_lookup_extent_cache(inode, pgofs, &ei)) { map->m_pblk = ei.blk + pgofs - ei.fofs; map->m_len = min((pgoff_t)maxblocks, ei.fofs + ei.len - pgofs); map->m_flags = F2FS_MAP_MAPPED; goto out; } +next_dnode: if (create) - f2fs_lock_op(F2FS_I_SB(inode)); + f2fs_lock_op(sbi); /* When reading holes, we need its node page */ set_new_dnode(&dn, inode, NULL, NULL, 0); err = get_dnode_of_data(&dn, pgofs, mode); if (err) { - if (err == -ENOENT) + if (flag == F2FS_GET_BLOCK_BMAP) + map->m_pblk = 0; + if (err == -ENOENT) { err = 0; + if (map->m_next_pgofs) + *map->m_next_pgofs = + get_next_page_offset(&dn, pgofs); + } goto unlock_out; } - if (dn.data_blkaddr == NEW_ADDR || dn.data_blkaddr == NULL_ADDR) { + prealloc = 0; + last_ofs_in_node = ofs_in_node = dn.ofs_in_node; + end_offset = ADDRS_PER_PAGE(dn.node_page, inode); + +next_block: + blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node); + + if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR) { if (create) { if (unlikely(f2fs_cp_error(sbi))) { err = -EIO; - goto put_out; + goto sync_out; + } + if (flag == F2FS_GET_BLOCK_PRE_AIO) { + if (blkaddr == NULL_ADDR) { + prealloc++; + last_ofs_in_node = dn.ofs_in_node; + } + } else { + err = __allocate_data_block(&dn); + if (!err) + set_inode_flag(inode, FI_APPEND_WRITE); } - err = __allocate_data_block(&dn); if (err) - goto put_out; - allocated = true; + goto sync_out; map->m_flags = F2FS_MAP_NEW; + blkaddr = dn.data_blkaddr; } else { - if (flag != F2FS_GET_BLOCK_FIEMAP || - dn.data_blkaddr != NEW_ADDR) { - if (flag == F2FS_GET_BLOCK_BMAP) - err = -ENOENT; - goto put_out; + if (flag == F2FS_GET_BLOCK_BMAP) { + map->m_pblk = 0; + goto sync_out; } - - /* - * preallocated unwritten block should be mapped - * for fiemap. - */ - if (dn.data_blkaddr == NEW_ADDR) - map->m_flags = F2FS_MAP_UNWRITTEN; + if (flag == F2FS_GET_BLOCK_FIEMAP && + blkaddr == NULL_ADDR) { + if (map->m_next_pgofs) + *map->m_next_pgofs = pgofs + 1; + } + if (flag != F2FS_GET_BLOCK_FIEMAP || + blkaddr != NEW_ADDR) + goto sync_out; } } - map->m_flags |= F2FS_MAP_MAPPED; - map->m_pblk = dn.data_blkaddr; - map->m_len = 1; + if (flag == F2FS_GET_BLOCK_PRE_AIO) + goto skip; + + if (map->m_len == 0) { + /* preallocated unwritten block should be mapped for fiemap. */ + if (blkaddr == NEW_ADDR) + map->m_flags |= F2FS_MAP_UNWRITTEN; + map->m_flags |= F2FS_MAP_MAPPED; + + map->m_pblk = blkaddr; + map->m_len = 1; + } else if ((map->m_pblk != NEW_ADDR && + blkaddr == (map->m_pblk + ofs)) || + (map->m_pblk == NEW_ADDR && blkaddr == NEW_ADDR) || + flag == F2FS_GET_BLOCK_PRE_DIO) { + ofs++; + map->m_len++; + } else { + goto sync_out; + } - end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode)); +skip: dn.ofs_in_node++; pgofs++; -get_next: - if (dn.ofs_in_node >= end_offset) { - if (allocated) - sync_inode_page(&dn); - allocated = false; - f2fs_put_dnode(&dn); + /* preallocate blocks in batch for one dnode page */ + if (flag == F2FS_GET_BLOCK_PRE_AIO && + (pgofs == end || dn.ofs_in_node == end_offset)) { - set_new_dnode(&dn, inode, NULL, NULL, 0); - err = get_dnode_of_data(&dn, pgofs, mode); - if (err) { - if (err == -ENOENT) - err = 0; - goto unlock_out; - } + dn.ofs_in_node = ofs_in_node; + err = reserve_new_blocks(&dn, prealloc); + if (err) + goto sync_out; - end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode)); + map->m_len += dn.ofs_in_node - ofs_in_node; + if (prealloc && dn.ofs_in_node != last_ofs_in_node + 1) { + err = -ENOSPC; + goto sync_out; + } + dn.ofs_in_node = end_offset; } - if (maxblocks > map->m_len) { - block_t blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node); + if (pgofs >= end) + goto sync_out; + else if (dn.ofs_in_node < end_offset) + goto next_block; - if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR) { - if (create) { - if (unlikely(f2fs_cp_error(sbi))) { - err = -EIO; - goto sync_out; - } - err = __allocate_data_block(&dn); - if (err) - goto sync_out; - allocated = true; - map->m_flags |= F2FS_MAP_NEW; - blkaddr = dn.data_blkaddr; - } else { - /* - * we only merge preallocated unwritten blocks - * for fiemap. - */ - if (flag != F2FS_GET_BLOCK_FIEMAP || - blkaddr != NEW_ADDR) - goto sync_out; - } - } + f2fs_put_dnode(&dn); - /* Give more consecutive addresses for the readahead */ - if ((map->m_pblk != NEW_ADDR && - blkaddr == (map->m_pblk + ofs)) || - (map->m_pblk == NEW_ADDR && - blkaddr == NEW_ADDR)) { - ofs++; - dn.ofs_in_node++; - pgofs++; - map->m_len++; - goto get_next; - } + if (create) { + f2fs_unlock_op(sbi); + f2fs_balance_fs(sbi, dn.node_changed); } + goto next_dnode; + sync_out: - if (allocated) - sync_inode_page(&dn); -put_out: f2fs_put_dnode(&dn); unlock_out: - if (create) - f2fs_unlock_op(F2FS_I_SB(inode)); + if (create) { + f2fs_unlock_op(sbi); + f2fs_balance_fs(sbi, dn.node_changed); + } out: trace_f2fs_map_blocks(inode, map, err); return err; } static int __get_data_block(struct inode *inode, sector_t iblock, - struct buffer_head *bh, int create, int flag) + struct buffer_head *bh, int create, int flag, + pgoff_t *next_pgofs) { struct f2fs_map_blocks map; - int ret; + int err; map.m_lblk = iblock; map.m_len = bh->b_size >> inode->i_blkbits; + map.m_next_pgofs = next_pgofs; - ret = f2fs_map_blocks(inode, &map, create, flag); - if (!ret) { + err = f2fs_map_blocks(inode, &map, create, flag); + if (!err) { map_bh(bh, inode->i_sb, map.m_pblk); bh->b_state = (bh->b_state & ~F2FS_MAP_FLAGS) | map.m_flags; bh->b_size = map.m_len << inode->i_blkbits; } - return ret; + return err; } static int get_data_block(struct inode *inode, sector_t iblock, - struct buffer_head *bh_result, int create, int flag) + struct buffer_head *bh_result, int create, int flag, + pgoff_t *next_pgofs) { - return __get_data_block(inode, iblock, bh_result, create, flag); + return __get_data_block(inode, iblock, bh_result, create, + flag, next_pgofs); } static int get_data_block_dio(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { return __get_data_block(inode, iblock, bh_result, create, - F2FS_GET_BLOCK_DIO); + F2FS_GET_BLOCK_DIO, NULL); } static int get_data_block_bmap(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { /* Block number less than F2FS MAX BLOCKS */ - if (unlikely(iblock >= max_file_size(0))) + if (unlikely(iblock >= F2FS_I_SB(inode)->max_file_blocks)) return -EFBIG; return __get_data_block(inode, iblock, bh_result, create, - F2FS_GET_BLOCK_BMAP); + F2FS_GET_BLOCK_BMAP, NULL); } static inline sector_t logical_to_blk(struct inode *inode, loff_t offset) @@ -766,10 +949,9 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, { struct buffer_head map_bh; sector_t start_blk, last_blk; - loff_t isize = i_size_read(inode); + pgoff_t next_pgofs; u64 logical = 0, phys = 0, size = 0; u32 flags = 0; - bool past_eof = false, whole_file = false; int ret = 0; ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC); @@ -782,82 +964,55 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, return ret; } - mutex_lock(&inode->i_mutex); - - if (len >= isize) { - whole_file = true; - len = isize; - } + inode_lock(inode); if (logical_to_blk(inode, len) == 0) len = blk_to_logical(inode, 1); start_blk = logical_to_blk(inode, start); last_blk = logical_to_blk(inode, start + len - 1); + next: memset(&map_bh, 0, sizeof(struct buffer_head)); map_bh.b_size = len; ret = get_data_block(inode, start_blk, &map_bh, 0, - F2FS_GET_BLOCK_FIEMAP); + F2FS_GET_BLOCK_FIEMAP, &next_pgofs); if (ret) goto out; /* HOLE */ if (!buffer_mapped(&map_bh)) { - start_blk++; - - if (!past_eof && blk_to_logical(inode, start_blk) >= isize) - past_eof = 1; - - if (past_eof && size) { - flags |= FIEMAP_EXTENT_LAST; - ret = fiemap_fill_next_extent(fieinfo, logical, - phys, size, flags); - } else if (size) { - ret = fiemap_fill_next_extent(fieinfo, logical, - phys, size, flags); - size = 0; - } + start_blk = next_pgofs; - /* if we have holes up to/past EOF then we're done */ - if (start_blk > last_blk || past_eof || ret) - goto out; - } else { - if (start_blk > last_blk && !whole_file) { - ret = fiemap_fill_next_extent(fieinfo, logical, - phys, size, flags); - goto out; - } - - /* - * if size != 0 then we know we already have an extent - * to add, so add it. - */ - if (size) { - ret = fiemap_fill_next_extent(fieinfo, logical, - phys, size, flags); - if (ret) - goto out; - } + if (blk_to_logical(inode, start_blk) < blk_to_logical(inode, + F2FS_I_SB(inode)->max_file_blocks)) + goto prep_next; - logical = blk_to_logical(inode, start_blk); - phys = blk_to_logical(inode, map_bh.b_blocknr); - size = map_bh.b_size; - flags = 0; - if (buffer_unwritten(&map_bh)) - flags = FIEMAP_EXTENT_UNWRITTEN; + flags |= FIEMAP_EXTENT_LAST; + } - start_blk += logical_to_blk(inode, size); + if (size) { + if (f2fs_encrypted_inode(inode)) + flags |= FIEMAP_EXTENT_DATA_ENCRYPTED; - /* - * If we are past the EOF, then we need to make sure as - * soon as we find a hole that the last extent we found - * is marked with FIEMAP_EXTENT_LAST - */ - if (!past_eof && logical + size >= isize) - past_eof = true; + ret = fiemap_fill_next_extent(fieinfo, logical, + phys, size, flags); } + + if (start_blk > last_blk || ret) + goto out; + + logical = blk_to_logical(inode, start_blk); + phys = blk_to_logical(inode, map_bh.b_blocknr); + size = map_bh.b_size; + flags = 0; + if (buffer_unwritten(&map_bh)) + flags = FIEMAP_EXTENT_UNWRITTEN; + + start_blk += logical_to_blk(inode, size); + +prep_next: cond_resched(); if (fatal_signal_pending(current)) ret = -EINTR; @@ -867,10 +1022,39 @@ out: if (ret == 1) ret = 0; - mutex_unlock(&inode->i_mutex); + inode_unlock(inode); return ret; } +static struct bio *f2fs_grab_bio(struct inode *inode, block_t blkaddr, + unsigned nr_pages) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct fscrypt_ctx *ctx = NULL; + struct bio *bio; + + if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) { + ctx = fscrypt_get_ctx(inode, GFP_NOFS); + 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) + fscrypt_release_ctx(ctx); + return ERR_PTR(-ENOMEM); + } + f2fs_target_device(sbi, blkaddr, bio); + 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. @@ -889,13 +1073,13 @@ 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; map.m_lblk = 0; map.m_len = 0; map.m_flags = 0; + map.m_next_pgofs = NULL; for (page_idx = 0; nr_pages; page_idx++, nr_pages--) { @@ -934,7 +1118,7 @@ static int f2fs_mpage_readpages(struct address_space *mapping, map.m_len = last_block - block_in_file; if (f2fs_map_blocks(inode, &map, 0, - F2FS_GET_BLOCK_READ)) + F2FS_GET_BLOCK_READ)) goto set_error_page; } got_it: @@ -947,8 +1131,9 @@ got_it: goto confused; } } else { - zero_user_segment(page, 0, PAGE_CACHE_SIZE); - SetPageUptodate(page); + zero_user_segment(page, 0, PAGE_SIZE); + if (!PageUptodate(page)) + SetPageUptodate(page); unlock_page(page); goto next_page; } @@ -957,37 +1142,18 @@ got_it: * This page will go to BIO. Do we need to send this * BIO off first? */ - if (bio && (last_block_in_bio != block_nr - 1)) { + if (bio && (last_block_in_bio != block_nr - 1 || + !__same_bdev(F2FS_I_SB(inode), block_nr, bio))) { submit_and_realloc: - submit_bio(READ, bio); + __submit_bio(F2FS_I_SB(inode), READ, bio, DATA); 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)) { + bio = NULL; 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) @@ -997,22 +1163,22 @@ submit_and_realloc: goto next_page; set_error_page: SetPageError(page); - zero_user_segment(page, 0, PAGE_CACHE_SIZE); + zero_user_segment(page, 0, PAGE_SIZE); unlock_page(page); goto next_page; confused: if (bio) { - submit_bio(READ, bio); + __submit_bio(F2FS_I_SB(inode), READ, bio, DATA); bio = NULL; } unlock_page(page); next_page: if (pages) - page_cache_release(page); + put_page(page); } BUG_ON(pages && !list_empty(pages)); if (bio) - submit_bio(READ, bio); + __submit_bio(F2FS_I_SB(inode), READ, bio, DATA); return 0; } @@ -1059,23 +1225,33 @@ int do_write_data_page(struct f2fs_io_info *fio) if (err) return err; - fio->blk_addr = dn.data_blkaddr; + fio->old_blkaddr = dn.data_blkaddr; /* This page is already truncated */ - if (fio->blk_addr == NULL_ADDR) { + if (fio->old_blkaddr == NULL_ADDR) { ClearPageUptodate(page); goto out_writepage; } if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) { + gfp_t gfp_flags = GFP_NOFS; /* wait for GCed encrypted page writeback */ f2fs_wait_on_encrypted_page_writeback(F2FS_I_SB(inode), - fio->blk_addr); - - fio->encrypted_page = f2fs_encrypt(inode, fio->page); + fio->old_blkaddr); +retry_encrypt: + fio->encrypted_page = fscrypt_encrypt_page(inode, fio->page, + gfp_flags); if (IS_ERR(fio->encrypted_page)) { err = PTR_ERR(fio->encrypted_page); + if (err == -ENOMEM) { + /* flush pending ios and wait for a while */ + f2fs_flush_merged_bios(F2FS_I_SB(inode)); + congestion_wait(BLK_RW_ASYNC, HZ/50); + gfp_flags |= __GFP_NOFAIL; + err = 0; + goto retry_encrypt; + } goto out_writepage; } } @@ -1086,20 +1262,19 @@ int do_write_data_page(struct f2fs_io_info *fio) * If current allocation needs SSR, * it had better in-place writes for updated data. */ - if (unlikely(fio->blk_addr != NEW_ADDR && + if (unlikely(fio->old_blkaddr != NEW_ADDR && !is_cold_data(page) && + !IS_ATOMIC_WRITTEN_PAGE(page) && need_inplace_update(inode))) { rewrite_data_page(fio); - set_inode_flag(F2FS_I(inode), FI_UPDATE_WRITE); + set_inode_flag(inode, FI_UPDATE_WRITE); trace_f2fs_do_write_data_page(page, IPU); } else { write_data_page(&dn, fio); - set_data_blkaddr(&dn); - f2fs_update_extent_cache(&dn); trace_f2fs_do_write_data_page(page, OPU); - set_inode_flag(F2FS_I(inode), FI_APPEND_WRITE); + set_inode_flag(inode, FI_APPEND_WRITE); if (page->index == 0) - set_inode_flag(F2FS_I(inode), FI_FIRST_BLOCK_WRITTEN); + set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN); } out_writepage: f2fs_put_dnode(&dn); @@ -1113,7 +1288,8 @@ static int f2fs_write_data_page(struct page *page, struct f2fs_sb_info *sbi = F2FS_I_SB(inode); loff_t i_size = i_size_read(inode); const pgoff_t end_index = ((unsigned long long) i_size) - >> PAGE_CACHE_SHIFT; + >> PAGE_SHIFT; + loff_t psize = (page->index + 1) << PAGE_SHIFT; unsigned offset = 0; bool need_balance_fs = false; int err = 0; @@ -1134,37 +1310,37 @@ static int f2fs_write_data_page(struct page *page, * If the offset is out-of-range of file size, * this page does not have to be written to disk. */ - offset = i_size & (PAGE_CACHE_SIZE - 1); + offset = i_size & (PAGE_SIZE - 1); if ((page->index >= end_index + 1) || !offset) goto out; - zero_user_segment(page, offset, PAGE_CACHE_SIZE); + zero_user_segment(page, offset, PAGE_SIZE); write: if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) goto redirty_out; if (f2fs_is_drop_cache(inode)) goto out; - if (f2fs_is_volatile_file(inode) && !wbc->for_reclaim && - available_free_memory(sbi, BASE_CHECK)) + /* we should not write 0'th page having journal header */ + if (f2fs_is_volatile_file(inode) && (!page->index || + (!wbc->for_reclaim && + available_free_memory(sbi, BASE_CHECK)))) goto redirty_out; + /* we should bypass data pages to proceed the kworkder jobs */ + if (unlikely(f2fs_cp_error(sbi))) { + mapping_set_error(page->mapping, -EIO); + goto out; + } + /* Dentry blocks are controlled by checkpoint */ if (S_ISDIR(inode->i_mode)) { - if (unlikely(f2fs_cp_error(sbi))) - goto redirty_out; err = do_write_data_page(&fio); goto done; } - /* we should bypass data pages to proceed the kworkder jobs */ - if (unlikely(f2fs_cp_error(sbi))) { - SetPageError(page); - goto out; - } - if (!wbc->for_reclaim) need_balance_fs = true; - else if (has_not_enough_free_secs(sbi, 0)) + else if (has_not_enough_free_secs(sbi, 0, 0)) goto redirty_out; err = -EAGAIN; @@ -1173,35 +1349,37 @@ write: err = f2fs_write_inline_data(inode, page); if (err == -EAGAIN) err = do_write_data_page(&fio); + if (F2FS_I(inode)->last_disk_size < psize) + F2FS_I(inode)->last_disk_size = psize; f2fs_unlock_op(sbi); done: if (err && err != -ENOENT) goto redirty_out; - clear_cold_data(page); out: inode_dec_dirty_pages(inode); if (err) ClearPageUptodate(page); + + if (wbc->for_reclaim) { + f2fs_submit_merged_bio_cond(sbi, NULL, page, 0, DATA, WRITE); + remove_dirty_inode(inode); + } + unlock_page(page); - if (need_balance_fs) - f2fs_balance_fs(sbi); - if (wbc->for_reclaim) + f2fs_balance_fs(sbi, need_balance_fs); + + if (unlikely(f2fs_cp_error(sbi))) f2fs_submit_merged_bio(sbi, DATA, WRITE); + return 0; redirty_out: redirty_page_for_writepage(wbc, page); - return AOP_WRITEPAGE_ACTIVATE; -} - -static int __f2fs_writepage(struct page *page, struct writeback_control *wbc, - void *data) -{ - struct address_space *mapping = data; - int ret = mapping->a_ops->writepage(page, wbc); - mapping_set_error(mapping, ret); - return ret; + if (!err) + return AOP_WRITEPAGE_ACTIVATE; + unlock_page(page); + return err; } /* @@ -1210,8 +1388,7 @@ static int __f2fs_writepage(struct page *page, struct writeback_control *wbc, * warm/hot data page. */ static int f2fs_write_cache_pages(struct address_space *mapping, - struct writeback_control *wbc, writepage_t writepage, - void *data) + struct writeback_control *wbc) { int ret = 0; int done = 0; @@ -1224,10 +1401,10 @@ static int f2fs_write_cache_pages(struct address_space *mapping, int cycled; int range_whole = 0; int tag; - int step = 0; + int nwritten = 0; pagevec_init(&pvec, 0); -next: + if (wbc->range_cyclic) { writeback_index = mapping->writeback_index; /* prev offset */ index = writeback_index; @@ -1237,8 +1414,8 @@ next: cycled = 0; end = -1; } else { - index = wbc->range_start >> PAGE_CACHE_SHIFT; - end = wbc->range_end >> PAGE_CACHE_SHIFT; + index = wbc->range_start >> PAGE_SHIFT; + end = wbc->range_end >> PAGE_SHIFT; if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) range_whole = 1; cycled = 1; /* ignore range_cyclic tests */ @@ -1282,12 +1459,10 @@ continue_unlock: goto continue_unlock; } - if (step == is_cold_data(page)) - goto continue_unlock; - if (PageWriteback(page)) { if (wbc->sync_mode != WB_SYNC_NONE) - f2fs_wait_on_page_writeback(page, DATA); + f2fs_wait_on_page_writeback(page, + DATA, true); else goto continue_unlock; } @@ -1296,16 +1471,22 @@ continue_unlock: if (!clear_page_dirty_for_io(page)) goto continue_unlock; - ret = (*writepage)(page, wbc, data); + ret = mapping->a_ops->writepage(page, wbc); if (unlikely(ret)) { + /* + * keep nr_to_write, since vfs uses this to + * get # of written pages. + */ if (ret == AOP_WRITEPAGE_ACTIVATE) { unlock_page(page); ret = 0; - } else { - done_index = page->index + 1; - done = 1; - break; + continue; } + done_index = page->index + 1; + done = 1; + break; + } else { + nwritten++; } if (--wbc->nr_to_write <= 0 && @@ -1318,11 +1499,6 @@ continue_unlock: cond_resched(); } - if (step < 1) { - step++; - goto next; - } - if (!cycled && !done) { cycled = 1; index = 0; @@ -1332,6 +1508,10 @@ continue_unlock: if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0)) mapping->writeback_index = done_index; + if (nwritten) + f2fs_submit_merged_bio_cond(F2FS_M_SB(mapping), mapping->host, + NULL, 0, DATA, WRITE); + return ret; } @@ -1340,11 +1520,8 @@ static int f2fs_write_data_pages(struct address_space *mapping, { struct inode *inode = mapping->host; struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - bool locked = false; + struct blk_plug plug; int ret; - long diff; - - trace_f2fs_writepages(mapping->host, wbc, DATA); /* deal with chardevs and other special file */ if (!mapping->a_ops->writepage) @@ -1359,39 +1536,117 @@ static int f2fs_write_data_pages(struct address_space *mapping, available_free_memory(sbi, DIRTY_DENTS)) goto skip_write; + /* skip writing during file defragment */ + if (is_inode_flag_set(inode, FI_DO_DEFRAG)) + goto skip_write; + /* during POR, we don't need to trigger writepage at all. */ if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) goto skip_write; - diff = nr_pages_to_write(sbi, DATA, wbc); - - if (!S_ISDIR(inode->i_mode)) { - mutex_lock(&sbi->writepages); - locked = true; - } - ret = f2fs_write_cache_pages(mapping, wbc, __f2fs_writepage, mapping); - f2fs_submit_merged_bio(sbi, DATA, WRITE); - if (locked) - mutex_unlock(&sbi->writepages); + trace_f2fs_writepages(mapping->host, wbc, DATA); - remove_dirty_dir_inode(inode); + blk_start_plug(&plug); + ret = f2fs_write_cache_pages(mapping, wbc); + blk_finish_plug(&plug); + /* + * if some pages were truncated, we cannot guarantee its mapping->host + * to detect pending bios. + */ - wbc->nr_to_write = max((long)0, wbc->nr_to_write - diff); + remove_dirty_inode(inode); return ret; skip_write: wbc->pages_skipped += get_dirty_pages(inode); + trace_f2fs_writepages(mapping->host, wbc, DATA); return 0; } static void f2fs_write_failed(struct address_space *mapping, loff_t to) { struct inode *inode = mapping->host; + loff_t i_size = i_size_read(inode); + + if (to > i_size) { + truncate_pagecache(inode, i_size); + truncate_blocks(inode, i_size, true); + } +} + +static int prepare_write_begin(struct f2fs_sb_info *sbi, + struct page *page, loff_t pos, unsigned len, + block_t *blk_addr, bool *node_changed) +{ + struct inode *inode = page->mapping->host; + pgoff_t index = page->index; + struct dnode_of_data dn; + struct page *ipage; + bool locked = false; + struct extent_info ei; + int err = 0; + + /* + * we already allocated all the blocks, so we don't need to get + * the block addresses when there is no need to fill the page. + */ + if (!f2fs_has_inline_data(inode) && len == PAGE_SIZE) + return 0; + + if (f2fs_has_inline_data(inode) || + (pos & PAGE_MASK) >= i_size_read(inode)) { + f2fs_lock_op(sbi); + locked = true; + } +restart: + /* check inline_data */ + ipage = get_node_page(sbi, inode->i_ino); + if (IS_ERR(ipage)) { + err = PTR_ERR(ipage); + goto unlock_out; + } + + set_new_dnode(&dn, inode, ipage, ipage, 0); - if (to > inode->i_size) { - truncate_pagecache(inode, inode->i_size); - truncate_blocks(inode, inode->i_size, true); + if (f2fs_has_inline_data(inode)) { + if (pos + len <= MAX_INLINE_DATA) { + read_inline_data(page, ipage); + set_inode_flag(inode, FI_DATA_EXIST); + if (inode->i_nlink) + set_inline_node(ipage); + } else { + err = f2fs_convert_inline_page(&dn, page); + if (err) + goto out; + if (dn.data_blkaddr == NULL_ADDR) + err = f2fs_get_block(&dn, index); + } + } else if (locked) { + err = f2fs_get_block(&dn, index); + } else { + if (f2fs_lookup_extent_cache(inode, index, &ei)) { + dn.data_blkaddr = ei.blk + index - ei.fofs; + } else { + /* hole case */ + err = get_dnode_of_data(&dn, index, LOOKUP_NODE); + if (err || dn.data_blkaddr == NULL_ADDR) { + f2fs_put_dnode(&dn); + f2fs_lock_op(sbi); + locked = true; + goto restart; + } + } } + + /* convert_inline_page can make node_changed */ + *blk_addr = dn.data_blkaddr; + *node_changed = dn.node_changed; +out: + f2fs_put_dnode(&dn); +unlock_out: + if (locked) + f2fs_unlock_op(sbi); + return err; } static int f2fs_write_begin(struct file *file, struct address_space *mapping, @@ -1401,9 +1656,9 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping, struct inode *inode = mapping->host; struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct page *page = NULL; - struct page *ipage; - pgoff_t index = ((unsigned long long) pos) >> PAGE_CACHE_SHIFT; - struct dnode_of_data dn; + pgoff_t index = ((unsigned long long) pos) >> PAGE_SHIFT; + bool need_balance = false; + block_t blkaddr = NULL_ADDR; int err = 0; if (trace_android_fs_datawrite_start_enabled()) { @@ -1418,8 +1673,6 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping, } trace_f2fs_write_begin(inode, pos, len, flags); - f2fs_balance_fs(sbi); - /* * We should check this at this moment to avoid deadlock on inode page * and #0 page. The locking rule for inline_data conversion should be: @@ -1439,98 +1692,63 @@ repeat: *pagep = page; - f2fs_lock_op(sbi); - - /* check inline_data */ - ipage = get_node_page(sbi, inode->i_ino); - if (IS_ERR(ipage)) { - err = PTR_ERR(ipage); - goto unlock_fail; - } - - set_new_dnode(&dn, inode, ipage, ipage, 0); + err = prepare_write_begin(sbi, page, pos, len, + &blkaddr, &need_balance); + if (err) + goto fail; - if (f2fs_has_inline_data(inode)) { - if (pos + len <= MAX_INLINE_DATA) { - read_inline_data(page, ipage); - set_inode_flag(F2FS_I(inode), FI_DATA_EXIST); - sync_inode_page(&dn); - goto put_next; + if (need_balance && has_not_enough_free_secs(sbi, 0, 0)) { + unlock_page(page); + f2fs_balance_fs(sbi, true); + lock_page(page); + if (page->mapping != mapping) { + /* The page got truncated from under us */ + f2fs_put_page(page, 1); + goto repeat; } - err = f2fs_convert_inline_page(&dn, page); - if (err) - goto put_fail; } - err = f2fs_get_block(&dn, index); - if (err) - goto put_fail; -put_next: - f2fs_put_dnode(&dn); - f2fs_unlock_op(sbi); - - f2fs_wait_on_page_writeback(page, DATA); + f2fs_wait_on_page_writeback(page, DATA, false); /* wait for GCed encrypted page writeback */ if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) - f2fs_wait_on_encrypted_page_writeback(sbi, dn.data_blkaddr); - - if (len == PAGE_CACHE_SIZE) - goto out_update; - if (PageUptodate(page)) - goto out_clear; - - if ((pos & PAGE_CACHE_MASK) >= i_size_read(inode)) { - unsigned start = pos & (PAGE_CACHE_SIZE - 1); - unsigned end = start + len; + f2fs_wait_on_encrypted_page_writeback(sbi, blkaddr); - /* Reading beyond i_size is simple: memset to zero */ - zero_user_segments(page, 0, start, end, PAGE_CACHE_SIZE); - goto out_update; - } + if (len == PAGE_SIZE || PageUptodate(page)) + return 0; - if (dn.data_blkaddr == NEW_ADDR) { - zero_user_segment(page, 0, PAGE_CACHE_SIZE); + if (blkaddr == NEW_ADDR) { + zero_user_segment(page, 0, PAGE_SIZE); + SetPageUptodate(page); } 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, blkaddr, 1); + if (IS_ERR(bio)) { + err = PTR_ERR(bio); goto fail; + } - lock_page(page); - if (unlikely(!PageUptodate(page))) { - err = -EIO; + if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) { + bio_put(bio); + err = -EFAULT; goto fail; } + + __submit_bio(sbi, READ_SYNC, bio, DATA); + + lock_page(page); if (unlikely(page->mapping != mapping)) { 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; + if (unlikely(!PageUptodate(page))) { + err = -EIO; + goto fail; } } -out_update: - SetPageUptodate(page); -out_clear: - clear_cold_data(page); return 0; -put_fail: - f2fs_put_dnode(&dn); -unlock_fail: - f2fs_unlock_op(sbi); fail: f2fs_put_page(page, 1); f2fs_write_failed(mapping, pos + len); @@ -1547,15 +1765,27 @@ static int f2fs_write_end(struct file *file, trace_android_fs_datawrite_end(inode, pos, len); trace_f2fs_write_end(inode, pos, len, copied); - set_page_dirty(page); - - if (pos + copied > i_size_read(inode)) { - i_size_write(inode, pos + copied); - mark_inode_dirty(inode); - update_inode_page(inode); + /* + * This should be come from len == PAGE_SIZE, and we expect copied + * should be PAGE_SIZE. Otherwise, we treat it with zero copied and + * let generic_perform_write() try to copy data again through copied=0. + */ + if (!PageUptodate(page)) { + if (unlikely(copied != PAGE_SIZE)) + copied = 0; + else + SetPageUptodate(page); } + if (!copied) + goto unlock_out; + set_page_dirty(page); + + if (pos + copied > i_size_read(inode)) + f2fs_i_size_write(inode, pos + copied); +unlock_out: f2fs_put_page(page, 1); + f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); return copied; } @@ -1574,29 +1804,20 @@ static int check_direct_IO(struct inode *inode, struct iov_iter *iter, } static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, - loff_t offset) + loff_t offset) { - struct file *file = iocb->ki_filp; - struct address_space *mapping = file->f_mapping; + struct address_space *mapping = iocb->ki_filp->f_mapping; struct inode *inode = mapping->host; size_t count = iov_iter_count(iter); + int rw = iov_iter_rw(iter); int err; - /* we don't need to use inline_data strictly */ - if (f2fs_has_inline_data(inode)) { - err = f2fs_convert_inline_inode(inode); - if (err) - return err; - } - - if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) - return 0; - err = check_direct_IO(inode, iter, offset); if (err) return err; - trace_f2fs_direct_IO_enter(inode, offset, count, iov_iter_rw(iter)); + if (__force_buffered_io(inode, rw)) + return 0; if (trace_android_fs_dataread_start_enabled() && (iov_iter_rw(iter) == READ)) { @@ -1620,18 +1841,18 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, current->pid, path, current->comm); } - if (iov_iter_rw(iter) == WRITE) { - __allocate_data_blocks(inode, offset, count); - if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) { - err = -EIO; - goto out; - } - } + trace_f2fs_direct_IO_enter(inode, offset, count, rw); + down_read(&F2FS_I(inode)->dio_rwsem[rw]); err = blockdev_direct_IO(iocb, inode, iter, offset, get_data_block_dio); -out: - if (err < 0 && iov_iter_rw(iter) == WRITE) - f2fs_write_failed(mapping, offset + count); + up_read(&F2FS_I(inode)->dio_rwsem[rw]); + + if (rw == WRITE) { + if (err > 0) + set_inode_flag(inode, FI_UPDATE_WRITE); + else if (err < 0) + f2fs_write_failed(mapping, offset + count); + } if (trace_android_fs_dataread_start_enabled() && (iov_iter_rw(iter) == READ)) @@ -1640,7 +1861,7 @@ out: (iov_iter_rw(iter) == WRITE)) trace_android_fs_datawrite_end(inode, offset, count); - trace_f2fs_direct_IO_exit(inode, offset, count, iov_iter_rw(iter), err); + trace_f2fs_direct_IO_exit(inode, offset, count, rw, err); return err; } @@ -1652,22 +1873,25 @@ void f2fs_invalidate_page(struct page *page, unsigned int offset, struct f2fs_sb_info *sbi = F2FS_I_SB(inode); if (inode->i_ino >= F2FS_ROOT_INO(sbi) && - (offset % PAGE_CACHE_SIZE || length != PAGE_CACHE_SIZE)) + (offset % PAGE_SIZE || length != PAGE_SIZE)) return; if (PageDirty(page)) { - if (inode->i_ino == F2FS_META_INO(sbi)) + if (inode->i_ino == F2FS_META_INO(sbi)) { dec_page_count(sbi, F2FS_DIRTY_META); - else if (inode->i_ino == F2FS_NODE_INO(sbi)) + } else if (inode->i_ino == F2FS_NODE_INO(sbi)) { dec_page_count(sbi, F2FS_DIRTY_NODES); - else + } else { inode_dec_dirty_pages(inode); + remove_dirty_inode(inode); + } } /* This is atomic written page, keep Private */ if (IS_ATOMIC_WRITTEN_PAGE(page)) return; + set_page_private(page, 0); ClearPagePrivate(page); } @@ -1681,10 +1905,42 @@ int f2fs_release_page(struct page *page, gfp_t wait) if (IS_ATOMIC_WRITTEN_PAGE(page)) return 0; + set_page_private(page, 0); ClearPagePrivate(page); return 1; } +/* + * This was copied from __set_page_dirty_buffers which gives higher performance + * in very high speed storages. (e.g., pmem) + */ +void f2fs_set_page_dirty_nobuffers(struct page *page) +{ + struct address_space *mapping = page->mapping; + struct mem_cgroup *memcg; + unsigned long flags; + + if (unlikely(!mapping)) + return; + + spin_lock(&mapping->private_lock); + memcg = mem_cgroup_begin_page_stat(page); + SetPageDirty(page); + spin_unlock(&mapping->private_lock); + + spin_lock_irqsave(&mapping->tree_lock, flags); + WARN_ON_ONCE(!PageUptodate(page)); + account_page_dirtied(page, mapping, memcg); + radix_tree_tag_set(&mapping->page_tree, + page_index(page), PAGECACHE_TAG_DIRTY); + spin_unlock_irqrestore(&mapping->tree_lock, flags); + + mem_cgroup_end_page_stat(memcg); + + __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); + return; +} + static int f2fs_set_data_page_dirty(struct page *page) { struct address_space *mapping = page->mapping; @@ -1692,7 +1948,8 @@ static int f2fs_set_data_page_dirty(struct page *page) trace_f2fs_set_page_dirty(page, DATA); - SetPageUptodate(page); + if (!PageUptodate(page)) + SetPageUptodate(page); if (f2fs_is_atomic_file(inode)) { if (!IS_ATOMIC_WRITTEN_PAGE(page)) { @@ -1707,7 +1964,7 @@ static int f2fs_set_data_page_dirty(struct page *page) } if (!PageDirty(page)) { - __set_page_dirty_nobuffers(page); + f2fs_set_page_dirty_nobuffers(page); update_dirty_page(inode, page); return 1; } @@ -1728,6 +1985,58 @@ static sector_t f2fs_bmap(struct address_space *mapping, sector_t block) return generic_block_bmap(mapping, block, get_data_block_bmap); } +#ifdef CONFIG_MIGRATION +#include <linux/migrate.h> + +int f2fs_migrate_page(struct address_space *mapping, + struct page *newpage, struct page *page, enum migrate_mode mode) +{ + int rc, extra_count; + struct f2fs_inode_info *fi = F2FS_I(mapping->host); + bool atomic_written = IS_ATOMIC_WRITTEN_PAGE(page); + + BUG_ON(PageWriteback(page)); + + /* migrating an atomic written page is safe with the inmem_lock hold */ + if (atomic_written && !mutex_trylock(&fi->inmem_lock)) + return -EAGAIN; + + /* + * A reference is expected if PagePrivate set when move mapping, + * however F2FS breaks this for maintaining dirty page counts when + * truncating pages. So here adjusting the 'extra_count' make it work. + */ + extra_count = (atomic_written ? 1 : 0) - page_has_private(page); + rc = migrate_page_move_mapping(mapping, newpage, + page, NULL, mode, extra_count); + if (rc != MIGRATEPAGE_SUCCESS) { + if (atomic_written) + mutex_unlock(&fi->inmem_lock); + return rc; + } + + if (atomic_written) { + struct inmem_pages *cur; + list_for_each_entry(cur, &fi->inmem_pages, list) + if (cur->page == page) { + cur->page = newpage; + break; + } + mutex_unlock(&fi->inmem_lock); + put_page(page); + get_page(newpage); + } + + if (PagePrivate(page)) + SetPagePrivate(newpage); + set_page_private(newpage, page_private(page)); + + migrate_page_copy(newpage, page); + + return MIGRATEPAGE_SUCCESS; +} +#endif + const struct address_space_operations f2fs_dblock_aops = { .readpage = f2fs_read_data_page, .readpages = f2fs_read_data_pages, @@ -1740,4 +2049,7 @@ const struct address_space_operations f2fs_dblock_aops = { .releasepage = f2fs_release_page, .direct_IO = f2fs_direct_IO, .bmap = f2fs_bmap, +#ifdef CONFIG_MIGRATION + .migratepage = f2fs_migrate_page, +#endif }; diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c index 24d6a51b48d1..fbd5184140d0 100644 --- a/fs/f2fs/debug.c +++ b/fs/f2fs/debug.c @@ -38,23 +38,31 @@ static void update_general_status(struct f2fs_sb_info *sbi) si->hit_rbtree = atomic64_read(&sbi->read_hit_rbtree); si->hit_total = si->hit_largest + si->hit_cached + si->hit_rbtree; si->total_ext = atomic64_read(&sbi->total_hit_ext); - si->ext_tree = sbi->total_ext_tree; + si->ext_tree = atomic_read(&sbi->total_ext_tree); + si->zombie_tree = atomic_read(&sbi->total_zombie_tree); si->ext_node = atomic_read(&sbi->total_ext_node); si->ndirty_node = get_pages(sbi, F2FS_DIRTY_NODES); si->ndirty_dent = get_pages(sbi, F2FS_DIRTY_DENTS); - si->ndirty_dirs = sbi->n_dirty_dirs; si->ndirty_meta = get_pages(sbi, F2FS_DIRTY_META); + si->ndirty_data = get_pages(sbi, F2FS_DIRTY_DATA); + si->ndirty_imeta = get_pages(sbi, F2FS_DIRTY_IMETA); + si->ndirty_dirs = sbi->ndirty_inode[DIR_INODE]; + si->ndirty_files = sbi->ndirty_inode[FILE_INODE]; + si->ndirty_all = sbi->ndirty_inode[DIRTY_META]; si->inmem_pages = get_pages(sbi, F2FS_INMEM_PAGES); - si->wb_pages = get_pages(sbi, F2FS_WRITEBACK); + si->nr_wb_cp_data = get_pages(sbi, F2FS_WB_CP_DATA); + si->nr_wb_data = get_pages(sbi, F2FS_WB_DATA); si->total_count = (int)sbi->user_block_count / sbi->blocks_per_seg; si->rsvd_segs = reserved_segments(sbi); si->overp_segs = overprovision_segments(sbi); si->valid_count = valid_user_blocks(sbi); + si->discard_blks = discard_blocks(sbi); si->valid_node_count = valid_node_count(sbi); si->valid_inode_count = valid_inode_count(sbi); si->inline_xattr = atomic_read(&sbi->inline_xattr); si->inline_inode = atomic_read(&sbi->inline_inode); si->inline_dir = atomic_read(&sbi->inline_dir); + si->orphans = sbi->im[ORPHAN_INO].ino_num; si->utilization = utilization(sbi); si->free_segs = free_segments(sbi); @@ -67,7 +75,8 @@ static void update_general_status(struct f2fs_sb_info *sbi) si->dirty_nats = NM_I(sbi)->dirty_nat_cnt; si->sits = MAIN_SEGS(sbi); si->dirty_sits = SIT_I(sbi)->dirty_sentries; - si->fnids = NM_I(sbi)->fcnt; + si->free_nids = NM_I(sbi)->nid_cnt[FREE_NID_LIST]; + si->alloc_nids = NM_I(sbi)->nid_cnt[ALLOC_NID_LIST]; si->bg_gc = sbi->bg_gc; si->util_free = (int)(free_user_blocks(sbi) >> sbi->log_blocks_per_seg) * 100 / (int)(sbi->user_block_count >> sbi->log_blocks_per_seg) @@ -105,7 +114,7 @@ static void update_sit_info(struct f2fs_sb_info *sbi) bimodal = 0; total_vblocks = 0; - blks_per_sec = sbi->segs_per_sec * (1 << sbi->log_blocks_per_seg); + blks_per_sec = sbi->segs_per_sec * sbi->blocks_per_seg; hblks_per_sec = blks_per_sec / 2; for (segno = 0; segno < MAIN_SEGS(sbi); segno += sbi->segs_per_sec) { vblocks = get_valid_blocks(sbi, segno, sbi->segs_per_sec); @@ -140,6 +149,7 @@ static void update_mem_info(struct f2fs_sb_info *sbi) si->base_mem = sizeof(struct f2fs_sb_info) + sbi->sb->s_blocksize; si->base_mem += 2 * sizeof(struct f2fs_inode_info); si->base_mem += sizeof(*sbi->ckpt); + si->base_mem += sizeof(struct percpu_counter) * NR_COUNT_TYPE; /* build sm */ si->base_mem += sizeof(struct f2fs_sm_info); @@ -148,7 +158,9 @@ static void update_mem_info(struct f2fs_sb_info *sbi) si->base_mem += sizeof(struct sit_info); si->base_mem += MAIN_SEGS(sbi) * sizeof(struct seg_entry); si->base_mem += f2fs_bitmap_size(MAIN_SEGS(sbi)); - si->base_mem += 3 * SIT_VBLOCK_MAP_SIZE * MAIN_SEGS(sbi); + si->base_mem += 2 * SIT_VBLOCK_MAP_SIZE * MAIN_SEGS(sbi); + if (f2fs_discard_en(sbi)) + si->base_mem += SIT_VBLOCK_MAP_SIZE * MAIN_SEGS(sbi); si->base_mem += SIT_VBLOCK_MAP_SIZE; if (sbi->segs_per_sec > 1) si->base_mem += MAIN_SECS(sbi) * sizeof(struct sec_entry); @@ -161,7 +173,7 @@ static void update_mem_info(struct f2fs_sb_info *sbi) /* build curseg */ si->base_mem += sizeof(struct curseg_info) * NR_CURSEG_TYPE; - si->base_mem += PAGE_CACHE_SIZE * NR_CURSEG_TYPE; + si->base_mem += PAGE_SIZE * NR_CURSEG_TYPE; /* build dirty segmap */ si->base_mem += sizeof(struct dirty_seglist_info); @@ -184,23 +196,25 @@ get_cache: si->cache_mem += sizeof(struct flush_cmd_control); /* free nids */ - si->cache_mem += NM_I(sbi)->fcnt * sizeof(struct free_nid); + si->cache_mem += (NM_I(sbi)->nid_cnt[FREE_NID_LIST] + + NM_I(sbi)->nid_cnt[ALLOC_NID_LIST]) * + sizeof(struct free_nid); si->cache_mem += NM_I(sbi)->nat_cnt * sizeof(struct nat_entry); si->cache_mem += NM_I(sbi)->dirty_nat_cnt * sizeof(struct nat_entry_set); si->cache_mem += si->inmem_pages * sizeof(struct inmem_pages); - si->cache_mem += sbi->n_dirty_dirs * sizeof(struct inode_entry); - for (i = 0; i <= UPDATE_INO; i++) + for (i = 0; i <= ORPHAN_INO; i++) si->cache_mem += sbi->im[i].ino_num * sizeof(struct ino_entry); - si->cache_mem += sbi->total_ext_tree * sizeof(struct extent_tree); + si->cache_mem += atomic_read(&sbi->total_ext_tree) * + sizeof(struct extent_tree); si->cache_mem += atomic_read(&sbi->total_ext_node) * sizeof(struct extent_node); si->page_mem = 0; npages = NODE_MAPPING(sbi)->nrpages; - si->page_mem += (unsigned long long)npages << PAGE_CACHE_SHIFT; + si->page_mem += (unsigned long long)npages << PAGE_SHIFT; npages = META_MAPPING(sbi)->nrpages; - si->page_mem += (unsigned long long)npages << PAGE_CACHE_SHIFT; + si->page_mem += (unsigned long long)npages << PAGE_SHIFT; } static int stat_show(struct seq_file *s, void *v) @@ -211,20 +225,24 @@ static int stat_show(struct seq_file *s, void *v) mutex_lock(&f2fs_stat_mutex); list_for_each_entry(si, &f2fs_stat_list, stat_list) { - char devname[BDEVNAME_SIZE]; - update_general_status(si->sbi); - seq_printf(s, "\n=====[ partition info(%s). #%d ]=====\n", - bdevname(si->sbi->sb->s_bdev, devname), i++); + seq_printf(s, "\n=====[ partition info(%pg). #%d, %s]=====\n", + si->sbi->sb->s_bdev, i++, + f2fs_readonly(si->sbi->sb) ? "RO": "RW"); seq_printf(s, "[SB: 1] [CP: 2] [SIT: %d] [NAT: %d] ", si->sit_area_segs, si->nat_area_segs); seq_printf(s, "[SSA: %d] [MAIN: %d", si->ssa_area_segs, si->main_area_segs); seq_printf(s, "(OverProv:%d Resv:%d)]\n\n", si->overp_segs, si->rsvd_segs); - seq_printf(s, "Utilization: %d%% (%d valid blocks)\n", - si->utilization, si->valid_count); + if (test_opt(si->sbi, DISCARD)) + seq_printf(s, "Utilization: %u%% (%u valid blocks, %u discard blocks)\n", + si->utilization, si->valid_count, si->discard_blks); + else + seq_printf(s, "Utilization: %u%% (%u valid blocks)\n", + si->utilization, si->valid_count); + seq_printf(s, " - Node: %u (Inode: %u, ", si->valid_node_count, si->valid_inode_count); seq_printf(s, "Other: %u)\n - Data: %u\n", @@ -236,6 +254,8 @@ static int stat_show(struct seq_file *s, void *v) si->inline_inode); seq_printf(s, " - Inline_dentry Inode: %u\n", si->inline_dir); + seq_printf(s, " - Orphan Inode: %u\n", + si->orphans); seq_printf(s, "\nMain area: %d segs, %d secs %d zones\n", si->main_area_segs, si->main_area_sections, si->main_area_zones); @@ -269,7 +289,8 @@ static int stat_show(struct seq_file *s, void *v) si->dirty_count); seq_printf(s, " - Prefree: %d\n - Free: %d (%d)\n\n", si->prefree_count, si->free_segs, si->free_secs); - seq_printf(s, "CP calls: %d\n", si->cp_count); + seq_printf(s, "CP calls: %d (BG: %d)\n", + si->cp_count, si->bg_cp_count); seq_printf(s, "GC calls: %d (BG: %d)\n", si->call_count, si->bg_gc); seq_printf(s, " - data segments : %d (%d)\n", @@ -290,21 +311,25 @@ static int stat_show(struct seq_file *s, void *v) !si->total_ext ? 0 : div64_u64(si->hit_total * 100, si->total_ext), si->hit_total, si->total_ext); - seq_printf(s, " - Inner Struct Count: tree: %d, node: %d\n", - si->ext_tree, si->ext_node); + seq_printf(s, " - Inner Struct Count: tree: %d(%d), node: %d\n", + si->ext_tree, si->zombie_tree, si->ext_node); seq_puts(s, "\nBalancing F2FS Async:\n"); - seq_printf(s, " - inmem: %4d, wb: %4d\n", - si->inmem_pages, si->wb_pages); + seq_printf(s, " - inmem: %4d, wb_cp_data: %4d, wb_data: %4d\n", + si->inmem_pages, si->nr_wb_cp_data, si->nr_wb_data); seq_printf(s, " - nodes: %4d in %4d\n", si->ndirty_node, si->node_pages); - seq_printf(s, " - dents: %4d in dirs:%4d\n", - si->ndirty_dent, si->ndirty_dirs); + seq_printf(s, " - dents: %4d in dirs:%4d (%4d)\n", + si->ndirty_dent, si->ndirty_dirs, si->ndirty_all); + seq_printf(s, " - datas: %4d in files:%4d\n", + si->ndirty_data, si->ndirty_files); seq_printf(s, " - meta: %4d in %4d\n", si->ndirty_meta, si->meta_pages); + seq_printf(s, " - imeta: %4d\n", + si->ndirty_imeta); seq_printf(s, " - NATs: %9d/%9d\n - SITs: %9d/%9d\n", si->dirty_nats, si->nats, si->dirty_sits, si->sits); - seq_printf(s, " - free_nids: %9d\n", - si->fnids); + seq_printf(s, " - free_nids: %9d, alloc_nids: %9d\n", + si->free_nids, si->alloc_nids); seq_puts(s, "\nDistribution of User Blocks:"); seq_puts(s, " [ valid | invalid | free ]\n"); seq_puts(s, " ["); @@ -407,20 +432,23 @@ void f2fs_destroy_stats(struct f2fs_sb_info *sbi) kfree(si); } -void __init f2fs_create_root_stats(void) +int __init f2fs_create_root_stats(void) { struct dentry *file; f2fs_debugfs_root = debugfs_create_dir("f2fs", NULL); if (!f2fs_debugfs_root) - return; + return -ENOMEM; file = debugfs_create_file("status", S_IRUGO, f2fs_debugfs_root, NULL, &stat_fops); if (!file) { debugfs_remove(f2fs_debugfs_root); f2fs_debugfs_root = NULL; + return -ENOMEM; } + + return 0; } void f2fs_destroy_root_stats(void) diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index 60972a559685..4436079dbf0c 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -17,8 +17,8 @@ static unsigned long dir_blocks(struct inode *inode) { - return ((unsigned long long) (i_size_read(inode) + PAGE_CACHE_SIZE - 1)) - >> PAGE_CACHE_SHIFT; + return ((unsigned long long) (i_size_read(inode) + PAGE_SIZE - 1)) + >> PAGE_SHIFT; } static unsigned int dir_buckets(unsigned int level, int dir_level) @@ -37,7 +37,7 @@ static unsigned int bucket_blocks(unsigned int level) return 4; } -unsigned char f2fs_filetype_table[F2FS_FT_MAX] = { +static unsigned char f2fs_filetype_table[F2FS_FT_MAX] = { [F2FS_FT_UNKNOWN] = DT_UNKNOWN, [F2FS_FT_REG_FILE] = DT_REG, [F2FS_FT_DIR] = DT_DIR, @@ -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) { @@ -77,7 +83,7 @@ static unsigned long dir_block_index(unsigned int level, } static struct f2fs_dir_entry *find_in_block(struct page *dentry_page, - struct f2fs_filename *fname, + struct fscrypt_name *fname, f2fs_hash_t namehash, int *max_slots, struct page **res_page) @@ -95,23 +101,18 @@ static struct f2fs_dir_entry *find_in_block(struct page *dentry_page, else kunmap(dentry_page); - /* - * For the most part, it should be a bug when name_len is zero. - * We stop here for figuring out where the bugs has occurred. - */ - f2fs_bug_on(F2FS_P_SB(dentry_page), d.max < 0); return de; } -struct f2fs_dir_entry *find_target_dentry(struct f2fs_filename *fname, +struct f2fs_dir_entry *find_target_dentry(struct fscrypt_name *fname, f2fs_hash_t namehash, int *max_slots, struct f2fs_dentry_ptr *d) { struct f2fs_dir_entry *de; unsigned long bit_pos = 0; int max_len = 0; - struct f2fs_str de_name = FSTR_INIT(NULL, 0); - struct f2fs_str *name = &fname->disk_name; + struct fscrypt_str de_name = FSTR_INIT(NULL, 0); + struct fscrypt_str *name = &fname->disk_name; if (max_slots) *max_slots = 0; @@ -124,37 +125,28 @@ struct f2fs_dir_entry *find_target_dentry(struct f2fs_filename *fname, de = &d->dentry[bit_pos]; - if (de->hash_code != namehash) - goto not_match; + if (unlikely(!de->name_len)) { + bit_pos++; + continue; + } + /* encrypted case */ de_name.name = d->filename[bit_pos]; de_name.len = le16_to_cpu(de->name_len); -#ifdef CONFIG_F2FS_FS_ENCRYPTION - if (unlikely(!name->name)) { - if (fname->usr_fname->name[0] == '_') { - if (de_name.len > 32 && - !memcmp(de_name.name + ((de_name.len - 17) & ~15), - fname->crypto_buf.name + 8, 16)) - goto found; - goto not_match; - } - name->name = fname->crypto_buf.name; - name->len = fname->crypto_buf.len; - } -#endif - if (de_name.len == name->len && - !memcmp(de_name.name, name->name, name->len)) + /* show encrypted name */ + if (fname->hash) { + if (de->hash_code == cpu_to_le32(fname->hash)) + goto found; + } else if (de_name.len == name->len && + de->hash_code == namehash && + !memcmp(de_name.name, name->name, name->len)) goto found; -not_match: + if (max_slots && max_len > *max_slots) *max_slots = max_len; max_len = 0; - /* remain bug on condition */ - if (unlikely(!de->name_len)) - d->max = -1; - bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len)); } @@ -167,7 +159,7 @@ found: static struct f2fs_dir_entry *find_in_level(struct inode *dir, unsigned int level, - struct f2fs_filename *fname, + struct fscrypt_name *fname, struct page **res_page) { struct qstr name = FSTR_TO_QSTR(&fname->disk_name); @@ -180,9 +172,10 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir, int max_slots; f2fs_hash_t namehash; - namehash = f2fs_dentry_hash(&name, fname); - - f2fs_bug_on(F2FS_I_SB(dir), level > MAX_DIR_HASH_DEPTH); + if(fname->hash) + namehash = cpu_to_le32(fname->hash); + else + namehash = f2fs_dentry_hash(&name); nbucket = dir_buckets(level, F2FS_I(dir)->i_dir_level); nblock = bucket_blocks(level); @@ -195,8 +188,13 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir, /* no need to allocate new dentry pages to all the indices */ dentry_page = find_data_page(dir, bidx); if (IS_ERR(dentry_page)) { - room = true; - continue; + if (PTR_ERR(dentry_page) == -ENOENT) { + room = true; + continue; + } else { + *res_page = dentry_page; + break; + } } de = find_in_block(dentry_page, fname, namehash, &max_slots, @@ -217,79 +215,87 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir, return de; } -/* - * Find an entry in the specified directory with the wanted name. - * It returns the page where the entry was found (as a parameter - res_page), - * and the entry itself. Page is returned mapped and unlocked. - * Entry is guaranteed to be valid. - */ -struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir, - struct qstr *child, struct page **res_page) +struct f2fs_dir_entry *__f2fs_find_entry(struct inode *dir, + struct fscrypt_name *fname, struct page **res_page) { unsigned long npages = dir_blocks(dir); struct f2fs_dir_entry *de = NULL; unsigned int max_depth; unsigned int level; - struct f2fs_filename fname; - int err; - - *res_page = NULL; - - err = f2fs_fname_setup_filename(dir, child, 1, &fname); - if (err) - return NULL; if (f2fs_has_inline_dentry(dir)) { - de = find_in_inline_dir(dir, &fname, res_page); + *res_page = NULL; + de = find_in_inline_dir(dir, fname, res_page); goto out; } - if (npages == 0) + if (npages == 0) { + *res_page = NULL; goto out; + } max_depth = F2FS_I(dir)->i_current_depth; + if (unlikely(max_depth > MAX_DIR_HASH_DEPTH)) { + f2fs_msg(F2FS_I_SB(dir)->sb, KERN_WARNING, + "Corrupted max_depth of %lu: %u", + dir->i_ino, max_depth); + max_depth = MAX_DIR_HASH_DEPTH; + f2fs_i_depth_write(dir, max_depth); + } for (level = 0; level < max_depth; level++) { - de = find_in_level(dir, level, &fname, res_page); - if (de) + *res_page = NULL; + de = find_in_level(dir, level, fname, res_page); + if (de || IS_ERR(*res_page)) break; } out: - f2fs_fname_free_filename(&fname); return de; } -struct f2fs_dir_entry *f2fs_parent_dir(struct inode *dir, struct page **p) +/* + * Find an entry in the specified directory with the wanted name. + * It returns the page where the entry was found (as a parameter - res_page), + * and the entry itself. Page is returned mapped and unlocked. + * Entry is guaranteed to be valid. + */ +struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir, + const struct qstr *child, struct page **res_page) { - struct page *page; - struct f2fs_dir_entry *de; - struct f2fs_dentry_block *dentry_blk; - - if (f2fs_has_inline_dentry(dir)) - return f2fs_parent_inline_dir(dir, p); + struct f2fs_dir_entry *de = NULL; + struct fscrypt_name fname; + int err; - page = get_lock_data_page(dir, 0, false); - if (IS_ERR(page)) + err = fscrypt_setup_filename(dir, child, 1, &fname); + if (err) { + *res_page = ERR_PTR(err); return NULL; + } + + de = __f2fs_find_entry(dir, &fname, res_page); - dentry_blk = kmap(page); - de = &dentry_blk->dentry[1]; - *p = page; - unlock_page(page); + fscrypt_free_filename(&fname); return de; } -ino_t f2fs_inode_by_name(struct inode *dir, struct qstr *qstr) +struct f2fs_dir_entry *f2fs_parent_dir(struct inode *dir, struct page **p) +{ + struct qstr dotdot = QSTR_INIT("..", 2); + + return f2fs_find_entry(dir, &dotdot, p); +} + +ino_t f2fs_inode_by_name(struct inode *dir, const struct qstr *qstr, + struct page **page) { ino_t res = 0; struct f2fs_dir_entry *de; - struct page *page; - de = f2fs_find_entry(dir, qstr, &page); + de = f2fs_find_entry(dir, qstr, page); if (de) { res = le32_to_cpu(de->ino); - f2fs_dentry_kunmap(dir, page); - f2fs_put_page(page, 0); + f2fs_dentry_kunmap(dir, *page); + f2fs_put_page(*page, 0); } return res; @@ -300,14 +306,14 @@ void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de, { enum page_type type = f2fs_has_inline_dentry(dir) ? NODE : DATA; lock_page(page); - f2fs_wait_on_page_writeback(page, type); + f2fs_wait_on_page_writeback(page, type, true); de->ino = cpu_to_le32(inode->i_ino); set_de_type(de, inode->i_mode); f2fs_dentry_kunmap(dir, page); set_page_dirty(page); - dir->i_mtime = dir->i_ctime = CURRENT_TIME; - mark_inode_dirty(dir); + dir->i_mtime = dir->i_ctime = current_time(dir); + f2fs_mark_inode_dirty_sync(dir, false); f2fs_put_page(page, 1); } @@ -315,7 +321,7 @@ static void init_dent_inode(const struct qstr *name, struct page *ipage) { struct f2fs_inode *ri; - f2fs_wait_on_page_writeback(ipage, NODE); + f2fs_wait_on_page_writeback(ipage, NODE, true); /* copy name info. to this inode page */ ri = F2FS_INODE(ipage); @@ -345,24 +351,14 @@ int update_dent_inode(struct inode *inode, struct inode *to, void do_make_empty_dir(struct inode *inode, struct inode *parent, struct f2fs_dentry_ptr *d) { - struct f2fs_dir_entry *de; + struct qstr dot = QSTR_INIT(".", 1); + struct qstr dotdot = QSTR_INIT("..", 2); - de = &d->dentry[0]; - de->name_len = cpu_to_le16(1); - de->hash_code = 0; - de->ino = cpu_to_le32(inode->i_ino); - memcpy(d->filename[0], ".", 1); - set_de_type(de, inode->i_mode); + /* update dirent of "." */ + f2fs_update_dentry(inode->i_ino, inode->i_mode, d, &dot, 0, 0); - de = &d->dentry[1]; - de->hash_code = 0; - de->name_len = cpu_to_le16(2); - de->ino = cpu_to_le32(parent->i_ino); - memcpy(d->filename[1], "..", 2); - set_de_type(de, parent->i_mode); - - test_and_set_bit_le(0, (void *)d->bitmap); - test_and_set_bit_le(1, (void *)d->bitmap); + /* update dirent of ".." */ + f2fs_update_dentry(parent->i_ino, parent->i_mode, d, &dotdot, 0, 1); } static int make_empty_dir(struct inode *inode, @@ -392,32 +388,38 @@ static int make_empty_dir(struct inode *inode, } struct page *init_inode_metadata(struct inode *inode, struct inode *dir, - const struct qstr *name, struct page *dpage) + const struct qstr *new_name, const struct qstr *orig_name, + struct page *dpage) { struct page *page; int err; - if (is_inode_flag_set(F2FS_I(inode), FI_NEW_INODE)) { + if (is_inode_flag_set(inode, FI_NEW_INODE)) { page = new_inode_page(inode); if (IS_ERR(page)) return page; if (S_ISDIR(inode->i_mode)) { + /* in order to handle error case */ + get_page(page); err = make_empty_dir(inode, dir, page); - if (err) - goto error; + if (err) { + lock_page(page); + goto put_error; + } + put_page(page); } err = f2fs_init_acl(inode, dir, page, dpage); if (err) goto put_error; - err = f2fs_init_security(inode, dir, name, page); + err = f2fs_init_security(inode, dir, orig_name, page); if (err) goto put_error; if (f2fs_encrypted_inode(dir) && f2fs_may_encrypt(inode)) { - err = f2fs_inherit_context(dir, inode, page); + err = fscrypt_inherit_context(dir, inode, page, false); if (err) goto put_error; } @@ -429,14 +431,14 @@ struct page *init_inode_metadata(struct inode *inode, struct inode *dir, set_cold_node(inode, page); } - if (name) - init_dent_inode(name, page); + if (new_name) + init_dent_inode(new_name, page); /* * This file should be checkpointed during fsync. * We lost i_pino from now on. */ - if (is_inode_flag_set(F2FS_I(inode), FI_INC_LINK)) { + if (is_inode_flag_set(inode, FI_INC_LINK)) { file_lost_pino(inode); /* * If link the tmpfile to alias through linkat path, @@ -444,41 +446,33 @@ struct page *init_inode_metadata(struct inode *inode, struct inode *dir, */ if (inode->i_nlink == 0) remove_orphan_inode(F2FS_I_SB(dir), inode->i_ino); - inc_nlink(inode); + f2fs_i_links_write(inode, true); } return page; put_error: + clear_nlink(inode); + update_inode(inode, page); f2fs_put_page(page, 1); -error: - /* once the failed inode becomes a bad inode, i_mode is S_IFREG */ - truncate_inode_pages(&inode->i_data, 0); - truncate_blocks(inode, 0, false); - remove_dirty_dir_inode(inode); - remove_inode_page(inode); return ERR_PTR(err); } void update_parent_metadata(struct inode *dir, struct inode *inode, unsigned int current_depth) { - if (inode && is_inode_flag_set(F2FS_I(inode), FI_NEW_INODE)) { - if (S_ISDIR(inode->i_mode)) { - inc_nlink(dir); - set_inode_flag(F2FS_I(dir), FI_UPDATE_DIR); - } - clear_inode_flag(F2FS_I(inode), FI_NEW_INODE); + if (inode && is_inode_flag_set(inode, FI_NEW_INODE)) { + if (S_ISDIR(inode->i_mode)) + f2fs_i_links_write(dir, true); + clear_inode_flag(inode, FI_NEW_INODE); } - dir->i_mtime = dir->i_ctime = CURRENT_TIME; - mark_inode_dirty(dir); + dir->i_mtime = dir->i_ctime = current_time(dir); + f2fs_mark_inode_dirty_sync(dir, false); - if (F2FS_I(dir)->i_current_depth != current_depth) { - F2FS_I(dir)->i_current_depth = current_depth; - set_inode_flag(F2FS_I(dir), FI_UPDATE_DIR); - } + if (F2FS_I(dir)->i_current_depth != current_depth) + f2fs_i_depth_write(dir, current_depth); - if (inode && is_inode_flag_set(F2FS_I(inode), FI_INC_LINK)) - clear_inode_flag(F2FS_I(inode), FI_INC_LINK); + if (inode && is_inode_flag_set(inode, FI_INC_LINK)) + clear_inode_flag(inode, FI_INC_LINK); } int room_for_filename(const void *bitmap, int slots, int max_slots) @@ -515,15 +509,16 @@ void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *d, memcpy(d->filename[bit_pos], name->name, name->len); de->ino = cpu_to_le32(ino); set_de_type(de, mode); - for (i = 0; i < slots; i++) - test_and_set_bit_le(bit_pos + i, (void *)d->bitmap); + for (i = 0; i < slots; i++) { + __set_bit_le(bit_pos + i, (void *)d->bitmap); + /* avoid wrong garbage data for readdir */ + if (i) + (de + i)->name_len = 0; + } } -/* - * 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, + const struct qstr *orig_name, struct inode *inode, nid_t ino, umode_t mode) { unsigned int bit_pos; @@ -536,28 +531,11 @@ 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); current_depth = F2FS_I(dir)->i_current_depth; if (F2FS_I(dir)->chash == dentry_hash) { @@ -566,10 +544,12 @@ int __f2fs_add_link(struct inode *dir, const struct qstr *name, } start: - if (unlikely(current_depth == MAX_DIR_HASH_DEPTH)) { - err = -ENOSPC; - goto out; - } +#ifdef CONFIG_F2FS_FAULT_INJECTION + if (time_to_inject(F2FS_I_SB(dir), FAULT_DIR_DEPTH)) + return -ENOSPC; +#endif + if (unlikely(current_depth == MAX_DIR_HASH_DEPTH)) + return -ENOSPC; /* Increase the depth, if required */ if (level == current_depth) @@ -583,10 +563,8 @@ 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, @@ -602,11 +580,12 @@ start: ++level; goto start; add_dentry: - f2fs_wait_on_page_writeback(dentry_page, DATA); + f2fs_wait_on_page_writeback(dentry_page, DATA, true); 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, + orig_name, NULL); if (IS_ERR(page)) { err = PTR_ERR(page); goto fail; @@ -616,14 +595,12 @@ 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); if (inode) { - /* we don't need to mark_inode_dirty now */ - F2FS_I(inode)->i_pino = dir->i_ino; - update_inode(inode, page); + f2fs_i_pino_write(inode, dir->i_ino); f2fs_put_page(page, 1); } @@ -632,14 +609,49 @@ fail: if (inode) up_write(&F2FS_I(inode)->i_sem); - if (is_inode_flag_set(F2FS_I(dir), FI_UPDATE_DIR)) { - update_inode_page(dir); - clear_inode_flag(F2FS_I(dir), FI_UPDATE_DIR); - } kunmap(dentry_page); f2fs_put_page(dentry_page, 1); -out: - f2fs_fname_free_filename(&fname); + + return err; +} + +int __f2fs_do_add_link(struct inode *dir, struct fscrypt_name *fname, + struct inode *inode, nid_t ino, umode_t mode) +{ + struct qstr new_name; + int err = -EAGAIN; + + 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, fname->usr_fname, + inode, ino, mode); + if (err == -EAGAIN) + err = f2fs_add_regular_entry(dir, &new_name, fname->usr_fname, + inode, ino, mode); + + f2fs_update_time(F2FS_I_SB(dir), REQ_TIME); + 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 fscrypt_name fname; + int err; + + err = fscrypt_setup_filename(dir, name, 0, &fname); + if (err) + return err; + + err = __f2fs_do_add_link(dir, &fname, inode, ino, mode); + + fscrypt_free_filename(&fname); return err; } @@ -649,46 +661,39 @@ int f2fs_do_tmpfile(struct inode *inode, struct inode *dir) int err = 0; down_write(&F2FS_I(inode)->i_sem); - page = init_inode_metadata(inode, dir, NULL, NULL); + page = init_inode_metadata(inode, dir, NULL, NULL, NULL); if (IS_ERR(page)) { err = PTR_ERR(page); goto fail; } - /* we don't need to mark_inode_dirty now */ - update_inode(inode, page); f2fs_put_page(page, 1); - clear_inode_flag(F2FS_I(inode), FI_NEW_INODE); + clear_inode_flag(inode, FI_NEW_INODE); fail: up_write(&F2FS_I(inode)->i_sem); + f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); return err; } -void f2fs_drop_nlink(struct inode *dir, struct inode *inode, struct page *page) +void f2fs_drop_nlink(struct inode *dir, struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(dir); down_write(&F2FS_I(inode)->i_sem); - if (S_ISDIR(inode->i_mode)) { - drop_nlink(dir); - if (page) - update_inode(dir, page); - else - update_inode_page(dir); - } - inode->i_ctime = CURRENT_TIME; + if (S_ISDIR(inode->i_mode)) + f2fs_i_links_write(dir, false); + inode->i_ctime = current_time(inode); - drop_nlink(inode); + f2fs_i_links_write(inode, false); if (S_ISDIR(inode->i_mode)) { - drop_nlink(inode); - i_size_write(inode, 0); + f2fs_i_links_write(inode, false); + f2fs_i_size_write(inode, 0); } up_write(&F2FS_I(inode)->i_sem); - update_inode_page(inode); if (inode->i_nlink == 0) - add_orphan_inode(sbi, inode->i_ino); + add_orphan_inode(inode); else release_orphan_inode(sbi); } @@ -705,11 +710,13 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page, int slots = GET_DENTRY_SLOTS(le16_to_cpu(dentry->name_len)); int i; + f2fs_update_time(F2FS_I_SB(dir), REQ_TIME); + if (f2fs_has_inline_dentry(dir)) return f2fs_delete_inline_entry(dentry, page, dir, inode); lock_page(page); - f2fs_wait_on_page_writeback(page, DATA); + f2fs_wait_on_page_writeback(page, DATA, true); dentry_blk = page_address(page); bit_pos = dentry - dentry_blk->dentry; @@ -723,10 +730,11 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page, kunmap(page); /* kunmap - pair of f2fs_find_entry */ set_page_dirty(page); - dir->i_ctime = dir->i_mtime = CURRENT_TIME; + dir->i_ctime = dir->i_mtime = current_time(dir); + f2fs_mark_inode_dirty_sync(dir, false); if (inode) - f2fs_drop_nlink(dir, inode, NULL); + f2fs_drop_nlink(dir, inode); if (bit_pos == NR_DENTRY_IN_BLOCK && !truncate_hole(dir, page->index, page->index + 1)) { @@ -734,6 +742,7 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page, ClearPagePrivate(page); ClearPageUptodate(page); inode_dec_dirty_pages(dir); + remove_dirty_inode(dir); } f2fs_put_page(page, 1); } @@ -776,13 +785,13 @@ bool f2fs_empty_dir(struct inode *dir) return true; } -bool f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d, - unsigned int start_pos, struct f2fs_str *fstr) +int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d, + unsigned int start_pos, struct fscrypt_str *fstr) { unsigned char d_type = DT_UNKNOWN; unsigned int bit_pos; struct f2fs_dir_entry *de = NULL; - struct f2fs_str de_name = FSTR_INIT(NULL, 0); + struct fscrypt_str de_name = FSTR_INIT(NULL, 0); bit_pos = ((unsigned long)ctx->pos % d->max); @@ -792,29 +801,26 @@ 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; + if (de->name_len == 0) { + bit_pos++; + ctx->pos = start_pos + bit_pos; + continue; + } + + d_type = get_de_type(de); de_name.name = d->filename[bit_pos]; de_name.len = le16_to_cpu(de->name_len); if (f2fs_encrypted_inode(d->inode)) { int save_len = fstr->len; - int ret; + int err; - de_name.name = kmalloc(de_name.len, GFP_NOFS); - if (!de_name.name) - return false; - - memcpy(de_name.name, d->filename[bit_pos], de_name.len); - - ret = f2fs_fname_disk_to_usr(d->inode, &de->hash_code, - &de_name, fstr); - kfree(de_name.name); - if (ret < 0) - return true; + err = fscrypt_fname_disk_to_usr(d->inode, + (u32)de->hash_code, 0, + &de_name, fstr); + if (err) + return err; de_name = *fstr; fstr->len = save_len; @@ -822,12 +828,12 @@ bool f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d, if (!dir_emit(ctx, de_name.name, de_name.len, le32_to_cpu(de->ino), d_type)) - return true; + return 1; bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len)); ctx->pos = start_pos + bit_pos; } - return false; + return 0; } static int f2fs_readdir(struct file *file, struct dir_context *ctx) @@ -839,16 +845,15 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx) struct file_ra_state *ra = &file->f_ra; unsigned int n = ((unsigned long)ctx->pos / NR_DENTRY_IN_BLOCK); struct f2fs_dentry_ptr d; - struct f2fs_str fstr = FSTR_INIT(NULL, 0); + struct fscrypt_str fstr = FSTR_INIT(NULL, 0); int err = 0; if (f2fs_encrypted_inode(inode)) { - err = f2fs_get_encryption_info(inode); - if (err) + err = fscrypt_get_encryption_info(inode); + if (err && err != -ENOKEY) return err; - err = f2fs_fname_crypto_alloc_buffer(inode, F2FS_NAME_LEN, - &fstr); + err = fscrypt_fname_alloc_buffer(inode, F2FS_NAME_LEN, &fstr); if (err < 0) return err; } @@ -865,29 +870,42 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx) for (; n < npages; n++) { dentry_page = get_lock_data_page(inode, n, false); - if (IS_ERR(dentry_page)) - continue; + if (IS_ERR(dentry_page)) { + err = PTR_ERR(dentry_page); + if (err == -ENOENT) { + err = 0; + continue; + } else { + goto out; + } + } dentry_blk = kmap(dentry_page); make_dentry_ptr(inode, &d, (void *)dentry_blk, 1); - if (f2fs_fill_dentries(ctx, &d, n * NR_DENTRY_IN_BLOCK, &fstr)) - goto stop; + err = f2fs_fill_dentries(ctx, &d, + n * NR_DENTRY_IN_BLOCK, &fstr); + if (err) { + kunmap(dentry_page); + f2fs_put_page(dentry_page, 1); + break; + } ctx->pos = (n + 1) * NR_DENTRY_IN_BLOCK; kunmap(dentry_page); f2fs_put_page(dentry_page, 1); - dentry_page = NULL; - } -stop: - if (dentry_page && !IS_ERR(dentry_page)) { - kunmap(dentry_page); - f2fs_put_page(dentry_page, 1); } out: - f2fs_fname_crypto_free_buffer(&fstr); - return err; + fscrypt_fname_free_buffer(&fstr); + return err < 0 ? err : 0; +} + +static int f2fs_dir_open(struct inode *inode, struct file *filp) +{ + if (f2fs_encrypted_inode(inode)) + return fscrypt_get_encryption_info(inode) ? -EACCES : 0; + return 0; } const struct file_operations f2fs_dir_operations = { @@ -895,6 +913,7 @@ const struct file_operations f2fs_dir_operations = { .read = generic_read_dir, .iterate = f2fs_readdir, .fsync = f2fs_sync_file, + .open = f2fs_dir_open, .unlocked_ioctl = f2fs_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = f2fs_compat_ioctl, diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c index 7ddba812e11b..4db44da7ef69 100644 --- a/fs/f2fs/extent_cache.c +++ b/fs/f2fs/extent_cache.c @@ -33,10 +33,11 @@ static struct extent_node *__attach_extent_node(struct f2fs_sb_info *sbi, en->ei = *ei; INIT_LIST_HEAD(&en->list); + en->et = et; rb_link_node(&en->rb_node, parent, p); rb_insert_color(&en->rb_node, &et->root); - et->count++; + atomic_inc(&et->node_cnt); atomic_inc(&sbi->total_ext_node); return en; } @@ -45,11 +46,29 @@ static void __detach_extent_node(struct f2fs_sb_info *sbi, struct extent_tree *et, struct extent_node *en) { rb_erase(&en->rb_node, &et->root); - et->count--; + atomic_dec(&et->node_cnt); atomic_dec(&sbi->total_ext_node); if (et->cached_en == en) et->cached_en = NULL; + kmem_cache_free(extent_node_slab, en); +} + +/* + * Flow to release an extent_node: + * 1. list_del_init + * 2. __detach_extent_node + * 3. kmem_cache_free. + */ +static void __release_extent_node(struct f2fs_sb_info *sbi, + struct extent_tree *et, struct extent_node *en) +{ + spin_lock(&sbi->extent_lock); + f2fs_bug_on(sbi, list_empty(&en->list)); + list_del_init(&en->list); + spin_unlock(&sbi->extent_lock); + + __detach_extent_node(sbi, et, en); } static struct extent_tree *__grab_extent_tree(struct inode *inode) @@ -68,11 +87,13 @@ static struct extent_tree *__grab_extent_tree(struct inode *inode) et->root = RB_ROOT; et->cached_en = NULL; rwlock_init(&et->lock); - atomic_set(&et->refcount, 0); - et->count = 0; - sbi->total_ext_tree++; + INIT_LIST_HEAD(&et->list); + atomic_set(&et->node_cnt, 0); + atomic_inc(&sbi->total_ext_tree); + } else { + atomic_dec(&sbi->total_zombie_tree); + list_del_init(&et->list); } - atomic_inc(&et->refcount); up_write(&sbi->extent_tree_lock); /* never died until evict_inode */ @@ -127,32 +148,21 @@ static struct extent_node *__init_extent_tree(struct f2fs_sb_info *sbi, } static unsigned int __free_extent_tree(struct f2fs_sb_info *sbi, - struct extent_tree *et, bool free_all) + struct extent_tree *et) { struct rb_node *node, *next; struct extent_node *en; - unsigned int count = et->count; + unsigned int count = atomic_read(&et->node_cnt); node = rb_first(&et->root); while (node) { next = rb_next(node); en = rb_entry(node, struct extent_node, rb_node); - - if (free_all) { - spin_lock(&sbi->extent_lock); - if (!list_empty(&en->list)) - list_del_init(&en->list); - spin_unlock(&sbi->extent_lock); - } - - if (free_all || list_empty(&en->list)) { - __detach_extent_node(sbi, et, en); - kmem_cache_free(extent_node_slab, en); - } + __release_extent_node(sbi, et, en); node = next; } - return count - et->count; + return count - atomic_read(&et->node_cnt); } static void __drop_largest_extent(struct inode *inode, @@ -160,38 +170,38 @@ static void __drop_largest_extent(struct inode *inode, { struct extent_info *largest = &F2FS_I(inode)->extent_tree->largest; - if (fofs < largest->fofs + largest->len && fofs + len > largest->fofs) + if (fofs < largest->fofs + largest->len && fofs + len > largest->fofs) { largest->len = 0; + f2fs_mark_inode_dirty_sync(inode, true); + } } -void f2fs_drop_largest_extent(struct inode *inode, pgoff_t fofs) -{ - if (!f2fs_may_extent_tree(inode)) - return; - - __drop_largest_extent(inode, fofs, 1); -} - -void f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext) +/* return true, if inode page is changed */ +bool f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct extent_tree *et; struct extent_node *en; struct extent_info ei; - if (!f2fs_may_extent_tree(inode)) - return; + if (!f2fs_may_extent_tree(inode)) { + /* drop largest extent */ + if (i_ext && i_ext->len) { + i_ext->len = 0; + return true; + } + return false; + } et = __grab_extent_tree(inode); - if (!i_ext || le32_to_cpu(i_ext->len) < F2FS_MIN_EXTENT_LEN) - return; + if (!i_ext || !i_ext->len) + return false; - set_extent_info(&ei, le32_to_cpu(i_ext->fofs), - le32_to_cpu(i_ext->blk), le32_to_cpu(i_ext->len)); + get_extent_info(&ei, i_ext); write_lock(&et->lock); - if (et->count) + if (atomic_read(&et->node_cnt)) goto out; en = __init_extent_tree(sbi, et, &ei); @@ -202,6 +212,7 @@ void f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext) } out: write_unlock(&et->lock); + return false; } static bool f2fs_lookup_extent_tree(struct inode *inode, pgoff_t pgofs, @@ -230,9 +241,10 @@ static bool f2fs_lookup_extent_tree(struct inode *inode, pgoff_t pgofs, if (en) { *ei = en->ei; spin_lock(&sbi->extent_lock); - if (!list_empty(&en->list)) + if (!list_empty(&en->list)) { list_move_tail(&en->list, &sbi->extent_list); - et->cached_en = en; + et->cached_en = en; + } spin_unlock(&sbi->extent_lock); ret = true; } @@ -325,12 +337,12 @@ lookup_neighbors: return en; } -static struct extent_node *__try_merge_extent_node(struct f2fs_sb_info *sbi, +static struct extent_node *__try_merge_extent_node(struct inode *inode, struct extent_tree *et, struct extent_info *ei, - struct extent_node **den, struct extent_node *prev_ex, struct extent_node *next_ex) { + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct extent_node *en = NULL; if (prev_ex && __is_back_mergeable(ei, &prev_ex->ei)) { @@ -340,28 +352,34 @@ static struct extent_node *__try_merge_extent_node(struct f2fs_sb_info *sbi, } if (next_ex && __is_front_mergeable(ei, &next_ex->ei)) { - if (en) { - __detach_extent_node(sbi, et, prev_ex); - *den = prev_ex; - } + if (en) + __release_extent_node(sbi, et, prev_ex); next_ex->ei.fofs = ei->fofs; next_ex->ei.blk = ei->blk; next_ex->ei.len += ei->len; en = next_ex; } - if (en) { - __try_update_largest_extent(et, en); + if (!en) + return NULL; + + __try_update_largest_extent(inode, et, en); + + spin_lock(&sbi->extent_lock); + if (!list_empty(&en->list)) { + list_move_tail(&en->list, &sbi->extent_list); et->cached_en = en; } + spin_unlock(&sbi->extent_lock); return en; } -static struct extent_node *__insert_extent_tree(struct f2fs_sb_info *sbi, +static struct extent_node *__insert_extent_tree(struct inode *inode, struct extent_tree *et, struct extent_info *ei, struct rb_node **insert_p, struct rb_node *insert_parent) { + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct rb_node **p = &et->root.rb_node; struct rb_node *parent = NULL; struct extent_node *en = NULL; @@ -388,8 +406,13 @@ do_insert: if (!en) return NULL; - __try_update_largest_extent(et, en); + __try_update_largest_extent(inode, et, en); + + /* update in global extent list */ + spin_lock(&sbi->extent_lock); + list_add_tail(&en->list, &sbi->extent_list); et->cached_en = en; + spin_unlock(&sbi->extent_lock); return en; } @@ -412,7 +435,7 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode, write_lock(&et->lock); - if (is_inode_flag_set(F2FS_I(inode), FI_NO_EXTENT)) { + if (is_inode_flag_set(inode, FI_NO_EXTENT)) { write_unlock(&et->lock); return false; } @@ -454,7 +477,7 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode, set_extent_info(&ei, end, end - dei.fofs + dei.blk, org_end - end); - en1 = __insert_extent_tree(sbi, et, &ei, + en1 = __insert_extent_tree(inode, et, &ei, NULL, NULL); next_en = en1; } else { @@ -475,9 +498,9 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode, } if (parts) - __try_update_largest_extent(et, en); + __try_update_largest_extent(inode, et, en); else - __detach_extent_node(sbi, et, en); + __release_extent_node(sbi, et, en); /* * if original extent is split into zero or two parts, extent @@ -488,58 +511,28 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode, insert_p = NULL; insert_parent = NULL; } - - /* update in global extent list */ - spin_lock(&sbi->extent_lock); - if (!parts && !list_empty(&en->list)) - list_del(&en->list); - if (en1) - list_add_tail(&en1->list, &sbi->extent_list); - spin_unlock(&sbi->extent_lock); - - /* release extent node */ - if (!parts) - kmem_cache_free(extent_node_slab, en); - en = next_en; } /* 3. update extent in extent cache */ if (blkaddr) { - struct extent_node *den = NULL; set_extent_info(&ei, fofs, blkaddr, len); - en1 = __try_merge_extent_node(sbi, et, &ei, &den, - prev_en, next_en); - if (!en1) - en1 = __insert_extent_tree(sbi, et, &ei, + if (!__try_merge_extent_node(inode, et, &ei, prev_en, next_en)) + __insert_extent_tree(inode, et, &ei, insert_p, insert_parent); /* give up extent_cache, if split and small updates happen */ if (dei.len >= 1 && prev.len < F2FS_MIN_EXTENT_LEN && et->largest.len < F2FS_MIN_EXTENT_LEN) { - et->largest.len = 0; - set_inode_flag(F2FS_I(inode), FI_NO_EXTENT); - } - - spin_lock(&sbi->extent_lock); - if (en1) { - if (list_empty(&en1->list)) - list_add_tail(&en1->list, &sbi->extent_list); - else - list_move_tail(&en1->list, &sbi->extent_list); + __drop_largest_extent(inode, 0, UINT_MAX); + set_inode_flag(inode, FI_NO_EXTENT); } - if (den && !list_empty(&den->list)) - list_del(&den->list); - spin_unlock(&sbi->extent_lock); - - if (den) - kmem_cache_free(extent_node_slab, den); } - if (is_inode_flag_set(F2FS_I(inode), FI_NO_EXTENT)) - __free_extent_tree(sbi, et, true); + if (is_inode_flag_set(inode, FI_NO_EXTENT)) + __free_extent_tree(sbi, et); write_unlock(&et->lock); @@ -548,46 +541,42 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode, unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink) { - struct extent_tree *treevec[EXT_TREE_VEC_SIZE]; - struct extent_node *en, *tmp; - unsigned long ino = F2FS_ROOT_INO(sbi); - struct radix_tree_root *root = &sbi->extent_tree_root; - unsigned int found; + struct extent_tree *et, *next; + struct extent_node *en; unsigned int node_cnt = 0, tree_cnt = 0; int remained; if (!test_opt(sbi, EXTENT_CACHE)) return 0; + if (!atomic_read(&sbi->total_zombie_tree)) + goto free_node; + if (!down_write_trylock(&sbi->extent_tree_lock)) goto out; /* 1. remove unreferenced extent tree */ - while ((found = radix_tree_gang_lookup(root, - (void **)treevec, ino, EXT_TREE_VEC_SIZE))) { - unsigned i; - - ino = treevec[found - 1]->ino + 1; - for (i = 0; i < found; i++) { - struct extent_tree *et = treevec[i]; - - if (!atomic_read(&et->refcount)) { - write_lock(&et->lock); - node_cnt += __free_extent_tree(sbi, et, true); - write_unlock(&et->lock); - - radix_tree_delete(root, et->ino); - kmem_cache_free(extent_tree_slab, et); - sbi->total_ext_tree--; - tree_cnt++; - - if (node_cnt + tree_cnt >= nr_shrink) - goto unlock_out; - } + list_for_each_entry_safe(et, next, &sbi->zombie_list, list) { + if (atomic_read(&et->node_cnt)) { + write_lock(&et->lock); + node_cnt += __free_extent_tree(sbi, et); + write_unlock(&et->lock); } + f2fs_bug_on(sbi, atomic_read(&et->node_cnt)); + list_del_init(&et->list); + radix_tree_delete(&sbi->extent_tree_root, et->ino); + kmem_cache_free(extent_tree_slab, et); + atomic_dec(&sbi->total_ext_tree); + atomic_dec(&sbi->total_zombie_tree); + tree_cnt++; + + if (node_cnt + tree_cnt >= nr_shrink) + goto unlock_out; + cond_resched(); } up_write(&sbi->extent_tree_lock); +free_node: /* 2. remove LRU extent entries */ if (!down_write_trylock(&sbi->extent_tree_lock)) goto out; @@ -595,34 +584,29 @@ unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink) remained = nr_shrink - (node_cnt + tree_cnt); spin_lock(&sbi->extent_lock); - list_for_each_entry_safe(en, tmp, &sbi->extent_list, list) { - if (!remained--) + for (; remained > 0; remained--) { + if (list_empty(&sbi->extent_list)) break; - list_del_init(&en->list); - } - spin_unlock(&sbi->extent_lock); - - /* - * reset ino for searching victims from beginning of global extent tree. - */ - ino = F2FS_ROOT_INO(sbi); - - while ((found = radix_tree_gang_lookup(root, - (void **)treevec, ino, EXT_TREE_VEC_SIZE))) { - unsigned i; + en = list_first_entry(&sbi->extent_list, + struct extent_node, list); + et = en->et; + if (!write_trylock(&et->lock)) { + /* refresh this extent node's position in extent list */ + list_move_tail(&en->list, &sbi->extent_list); + continue; + } - ino = treevec[found - 1]->ino + 1; - for (i = 0; i < found; i++) { - struct extent_tree *et = treevec[i]; + list_del_init(&en->list); + spin_unlock(&sbi->extent_lock); - write_lock(&et->lock); - node_cnt += __free_extent_tree(sbi, et, false); - write_unlock(&et->lock); + __detach_extent_node(sbi, et, en); - if (node_cnt + tree_cnt >= nr_shrink) - goto unlock_out; - } + write_unlock(&et->lock); + node_cnt++; + spin_lock(&sbi->extent_lock); } + spin_unlock(&sbi->extent_lock); + unlock_out: up_write(&sbi->extent_tree_lock); out: @@ -637,16 +621,29 @@ unsigned int f2fs_destroy_extent_node(struct inode *inode) struct extent_tree *et = F2FS_I(inode)->extent_tree; unsigned int node_cnt = 0; - if (!et) + if (!et || !atomic_read(&et->node_cnt)) return 0; write_lock(&et->lock); - node_cnt = __free_extent_tree(sbi, et, true); + node_cnt = __free_extent_tree(sbi, et); write_unlock(&et->lock); return node_cnt; } +void f2fs_drop_extent_tree(struct inode *inode) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct extent_tree *et = F2FS_I(inode)->extent_tree; + + set_inode_flag(inode, FI_NO_EXTENT); + + write_lock(&et->lock); + __free_extent_tree(sbi, et); + __drop_largest_extent(inode, 0, UINT_MAX); + write_unlock(&et->lock); +} + void f2fs_destroy_extent_tree(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); @@ -656,8 +653,12 @@ void f2fs_destroy_extent_tree(struct inode *inode) if (!et) return; - if (inode->i_nlink && !is_bad_inode(inode) && et->count) { - atomic_dec(&et->refcount); + if (inode->i_nlink && !is_bad_inode(inode) && + atomic_read(&et->node_cnt)) { + down_write(&sbi->extent_tree_lock); + list_add_tail(&et->list, &sbi->zombie_list); + atomic_inc(&sbi->total_zombie_tree); + up_write(&sbi->extent_tree_lock); return; } @@ -666,11 +667,10 @@ void f2fs_destroy_extent_tree(struct inode *inode) /* delete extent tree entry in radix tree */ down_write(&sbi->extent_tree_lock); - atomic_dec(&et->refcount); - f2fs_bug_on(sbi, atomic_read(&et->refcount) || et->count); + f2fs_bug_on(sbi, atomic_read(&et->node_cnt)); radix_tree_delete(&sbi->extent_tree_root, inode->i_ino); kmem_cache_free(extent_tree_slab, et); - sbi->total_ext_tree--; + atomic_dec(&sbi->total_ext_tree); up_write(&sbi->extent_tree_lock); F2FS_I(inode)->extent_tree = NULL; @@ -689,20 +689,20 @@ bool f2fs_lookup_extent_cache(struct inode *inode, pgoff_t pgofs, void f2fs_update_extent_cache(struct dnode_of_data *dn) { - struct f2fs_inode_info *fi = F2FS_I(dn->inode); pgoff_t fofs; + block_t blkaddr; if (!f2fs_may_extent_tree(dn->inode)) return; - f2fs_bug_on(F2FS_I_SB(dn->inode), dn->data_blkaddr == NEW_ADDR); - - - fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) + - dn->ofs_in_node; + if (dn->data_blkaddr == NEW_ADDR) + blkaddr = NULL_ADDR; + else + blkaddr = dn->data_blkaddr; - if (f2fs_update_extent_tree_range(dn->inode, fofs, dn->data_blkaddr, 1)) - sync_inode_page(dn); + fofs = start_bidx_of_node(ofs_of_node(dn->node_page), dn->inode) + + dn->ofs_in_node; + f2fs_update_extent_tree_range(dn->inode, fofs, blkaddr, 1); } void f2fs_update_extent_cache_range(struct dnode_of_data *dn, @@ -712,8 +712,7 @@ void f2fs_update_extent_cache_range(struct dnode_of_data *dn, if (!f2fs_may_extent_tree(dn->inode)) return; - if (f2fs_update_extent_tree_range(dn->inode, fofs, blkaddr, len)) - sync_inode_page(dn); + f2fs_update_extent_tree_range(dn->inode, fofs, blkaddr, len); } void init_extent_cache_info(struct f2fs_sb_info *sbi) @@ -722,7 +721,9 @@ void init_extent_cache_info(struct f2fs_sb_info *sbi) init_rwsem(&sbi->extent_tree_lock); INIT_LIST_HEAD(&sbi->extent_list); spin_lock_init(&sbi->extent_lock); - sbi->total_ext_tree = 0; + atomic_set(&sbi->total_ext_tree, 0); + INIT_LIST_HEAD(&sbi->zombie_list); + atomic_set(&sbi->total_zombie_tree, 0); atomic_set(&sbi->total_ext_node, 0); } diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 9dfbfe6dc775..eb01a0329e90 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -21,10 +21,12 @@ #include <linux/sched.h> #include <linux/vmalloc.h> #include <linux/bio.h> +#include <linux/blkdev.h> +#include <linux/fscrypto.h> +#include <crypto/hash.h> #ifdef CONFIG_F2FS_CHECK_FS #define f2fs_bug_on(sbi, condition) BUG_ON(condition) -#define f2fs_down_write(x, y) down_write_nest_lock(x, y) #else #define f2fs_bug_on(sbi, condition) \ do { \ @@ -33,7 +35,30 @@ set_sbi_flag(sbi, SBI_NEED_FSCK); \ } \ } while (0) -#define f2fs_down_write(x, y) down_write(x) +#endif + +#ifdef CONFIG_F2FS_FAULT_INJECTION +enum { + FAULT_KMALLOC, + FAULT_PAGE_ALLOC, + FAULT_ALLOC_NID, + FAULT_ORPHAN, + FAULT_BLOCK, + FAULT_DIR_DEPTH, + FAULT_EVICT_INODE, + FAULT_IO, + FAULT_CHECKPOINT, + FAULT_MAX, +}; + +struct f2fs_fault_info { + atomic_t inject_ops; + unsigned int inject_rate; + unsigned int inject_type; +}; + +extern char *fault_name[FAULT_MAX]; +#define IS_FAULT_SET(fi, type) (fi->inject_type & (1 << (type))) #endif /* @@ -54,6 +79,10 @@ #define F2FS_MOUNT_FASTBOOT 0x00001000 #define F2FS_MOUNT_EXTENT_CACHE 0x00002000 #define F2FS_MOUNT_FORCE_FG_GC 0x00004000 +#define F2FS_MOUNT_DATA_FLUSH 0x00008000 +#define F2FS_MOUNT_FAULT_INJECTION 0x00010000 +#define F2FS_MOUNT_ADAPTIVE 0x00020000 +#define F2FS_MOUNT_LFS 0x00040000 #define clear_opt(sbi, option) (sbi->mount_opt.opt &= ~F2FS_MOUNT_##option) #define set_opt(sbi, option) (sbi->mount_opt.opt |= F2FS_MOUNT_##option) @@ -74,6 +103,7 @@ struct f2fs_mount_info { }; #define F2FS_FEATURE_ENCRYPT 0x0001 +#define F2FS_FEATURE_BLKZONED 0x0002 #define F2FS_HAS_FEATURE(sb, mask) \ ((F2FS_SB(sb)->raw_super->feature & cpu_to_le32(mask)) != 0) @@ -82,25 +112,52 @@ struct f2fs_mount_info { #define F2FS_CLEAR_FEATURE(sb, mask) \ F2FS_SB(sb)->raw_super->feature &= ~cpu_to_le32(mask) -#define CRCPOLY_LE 0xedb88320 - -static inline __u32 f2fs_crc32(void *buf, size_t len) +/** + * wq_has_sleeper - check if there are any waiting processes + * @wq: wait queue head + * + * Returns true if wq has waiting processes + * + * Please refer to the comment for waitqueue_active. + */ +static inline bool wq_has_sleeper(wait_queue_head_t *wq) { - unsigned char *p = (unsigned char *)buf; - __u32 crc = F2FS_SUPER_MAGIC; - int i; + /* + * We need to be sure we are in sync with the + * add_wait_queue modifications to the wait queue. + * + * This memory barrier should be paired with one on the + * waiting side. + */ + smp_mb(); + return waitqueue_active(wq); +} - while (len--) { - crc ^= *p++; - for (i = 0; i < 8; i++) - crc = (crc >> 1) ^ ((crc & 1) ? CRCPOLY_LE : 0); - } - return crc; +static inline void inode_nohighmem(struct inode *inode) +{ + mapping_set_gfp_mask(inode->i_mapping, GFP_USER); } -static inline bool f2fs_crc_valid(__u32 blk_crc, void *buf, size_t buf_size) +/** + * current_time - Return FS time + * @inode: inode. + * + * Return the current time truncated to the time granularity supported by + * the fs. + * + * Note that inode and inode->sb cannot be NULL. + * Otherwise, the function warns and returns time without truncation. + */ +static inline struct timespec current_time(struct inode *inode) { - return f2fs_crc32(buf, buf_size) == blk_crc; + struct timespec now = current_kernel_time(); + + if (unlikely(!inode->i_sb)) { + WARN(1, "current_time() called with uninitialized super_block in the inode"); + return now; + } + + return timespec_trunc(now, inode->i_sb->s_time_gran); } /* @@ -119,12 +176,13 @@ enum { CP_DISCARD, }; -#define DEF_BATCHED_TRIM_SECTIONS 32 +#define DEF_BATCHED_TRIM_SECTIONS 2 #define BATCHED_TRIM_SEGMENTS(sbi) \ (SM_I(sbi)->trim_sections * (sbi)->segs_per_sec) #define BATCHED_TRIM_BLOCKS(sbi) \ (BATCHED_TRIM_SEGMENTS(sbi) << (sbi)->log_blocks_per_seg) #define DEF_CP_INTERVAL 60 /* 60 secs */ +#define DEF_IDLE_INTERVAL 5 /* 5 secs */ struct cp_control { int reason; @@ -158,13 +216,7 @@ struct ino_entry { nid_t ino; /* inode number */ }; -/* - * for the list of directory inodes or gc inodes. - * NOTE: there are two slab users for this structure, if we add/modify/delete - * fields in structure for one of slab users, it may affect fields or size of - * other one, in this condition, it's better to split both of slab and related - * data structure. - */ +/* for the list of inodes to be GCed */ struct inode_entry { struct list_head list; /* list head */ struct inode *inode; /* vfs inode pointer */ @@ -177,46 +229,52 @@ struct discard_entry { int len; /* # of consecutive blocks of the discard */ }; +struct bio_entry { + struct list_head list; + struct bio *bio; + struct completion event; + int error; +}; + /* for the list of fsync inodes, used only during recovery */ struct fsync_inode_entry { struct list_head list; /* list head */ struct inode *inode; /* vfs inode pointer */ block_t blkaddr; /* block address locating the last fsync */ block_t last_dentry; /* block address locating the last dentry */ - block_t last_inode; /* block address locating the last inode */ }; -#define nats_in_cursum(sum) (le16_to_cpu(sum->n_nats)) -#define sits_in_cursum(sum) (le16_to_cpu(sum->n_sits)) +#define nats_in_cursum(jnl) (le16_to_cpu(jnl->n_nats)) +#define sits_in_cursum(jnl) (le16_to_cpu(jnl->n_sits)) -#define nat_in_journal(sum, i) (sum->nat_j.entries[i].ne) -#define nid_in_journal(sum, i) (sum->nat_j.entries[i].nid) -#define sit_in_journal(sum, i) (sum->sit_j.entries[i].se) -#define segno_in_journal(sum, i) (sum->sit_j.entries[i].segno) +#define nat_in_journal(jnl, i) (jnl->nat_j.entries[i].ne) +#define nid_in_journal(jnl, i) (jnl->nat_j.entries[i].nid) +#define sit_in_journal(jnl, i) (jnl->sit_j.entries[i].se) +#define segno_in_journal(jnl, i) (jnl->sit_j.entries[i].segno) -#define MAX_NAT_JENTRIES(sum) (NAT_JOURNAL_ENTRIES - nats_in_cursum(sum)) -#define MAX_SIT_JENTRIES(sum) (SIT_JOURNAL_ENTRIES - sits_in_cursum(sum)) +#define MAX_NAT_JENTRIES(jnl) (NAT_JOURNAL_ENTRIES - nats_in_cursum(jnl)) +#define MAX_SIT_JENTRIES(jnl) (SIT_JOURNAL_ENTRIES - sits_in_cursum(jnl)) -static inline int update_nats_in_cursum(struct f2fs_summary_block *rs, int i) +static inline int update_nats_in_cursum(struct f2fs_journal *journal, int i) { - int before = nats_in_cursum(rs); - rs->n_nats = cpu_to_le16(before + i); + int before = nats_in_cursum(journal); + journal->n_nats = cpu_to_le16(before + i); return before; } -static inline int update_sits_in_cursum(struct f2fs_summary_block *rs, int i) +static inline int update_sits_in_cursum(struct f2fs_journal *journal, int i) { - int before = sits_in_cursum(rs); - rs->n_sits = cpu_to_le16(before + i); + int before = sits_in_cursum(journal); + journal->n_sits = cpu_to_le16(before + i); return before; } -static inline bool __has_cursum_space(struct f2fs_summary_block *sum, int size, - int type) +static inline bool __has_cursum_space(struct f2fs_journal *journal, + int size, int type) { if (type == NAT_JOURNAL) - return size <= MAX_NAT_JENTRIES(sum); - return size <= MAX_SIT_JENTRIES(sum); + return size <= MAX_NAT_JENTRIES(journal); + return size <= MAX_SIT_JENTRIES(journal); } /* @@ -234,13 +292,13 @@ static inline bool __has_cursum_space(struct f2fs_summary_block *sum, int size, #define F2FS_IOC_ABORT_VOLATILE_WRITE _IO(F2FS_IOCTL_MAGIC, 5) #define F2FS_IOC_GARBAGE_COLLECT _IO(F2FS_IOCTL_MAGIC, 6) #define F2FS_IOC_WRITE_CHECKPOINT _IO(F2FS_IOCTL_MAGIC, 7) +#define F2FS_IOC_DEFRAGMENT _IO(F2FS_IOCTL_MAGIC, 8) +#define F2FS_IOC_MOVE_RANGE _IOWR(F2FS_IOCTL_MAGIC, 9, \ + struct f2fs_move_range) -#define F2FS_IOC_SET_ENCRYPTION_POLICY \ - _IOR('f', 19, struct f2fs_encryption_policy) -#define F2FS_IOC_GET_ENCRYPTION_PWSALT \ - _IOW('f', 20, __u8[16]) -#define F2FS_IOC_GET_ENCRYPTION_POLICY \ - _IOW('f', 21, struct f2fs_encryption_policy) +#define F2FS_IOC_SET_ENCRYPTION_POLICY FS_IOC_SET_ENCRYPTION_POLICY +#define F2FS_IOC_GET_ENCRYPTION_POLICY FS_IOC_GET_ENCRYPTION_POLICY +#define F2FS_IOC_GET_ENCRYPTION_PWSALT FS_IOC_GET_ENCRYPTION_PWSALT /* * should be same as XFS_IOC_GOINGDOWN. @@ -256,33 +314,27 @@ static inline bool __has_cursum_space(struct f2fs_summary_block *sum, int size, /* * ioctl commands in 32 bit emulation */ -#define F2FS_IOC32_GETFLAGS FS_IOC32_GETFLAGS -#define F2FS_IOC32_SETFLAGS FS_IOC32_SETFLAGS +#define F2FS_IOC32_GETFLAGS FS_IOC32_GETFLAGS +#define F2FS_IOC32_SETFLAGS FS_IOC32_SETFLAGS +#define F2FS_IOC32_GETVERSION FS_IOC32_GETVERSION #endif -/* - * For INODE and NODE manager - */ -/* for directory operations */ -struct f2fs_str { - unsigned char *name; - u32 len; +struct f2fs_defragment { + u64 start; + u64 len; }; -struct f2fs_filename { - const struct qstr *usr_fname; - struct f2fs_str disk_name; - f2fs_hash_t hash; -#ifdef CONFIG_F2FS_FS_ENCRYPTION - struct f2fs_str crypto_buf; -#endif +struct f2fs_move_range { + u32 dst_fd; /* destination fd */ + u64 pos_in; /* start position in src_fd */ + u64 pos_out; /* start position in dst_fd */ + u64 len; /* size to move */ }; -#define FSTR_INIT(n, l) { .name = n, .len = l } -#define FSTR_TO_QSTR(f) QSTR_INIT((f)->name, (f)->len) -#define fname_name(p) ((p)->disk_name.name) -#define fname_len(p) ((p)->disk_name.len) - +/* + * For INODE and NODE manager + */ +/* for directory operations */ struct f2fs_dentry_ptr { struct inode *inode; const void *bitmap; @@ -350,6 +402,7 @@ struct extent_node { struct rb_node rb_node; /* rb node located in rb-tree */ struct list_head list; /* node in global extent list of sbi */ struct extent_info ei; /* extent info */ + struct extent_tree *et; /* extent tree pointer */ }; struct extent_tree { @@ -357,9 +410,9 @@ struct extent_tree { struct rb_root root; /* root of extent info rb-tree */ struct extent_node *cached_en; /* recently accessed extent node */ struct extent_info largest; /* largested extent info */ + struct list_head list; /* to be used by sbi->zombie_list */ rwlock_t lock; /* protect extent info rb-tree */ - atomic_t refcount; /* reference count of rb-tree */ - unsigned int count; /* # of extent node in rb-tree*/ + atomic_t node_cnt; /* # of extent node in rb-tree*/ }; /* @@ -378,6 +431,7 @@ struct f2fs_map_blocks { block_t m_lblk; unsigned int m_len; unsigned int m_flags; + pgoff_t *m_next_pgofs; /* point next possible non-hole pgofs */ }; /* for flag in get_data_block */ @@ -385,6 +439,8 @@ struct f2fs_map_blocks { #define F2FS_GET_BLOCK_DIO 1 #define F2FS_GET_BLOCK_FIEMAP 2 #define F2FS_GET_BLOCK_BMAP 3 +#define F2FS_GET_BLOCK_PRE_DIO 4 +#define F2FS_GET_BLOCK_PRE_AIO 5 /* * i_advise uses FADVISE_XXX_BIT. We can add additional hints later. @@ -393,6 +449,7 @@ struct f2fs_map_blocks { #define FADVISE_LOST_PINO_BIT 0x02 #define FADVISE_ENCRYPT_BIT 0x04 #define FADVISE_ENC_NAME_BIT 0x08 +#define FADVISE_KEEP_SIZE_BIT 0x10 #define file_is_cold(inode) is_file(inode, FADVISE_COLD_BIT) #define file_wrong_pino(inode) is_file(inode, FADVISE_LOST_PINO_BIT) @@ -405,15 +462,8 @@ struct f2fs_map_blocks { #define file_clear_encrypt(inode) clear_file(inode, FADVISE_ENCRYPT_BIT) #define file_enc_name(inode) is_file(inode, FADVISE_ENC_NAME_BIT) #define file_set_enc_name(inode) set_file(inode, FADVISE_ENC_NAME_BIT) - -/* Encryption algorithms */ -#define F2FS_ENCRYPTION_MODE_INVALID 0 -#define F2FS_ENCRYPTION_MODE_AES_256_XTS 1 -#define F2FS_ENCRYPTION_MODE_AES_256_GCM 2 -#define F2FS_ENCRYPTION_MODE_AES_256_CBC 3 -#define F2FS_ENCRYPTION_MODE_AES_256_CTS 4 - -#include "f2fs_crypto.h" +#define file_keep_isize(inode) is_file(inode, FADVISE_KEEP_SIZE_BIT) +#define file_set_keep_isize(inode) set_file(inode, FADVISE_KEEP_SIZE_BIT) #define DEF_DIR_LEVEL 0 @@ -434,25 +484,22 @@ struct f2fs_inode_info { unsigned int clevel; /* maximum level of given file name */ nid_t i_xattr_nid; /* node id that contains xattrs */ unsigned long long xattr_ver; /* cp version of xattr modification */ - struct inode_entry *dirty_dir; /* the pointer of dirty dir */ + loff_t last_disk_size; /* lastly written file size */ + struct list_head dirty_list; /* dirty list for dirs and files */ + struct list_head gdirty_list; /* linked in global dirty list */ struct list_head inmem_pages; /* inmemory pages managed by f2fs */ struct mutex inmem_lock; /* lock for inmemory pages */ - struct extent_tree *extent_tree; /* cached extent_tree entry */ - -#ifdef CONFIG_F2FS_FS_ENCRYPTION - /* Encryption params */ - struct f2fs_crypt_info *i_crypt_info; -#endif + struct rw_semaphore dio_rwsem[2];/* avoid racing between dio and gc */ }; static inline void get_extent_info(struct extent_info *ext, - struct f2fs_extent i_ext) + struct f2fs_extent *i_ext) { - ext->fofs = le32_to_cpu(i_ext.fofs); - ext->blk = le32_to_cpu(i_ext.blk); - ext->len = le32_to_cpu(i_ext.len); + ext->fofs = le32_to_cpu(i_ext->fofs); + ext->blk = le32_to_cpu(i_ext->blk); + ext->len = le32_to_cpu(i_ext->len); } static inline void set_raw_extent(struct extent_info *ext, @@ -497,20 +544,30 @@ static inline bool __is_front_mergeable(struct extent_info *cur, return __is_extent_mergeable(cur, front); } -static inline void __try_update_largest_extent(struct extent_tree *et, - struct extent_node *en) +extern void f2fs_mark_inode_dirty_sync(struct inode *, bool); +static inline void __try_update_largest_extent(struct inode *inode, + struct extent_tree *et, struct extent_node *en) { - if (en->ei.len > et->largest.len) + if (en->ei.len > et->largest.len) { et->largest = en->ei; + f2fs_mark_inode_dirty_sync(inode, true); + } } +enum nid_list { + FREE_NID_LIST, + ALLOC_NID_LIST, + MAX_NID_LIST, +}; + struct f2fs_nm_info { block_t nat_blkaddr; /* base disk address of NAT */ nid_t max_nid; /* maximum possible node ids */ - nid_t available_nids; /* maximum available node ids */ + nid_t available_nids; /* # of available node ids */ nid_t next_scan_nid; /* the next nid to be scanned */ unsigned int ram_thresh; /* control the memory footprint */ unsigned int ra_nid_pages; /* # of nid pages to be readaheaded */ + unsigned int dirty_nats_ratio; /* control dirty nats ratio threshold */ /* NAT cache management */ struct radix_tree_root nat_root;/* root of the nat entry cache */ @@ -522,9 +579,9 @@ struct f2fs_nm_info { /* free node ids management */ struct radix_tree_root free_nid_root;/* root of the free_nid cache */ - struct list_head free_nid_list; /* a list for free nids */ - spinlock_t free_nid_list_lock; /* protect free nid list */ - unsigned int fcnt; /* the number of free node id */ + struct list_head nid_list[MAX_NID_LIST];/* lists for free nids */ + unsigned int nid_cnt[MAX_NID_LIST]; /* the number of free node id */ + spinlock_t nid_list_lock; /* protect nid lists ops */ struct mutex build_lock; /* lock for build free nids */ /* for checkpoint */ @@ -544,6 +601,9 @@ struct dnode_of_data { nid_t nid; /* node id of the direct node block */ unsigned int ofs_in_node; /* data offset in the node page */ bool inode_page_locked; /* inode page is locked or not */ + bool node_changed; /* is node block changed */ + char cur_level; /* level of hole node page */ + char max_level; /* level of current page located */ block_t data_blkaddr; /* block address of the node block */ }; @@ -582,7 +642,6 @@ enum { CURSEG_WARM_NODE, /* direct node blocks of normal files */ CURSEG_COLD_NODE, /* indirect node blocks */ NO_CHECK_TYPE, - CURSEG_DIRECT_IO, /* to use for the direct IO path */ }; struct flush_cmd { @@ -594,6 +653,7 @@ struct flush_cmd { struct flush_cmd_control { struct task_struct *f2fs_issue_flush; /* flush thread */ wait_queue_head_t flush_wait_queue; /* waiting queue for wake-up */ + atomic_t submit_flush; /* # of issued flushes */ struct llist_head issue_list; /* list for command issue */ struct llist_node *dispatch_list; /* list for command dispatch */ }; @@ -618,6 +678,7 @@ struct f2fs_sm_info { /* for small discard management */ struct list_head discard_list; /* 4KB discard list */ + struct list_head wait_list; /* linked with issued discard bio */ int nr_discards; /* # of discards in the list */ int max_discards; /* max. discards to be issued */ @@ -644,12 +705,16 @@ struct f2fs_sm_info { * f2fs monitors the number of several block types such as on-writeback, * dirty dentry blocks, dirty node blocks, and dirty meta blocks. */ +#define WB_DATA_TYPE(p) (__is_cp_guaranteed(p) ? F2FS_WB_CP_DATA : F2FS_WB_DATA) enum count_type { - F2FS_WRITEBACK, F2FS_DIRTY_DENTS, + F2FS_DIRTY_DATA, F2FS_DIRTY_NODES, F2FS_DIRTY_META, F2FS_INMEM_PAGES, + F2FS_DIRTY_IMETA, + F2FS_WB_CP_DATA, + F2FS_WB_DATA, NR_COUNT_TYPE, }; @@ -673,6 +738,7 @@ enum page_type { META_FLUSH, INMEM, /* the below types are used by tracepoints only. */ INMEM_DROP, + INMEM_REVOKE, IPU, OPU, }; @@ -681,7 +747,8 @@ struct f2fs_io_info { struct f2fs_sb_info *sbi; /* f2fs_sb_info pointer */ enum page_type type; /* contains DATA/NODE/META/META_FLUSH */ int rw; /* contains R/RS/W/WS with REQ_META/REQ_PRIO */ - block_t blk_addr; /* block address to be written */ + block_t new_blkaddr; /* new block address to be written */ + block_t old_blkaddr; /* old block address before Cow */ struct page *page; /* page to be written */ struct page *encrypted_page; /* encrypted page */ }; @@ -695,6 +762,27 @@ struct f2fs_bio_info { struct rw_semaphore io_rwsem; /* blocking op for bio */ }; +#define FDEV(i) (sbi->devs[i]) +#define RDEV(i) (raw_super->devs[i]) +struct f2fs_dev_info { + struct block_device *bdev; + char path[MAX_PATH_LEN]; + unsigned int total_segments; + block_t start_blk; + block_t end_blk; +#ifdef CONFIG_BLK_DEV_ZONED + unsigned int nr_blkz; /* Total number of zones */ + u8 *blkz_type; /* Array of zones type */ +#endif +}; + +enum inode_type { + DIR_INODE, /* for dirty dir inode */ + FILE_INODE, /* for dirty regular/symlink inode */ + DIRTY_META, /* for all dirtied inode metadata */ + NR_INODE_TYPE, +}; + /* for inner inode cache management */ struct inode_management { struct radix_tree_root ino_root; /* ino entry array */ @@ -709,14 +797,36 @@ enum { SBI_IS_CLOSE, /* specify unmounting */ SBI_NEED_FSCK, /* need fsck.f2fs to fix */ SBI_POR_DOING, /* recovery is doing or not */ + SBI_NEED_SB_WRITE, /* need to recover superblock */ + SBI_NEED_CP, /* need to checkpoint */ }; +enum { + CP_TIME, + REQ_TIME, + MAX_TIME, +}; + +#ifdef CONFIG_F2FS_FS_ENCRYPTION +#define F2FS_KEY_DESC_PREFIX "f2fs:" +#define F2FS_KEY_DESC_PREFIX_SIZE 5 +#endif struct f2fs_sb_info { struct super_block *sb; /* pointer to VFS super block */ struct proc_dir_entry *s_proc; /* proc entry */ - struct buffer_head *raw_super_buf; /* buffer head of raw sb */ struct f2fs_super_block *raw_super; /* raw super block pointer */ - int s_flag; /* flags for sbi */ + int valid_super_block; /* valid super block no */ + unsigned long s_flag; /* flags for sbi */ + +#ifdef CONFIG_F2FS_FS_ENCRYPTION + u8 key_prefix[F2FS_KEY_DESC_PREFIX_SIZE]; + u8 key_prefix_size; +#endif + +#ifdef CONFIG_BLK_DEV_ZONED + unsigned int blocks_per_blkz; /* F2FS blocks per zone */ + unsigned int log_blocks_per_blkz; /* log2 F2FS blocks per zone */ +#endif /* for node-related operations */ struct f2fs_nm_info *nm_info; /* node manager */ @@ -728,32 +838,37 @@ struct f2fs_sb_info { /* for bio operations */ struct f2fs_bio_info read_io; /* for read bios */ struct f2fs_bio_info write_io[NR_PAGE_TYPE]; /* for write bios */ + struct mutex wio_mutex[NODE + 1]; /* bio ordering for NODE/DATA */ /* for checkpoint */ struct f2fs_checkpoint *ckpt; /* raw checkpoint pointer */ + int cur_cp_pack; /* remain current cp pack */ + spinlock_t cp_lock; /* for flag in ckpt */ struct inode *meta_inode; /* cache meta blocks */ struct mutex cp_mutex; /* checkpoint procedure lock */ struct rw_semaphore cp_rwsem; /* blocking FS operations */ struct rw_semaphore node_write; /* locking node writes */ - struct mutex writepages; /* mutex for writepages() */ wait_queue_head_t cp_wait; - long cp_expires, cp_interval; /* next expected periodic cp */ + unsigned long last_time[MAX_TIME]; /* to store time in jiffies */ + long interval_time[MAX_TIME]; /* to store thresholds */ struct inode_management im[MAX_INO_ENTRY]; /* manage inode cache */ /* for orphan inode, use 0'th array */ unsigned int max_orphans; /* max orphan inodes */ - /* for directory inode management */ - struct list_head dir_inode_list; /* dir inode list */ - spinlock_t dir_inode_lock; /* for dir inode list lock */ + /* for inode management */ + struct list_head inode_list[NR_INODE_TYPE]; /* dirty inode list */ + spinlock_t inode_lock[NR_INODE_TYPE]; /* for dirty inode list lock */ /* for extent tree cache */ struct radix_tree_root extent_tree_root;/* cache extent cache entries */ struct rw_semaphore extent_tree_lock; /* locking extent radix tree */ struct list_head extent_list; /* lru list for shrinker */ spinlock_t extent_lock; /* locking extent lru list */ - int total_ext_tree; /* extent tree count */ + atomic_t total_ext_tree; /* extent tree count */ + struct list_head zombie_list; /* extent zombie tree list */ + atomic_t total_zombie_tree; /* extent zombie tree count */ atomic_t total_ext_node; /* extent info count */ /* basic filesystem units */ @@ -770,17 +885,23 @@ struct f2fs_sb_info { unsigned int total_sections; /* total section count */ unsigned int total_node_count; /* total node block count */ unsigned int total_valid_node_count; /* valid node block count */ - unsigned int total_valid_inode_count; /* valid inode count */ + loff_t max_file_blocks; /* max block index of file */ int active_logs; /* # of active logs */ int dir_level; /* directory level */ block_t user_block_count; /* # of user blocks */ block_t total_valid_block_count; /* # of valid blocks */ - block_t alloc_valid_block_count; /* # of allocated blocks */ block_t discard_blks; /* discard command candidats */ block_t last_valid_block_count; /* for recovery */ u32 s_next_generation; /* for NFS support */ - atomic_t nr_pages[NR_COUNT_TYPE]; /* # of pages, see count_type */ + + /* # of pages, see count_type */ + atomic_t nr_pages[NR_COUNT_TYPE]; + /* # of allocated blocks */ + struct percpu_counter alloc_valid_block_count; + + /* valid inode count */ + struct percpu_counter total_valid_inode_count; struct f2fs_mount_info mount_opt; /* mount options */ @@ -809,7 +930,7 @@ struct f2fs_sb_info { atomic_t inline_inode; /* # of inline_data inodes */ atomic_t inline_dir; /* # of inline_dentry inodes */ int bg_gc; /* background gc calls */ - unsigned int n_dirty_dirs; /* # of dir inodes */ + unsigned int ndirty_inode[NR_INODE_TYPE]; /* # of dirty inodes */ #endif unsigned int last_victim[2]; /* last victim segment # */ spinlock_t stat_lock; /* lock for stat operations */ @@ -820,13 +941,106 @@ struct f2fs_sb_info { /* For shrinker support */ struct list_head s_list; + int s_ndevs; /* number of devices */ + struct f2fs_dev_info *devs; /* for device list */ struct mutex umount_mutex; unsigned int shrinker_run_no; + + /* For write statistics */ + u64 sectors_written_start; + u64 kbytes_written; + + /* Reference to checksum algorithm driver via cryptoapi */ + struct crypto_shash *s_chksum_driver; + + /* For fault injection */ +#ifdef CONFIG_F2FS_FAULT_INJECTION + struct f2fs_fault_info fault_info; +#endif }; +#ifdef CONFIG_F2FS_FAULT_INJECTION +static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type) +{ + struct f2fs_fault_info *ffi = &sbi->fault_info; + + if (!ffi->inject_rate) + return false; + + if (!IS_FAULT_SET(ffi, type)) + return false; + + atomic_inc(&ffi->inject_ops); + if (atomic_read(&ffi->inject_ops) >= ffi->inject_rate) { + atomic_set(&ffi->inject_ops, 0); + printk("%sF2FS-fs : inject %s in %pF\n", + KERN_INFO, + fault_name[type], + __builtin_return_address(0)); + return true; + } + return false; +} +#endif + +/* For write statistics. Suppose sector size is 512 bytes, + * and the return value is in kbytes. s is of struct f2fs_sb_info. + */ +#define BD_PART_WRITTEN(s) \ +(((u64)part_stat_read(s->sb->s_bdev->bd_part, sectors[1]) - \ + s->sectors_written_start) >> 1) + +static inline void f2fs_update_time(struct f2fs_sb_info *sbi, int type) +{ + sbi->last_time[type] = jiffies; +} + +static inline bool f2fs_time_over(struct f2fs_sb_info *sbi, int type) +{ + struct timespec ts = {sbi->interval_time[type], 0}; + unsigned long interval = timespec_to_jiffies(&ts); + + return time_after(jiffies, sbi->last_time[type] + interval); +} + +static inline bool is_idle(struct f2fs_sb_info *sbi) +{ + struct block_device *bdev = sbi->sb->s_bdev; + struct request_queue *q = bdev_get_queue(bdev); + struct request_list *rl = &q->root_rl; + + if (rl->count[BLK_RW_SYNC] || rl->count[BLK_RW_ASYNC]) + return 0; + + return f2fs_time_over(sbi, REQ_TIME); +} + /* * Inline functions */ +static inline u32 f2fs_crc32(struct f2fs_sb_info *sbi, const void *address, + unsigned int length) +{ + SHASH_DESC_ON_STACK(shash, sbi->s_chksum_driver); + u32 *ctx = (u32 *)shash_desc_ctx(shash); + int err; + + shash->tfm = sbi->s_chksum_driver; + shash->flags = 0; + *ctx = F2FS_SUPER_MAGIC; + + err = crypto_shash_update(shash, address, length); + BUG_ON(err); + + return *ctx; +} + +static inline bool f2fs_crc_valid(struct f2fs_sb_info *sbi, __u32 blk_crc, + void *buf, size_t buf_size) +{ + return f2fs_crc32(sbi, buf, buf_size) == blk_crc; +} + static inline struct f2fs_inode_info *F2FS_I(struct inode *inode) { return container_of(inode, struct f2fs_inode_info, vfs_inode); @@ -909,17 +1123,17 @@ static inline struct address_space *NODE_MAPPING(struct f2fs_sb_info *sbi) static inline bool is_sbi_flag_set(struct f2fs_sb_info *sbi, unsigned int type) { - return sbi->s_flag & (0x01 << type); + return test_bit(type, &sbi->s_flag); } static inline void set_sbi_flag(struct f2fs_sb_info *sbi, unsigned int type) { - sbi->s_flag |= (0x01 << type); + set_bit(type, &sbi->s_flag); } static inline void clear_sbi_flag(struct f2fs_sb_info *sbi, unsigned int type) { - sbi->s_flag &= ~(0x01 << type); + clear_bit(type, &sbi->s_flag); } static inline unsigned long long cur_cp_version(struct f2fs_checkpoint *cp) @@ -927,26 +1141,50 @@ static inline unsigned long long cur_cp_version(struct f2fs_checkpoint *cp) return le64_to_cpu(cp->checkpoint_ver); } -static inline bool is_set_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f) +static inline bool __is_set_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f) { unsigned int ckpt_flags = le32_to_cpu(cp->ckpt_flags); + return ckpt_flags & f; } -static inline void set_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f) +static inline bool is_set_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f) { - unsigned int ckpt_flags = le32_to_cpu(cp->ckpt_flags); + return __is_set_ckpt_flags(F2FS_CKPT(sbi), f); +} + +static inline void __set_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f) +{ + unsigned int ckpt_flags; + + ckpt_flags = le32_to_cpu(cp->ckpt_flags); ckpt_flags |= f; cp->ckpt_flags = cpu_to_le32(ckpt_flags); } -static inline void clear_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f) +static inline void set_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f) { - unsigned int ckpt_flags = le32_to_cpu(cp->ckpt_flags); + spin_lock(&sbi->cp_lock); + __set_ckpt_flags(F2FS_CKPT(sbi), f); + spin_unlock(&sbi->cp_lock); +} + +static inline void __clear_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f) +{ + unsigned int ckpt_flags; + + ckpt_flags = le32_to_cpu(cp->ckpt_flags); ckpt_flags &= (~f); cp->ckpt_flags = cpu_to_le32(ckpt_flags); } +static inline void clear_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f) +{ + spin_lock(&sbi->cp_lock); + __clear_ckpt_flags(F2FS_CKPT(sbi), f); + spin_unlock(&sbi->cp_lock); +} + static inline void f2fs_lock_op(struct f2fs_sb_info *sbi) { down_read(&sbi->cp_rwsem); @@ -959,7 +1197,7 @@ static inline void f2fs_unlock_op(struct f2fs_sb_info *sbi) static inline void f2fs_lock_all(struct f2fs_sb_info *sbi) { - f2fs_down_write(&sbi->cp_rwsem, &sbi->cp_mutex); + down_write(&sbi->cp_rwsem); } static inline void f2fs_unlock_all(struct f2fs_sb_info *sbi) @@ -985,8 +1223,8 @@ static inline bool __remain_node_summaries(int reason) static inline bool __exist_node_summaries(struct f2fs_sb_info *sbi) { - return (is_set_ckpt_flags(F2FS_CKPT(sbi), CP_UMOUNT_FLAG) || - is_set_ckpt_flags(F2FS_CKPT(sbi), CP_FASTBOOT_FLAG)); + return (is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG) || + is_set_ckpt_flags(sbi, CP_FASTBOOT_FLAG)); } /* @@ -1019,22 +1257,37 @@ static inline bool f2fs_has_xattr_block(unsigned int ofs) return ofs == XATTR_NODE_OFFSET; } +static inline void f2fs_i_blocks_write(struct inode *, blkcnt_t, bool); static inline bool inc_valid_block_count(struct f2fs_sb_info *sbi, - struct inode *inode, blkcnt_t count) + struct inode *inode, blkcnt_t *count) { - block_t valid_block_count; + blkcnt_t diff; - spin_lock(&sbi->stat_lock); - valid_block_count = - sbi->total_valid_block_count + (block_t)count; - if (unlikely(valid_block_count > sbi->user_block_count)) { - spin_unlock(&sbi->stat_lock); +#ifdef CONFIG_F2FS_FAULT_INJECTION + if (time_to_inject(sbi, FAULT_BLOCK)) return false; +#endif + /* + * let's increase this in prior to actual block count change in order + * for f2fs_sync_file to avoid data races when deciding checkpoint. + */ + percpu_counter_add(&sbi->alloc_valid_block_count, (*count)); + + spin_lock(&sbi->stat_lock); + sbi->total_valid_block_count += (block_t)(*count); + if (unlikely(sbi->total_valid_block_count > sbi->user_block_count)) { + diff = sbi->total_valid_block_count - sbi->user_block_count; + *count -= diff; + sbi->total_valid_block_count = sbi->user_block_count; + if (!*count) { + spin_unlock(&sbi->stat_lock); + percpu_counter_sub(&sbi->alloc_valid_block_count, diff); + return false; + } } - inode->i_blocks += count; - sbi->total_valid_block_count = valid_block_count; - sbi->alloc_valid_block_count += (block_t)count; spin_unlock(&sbi->stat_lock); + + f2fs_i_blocks_write(inode, *count, true); return true; } @@ -1045,22 +1298,27 @@ static inline void dec_valid_block_count(struct f2fs_sb_info *sbi, spin_lock(&sbi->stat_lock); f2fs_bug_on(sbi, sbi->total_valid_block_count < (block_t) count); f2fs_bug_on(sbi, inode->i_blocks < count); - inode->i_blocks -= count; sbi->total_valid_block_count -= (block_t)count; spin_unlock(&sbi->stat_lock); + f2fs_i_blocks_write(inode, count, false); } static inline void inc_page_count(struct f2fs_sb_info *sbi, int count_type) { atomic_inc(&sbi->nr_pages[count_type]); + + if (count_type == F2FS_DIRTY_DATA || count_type == F2FS_INMEM_PAGES || + count_type == F2FS_WB_CP_DATA || count_type == F2FS_WB_DATA) + return; + set_sbi_flag(sbi, SBI_IS_DIRTY); } static inline void inode_inc_dirty_pages(struct inode *inode) { atomic_inc(&F2FS_I(inode)->dirty_pages); - if (S_ISDIR(inode->i_mode)) - inc_page_count(F2FS_I_SB(inode), F2FS_DIRTY_DENTS); + inc_page_count(F2FS_I_SB(inode), S_ISDIR(inode->i_mode) ? + F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA); } static inline void dec_page_count(struct f2fs_sb_info *sbi, int count_type) @@ -1075,12 +1333,11 @@ static inline void inode_dec_dirty_pages(struct inode *inode) return; atomic_dec(&F2FS_I(inode)->dirty_pages); - - if (S_ISDIR(inode->i_mode)) - dec_page_count(F2FS_I_SB(inode), F2FS_DIRTY_DENTS); + dec_page_count(F2FS_I_SB(inode), S_ISDIR(inode->i_mode) ? + F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA); } -static inline int get_pages(struct f2fs_sb_info *sbi, int count_type) +static inline s64 get_pages(struct f2fs_sb_info *sbi, int count_type) { return atomic_read(&sbi->nr_pages[count_type]); } @@ -1092,10 +1349,11 @@ static inline int get_dirty_pages(struct inode *inode) static inline int get_blocktype_secs(struct f2fs_sb_info *sbi, int block_type) { - unsigned int pages_per_sec = sbi->segs_per_sec * - (1 << sbi->log_blocks_per_seg); - return ((get_pages(sbi, block_type) + pages_per_sec - 1) - >> sbi->log_blocks_per_seg) / sbi->segs_per_sec; + unsigned int pages_per_sec = sbi->segs_per_sec * sbi->blocks_per_seg; + unsigned int segs = (get_pages(sbi, block_type) + pages_per_sec - 1) >> + sbi->log_blocks_per_seg; + + return segs / sbi->segs_per_sec; } static inline block_t valid_user_blocks(struct f2fs_sb_info *sbi) @@ -1103,6 +1361,11 @@ static inline block_t valid_user_blocks(struct f2fs_sb_info *sbi) return sbi->total_valid_block_count; } +static inline block_t discard_blocks(struct f2fs_sb_info *sbi) +{ + return sbi->discard_blks; +} + static inline unsigned long __bitmap_size(struct f2fs_sb_info *sbi, int flag) { struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); @@ -1140,22 +1403,27 @@ 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); @@ -1182,13 +1450,13 @@ static inline bool inc_valid_node_count(struct f2fs_sb_info *sbi, } if (inode) - inode->i_blocks++; + f2fs_i_blocks_write(inode, 1, true); - sbi->alloc_valid_block_count++; sbi->total_valid_node_count++; sbi->total_valid_block_count++; spin_unlock(&sbi->stat_lock); + percpu_counter_inc(&sbi->alloc_valid_block_count); return true; } @@ -1201,7 +1469,7 @@ static inline void dec_valid_node_count(struct f2fs_sb_info *sbi, f2fs_bug_on(sbi, !sbi->total_valid_node_count); f2fs_bug_on(sbi, !inode->i_blocks); - inode->i_blocks--; + f2fs_i_blocks_write(inode, 1, false); sbi->total_valid_node_count--; sbi->total_valid_block_count--; @@ -1215,28 +1483,30 @@ static inline unsigned int valid_node_count(struct f2fs_sb_info *sbi) static inline void inc_valid_inode_count(struct f2fs_sb_info *sbi) { - spin_lock(&sbi->stat_lock); - f2fs_bug_on(sbi, sbi->total_valid_inode_count == sbi->total_node_count); - sbi->total_valid_inode_count++; - spin_unlock(&sbi->stat_lock); + percpu_counter_inc(&sbi->total_valid_inode_count); } static inline void dec_valid_inode_count(struct f2fs_sb_info *sbi) { - spin_lock(&sbi->stat_lock); - f2fs_bug_on(sbi, !sbi->total_valid_inode_count); - sbi->total_valid_inode_count--; - spin_unlock(&sbi->stat_lock); + percpu_counter_dec(&sbi->total_valid_inode_count); } -static inline unsigned int valid_inode_count(struct f2fs_sb_info *sbi) +static inline s64 valid_inode_count(struct f2fs_sb_info *sbi) { - return sbi->total_valid_inode_count; + return percpu_counter_sum_positive(&sbi->total_valid_inode_count); } static inline struct page *f2fs_grab_cache_page(struct address_space *mapping, pgoff_t index, bool for_write) { +#ifdef CONFIG_F2FS_FAULT_INJECTION + struct page *page = find_lock_page(mapping, index); + if (page) + return page; + + if (time_to_inject(F2FS_M_SB(mapping), FAULT_PAGE_ALLOC)) + return NULL; +#endif if (!for_write) return grab_cache_page(mapping, index); return grab_cache_page_write_begin(mapping, index, AOP_FLAG_NOFS); @@ -1261,7 +1531,7 @@ static inline void f2fs_put_page(struct page *page, int unlock) f2fs_bug_on(F2FS_P_SB(page), !PageLocked(page)); unlock_page(page); } - page_cache_release(page); + put_page(page); } static inline void f2fs_put_dnode(struct dnode_of_data *dn) @@ -1396,13 +1666,12 @@ static inline void f2fs_change_bit(unsigned int nr, char *addr) enum { FI_NEW_INODE, /* indicate newly allocated inode */ FI_DIRTY_INODE, /* indicate inode is dirty or not */ + FI_AUTO_RECOVER, /* indicate inode is recoverable */ FI_DIRTY_DIR, /* indicate directory has dirty pages */ FI_INC_LINK, /* need to increment i_nlink */ FI_ACL_MODE, /* indicate acl mode */ 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*/ @@ -1416,71 +1685,145 @@ enum { FI_DROP_CACHE, /* drop dirty page cache */ FI_DATA_EXIST, /* indicate data exists */ FI_INLINE_DOTS, /* indicate inline dot dentries */ + FI_DO_DEFRAG, /* indicate defragment is running */ + FI_DIRTY_FILE, /* indicate regular/symlink has dirty pages */ }; -static inline void set_inode_flag(struct f2fs_inode_info *fi, int flag) +static inline void __mark_inode_dirty_flag(struct inode *inode, + int flag, bool set) +{ + switch (flag) { + case FI_INLINE_XATTR: + case FI_INLINE_DATA: + case FI_INLINE_DENTRY: + if (set) + return; + case FI_DATA_EXIST: + case FI_INLINE_DOTS: + f2fs_mark_inode_dirty_sync(inode, true); + } +} + +static inline void set_inode_flag(struct inode *inode, int flag) +{ + if (!test_bit(flag, &F2FS_I(inode)->flags)) + set_bit(flag, &F2FS_I(inode)->flags); + __mark_inode_dirty_flag(inode, flag, true); +} + +static inline int is_inode_flag_set(struct inode *inode, int flag) +{ + return test_bit(flag, &F2FS_I(inode)->flags); +} + +static inline void clear_inode_flag(struct inode *inode, int flag) +{ + if (test_bit(flag, &F2FS_I(inode)->flags)) + clear_bit(flag, &F2FS_I(inode)->flags); + __mark_inode_dirty_flag(inode, flag, false); +} + +static inline void set_acl_inode(struct inode *inode, umode_t mode) { - if (!test_bit(flag, &fi->flags)) - set_bit(flag, &fi->flags); + F2FS_I(inode)->i_acl_mode = mode; + set_inode_flag(inode, FI_ACL_MODE); + f2fs_mark_inode_dirty_sync(inode, false); } -static inline int is_inode_flag_set(struct f2fs_inode_info *fi, int flag) +static inline void f2fs_i_links_write(struct inode *inode, bool inc) { - return test_bit(flag, &fi->flags); + if (inc) + inc_nlink(inode); + else + drop_nlink(inode); + f2fs_mark_inode_dirty_sync(inode, true); } -static inline void clear_inode_flag(struct f2fs_inode_info *fi, int flag) +static inline void f2fs_i_blocks_write(struct inode *inode, + blkcnt_t diff, bool add) { - if (test_bit(flag, &fi->flags)) - clear_bit(flag, &fi->flags); + bool clean = !is_inode_flag_set(inode, FI_DIRTY_INODE); + bool recover = is_inode_flag_set(inode, FI_AUTO_RECOVER); + + inode->i_blocks = add ? inode->i_blocks + diff : + inode->i_blocks - diff; + f2fs_mark_inode_dirty_sync(inode, true); + if (clean || recover) + set_inode_flag(inode, FI_AUTO_RECOVER); } -static inline void set_acl_inode(struct f2fs_inode_info *fi, umode_t mode) +static inline void f2fs_i_size_write(struct inode *inode, loff_t i_size) { - fi->i_acl_mode = mode; - set_inode_flag(fi, FI_ACL_MODE); + bool clean = !is_inode_flag_set(inode, FI_DIRTY_INODE); + bool recover = is_inode_flag_set(inode, FI_AUTO_RECOVER); + + if (i_size_read(inode) == i_size) + return; + + i_size_write(inode, i_size); + f2fs_mark_inode_dirty_sync(inode, true); + if (clean || recover) + set_inode_flag(inode, FI_AUTO_RECOVER); } -static inline void get_inline_info(struct f2fs_inode_info *fi, - struct f2fs_inode *ri) +static inline void f2fs_i_depth_write(struct inode *inode, unsigned int depth) { + F2FS_I(inode)->i_current_depth = depth; + f2fs_mark_inode_dirty_sync(inode, true); +} + +static inline void f2fs_i_xnid_write(struct inode *inode, nid_t xnid) +{ + F2FS_I(inode)->i_xattr_nid = xnid; + f2fs_mark_inode_dirty_sync(inode, true); +} + +static inline void f2fs_i_pino_write(struct inode *inode, nid_t pino) +{ + F2FS_I(inode)->i_pino = pino; + f2fs_mark_inode_dirty_sync(inode, true); +} + +static inline void get_inline_info(struct inode *inode, struct f2fs_inode *ri) +{ + struct f2fs_inode_info *fi = F2FS_I(inode); + if (ri->i_inline & F2FS_INLINE_XATTR) - set_inode_flag(fi, FI_INLINE_XATTR); + set_bit(FI_INLINE_XATTR, &fi->flags); if (ri->i_inline & F2FS_INLINE_DATA) - set_inode_flag(fi, FI_INLINE_DATA); + set_bit(FI_INLINE_DATA, &fi->flags); if (ri->i_inline & F2FS_INLINE_DENTRY) - set_inode_flag(fi, FI_INLINE_DENTRY); + set_bit(FI_INLINE_DENTRY, &fi->flags); if (ri->i_inline & F2FS_DATA_EXIST) - set_inode_flag(fi, FI_DATA_EXIST); + set_bit(FI_DATA_EXIST, &fi->flags); if (ri->i_inline & F2FS_INLINE_DOTS) - set_inode_flag(fi, FI_INLINE_DOTS); + set_bit(FI_INLINE_DOTS, &fi->flags); } -static inline void set_raw_inline(struct f2fs_inode_info *fi, - struct f2fs_inode *ri) +static inline void set_raw_inline(struct inode *inode, struct f2fs_inode *ri) { ri->i_inline = 0; - if (is_inode_flag_set(fi, FI_INLINE_XATTR)) + if (is_inode_flag_set(inode, FI_INLINE_XATTR)) ri->i_inline |= F2FS_INLINE_XATTR; - if (is_inode_flag_set(fi, FI_INLINE_DATA)) + if (is_inode_flag_set(inode, FI_INLINE_DATA)) ri->i_inline |= F2FS_INLINE_DATA; - if (is_inode_flag_set(fi, FI_INLINE_DENTRY)) + if (is_inode_flag_set(inode, FI_INLINE_DENTRY)) ri->i_inline |= F2FS_INLINE_DENTRY; - if (is_inode_flag_set(fi, FI_DATA_EXIST)) + if (is_inode_flag_set(inode, FI_DATA_EXIST)) ri->i_inline |= F2FS_DATA_EXIST; - if (is_inode_flag_set(fi, FI_INLINE_DOTS)) + if (is_inode_flag_set(inode, FI_INLINE_DOTS)) ri->i_inline |= F2FS_INLINE_DOTS; } static inline int f2fs_has_inline_xattr(struct inode *inode) { - return is_inode_flag_set(F2FS_I(inode), FI_INLINE_XATTR); + return is_inode_flag_set(inode, FI_INLINE_XATTR); } -static inline unsigned int addrs_per_inode(struct f2fs_inode_info *fi) +static inline unsigned int addrs_per_inode(struct inode *inode) { - if (f2fs_has_inline_xattr(&fi->vfs_inode)) + if (f2fs_has_inline_xattr(inode)) return DEF_ADDRS_PER_INODE - F2FS_INLINE_XATTR_ADDRS; return DEF_ADDRS_PER_INODE; } @@ -1502,43 +1845,43 @@ static inline int inline_xattr_size(struct inode *inode) static inline int f2fs_has_inline_data(struct inode *inode) { - return is_inode_flag_set(F2FS_I(inode), FI_INLINE_DATA); + return is_inode_flag_set(inode, FI_INLINE_DATA); } static inline void f2fs_clear_inline_inode(struct inode *inode) { - clear_inode_flag(F2FS_I(inode), FI_INLINE_DATA); - clear_inode_flag(F2FS_I(inode), FI_DATA_EXIST); + clear_inode_flag(inode, FI_INLINE_DATA); + clear_inode_flag(inode, FI_DATA_EXIST); } static inline int f2fs_exist_data(struct inode *inode) { - return is_inode_flag_set(F2FS_I(inode), FI_DATA_EXIST); + return is_inode_flag_set(inode, FI_DATA_EXIST); } static inline int f2fs_has_inline_dots(struct inode *inode) { - return is_inode_flag_set(F2FS_I(inode), FI_INLINE_DOTS); + return is_inode_flag_set(inode, FI_INLINE_DOTS); } static inline bool f2fs_is_atomic_file(struct inode *inode) { - return is_inode_flag_set(F2FS_I(inode), FI_ATOMIC_FILE); + return is_inode_flag_set(inode, FI_ATOMIC_FILE); } static inline bool f2fs_is_volatile_file(struct inode *inode) { - return is_inode_flag_set(F2FS_I(inode), FI_VOLATILE_FILE); + return is_inode_flag_set(inode, FI_VOLATILE_FILE); } static inline bool f2fs_is_first_block_written(struct inode *inode) { - return is_inode_flag_set(F2FS_I(inode), FI_FIRST_BLOCK_WRITTEN); + return is_inode_flag_set(inode, FI_FIRST_BLOCK_WRITTEN); } static inline bool f2fs_is_drop_cache(struct inode *inode) { - return is_inode_flag_set(F2FS_I(inode), FI_DROP_CACHE); + return is_inode_flag_set(inode, FI_DROP_CACHE); } static inline void *inline_data_addr(struct page *page) @@ -1549,7 +1892,7 @@ static inline void *inline_data_addr(struct page *page) static inline int f2fs_has_inline_dentry(struct inode *inode) { - return is_inode_flag_set(F2FS_I(inode), FI_INLINE_DENTRY); + return is_inode_flag_set(inode, FI_INLINE_DENTRY); } static inline void f2fs_dentry_kunmap(struct inode *dir, struct page *page) @@ -1566,27 +1909,41 @@ static inline int is_file(struct inode *inode, int type) static inline void set_file(struct inode *inode, int type) { F2FS_I(inode)->i_advise |= type; + f2fs_mark_inode_dirty_sync(inode, true); } static inline void clear_file(struct inode *inode, int type) { F2FS_I(inode)->i_advise &= ~type; + f2fs_mark_inode_dirty_sync(inode, true); } -static inline int f2fs_readonly(struct super_block *sb) +static inline bool f2fs_skip_inode_update(struct inode *inode, int dsync) { - return sb->s_flags & MS_RDONLY; + if (dsync) { + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + bool ret; + + spin_lock(&sbi->inode_lock[DIRTY_META]); + ret = list_empty(&F2FS_I(inode)->gdirty_list); + spin_unlock(&sbi->inode_lock[DIRTY_META]); + return ret; + } + if (!is_inode_flag_set(inode, FI_AUTO_RECOVER) || + file_keep_isize(inode) || + i_size_read(inode) & PAGE_MASK) + return false; + return F2FS_I(inode)->last_disk_size == i_size_read(inode); } -static inline bool f2fs_cp_error(struct f2fs_sb_info *sbi) +static inline int f2fs_readonly(struct super_block *sb) { - return is_set_ckpt_flags(sbi->ckpt, CP_ERROR_FLAG); + return sb->s_flags & MS_RDONLY; } -static inline void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi) +static inline bool f2fs_cp_error(struct f2fs_sb_info *sbi) { - set_ckpt_flags(sbi->ckpt, CP_ERROR_FLAG); - sbi->sb->s_flags |= MS_RDONLY; + return is_set_ckpt_flags(sbi, CP_ERROR_FLAG); } static inline bool is_dot_dotdot(const struct qstr *str) @@ -1602,13 +1959,21 @@ static inline bool is_dot_dotdot(const struct qstr *str) static inline bool f2fs_may_extent_tree(struct inode *inode) { - mode_t mode = inode->i_mode; - if (!test_opt(F2FS_I_SB(inode), EXTENT_CACHE) || - is_inode_flag_set(F2FS_I(inode), FI_NO_EXTENT)) + is_inode_flag_set(inode, FI_NO_EXTENT)) return false; - return S_ISREG(mode); + return S_ISREG(inode->i_mode); +} + +static inline void *f2fs_kmalloc(struct f2fs_sb_info *sbi, + size_t size, gfp_t flags) +{ +#ifdef CONFIG_F2FS_FAULT_INJECTION + if (time_to_inject(sbi, FAULT_KMALLOC)) + return NULL; +#endif + return kmalloc(size, flags); } static inline void *f2fs_kvmalloc(size_t size, gfp_t flags) @@ -1632,14 +1997,14 @@ static inline void *f2fs_kvzalloc(size_t size, gfp_t flags) } #define get_inode_mode(i) \ - ((is_inode_flag_set(F2FS_I(i), FI_ACL_MODE)) ? \ + ((is_inode_flag_set(i, FI_ACL_MODE)) ? \ (F2FS_I(i)->i_acl_mode) : ((i)->i_mode)) /* get offset of first page in next direct node */ -#define PGOFS_OF_NEXT_DNODE(pgofs, fi) \ - ((pgofs < ADDRS_PER_INODE(fi)) ? ADDRS_PER_INODE(fi) : \ - (pgofs - ADDRS_PER_INODE(fi) + ADDRS_PER_BLOCK) / \ - ADDRS_PER_BLOCK * ADDRS_PER_BLOCK + ADDRS_PER_INODE(fi)) +#define PGOFS_OF_NEXT_DNODE(pgofs, inode) \ + ((pgofs < ADDRS_PER_INODE(inode)) ? ADDRS_PER_INODE(inode) : \ + (pgofs - ADDRS_PER_INODE(inode) + ADDRS_PER_BLOCK) / \ + ADDRS_PER_BLOCK * ADDRS_PER_BLOCK + ADDRS_PER_INODE(inode)) /* * file.c @@ -1647,7 +2012,7 @@ static inline void *f2fs_kvzalloc(size_t size, gfp_t flags) int f2fs_sync_file(struct file *, loff_t, loff_t, int); void truncate_data_blocks(struct dnode_of_data *); int truncate_blocks(struct inode *, u64, bool); -int f2fs_truncate(struct inode *, bool); +int f2fs_truncate(struct inode *); int f2fs_getattr(struct vfsmount *, struct dentry *, struct kstat *); int f2fs_setattr(struct dentry *, struct iattr *); int truncate_hole(struct inode *, pgoff_t, pgoff_t); @@ -1660,9 +2025,10 @@ long f2fs_compat_ioctl(struct file *, unsigned int, unsigned long); */ void f2fs_set_inode_flags(struct inode *); struct inode *f2fs_iget(struct super_block *, unsigned long); +struct inode *f2fs_iget_retry(struct super_block *, unsigned long); int try_to_free_nats(struct f2fs_sb_info *, int); -void update_inode(struct inode *, struct page *); -void update_inode_page(struct inode *); +int update_inode(struct inode *, struct page *); +int update_inode_page(struct inode *); int f2fs_write_inode(struct inode *, struct writeback_control *); void f2fs_evict_inode(struct inode *); void handle_failed_inode(struct inode *); @@ -1675,29 +2041,34 @@ struct dentry *f2fs_get_parent(struct dentry *child); /* * dir.c */ -extern unsigned char f2fs_filetype_table[F2FS_FT_MAX]; void set_de_type(struct f2fs_dir_entry *, umode_t); - -struct f2fs_dir_entry *find_target_dentry(struct f2fs_filename *, +unsigned char get_de_type(struct f2fs_dir_entry *); +struct f2fs_dir_entry *find_target_dentry(struct fscrypt_name *, f2fs_hash_t, int *, struct f2fs_dentry_ptr *); -bool f2fs_fill_dentries(struct dir_context *, struct f2fs_dentry_ptr *, - unsigned int, struct f2fs_str *); +int f2fs_fill_dentries(struct dir_context *, struct f2fs_dentry_ptr *, + unsigned int, struct fscrypt_str *); void do_make_empty_dir(struct inode *, struct inode *, struct f2fs_dentry_ptr *); struct page *init_inode_metadata(struct inode *, struct inode *, - const struct qstr *, struct page *); + const struct qstr *, const struct qstr *, struct page *); void update_parent_metadata(struct inode *, struct inode *, unsigned int); int room_for_filename(const void *, int, int); -void f2fs_drop_nlink(struct inode *, struct inode *, struct page *); -struct f2fs_dir_entry *f2fs_find_entry(struct inode *, struct qstr *, +void f2fs_drop_nlink(struct inode *, struct inode *); +struct f2fs_dir_entry *__f2fs_find_entry(struct inode *, struct fscrypt_name *, + struct page **); +struct f2fs_dir_entry *f2fs_find_entry(struct inode *, const struct qstr *, struct page **); struct f2fs_dir_entry *f2fs_parent_dir(struct inode *, struct page **); -ino_t f2fs_inode_by_name(struct inode *, struct qstr *); +ino_t f2fs_inode_by_name(struct inode *, const struct qstr *, struct page **); void f2fs_set_link(struct inode *, struct f2fs_dir_entry *, struct page *, struct inode *); 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 *, + const struct qstr *, struct inode *, nid_t, umode_t); +int __f2fs_do_add_link(struct inode *, struct fscrypt_name*, 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 *, @@ -1714,17 +2085,19 @@ static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode) /* * super.c */ +int f2fs_inode_dirtied(struct inode *, bool); +void f2fs_inode_synced(struct inode *); int f2fs_commit_super(struct f2fs_sb_info *, bool); loff_t max_file_size(unsigned bits); 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 */ -f2fs_hash_t f2fs_dentry_hash(const struct qstr *name_info, - struct f2fs_filename *fname); +f2fs_hash_t f2fs_dentry_hash(const struct qstr *); /* * node.c @@ -1737,6 +2110,7 @@ int need_dentry_mark(struct f2fs_sb_info *, nid_t); bool is_checkpointed_node(struct f2fs_sb_info *, nid_t); bool need_inode_block_update(struct f2fs_sb_info *, nid_t); void get_node_info(struct f2fs_sb_info *, nid_t, struct node_info *); +pgoff_t get_next_page_offset(struct dnode_of_data *, pgoff_t); int get_dnode_of_data(struct dnode_of_data *, pgoff_t, int); int truncate_inode_blocks(struct inode *, pgoff_t); int truncate_xattr_node(struct inode *, struct page *); @@ -1747,8 +2121,11 @@ struct page *new_node_page(struct dnode_of_data *, unsigned int, struct page *); void ra_node_page(struct f2fs_sb_info *, nid_t); struct page *get_node_page(struct f2fs_sb_info *, pgoff_t); struct page *get_node_page_ra(struct page *, int); -void sync_inode_page(struct dnode_of_data *); -int sync_node_pages(struct f2fs_sb_info *, nid_t, struct writeback_control *); +void move_node_page(struct page *, int); +int fsync_node_pages(struct f2fs_sb_info *, struct inode *, + struct writeback_control *, bool); +int sync_node_pages(struct f2fs_sb_info *, struct writeback_control *); +void build_free_nids(struct f2fs_sb_info *, bool); bool alloc_nid(struct f2fs_sb_info *, nid_t *); void alloc_nid_done(struct f2fs_sb_info *, nid_t); void alloc_nid_failed(struct f2fs_sb_info *, nid_t); @@ -1768,18 +2145,18 @@ void destroy_node_manager_caches(void); * segment.c */ void register_inmem_page(struct inode *, struct page *); -int commit_inmem_pages(struct inode *, bool); -void f2fs_balance_fs(struct f2fs_sb_info *); +void drop_inmem_pages(struct inode *); +int commit_inmem_pages(struct inode *); +void f2fs_balance_fs(struct f2fs_sb_info *, bool); void f2fs_balance_fs_bg(struct f2fs_sb_info *); int f2fs_issue_flush(struct f2fs_sb_info *); int create_flush_cmd_control(struct f2fs_sb_info *); -void destroy_flush_cmd_control(struct f2fs_sb_info *); +void destroy_flush_cmd_control(struct f2fs_sb_info *, bool); void invalidate_blocks(struct f2fs_sb_info *, block_t); 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 *); @@ -1789,16 +2166,17 @@ void write_meta_page(struct f2fs_sb_info *, struct page *); void write_node_page(unsigned int, struct f2fs_io_info *); void write_data_page(struct dnode_of_data *, struct f2fs_io_info *); void rewrite_data_page(struct f2fs_io_info *); +void __f2fs_replace_block(struct f2fs_sb_info *, struct f2fs_summary *, + block_t, block_t, bool, bool); void f2fs_replace_block(struct f2fs_sb_info *, struct dnode_of_data *, - block_t, block_t, unsigned char, bool); + block_t, block_t, unsigned char, bool, bool); void allocate_data_block(struct f2fs_sb_info *, struct page *, block_t, block_t *, struct f2fs_summary *, int); -void f2fs_wait_on_page_writeback(struct page *, enum page_type); +void f2fs_wait_on_page_writeback(struct page *, enum page_type, bool); void f2fs_wait_on_encrypted_page_writeback(struct f2fs_sb_info *, block_t); void write_data_summaries(struct f2fs_sb_info *, block_t); void write_node_summaries(struct f2fs_sb_info *, block_t); -int lookup_journal_in_cursum(struct f2fs_summary_block *, - int, unsigned int, int); +int lookup_journal_in_cursum(struct f2fs_journal *, int, unsigned int, int); void flush_sit_entries(struct f2fs_sb_info *, struct cp_control *); int build_segment_manager(struct f2fs_sb_info *); void destroy_segment_manager(struct f2fs_sb_info *); @@ -1808,6 +2186,7 @@ void destroy_segment_manager_caches(void); /* * checkpoint.c */ +void f2fs_stop_checkpoint(struct f2fs_sb_info *, bool); 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); @@ -1815,21 +2194,21 @@ bool is_valid_blkaddr(struct f2fs_sb_info *, block_t, int); 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); -void add_dirty_inode(struct f2fs_sb_info *, nid_t, int type); -void remove_dirty_inode(struct f2fs_sb_info *, nid_t, int type); -void release_dirty_inode(struct f2fs_sb_info *); +void add_ino_entry(struct f2fs_sb_info *, nid_t, int type); +void remove_ino_entry(struct f2fs_sb_info *, nid_t, int type); +void release_ino_entry(struct f2fs_sb_info *, bool); bool exist_written_data(struct f2fs_sb_info *, nid_t, int); +int f2fs_sync_inode_meta(struct f2fs_sb_info *); int acquire_orphan_inode(struct f2fs_sb_info *); void release_orphan_inode(struct f2fs_sb_info *); -void add_orphan_inode(struct f2fs_sb_info *, nid_t); +void add_orphan_inode(struct inode *); 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 *); +void remove_dirty_inode(struct inode *); +int sync_dirty_inodes(struct f2fs_sb_info *, enum inode_type); +int write_checkpoint(struct f2fs_sb_info *, struct cp_control *); void init_ino_entry_info(struct f2fs_sb_info *); int __init create_checkpoint_caches(void); void destroy_checkpoint_caches(void); @@ -1838,34 +2217,49 @@ void destroy_checkpoint_caches(void); * data.c */ void f2fs_submit_merged_bio(struct f2fs_sb_info *, enum page_type, int); +void f2fs_submit_merged_bio_cond(struct f2fs_sb_info *, struct inode *, + struct page *, nid_t, enum page_type, int); +void f2fs_flush_merged_bios(struct f2fs_sb_info *); int f2fs_submit_page_bio(struct f2fs_io_info *); void f2fs_submit_page_mbio(struct f2fs_io_info *); +struct block_device *f2fs_target_device(struct f2fs_sb_info *, + block_t, struct bio *); +int f2fs_target_device_index(struct f2fs_sb_info *, block_t); void set_data_blkaddr(struct dnode_of_data *); +void f2fs_update_data_blkaddr(struct dnode_of_data *, block_t); +int reserve_new_blocks(struct dnode_of_data *, blkcnt_t); int reserve_new_block(struct dnode_of_data *); int f2fs_get_block(struct dnode_of_data *, pgoff_t); +int f2fs_preallocate_blocks(struct kiocb *, struct iov_iter *); int f2fs_reserve_block(struct dnode_of_data *, pgoff_t); struct page *get_read_data_page(struct inode *, pgoff_t, int, bool); struct page *find_data_page(struct inode *, pgoff_t); struct page *get_lock_data_page(struct inode *, pgoff_t, bool); struct page *get_new_data_page(struct inode *, struct page *, pgoff_t, bool); int do_write_data_page(struct f2fs_io_info *); +int f2fs_map_blocks(struct inode *, struct f2fs_map_blocks *, int, int); int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *, u64, u64); +void f2fs_set_page_dirty_nobuffers(struct page *); void f2fs_invalidate_page(struct page *, unsigned int, unsigned int); int f2fs_release_page(struct page *, gfp_t); +#ifdef CONFIG_MIGRATION +int f2fs_migrate_page(struct address_space *, struct page *, struct page *, + enum migrate_mode); +#endif /* * gc.c */ int start_gc_thread(struct f2fs_sb_info *); void stop_gc_thread(struct f2fs_sb_info *); -block_t start_bidx_of_node(unsigned int, struct f2fs_inode_info *); -int f2fs_gc(struct f2fs_sb_info *, bool); +block_t start_bidx_of_node(unsigned int, struct inode *); +int f2fs_gc(struct f2fs_sb_info *, bool, bool); 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 *); /* @@ -1879,18 +2273,20 @@ struct f2fs_stat_info { int main_area_segs, main_area_sections, main_area_zones; unsigned long long hit_largest, hit_cached, hit_rbtree; unsigned long long hit_total, total_ext; - int ext_tree, ext_node; - int ndirty_node, ndirty_dent, ndirty_dirs, ndirty_meta; - int nats, dirty_nats, sits, dirty_sits, fnids; + int ext_tree, zombie_tree, ext_node; + int ndirty_node, ndirty_dent, ndirty_meta, ndirty_data, ndirty_imeta; + int inmem_pages; + unsigned int ndirty_dirs, ndirty_files, ndirty_all; + int nats, dirty_nats, sits, dirty_sits, free_nids, alloc_nids; int total_count, utilization; - int bg_gc, inmem_pages, wb_pages; - int inline_xattr, inline_inode, inline_dir; - unsigned int valid_count, valid_node_count, valid_inode_count; + int bg_gc, nr_wb_cp_data, nr_wb_data; + int inline_xattr, inline_inode, inline_dir, orphans; + unsigned int valid_count, valid_node_count, valid_inode_count, discard_blks; unsigned int bimodal, avg_vblocks; int util_free, util_valid, util_invalid; int rsvd_segs, overp_segs; int dirty_count, node_pages, meta_pages; - int prefree_count, call_count, cp_count; + int prefree_count, call_count, cp_count, bg_cp_count; int tot_segs, node_segs, data_segs, free_segs, free_secs; int bg_node_segs, bg_data_segs; int tot_blks, data_blks, node_blks; @@ -1911,10 +2307,11 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi) } #define stat_inc_cp_count(si) ((si)->cp_count++) +#define stat_inc_bg_cp_count(si) ((si)->bg_cp_count++) #define stat_inc_call_count(si) ((si)->call_count++) #define stat_inc_bggc_count(sbi) ((sbi)->bg_gc++) -#define stat_inc_dirty_dir(sbi) ((sbi)->n_dirty_dirs++) -#define stat_dec_dirty_dir(sbi) ((sbi)->n_dirty_dirs--) +#define stat_inc_dirty_inode(sbi, type) ((sbi)->ndirty_inode[type]++) +#define stat_dec_dirty_inode(sbi, type) ((sbi)->ndirty_inode[type]--) #define stat_inc_total_hit(sbi) (atomic64_inc(&(sbi)->total_hit_ext)) #define stat_inc_rbtree_node_hit(sbi) (atomic64_inc(&(sbi)->read_hit_rbtree)) #define stat_inc_largest_node_hit(sbi) (atomic64_inc(&(sbi)->read_hit_largest)) @@ -1989,14 +2386,15 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi) int f2fs_build_stats(struct f2fs_sb_info *); void f2fs_destroy_stats(struct f2fs_sb_info *); -void __init f2fs_create_root_stats(void); +int __init f2fs_create_root_stats(void); void f2fs_destroy_root_stats(void); #else #define stat_inc_cp_count(si) +#define stat_inc_bg_cp_count(si) #define stat_inc_call_count(si) #define stat_inc_bggc_count(si) -#define stat_inc_dirty_dir(sbi) -#define stat_dec_dirty_dir(sbi) +#define stat_inc_dirty_inode(sbi, type) +#define stat_dec_dirty_inode(sbi, type) #define stat_inc_total_hit(sb) #define stat_inc_rbtree_node_hit(sb) #define stat_inc_largest_node_hit(sbi) @@ -2017,7 +2415,7 @@ void f2fs_destroy_root_stats(void); static inline int f2fs_build_stats(struct f2fs_sb_info *sbi) { return 0; } static inline void f2fs_destroy_stats(struct f2fs_sb_info *sbi) { } -static inline void __init f2fs_create_root_stats(void) { } +static inline int __init f2fs_create_root_stats(void) { return 0; } static inline void f2fs_destroy_root_stats(void) { } #endif @@ -2046,16 +2444,15 @@ int f2fs_convert_inline_inode(struct inode *); int f2fs_write_inline_data(struct inode *, struct page *); bool recover_inline_data(struct inode *, struct page *); struct f2fs_dir_entry *find_in_inline_dir(struct inode *, - struct f2fs_filename *, struct page **); -struct f2fs_dir_entry *f2fs_parent_inline_dir(struct inode *, struct page **); + struct fscrypt_name *, struct page **); int make_empty_inline_dir(struct inode *inode, struct inode *, struct page *); -int f2fs_add_inline_entry(struct inode *, const struct qstr *, struct inode *, - nid_t, umode_t); +int f2fs_add_inline_entry(struct inode *, const struct qstr *, + const struct qstr *, struct inode *, nid_t, umode_t); void f2fs_delete_inline_entry(struct f2fs_dir_entry *, struct page *, struct inode *, struct inode *); bool f2fs_empty_inline_dir(struct inode *); int f2fs_read_inline_dir(struct file *, struct dir_context *, - struct f2fs_str *); + struct fscrypt_str *); int f2fs_inline_data_fiemap(struct inode *, struct fiemap_extent_info *, __u64, __u64); @@ -2071,8 +2468,8 @@ void f2fs_leave_shrinker(struct f2fs_sb_info *); * extent_cache.c */ unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *, int); -void f2fs_drop_largest_extent(struct inode *, pgoff_t); -void f2fs_init_extent_tree(struct inode *, struct f2fs_extent *); +bool f2fs_init_extent_tree(struct inode *, struct f2fs_extent *); +void f2fs_drop_extent_tree(struct inode *); unsigned int f2fs_destroy_extent_node(struct inode *); void f2fs_destroy_extent_tree(struct inode *); bool f2fs_lookup_extent_cache(struct inode *, pgoff_t, struct extent_info *); @@ -2086,13 +2483,9 @@ void destroy_extent_cache(void); /* * crypto support */ -static inline int f2fs_encrypted_inode(struct inode *inode) +static inline bool f2fs_encrypted_inode(struct inode *inode) { -#ifdef CONFIG_F2FS_FS_ENCRYPTION return file_is_encrypt(inode); -#else - return 0; -#endif } static inline void f2fs_set_encrypted_inode(struct inode *inode) @@ -2104,113 +2497,88 @@ static inline void f2fs_set_encrypted_inode(struct inode *inode) static inline bool f2fs_bio_encrypted(struct bio *bio) { -#ifdef CONFIG_F2FS_FS_ENCRYPTION - return unlikely(bio->bi_private != NULL); -#else - return false; -#endif + return bio->bi_private != NULL; } static inline int f2fs_sb_has_crypto(struct super_block *sb) { -#ifdef CONFIG_F2FS_FS_ENCRYPTION return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_ENCRYPT); -#else - return 0; -#endif } -static inline bool f2fs_may_encrypt(struct inode *inode) +static inline int f2fs_sb_mounted_blkzoned(struct super_block *sb) { -#ifdef CONFIG_F2FS_FS_ENCRYPTION - mode_t mode = inode->i_mode; - - return (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)); -#else - return 0; -#endif + return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_BLKZONED); } -/* crypto_policy.c */ -int f2fs_is_child_context_consistent_with_parent(struct inode *, - struct inode *); -int f2fs_inherit_context(struct inode *, struct inode *, struct page *); -int f2fs_process_policy(const struct f2fs_encryption_policy *, struct inode *); -int f2fs_get_policy(struct inode *, struct f2fs_encryption_policy *); - -/* crypt.c */ -extern struct kmem_cache *f2fs_crypt_info_cachep; -bool f2fs_valid_contents_enc_mode(uint32_t); -uint32_t f2fs_validate_encryption_key_size(uint32_t, uint32_t); -struct f2fs_crypto_ctx *f2fs_get_crypto_ctx(struct inode *); -void f2fs_release_crypto_ctx(struct f2fs_crypto_ctx *); -struct page *f2fs_encrypt(struct inode *, struct page *); -int f2fs_decrypt(struct f2fs_crypto_ctx *, struct page *); -int f2fs_decrypt_one(struct inode *, struct page *); -void f2fs_end_io_crypto_work(struct f2fs_crypto_ctx *, struct bio *); - -/* crypto_key.c */ -void f2fs_free_encryption_info(struct inode *, struct f2fs_crypt_info *); -int _f2fs_get_encryption_info(struct inode *inode); - -/* crypto_fname.c */ -bool f2fs_valid_filenames_enc_mode(uint32_t); -u32 f2fs_fname_crypto_round_up(u32, u32); -int f2fs_fname_crypto_alloc_buffer(struct inode *, u32, struct f2fs_str *); -int f2fs_fname_disk_to_usr(struct inode *, f2fs_hash_t *, - const struct f2fs_str *, struct f2fs_str *); -int f2fs_fname_usr_to_disk(struct inode *, const struct qstr *, - struct f2fs_str *); - -#ifdef CONFIG_F2FS_FS_ENCRYPTION -void f2fs_restore_and_release_control_page(struct page **); -void f2fs_restore_control_page(struct page *); - -int __init f2fs_init_crypto(void); -int f2fs_crypto_initialize(void); -void f2fs_exit_crypto(void); +#ifdef CONFIG_BLK_DEV_ZONED +static inline int get_blkz_type(struct f2fs_sb_info *sbi, + struct block_device *bdev, block_t blkaddr) +{ + unsigned int zno = blkaddr >> sbi->log_blocks_per_blkz; + int i; -int f2fs_has_encryption_key(struct inode *); + for (i = 0; i < sbi->s_ndevs; i++) + if (FDEV(i).bdev == bdev) + return FDEV(i).blkz_type[zno]; + return -EINVAL; +} +#endif -static inline int f2fs_get_encryption_info(struct inode *inode) +static inline bool f2fs_discard_en(struct f2fs_sb_info *sbi) { - struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info; + struct request_queue *q = bdev_get_queue(sbi->sb->s_bdev); - if (!ci || - (ci->ci_keyring_key && - (ci->ci_keyring_key->flags & ((1 << KEY_FLAG_INVALIDATED) | - (1 << KEY_FLAG_REVOKED) | - (1 << KEY_FLAG_DEAD))))) - return _f2fs_get_encryption_info(inode); - return 0; + return blk_queue_discard(q) || f2fs_sb_mounted_blkzoned(sbi->sb); } -void f2fs_fname_crypto_free_buffer(struct f2fs_str *); -int f2fs_fname_setup_filename(struct inode *, const struct qstr *, - int lookup, struct f2fs_filename *); -void f2fs_fname_free_filename(struct f2fs_filename *); -#else -static inline void f2fs_restore_and_release_control_page(struct page **p) { } -static inline void f2fs_restore_control_page(struct page *p) { } - -static inline int __init f2fs_init_crypto(void) { return 0; } -static inline void f2fs_exit_crypto(void) { } +static inline void set_opt_mode(struct f2fs_sb_info *sbi, unsigned int mt) +{ + clear_opt(sbi, ADAPTIVE); + clear_opt(sbi, LFS); -static inline int f2fs_has_encryption_key(struct inode *i) { return 0; } -static inline int f2fs_get_encryption_info(struct inode *i) { return 0; } -static inline void f2fs_fname_crypto_free_buffer(struct f2fs_str *p) { } + switch (mt) { + case F2FS_MOUNT_ADAPTIVE: + set_opt(sbi, ADAPTIVE); + break; + case F2FS_MOUNT_LFS: + set_opt(sbi, LFS); + break; + } +} -static inline int f2fs_fname_setup_filename(struct inode *dir, - const struct qstr *iname, - int lookup, struct f2fs_filename *fname) +static inline bool f2fs_may_encrypt(struct inode *inode) { - memset(fname, 0, sizeof(struct f2fs_filename)); - fname->usr_fname = iname; - fname->disk_name.name = (unsigned char *)iname->name; - fname->disk_name.len = iname->len; +#ifdef CONFIG_F2FS_FS_ENCRYPTION + umode_t mode = inode->i_mode; + + return (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)); +#else return 0; +#endif } -static inline void f2fs_fname_free_filename(struct f2fs_filename *fname) { } +#ifndef CONFIG_F2FS_FS_ENCRYPTION +#define fscrypt_set_d_op(i) +#define fscrypt_get_ctx fscrypt_notsupp_get_ctx +#define fscrypt_release_ctx fscrypt_notsupp_release_ctx +#define fscrypt_encrypt_page fscrypt_notsupp_encrypt_page +#define fscrypt_decrypt_page fscrypt_notsupp_decrypt_page +#define fscrypt_decrypt_bio_pages fscrypt_notsupp_decrypt_bio_pages +#define fscrypt_pullback_bio_page fscrypt_notsupp_pullback_bio_page +#define fscrypt_restore_control_page fscrypt_notsupp_restore_control_page +#define fscrypt_zeroout_range fscrypt_notsupp_zeroout_range +#define fscrypt_process_policy fscrypt_notsupp_process_policy +#define fscrypt_get_policy fscrypt_notsupp_get_policy +#define fscrypt_has_permitted_context fscrypt_notsupp_has_permitted_context +#define fscrypt_inherit_context fscrypt_notsupp_inherit_context +#define fscrypt_get_encryption_info fscrypt_notsupp_get_encryption_info +#define fscrypt_put_encryption_info fscrypt_notsupp_put_encryption_info +#define fscrypt_setup_filename fscrypt_notsupp_setup_filename +#define fscrypt_free_filename fscrypt_notsupp_free_filename +#define fscrypt_fname_encrypted_size fscrypt_notsupp_fname_encrypted_size +#define fscrypt_fname_alloc_buffer fscrypt_notsupp_fname_alloc_buffer +#define fscrypt_fname_free_buffer fscrypt_notsupp_fname_free_buffer +#define fscrypt_fname_disk_to_usr fscrypt_notsupp_fname_disk_to_usr +#define fscrypt_fname_usr_to_disk fscrypt_notsupp_fname_usr_to_disk #endif #endif diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 4b449d263333..5808d5c709a7 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -21,6 +21,8 @@ #include <linux/mount.h> #include <linux/pagevec.h> #include <linux/random.h> +#include <linux/uuid.h> +#include <linux/file.h> #include "f2fs.h" #include "node.h" @@ -40,8 +42,6 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma, struct dnode_of_data dn; int err; - f2fs_balance_fs(sbi); - sb_start_pagefault(inode->i_sb); f2fs_bug_on(sbi, f2fs_has_inline_data(inode)); @@ -57,6 +57,8 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma, f2fs_put_dnode(&dn); f2fs_unlock_op(sbi); + f2fs_balance_fs(sbi, dn.node_changed); + file_update_time(vma->vm_file); lock_page(page); if (unlikely(page->mapping != inode->i_mapping || @@ -74,28 +76,28 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma, goto mapped; /* page is wholly or partially inside EOF */ - if (((loff_t)(page->index + 1) << PAGE_CACHE_SHIFT) > + if (((loff_t)(page->index + 1) << PAGE_SHIFT) > i_size_read(inode)) { unsigned offset; - offset = i_size_read(inode) & ~PAGE_CACHE_MASK; - zero_user_segment(page, offset, PAGE_CACHE_SIZE); + offset = i_size_read(inode) & ~PAGE_MASK; + zero_user_segment(page, offset, PAGE_SIZE); } set_page_dirty(page); - SetPageUptodate(page); + if (!PageUptodate(page)) + SetPageUptodate(page); trace_f2fs_vm_page_mkwrite(page, DATA); mapped: /* fill the page */ - f2fs_wait_on_page_writeback(page, DATA); + f2fs_wait_on_page_writeback(page, DATA, false); /* wait for GCed encrypted page writeback */ if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) f2fs_wait_on_encrypted_page_writeback(sbi, dn.data_blkaddr); - /* if gced page is attached, don't write to cold segment */ - clear_cold_data(page); out: sb_end_pagefault(inode->i_sb); + f2fs_update_time(sbi, REQ_TIME); return block_page_mkwrite_return(err); } @@ -132,7 +134,7 @@ static inline bool need_do_checkpoint(struct inode *inode) if (!S_ISREG(inode->i_mode) || inode->i_nlink != 1) need_cp = true; - else if (file_enc_name(inode) && need_dentry_mark(sbi, inode->i_ino)) + else if (is_sbi_flag_set(sbi, SBI_NEED_CP)) need_cp = true; else if (file_wrong_pino(inode)) need_cp = true; @@ -170,21 +172,16 @@ static void try_to_fix_pino(struct inode *inode) fi->xattr_ver = 0; if (file_wrong_pino(inode) && inode->i_nlink == 1 && get_parent_ino(inode, &pino)) { - fi->i_pino = pino; + f2fs_i_pino_write(inode, pino); file_got_pino(inode); - up_write(&fi->i_sem); - - mark_inode_dirty_sync(inode); - f2fs_write_inode(inode, NULL); - } else { - up_write(&fi->i_sem); } + up_write(&fi->i_sem); } -int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) +static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end, + int datasync, bool atomic) { struct inode *inode = file->f_mapping->host; - struct f2fs_inode_info *fi = F2FS_I(inode); struct f2fs_sb_info *sbi = F2FS_I_SB(inode); nid_t ino = inode->i_ino; int ret = 0; @@ -201,10 +198,10 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) trace_f2fs_sync_file_enter(inode); /* if fdatasync is triggered, let's do in-place-update */ - if (get_dirty_pages(inode) <= SM_I(sbi)->min_fsync_blocks) - set_inode_flag(fi, FI_NEED_IPU); + if (datasync || get_dirty_pages(inode) <= SM_I(sbi)->min_fsync_blocks) + set_inode_flag(inode, FI_NEED_IPU); ret = filemap_write_and_wait_range(inode->i_mapping, start, end); - clear_inode_flag(fi, FI_NEED_IPU); + clear_inode_flag(inode, FI_NEED_IPU); if (ret) { trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret); @@ -212,7 +209,7 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) } /* if the inode is dirty, let's recover all the time */ - if (!datasync) { + if (!f2fs_skip_inode_update(inode, datasync)) { f2fs_write_inode(inode, NULL); goto go_write; } @@ -220,29 +217,26 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) /* * if there is no written data, don't waste time to write recovery info. */ - if (!is_inode_flag_set(fi, FI_APPEND_WRITE) && + if (!is_inode_flag_set(inode, FI_APPEND_WRITE) && !exist_written_data(sbi, ino, APPEND_INO)) { /* it may call write_inode just prior to fsync */ if (need_inode_page_update(sbi, ino)) goto go_write; - if (is_inode_flag_set(fi, FI_UPDATE_WRITE) || + if (is_inode_flag_set(inode, FI_UPDATE_WRITE) || exist_written_data(sbi, ino, UPDATE_INO)) goto flush_out; goto out; } go_write: - /* guarantee free sections for fsync */ - f2fs_balance_fs(sbi); - /* * Both of fdatasync() and fsync() are able to be recovered from * sudden-power-off. */ - down_read(&fi->i_sem); + down_read(&F2FS_I(inode)->i_sem); need_cp = need_do_checkpoint(inode); - up_read(&fi->i_sem); + up_read(&F2FS_I(inode)->i_sem); if (need_cp) { /* all the dirty node pages should be flushed for POR */ @@ -253,19 +247,23 @@ go_write: * will be used only for fsynced inodes after checkpoint. */ try_to_fix_pino(inode); - clear_inode_flag(fi, FI_APPEND_WRITE); - clear_inode_flag(fi, FI_UPDATE_WRITE); + clear_inode_flag(inode, FI_APPEND_WRITE); + clear_inode_flag(inode, FI_UPDATE_WRITE); goto out; } sync_nodes: - sync_node_pages(sbi, ino, &wbc); + ret = fsync_node_pages(sbi, inode, &wbc, atomic); + if (ret) + goto out; /* if cp_error was enabled, we should avoid infinite loop */ - if (unlikely(f2fs_cp_error(sbi))) + if (unlikely(f2fs_cp_error(sbi))) { + ret = -EIO; goto out; + } if (need_inode_block_update(sbi, ino)) { - mark_inode_dirty_sync(inode); + f2fs_mark_inode_dirty_sync(inode, true); f2fs_write_inode(inode, NULL); goto sync_nodes; } @@ -275,18 +273,24 @@ sync_nodes: goto out; /* once recovery info is written, don't need to tack this */ - remove_dirty_inode(sbi, ino, APPEND_INO); - clear_inode_flag(fi, FI_APPEND_WRITE); + remove_ino_entry(sbi, ino, APPEND_INO); + clear_inode_flag(inode, FI_APPEND_WRITE); flush_out: - remove_dirty_inode(sbi, ino, UPDATE_INO); - clear_inode_flag(fi, FI_UPDATE_WRITE); + remove_ino_entry(sbi, ino, UPDATE_INO); + clear_inode_flag(inode, FI_UPDATE_WRITE); ret = f2fs_issue_flush(sbi); + f2fs_update_time(sbi, REQ_TIME); out: trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret); f2fs_trace_ios(NULL, 1); return ret; } +int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) +{ + return f2fs_do_sync_file(file, start, end, datasync, false); +} + static pgoff_t __get_first_dirty_index(struct address_space *mapping, pgoff_t pgofs, int whence) { @@ -300,7 +304,7 @@ static pgoff_t __get_first_dirty_index(struct address_space *mapping, pagevec_init(&pvec, 0); nr_pages = pagevec_lookup_tag(&pvec, mapping, &pgofs, PAGECACHE_TAG_DIRTY, 1); - pgofs = nr_pages ? pvec.pages[0]->index : LONG_MAX; + pgofs = nr_pages ? pvec.pages[0]->index : ULONG_MAX; pagevec_release(&pvec); return pgofs; } @@ -332,7 +336,7 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence) loff_t isize; int err = 0; - mutex_lock(&inode->i_mutex); + inode_lock(inode); isize = i_size_read(inode); if (offset >= isize) @@ -345,32 +349,31 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence) goto found; } - pgofs = (pgoff_t)(offset >> PAGE_CACHE_SHIFT); + pgofs = (pgoff_t)(offset >> PAGE_SHIFT); dirty = __get_first_dirty_index(inode->i_mapping, pgofs, whence); - for (; data_ofs < isize; data_ofs = (loff_t)pgofs << PAGE_CACHE_SHIFT) { + for (; data_ofs < isize; data_ofs = (loff_t)pgofs << PAGE_SHIFT) { set_new_dnode(&dn, inode, NULL, NULL, 0); - err = get_dnode_of_data(&dn, pgofs, LOOKUP_NODE_RA); + err = get_dnode_of_data(&dn, pgofs, LOOKUP_NODE); if (err && err != -ENOENT) { goto fail; } else if (err == -ENOENT) { /* direct node does not exists */ if (whence == SEEK_DATA) { - pgofs = PGOFS_OF_NEXT_DNODE(pgofs, - F2FS_I(inode)); + pgofs = get_next_page_offset(&dn, pgofs); continue; } else { goto found; } } - end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode)); + end_offset = ADDRS_PER_PAGE(dn.node_page, inode); /* find data/hole in dnode block */ for (; dn.ofs_in_node < end_offset; dn.ofs_in_node++, pgofs++, - data_ofs = (loff_t)pgofs << PAGE_CACHE_SHIFT) { + data_ofs = (loff_t)pgofs << PAGE_SHIFT) { block_t blkaddr; blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node); @@ -387,10 +390,10 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence) found: if (whence == SEEK_HOLE && data_ofs > isize) data_ofs = isize; - mutex_unlock(&inode->i_mutex); + inode_unlock(inode); return vfs_setpos(file, data_ofs, maxbytes); fail: - mutex_unlock(&inode->i_mutex); + inode_unlock(inode); return -ENXIO; } @@ -418,19 +421,20 @@ static loff_t f2fs_llseek(struct file *file, loff_t offset, int whence) static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma) { struct inode *inode = file_inode(file); + int err; if (f2fs_encrypted_inode(inode)) { - int err = f2fs_get_encryption_info(inode); + err = fscrypt_get_encryption_info(inode); if (err) return 0; + if (!f2fs_encrypted_inode(inode)) + return -ENOKEY; } /* we don't need to use inline_data strictly */ - if (f2fs_has_inline_data(inode)) { - int err = f2fs_convert_inline_inode(inode); - if (err) - return err; - } + err = f2fs_convert_inline_inode(inode); + if (err) + return err; file_accessed(file); vma->vm_ops = &f2fs_file_vm_ops; @@ -440,12 +444,22 @@ static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma) static int f2fs_file_open(struct inode *inode, struct file *filp) { int ret = generic_file_open(inode, filp); + struct dentry *dir; if (!ret && f2fs_encrypted_inode(inode)) { - ret = f2fs_get_encryption_info(inode); + ret = fscrypt_get_encryption_info(inode); if (ret) - ret = -EACCES; + return -EACCES; + if (!fscrypt_has_encryption_key(inode)) + return -ENOKEY; + } + dir = dget_parent(file_dentry(filp)); + if (f2fs_encrypted_inode(d_inode(dir)) && + !fscrypt_has_permitted_context(d_inode(dir), inode)) { + dput(dir); + return -EPERM; } + dput(dir); return ret; } @@ -468,8 +482,7 @@ int truncate_data_blocks_range(struct dnode_of_data *dn, int count) set_data_blkaddr(dn); invalidate_blocks(sbi, blkaddr); if (dn->ofs_in_node == 0 && IS_INODE(dn->node_page)) - clear_inode_flag(F2FS_I(dn->inode), - FI_FIRST_BLOCK_WRITTEN); + clear_inode_flag(dn->inode, FI_FIRST_BLOCK_WRITTEN); nr_free++; } @@ -480,14 +493,13 @@ int truncate_data_blocks_range(struct dnode_of_data *dn, int count) * we will invalidate all blkaddr in the whole range. */ fofs = start_bidx_of_node(ofs_of_node(dn->node_page), - F2FS_I(dn->inode)) + ofs; + dn->inode) + ofs; f2fs_update_extent_cache_range(dn, fofs, 0, len); dec_valid_block_count(sbi, dn->inode, nr_free); - set_page_dirty(dn->node_page); - sync_inode_page(dn); } dn->ofs_in_node = ofs; + f2fs_update_time(sbi, REQ_TIME); trace_f2fs_truncate_data_blocks_range(dn->inode, dn->nid, dn->ofs_in_node, nr_free); return nr_free; @@ -501,8 +513,8 @@ void truncate_data_blocks(struct dnode_of_data *dn) static int truncate_partial_data_page(struct inode *inode, u64 from, bool cache_only) { - unsigned offset = from & (PAGE_CACHE_SIZE - 1); - pgoff_t index = from >> PAGE_CACHE_SHIFT; + unsigned offset = from & (PAGE_SIZE - 1); + pgoff_t index = from >> PAGE_SHIFT; struct address_space *mapping = inode->i_mapping; struct page *page; @@ -510,7 +522,7 @@ static int truncate_partial_data_page(struct inode *inode, u64 from, return 0; if (cache_only) { - page = f2fs_grab_cache_page(mapping, index, false); + page = find_lock_page(mapping, index); if (page && PageUptodate(page)) goto truncate_out; f2fs_put_page(page, 1); @@ -521,9 +533,10 @@ static int truncate_partial_data_page(struct inode *inode, u64 from, if (IS_ERR(page)) return 0; truncate_out: - f2fs_wait_on_page_writeback(page, DATA); - zero_user(page, offset, PAGE_CACHE_SIZE - offset); - if (!cache_only || !f2fs_encrypted_inode(inode) || !S_ISREG(inode->i_mode)) + f2fs_wait_on_page_writeback(page, DATA, true); + zero_user(page, offset, PAGE_SIZE - offset); + if (!cache_only || !f2fs_encrypted_inode(inode) || + !S_ISREG(inode->i_mode)) set_page_dirty(page); f2fs_put_page(page, 1); return 0; @@ -543,6 +556,9 @@ int truncate_blocks(struct inode *inode, u64 from, bool lock) free_from = (pgoff_t)F2FS_BYTES_TO_BLK(from + blocksize - 1); + if (free_from >= sbi->max_file_blocks) + goto free_partial; + if (lock) f2fs_lock_op(sbi); @@ -561,14 +577,14 @@ int truncate_blocks(struct inode *inode, u64 from, bool lock) } set_new_dnode(&dn, inode, ipage, NULL, 0); - err = get_dnode_of_data(&dn, free_from, LOOKUP_NODE); + err = get_dnode_of_data(&dn, free_from, LOOKUP_NODE_RA); if (err) { if (err == -ENOENT) goto free_next; goto out; } - count = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode)); + count = ADDRS_PER_PAGE(dn.node_page, inode); count -= dn.ofs_in_node; f2fs_bug_on(sbi, count < 0); @@ -584,7 +600,7 @@ free_next: out: if (lock) f2fs_unlock_op(sbi); - +free_partial: /* lastly zero out the first data page */ if (!err) err = truncate_partial_data_page(inode, from, truncate_page); @@ -593,7 +609,7 @@ out: return err; } -int f2fs_truncate(struct inode *inode, bool lock) +int f2fs_truncate(struct inode *inode) { int err; @@ -604,18 +620,18 @@ int f2fs_truncate(struct inode *inode, bool lock) trace_f2fs_truncate(inode); /* we should check inline_data size */ - if (f2fs_has_inline_data(inode) && !f2fs_may_inline_data(inode)) { + if (!f2fs_may_inline_data(inode)) { err = f2fs_convert_inline_inode(inode); if (err) return err; } - err = truncate_blocks(inode, i_size_read(inode), lock); + err = truncate_blocks(inode, i_size_read(inode), true); if (err) return err; - inode->i_mtime = inode->i_ctime = CURRENT_TIME; - mark_inode_dirty(inode); + inode->i_mtime = inode->i_ctime = current_time(inode); + f2fs_mark_inode_dirty_sync(inode, false); return 0; } @@ -631,7 +647,6 @@ int f2fs_getattr(struct vfsmount *mnt, #ifdef CONFIG_F2FS_FS_POSIX_ACL static void __setattr_copy(struct inode *inode, const struct iattr *attr) { - struct f2fs_inode_info *fi = F2FS_I(inode); unsigned int ia_valid = attr->ia_valid; if (ia_valid & ATTR_UID) @@ -652,7 +667,7 @@ static void __setattr_copy(struct inode *inode, const struct iattr *attr) if (!in_group_p(inode->i_gid) && !capable(CAP_FSETID)) mode &= ~S_ISGID; - set_acl_inode(fi, mode); + set_acl_inode(inode, mode); } } #else @@ -662,8 +677,8 @@ static void __setattr_copy(struct inode *inode, const struct iattr *attr) int f2fs_setattr(struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); - struct f2fs_inode_info *fi = F2FS_I(inode); int err; + bool size_changed = false; err = inode_change_ok(inode, attr); if (err) @@ -671,36 +686,49 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr) if (attr->ia_valid & ATTR_SIZE) { if (f2fs_encrypted_inode(inode) && - f2fs_get_encryption_info(inode)) + fscrypt_get_encryption_info(inode)) return -EACCES; if (attr->ia_size <= i_size_read(inode)) { truncate_setsize(inode, attr->ia_size); - err = f2fs_truncate(inode, true); + err = f2fs_truncate(inode); if (err) return err; - f2fs_balance_fs(F2FS_I_SB(inode)); } else { /* * do not trim all blocks after i_size if target size is * larger than i_size. */ truncate_setsize(inode, attr->ia_size); - inode->i_mtime = inode->i_ctime = CURRENT_TIME; + + /* should convert inline inode here */ + if (!f2fs_may_inline_data(inode)) { + err = f2fs_convert_inline_inode(inode); + if (err) + return err; + } + inode->i_mtime = inode->i_ctime = current_time(inode); } + + size_changed = true; } __setattr_copy(inode, attr); if (attr->ia_valid & ATTR_MODE) { err = posix_acl_chmod(inode, get_inode_mode(inode)); - if (err || is_inode_flag_set(fi, FI_ACL_MODE)) { - inode->i_mode = fi->i_acl_mode; - clear_inode_flag(fi, FI_ACL_MODE); + if (err || is_inode_flag_set(inode, FI_ACL_MODE)) { + inode->i_mode = F2FS_I(inode)->i_acl_mode; + clear_inode_flag(inode, FI_ACL_MODE); } } - mark_inode_dirty(inode); + /* file size may changed here */ + f2fs_mark_inode_dirty_sync(inode, size_changed); + + /* inode change will produce dirty node pages flushed by checkpoint */ + f2fs_balance_fs(F2FS_I_SB(inode), true); + return err; } @@ -727,7 +755,7 @@ static int fill_zero(struct inode *inode, pgoff_t index, if (!len) return 0; - f2fs_balance_fs(sbi); + f2fs_balance_fs(sbi, true); f2fs_lock_op(sbi); page = get_new_data_page(inode, NULL, index, false); @@ -736,7 +764,7 @@ static int fill_zero(struct inode *inode, pgoff_t index, if (IS_ERR(page)) return PTR_ERR(page); - f2fs_wait_on_page_writeback(page, DATA); + f2fs_wait_on_page_writeback(page, DATA, true); zero_user(page, start, len); set_page_dirty(page); f2fs_put_page(page, 1); @@ -761,7 +789,7 @@ int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end) return err; } - end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode)); + end_offset = ADDRS_PER_PAGE(dn.node_page, inode); count = min(end_offset - dn.ofs_in_node, pg_end - pg_start); f2fs_bug_on(F2FS_I_SB(inode), count == 0 || count > end_offset); @@ -778,19 +806,17 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len) { pgoff_t pg_start, pg_end; loff_t off_start, off_end; - int ret = 0; + int ret; - if (f2fs_has_inline_data(inode)) { - ret = f2fs_convert_inline_inode(inode); - if (ret) - return ret; - } + ret = f2fs_convert_inline_inode(inode); + if (ret) + return ret; - pg_start = ((unsigned long long) offset) >> PAGE_CACHE_SHIFT; - pg_end = ((unsigned long long) offset + len) >> PAGE_CACHE_SHIFT; + pg_start = ((unsigned long long) offset) >> PAGE_SHIFT; + pg_end = ((unsigned long long) offset + len) >> PAGE_SHIFT; - off_start = offset & (PAGE_CACHE_SIZE - 1); - off_end = (offset + len) & (PAGE_CACHE_SIZE - 1); + off_start = offset & (PAGE_SIZE - 1); + off_end = (offset + len) & (PAGE_SIZE - 1); if (pg_start == pg_end) { ret = fill_zero(inode, pg_start, off_start, @@ -800,7 +826,7 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len) } else { if (off_start) { ret = fill_zero(inode, pg_start++, off_start, - PAGE_CACHE_SIZE - off_start); + PAGE_SIZE - off_start); if (ret) return ret; } @@ -815,10 +841,10 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len) loff_t blk_start, blk_end; struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - f2fs_balance_fs(sbi); + f2fs_balance_fs(sbi, true); - blk_start = (loff_t)pg_start << PAGE_CACHE_SHIFT; - blk_end = (loff_t)pg_end << PAGE_CACHE_SHIFT; + blk_start = (loff_t)pg_start << PAGE_SHIFT; + blk_end = (loff_t)pg_end << PAGE_SHIFT; truncate_inode_pages_range(mapping, blk_start, blk_end - 1); @@ -831,83 +857,199 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len) return ret; } -static int __exchange_data_block(struct inode *inode, pgoff_t src, - pgoff_t dst, bool full) +static int __read_out_blkaddrs(struct inode *inode, block_t *blkaddr, + int *do_replace, pgoff_t off, pgoff_t len) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct dnode_of_data dn; - block_t new_addr; - bool do_replace = false; - int ret; + int ret, done, i; +next_dnode: set_new_dnode(&dn, inode, NULL, NULL, 0); - ret = get_dnode_of_data(&dn, src, LOOKUP_NODE_RA); + ret = get_dnode_of_data(&dn, off, LOOKUP_NODE_RA); if (ret && ret != -ENOENT) { return ret; } else if (ret == -ENOENT) { - new_addr = NULL_ADDR; - } else { - new_addr = dn.data_blkaddr; - if (!is_checkpointed_data(sbi, new_addr)) { - dn.data_blkaddr = NULL_ADDR; + if (dn.max_level == 0) + return -ENOENT; + done = min((pgoff_t)ADDRS_PER_BLOCK - dn.ofs_in_node, len); + blkaddr += done; + do_replace += done; + goto next; + } + + done = min((pgoff_t)ADDRS_PER_PAGE(dn.node_page, inode) - + dn.ofs_in_node, len); + for (i = 0; i < done; i++, blkaddr++, do_replace++, dn.ofs_in_node++) { + *blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node); + if (!is_checkpointed_data(sbi, *blkaddr)) { + + if (test_opt(sbi, LFS)) { + f2fs_put_dnode(&dn); + return -ENOTSUPP; + } + /* do not invalidate this block address */ - set_data_blkaddr(&dn); - f2fs_update_extent_cache(&dn); - do_replace = true; + f2fs_update_data_blkaddr(&dn, NULL_ADDR); + *do_replace = 1; } - f2fs_put_dnode(&dn); } + f2fs_put_dnode(&dn); +next: + len -= done; + off += done; + if (len) + goto next_dnode; + return 0; +} - if (new_addr == NULL_ADDR) - return full ? truncate_hole(inode, dst, dst + 1) : 0; +static int __roll_back_blkaddrs(struct inode *inode, block_t *blkaddr, + int *do_replace, pgoff_t off, int len) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct dnode_of_data dn; + int ret, i; - if (do_replace) { - struct page *ipage = get_node_page(sbi, inode->i_ino); - struct node_info ni; + for (i = 0; i < len; i++, do_replace++, blkaddr++) { + if (*do_replace == 0) + continue; - if (IS_ERR(ipage)) { - ret = PTR_ERR(ipage); - goto err_out; + set_new_dnode(&dn, inode, NULL, NULL, 0); + ret = get_dnode_of_data(&dn, off + i, LOOKUP_NODE_RA); + if (ret) { + dec_valid_block_count(sbi, inode, 1); + invalidate_blocks(sbi, *blkaddr); + } else { + f2fs_update_data_blkaddr(&dn, *blkaddr); } + f2fs_put_dnode(&dn); + } + return 0; +} - set_new_dnode(&dn, inode, ipage, NULL, 0); - ret = f2fs_reserve_block(&dn, dst); - if (ret) - goto err_out; +static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode, + block_t *blkaddr, int *do_replace, + pgoff_t src, pgoff_t dst, pgoff_t len, bool full) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(src_inode); + pgoff_t i = 0; + int ret; + + while (i < len) { + if (blkaddr[i] == NULL_ADDR && !full) { + i++; + continue; + } - truncate_data_blocks_range(&dn, 1); + if (do_replace[i] || blkaddr[i] == NULL_ADDR) { + struct dnode_of_data dn; + struct node_info ni; + size_t new_size; + pgoff_t ilen; - get_node_info(sbi, dn.nid, &ni); - f2fs_replace_block(sbi, &dn, dn.data_blkaddr, new_addr, - ni.version, true); - f2fs_put_dnode(&dn); - } else { - struct page *psrc, *pdst; + set_new_dnode(&dn, dst_inode, NULL, NULL, 0); + ret = get_dnode_of_data(&dn, dst + i, ALLOC_NODE); + if (ret) + return ret; + + get_node_info(sbi, dn.nid, &ni); + ilen = min((pgoff_t) + ADDRS_PER_PAGE(dn.node_page, dst_inode) - + dn.ofs_in_node, len - i); + do { + dn.data_blkaddr = datablock_addr(dn.node_page, + dn.ofs_in_node); + truncate_data_blocks_range(&dn, 1); + + if (do_replace[i]) { + f2fs_i_blocks_write(src_inode, + 1, false); + f2fs_i_blocks_write(dst_inode, + 1, true); + f2fs_replace_block(sbi, &dn, dn.data_blkaddr, + blkaddr[i], ni.version, true, false); + + do_replace[i] = 0; + } + dn.ofs_in_node++; + i++; + new_size = (dst + i) << PAGE_SHIFT; + if (dst_inode->i_size < new_size) + f2fs_i_size_write(dst_inode, new_size); + } while (--ilen && (do_replace[i] || blkaddr[i] == NULL_ADDR)); - psrc = get_lock_data_page(inode, src, true); - if (IS_ERR(psrc)) - return PTR_ERR(psrc); - pdst = get_new_data_page(inode, NULL, dst, false); - if (IS_ERR(pdst)) { + f2fs_put_dnode(&dn); + } else { + struct page *psrc, *pdst; + + psrc = get_lock_data_page(src_inode, src + i, true); + if (IS_ERR(psrc)) + return PTR_ERR(psrc); + pdst = get_new_data_page(dst_inode, NULL, dst + i, + true); + if (IS_ERR(pdst)) { + f2fs_put_page(psrc, 1); + return PTR_ERR(pdst); + } + f2fs_copy_page(psrc, pdst); + set_page_dirty(pdst); + f2fs_put_page(pdst, 1); f2fs_put_page(psrc, 1); - return PTR_ERR(pdst); - } - f2fs_copy_page(psrc, pdst); - set_page_dirty(pdst); - f2fs_put_page(pdst, 1); - f2fs_put_page(psrc, 1); - return truncate_hole(inode, src, src + 1); + ret = truncate_hole(src_inode, src + i, src + i + 1); + if (ret) + return ret; + i++; + } } return 0; +} -err_out: - if (!get_dnode_of_data(&dn, src, LOOKUP_NODE)) { - dn.data_blkaddr = new_addr; - set_data_blkaddr(&dn); - f2fs_update_extent_cache(&dn); - f2fs_put_dnode(&dn); +static int __exchange_data_block(struct inode *src_inode, + struct inode *dst_inode, pgoff_t src, pgoff_t dst, + pgoff_t len, bool full) +{ + block_t *src_blkaddr; + int *do_replace; + pgoff_t olen; + int ret; + + while (len) { + olen = min((pgoff_t)4 * ADDRS_PER_BLOCK, len); + + src_blkaddr = f2fs_kvzalloc(sizeof(block_t) * olen, GFP_KERNEL); + if (!src_blkaddr) + return -ENOMEM; + + do_replace = f2fs_kvzalloc(sizeof(int) * olen, GFP_KERNEL); + if (!do_replace) { + kvfree(src_blkaddr); + return -ENOMEM; + } + + ret = __read_out_blkaddrs(src_inode, src_blkaddr, + do_replace, src, olen); + if (ret) + goto roll_back; + + ret = __clone_blkaddrs(src_inode, dst_inode, src_blkaddr, + do_replace, src, dst, olen, full); + if (ret) + goto roll_back; + + src += olen; + dst += olen; + len -= olen; + + kvfree(src_blkaddr); + kvfree(do_replace); } + return 0; + +roll_back: + __roll_back_blkaddrs(src_inode, src_blkaddr, do_replace, src, len); + kvfree(src_blkaddr); + kvfree(do_replace); return ret; } @@ -915,16 +1057,15 @@ static int f2fs_do_collapse(struct inode *inode, pgoff_t start, pgoff_t end) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); pgoff_t nrpages = (i_size_read(inode) + PAGE_SIZE - 1) / PAGE_SIZE; - int ret = 0; + int ret; - for (; end < nrpages; start++, end++) { - f2fs_balance_fs(sbi); - f2fs_lock_op(sbi); - ret = __exchange_data_block(inode, end, start, true); - f2fs_unlock_op(sbi); - if (ret) - break; - } + f2fs_balance_fs(sbi, true); + f2fs_lock_op(sbi); + + f2fs_drop_extent_tree(inode); + + ret = __exchange_data_block(inode, inode, end, start, nrpages - end, true); + f2fs_unlock_op(sbi); return ret; } @@ -941,16 +1082,12 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len) if (offset & (F2FS_BLKSIZE - 1) || len & (F2FS_BLKSIZE - 1)) return -EINVAL; - f2fs_balance_fs(F2FS_I_SB(inode)); - - if (f2fs_has_inline_data(inode)) { - ret = f2fs_convert_inline_inode(inode); - if (ret) - return ret; - } + ret = f2fs_convert_inline_inode(inode); + if (ret) + return ret; - pg_start = offset >> PAGE_CACHE_SHIFT; - pg_end = (offset + len) >> PAGE_CACHE_SHIFT; + pg_start = offset >> PAGE_SHIFT; + pg_end = (offset + len) >> PAGE_SHIFT; /* write out all dirty pages from offset */ ret = filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX); @@ -972,7 +1109,50 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len) ret = truncate_blocks(inode, new_size, true); if (!ret) - i_size_write(inode, new_size); + f2fs_i_size_write(inode, new_size); + + return ret; +} + +static int f2fs_do_zero_range(struct dnode_of_data *dn, pgoff_t start, + pgoff_t end) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); + pgoff_t index = start; + unsigned int ofs_in_node = dn->ofs_in_node; + blkcnt_t count = 0; + int ret; + + for (; index < end; index++, dn->ofs_in_node++) { + if (datablock_addr(dn->node_page, dn->ofs_in_node) == NULL_ADDR) + count++; + } + + dn->ofs_in_node = ofs_in_node; + ret = reserve_new_blocks(dn, count); + if (ret) + return ret; + + dn->ofs_in_node = ofs_in_node; + for (index = start; index < end; index++, dn->ofs_in_node++) { + dn->data_blkaddr = + datablock_addr(dn->node_page, dn->ofs_in_node); + /* + * reserve_new_blocks will not guarantee entire block + * allocation. + */ + if (dn->data_blkaddr == NULL_ADDR) { + ret = -ENOSPC; + break; + } + if (dn->data_blkaddr != NEW_ADDR) { + invalidate_blocks(sbi, dn->data_blkaddr); + dn->data_blkaddr = NEW_ADDR; + set_data_blkaddr(dn); + } + } + + f2fs_update_extent_cache_range(dn, start, 0, index - start); return ret; } @@ -991,13 +1171,9 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len, if (ret) return ret; - f2fs_balance_fs(sbi); - - if (f2fs_has_inline_data(inode)) { - ret = f2fs_convert_inline_inode(inode); - if (ret) - return ret; - } + ret = f2fs_convert_inline_inode(inode); + if (ret) + return ret; ret = filemap_write_and_wait_range(mapping, offset, offset + len - 1); if (ret) @@ -1005,11 +1181,11 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len, truncate_pagecache_range(inode, offset, offset + len - 1); - pg_start = ((unsigned long long) offset) >> PAGE_CACHE_SHIFT; - pg_end = ((unsigned long long) offset + len) >> PAGE_CACHE_SHIFT; + pg_start = ((unsigned long long) offset) >> PAGE_SHIFT; + pg_end = ((unsigned long long) offset + len) >> PAGE_SHIFT; - off_start = offset & (PAGE_CACHE_SIZE - 1); - off_end = (offset + len) & (PAGE_CACHE_SIZE - 1); + off_start = offset & (PAGE_SIZE - 1); + off_end = (offset + len) & (PAGE_SIZE - 1); if (pg_start == pg_end) { ret = fill_zero(inode, pg_start, off_start, @@ -1023,48 +1199,43 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len, } else { if (off_start) { ret = fill_zero(inode, pg_start++, off_start, - PAGE_CACHE_SIZE - off_start); + PAGE_SIZE - off_start); if (ret) return ret; new_size = max_t(loff_t, new_size, - (loff_t)pg_start << PAGE_CACHE_SHIFT); + (loff_t)pg_start << PAGE_SHIFT); } - for (index = pg_start; index < pg_end; index++) { + for (index = pg_start; index < pg_end;) { struct dnode_of_data dn; - struct page *ipage; + unsigned int end_offset; + pgoff_t end; f2fs_lock_op(sbi); - ipage = get_node_page(sbi, inode->i_ino); - if (IS_ERR(ipage)) { - ret = PTR_ERR(ipage); - f2fs_unlock_op(sbi); - goto out; - } - - set_new_dnode(&dn, inode, ipage, NULL, 0); - ret = f2fs_reserve_block(&dn, index); + set_new_dnode(&dn, inode, NULL, NULL, 0); + ret = get_dnode_of_data(&dn, index, ALLOC_NODE); if (ret) { f2fs_unlock_op(sbi); goto out; } - if (dn.data_blkaddr != NEW_ADDR) { - invalidate_blocks(sbi, dn.data_blkaddr); - - dn.data_blkaddr = NEW_ADDR; - set_data_blkaddr(&dn); + end_offset = ADDRS_PER_PAGE(dn.node_page, inode); + end = min(pg_end, end_offset - dn.ofs_in_node + index); - dn.data_blkaddr = NULL_ADDR; - f2fs_update_extent_cache(&dn); - } + ret = f2fs_do_zero_range(&dn, index, end); f2fs_put_dnode(&dn); f2fs_unlock_op(sbi); + f2fs_balance_fs(sbi, dn.node_changed); + + if (ret) + goto out; + + index = end; new_size = max_t(loff_t, new_size, - (loff_t)(index + 1) << PAGE_CACHE_SHIFT); + (loff_t)index << PAGE_SHIFT); } if (off_end) { @@ -1077,11 +1248,8 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len, } out: - if (!(mode & FALLOC_FL_KEEP_SIZE) && i_size_read(inode) < new_size) { - i_size_write(inode, new_size); - mark_inode_dirty(inode); - update_inode_page(inode); - } + if (!(mode & FALLOC_FL_KEEP_SIZE) && i_size_read(inode) < new_size) + f2fs_i_size_write(inode, new_size); return ret; } @@ -1089,7 +1257,7 @@ out: static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - pgoff_t pg_start, pg_end, delta, nrpages, idx; + pgoff_t nr, pg_start, pg_end, delta, idx; loff_t new_size; int ret = 0; @@ -1104,13 +1272,11 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len) if (offset & (F2FS_BLKSIZE - 1) || len & (F2FS_BLKSIZE - 1)) return -EINVAL; - f2fs_balance_fs(sbi); + ret = f2fs_convert_inline_inode(inode); + if (ret) + return ret; - if (f2fs_has_inline_data(inode)) { - ret = f2fs_convert_inline_inode(inode); - if (ret) - return ret; - } + f2fs_balance_fs(sbi, true); ret = truncate_blocks(inode, i_size_read(inode), true); if (ret) @@ -1123,17 +1289,23 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len) truncate_pagecache(inode, offset); - pg_start = offset >> PAGE_CACHE_SHIFT; - pg_end = (offset + len) >> PAGE_CACHE_SHIFT; + pg_start = offset >> PAGE_SHIFT; + pg_end = (offset + len) >> PAGE_SHIFT; delta = pg_end - pg_start; - nrpages = (i_size_read(inode) + PAGE_SIZE - 1) / PAGE_SIZE; + idx = (i_size_read(inode) + PAGE_SIZE - 1) / PAGE_SIZE; + + while (!ret && idx > pg_start) { + nr = idx - pg_start; + if (nr > delta) + nr = delta; + idx -= nr; - for (idx = nrpages - 1; idx >= pg_start && idx != -1; idx--) { f2fs_lock_op(sbi); - ret = __exchange_data_block(inode, idx, idx + delta, false); + f2fs_drop_extent_tree(inode); + + ret = __exchange_data_block(inode, inode, idx, + idx + delta, nr, false); f2fs_unlock_op(sbi); - if (ret) - break; } /* write out all moved pages, if possible */ @@ -1141,7 +1313,7 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len) truncate_pagecache(inode, offset); if (!ret) - i_size_write(inode, new_size); + f2fs_i_size_write(inode, new_size); return ret; } @@ -1149,62 +1321,50 @@ static int expand_inode_data(struct inode *inode, loff_t offset, loff_t len, int mode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - pgoff_t index, pg_start, pg_end; + struct f2fs_map_blocks map = { .m_next_pgofs = NULL }; + pgoff_t pg_end; loff_t new_size = i_size_read(inode); - loff_t off_start, off_end; - int ret = 0; + loff_t off_end; + int err; - f2fs_balance_fs(sbi); + err = inode_newsize_ok(inode, (len + offset)); + if (err) + return err; - ret = inode_newsize_ok(inode, (len + offset)); - if (ret) - return ret; + err = f2fs_convert_inline_inode(inode); + if (err) + return err; - if (f2fs_has_inline_data(inode)) { - ret = f2fs_convert_inline_inode(inode); - if (ret) - return ret; - } + f2fs_balance_fs(sbi, true); - pg_start = ((unsigned long long) offset) >> PAGE_CACHE_SHIFT; - pg_end = ((unsigned long long) offset + len) >> PAGE_CACHE_SHIFT; + pg_end = ((unsigned long long)offset + len) >> PAGE_SHIFT; + off_end = (offset + len) & (PAGE_SIZE - 1); - off_start = offset & (PAGE_CACHE_SIZE - 1); - off_end = (offset + len) & (PAGE_CACHE_SIZE - 1); + map.m_lblk = ((unsigned long long)offset) >> PAGE_SHIFT; + map.m_len = pg_end - map.m_lblk; + if (off_end) + map.m_len++; - f2fs_lock_op(sbi); + err = f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_AIO); + if (err) { + pgoff_t last_off; - for (index = pg_start; index <= pg_end; index++) { - struct dnode_of_data dn; + if (!map.m_len) + return err; - if (index == pg_end && !off_end) - goto noalloc; + last_off = map.m_lblk + map.m_len - 1; - set_new_dnode(&dn, inode, NULL, NULL, 0); - ret = f2fs_reserve_block(&dn, index); - if (ret) - break; -noalloc: - if (pg_start == pg_end) - new_size = offset + len; - else if (index == pg_start && off_start) - new_size = (loff_t)(index + 1) << PAGE_CACHE_SHIFT; - else if (index == pg_end) - new_size = ((loff_t)index << PAGE_CACHE_SHIFT) + - off_end; - else - new_size += PAGE_CACHE_SIZE; + /* update new size to the failed position */ + new_size = (last_off == pg_end) ? offset + len: + (loff_t)(last_off + 1) << PAGE_SHIFT; + } else { + new_size = ((loff_t)pg_end << PAGE_SHIFT) + off_end; } - if (!(mode & FALLOC_FL_KEEP_SIZE) && - i_size_read(inode) < new_size) { - i_size_write(inode, new_size); - mark_inode_dirty(inode); - update_inode_page(inode); - } - f2fs_unlock_op(sbi); + if (!(mode & FALLOC_FL_KEEP_SIZE) && i_size_read(inode) < new_size) + f2fs_i_size_write(inode, new_size); - return ret; + return err; } static long f2fs_fallocate(struct file *file, int mode, @@ -1226,7 +1386,7 @@ static long f2fs_fallocate(struct file *file, int mode, FALLOC_FL_INSERT_RANGE)) return -EOPNOTSUPP; - mutex_lock(&inode->i_mutex); + inode_lock(inode); if (mode & FALLOC_FL_PUNCH_HOLE) { if (offset >= inode->i_size) @@ -1244,12 +1404,15 @@ static long f2fs_fallocate(struct file *file, int mode, } if (!ret) { - inode->i_mtime = inode->i_ctime = CURRENT_TIME; - mark_inode_dirty(inode); + inode->i_mtime = inode->i_ctime = current_time(inode); + f2fs_mark_inode_dirty_sync(inode, false); + if (mode & FALLOC_FL_KEEP_SIZE) + file_set_keep_isize(inode); + f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); } out: - mutex_unlock(&inode->i_mutex); + inode_unlock(inode); trace_f2fs_fallocate(inode, mode, offset, len, ret); return ret; @@ -1257,13 +1420,22 @@ out: static int f2fs_release_file(struct inode *inode, struct file *filp) { + /* + * f2fs_relase_file is called at every close calls. So we should + * not drop any inmemory pages by close called by other process. + */ + if (!(filp->f_mode & FMODE_WRITE) || + atomic_read(&inode->i_writecount) != 1) + return 0; + /* some remained atomic pages should discarded */ if (f2fs_is_atomic_file(inode)) - commit_inmem_pages(inode, true); + drop_inmem_pages(inode); if (f2fs_is_volatile_file(inode)) { - set_inode_flag(F2FS_I(inode), FI_DROP_CACHE); + clear_inode_flag(inode, FI_VOLATILE_FILE); + set_inode_flag(inode, FI_DROP_CACHE); filemap_fdatawrite(inode->i_mapping); - clear_inode_flag(F2FS_I(inode), FI_DROP_CACHE); + clear_inode_flag(inode, FI_DROP_CACHE); } return 0; } @@ -1293,33 +1465,29 @@ static int f2fs_ioc_setflags(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); struct f2fs_inode_info *fi = F2FS_I(inode); - unsigned int flags = fi->i_flags & FS_FL_USER_VISIBLE; + unsigned int flags; unsigned int oldflags; int ret; + if (!inode_owner_or_capable(inode)) + return -EACCES; + + if (get_user(flags, (int __user *)arg)) + return -EFAULT; + ret = mnt_want_write_file(filp); if (ret) return ret; - if (!inode_owner_or_capable(inode)) { - ret = -EACCES; - goto out; - } - - if (get_user(flags, (int __user *)arg)) { - ret = -EFAULT; - goto out; - } - flags = f2fs_mask_flags(inode->i_mode, flags); - mutex_lock(&inode->i_mutex); + inode_lock(inode); oldflags = fi->i_flags; if ((flags ^ oldflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL)) { if (!capable(CAP_LINUX_IMMUTABLE)) { - mutex_unlock(&inode->i_mutex); + inode_unlock(inode); ret = -EPERM; goto out; } @@ -1328,11 +1496,10 @@ static int f2fs_ioc_setflags(struct file *filp, unsigned long arg) flags = flags & FS_FL_USER_MODIFIABLE; flags |= oldflags & ~FS_FL_USER_MODIFIABLE; fi->i_flags = flags; - mutex_unlock(&inode->i_mutex); + inode_unlock(inode); + inode->i_ctime = current_time(inode); f2fs_set_inode_flags(inode); - inode->i_ctime = CURRENT_TIME; - mark_inode_dirty(inode); out: mnt_drop_write_file(filp); return ret; @@ -1353,17 +1520,35 @@ static int f2fs_ioc_start_atomic_write(struct file *filp) if (!inode_owner_or_capable(inode)) return -EACCES; - f2fs_balance_fs(F2FS_I_SB(inode)); + ret = mnt_want_write_file(filp); + if (ret) + return ret; + + inode_lock(inode); if (f2fs_is_atomic_file(inode)) - return 0; + goto out; ret = f2fs_convert_inline_inode(inode); if (ret) - return ret; + goto out; - set_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE); - return 0; + set_inode_flag(inode, FI_ATOMIC_FILE); + f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); + + if (!get_dirty_pages(inode)) + goto out; + + f2fs_msg(F2FS_I_SB(inode)->sb, KERN_WARNING, + "Unexpected flush for atomic writes: ino=%lu, npages=%u", + inode->i_ino, get_dirty_pages(inode)); + ret = filemap_write_and_wait_range(inode->i_mapping, 0, LLONG_MAX); + if (ret) + clear_inode_flag(inode, FI_ATOMIC_FILE); +out: + inode_unlock(inode); + mnt_drop_write_file(filp); + return ret; } static int f2fs_ioc_commit_atomic_write(struct file *filp) @@ -1374,22 +1559,27 @@ static int f2fs_ioc_commit_atomic_write(struct file *filp) if (!inode_owner_or_capable(inode)) return -EACCES; - if (f2fs_is_volatile_file(inode)) - return 0; - ret = mnt_want_write_file(filp); if (ret) return ret; + inode_lock(inode); + + if (f2fs_is_volatile_file(inode)) + goto err_out; + if (f2fs_is_atomic_file(inode)) { - clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE); - ret = commit_inmem_pages(inode, false); - if (ret) + clear_inode_flag(inode, FI_ATOMIC_FILE); + ret = commit_inmem_pages(inode); + if (ret) { + set_inode_flag(inode, FI_ATOMIC_FILE); goto err_out; + } } - ret = f2fs_sync_file(filp, 0, LLONG_MAX, 0); + ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true); err_out: + inode_unlock(inode); mnt_drop_write_file(filp); return ret; } @@ -1402,31 +1592,54 @@ static int f2fs_ioc_start_volatile_write(struct file *filp) if (!inode_owner_or_capable(inode)) return -EACCES; + ret = mnt_want_write_file(filp); + if (ret) + return ret; + + inode_lock(inode); + if (f2fs_is_volatile_file(inode)) - return 0; + goto out; ret = f2fs_convert_inline_inode(inode); if (ret) - return ret; + goto out; - set_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE); - return 0; + set_inode_flag(inode, FI_VOLATILE_FILE); + f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); +out: + inode_unlock(inode); + mnt_drop_write_file(filp); + return ret; } static int f2fs_ioc_release_volatile_write(struct file *filp) { struct inode *inode = file_inode(filp); + int ret; if (!inode_owner_or_capable(inode)) return -EACCES; + ret = mnt_want_write_file(filp); + if (ret) + return ret; + + inode_lock(inode); + if (!f2fs_is_volatile_file(inode)) - return 0; + goto out; - if (!f2fs_is_first_block_written(inode)) - return truncate_partial_data_page(inode, 0, true); + if (!f2fs_is_first_block_written(inode)) { + ret = truncate_partial_data_page(inode, 0, true); + goto out; + } - return punch_hole(inode, 0, F2FS_BLKSIZE); + ret = punch_hole(inode, 0, F2FS_BLKSIZE); +out: + inode_unlock(inode); + mnt_drop_write_file(filp); + return ret; } static int f2fs_ioc_abort_volatile_write(struct file *filp) @@ -1441,13 +1654,19 @@ static int f2fs_ioc_abort_volatile_write(struct file *filp) if (ret) return ret; - f2fs_balance_fs(F2FS_I_SB(inode)); + inode_lock(inode); + + if (f2fs_is_atomic_file(inode)) + drop_inmem_pages(inode); + if (f2fs_is_volatile_file(inode)) { + clear_inode_flag(inode, FI_VOLATILE_FILE); + ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true); + } - clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE); - clear_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE); - commit_inmem_pages(inode, true); + inode_unlock(inode); mnt_drop_write_file(filp); + f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); return ret; } @@ -1457,6 +1676,7 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg) struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct super_block *sb = sbi->sb; __u32 in; + int ret; if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -1464,30 +1684,38 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg) if (get_user(in, (__u32 __user *)arg)) return -EFAULT; + ret = mnt_want_write_file(filp); + if (ret) + return ret; + switch (in) { case F2FS_GOING_DOWN_FULLSYNC: sb = freeze_bdev(sb->s_bdev); if (sb && !IS_ERR(sb)) { - f2fs_stop_checkpoint(sbi); + f2fs_stop_checkpoint(sbi, false); thaw_bdev(sb->s_bdev, sb); } break; case F2FS_GOING_DOWN_METASYNC: /* do checkpoint only */ f2fs_sync_fs(sb, 1); - f2fs_stop_checkpoint(sbi); + f2fs_stop_checkpoint(sbi, false); break; case F2FS_GOING_DOWN_NOSYNC: - f2fs_stop_checkpoint(sbi); + f2fs_stop_checkpoint(sbi, false); break; case F2FS_GOING_DOWN_METAFLUSH: sync_meta_pages(sbi, META, LONG_MAX); - f2fs_stop_checkpoint(sbi); + f2fs_stop_checkpoint(sbi, false); break; default: - return -EINVAL; + ret = -EINVAL; + goto out; } - return 0; + f2fs_update_time(sbi, REQ_TIME); +out: + mnt_drop_write_file(filp); + return ret; } static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg) @@ -1508,15 +1736,21 @@ static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg) sizeof(range))) return -EFAULT; + ret = mnt_want_write_file(filp); + if (ret) + return ret; + range.minlen = max((unsigned int)range.minlen, q->limits.discard_granularity); ret = f2fs_trim_fs(F2FS_SB(sb), &range); + mnt_drop_write_file(filp); if (ret < 0) return ret; if (copy_to_user((struct fstrim_range __user *)arg, &range, sizeof(range))) return -EFAULT; + f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); return 0; } @@ -1532,45 +1766,31 @@ static bool uuid_is_nonzero(__u8 u[16]) static int f2fs_ioc_set_encryption_policy(struct file *filp, unsigned long arg) { -#ifdef CONFIG_F2FS_FS_ENCRYPTION - struct f2fs_encryption_policy policy; + struct fscrypt_policy policy; struct inode *inode = file_inode(filp); - int err; - if (copy_from_user(&policy, (struct f2fs_encryption_policy __user *)arg, - sizeof(policy))) + if (copy_from_user(&policy, (struct fscrypt_policy __user *)arg, + sizeof(policy))) return -EFAULT; - mutex_lock(&inode->i_mutex); + f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); - err = f2fs_process_policy(&policy, inode); - - mutex_unlock(&inode->i_mutex); - - return err; -#else - return -EOPNOTSUPP; -#endif + return fscrypt_process_policy(filp, &policy); } static int f2fs_ioc_get_encryption_policy(struct file *filp, unsigned long arg) { -#ifdef CONFIG_F2FS_FS_ENCRYPTION - struct f2fs_encryption_policy policy; + struct fscrypt_policy policy; struct inode *inode = file_inode(filp); int err; - err = f2fs_get_policy(inode, &policy); + err = fscrypt_get_policy(inode, &policy); if (err) return err; - if (copy_to_user((struct f2fs_encryption_policy __user *)arg, &policy, - sizeof(policy))) + if (copy_to_user((struct fscrypt_policy __user *)arg, &policy, sizeof(policy))) return -EFAULT; return 0; -#else - return -EOPNOTSUPP; -#endif } static int f2fs_ioc_get_encryption_pwsalt(struct file *filp, unsigned long arg) @@ -1593,13 +1813,13 @@ static int f2fs_ioc_get_encryption_pwsalt(struct file *filp, unsigned long arg) generate_random_uuid(sbi->raw_super->encrypt_pw_salt); err = f2fs_commit_super(sbi, false); - - mnt_drop_write_file(filp); if (err) { /* undo new data */ memset(sbi->raw_super->encrypt_pw_salt, 0, 16); + mnt_drop_write_file(filp); return err; } + mnt_drop_write_file(filp); got_it: if (copy_to_user((__u8 __user *)arg, sbi->raw_super->encrypt_pw_salt, 16)) @@ -1612,6 +1832,7 @@ static int f2fs_ioc_gc(struct file *filp, unsigned long arg) struct inode *inode = file_inode(filp); struct f2fs_sb_info *sbi = F2FS_I_SB(inode); __u32 sync; + int ret; if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -1622,21 +1843,30 @@ static int f2fs_ioc_gc(struct file *filp, unsigned long arg) if (f2fs_readonly(sbi->sb)) return -EROFS; + ret = mnt_want_write_file(filp); + if (ret) + return ret; + if (!sync) { - if (!mutex_trylock(&sbi->gc_mutex)) - return -EBUSY; + if (!mutex_trylock(&sbi->gc_mutex)) { + ret = -EBUSY; + goto out; + } } else { mutex_lock(&sbi->gc_mutex); } - return f2fs_gc(sbi, sync); + ret = f2fs_gc(sbi, sync, true); +out: + mnt_drop_write_file(filp); + return ret; } static int f2fs_ioc_write_checkpoint(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct cp_control cpc; + int ret; if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -1644,13 +1874,343 @@ static int f2fs_ioc_write_checkpoint(struct file *filp, unsigned long arg) if (f2fs_readonly(sbi->sb)) return -EROFS; - cpc.reason = __get_cp_reason(sbi); + ret = mnt_want_write_file(filp); + if (ret) + return ret; + + ret = f2fs_sync_fs(sbi->sb, 1); - mutex_lock(&sbi->gc_mutex); - write_checkpoint(sbi, &cpc); - mutex_unlock(&sbi->gc_mutex); + mnt_drop_write_file(filp); + return ret; +} - return 0; +static int f2fs_defragment_range(struct f2fs_sb_info *sbi, + struct file *filp, + struct f2fs_defragment *range) +{ + struct inode *inode = file_inode(filp); + struct f2fs_map_blocks map = { .m_next_pgofs = NULL }; + struct extent_info ei; + pgoff_t pg_start, pg_end; + unsigned int blk_per_seg = sbi->blocks_per_seg; + unsigned int total = 0, sec_num; + unsigned int pages_per_sec = sbi->segs_per_sec * blk_per_seg; + block_t blk_end = 0; + bool fragmented = false; + int err; + + /* if in-place-update policy is enabled, don't waste time here */ + if (need_inplace_update(inode)) + return -EINVAL; + + pg_start = range->start >> PAGE_SHIFT; + pg_end = (range->start + range->len) >> PAGE_SHIFT; + + f2fs_balance_fs(sbi, true); + + inode_lock(inode); + + /* writeback all dirty pages in the range */ + err = filemap_write_and_wait_range(inode->i_mapping, range->start, + range->start + range->len - 1); + if (err) + goto out; + + /* + * lookup mapping info in extent cache, skip defragmenting if physical + * block addresses are continuous. + */ + if (f2fs_lookup_extent_cache(inode, pg_start, &ei)) { + if (ei.fofs + ei.len >= pg_end) + goto out; + } + + map.m_lblk = pg_start; + + /* + * lookup mapping info in dnode page cache, skip defragmenting if all + * physical block addresses are continuous even if there are hole(s) + * in logical blocks. + */ + while (map.m_lblk < pg_end) { + map.m_len = pg_end - map.m_lblk; + err = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_READ); + if (err) + goto out; + + if (!(map.m_flags & F2FS_MAP_FLAGS)) { + map.m_lblk++; + continue; + } + + if (blk_end && blk_end != map.m_pblk) { + fragmented = true; + break; + } + blk_end = map.m_pblk + map.m_len; + + map.m_lblk += map.m_len; + } + + if (!fragmented) + goto out; + + map.m_lblk = pg_start; + map.m_len = pg_end - pg_start; + + sec_num = (map.m_len + pages_per_sec - 1) / pages_per_sec; + + /* + * make sure there are enough free section for LFS allocation, this can + * avoid defragment running in SSR mode when free section are allocated + * intensively + */ + if (has_not_enough_free_secs(sbi, 0, sec_num)) { + err = -EAGAIN; + goto out; + } + + while (map.m_lblk < pg_end) { + pgoff_t idx; + int cnt = 0; + +do_map: + map.m_len = pg_end - map.m_lblk; + err = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_READ); + if (err) + goto clear_out; + + if (!(map.m_flags & F2FS_MAP_FLAGS)) { + map.m_lblk++; + continue; + } + + set_inode_flag(inode, FI_DO_DEFRAG); + + idx = map.m_lblk; + while (idx < map.m_lblk + map.m_len && cnt < blk_per_seg) { + struct page *page; + + page = get_lock_data_page(inode, idx, true); + if (IS_ERR(page)) { + err = PTR_ERR(page); + goto clear_out; + } + + set_page_dirty(page); + f2fs_put_page(page, 1); + + idx++; + cnt++; + total++; + } + + map.m_lblk = idx; + + if (idx < pg_end && cnt < blk_per_seg) + goto do_map; + + clear_inode_flag(inode, FI_DO_DEFRAG); + + err = filemap_fdatawrite(inode->i_mapping); + if (err) + goto out; + } +clear_out: + clear_inode_flag(inode, FI_DO_DEFRAG); +out: + inode_unlock(inode); + if (!err) + range->len = (u64)total << PAGE_SHIFT; + return err; +} + +static int f2fs_ioc_defragment(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct f2fs_defragment range; + int err; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (!S_ISREG(inode->i_mode)) + return -EINVAL; + + err = mnt_want_write_file(filp); + if (err) + return err; + + if (f2fs_readonly(sbi->sb)) { + err = -EROFS; + goto out; + } + + if (copy_from_user(&range, (struct f2fs_defragment __user *)arg, + sizeof(range))) { + err = -EFAULT; + goto out; + } + + /* verify alignment of offset & size */ + if (range.start & (F2FS_BLKSIZE - 1) || + range.len & (F2FS_BLKSIZE - 1)) { + err = -EINVAL; + goto out; + } + + err = f2fs_defragment_range(sbi, filp, &range); + f2fs_update_time(sbi, REQ_TIME); + if (err < 0) + goto out; + + if (copy_to_user((struct f2fs_defragment __user *)arg, &range, + sizeof(range))) + err = -EFAULT; +out: + mnt_drop_write_file(filp); + return err; +} + +static int f2fs_move_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, size_t len) +{ + struct inode *src = file_inode(file_in); + struct inode *dst = file_inode(file_out); + struct f2fs_sb_info *sbi = F2FS_I_SB(src); + size_t olen = len, dst_max_i_size = 0; + size_t dst_osize; + int ret; + + if (file_in->f_path.mnt != file_out->f_path.mnt || + src->i_sb != dst->i_sb) + return -EXDEV; + + if (unlikely(f2fs_readonly(src->i_sb))) + return -EROFS; + + if (!S_ISREG(src->i_mode) || !S_ISREG(dst->i_mode)) + return -EINVAL; + + if (f2fs_encrypted_inode(src) || f2fs_encrypted_inode(dst)) + return -EOPNOTSUPP; + + if (src == dst) { + if (pos_in == pos_out) + return 0; + if (pos_out > pos_in && pos_out < pos_in + len) + return -EINVAL; + } + + inode_lock(src); + if (src != dst) { + if (!inode_trylock(dst)) { + ret = -EBUSY; + goto out; + } + } + + ret = -EINVAL; + if (pos_in + len > src->i_size || pos_in + len < pos_in) + goto out_unlock; + if (len == 0) + olen = len = src->i_size - pos_in; + if (pos_in + len == src->i_size) + len = ALIGN(src->i_size, F2FS_BLKSIZE) - pos_in; + if (len == 0) { + ret = 0; + goto out_unlock; + } + + dst_osize = dst->i_size; + if (pos_out + olen > dst->i_size) + dst_max_i_size = pos_out + olen; + + /* verify the end result is block aligned */ + if (!IS_ALIGNED(pos_in, F2FS_BLKSIZE) || + !IS_ALIGNED(pos_in + len, F2FS_BLKSIZE) || + !IS_ALIGNED(pos_out, F2FS_BLKSIZE)) + goto out_unlock; + + ret = f2fs_convert_inline_inode(src); + if (ret) + goto out_unlock; + + ret = f2fs_convert_inline_inode(dst); + if (ret) + goto out_unlock; + + /* write out all dirty pages from offset */ + ret = filemap_write_and_wait_range(src->i_mapping, + pos_in, pos_in + len); + if (ret) + goto out_unlock; + + ret = filemap_write_and_wait_range(dst->i_mapping, + pos_out, pos_out + len); + if (ret) + goto out_unlock; + + f2fs_balance_fs(sbi, true); + f2fs_lock_op(sbi); + ret = __exchange_data_block(src, dst, pos_in >> F2FS_BLKSIZE_BITS, + pos_out >> F2FS_BLKSIZE_BITS, + len >> F2FS_BLKSIZE_BITS, false); + + if (!ret) { + if (dst_max_i_size) + f2fs_i_size_write(dst, dst_max_i_size); + else if (dst_osize != dst->i_size) + f2fs_i_size_write(dst, dst_osize); + } + f2fs_unlock_op(sbi); +out_unlock: + if (src != dst) + inode_unlock(dst); +out: + inode_unlock(src); + return ret; +} + +static int f2fs_ioc_move_range(struct file *filp, unsigned long arg) +{ + struct f2fs_move_range range; + struct fd dst; + int err; + + if (!(filp->f_mode & FMODE_READ) || + !(filp->f_mode & FMODE_WRITE)) + return -EBADF; + + if (copy_from_user(&range, (struct f2fs_move_range __user *)arg, + sizeof(range))) + return -EFAULT; + + dst = fdget(range.dst_fd); + if (!dst.file) + return -EBADF; + + if (!(dst.file->f_mode & FMODE_WRITE)) { + err = -EBADF; + goto err_out; + } + + err = mnt_want_write_file(filp); + if (err) + goto err_out; + + err = f2fs_move_file_range(filp, range.pos_in, dst.file, + range.pos_out, range.len); + + mnt_drop_write_file(filp); + + if (copy_to_user((struct f2fs_move_range __user *)arg, + &range, sizeof(range))) + err = -EFAULT; +err_out: + fdput(dst); + return err; } long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) @@ -1686,6 +2246,10 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return f2fs_ioc_gc(filp, arg); case F2FS_IOC_WRITE_CHECKPOINT: return f2fs_ioc_write_checkpoint(filp, arg); + case F2FS_IOC_DEFRAGMENT: + return f2fs_ioc_defragment(filp, arg); + case F2FS_IOC_MOVE_RANGE: + return f2fs_ioc_move_range(filp, arg); default: return -ENOTTY; } @@ -1693,14 +2257,39 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { - struct inode *inode = file_inode(iocb->ki_filp); + struct file *file = iocb->ki_filp; + struct inode *inode = file_inode(file); + struct blk_plug plug; + ssize_t ret; if (f2fs_encrypted_inode(inode) && - !f2fs_has_encryption_key(inode) && - f2fs_get_encryption_info(inode)) + !fscrypt_has_encryption_key(inode) && + fscrypt_get_encryption_info(inode)) return -EACCES; - return generic_file_write_iter(iocb, from); + inode_lock(inode); + ret = generic_write_checks(iocb, from); + if (ret > 0) { + int err = f2fs_preallocate_blocks(iocb, from); + + if (err) { + inode_unlock(inode); + return err; + } + blk_start_plug(&plug); + ret = __generic_file_write_iter(iocb, from); + blk_finish_plug(&plug); + } + inode_unlock(inode); + + if (ret > 0) { + ssize_t err; + + err = generic_write_sync(file, iocb->ki_pos - ret, ret); + if (err < 0) + ret = err; + } + return ret; } #ifdef CONFIG_COMPAT @@ -1713,6 +2302,24 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case F2FS_IOC32_SETFLAGS: cmd = F2FS_IOC_SETFLAGS; break; + case F2FS_IOC32_GETVERSION: + cmd = F2FS_IOC_GETVERSION; + break; + case F2FS_IOC_START_ATOMIC_WRITE: + case F2FS_IOC_COMMIT_ATOMIC_WRITE: + case F2FS_IOC_START_VOLATILE_WRITE: + case F2FS_IOC_RELEASE_VOLATILE_WRITE: + case F2FS_IOC_ABORT_VOLATILE_WRITE: + case F2FS_IOC_SHUTDOWN: + case F2FS_IOC_SET_ENCRYPTION_POLICY: + case F2FS_IOC_GET_ENCRYPTION_PWSALT: + case F2FS_IOC_GET_ENCRYPTION_POLICY: + case F2FS_IOC_GARBAGE_COLLECT: + case F2FS_IOC_WRITE_CHECKPOINT: + case F2FS_IOC_DEFRAGMENT: + break; + case F2FS_IOC_MOVE_RANGE: + break; default: return -ENOIOCTLCMD; } diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index fedbf67a0842..6390d45c1b68 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -16,7 +16,6 @@ #include <linux/kthread.h> #include <linux/delay.h> #include <linux/freezer.h> -#include <linux/blkdev.h> #include "f2fs.h" #include "node.h" @@ -48,6 +47,11 @@ static int gc_thread_func(void *data) continue; } +#ifdef CONFIG_F2FS_FAULT_INJECTION + if (time_to_inject(sbi, FAULT_CHECKPOINT)) + f2fs_stop_checkpoint(sbi, false); +#endif + /* * [GC triggering condition] * 0. GC is not conducted currently. @@ -78,7 +82,7 @@ static int gc_thread_func(void *data) stat_inc_bggc_count(sbi); /* if return value is not zero, no victim was selected */ - if (f2fs_gc(sbi, test_opt(sbi, FORCE_FG_GC))) + if (f2fs_gc(sbi, test_opt(sbi, FORCE_FG_GC), true)) wait_ms = gc_th->no_gc_sleep_time; trace_f2fs_background_gc(sbi->sb, wait_ms, @@ -97,7 +101,7 @@ int start_gc_thread(struct f2fs_sb_info *sbi) dev_t dev = sbi->sb->s_bdev->bd_dev; int err = 0; - gc_th = kmalloc(sizeof(struct f2fs_gc_kthread), GFP_KERNEL); + gc_th = f2fs_kmalloc(sbi, sizeof(struct f2fs_gc_kthread), GFP_KERNEL); if (!gc_th) { err = -ENOMEM; goto out; @@ -173,9 +177,9 @@ static unsigned int get_max_cost(struct f2fs_sb_info *sbi, { /* SSR allocates in a segment unit */ if (p->alloc_mode == SSR) - return 1 << sbi->log_blocks_per_seg; + return sbi->blocks_per_seg; if (p->gc_mode == GC_GREEDY) - return (1 << sbi->log_blocks_per_seg) * p->ofs_unit; + return sbi->blocks_per_seg * p->ofs_unit; else if (p->gc_mode == GC_CB) return UINT_MAX; else /* No other gc_mode */ @@ -246,6 +250,18 @@ static inline unsigned int get_gc_cost(struct f2fs_sb_info *sbi, return get_cb_cost(sbi, segno); } +static unsigned int count_bits(const unsigned long *addr, + unsigned int offset, unsigned int len) +{ + unsigned int end = offset + len, sum = 0; + + while (offset < end) { + if (test_bit(offset++, addr)) + ++sum; + } + return sum; +} + /* * This function is called from two paths. * One is garbage collection and the other is SSR segment selection. @@ -259,9 +275,9 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi, { struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); struct victim_sel_policy p; - unsigned int secno, max_cost; + unsigned int secno, last_victim; unsigned int last_segment = MAIN_SEGS(sbi); - int nsearched = 0; + unsigned int nsearched = 0; mutex_lock(&dirty_i->seglist_lock); @@ -269,11 +285,12 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi, select_policy(sbi, gc_type, type, &p); p.min_segno = NULL_SEGNO; - p.min_cost = max_cost = get_max_cost(sbi, &p); + p.min_cost = get_max_cost(sbi, &p); if (p.max_search == 0) goto out; + last_victim = sbi->last_victim[p.gc_mode]; if (p.alloc_mode == LFS && gc_type == FG_GC) { p.min_segno = check_bg_victims(sbi); if (p.min_segno != NULL_SEGNO) @@ -296,27 +313,35 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi, } p.offset = segno + p.ofs_unit; - if (p.ofs_unit > 1) + if (p.ofs_unit > 1) { p.offset -= segno % p.ofs_unit; + nsearched += count_bits(p.dirty_segmap, + p.offset - p.ofs_unit, + p.ofs_unit); + } else { + nsearched++; + } + secno = GET_SECNO(sbi, segno); if (sec_usage_check(sbi, secno)) - continue; + goto next; if (gc_type == BG_GC && test_bit(secno, dirty_i->victim_secmap)) - continue; + goto next; cost = get_gc_cost(sbi, segno, &p); if (p.min_cost > cost) { p.min_segno = segno; p.min_cost = cost; - } else if (unlikely(cost == max_cost)) { - continue; } - - if (nsearched++ >= p.max_search) { - sbi->last_victim[p.gc_mode] = segno; +next: + if (nsearched >= p.max_search) { + if (!sbi->last_victim[p.gc_mode] && segno <= last_victim) + sbi->last_victim[p.gc_mode] = last_victim + 1; + else + sbi->last_victim[p.gc_mode] = segno + 1; break; } } @@ -400,13 +425,13 @@ static int check_valid_map(struct f2fs_sb_info *sbi, * On validity, copy that node with cold status, otherwise (invalid node) * ignore that. */ -static int gc_node_segment(struct f2fs_sb_info *sbi, +static void gc_node_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, unsigned int segno, int gc_type) { - bool initial = true; struct f2fs_summary *entry; block_t start_addr; int off; + int phase = 0; start_addr = START_BLOCK(sbi, segno); @@ -419,16 +444,24 @@ next_step: struct node_info ni; /* stop BG_GC if there is not enough free sections. */ - if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0)) - return 0; + if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0, 0)) + return; if (check_valid_map(sbi, segno, off) == 0) continue; - if (initial) { + if (phase == 0) { + ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), 1, + META_NAT, true); + continue; + } + + if (phase == 1) { ra_node_page(sbi, nid); continue; } + + /* phase == 2 */ node_page = get_node_page(sbi, nid); if (IS_ERR(node_page)) continue; @@ -445,36 +478,12 @@ next_step: continue; } - /* set page dirty and write it */ - if (gc_type == FG_GC) { - f2fs_wait_on_page_writeback(node_page, NODE); - set_page_dirty(node_page); - } else { - if (!PageWriteback(node_page)) - set_page_dirty(node_page); - } - f2fs_put_page(node_page, 1); + move_node_page(node_page, gc_type); stat_inc_node_blk_count(sbi, 1, gc_type); } - if (initial) { - initial = false; + if (++phase < 3) goto next_step; - } - - if (gc_type == FG_GC) { - struct writeback_control wbc = { - .sync_mode = WB_SYNC_ALL, - .nr_to_write = LONG_MAX, - .for_reclaim = 0, - }; - sync_node_pages(sbi, 0, &wbc); - - /* return 1 only if FG_GC succefully reclaimed one */ - if (get_valid_blocks(sbi, segno, 1) == 0) - return 1; - } - return 0; } /* @@ -484,7 +493,7 @@ next_step: * as indirect or double indirect node blocks, are given, it must be a caller's * bug. */ -block_t start_bidx_of_node(unsigned int node_ofs, struct f2fs_inode_info *fi) +block_t start_bidx_of_node(unsigned int node_ofs, struct inode *inode) { unsigned int indirect_blks = 2 * NIDS_PER_BLOCK + 4; unsigned int bidx; @@ -501,7 +510,7 @@ block_t start_bidx_of_node(unsigned int node_ofs, struct f2fs_inode_info *fi) int dec = (node_ofs - indirect_blks - 3) / (NIDS_PER_BLOCK + 1); bidx = node_ofs - 5 - dec; } - return bidx * ADDRS_PER_BLOCK + ADDRS_PER_INODE(fi); + return bidx * ADDRS_PER_BLOCK + ADDRS_PER_INODE(inode); } static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, @@ -535,7 +544,8 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, return true; } -static void move_encrypted_block(struct inode *inode, block_t bidx) +static void move_encrypted_block(struct inode *inode, block_t bidx, + unsigned int segno, int off) { struct f2fs_io_info fio = { .sbi = F2FS_I_SB(inode), @@ -547,6 +557,7 @@ static void move_encrypted_block(struct inode *inode, block_t bidx) struct f2fs_summary sum; struct node_info ni; struct page *page; + block_t newaddr; int err; /* do not read out */ @@ -554,6 +565,9 @@ static void move_encrypted_block(struct inode *inode, block_t bidx) if (!page) return; + if (!check_valid_map(F2FS_I_SB(inode), segno, off)) + goto out; + set_new_dnode(&dn, inode, NULL, NULL, 0); err = get_dnode_of_data(&dn, bidx, LOOKUP_NODE); if (err) @@ -568,21 +582,24 @@ static void move_encrypted_block(struct inode *inode, block_t bidx) * don't cache encrypted data into meta inode until previous dirty * data were writebacked to avoid racing between GC and flush. */ - f2fs_wait_on_page_writeback(page, DATA); + f2fs_wait_on_page_writeback(page, DATA, true); get_node_info(fio.sbi, dn.nid, &ni); set_summary(&sum, dn.nid, dn.ofs_in_node, ni.version); /* read page */ fio.page = page; - fio.blk_addr = dn.data_blkaddr; + fio.new_blkaddr = fio.old_blkaddr = dn.data_blkaddr; - fio.encrypted_page = pagecache_get_page(META_MAPPING(fio.sbi), - fio.blk_addr, - FGP_LOCK|FGP_CREAT, - GFP_NOFS); - if (!fio.encrypted_page) - goto put_out; + allocate_data_block(fio.sbi, NULL, fio.old_blkaddr, &newaddr, + &sum, CURSEG_COLD_DATA); + + fio.encrypted_page = pagecache_get_page(META_MAPPING(fio.sbi), newaddr, + FGP_LOCK | FGP_CREAT, GFP_NOFS); + if (!fio.encrypted_page) { + err = -ENOMEM; + goto recover_block; + } err = f2fs_submit_page_bio(&fio); if (err) @@ -591,40 +608,47 @@ static void move_encrypted_block(struct inode *inode, block_t bidx) /* write page */ lock_page(fio.encrypted_page); - if (unlikely(!PageUptodate(fio.encrypted_page))) + if (unlikely(fio.encrypted_page->mapping != META_MAPPING(fio.sbi))) { + err = -EIO; goto put_page_out; - if (unlikely(fio.encrypted_page->mapping != META_MAPPING(fio.sbi))) + } + if (unlikely(!PageUptodate(fio.encrypted_page))) { + err = -EIO; goto put_page_out; + } set_page_dirty(fio.encrypted_page); - f2fs_wait_on_page_writeback(fio.encrypted_page, DATA); + f2fs_wait_on_page_writeback(fio.encrypted_page, DATA, true); if (clear_page_dirty_for_io(fio.encrypted_page)) dec_page_count(fio.sbi, F2FS_DIRTY_META); set_page_writeback(fio.encrypted_page); /* allocate block address */ - f2fs_wait_on_page_writeback(dn.node_page, NODE); - allocate_data_block(fio.sbi, NULL, fio.blk_addr, - &fio.blk_addr, &sum, CURSEG_COLD_DATA); + f2fs_wait_on_page_writeback(dn.node_page, NODE, true); + fio.rw = WRITE_SYNC; + fio.new_blkaddr = newaddr; f2fs_submit_page_mbio(&fio); - dn.data_blkaddr = fio.blk_addr; - set_data_blkaddr(&dn); - f2fs_update_extent_cache(&dn); - set_inode_flag(F2FS_I(inode), FI_APPEND_WRITE); + f2fs_update_data_blkaddr(&dn, newaddr); + set_inode_flag(inode, FI_APPEND_WRITE); if (page->index == 0) - set_inode_flag(F2FS_I(inode), FI_FIRST_BLOCK_WRITTEN); + set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN); put_page_out: f2fs_put_page(fio.encrypted_page, 1); +recover_block: + if (err) + __f2fs_replace_block(fio.sbi, &sum, newaddr, fio.old_blkaddr, + true, true); put_out: f2fs_put_dnode(&dn); out: f2fs_put_page(page, 1); } -static void move_data_page(struct inode *inode, block_t bidx, int gc_type) +static void move_data_page(struct inode *inode, block_t bidx, int gc_type, + unsigned int segno, int off) { struct page *page; @@ -632,6 +656,9 @@ static void move_data_page(struct inode *inode, block_t bidx, int gc_type) if (IS_ERR(page)) return; + if (!check_valid_map(F2FS_I_SB(inode), segno, off)) + goto out; + if (gc_type == BG_GC) { if (PageWriteback(page)) goto out; @@ -645,13 +672,24 @@ static void move_data_page(struct inode *inode, block_t bidx, int gc_type) .page = page, .encrypted_page = NULL, }; + bool is_dirty = PageDirty(page); + int err; + +retry: set_page_dirty(page); - f2fs_wait_on_page_writeback(page, DATA); - if (clear_page_dirty_for_io(page)) + f2fs_wait_on_page_writeback(page, DATA, true); + if (clear_page_dirty_for_io(page)) { inode_dec_dirty_pages(inode); + remove_dirty_inode(inode); + } + set_cold_data(page); - do_write_data_page(&fio); - clear_cold_data(page); + + err = do_write_data_page(&fio); + if (err == -ENOMEM && is_dirty) { + congestion_wait(BLK_RW_ASYNC, HZ/50); + goto retry; + } } out: f2fs_put_page(page, 1); @@ -664,7 +702,7 @@ out: * If the parent node is not valid or the data block address is different, * the victim data block is ignored. */ -static int gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, +static void gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, struct gc_inode_list *gc_list, unsigned int segno, int gc_type) { struct super_block *sb = sbi->sb; @@ -684,16 +722,23 @@ next_step: struct node_info dni; /* dnode info for the data */ unsigned int ofs_in_node, nofs; block_t start_bidx; + nid_t nid = le32_to_cpu(entry->nid); /* stop BG_GC if there is not enough free sections. */ - if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0)) - return 0; + if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0, 0)) + return; if (check_valid_map(sbi, segno, off) == 0) continue; if (phase == 0) { - ra_node_page(sbi, le32_to_cpu(entry->nid)); + ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), 1, + META_NAT, true); + continue; + } + + if (phase == 1) { + ra_node_page(sbi, nid); continue; } @@ -701,14 +746,14 @@ next_step: if (!is_alive(sbi, entry, &dni, start_addr + off, &nofs)) continue; - if (phase == 1) { + if (phase == 2) { ra_node_page(sbi, dni.ino); continue; } ofs_in_node = le16_to_cpu(entry->ofs_in_node); - if (phase == 2) { + if (phase == 3) { inode = f2fs_iget(sb, dni.ino); if (IS_ERR(inode) || is_bad_inode(inode)) continue; @@ -720,7 +765,7 @@ next_step: continue; } - start_bidx = start_bidx_of_node(nofs, F2FS_I(inode)); + start_bidx = start_bidx_of_node(nofs, inode); data_page = get_read_data_page(inode, start_bidx + ofs_in_node, READA, true); if (IS_ERR(data_page)) { @@ -733,30 +778,41 @@ next_step: continue; } - /* phase 3 */ + /* phase 4 */ inode = find_gc_inode(gc_list, dni.ino); if (inode) { - start_bidx = start_bidx_of_node(nofs, F2FS_I(inode)) + struct f2fs_inode_info *fi = F2FS_I(inode); + bool locked = false; + + if (S_ISREG(inode->i_mode)) { + if (!down_write_trylock(&fi->dio_rwsem[READ])) + continue; + if (!down_write_trylock( + &fi->dio_rwsem[WRITE])) { + up_write(&fi->dio_rwsem[READ]); + continue; + } + locked = true; + } + + start_bidx = start_bidx_of_node(nofs, inode) + ofs_in_node; if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) - move_encrypted_block(inode, start_bidx); + move_encrypted_block(inode, start_bidx, segno, off); else - move_data_page(inode, start_bidx, gc_type); + move_data_page(inode, start_bidx, gc_type, segno, off); + + if (locked) { + up_write(&fi->dio_rwsem[WRITE]); + up_write(&fi->dio_rwsem[READ]); + } + stat_inc_data_blk_count(sbi, 1, gc_type); } } - if (++phase < 4) + if (++phase < 5) goto next_step; - - if (gc_type == FG_GC) { - f2fs_submit_merged_bio(sbi, DATA, WRITE); - - /* return 1 only if FG_GC succefully reclaimed one */ - if (get_valid_blocks(sbi, segno, 1) == 0) - return 1; - } - return 0; } static int __get_victim(struct f2fs_sb_info *sbi, unsigned int *victim, @@ -772,51 +828,84 @@ static int __get_victim(struct f2fs_sb_info *sbi, unsigned int *victim, return ret; } -static int do_garbage_collect(struct f2fs_sb_info *sbi, unsigned int segno, +static int do_garbage_collect(struct f2fs_sb_info *sbi, + unsigned int start_segno, struct gc_inode_list *gc_list, int gc_type) { struct page *sum_page; struct f2fs_summary_block *sum; struct blk_plug plug; - int nfree = 0; + unsigned int segno = start_segno; + unsigned int end_segno = start_segno + sbi->segs_per_sec; + int sec_freed = 0; + unsigned char type = IS_DATASEG(get_seg_entry(sbi, segno)->type) ? + SUM_TYPE_DATA : SUM_TYPE_NODE; + + /* readahead multi ssa blocks those have contiguous address */ + if (sbi->segs_per_sec > 1) + ra_meta_pages(sbi, GET_SUM_BLOCK(sbi, segno), + sbi->segs_per_sec, META_SSA, true); - /* read segment summary of victim */ - sum_page = get_sum_page(sbi, segno); + /* reference all summary page */ + while (segno < end_segno) { + sum_page = get_sum_page(sbi, segno++); + unlock_page(sum_page); + } blk_start_plug(&plug); - sum = page_address(sum_page); + for (segno = start_segno; segno < end_segno; segno++) { - /* - * this is to avoid deadlock: - * - lock_page(sum_page) - f2fs_replace_block - * - check_valid_map() - mutex_lock(sentry_lock) - * - mutex_lock(sentry_lock) - change_curseg() - * - lock_page(sum_page) - */ - unlock_page(sum_page); - - switch (GET_SUM_TYPE((&sum->footer))) { - case SUM_TYPE_NODE: - nfree = gc_node_segment(sbi, sum->entries, segno, gc_type); - break; - case SUM_TYPE_DATA: - nfree = gc_data_segment(sbi, sum->entries, gc_list, - segno, gc_type); - break; + /* find segment summary of victim */ + sum_page = find_get_page(META_MAPPING(sbi), + GET_SUM_BLOCK(sbi, segno)); + f2fs_put_page(sum_page, 0); + + if (get_valid_blocks(sbi, segno, 1) == 0 || + !PageUptodate(sum_page) || + unlikely(f2fs_cp_error(sbi))) + goto next; + + sum = page_address(sum_page); + f2fs_bug_on(sbi, type != GET_SUM_TYPE((&sum->footer))); + + /* + * this is to avoid deadlock: + * - lock_page(sum_page) - f2fs_replace_block + * - check_valid_map() - mutex_lock(sentry_lock) + * - mutex_lock(sentry_lock) - change_curseg() + * - lock_page(sum_page) + */ + + if (type == SUM_TYPE_NODE) + gc_node_segment(sbi, sum->entries, segno, gc_type); + else + gc_data_segment(sbi, sum->entries, gc_list, segno, + gc_type); + + stat_inc_seg_count(sbi, type, gc_type); +next: + f2fs_put_page(sum_page, 0); } + + if (gc_type == FG_GC) + f2fs_submit_merged_bio(sbi, + (type == SUM_TYPE_NODE) ? NODE : DATA, WRITE); + blk_finish_plug(&plug); - stat_inc_seg_count(sbi, GET_SUM_TYPE((&sum->footer)), gc_type); + if (gc_type == FG_GC && + get_valid_blocks(sbi, start_segno, sbi->segs_per_sec) == 0) + sec_freed = 1; + stat_inc_call_count(sbi->stat_info); - f2fs_put_page(sum_page, 0); - return nfree; + return sec_freed; } -int f2fs_gc(struct f2fs_sb_info *sbi, bool sync) +int f2fs_gc(struct f2fs_sb_info *sbi, bool sync, bool background) { - unsigned int segno, i; + unsigned int segno; int gc_type = sync ? FG_GC : BG_GC; int sec_freed = 0; int ret = -EINVAL; @@ -832,46 +921,51 @@ gc_more: if (unlikely(!(sbi->sb->s_flags & MS_ACTIVE))) goto stop; - if (unlikely(f2fs_cp_error(sbi))) + if (unlikely(f2fs_cp_error(sbi))) { + ret = -EIO; goto stop; + } - if (gc_type == BG_GC && has_not_enough_free_secs(sbi, sec_freed)) { + if (gc_type == BG_GC && has_not_enough_free_secs(sbi, sec_freed, 0)) { gc_type = FG_GC; - if (__get_victim(sbi, &segno, gc_type) || prefree_segments(sbi)) - write_checkpoint(sbi, &cpc); + /* + * If there is no victim and no prefree segment but still not + * enough free sections, we should flush dent/node blocks and do + * garbage collections. + */ + if (__get_victim(sbi, &segno, gc_type) || + prefree_segments(sbi)) { + ret = write_checkpoint(sbi, &cpc); + if (ret) + goto stop; + segno = NULL_SEGNO; + } else if (has_not_enough_free_secs(sbi, 0, 0)) { + ret = write_checkpoint(sbi, &cpc); + if (ret) + goto stop; + } + } else if (gc_type == BG_GC && !background) { + /* f2fs_balance_fs doesn't need to do BG_GC in critical path. */ + goto stop; } if (segno == NULL_SEGNO && !__get_victim(sbi, &segno, gc_type)) goto stop; ret = 0; - /* readahead multi ssa blocks those have contiguous address */ - if (sbi->segs_per_sec > 1) - ra_meta_pages(sbi, GET_SUM_BLOCK(sbi, segno), sbi->segs_per_sec, - META_SSA, true); - - for (i = 0; i < sbi->segs_per_sec; i++) { - /* - * for FG_GC case, halt gcing left segments once failed one - * of segments in selected section to avoid long latency. - */ - if (!do_garbage_collect(sbi, segno + i, &gc_list, gc_type) && - gc_type == FG_GC) - break; - } - - if (i == sbi->segs_per_sec && gc_type == FG_GC) + if (do_garbage_collect(sbi, segno, &gc_list, gc_type) && + gc_type == FG_GC) sec_freed++; if (gc_type == FG_GC) sbi->cur_victim_sec = NULL_SEGNO; if (!sync) { - if (has_not_enough_free_secs(sbi, sec_freed)) + if (has_not_enough_free_secs(sbi, sec_freed, 0)) goto gc_more; if (gc_type == FG_GC) - write_checkpoint(sbi, &cpc); + ret = write_checkpoint(sbi, &cpc); } stop: mutex_unlock(&sbi->gc_mutex); diff --git a/fs/f2fs/gc.h b/fs/f2fs/gc.h index b4a65be9f7d3..a993967dcdb9 100644 --- a/fs/f2fs/gc.h +++ b/fs/f2fs/gc.h @@ -100,11 +100,3 @@ static inline bool has_enough_invalid_blocks(struct f2fs_sb_info *sbi) return true; return false; } - -static inline int is_idle(struct f2fs_sb_info *sbi) -{ - struct block_device *bdev = sbi->sb->s_bdev; - struct request_queue *q = bdev_get_queue(bdev); - struct request_list *rl = &q->root_rl; - return !(rl->count[BLK_RW_SYNC]) && !(rl->count[BLK_RW_ASYNC]); -} diff --git a/fs/f2fs/hash.c b/fs/f2fs/hash.c index b238d2fec3e5..71b7206c431e 100644 --- a/fs/f2fs/hash.c +++ b/fs/f2fs/hash.c @@ -70,8 +70,7 @@ static void str2hashbuf(const unsigned char *msg, size_t len, *buf++ = pad; } -f2fs_hash_t f2fs_dentry_hash(const struct qstr *name_info, - struct f2fs_filename *fname) +f2fs_hash_t f2fs_dentry_hash(const struct qstr *name_info) { __u32 hash; f2fs_hash_t f2fs_hash; @@ -80,10 +79,6 @@ f2fs_hash_t f2fs_dentry_hash(const struct qstr *name_info, const unsigned char *name = name_info->name; size_t len = name_info->len; - /* encrypted bigname case */ - if (fname && !fname->disk_name.name) - return cpu_to_le32(fname->hash); - if (is_dot_dotdot(name_info)) return 0; diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index f35f3eb3541f..b85987703d1e 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -17,9 +17,6 @@ bool f2fs_may_inline_data(struct inode *inode) { - if (!test_opt(F2FS_I_SB(inode), INLINE_DATA)) - return false; - if (f2fs_is_atomic_file(inode)) return false; @@ -55,7 +52,7 @@ void read_inline_data(struct page *page, struct page *ipage) f2fs_bug_on(F2FS_P_SB(page), page->index); - zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_SIZE); + zero_user_segment(page, MAX_INLINE_DATA, PAGE_SIZE); /* Copy the whole inline data block */ src_addr = inline_data_addr(ipage); @@ -63,7 +60,8 @@ void read_inline_data(struct page *page, struct page *ipage) memcpy(dst_addr, src_addr, MAX_INLINE_DATA); flush_dcache_page(page); kunmap_atomic(dst_addr); - SetPageUptodate(page); + if (!PageUptodate(page)) + SetPageUptodate(page); } bool truncate_inline_inode(struct page *ipage, u64 from) @@ -75,9 +73,9 @@ bool truncate_inline_inode(struct page *ipage, u64 from) addr = inline_data_addr(ipage); - f2fs_wait_on_page_writeback(ipage, NODE); + f2fs_wait_on_page_writeback(ipage, NODE, true); memset(addr + from, 0, MAX_INLINE_DATA - from); - + set_page_dirty(ipage); return true; } @@ -112,11 +110,12 @@ int f2fs_read_inline_data(struct inode *inode, struct page *page) } if (page->index) - zero_user_segment(page, 0, PAGE_CACHE_SIZE); + zero_user_segment(page, 0, PAGE_SIZE); else read_inline_data(page, ipage); - SetPageUptodate(page); + if (!PageUptodate(page)) + SetPageUptodate(page); f2fs_put_page(ipage, 1); trace_android_fs_dataread_end(inode, page_offset(page), PAGE_SIZE); @@ -126,7 +125,6 @@ int f2fs_read_inline_data(struct inode *inode, struct page *page) int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page) { - void *src_addr, *dst_addr; struct f2fs_io_info fio = { .sbi = F2FS_I_SB(dn->inode), .type = DATA, @@ -136,8 +134,6 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page) }; int dirty, err; - f2fs_bug_on(F2FS_I_SB(dn->inode), page->index); - if (!f2fs_exist_data(dn->inode)) goto clear_out; @@ -145,21 +141,9 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page) if (err) return err; - f2fs_wait_on_page_writeback(page, DATA); + f2fs_bug_on(F2FS_P_SB(page), PageWriteback(page)); - if (PageUptodate(page)) - goto no_update; - - zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_SIZE); - - /* Copy the whole inline data block */ - src_addr = inline_data_addr(dn->inode_page); - dst_addr = kmap_atomic(page); - memcpy(dst_addr, src_addr, MAX_INLINE_DATA); - flush_dcache_page(page); - kunmap_atomic(dst_addr); - SetPageUptodate(page); -no_update: + read_inline_data(page, dn->inode_page); set_page_dirty(page); /* clear dirty state */ @@ -167,23 +151,23 @@ no_update: /* write data page to try to make data consistent */ set_page_writeback(page); - fio.blk_addr = dn->data_blkaddr; + fio.old_blkaddr = dn->data_blkaddr; write_data_page(dn, &fio); - set_data_blkaddr(dn); - f2fs_update_extent_cache(dn); - f2fs_wait_on_page_writeback(page, DATA); - if (dirty) + f2fs_wait_on_page_writeback(page, DATA, true); + if (dirty) { inode_dec_dirty_pages(dn->inode); + remove_dirty_inode(dn->inode); + } /* this converted inline_data should be recovered. */ - set_inode_flag(F2FS_I(dn->inode), FI_APPEND_WRITE); + set_inode_flag(dn->inode, FI_APPEND_WRITE); /* clear inline data and flag after data writeback */ truncate_inline_inode(dn->inode_page, 0); + clear_inline_node(dn->inode_page); clear_out: stat_dec_inline_inode(dn->inode); f2fs_clear_inline_inode(dn->inode); - sync_inode_page(dn); f2fs_put_dnode(dn); return 0; } @@ -195,7 +179,10 @@ int f2fs_convert_inline_inode(struct inode *inode) struct page *ipage, *page; int err = 0; - page = grab_cache_page(inode->i_mapping, 0); + if (!f2fs_has_inline_data(inode)) + return 0; + + page = f2fs_grab_cache_page(inode->i_mapping, 0, false); if (!page) return -ENOMEM; @@ -217,6 +204,9 @@ out: f2fs_unlock_op(sbi); f2fs_put_page(page, 1); + + f2fs_balance_fs(sbi, dn.node_changed); + return err; } @@ -238,16 +228,17 @@ int f2fs_write_inline_data(struct inode *inode, struct page *page) f2fs_bug_on(F2FS_I_SB(inode), page->index); - f2fs_wait_on_page_writeback(dn.inode_page, NODE); + f2fs_wait_on_page_writeback(dn.inode_page, NODE, true); src_addr = kmap_atomic(page); dst_addr = inline_data_addr(dn.inode_page); memcpy(dst_addr, src_addr, MAX_INLINE_DATA); kunmap_atomic(src_addr); + set_page_dirty(dn.inode_page); - set_inode_flag(F2FS_I(inode), FI_APPEND_WRITE); - set_inode_flag(F2FS_I(inode), FI_DATA_EXIST); + set_inode_flag(inode, FI_APPEND_WRITE); + set_inode_flag(inode, FI_DATA_EXIST); - sync_inode_page(&dn); + clear_inline_node(dn.inode_page); f2fs_put_dnode(&dn); return 0; } @@ -276,16 +267,16 @@ process_inline: ipage = get_node_page(sbi, inode->i_ino); f2fs_bug_on(sbi, IS_ERR(ipage)); - f2fs_wait_on_page_writeback(ipage, NODE); + f2fs_wait_on_page_writeback(ipage, NODE, true); src_addr = inline_data_addr(npage); dst_addr = inline_data_addr(ipage); memcpy(dst_addr, src_addr, MAX_INLINE_DATA); - set_inode_flag(F2FS_I(inode), FI_INLINE_DATA); - set_inode_flag(F2FS_I(inode), FI_DATA_EXIST); + set_inode_flag(inode, FI_INLINE_DATA); + set_inode_flag(inode, FI_DATA_EXIST); - update_inode(inode, ipage); + set_page_dirty(ipage); f2fs_put_page(ipage, 1); return true; } @@ -296,7 +287,6 @@ process_inline: if (!truncate_inline_inode(ipage, 0)) return false; f2fs_clear_inline_inode(inode); - update_inode(inode, ipage); f2fs_put_page(ipage, 1); } else if (ri && (ri->i_inline & F2FS_INLINE_DATA)) { if (truncate_blocks(inode, 0, false)) @@ -307,7 +297,7 @@ process_inline: } struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir, - struct f2fs_filename *fname, struct page **res_page) + struct fscrypt_name *fname, struct page **res_page) { struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb); struct f2fs_inline_dentry *inline_dentry; @@ -318,10 +308,12 @@ struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir, f2fs_hash_t namehash; ipage = get_node_page(sbi, dir->i_ino); - if (IS_ERR(ipage)) + if (IS_ERR(ipage)) { + *res_page = ipage; return NULL; + } - namehash = f2fs_dentry_hash(&name, fname); + namehash = f2fs_dentry_hash(&name); inline_dentry = inline_data_addr(ipage); @@ -333,30 +325,6 @@ struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir, else f2fs_put_page(ipage, 0); - /* - * For the most part, it should be a bug when name_len is zero. - * We stop here for figuring out where the bugs has occurred. - */ - f2fs_bug_on(sbi, d.max < 0); - return de; -} - -struct f2fs_dir_entry *f2fs_parent_inline_dir(struct inode *dir, - struct page **p) -{ - struct f2fs_sb_info *sbi = F2FS_I_SB(dir); - struct page *ipage; - struct f2fs_dir_entry *de; - struct f2fs_inline_dentry *dentry_blk; - - ipage = get_node_page(sbi, dir->i_ino); - if (IS_ERR(ipage)) - return NULL; - - dentry_blk = inline_data_addr(ipage); - de = &dentry_blk->dentry[1]; - *p = ipage; - unlock_page(ipage); return de; } @@ -374,10 +342,8 @@ int make_empty_inline_dir(struct inode *inode, struct inode *parent, set_page_dirty(ipage); /* update i_size to MAX_INLINE_DATA */ - if (i_size_read(inode) < MAX_INLINE_DATA) { - i_size_write(inode, MAX_INLINE_DATA); - set_inode_flag(F2FS_I(inode), FI_UPDATE_DIR); - } + if (i_size_read(inode) < MAX_INLINE_DATA) + f2fs_i_size_write(inode, MAX_INLINE_DATA); return 0; } @@ -385,7 +351,7 @@ 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; @@ -393,7 +359,7 @@ static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage, struct f2fs_dentry_block *dentry_blk; int err; - page = grab_cache_page(dir->i_mapping, 0); + page = f2fs_grab_cache_page(dir->i_mapping, 0, false); if (!page) { f2fs_put_page(ipage, 1); return -ENOMEM; @@ -404,8 +370,8 @@ static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage, if (err) goto out; - f2fs_wait_on_page_writeback(page, DATA); - zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_SIZE); + f2fs_wait_on_page_writeback(page, DATA, true); + zero_user_segment(page, MAX_INLINE_DATA, PAGE_SIZE); dentry_blk = kmap_atomic(page); @@ -426,37 +392,132 @@ static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage, NR_INLINE_DENTRY * F2FS_SLOT_LEN); kunmap_atomic(dentry_blk); - SetPageUptodate(page); + if (!PageUptodate(page)) + SetPageUptodate(page); set_page_dirty(page); /* clear inline dir and flag after data writeback */ truncate_inline_inode(ipage, 0); stat_dec_inline_dir(dir); - clear_inode_flag(F2FS_I(dir), FI_INLINE_DENTRY); + clear_inode_flag(dir, FI_INLINE_DENTRY); - if (i_size_read(dir) < PAGE_CACHE_SIZE) { - i_size_write(dir, PAGE_CACHE_SIZE); - set_inode_flag(F2FS_I(dir), FI_UPDATE_DIR); - } - - sync_inode_page(&dn); + f2fs_i_depth_write(dir, 1); + if (i_size_read(dir) < PAGE_SIZE) + f2fs_i_size_write(dir, PAGE_SIZE); out: f2fs_put_page(page, 1); return err; } -int f2fs_add_inline_entry(struct inode *dir, const struct qstr *name, - struct inode *inode, nid_t ino, umode_t mode) +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]; + + if (unlikely(!de->name_len)) { + bit_pos++; + continue; + } + + new_name.name = d.filename[bit_pos]; + new_name.len = le16_to_cpu(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, NULL, + ino, fake_mode); + if (err) + goto punch_dentry_pages; + + 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_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 = f2fs_kmalloc(F2FS_I_SB(dir), + sizeof(struct f2fs_inline_dentry), GFP_F2FS_ZERO); + if (!backup_dentry) { + f2fs_put_page(ipage, 1); + 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(dir, FI_INLINE_DENTRY); + kfree(backup_dentry); + return 0; +recover: + lock_page(ipage); + memcpy(inline_dentry, backup_dentry, MAX_INLINE_DATA); + f2fs_i_depth_write(dir, 0); + f2fs_i_size_write(dir, MAX_INLINE_DATA); + set_page_dirty(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 *new_name, + const struct qstr *orig_name, + struct inode *inode, nid_t ino, umode_t mode) { struct f2fs_sb_info *sbi = F2FS_I_SB(dir); struct page *ipage; unsigned int bit_pos; f2fs_hash_t name_hash; - size_t namelen = name->len; struct f2fs_inline_dentry *dentry_blk = NULL; struct f2fs_dentry_ptr d; - int slots = GET_DENTRY_SLOTS(namelen); + int slots = GET_DENTRY_SLOTS(new_name->len); struct page *page = NULL; int err = 0; @@ -477,25 +538,27 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *name, if (inode) { down_write(&F2FS_I(inode)->i_sem); - page = init_inode_metadata(inode, dir, name, ipage); + page = init_inode_metadata(inode, dir, new_name, + orig_name, ipage); if (IS_ERR(page)) { err = PTR_ERR(page); goto fail; } + if (f2fs_encrypted_inode(dir)) + file_set_enc_name(inode); } - f2fs_wait_on_page_writeback(ipage, NODE); + f2fs_wait_on_page_writeback(ipage, NODE, true); - name_hash = f2fs_dentry_hash(name, NULL); + name_hash = f2fs_dentry_hash(new_name); make_dentry_ptr(NULL, &d, (void *)dentry_blk, 2); - f2fs_update_dentry(ino, mode, &d, name, name_hash, bit_pos); + f2fs_update_dentry(ino, mode, &d, new_name, name_hash, bit_pos); set_page_dirty(ipage); /* we don't need to mark_inode_dirty now */ if (inode) { - F2FS_I(inode)->i_pino = dir->i_ino; - update_inode(inode, page); + f2fs_i_pino_write(inode, dir->i_ino); f2fs_put_page(page, 1); } @@ -503,11 +566,6 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *name, fail: if (inode) up_write(&F2FS_I(inode)->i_sem); - - if (is_inode_flag_set(F2FS_I(dir), FI_UPDATE_DIR)) { - update_inode(dir, ipage); - clear_inode_flag(F2FS_I(dir), FI_UPDATE_DIR); - } out: f2fs_put_page(ipage, 1); return err; @@ -522,22 +580,22 @@ void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry, struct page *page, int i; lock_page(page); - f2fs_wait_on_page_writeback(page, NODE); + f2fs_wait_on_page_writeback(page, NODE, true); inline_dentry = inline_data_addr(page); bit_pos = dentry - inline_dentry->dentry; for (i = 0; i < slots; i++) - test_and_clear_bit_le(bit_pos + i, + __clear_bit_le(bit_pos + i, &inline_dentry->dentry_bitmap); set_page_dirty(page); + f2fs_put_page(page, 1); - dir->i_ctime = dir->i_mtime = CURRENT_TIME; + dir->i_ctime = dir->i_mtime = current_time(dir); + f2fs_mark_inode_dirty_sync(dir, false); if (inode) - f2fs_drop_nlink(dir, inode, page); - - f2fs_put_page(page, 1); + f2fs_drop_nlink(dir, inode); } bool f2fs_empty_inline_dir(struct inode *dir) @@ -565,12 +623,13 @@ bool f2fs_empty_inline_dir(struct inode *dir) } int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx, - struct f2fs_str *fstr) + struct fscrypt_str *fstr) { struct inode *inode = file_inode(file); struct f2fs_inline_dentry *inline_dentry = NULL; struct page *ipage = NULL; struct f2fs_dentry_ptr d; + int err; if (ctx->pos == NR_INLINE_DENTRY) return 0; @@ -583,11 +642,12 @@ int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx, make_dentry_ptr(inode, &d, (void *)inline_dentry, 2); - if (!f2fs_fill_dentries(ctx, &d, 0, fstr)) + err = f2fs_fill_dentries(ctx, &d, 0, fstr); + if (!err) ctx->pos = NR_INLINE_DENTRY; f2fs_put_page(ipage, 1); - return 0; + return err < 0 ? err : 0; } int f2fs_inline_data_fiemap(struct inode *inode, diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 97e20decacb4..af06bda51a54 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -11,6 +11,7 @@ #include <linux/fs.h> #include <linux/f2fs_fs.h> #include <linux/buffer_head.h> +#include <linux/backing-dev.h> #include <linux/writeback.h> #include "f2fs.h" @@ -18,6 +19,14 @@ #include <trace/events/f2fs.h> +void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync) +{ + if (f2fs_inode_dirtied(inode, sync)) + return; + + mark_inode_dirty_sync(inode); +} + void f2fs_set_inode_flags(struct inode *inode) { unsigned int flags = F2FS_I(inode)->i_flags; @@ -35,6 +44,7 @@ void f2fs_set_inode_flags(struct inode *inode) new_fl |= S_DIRSYNC; inode_set_flags(inode, new_fl, S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC); + f2fs_mark_inode_dirty_sync(inode, false); } static void __get_inode_rdev(struct inode *inode, struct f2fs_inode *ri) @@ -83,10 +93,10 @@ static void __recover_inline_status(struct inode *inode, struct page *ipage) while (start < end) { if (*start++) { - f2fs_wait_on_page_writeback(ipage, NODE); + f2fs_wait_on_page_writeback(ipage, NODE, true); - set_inode_flag(F2FS_I(inode), FI_DATA_EXIST); - set_raw_inline(F2FS_I(inode), F2FS_INODE(ipage)); + set_inode_flag(inode, FI_DATA_EXIST); + set_raw_inline(inode, F2FS_INODE(ipage)); set_page_dirty(ipage); return; } @@ -138,9 +148,10 @@ static int do_read_inode(struct inode *inode) fi->i_pino = le32_to_cpu(ri->i_pino); fi->i_dir_level = ri->i_dir_level; - f2fs_init_extent_tree(inode, &ri->i_ext); + if (f2fs_init_extent_tree(inode, &ri->i_ext)) + set_page_dirty(node_page); - get_inline_info(fi, ri); + get_inline_info(inode, ri); /* check data exist */ if (f2fs_has_inline_data(inode) && !f2fs_exist_data(inode)) @@ -150,7 +161,10 @@ static int do_read_inode(struct inode *inode) __get_inode_rdev(inode, ri); if (__written_first_block(ri)) - set_inode_flag(F2FS_I(inode), FI_FIRST_BLOCK_WRITTEN); + set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN); + + if (!need_inode_block_update(sbi, inode->i_ino)) + fi->last_disk_size = inode->i_size; f2fs_put_page(node_page, 1); @@ -202,6 +216,7 @@ make_now: inode->i_op = &f2fs_encrypted_symlink_inode_operations; else inode->i_op = &f2fs_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &f2fs_dblock_aops; } else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) || S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) { @@ -221,11 +236,28 @@ bad_inode: return ERR_PTR(ret); } -void update_inode(struct inode *inode, struct page *node_page) +struct inode *f2fs_iget_retry(struct super_block *sb, unsigned long ino) +{ + struct inode *inode; +retry: + inode = f2fs_iget(sb, ino); + if (IS_ERR(inode)) { + if (PTR_ERR(inode) == -ENOMEM) { + congestion_wait(BLK_RW_ASYNC, HZ/50); + goto retry; + } + } + return inode; +} + +int update_inode(struct inode *inode, struct page *node_page) { struct f2fs_inode *ri; + struct extent_tree *et = F2FS_I(inode)->extent_tree; + + f2fs_inode_synced(inode); - f2fs_wait_on_page_writeback(node_page, NODE); + f2fs_wait_on_page_writeback(node_page, NODE, true); ri = F2FS_INODE(node_page); @@ -237,12 +269,14 @@ void update_inode(struct inode *inode, struct page *node_page) ri->i_size = cpu_to_le64(i_size_read(inode)); ri->i_blocks = cpu_to_le64(inode->i_blocks); - if (F2FS_I(inode)->extent_tree) - set_raw_extent(&F2FS_I(inode)->extent_tree->largest, - &ri->i_ext); - else + if (et) { + read_lock(&et->lock); + set_raw_extent(&et->largest, &ri->i_ext); + read_unlock(&et->lock); + } else { memset(&ri->i_ext, 0, sizeof(ri->i_ext)); - set_raw_inline(F2FS_I(inode), ri); + } + set_raw_inline(inode, ri); ri->i_atime = cpu_to_le64(inode->i_atime.tv_sec); ri->i_ctime = cpu_to_le64(inode->i_ctime.tv_sec); @@ -259,15 +293,19 @@ void update_inode(struct inode *inode, struct page *node_page) __set_inode_rdev(inode, ri); set_cold_node(inode, node_page); - set_page_dirty(node_page); - clear_inode_flag(F2FS_I(inode), FI_DIRTY_INODE); + /* deleted inode */ + if (inode->i_nlink == 0) + clear_inline_node(node_page); + + return set_page_dirty(node_page); } -void update_inode_page(struct inode *inode) +int update_inode_page(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct page *node_page; + int ret = 0; retry: node_page = get_node_page(sbi, inode->i_ino); if (IS_ERR(node_page)) { @@ -276,12 +314,14 @@ retry: cond_resched(); goto retry; } else if (err != -ENOENT) { - f2fs_stop_checkpoint(sbi); + f2fs_stop_checkpoint(sbi, false); } - return; + f2fs_inode_synced(inode); + return 0; } - update_inode(inode, node_page); + ret = update_inode(inode, node_page); f2fs_put_page(node_page, 1); + return ret; } int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc) @@ -292,16 +332,15 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc) inode->i_ino == F2FS_META_INO(sbi)) return 0; - if (!is_inode_flag_set(F2FS_I(inode), FI_DIRTY_INODE)) + if (!is_inode_flag_set(inode, FI_DIRTY_INODE)) return 0; /* * We need to balance fs here to prevent from producing dirty node pages * during the urgent cleaning time when runing out of free sections. */ - update_inode_page(inode); - - f2fs_balance_fs(sbi); + if (update_inode_page(inode) && wbc && wbc->nr_to_write) + f2fs_balance_fs(sbi, true); return 0; } @@ -311,13 +350,12 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc) void f2fs_evict_inode(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct f2fs_inode_info *fi = F2FS_I(inode); - nid_t xnid = fi->i_xattr_nid; + nid_t xnid = F2FS_I(inode)->i_xattr_nid; int err = 0; /* some remained atomic pages should discarded */ if (f2fs_is_atomic_file(inode)) - commit_inmem_pages(inode, true); + drop_inmem_pages(inode); trace_f2fs_evict_inode(inode); truncate_inode_pages_final(&inode->i_data); @@ -327,26 +365,44 @@ void f2fs_evict_inode(struct inode *inode) goto out_clear; f2fs_bug_on(sbi, get_dirty_pages(inode)); - remove_dirty_dir_inode(inode); + remove_dirty_inode(inode); f2fs_destroy_extent_tree(inode); if (inode->i_nlink || is_bad_inode(inode)) goto no_delete; +#ifdef CONFIG_F2FS_FAULT_INJECTION + if (time_to_inject(sbi, FAULT_EVICT_INODE)) + goto no_delete; +#endif + + remove_ino_entry(sbi, inode->i_ino, APPEND_INO); + remove_ino_entry(sbi, inode->i_ino, UPDATE_INO); + sb_start_intwrite(inode->i_sb); - set_inode_flag(fi, FI_NO_ALLOC); + set_inode_flag(inode, FI_NO_ALLOC); i_size_write(inode, 0); - +retry: if (F2FS_HAS_BLOCKS(inode)) - err = f2fs_truncate(inode, true); + err = f2fs_truncate(inode); if (!err) { f2fs_lock_op(sbi); err = remove_inode_page(inode); f2fs_unlock_op(sbi); + if (err == -ENOENT) + err = 0; } + /* give more chances, if ENOMEM case */ + if (err == -ENOMEM) { + err = 0; + goto retry; + } + + if (err) + update_inode_page(inode); sb_end_intwrite(inode->i_sb); no_delete: stat_dec_inline_xattr(inode); @@ -356,36 +412,20 @@ no_delete: invalidate_mapping_pages(NODE_MAPPING(sbi), inode->i_ino, inode->i_ino); if (xnid) invalidate_mapping_pages(NODE_MAPPING(sbi), xnid, xnid); - if (is_inode_flag_set(fi, FI_APPEND_WRITE)) - add_dirty_inode(sbi, inode->i_ino, APPEND_INO); - if (is_inode_flag_set(fi, FI_UPDATE_WRITE)) - add_dirty_inode(sbi, inode->i_ino, UPDATE_INO); - if (is_inode_flag_set(fi, FI_FREE_NID)) { - if (err && err != -ENOENT) - alloc_nid_done(sbi, inode->i_ino); - else - alloc_nid_failed(sbi, inode->i_ino); - clear_inode_flag(fi, FI_FREE_NID); + if (inode->i_nlink) { + if (is_inode_flag_set(inode, FI_APPEND_WRITE)) + add_ino_entry(sbi, inode->i_ino, APPEND_INO); + if (is_inode_flag_set(inode, FI_UPDATE_WRITE)) + add_ino_entry(sbi, inode->i_ino, UPDATE_INO); } - - if (err && err != -ENOENT) { - if (!exist_written_data(sbi, inode->i_ino, ORPHAN_INO)) { - /* - * get here because we failed to release resource - * of inode previously, reminder our user to run fsck - * for fixing. - */ - set_sbi_flag(sbi, SBI_NEED_FSCK); - f2fs_msg(sbi->sb, KERN_WARNING, - "inode (ino:%lu) resource leak, run fsck " - "to fix this issue!", inode->i_ino); - } + if (is_inode_flag_set(inode, FI_FREE_NID)) { + alloc_nid_failed(sbi, inode->i_ino); + clear_inode_flag(inode, FI_FREE_NID); } + f2fs_bug_on(sbi, err && + !exist_written_data(sbi, inode->i_ino, ORPHAN_INO)); out_clear: -#ifdef CONFIG_F2FS_FS_ENCRYPTION - if (fi->i_crypt_info) - f2fs_free_encryption_info(inode, fi->i_crypt_info); -#endif + fscrypt_put_encryption_info(inode, NULL); clear_inode(inode); } @@ -393,37 +433,44 @@ out_clear: void handle_failed_inode(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - int err = 0; + struct node_info ni; + /* + * clear nlink of inode in order to release resource of inode + * immediately. + */ clear_nlink(inode); - make_bad_inode(inode); - unlock_new_inode(inode); - i_size_write(inode, 0); - if (F2FS_HAS_BLOCKS(inode)) - err = f2fs_truncate(inode, false); + /* + * we must call this to avoid inode being remained as dirty, resulting + * in a panic when flushing dirty inodes in gdirty_list. + */ + update_inode_page(inode); - if (!err) - err = remove_inode_page(inode); + /* don't make bad inode, since it becomes a regular file. */ + unlock_new_inode(inode); /* - * if we skip truncate_node in remove_inode_page bacause we failed - * before, it's better to find another way to release resource of - * this inode (e.g. valid block count, node block or nid). Here we - * choose to add this inode to orphan list, so that we can call iput - * for releasing in orphan recovery flow. - * * Note: we should add inode to orphan list before f2fs_unlock_op() * so we can prevent losing this orphan when encoutering checkpoint * and following suddenly power-off. */ - if (err && err != -ENOENT) { - err = acquire_orphan_inode(sbi); - if (!err) - add_orphan_inode(sbi, inode->i_ino); + get_node_info(sbi, inode->i_ino, &ni); + + if (ni.blk_addr != NULL_ADDR) { + int err = acquire_orphan_inode(sbi); + if (err) { + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_msg(sbi->sb, KERN_WARNING, + "Too many orphan inodes, run fsck to fix."); + } else { + add_orphan_inode(inode); + } + alloc_nid_done(sbi, inode->i_ino); + } else { + set_inode_flag(inode, FI_FREE_NID); } - set_inode_flag(F2FS_I(inode), FI_FREE_NID); f2fs_unlock_op(sbi); /* iput will drop the inode object */ diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index 2c32110f9fc0..468b2dbe6d34 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -46,7 +46,7 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode) inode->i_ino = ino; inode->i_blocks = 0; - inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; + inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode); inode->i_generation = sbi->s_next_generation++; err = insert_inode_locked(inode); @@ -60,10 +60,14 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode) if (f2fs_encrypted_inode(dir) && f2fs_may_encrypt(inode)) f2fs_set_encrypted_inode(inode); - if (f2fs_may_inline_data(inode)) - set_inode_flag(F2FS_I(inode), FI_INLINE_DATA); + set_inode_flag(inode, FI_NEW_INODE); + + if (test_opt(sbi, INLINE_XATTR)) + set_inode_flag(inode, FI_INLINE_XATTR); + if (test_opt(sbi, INLINE_DATA) && f2fs_may_inline_data(inode)) + set_inode_flag(inode, FI_INLINE_DATA); if (f2fs_may_inline_dentry(inode)) - set_inode_flag(F2FS_I(inode), FI_INLINE_DENTRY); + set_inode_flag(inode, FI_INLINE_DENTRY); f2fs_init_extent_tree(inode, NULL); @@ -72,14 +76,13 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode) stat_inc_inline_dir(inode); trace_f2fs_new_inode(inode, 0); - mark_inode_dirty(inode); return inode; fail: trace_f2fs_new_inode(inode, err); make_bad_inode(inode); if (nid_free) - set_inode_flag(F2FS_I(inode), FI_FREE_NID); + set_inode_flag(inode, FI_FREE_NID); iput(inode); return ERR_PTR(err); } @@ -88,18 +91,23 @@ static int is_multimedia_file(const unsigned char *s, const char *sub) { size_t slen = strlen(s); size_t sublen = strlen(sub); + int i; /* * filename format of multimedia file should be defined as: - * "filename + '.' + extension". + * "filename + '.' + extension + (optional: '.' + temp extension)". */ if (slen < sublen + 2) return 0; - if (s[slen - sublen - 1] != '.') - return 0; + for (i = 1; i < slen - sublen; i++) { + if (s[i] != '.') + continue; + if (!strncasecmp(s + i + 1, sub, sublen)) + return 1; + } - return !strncasecmp(s + slen - sublen, sub, sublen); + return 0; } /* @@ -128,8 +136,6 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode, nid_t ino = 0; int err; - f2fs_balance_fs(sbi); - inode = f2fs_new_inode(dir, mode); if (IS_ERR(inode)) return PTR_ERR(inode); @@ -142,6 +148,8 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode, inode->i_mapping->a_ops = &f2fs_dblock_aops; ino = inode->i_ino; + f2fs_balance_fs(sbi, true); + f2fs_lock_op(sbi); err = f2fs_add_link(dentry, inode); if (err) @@ -169,15 +177,15 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir, int err; if (f2fs_encrypted_inode(dir) && - !f2fs_is_child_context_consistent_with_parent(dir, inode)) + !fscrypt_has_permitted_context(dir, inode)) return -EPERM; - f2fs_balance_fs(sbi); + f2fs_balance_fs(sbi, true); - inode->i_ctime = CURRENT_TIME; + inode->i_ctime = current_time(inode); ihold(inode); - set_inode_flag(F2FS_I(inode), FI_INC_LINK); + set_inode_flag(inode, FI_INC_LINK); f2fs_lock_op(sbi); err = f2fs_add_link(dentry, inode); if (err) @@ -190,7 +198,7 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir, f2fs_sync_fs(sbi->sb, 1); return 0; out: - clear_inode_flag(F2FS_I(inode), FI_INC_LINK); + clear_inode_flag(inode, FI_INC_LINK); iput(inode); f2fs_unlock_op(sbi); return err; @@ -199,10 +207,14 @@ out: struct dentry *f2fs_get_parent(struct dentry *child) { struct qstr dotdot = QSTR_INIT("..", 2); - unsigned long ino = f2fs_inode_by_name(d_inode(child), &dotdot); - if (!ino) + struct page *page; + unsigned long ino = f2fs_inode_by_name(d_inode(child), &dotdot, &page); + if (!ino) { + if (IS_ERR(page)) + return ERR_CAST(page); return ERR_PTR(-ENOENT); - return d_obtain_alias(f2fs_iget(d_inode(child)->i_sb, ino)); + } + return d_obtain_alias(f2fs_iget(child->d_sb, ino)); } static int __recover_dot_dentries(struct inode *dir, nid_t pino) @@ -214,12 +226,24 @@ static int __recover_dot_dentries(struct inode *dir, nid_t pino) struct page *page; int err = 0; + if (f2fs_readonly(sbi->sb)) { + f2fs_msg(sbi->sb, KERN_INFO, + "skip recovering inline_dots inode (ino:%lu, pino:%u) " + "in readonly mountpoint", dir->i_ino, pino); + return 0; + } + + f2fs_balance_fs(sbi, true); + f2fs_lock_op(sbi); de = f2fs_find_entry(dir, &dot, &page); if (de) { f2fs_dentry_kunmap(dir, page); f2fs_put_page(page, 0); + } else if (IS_ERR(page)) { + err = PTR_ERR(page); + goto out; } else { err = __f2fs_add_link(dir, &dot, NULL, dir->i_ino, S_IFDIR); if (err) @@ -230,14 +254,14 @@ static int __recover_dot_dentries(struct inode *dir, nid_t pino) if (de) { f2fs_dentry_kunmap(dir, page); f2fs_put_page(page, 0); + } else if (IS_ERR(page)) { + err = PTR_ERR(page); } else { err = __f2fs_add_link(dir, &dotdot, NULL, pino, S_IFDIR); } out: - if (!err) { - clear_inode_flag(F2FS_I(dir), FI_INLINE_DOTS); - mark_inode_dirty(dir); - } + if (!err) + clear_inode_flag(dir, FI_INLINE_DOTS); f2fs_unlock_op(sbi); return err; @@ -251,13 +275,32 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry, struct page *page; nid_t ino; int err = 0; + unsigned int root_ino = F2FS_ROOT_INO(F2FS_I_SB(dir)); + + if (f2fs_encrypted_inode(dir)) { + int res = fscrypt_get_encryption_info(dir); + + /* + * DCACHE_ENCRYPTED_WITH_KEY is set if the dentry is + * created while the directory was encrypted and we + * don't have access to the key. + */ + if (fscrypt_has_encryption_key(dir)) + fscrypt_set_encrypted_dentry(dentry); + fscrypt_set_d_op(dentry); + if (res && res != -ENOKEY) + return ERR_PTR(res); + } if (dentry->d_name.len > F2FS_NAME_LEN) return ERR_PTR(-ENAMETOOLONG); de = f2fs_find_entry(dir, &dentry->d_name, &page); - if (!de) + if (!de) { + if (IS_ERR(page)) + return (struct dentry *)page; return d_splice_alias(inode, dentry); + } ino = le32_to_cpu(de->ino); f2fs_dentry_kunmap(dir, page); @@ -267,15 +310,29 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry, if (IS_ERR(inode)) return ERR_CAST(inode); + if ((dir->i_ino == root_ino) && f2fs_has_inline_dots(dir)) { + err = __recover_dot_dentries(dir, root_ino); + if (err) + goto err_out; + } + if (f2fs_has_inline_dots(inode)) { err = __recover_dot_dentries(inode, dir->i_ino); if (err) goto err_out; } + if (!IS_ERR(inode) && f2fs_encrypted_inode(dir) && + (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) && + !fscrypt_has_permitted_context(dir, inode)) { + bool nokey = f2fs_encrypted_inode(inode) && + !fscrypt_has_encryption_key(inode); + err = nokey ? -ENOKEY : -EPERM; + goto err_out; + } return d_splice_alias(inode, dentry); err_out: - iget_failed(inode); + iput(inode); return ERR_PTR(err); } @@ -288,11 +345,15 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry) int err = -ENOENT; trace_f2fs_unlink_enter(dir, dentry); - f2fs_balance_fs(sbi); de = f2fs_find_entry(dir, &dentry->d_name, &page); - if (!de) + if (!de) { + if (IS_ERR(page)) + err = PTR_ERR(page); goto fail; + } + + f2fs_balance_fs(sbi, true); f2fs_lock_op(sbi); err = acquire_orphan_inode(sbi); @@ -305,9 +366,6 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry) f2fs_delete_entry(de, page, dir, inode); f2fs_unlock_op(sbi); - /* In order to evict this inode, we set it dirty */ - mark_inode_dirty(inode); - if (IS_DIRSYNC(dir)) f2fs_sync_fs(sbi->sb, 1); fail: @@ -332,16 +390,24 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry, struct f2fs_sb_info *sbi = F2FS_I_SB(dir); struct inode *inode; size_t len = strlen(symname); - size_t p_len; - char *p_str; - struct f2fs_str disk_link = FSTR_INIT(NULL, 0); - struct f2fs_encrypted_symlink_data *sd = NULL; + struct fscrypt_str disk_link = FSTR_INIT((char *)symname, len + 1); + struct fscrypt_symlink_data *sd = NULL; int err; - if (len > dir->i_sb->s_blocksize) - return -ENAMETOOLONG; + if (f2fs_encrypted_inode(dir)) { + err = fscrypt_get_encryption_info(dir); + if (err) + return err; + + if (!fscrypt_has_encryption_key(dir)) + return -EPERM; - f2fs_balance_fs(sbi); + disk_link.len = (fscrypt_fname_encrypted_size(dir, len) + + sizeof(struct fscrypt_symlink_data)); + } + + if (disk_link.len > dir->i_sb->s_blocksize) + return -ENAMETOOLONG; inode = f2fs_new_inode(dir, S_IFLNK | S_IRWXUGO); if (IS_ERR(inode)) @@ -351,8 +417,11 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry, inode->i_op = &f2fs_encrypted_symlink_inode_operations; else inode->i_op = &f2fs_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &f2fs_dblock_aops; + f2fs_balance_fs(sbi, true); + f2fs_lock_op(sbi); err = f2fs_add_link(dentry, inode); if (err) @@ -360,42 +429,36 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry, f2fs_unlock_op(sbi); alloc_nid_done(sbi, inode->i_ino); - if (f2fs_encrypted_inode(dir)) { + if (f2fs_encrypted_inode(inode)) { struct qstr istr = QSTR_INIT(symname, len); + struct fscrypt_str ostr; - err = f2fs_get_encryption_info(inode); - if (err) + sd = kzalloc(disk_link.len, GFP_NOFS); + if (!sd) { + err = -ENOMEM; goto err_out; + } - err = f2fs_fname_crypto_alloc_buffer(inode, len, &disk_link); + err = fscrypt_get_encryption_info(inode); if (err) goto err_out; - err = f2fs_fname_usr_to_disk(inode, &istr, &disk_link); - if (err < 0) - goto err_out; - - p_len = encrypted_symlink_data_len(disk_link.len) + 1; - - if (p_len > dir->i_sb->s_blocksize) { - err = -ENAMETOOLONG; + if (!fscrypt_has_encryption_key(inode)) { + err = -EPERM; goto err_out; } - sd = kzalloc(p_len, GFP_NOFS); - if (!sd) { - err = -ENOMEM; + ostr.name = sd->encrypted_path; + ostr.len = disk_link.len; + err = fscrypt_fname_usr_to_disk(inode, &istr, &ostr); + if (err) goto err_out; - } - memcpy(sd->encrypted_path, disk_link.name, disk_link.len); - sd->len = cpu_to_le16(disk_link.len); - p_str = (char *)sd; - } else { - p_len = len + 1; - p_str = (char *)symname; + + sd->len = cpu_to_le16(ostr.len); + disk_link.name = (char *)sd; } - err = page_symlink(inode, p_str, p_len); + err = page_symlink(inode, disk_link.name, disk_link.len); err_out: d_instantiate(dentry, inode); @@ -411,7 +474,8 @@ err_out: * performance regression. */ if (!err) { - filemap_write_and_wait_range(inode->i_mapping, 0, p_len - 1); + filemap_write_and_wait_range(inode->i_mapping, 0, + disk_link.len - 1); if (IS_DIRSYNC(dir)) f2fs_sync_fs(sbi->sb, 1); @@ -420,7 +484,6 @@ err_out: } kfree(sd); - f2fs_fname_crypto_free_buffer(&disk_link); return err; out: handle_failed_inode(inode); @@ -433,8 +496,6 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) struct inode *inode; int err; - f2fs_balance_fs(sbi); - inode = f2fs_new_inode(dir, S_IFDIR | mode); if (IS_ERR(inode)) return PTR_ERR(inode); @@ -444,7 +505,9 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) inode->i_mapping->a_ops = &f2fs_dblock_aops; mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_HIGH_ZERO); - set_inode_flag(F2FS_I(inode), FI_INC_LINK); + f2fs_balance_fs(sbi, true); + + set_inode_flag(inode, FI_INC_LINK); f2fs_lock_op(sbi); err = f2fs_add_link(dentry, inode); if (err) @@ -461,7 +524,7 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) return 0; out_fail: - clear_inode_flag(F2FS_I(inode), FI_INC_LINK); + clear_inode_flag(inode, FI_INC_LINK); handle_failed_inode(inode); return err; } @@ -481,8 +544,6 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry, struct inode *inode; int err = 0; - f2fs_balance_fs(sbi); - inode = f2fs_new_inode(dir, mode); if (IS_ERR(inode)) return PTR_ERR(inode); @@ -490,6 +551,8 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry, init_special_inode(inode, inode->i_mode, rdev); inode->i_op = &f2fs_special_inode_operations; + f2fs_balance_fs(sbi, true); + f2fs_lock_op(sbi); err = f2fs_add_link(dentry, inode); if (err) @@ -516,9 +579,6 @@ static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry, struct inode *inode; int err; - if (!whiteout) - f2fs_balance_fs(sbi); - inode = f2fs_new_inode(dir, mode); if (IS_ERR(inode)) return PTR_ERR(inode); @@ -532,6 +592,8 @@ static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry, inode->i_mapping->a_ops = &f2fs_dblock_aops; } + f2fs_balance_fs(sbi, true); + f2fs_lock_op(sbi); err = acquire_orphan_inode(sbi); if (err) @@ -545,17 +607,17 @@ static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry, * add this non-linked tmpfile to orphan list, in this way we could * remove all unused data of tmpfile after abnormal power-off. */ - add_orphan_inode(sbi, inode->i_ino); - f2fs_unlock_op(sbi); - + add_orphan_inode(inode); alloc_nid_done(sbi, inode->i_ino); if (whiteout) { - inode_dec_link_count(inode); + f2fs_i_links_write(inode, false); *whiteout = inode; } else { d_tmpfile(dentry, inode); } + /* link_count was changed by d_tmpfile as well. */ + f2fs_unlock_op(sbi); unlock_new_inode(inode); return 0; @@ -569,7 +631,7 @@ out: static int f2fs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) { if (f2fs_encrypted_inode(dir)) { - int err = f2fs_get_encryption_info(dir); + int err = fscrypt_get_encryption_info(dir); if (err) return err; } @@ -595,26 +657,29 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, struct f2fs_dir_entry *old_dir_entry = NULL; struct f2fs_dir_entry *old_entry; struct f2fs_dir_entry *new_entry; + bool is_old_inline = f2fs_has_inline_dentry(old_dir); int err = -ENOENT; if ((old_dir != new_dir) && f2fs_encrypted_inode(new_dir) && - !f2fs_is_child_context_consistent_with_parent(new_dir, - old_inode)) { + !fscrypt_has_permitted_context(new_dir, old_inode)) { err = -EPERM; goto out; } - f2fs_balance_fs(sbi); - old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page); - if (!old_entry) + if (!old_entry) { + if (IS_ERR(old_page)) + err = PTR_ERR(old_page); goto out; + } if (S_ISDIR(old_inode->i_mode)) { - err = -EIO; old_dir_entry = f2fs_parent_dir(old_inode, &old_dir_page); - if (!old_dir_entry) + if (!old_dir_entry) { + if (IS_ERR(old_dir_page)) + err = PTR_ERR(old_dir_page); goto out_old; + } } if (flags & RENAME_WHITEOUT) { @@ -632,8 +697,13 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, err = -ENOENT; new_entry = f2fs_find_entry(new_dir, &new_dentry->d_name, &new_page); - if (!new_entry) + if (!new_entry) { + if (IS_ERR(new_page)) + err = PTR_ERR(new_page); goto out_whiteout; + } + + f2fs_balance_fs(sbi, true); f2fs_lock_op(sbi); @@ -641,31 +711,29 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, if (err) goto put_out_dir; - if (update_dent_inode(old_inode, new_inode, - &new_dentry->d_name)) { + err = update_dent_inode(old_inode, new_inode, + &new_dentry->d_name); + if (err) { release_orphan_inode(sbi); goto put_out_dir; } f2fs_set_link(new_dir, new_entry, new_page, old_inode); - new_inode->i_ctime = CURRENT_TIME; + new_inode->i_ctime = current_time(new_inode); down_write(&F2FS_I(new_inode)->i_sem); if (old_dir_entry) - drop_nlink(new_inode); - drop_nlink(new_inode); + f2fs_i_links_write(new_inode, false); + f2fs_i_links_write(new_inode, false); up_write(&F2FS_I(new_inode)->i_sem); - mark_inode_dirty(new_inode); - if (!new_inode->i_nlink) - add_orphan_inode(sbi, new_inode->i_ino); + add_orphan_inode(new_inode); else release_orphan_inode(sbi); - - update_inode_page(old_inode); - update_inode_page(new_inode); } else { + f2fs_balance_fs(sbi, true); + f2fs_lock_op(sbi); err = f2fs_add_link(new_dentry, old_inode); @@ -674,9 +742,29 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, goto out_whiteout; } - if (old_dir_entry) { - inc_nlink(new_dir); - update_inode_page(new_dir); + if (old_dir_entry) + f2fs_i_links_write(new_dir, true); + + /* + * old entry and new entry can locate in the same inline + * dentry in inode, when attaching new entry in inline dentry, + * it could force inline dentry conversion, after that, + * old_entry and old_page will point to wrong address, in + * order to avoid this, let's do the check and update here. + */ + if (is_old_inline && !f2fs_has_inline_dentry(old_dir)) { + f2fs_put_page(old_page, 0); + old_page = NULL; + + old_entry = f2fs_find_entry(old_dir, + &old_dentry->d_name, &old_page); + if (!old_entry) { + err = -ENOENT; + if (IS_ERR(old_page)) + err = PTR_ERR(old_page); + f2fs_unlock_op(sbi); + goto out_whiteout; + } } } @@ -686,14 +774,14 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, file_set_enc_name(old_inode); up_write(&F2FS_I(old_inode)->i_sem); - old_inode->i_ctime = CURRENT_TIME; - mark_inode_dirty(old_inode); + old_inode->i_ctime = current_time(old_inode); + f2fs_mark_inode_dirty_sync(old_inode, false); f2fs_delete_entry(old_entry, old_page, old_dir, NULL); if (whiteout) { whiteout->i_state |= I_LINKABLE; - set_inode_flag(F2FS_I(whiteout), FI_INC_LINK); + set_inode_flag(whiteout, FI_INC_LINK); err = f2fs_add_link(old_dentry, whiteout); if (err) goto put_out_dir; @@ -705,14 +793,11 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, if (old_dir != new_dir && !whiteout) { f2fs_set_link(old_inode, old_dir_entry, old_dir_page, new_dir); - update_inode_page(old_inode); } else { f2fs_dentry_kunmap(old_inode, old_dir_page); f2fs_put_page(old_dir_page, 0); } - drop_nlink(old_dir); - mark_inode_dirty(old_dir); - update_inode_page(old_dir); + f2fs_i_links_write(old_dir, false); } f2fs_unlock_op(sbi); @@ -756,39 +841,45 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry, int err = -ENOENT; if ((f2fs_encrypted_inode(old_dir) || f2fs_encrypted_inode(new_dir)) && - (old_dir != new_dir) && - (!f2fs_is_child_context_consistent_with_parent(new_dir, - old_inode) || - !f2fs_is_child_context_consistent_with_parent(old_dir, - new_inode))) + (old_dir != new_dir) && + (!fscrypt_has_permitted_context(new_dir, old_inode) || + !fscrypt_has_permitted_context(old_dir, new_inode))) return -EPERM; - f2fs_balance_fs(sbi); - old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page); - if (!old_entry) + if (!old_entry) { + if (IS_ERR(old_page)) + err = PTR_ERR(old_page); goto out; + } new_entry = f2fs_find_entry(new_dir, &new_dentry->d_name, &new_page); - if (!new_entry) + if (!new_entry) { + if (IS_ERR(new_page)) + err = PTR_ERR(new_page); goto out_old; + } /* prepare for updating ".." directory entry info later */ if (old_dir != new_dir) { if (S_ISDIR(old_inode->i_mode)) { - err = -EIO; old_dir_entry = f2fs_parent_dir(old_inode, &old_dir_page); - if (!old_dir_entry) + if (!old_dir_entry) { + if (IS_ERR(old_dir_page)) + err = PTR_ERR(old_dir_page); goto out_new; + } } if (S_ISDIR(new_inode->i_mode)) { - err = -EIO; new_dir_entry = f2fs_parent_dir(new_inode, &new_dir_page); - if (!new_dir_entry) + if (!new_dir_entry) { + if (IS_ERR(new_dir_page)) + err = PTR_ERR(new_dir_page); goto out_old_dir; + } } } @@ -807,6 +898,8 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry, goto out_new_dir; } + f2fs_balance_fs(sbi, true); + f2fs_lock_op(sbi); err = update_dent_inode(old_inode, new_inode, &new_dentry->d_name); @@ -836,19 +929,13 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry, file_lost_pino(old_inode); up_write(&F2FS_I(old_inode)->i_sem); - update_inode_page(old_inode); - old_dir->i_ctime = CURRENT_TIME; if (old_nlink) { down_write(&F2FS_I(old_dir)->i_sem); - if (old_nlink < 0) - drop_nlink(old_dir); - else - inc_nlink(old_dir); + f2fs_i_links_write(old_dir, old_nlink > 0); up_write(&F2FS_I(old_dir)->i_sem); } - mark_inode_dirty(old_dir); - update_inode_page(old_dir); + f2fs_mark_inode_dirty_sync(old_dir, false); /* update directory entry info of new dir inode */ f2fs_set_link(new_dir, new_entry, new_page, old_inode); @@ -857,19 +944,13 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry, file_lost_pino(new_inode); up_write(&F2FS_I(new_inode)->i_sem); - update_inode_page(new_inode); - new_dir->i_ctime = CURRENT_TIME; if (new_nlink) { down_write(&F2FS_I(new_dir)->i_sem); - if (new_nlink < 0) - drop_nlink(new_dir); - else - inc_nlink(new_dir); + f2fs_i_links_write(new_dir, new_nlink > 0); up_write(&F2FS_I(new_dir)->i_sem); } - mark_inode_dirty(new_dir); - update_inode_page(new_dir); + f2fs_mark_inode_dirty_sync(new_dir, false); f2fs_unlock_op(sbi); @@ -922,89 +1003,85 @@ static int f2fs_rename2(struct inode *old_dir, struct dentry *old_dentry, return f2fs_rename(old_dir, old_dentry, new_dir, new_dentry, flags); } -#ifdef CONFIG_F2FS_FS_ENCRYPTION static const char *f2fs_encrypted_follow_link(struct dentry *dentry, void **cookie) { struct page *cpage = NULL; char *caddr, *paddr = NULL; - struct f2fs_str cstr; - struct f2fs_str pstr = FSTR_INIT(NULL, 0); + struct fscrypt_str cstr = FSTR_INIT(NULL, 0); + struct fscrypt_str pstr = FSTR_INIT(NULL, 0); + struct fscrypt_symlink_data *sd; struct inode *inode = d_inode(dentry); - struct f2fs_encrypted_symlink_data *sd; - loff_t size = min_t(loff_t, i_size_read(inode), PAGE_SIZE - 1); u32 max_size = inode->i_sb->s_blocksize; int res; - res = f2fs_get_encryption_info(inode); + if (!dentry) + return ERR_PTR(-ECHILD); + + res = fscrypt_get_encryption_info(inode); if (res) return ERR_PTR(res); cpage = read_mapping_page(inode->i_mapping, 0, NULL); if (IS_ERR(cpage)) return ERR_CAST(cpage); - caddr = kmap(cpage); - caddr[size] = 0; + caddr = page_address(cpage); /* Symlink is encrypted */ - sd = (struct f2fs_encrypted_symlink_data *)caddr; + sd = (struct fscrypt_symlink_data *)caddr; + cstr.name = sd->encrypted_path; cstr.len = le16_to_cpu(sd->len); - cstr.name = kmalloc(cstr.len, GFP_NOFS); - if (!cstr.name) { - res = -ENOMEM; - goto errout; - } - memcpy(cstr.name, sd->encrypted_path, cstr.len); /* this is broken symlink case */ - if (cstr.name[0] == 0 && cstr.len == 0) { + if (unlikely(cstr.len == 0)) { res = -ENOENT; goto errout; } - if ((cstr.len + sizeof(struct f2fs_encrypted_symlink_data) - 1) > - max_size) { + if ((cstr.len + sizeof(struct fscrypt_symlink_data) - 1) > max_size) { /* Symlink data on the disk is corrupted */ res = -EIO; goto errout; } - res = f2fs_fname_crypto_alloc_buffer(inode, cstr.len, &pstr); + res = fscrypt_fname_alloc_buffer(inode, cstr.len, &pstr); if (res) goto errout; - res = f2fs_fname_disk_to_usr(inode, NULL, &cstr, &pstr); - if (res < 0) + res = fscrypt_fname_disk_to_usr(inode, 0, 0, &cstr, &pstr); + if (res) goto errout; - kfree(cstr.name); + /* this is broken symlink case */ + if (unlikely(pstr.name[0] == 0)) { + res = -ENOENT; + goto errout; + } paddr = pstr.name; /* Null-terminate the name */ - paddr[res] = '\0'; + paddr[pstr.len] = '\0'; - kunmap(cpage); - page_cache_release(cpage); + put_page(cpage); return *cookie = paddr; errout: - kfree(cstr.name); - f2fs_fname_crypto_free_buffer(&pstr); - kunmap(cpage); - page_cache_release(cpage); + fscrypt_fname_free_buffer(&pstr); + put_page(cpage); return ERR_PTR(res); } const struct inode_operations f2fs_encrypted_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = f2fs_encrypted_follow_link, - .put_link = kfree_put_link, + .follow_link = f2fs_encrypted_follow_link, + .put_link = kfree_put_link, .getattr = f2fs_getattr, .setattr = f2fs_setattr, +#ifdef CONFIG_F2FS_FS_XATTR .setxattr = generic_setxattr, .getxattr = generic_getxattr, .listxattr = f2fs_listxattr, .removexattr = generic_removexattr, -}; #endif +}; const struct inode_operations f2fs_dir_inode_operations = { .create = f2fs_create, diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 7bcbc6e9c40d..edacbabb92cf 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -45,13 +45,15 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type) * give 25%, 25%, 50%, 50%, 50% memory for each components respectively */ if (type == FREE_NIDS) { - mem_size = (nm_i->fcnt * sizeof(struct free_nid)) >> - PAGE_CACHE_SHIFT; + mem_size = (nm_i->nid_cnt[FREE_NID_LIST] * + sizeof(struct free_nid)) >> PAGE_SHIFT; res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 2); } else if (type == NAT_ENTRIES) { mem_size = (nm_i->nat_cnt * sizeof(struct nat_entry)) >> - PAGE_CACHE_SHIFT; + PAGE_SHIFT; res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 2); + if (excess_cached_nats(sbi)) + res = false; } else if (type == DIRTY_DENTS) { if (sbi->sb->s_bdi->wb.dirty_exceeded) return false; @@ -62,16 +64,17 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type) for (i = 0; i <= UPDATE_INO; i++) mem_size += (sbi->im[i].ino_num * - sizeof(struct ino_entry)) >> PAGE_CACHE_SHIFT; + sizeof(struct ino_entry)) >> PAGE_SHIFT; res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1); } else if (type == EXTENT_CACHE) { - mem_size = (sbi->total_ext_tree * sizeof(struct extent_tree) + + mem_size = (atomic_read(&sbi->total_ext_tree) * + sizeof(struct extent_tree) + atomic_read(&sbi->total_ext_node) * - sizeof(struct extent_node)) >> PAGE_CACHE_SHIFT; + sizeof(struct extent_node)) >> PAGE_SHIFT; res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1); } else { - if (sbi->sb->s_bdi->wb.dirty_exceeded) - return false; + if (!sbi->sb->s_bdi->wb.dirty_exceeded) + return true; } return res; } @@ -120,7 +123,7 @@ static struct page *get_next_nat_page(struct f2fs_sb_info *sbi, nid_t nid) src_addr = page_address(src_page); dst_addr = page_address(dst_page); - memcpy(dst_addr, src_addr, PAGE_CACHE_SIZE); + memcpy(dst_addr, src_addr, PAGE_SIZE); set_page_dirty(dst_page); f2fs_put_page(src_page, 1); @@ -256,18 +259,22 @@ static struct nat_entry *grab_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid) return new; } -static void cache_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid, +static void cache_nat_entry(struct f2fs_sb_info *sbi, nid_t nid, struct f2fs_nat_entry *ne) { + struct f2fs_nm_info *nm_i = NM_I(sbi); 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); + } else { + f2fs_bug_on(sbi, nat_get_ino(e) != le32_to_cpu(ne->ino) || + nat_get_blkaddr(e) != + le32_to_cpu(ne->block_addr) || + nat_get_version(e) != ne->version); } - up_write(&nm_i->nat_tree_lock); } static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni, @@ -355,7 +362,7 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA); - struct f2fs_summary_block *sum = curseg->sum_blk; + struct f2fs_journal *journal = curseg->journal; nid_t start_nid = START_NID(nid); struct f2fs_nat_block *nat_blk; struct page *page = NULL; @@ -372,21 +379,20 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni) ni->ino = nat_get_ino(e); ni->blk_addr = nat_get_blkaddr(e); ni->version = nat_get_version(e); - } - up_read(&nm_i->nat_tree_lock); - if (e) + up_read(&nm_i->nat_tree_lock); return; + } memset(&ne, 0, sizeof(struct f2fs_nat_entry)); /* Check current segment summary */ - mutex_lock(&curseg->curseg_mutex); - i = lookup_journal_in_cursum(sum, NAT_JOURNAL, nid, 0); + down_read(&curseg->journal_rwsem); + i = lookup_journal_in_cursum(journal, NAT_JOURNAL, nid, 0); if (i >= 0) { - ne = nat_in_journal(sum, i); + ne = nat_in_journal(journal, i); node_info_from_raw_nat(ni, &ne); } - mutex_unlock(&curseg->curseg_mutex); + up_read(&curseg->journal_rwsem); if (i >= 0) goto cache; @@ -397,18 +403,75 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni) node_info_from_raw_nat(ni, &ne); f2fs_put_page(page, 1); cache: + up_read(&nm_i->nat_tree_lock); /* cache nat entry */ - cache_nat_entry(NM_I(sbi), nid, &ne); + down_write(&nm_i->nat_tree_lock); + cache_nat_entry(sbi, nid, &ne); + up_write(&nm_i->nat_tree_lock); +} + +/* + * readahead MAX_RA_NODE number of node pages. + */ +static void ra_node_pages(struct page *parent, int start, int n) +{ + struct f2fs_sb_info *sbi = F2FS_P_SB(parent); + struct blk_plug plug; + int i, end; + nid_t nid; + + blk_start_plug(&plug); + + /* Then, try readahead for siblings of the desired node */ + end = start + n; + end = min(end, NIDS_PER_BLOCK); + for (i = start; i < end; i++) { + nid = get_nid(parent, i, false); + ra_node_page(sbi, nid); + } + + blk_finish_plug(&plug); +} + +pgoff_t get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs) +{ + const long direct_index = ADDRS_PER_INODE(dn->inode); + const long direct_blks = ADDRS_PER_BLOCK; + const long indirect_blks = ADDRS_PER_BLOCK * NIDS_PER_BLOCK; + unsigned int skipped_unit = ADDRS_PER_BLOCK; + int cur_level = dn->cur_level; + int max_level = dn->max_level; + pgoff_t base = 0; + + if (!dn->max_level) + return pgofs + 1; + + while (max_level-- > cur_level) + skipped_unit *= NIDS_PER_BLOCK; + + switch (dn->max_level) { + case 3: + base += 2 * indirect_blks; + case 2: + base += 2 * direct_blks; + case 1: + base += direct_index; + break; + default: + f2fs_bug_on(F2FS_I_SB(dn->inode), 1); + } + + return ((pgofs - base) / skipped_unit + 1) * skipped_unit + base; } /* * The maximum depth is four. * Offset[0] will have raw inode offset. */ -static int get_node_path(struct f2fs_inode_info *fi, long block, +static int get_node_path(struct inode *inode, long block, int offset[4], unsigned int noffset[4]) { - const long direct_index = ADDRS_PER_INODE(fi); + const long direct_index = ADDRS_PER_INODE(inode); const long direct_blks = ADDRS_PER_BLOCK; const long dptrs_per_blk = NIDS_PER_BLOCK; const long indirect_blks = ADDRS_PER_BLOCK * NIDS_PER_BLOCK; @@ -493,10 +556,10 @@ int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode) int offset[4]; unsigned int noffset[4]; nid_t nids[4]; - int level, i; + int level, i = 0; int err = 0; - level = get_node_path(F2FS_I(dn->inode), index, offset, noffset); + level = get_node_path(dn->inode, index, offset, noffset); nids[0] = dn->inode->i_ino; npage[0] = dn->inode_page; @@ -583,6 +646,11 @@ release_pages: release_out: dn->inode_page = NULL; dn->node_page = NULL; + if (err == -ENOENT) { + dn->cur_level = i; + dn->max_level = level; + dn->ofs_in_node = offset[level]; + } return err; } @@ -606,8 +674,7 @@ static void truncate_node(struct dnode_of_data *dn) if (dn->nid == dn->inode->i_ino) { remove_orphan_inode(sbi, dn->nid); dec_valid_inode_count(sbi); - } else { - sync_inode_page(dn); + f2fs_inode_synced(dn->inode); } invalidate: clear_node_page_dirty(dn->node_page); @@ -666,6 +733,8 @@ static int truncate_nodes(struct dnode_of_data *dn, unsigned int nofs, return PTR_ERR(page); } + ra_node_pages(page, ofs, NIDS_PER_BLOCK); + rn = F2FS_NODE(page); if (depth < 3) { for (i = ofs; i < NIDS_PER_BLOCK; i++, freed++) { @@ -676,7 +745,8 @@ static int truncate_nodes(struct dnode_of_data *dn, unsigned int nofs, ret = truncate_dnode(&rdn); if (ret < 0) goto out_err; - set_nid(page, i, 0, false); + if (set_nid(page, i, 0, false)) + dn->node_changed = true; } } else { child_nofs = nofs + ofs * (NIDS_PER_BLOCK + 1) + 1; @@ -689,7 +759,8 @@ static int truncate_nodes(struct dnode_of_data *dn, unsigned int nofs, rdn.nid = child_nid; ret = truncate_nodes(&rdn, child_nofs, 0, depth - 1); if (ret == (NIDS_PER_BLOCK + 1)) { - set_nid(page, i, 0, false); + if (set_nid(page, i, 0, false)) + dn->node_changed = true; child_nofs += ret; } else if (ret < 0 && ret != -ENOENT) { goto out_err; @@ -741,6 +812,8 @@ static int truncate_partial_nodes(struct dnode_of_data *dn, nid[i + 1] = get_nid(pages[i], offset[i + 1], false); } + ra_node_pages(pages[idx], offset[idx + 1], NIDS_PER_BLOCK); + /* free direct nodes linked to a partial indirect node */ for (i = offset[idx + 1]; i < NIDS_PER_BLOCK; i++) { child_nid = get_nid(pages[idx], i, false); @@ -750,7 +823,8 @@ static int truncate_partial_nodes(struct dnode_of_data *dn, err = truncate_dnode(dn); if (err < 0) goto fail; - set_nid(pages[idx], i, 0, false); + if (set_nid(pages[idx], i, 0, false)) + dn->node_changed = true; } if (offset[idx + 1] == 0) { @@ -787,8 +861,8 @@ int truncate_inode_blocks(struct inode *inode, pgoff_t from) trace_f2fs_truncate_inode_blocks_enter(inode, from); - level = get_node_path(F2FS_I(inode), from, offset, noffset); -restart: + level = get_node_path(inode, from, offset, noffset); + page = get_node_page(sbi, inode->i_ino); if (IS_ERR(page)) { trace_f2fs_truncate_inode_blocks_exit(inode, PTR_ERR(page)); @@ -852,11 +926,8 @@ skip_partial: if (offset[1] == 0 && ri->i_nid[offset[0] - NODE_DIR1_BLOCK]) { lock_page(page); - if (unlikely(page->mapping != NODE_MAPPING(sbi))) { - f2fs_put_page(page, 1); - goto restart; - } - f2fs_wait_on_page_writeback(page, NODE); + BUG_ON(page->mapping != NODE_MAPPING(sbi)); + f2fs_wait_on_page_writeback(page, NODE, true); ri->i_nid[offset[0] - NODE_DIR1_BLOCK] = 0; set_page_dirty(page); unlock_page(page); @@ -885,7 +956,7 @@ int truncate_xattr_node(struct inode *inode, struct page *page) if (IS_ERR(npage)) return PTR_ERR(npage); - F2FS_I(inode)->i_xattr_nid = 0; + f2fs_i_xnid_write(inode, 0); /* need to do checkpoint during fsync */ F2FS_I(inode)->xattr_ver = cur_cp_version(F2FS_CKPT(sbi)); @@ -951,10 +1022,10 @@ struct page *new_node_page(struct dnode_of_data *dn, struct page *page; int err; - if (unlikely(is_inode_flag_set(F2FS_I(dn->inode), FI_NO_ALLOC))) + if (unlikely(is_inode_flag_set(dn->inode, FI_NO_ALLOC))) return ERR_PTR(-EPERM); - page = grab_cache_page(NODE_MAPPING(sbi), dn->nid); + page = f2fs_grab_cache_page(NODE_MAPPING(sbi), dn->nid, false); if (!page) return ERR_PTR(-ENOMEM); @@ -971,23 +1042,19 @@ struct page *new_node_page(struct dnode_of_data *dn, new_ni.ino = dn->inode->i_ino; set_node_addr(sbi, &new_ni, NEW_ADDR, false); - f2fs_wait_on_page_writeback(page, NODE); + f2fs_wait_on_page_writeback(page, NODE, true); fill_node_footer(page, dn->nid, dn->inode->i_ino, ofs, true); set_cold_node(dn->inode, page); - SetPageUptodate(page); - set_page_dirty(page); + if (!PageUptodate(page)) + SetPageUptodate(page); + if (set_page_dirty(page)) + dn->node_changed = true; if (f2fs_has_xattr_block(ofs)) - F2FS_I(dn->inode)->i_xattr_nid = dn->nid; + f2fs_i_xnid_write(dn->inode, dn->nid); - dn->node_page = page; - if (ipage) - update_inode(dn->inode, ipage); - else - sync_inode_page(dn); if (ofs == 0) inc_valid_inode_count(sbi); - return page; fail: @@ -1013,6 +1080,9 @@ static int read_node_page(struct page *page, int rw) .encrypted_page = NULL, }; + if (PageUptodate(page)) + return LOCKED_PAGE; + get_node_info(sbi, page->index, &ni); if (unlikely(ni.blk_addr == NULL_ADDR)) { @@ -1020,10 +1090,7 @@ static int read_node_page(struct page *page, int rw) return -ENOENT; } - if (PageUptodate(page)) - return LOCKED_PAGE; - - fio.blk_addr = ni.blk_addr; + fio.new_blkaddr = fio.old_blkaddr = ni.blk_addr; return f2fs_submit_page_bio(&fio); } @@ -1035,14 +1102,17 @@ void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid) struct page *apage; int err; - apage = find_get_page(NODE_MAPPING(sbi), nid); - if (apage && PageUptodate(apage)) { - f2fs_put_page(apage, 0); + if (!nid) + return; + f2fs_bug_on(sbi, check_nid_range(sbi, nid)); + + rcu_read_lock(); + apage = radix_tree_lookup(&NODE_MAPPING(sbi)->page_tree, nid); + rcu_read_unlock(); + if (apage) return; - } - f2fs_put_page(apage, 0); - apage = grab_cache_page(NODE_MAPPING(sbi), nid); + apage = f2fs_grab_cache_page(NODE_MAPPING(sbi), nid, false); if (!apage) return; @@ -1050,12 +1120,17 @@ void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid) f2fs_put_page(apage, err ? 1 : 0); } -struct page *get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid) +static struct page *__get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid, + struct page *parent, int start) { struct page *page; int err; + + if (!nid) + return ERR_PTR(-ENOENT); + f2fs_bug_on(sbi, check_nid_range(sbi, nid)); repeat: - page = grab_cache_page(NODE_MAPPING(sbi), nid); + page = f2fs_grab_cache_page(NODE_MAPPING(sbi), nid, false); if (!page) return ERR_PTR(-ENOMEM); @@ -1063,106 +1138,301 @@ repeat: if (err < 0) { f2fs_put_page(page, 1); return ERR_PTR(err); - } else if (err != LOCKED_PAGE) { - lock_page(page); + } else if (err == LOCKED_PAGE) { + goto page_hit; } - if (unlikely(!PageUptodate(page) || nid != nid_of_node(page))) { - ClearPageUptodate(page); - f2fs_put_page(page, 1); - return ERR_PTR(-EIO); - } + if (parent) + ra_node_pages(parent, start + 1, MAX_RA_NODE); + + lock_page(page); + if (unlikely(page->mapping != NODE_MAPPING(sbi))) { f2fs_put_page(page, 1); goto repeat; } + + if (unlikely(!PageUptodate(page))) + goto out_err; +page_hit: + if(unlikely(nid != nid_of_node(page))) { + f2fs_bug_on(sbi, 1); + ClearPageUptodate(page); +out_err: + f2fs_put_page(page, 1); + return ERR_PTR(-EIO); + } return page; } -/* - * Return a locked page for the desired node page. - * And, readahead MAX_RA_NODE number of node pages. - */ +struct page *get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid) +{ + return __get_node_page(sbi, nid, NULL, 0); +} + struct page *get_node_page_ra(struct page *parent, int start) { struct f2fs_sb_info *sbi = F2FS_P_SB(parent); - struct blk_plug plug; + nid_t nid = get_nid(parent, start, false); + + return __get_node_page(sbi, nid, parent, start); +} + +static void flush_inline_data(struct f2fs_sb_info *sbi, nid_t ino) +{ + struct inode *inode; struct page *page; - int err, i, end; - nid_t nid; + int ret; - /* First, try getting the desired direct node. */ - nid = get_nid(parent, start, false); - if (!nid) - return ERR_PTR(-ENOENT); -repeat: - page = grab_cache_page(NODE_MAPPING(sbi), nid); + /* should flush inline_data before evict_inode */ + inode = ilookup(sbi->sb, ino); + if (!inode) + return; + + page = pagecache_get_page(inode->i_mapping, 0, FGP_LOCK|FGP_NOWAIT, 0); if (!page) - return ERR_PTR(-ENOMEM); + goto iput_out; - err = read_node_page(page, READ_SYNC); - if (err < 0) { - f2fs_put_page(page, 1); - return ERR_PTR(err); - } else if (err == LOCKED_PAGE) { - goto page_hit; - } + if (!PageUptodate(page)) + goto page_out; - blk_start_plug(&plug); + if (!PageDirty(page)) + goto page_out; - /* Then, try readahead for siblings of the desired node */ - end = start + MAX_RA_NODE; - end = min(end, NIDS_PER_BLOCK); - for (i = start + 1; i < end; i++) { - nid = get_nid(parent, i, false); - if (!nid) - continue; - ra_node_page(sbi, nid); - } + if (!clear_page_dirty_for_io(page)) + goto page_out; - blk_finish_plug(&plug); + ret = f2fs_write_inline_data(inode, page); + inode_dec_dirty_pages(inode); + remove_dirty_inode(inode); + if (ret) + set_page_dirty(page); +page_out: + f2fs_put_page(page, 1); +iput_out: + iput(inode); +} - lock_page(page); - if (unlikely(page->mapping != NODE_MAPPING(sbi))) { - f2fs_put_page(page, 1); - goto repeat; - } -page_hit: - if (unlikely(!PageUptodate(page))) { - f2fs_put_page(page, 1); - return ERR_PTR(-EIO); +void move_node_page(struct page *node_page, int gc_type) +{ + if (gc_type == FG_GC) { + struct f2fs_sb_info *sbi = F2FS_P_SB(node_page); + struct writeback_control wbc = { + .sync_mode = WB_SYNC_ALL, + .nr_to_write = 1, + .for_reclaim = 0, + }; + + set_page_dirty(node_page); + f2fs_wait_on_page_writeback(node_page, NODE, true); + + f2fs_bug_on(sbi, PageWriteback(node_page)); + if (!clear_page_dirty_for_io(node_page)) + goto out_page; + + if (NODE_MAPPING(sbi)->a_ops->writepage(node_page, &wbc)) + unlock_page(node_page); + goto release_page; + } else { + /* set page dirty and write it */ + if (!PageWriteback(node_page)) + set_page_dirty(node_page); + } +out_page: + unlock_page(node_page); +release_page: + f2fs_put_page(node_page, 0); +} + +static struct page *last_fsync_dnode(struct f2fs_sb_info *sbi, nid_t ino) +{ + pgoff_t index, end; + struct pagevec pvec; + struct page *last_page = NULL; + + pagevec_init(&pvec, 0); + index = 0; + end = ULONG_MAX; + + while (index <= end) { + int i, nr_pages; + nr_pages = pagevec_lookup_tag(&pvec, NODE_MAPPING(sbi), &index, + PAGECACHE_TAG_DIRTY, + min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1); + if (nr_pages == 0) + break; + + for (i = 0; i < nr_pages; i++) { + struct page *page = pvec.pages[i]; + + if (unlikely(f2fs_cp_error(sbi))) { + f2fs_put_page(last_page, 0); + pagevec_release(&pvec); + return ERR_PTR(-EIO); + } + + if (!IS_DNODE(page) || !is_cold_node(page)) + continue; + if (ino_of_node(page) != ino) + continue; + + lock_page(page); + + if (unlikely(page->mapping != NODE_MAPPING(sbi))) { +continue_unlock: + unlock_page(page); + continue; + } + if (ino_of_node(page) != ino) + goto continue_unlock; + + if (!PageDirty(page)) { + /* someone wrote it for us */ + goto continue_unlock; + } + + if (last_page) + f2fs_put_page(last_page, 0); + + get_page(page); + last_page = page; + unlock_page(page); + } + pagevec_release(&pvec); + cond_resched(); } - return page; + return last_page; } -void sync_inode_page(struct dnode_of_data *dn) +int fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode, + struct writeback_control *wbc, bool atomic) { - if (IS_INODE(dn->node_page) || dn->inode_page == dn->node_page) { - update_inode(dn->inode, dn->node_page); - } else if (dn->inode_page) { - if (!dn->inode_page_locked) - lock_page(dn->inode_page); - update_inode(dn->inode, dn->inode_page); - if (!dn->inode_page_locked) - unlock_page(dn->inode_page); - } else { - update_inode_page(dn->inode); + pgoff_t index, end; + struct pagevec pvec; + int ret = 0; + struct page *last_page = NULL; + bool marked = false; + nid_t ino = inode->i_ino; + int nwritten = 0; + + if (atomic) { + last_page = last_fsync_dnode(sbi, ino); + if (IS_ERR_OR_NULL(last_page)) + return PTR_ERR_OR_ZERO(last_page); + } +retry: + pagevec_init(&pvec, 0); + index = 0; + end = ULONG_MAX; + + while (index <= end) { + int i, nr_pages; + nr_pages = pagevec_lookup_tag(&pvec, NODE_MAPPING(sbi), &index, + PAGECACHE_TAG_DIRTY, + min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1); + if (nr_pages == 0) + break; + + for (i = 0; i < nr_pages; i++) { + struct page *page = pvec.pages[i]; + + if (unlikely(f2fs_cp_error(sbi))) { + f2fs_put_page(last_page, 0); + pagevec_release(&pvec); + ret = -EIO; + goto out; + } + + if (!IS_DNODE(page) || !is_cold_node(page)) + continue; + if (ino_of_node(page) != ino) + continue; + + lock_page(page); + + if (unlikely(page->mapping != NODE_MAPPING(sbi))) { +continue_unlock: + unlock_page(page); + continue; + } + if (ino_of_node(page) != ino) + goto continue_unlock; + + if (!PageDirty(page) && page != last_page) { + /* someone wrote it for us */ + goto continue_unlock; + } + + f2fs_wait_on_page_writeback(page, NODE, true); + BUG_ON(PageWriteback(page)); + + if (!atomic || page == last_page) { + set_fsync_mark(page, 1); + if (IS_INODE(page)) { + if (is_inode_flag_set(inode, + FI_DIRTY_INODE)) + update_inode(inode, page); + set_dentry_mark(page, + need_dentry_mark(sbi, ino)); + } + /* may be written by other thread */ + if (!PageDirty(page)) + set_page_dirty(page); + } + + if (!clear_page_dirty_for_io(page)) + goto continue_unlock; + + ret = NODE_MAPPING(sbi)->a_ops->writepage(page, wbc); + if (ret) { + unlock_page(page); + f2fs_put_page(last_page, 0); + break; + } else { + nwritten++; + } + + if (page == last_page) { + f2fs_put_page(page, 0); + marked = true; + break; + } + } + pagevec_release(&pvec); + cond_resched(); + + if (ret || marked) + break; } + if (!ret && atomic && !marked) { + f2fs_msg(sbi->sb, KERN_DEBUG, + "Retry to write fsync mark: ino=%u, idx=%lx", + ino, last_page->index); + lock_page(last_page); + f2fs_wait_on_page_writeback(last_page, NODE, true); + set_page_dirty(last_page); + unlock_page(last_page); + goto retry; + } +out: + if (nwritten) + f2fs_submit_merged_bio_cond(sbi, NULL, NULL, ino, NODE, WRITE); + return ret ? -EIO: 0; } -int sync_node_pages(struct f2fs_sb_info *sbi, nid_t ino, - struct writeback_control *wbc) +int sync_node_pages(struct f2fs_sb_info *sbi, struct writeback_control *wbc) { pgoff_t index, end; struct pagevec pvec; - int step = ino ? 2 : 0; - int nwritten = 0, wrote = 0; + int step = 0; + int nwritten = 0; + int ret = 0; pagevec_init(&pvec, 0); next_step: index = 0; - end = LONG_MAX; + end = ULONG_MAX; while (index <= end) { int i, nr_pages; @@ -1175,6 +1445,12 @@ next_step: for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; + if (unlikely(f2fs_cp_error(sbi))) { + pagevec_release(&pvec); + ret = -EIO; + goto out; + } + /* * flushing sequence with step: * 0. indirect nodes @@ -1189,14 +1465,8 @@ next_step: if (step == 2 && (!IS_DNODE(page) || !is_cold_node(page))) continue; - - /* - * If an fsync mode, - * we should not skip writing node pages. - */ - if (ino && ino_of_node(page) == ino) - lock_page(page); - else if (!trylock_page(page)) +lock_node: + if (!trylock_page(page)) continue; if (unlikely(page->mapping != NODE_MAPPING(sbi))) { @@ -1204,33 +1474,33 @@ continue_unlock: unlock_page(page); continue; } - if (ino && ino_of_node(page) != ino) - goto continue_unlock; if (!PageDirty(page)) { /* someone wrote it for us */ goto continue_unlock; } + /* flush inline_data */ + if (is_inline_node(page)) { + clear_inline_node(page); + unlock_page(page); + flush_inline_data(sbi, ino_of_node(page)); + goto lock_node; + } + + f2fs_wait_on_page_writeback(page, NODE, true); + + BUG_ON(PageWriteback(page)); if (!clear_page_dirty_for_io(page)) goto continue_unlock; - /* called by fsync() */ - if (ino && IS_DNODE(page)) { - set_fsync_mark(page, 1); - if (IS_INODE(page)) - set_dentry_mark(page, - need_dentry_mark(sbi, ino)); - nwritten++; - } else { - set_fsync_mark(page, 0); - set_dentry_mark(page, 0); - } + set_fsync_mark(page, 0); + set_dentry_mark(page, 0); if (NODE_MAPPING(sbi)->a_ops->writepage(page, wbc)) unlock_page(page); else - wrote++; + nwritten++; if (--wbc->nr_to_write == 0) break; @@ -1248,15 +1518,15 @@ continue_unlock: step++; goto next_step; } - - if (wrote) +out: + if (nwritten) f2fs_submit_merged_bio(sbi, NODE, WRITE); - return nwritten; + return ret; } int wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, nid_t ino) { - pgoff_t index = 0, end = LONG_MAX; + pgoff_t index = 0, end = ULONG_MAX; struct pagevec pvec; int ret2 = 0, ret = 0; @@ -1278,7 +1548,7 @@ int wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, nid_t ino) continue; if (ino && ino_of_node(page) == ino) { - f2fs_wait_on_page_writeback(page, NODE); + f2fs_wait_on_page_writeback(page, NODE, true); if (TestClearPageError(page)) ret = -EIO; } @@ -1317,8 +1587,6 @@ static int f2fs_write_node_page(struct page *page, if (unlikely(f2fs_cp_error(sbi))) goto redirty_out; - f2fs_wait_on_page_writeback(page, NODE); - /* get old block addr of this node page */ nid = nid_of_node(page); f2fs_bug_on(sbi, page->index != nid); @@ -1342,14 +1610,18 @@ static int f2fs_write_node_page(struct page *page, } set_page_writeback(page); - fio.blk_addr = ni.blk_addr; + fio.old_blkaddr = ni.blk_addr; write_node_page(nid, &fio); - set_node_addr(sbi, &ni, fio.blk_addr, is_fsync_dnode(page)); + set_node_addr(sbi, &ni, fio.new_blkaddr, is_fsync_dnode(page)); dec_page_count(sbi, F2FS_DIRTY_NODES); up_read(&sbi->node_write); - unlock_page(page); if (wbc->for_reclaim) + f2fs_submit_merged_bio_cond(sbi, NULL, page, 0, NODE, WRITE); + + unlock_page(page); + + if (unlikely(f2fs_cp_error(sbi))) f2fs_submit_merged_bio(sbi, NODE, WRITE); return 0; @@ -1363,10 +1635,9 @@ static int f2fs_write_node_pages(struct address_space *mapping, struct writeback_control *wbc) { struct f2fs_sb_info *sbi = F2FS_M_SB(mapping); + struct blk_plug plug; long diff; - trace_f2fs_writepages(mapping->host, wbc, NODE); - /* balancing f2fs's metadata in background */ f2fs_balance_fs_bg(sbi); @@ -1374,14 +1645,19 @@ static int f2fs_write_node_pages(struct address_space *mapping, if (get_pages(sbi, F2FS_DIRTY_NODES) < nr_pages_to_skip(sbi, NODE)) goto skip_write; + trace_f2fs_writepages(mapping->host, wbc, NODE); + diff = nr_pages_to_write(sbi, NODE, wbc); wbc->sync_mode = WB_SYNC_NONE; - sync_node_pages(sbi, 0, wbc); + blk_start_plug(&plug); + sync_node_pages(sbi, wbc); + blk_finish_plug(&plug); wbc->nr_to_write = max((long)0, wbc->nr_to_write - diff); return 0; skip_write: wbc->pages_skipped += get_pages(sbi, F2FS_DIRTY_NODES); + trace_f2fs_writepages(mapping->host, wbc, NODE); return 0; } @@ -1389,9 +1665,10 @@ static int f2fs_set_node_page_dirty(struct page *page) { trace_f2fs_set_page_dirty(page, NODE); - SetPageUptodate(page); + if (!PageUptodate(page)) + SetPageUptodate(page); if (!PageDirty(page)) { - __set_page_dirty_nobuffers(page); + f2fs_set_page_dirty_nobuffers(page); inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_NODES); SetPagePrivate(page); f2fs_trace_pid(page); @@ -1409,6 +1686,9 @@ const struct address_space_operations f2fs_node_aops = { .set_page_dirty = f2fs_set_node_page_dirty, .invalidatepage = f2fs_invalidate_page, .releasepage = f2fs_release_page, +#ifdef CONFIG_MIGRATION + .migratepage = f2fs_migrate_page, +#endif }; static struct free_nid *__lookup_free_nid_list(struct f2fs_nm_info *nm_i, @@ -1417,11 +1697,35 @@ static struct free_nid *__lookup_free_nid_list(struct f2fs_nm_info *nm_i, return radix_tree_lookup(&nm_i->free_nid_root, n); } -static void __del_from_free_nid_list(struct f2fs_nm_info *nm_i, - struct free_nid *i) +static int __insert_nid_to_list(struct f2fs_sb_info *sbi, + struct free_nid *i, enum nid_list list, bool new) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); + + if (new) { + int err = radix_tree_insert(&nm_i->free_nid_root, i->nid, i); + if (err) + return err; + } + + f2fs_bug_on(sbi, list == FREE_NID_LIST ? i->state != NID_NEW : + i->state != NID_ALLOC); + nm_i->nid_cnt[list]++; + list_add_tail(&i->list, &nm_i->nid_list[list]); + return 0; +} + +static void __remove_nid_from_list(struct f2fs_sb_info *sbi, + struct free_nid *i, enum nid_list list, bool reuse) { + struct f2fs_nm_info *nm_i = NM_I(sbi); + + f2fs_bug_on(sbi, list == FREE_NID_LIST ? i->state != NID_NEW : + i->state != NID_ALLOC); + nm_i->nid_cnt[list]--; list_del(&i->list); - radix_tree_delete(&nm_i->free_nid_root, i->nid); + if (!reuse) + radix_tree_delete(&nm_i->free_nid_root, i->nid); } static int add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build) @@ -1429,10 +1733,7 @@ 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 nat_entry *ne; - bool allocated = false; - - if (!available_free_memory(sbi, FREE_NIDS)) - return -1; + int err; /* 0 nid should not be used */ if (unlikely(nid == 0)) @@ -1440,14 +1741,9 @@ static int add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build) 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) || + 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; } @@ -1460,33 +1756,30 @@ static int add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build) return 0; } - 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(); + spin_lock(&nm_i->nid_list_lock); + err = __insert_nid_to_list(sbi, i, FREE_NID_LIST, true); + spin_unlock(&nm_i->nid_list_lock); + radix_tree_preload_end(); + if (err) { kmem_cache_free(free_nid_slab, i); return 0; } - list_add_tail(&i->list, &nm_i->free_nid_list); - nm_i->fcnt++; - spin_unlock(&nm_i->free_nid_list_lock); - radix_tree_preload_end(); return 1; } -static void remove_free_nid(struct f2fs_nm_info *nm_i, nid_t nid) +static void remove_free_nid(struct f2fs_sb_info *sbi, nid_t nid) { + struct f2fs_nm_info *nm_i = NM_I(sbi); struct free_nid *i; bool need_free = false; - spin_lock(&nm_i->free_nid_list_lock); + spin_lock(&nm_i->nid_list_lock); i = __lookup_free_nid_list(nm_i, nid); if (i && i->state == NID_NEW) { - __del_from_free_nid_list(nm_i, i); - nm_i->fcnt--; + __remove_nid_from_list(sbi, i, FREE_NID_LIST, false); need_free = true; } - spin_unlock(&nm_i->free_nid_list_lock); + spin_unlock(&nm_i->nid_list_lock); if (need_free) kmem_cache_free(free_nid_slab, i); @@ -1509,29 +1802,32 @@ static void scan_nat_page(struct f2fs_sb_info *sbi, blk_addr = le32_to_cpu(nat_blk->entries[i].block_addr); f2fs_bug_on(sbi, blk_addr == NEW_ADDR); - if (blk_addr == NULL_ADDR) { - if (add_free_nid(sbi, start_nid, true) < 0) - break; - } + if (blk_addr == NULL_ADDR) + add_free_nid(sbi, start_nid, true); } } -static void build_free_nids(struct f2fs_sb_info *sbi) +static void __build_free_nids(struct f2fs_sb_info *sbi, bool sync) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA); - struct f2fs_summary_block *sum = curseg->sum_blk; + struct f2fs_journal *journal = curseg->journal; int i = 0; nid_t nid = nm_i->next_scan_nid; /* Enough entries */ - if (nm_i->fcnt > NAT_ENTRY_PER_BLOCK) + if (nm_i->nid_cnt[FREE_NID_LIST] >= NAT_ENTRY_PER_BLOCK) + return; + + if (!sync && !available_free_memory(sbi, FREE_NIDS)) return; /* readahead nat pages to be scanned */ 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); @@ -1550,21 +1846,31 @@ static void build_free_nids(struct f2fs_sb_info *sbi) nm_i->next_scan_nid = nid; /* find free nids from current sum_pages */ - mutex_lock(&curseg->curseg_mutex); - for (i = 0; i < nats_in_cursum(sum); i++) { - block_t addr = le32_to_cpu(nat_in_journal(sum, i).block_addr); - nid = le32_to_cpu(nid_in_journal(sum, i)); + down_read(&curseg->journal_rwsem); + for (i = 0; i < nats_in_cursum(journal); i++) { + block_t addr; + + addr = le32_to_cpu(nat_in_journal(journal, i).block_addr); + nid = le32_to_cpu(nid_in_journal(journal, i)); if (addr == NULL_ADDR) add_free_nid(sbi, nid, true); else - remove_free_nid(nm_i, nid); + remove_free_nid(sbi, nid); } - mutex_unlock(&curseg->curseg_mutex); + up_read(&curseg->journal_rwsem); + 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); } +void build_free_nids(struct f2fs_sb_info *sbi, bool sync) +{ + mutex_lock(&NM_I(sbi)->build_lock); + __build_free_nids(sbi, sync); + mutex_unlock(&NM_I(sbi)->build_lock); +} + /* * If this function returns success, caller can obtain a new nid * from second parameter of this function. @@ -1575,40 +1881,35 @@ bool alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid) struct f2fs_nm_info *nm_i = NM_I(sbi); struct free_nid *i = NULL; retry: - if (unlikely(sbi->total_valid_node_count + 1 > nm_i->available_nids)) +#ifdef CONFIG_F2FS_FAULT_INJECTION + if (time_to_inject(sbi, FAULT_ALLOC_NID)) return false; +#endif + spin_lock(&nm_i->nid_list_lock); - spin_lock(&nm_i->free_nid_list_lock); + if (unlikely(nm_i->available_nids == 0)) { + spin_unlock(&nm_i->nid_list_lock); + return false; + } /* We should not use stale free nids created by build_free_nids */ - if (nm_i->fcnt && !on_build_free_nids(nm_i)) { - struct node_info ni; - - f2fs_bug_on(sbi, list_empty(&nm_i->free_nid_list)); - list_for_each_entry(i, &nm_i->free_nid_list, list) - if (i->state == NID_NEW) - break; - - f2fs_bug_on(sbi, i->state != NID_NEW); + if (nm_i->nid_cnt[FREE_NID_LIST] && !on_build_free_nids(nm_i)) { + f2fs_bug_on(sbi, list_empty(&nm_i->nid_list[FREE_NID_LIST])); + i = list_first_entry(&nm_i->nid_list[FREE_NID_LIST], + struct free_nid, list); *nid = i->nid; + + __remove_nid_from_list(sbi, i, FREE_NID_LIST, true); i->state = NID_ALLOC; - nm_i->fcnt--; - spin_unlock(&nm_i->free_nid_list_lock); - - /* check nid is allocated already */ - get_node_info(sbi, *nid, &ni); - if (ni.blk_addr != NULL_ADDR) { - alloc_nid_done(sbi, *nid); - goto retry; - } + __insert_nid_to_list(sbi, i, ALLOC_NID_LIST, false); + nm_i->available_nids--; + spin_unlock(&nm_i->nid_list_lock); return true; } - spin_unlock(&nm_i->free_nid_list_lock); + spin_unlock(&nm_i->nid_list_lock); /* Let's scan nat pages and its caches to get free nids */ - mutex_lock(&nm_i->build_lock); - build_free_nids(sbi); - mutex_unlock(&nm_i->build_lock); + build_free_nids(sbi, true); goto retry; } @@ -1620,11 +1921,11 @@ void alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid) struct f2fs_nm_info *nm_i = NM_I(sbi); struct free_nid *i; - spin_lock(&nm_i->free_nid_list_lock); + spin_lock(&nm_i->nid_list_lock); i = __lookup_free_nid_list(nm_i, nid); - f2fs_bug_on(sbi, !i || i->state != NID_ALLOC); - __del_from_free_nid_list(nm_i, i); - spin_unlock(&nm_i->free_nid_list_lock); + f2fs_bug_on(sbi, !i); + __remove_nid_from_list(sbi, i, ALLOC_NID_LIST, false); + spin_unlock(&nm_i->nid_list_lock); kmem_cache_free(free_nid_slab, i); } @@ -1641,17 +1942,22 @@ void alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid) if (!nid) return; - spin_lock(&nm_i->free_nid_list_lock); + spin_lock(&nm_i->nid_list_lock); i = __lookup_free_nid_list(nm_i, nid); - f2fs_bug_on(sbi, !i || i->state != NID_ALLOC); + f2fs_bug_on(sbi, !i); + if (!available_free_memory(sbi, FREE_NIDS)) { - __del_from_free_nid_list(nm_i, i); + __remove_nid_from_list(sbi, i, ALLOC_NID_LIST, false); need_free = true; } else { + __remove_nid_from_list(sbi, i, ALLOC_NID_LIST, true); i->state = NID_NEW; - nm_i->fcnt++; + __insert_nid_to_list(sbi, i, FREE_NID_LIST, false); } - spin_unlock(&nm_i->free_nid_list_lock); + + nm_i->available_nids++; + + spin_unlock(&nm_i->nid_list_lock); if (need_free) kmem_cache_free(free_nid_slab, i); @@ -1663,21 +1969,24 @@ int try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink) struct free_nid *i, *next; int nr = nr_shrink; + if (nm_i->nid_cnt[FREE_NID_LIST] <= MAX_FREE_NIDS) + return 0; + if (!mutex_trylock(&nm_i->build_lock)) return 0; - spin_lock(&nm_i->free_nid_list_lock); - list_for_each_entry_safe(i, next, &nm_i->free_nid_list, list) { - if (nr_shrink <= 0 || nm_i->fcnt <= NAT_ENTRY_PER_BLOCK) + spin_lock(&nm_i->nid_list_lock); + list_for_each_entry_safe(i, next, &nm_i->nid_list[FREE_NID_LIST], + list) { + if (nr_shrink <= 0 || + nm_i->nid_cnt[FREE_NID_LIST] <= MAX_FREE_NIDS) break; - if (i->state == NID_ALLOC) - continue; - __del_from_free_nid_list(nm_i, i); + + __remove_nid_from_list(sbi, i, FREE_NID_LIST, false); kmem_cache_free(free_nid_slab, i); - nm_i->fcnt--; nr_shrink--; } - spin_unlock(&nm_i->free_nid_list_lock); + spin_unlock(&nm_i->nid_list_lock); mutex_unlock(&nm_i->build_lock); return nr - nr_shrink; @@ -1695,7 +2004,7 @@ void recover_inline_xattr(struct inode *inode, struct page *page) ri = F2FS_INODE(page); if (!(ri->i_inline & F2FS_INLINE_XATTR)) { - clear_inode_flag(F2FS_I(inode), FI_INLINE_XATTR); + clear_inode_flag(inode, FI_INLINE_XATTR); goto update_inode; } @@ -1703,7 +2012,7 @@ void recover_inline_xattr(struct inode *inode, struct page *page) src_addr = inline_xattr_addr(page); inline_size = inline_xattr_size(inode); - f2fs_wait_on_page_writeback(ipage, NODE); + f2fs_wait_on_page_writeback(ipage, NODE, true); memcpy(dst_addr, src_addr, inline_size); update_inode: update_inode(inode, ipage); @@ -1733,17 +2042,15 @@ recover_xnid: if (unlikely(!inc_valid_node_count(sbi, inode))) f2fs_bug_on(sbi, 1); - remove_free_nid(NM_I(sbi), new_xnid); + remove_free_nid(sbi, new_xnid); get_node_info(sbi, new_xnid, &ni); ni.ino = inode->i_ino; set_node_addr(sbi, &ni, NEW_ADDR, false); - F2FS_I(inode)->i_xattr_nid = new_xnid; + f2fs_i_xnid_write(inode, new_xnid); /* 3: update xattr blkaddr */ refresh_sit_entry(sbi, NEW_ADDR, blkaddr); set_node_addr(sbi, &ni, blkaddr, false); - - update_inode_page(inode); } int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page) @@ -1757,15 +2064,18 @@ int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page) if (unlikely(old_ni.blk_addr != NULL_ADDR)) return -EINVAL; - - ipage = grab_cache_page(NODE_MAPPING(sbi), ino); - if (!ipage) - return -ENOMEM; +retry: + ipage = f2fs_grab_cache_page(NODE_MAPPING(sbi), ino, false); + if (!ipage) { + congestion_wait(BLK_RW_ASYNC, HZ/50); + goto retry; + } /* Should not use this inode from free nid list */ - remove_free_nid(NM_I(sbi), ino); + remove_free_nid(sbi, ino); - SetPageUptodate(ipage); + if (!PageUptodate(ipage)) + SetPageUptodate(ipage); fill_node_footer(ipage, ino, ino, 0, true); src = F2FS_INODE(page); @@ -1796,7 +2106,6 @@ int restore_node_summary(struct f2fs_sb_info *sbi, struct f2fs_node *rn; struct f2fs_summary *sum_entry; block_t addr; - int bio_blocks = MAX_BIO_BLOCKS(sbi); int i, idx, last_offset, nrpages; /* scan the node segment */ @@ -1805,7 +2114,7 @@ int restore_node_summary(struct f2fs_sb_info *sbi, sum_entry = &sum->entries[0]; for (i = 0; i < last_offset; i += nrpages, addr += nrpages) { - nrpages = min(last_offset - i, bio_blocks); + nrpages = min(last_offset - i, BIO_MAX_PAGES); /* readahead node pages */ ra_meta_pages(sbi, addr, nrpages, META_POR, true); @@ -1831,28 +2140,39 @@ static void remove_nats_in_journal(struct f2fs_sb_info *sbi) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA); - struct f2fs_summary_block *sum = curseg->sum_blk; + struct f2fs_journal *journal = curseg->journal; int i; - mutex_lock(&curseg->curseg_mutex); - for (i = 0; i < nats_in_cursum(sum); i++) { + down_write(&curseg->journal_rwsem); + for (i = 0; i < nats_in_cursum(journal); i++) { struct nat_entry *ne; struct f2fs_nat_entry raw_ne; - nid_t nid = le32_to_cpu(nid_in_journal(sum, i)); + nid_t nid = le32_to_cpu(nid_in_journal(journal, i)); - raw_ne = nat_in_journal(sum, i); + raw_ne = nat_in_journal(journal, 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); } + + /* + * if a free nat in journal has not been used after last + * checkpoint, we should remove it from available nids, + * since later we will add it again. + */ + if (!get_nat_flag(ne, IS_DIRTY) && + le32_to_cpu(raw_ne.block_addr) == NULL_ADDR) { + spin_lock(&nm_i->nid_list_lock); + nm_i->available_nids--; + spin_unlock(&nm_i->nid_list_lock); + } + __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); + update_nats_in_cursum(journal, -i); + up_write(&curseg->journal_rwsem); } static void __adjust_nat_entry_set(struct nat_entry_set *nes, @@ -1877,24 +2197,23 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi, struct nat_entry_set *set) { struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA); - struct f2fs_summary_block *sum = curseg->sum_blk; + struct f2fs_journal *journal = curseg->journal; nid_t start_nid = set->set * NAT_ENTRY_PER_BLOCK; bool to_journal = true; 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: * #1, flush nat entries to journal in current hot data summary block. * #2, flush nat entries to nat page. */ - if (!__has_cursum_space(sum, set->entry_cnt, NAT_JOURNAL)) + if (!__has_cursum_space(journal, set->entry_cnt, NAT_JOURNAL)) to_journal = false; if (to_journal) { - mutex_lock(&curseg->curseg_mutex); + down_write(&curseg->journal_rwsem); } else { page = get_next_nat_page(sbi, start_nid); nat_blk = page_address(page); @@ -1911,35 +2230,33 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi, continue; if (to_journal) { - offset = lookup_journal_in_cursum(sum, + offset = lookup_journal_in_cursum(journal, NAT_JOURNAL, nid, 1); f2fs_bug_on(sbi, offset < 0); - raw_ne = &nat_in_journal(sum, offset); - nid_in_journal(sum, offset) = cpu_to_le32(nid); + raw_ne = &nat_in_journal(journal, offset); + nid_in_journal(journal, offset) = cpu_to_le32(nid); } else { 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) + if (nat_get_blkaddr(ne) == NULL_ADDR) { add_free_nid(sbi, nid, false); + spin_lock(&NM_I(sbi)->nid_list_lock); + NM_I(sbi)->available_nids++; + spin_unlock(&NM_I(sbi)->nid_list_lock); + } } if (to_journal) - mutex_unlock(&curseg->curseg_mutex); + up_write(&curseg->journal_rwsem); else f2fs_put_page(page, 1); 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); } @@ -1950,7 +2267,7 @@ void flush_nat_entries(struct f2fs_sb_info *sbi) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA); - struct f2fs_summary_block *sum = curseg->sum_blk; + struct f2fs_journal *journal = curseg->journal; struct nat_entry_set *setvec[SETVEC_SIZE]; struct nat_entry_set *set, *tmp; unsigned int found; @@ -1959,29 +2276,32 @@ 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 * into nat entry set. */ - if (!__has_cursum_space(sum, nm_i->dirty_nat_cnt, NAT_JOURNAL)) + if (!__has_cursum_space(journal, 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; set_idx = setvec[found - 1]->set + 1; for (idx = 0; idx < found; idx++) __adjust_nat_entry_set(setvec[idx], &sets, - MAX_NAT_JENTRIES(sum)); + MAX_NAT_JENTRIES(journal)); } - 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); } @@ -2001,20 +2321,24 @@ static int init_node_manager(struct f2fs_sb_info *sbi) nm_i->max_nid = NAT_ENTRY_PER_BLOCK * nat_blocks; /* not used nids: 0, node, meta, (and root counted as valid node) */ - nm_i->available_nids = nm_i->max_nid - F2FS_RESERVED_NODE_NUM; - nm_i->fcnt = 0; + nm_i->available_nids = nm_i->max_nid - sbi->total_valid_node_count - + F2FS_RESERVED_NODE_NUM; + nm_i->nid_cnt[FREE_NID_LIST] = 0; + nm_i->nid_cnt[ALLOC_NID_LIST] = 0; nm_i->nat_cnt = 0; nm_i->ram_thresh = DEF_RAM_THRESHOLD; nm_i->ra_nid_pages = DEF_RA_NID_PAGES; + nm_i->dirty_nats_ratio = DEF_DIRTY_NAT_RATIO_THRESHOLD; INIT_RADIX_TREE(&nm_i->free_nid_root, GFP_ATOMIC); - INIT_LIST_HEAD(&nm_i->free_nid_list); + INIT_LIST_HEAD(&nm_i->nid_list[FREE_NID_LIST]); + INIT_LIST_HEAD(&nm_i->nid_list[ALLOC_NID_LIST]); INIT_RADIX_TREE(&nm_i->nat_root, GFP_NOIO); INIT_RADIX_TREE(&nm_i->nat_set_root, GFP_NOIO); INIT_LIST_HEAD(&nm_i->nat_entries); mutex_init(&nm_i->build_lock); - spin_lock_init(&nm_i->free_nid_list_lock); + spin_lock_init(&nm_i->nid_list_lock); init_rwsem(&nm_i->nat_tree_lock); nm_i->next_scan_nid = le32_to_cpu(sbi->ckpt->next_free_nid); @@ -2042,7 +2366,7 @@ int build_node_manager(struct f2fs_sb_info *sbi) if (err) return err; - build_free_nids(sbi); + build_free_nids(sbi, true); return 0; } @@ -2059,17 +2383,18 @@ void destroy_node_manager(struct f2fs_sb_info *sbi) return; /* destroy free nid list */ - spin_lock(&nm_i->free_nid_list_lock); - list_for_each_entry_safe(i, next_i, &nm_i->free_nid_list, list) { - f2fs_bug_on(sbi, i->state == NID_ALLOC); - __del_from_free_nid_list(nm_i, i); - nm_i->fcnt--; - spin_unlock(&nm_i->free_nid_list_lock); + spin_lock(&nm_i->nid_list_lock); + list_for_each_entry_safe(i, next_i, &nm_i->nid_list[FREE_NID_LIST], + list) { + __remove_nid_from_list(sbi, i, FREE_NID_LIST, false); + spin_unlock(&nm_i->nid_list_lock); kmem_cache_free(free_nid_slab, i); - spin_lock(&nm_i->free_nid_list_lock); + spin_lock(&nm_i->nid_list_lock); } - f2fs_bug_on(sbi, nm_i->fcnt); - spin_unlock(&nm_i->free_nid_list_lock); + f2fs_bug_on(sbi, nm_i->nid_cnt[FREE_NID_LIST]); + f2fs_bug_on(sbi, nm_i->nid_cnt[ALLOC_NID_LIST]); + f2fs_bug_on(sbi, !list_empty(&nm_i->nid_list[ALLOC_NID_LIST])); + spin_unlock(&nm_i->nid_list_lock); /* destroy nat cache */ down_write(&nm_i->nat_tree_lock); diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h index e4fffd2d98c4..e7997e240366 100644 --- a/fs/f2fs/node.h +++ b/fs/f2fs/node.h @@ -15,15 +15,21 @@ #define NAT_BLOCK_OFFSET(start_nid) (start_nid / NAT_ENTRY_PER_BLOCK) /* # of pages to perform synchronous readahead before building free nids */ -#define FREE_NID_PAGES 4 +#define FREE_NID_PAGES 8 +#define MAX_FREE_NIDS (NAT_ENTRY_PER_BLOCK * FREE_NID_PAGES) -#define DEF_RA_NID_PAGES 4 /* # of nid pages to be readaheaded */ +#define DEF_RA_NID_PAGES 0 /* # of nid pages to be readaheaded */ /* maximum readahead size for node during getting data blocks */ #define MAX_RA_NODE 128 /* control the memory footprint threshold (10MB per 1GB ram) */ -#define DEF_RAM_THRESHOLD 10 +#define DEF_RAM_THRESHOLD 1 + +/* control dirty nats ratio threshold (default: 10% over max nid count) */ +#define DEF_DIRTY_NAT_RATIO_THRESHOLD 10 +/* control total # of nats */ +#define DEF_NAT_CACHE_THRESHOLD 100000 /* vector size for gang look-up from nat cache that consists of radix tree */ #define NATVEC_SIZE 64 @@ -117,6 +123,17 @@ static inline void raw_nat_from_node_info(struct f2fs_nat_entry *raw_ne, raw_ne->version = ni->version; } +static inline bool excess_dirty_nats(struct f2fs_sb_info *sbi) +{ + return NM_I(sbi)->dirty_nat_cnt >= NM_I(sbi)->max_nid * + NM_I(sbi)->dirty_nats_ratio / 100; +} + +static inline bool excess_cached_nats(struct f2fs_sb_info *sbi) +{ + return NM_I(sbi)->nat_cnt >= DEF_NAT_CACHE_THRESHOLD; +} + enum mem_type { FREE_NIDS, /* indicates the free nid list */ NAT_ENTRIES, /* indicates the cached nat entry */ @@ -152,14 +169,15 @@ static inline void next_free_nid(struct f2fs_sb_info *sbi, nid_t *nid) struct f2fs_nm_info *nm_i = NM_I(sbi); struct free_nid *fnid; - spin_lock(&nm_i->free_nid_list_lock); - if (nm_i->fcnt <= 0) { - spin_unlock(&nm_i->free_nid_list_lock); + spin_lock(&nm_i->nid_list_lock); + if (nm_i->nid_cnt[FREE_NID_LIST] <= 0) { + spin_unlock(&nm_i->nid_list_lock); return; } - fnid = list_entry(nm_i->free_nid_list.next, struct free_nid, list); + fnid = list_entry(nm_i->nid_list[FREE_NID_LIST].next, + struct free_nid, list); *nid = fnid->nid; - spin_unlock(&nm_i->free_nid_list_lock); + spin_unlock(&nm_i->nid_list_lock); } /* @@ -183,7 +201,7 @@ static inline pgoff_t current_nat_addr(struct f2fs_sb_info *sbi, nid_t start) block_addr = (pgoff_t)(nm_i->nat_blkaddr + (seg_off << sbi->log_blocks_per_seg << 1) + - (block_off & ((1 << sbi->log_blocks_per_seg) - 1))); + (block_off & (sbi->blocks_per_seg - 1))); if (f2fs_test_bit(block_off, nm_i->nat_bitmap)) block_addr += sbi->blocks_per_seg; @@ -212,6 +230,37 @@ 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 +291,30 @@ 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) -{ - 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) +static inline bool is_recoverable_dnode(struct page *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 cp_ver == cpver_of_node(page); } /* @@ -317,17 +356,17 @@ static inline bool IS_DNODE(struct page *node_page) return true; } -static inline void set_nid(struct page *p, int off, nid_t nid, bool i) +static inline int set_nid(struct page *p, int off, nid_t nid, bool i) { struct f2fs_node *rn = F2FS_NODE(p); - f2fs_wait_on_page_writeback(p, NODE); + f2fs_wait_on_page_writeback(p, NODE, true); if (i) rn->i.i_nid[off - NODE_DIR1_BLOCK] = cpu_to_le32(nid); else rn->in.nid[off] = cpu_to_le32(nid); - set_page_dirty(p); + return set_page_dirty(p); } static inline nid_t get_nid(struct page *p, int off, bool i) @@ -370,6 +409,21 @@ static inline int is_node(struct page *page, int type) #define is_fsync_dnode(page) is_node(page, FSYNC_BIT_SHIFT) #define is_dent_dnode(page) is_node(page, DENT_BIT_SHIFT) +static inline int is_inline_node(struct page *page) +{ + return PageChecked(page); +} + +static inline void set_inline_node(struct page *page) +{ + SetPageChecked(page); +} + +static inline void clear_inline_node(struct page *page) +{ + ClearPageChecked(page); +} + static inline void set_cold_node(struct inode *inode, struct page *page) { struct f2fs_node *rn = F2FS_NODE(page); diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index cbf74f47cce8..983c35da6bce 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -49,8 +49,9 @@ static struct kmem_cache *fsync_entry_slab; bool space_for_roll_forward(struct f2fs_sb_info *sbi) { - if (sbi->last_valid_block_count + sbi->alloc_valid_block_count - > sbi->user_block_count) + s64 nalloc = percpu_counter_sum_positive(&sbi->alloc_valid_block_count); + + if (sbi->last_valid_block_count + nalloc > sbi->user_block_count) return false; return true; } @@ -67,42 +68,71 @@ 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 f2fs_sb_info *sbi, + struct list_head *head, nid_t ino) +{ + struct inode *inode; + struct fsync_inode_entry *entry; + + inode = f2fs_iget_retry(sbi->sb, ino); + if (IS_ERR(inode)) + return ERR_CAST(inode); + + entry = f2fs_kmem_cache_alloc(fsync_entry_slab, GFP_F2FS_ZERO); + 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); struct f2fs_dir_entry *de; - struct qstr name; + struct fscrypt_name fname; struct page *page; struct inode *dir, *einode; + struct fsync_inode_entry *entry; int err = 0; + char *name; - 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) { + entry = add_fsync_inode(F2FS_I_SB(inode), dir_list, pino); + if (IS_ERR(entry)) { + dir = ERR_CAST(entry); + err = PTR_ERR(entry); + goto out; + } } - if (file_enc_name(inode)) { - iput(dir); - return 0; - } + dir = entry->inode; - name.len = le32_to_cpu(raw_inode->i_namelen); - name.name = raw_inode->i_name; + memset(&fname, 0, sizeof(struct fscrypt_name)); + fname.disk_name.len = le32_to_cpu(raw_inode->i_namelen); + fname.disk_name.name = raw_inode->i_name; - if (unlikely(name.len > F2FS_NAME_LEN)) { + if (unlikely(fname.disk_name.len > F2FS_NAME_LEN)) { WARN_ON(1); err = -ENAMETOOLONG; - goto out_err; + goto out; } retry: - de = f2fs_find_entry(dir, &name, &page); + de = __f2fs_find_entry(dir, &fname, &page); if (de && inode->i_ino == le32_to_cpu(de->ino)) goto out_unmap_put; if (de) { - einode = f2fs_iget(inode->i_sb, le32_to_cpu(de->ino)); + einode = f2fs_iget_retry(inode->i_sb, le32_to_cpu(de->ino)); if (IS_ERR(einode)) { WARN_ON(1); err = PTR_ERR(einode); @@ -118,29 +148,27 @@ retry: f2fs_delete_entry(de, page, dir, einode); iput(einode); 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 if (IS_ERR(page)) { + err = PTR_ERR(page); } else { - add_dirty_dir_inode(dir); - set_inode_flag(F2FS_I(dir), FI_DELAY_IPUT); + err = __f2fs_do_add_link(dir, &fname, inode, + inode->i_ino, inode->i_mode); } - + if (err == -ENOMEM) + goto retry; goto out; out_unmap_put: f2fs_dentry_kunmap(dir, page); f2fs_put_page(page, 0); -out_err: - iput(dir); out: + if (file_enc_name(inode)) + name = "<encrypted>"; + else + name = raw_inode->i_name; f2fs_msg(inode->i_sb, KERN_NOTICE, "%s: ino = %x, name = %s, dir = %lx, err = %d", - __func__, ino_of_node(ipage), raw_inode->i_name, + __func__, ino_of_node(ipage), name, IS_ERR(dir) ? 0 : dir->i_ino, err); return err; } @@ -151,14 +179,16 @@ static void recover_inode(struct inode *inode, struct page *page) char *name; inode->i_mode = le16_to_cpu(raw->i_mode); - i_size_write(inode, le64_to_cpu(raw->i_size)); - inode->i_atime.tv_sec = le64_to_cpu(raw->i_mtime); + f2fs_i_size_write(inode, le64_to_cpu(raw->i_size)); + inode->i_atime.tv_sec = le64_to_cpu(raw->i_atime); inode->i_ctime.tv_sec = le64_to_cpu(raw->i_ctime); inode->i_mtime.tv_sec = le64_to_cpu(raw->i_mtime); - inode->i_atime.tv_nsec = le32_to_cpu(raw->i_mtime_nsec); + inode->i_atime.tv_nsec = le32_to_cpu(raw->i_atime_nsec); inode->i_ctime.tv_nsec = le32_to_cpu(raw->i_ctime_nsec); inode->i_mtime.tv_nsec = le32_to_cpu(raw->i_mtime_nsec); + F2FS_I(inode)->i_advise = raw->i_advise; + if (file_enc_name(inode)) name = "<encrypted>"; else @@ -170,7 +200,6 @@ 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 page *page = NULL; block_t blkaddr; @@ -180,8 +209,6 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head) curseg = CURSEG_I(sbi, CURSEG_WARM_NODE); blkaddr = NEXT_FREE_BLKADDR(sbi, curseg); - ra_meta_pages(sbi, blkaddr, 1, META_POR, true); - while (1) { struct fsync_inode_entry *entry; @@ -190,7 +217,7 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head) page = get_tmp_page(sbi, blkaddr); - if (cp_ver != cpver_of_node(page)) + if (!is_recoverable_dnode(page)) break; if (!is_fsync_dnode(page)) @@ -204,35 +231,24 @@ 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); + entry = add_fsync_inode(sbi, head, ino_of_node(page)); + if (IS_ERR(entry)) { + err = PTR_ERR(entry); if (err == -ENOENT) { err = 0; goto next; } break; } - list_add_tail(&entry->list, head); } entry->blkaddr = blkaddr; - if (IS_INODE(page)) { - entry->last_inode = blkaddr; - if (is_dent_dnode(page)) - entry->last_dentry = blkaddr; - } + if (IS_INODE(page) && is_dent_dnode(page)) + entry->last_dentry = blkaddr; next: /* check next segment */ blkaddr = next_blkaddr_of_node(page); @@ -248,11 +264,8 @@ 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, @@ -276,7 +289,7 @@ static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi, return 0; /* Get the previous summary */ - for (i = CURSEG_WARM_DATA; i <= CURSEG_COLD_DATA; i++) { + for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) { struct curseg_info *curseg = CURSEG_I(sbi, i); if (curseg->segno == segno) { sum = curseg->sum_blk->entries[blkoff]; @@ -314,15 +327,14 @@ got_it: if (ino != dn->inode->i_ino) { /* Deallocate previous index in the node page */ - inode = f2fs_iget(sbi->sb, ino); + inode = f2fs_iget_retry(sbi->sb, ino); if (IS_ERR(inode)) return PTR_ERR(inode); } else { inode = dn->inode; } - bidx = start_bidx_of_node(offset, F2FS_I(inode)) + - le16_to_cpu(sum.ofs_in_node); + bidx = start_bidx_of_node(offset, inode) + le16_to_cpu(sum.ofs_in_node); /* * if inode page is locked, unlock temporarily, but its reference @@ -357,10 +369,9 @@ truncate_out: static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode, struct page *page, block_t blkaddr) { - struct f2fs_inode_info *fi = F2FS_I(inode); - unsigned int start, end; struct dnode_of_data dn; struct node_info ni; + unsigned int start, end; int err = 0, recovered = 0; /* step 1: recover xattr */ @@ -380,16 +391,21 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode, goto out; /* step 3: recover data indices */ - start = start_bidx_of_node(ofs_of_node(page), fi); - end = start + ADDRS_PER_PAGE(page, fi); + start = start_bidx_of_node(ofs_of_node(page), inode); + end = start + ADDRS_PER_PAGE(page, inode); set_new_dnode(&dn, inode, NULL, NULL, 0); - +retry_dn: err = get_dnode_of_data(&dn, start, ALLOC_NODE); - if (err) + if (err) { + if (err == -ENOMEM) { + congestion_wait(BLK_RW_ASYNC, HZ/50); + goto retry_dn; + } goto out; + } - f2fs_wait_on_page_writeback(dn.node_page, NODE); + f2fs_wait_on_page_writeback(dn.node_page, NODE, true); get_node_info(sbi, dn.nid, &ni); f2fs_bug_on(sbi, ni.ino != ino_of_node(page)); @@ -411,14 +427,17 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode, continue; } + if (!file_keep_isize(inode) && + (i_size_read(inode) <= (start << PAGE_SHIFT))) + f2fs_i_size_write(inode, (start + 1) << PAGE_SHIFT); + /* * dest is reserved block, invalidate src block * and then reserve one new block in dnode page. */ if (dest == NEW_ADDR) { truncate_data_blocks_range(&dn, 1); - err = reserve_new_block(&dn); - f2fs_bug_on(sbi, err); + reserve_new_block(&dn); continue; } @@ -427,25 +446,33 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode, if (src == NULL_ADDR) { err = reserve_new_block(&dn); +#ifdef CONFIG_F2FS_FAULT_INJECTION + while (err) + err = reserve_new_block(&dn); +#endif /* We should not get -ENOSPC */ f2fs_bug_on(sbi, err); + if (err) + goto err; } - +retry_prev: /* Check the previous node page having this index */ err = check_index_in_prev_nodes(sbi, dest, &dn); - if (err) + if (err) { + if (err == -ENOMEM) { + congestion_wait(BLK_RW_ASYNC, HZ/50); + goto retry_prev; + } goto err; + } /* write dummy data page */ f2fs_replace_block(sbi, &dn, src, dest, - ni.version, false); + ni.version, false, false); recovered++; } } - if (IS_INODE(dn.node_page)) - sync_inode_page(&dn); - copy_node_footer(dn.node_page, page); fill_node_footer(dn.node_page, dn.nid, ni.ino, ofs_of_node(page), false); @@ -454,22 +481,23 @@ err: f2fs_put_dnode(&dn); out: f2fs_msg(sbi->sb, KERN_NOTICE, - "recover_data: ino = %lx, recovered = %d blocks, err = %d", - inode->i_ino, recovered, err); + "recover_data: ino = %lx (i_size: %s) recovered = %d, err = %d", + inode->i_ino, + file_keep_isize(inode) ? "keep" : "recover", + recovered, err); 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) { @@ -482,12 +510,12 @@ static int recover_data(struct f2fs_sb_info *sbi, 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; /* @@ -495,10 +523,10 @@ static int recover_data(struct f2fs_sb_info *sbi, * In this case, we can lose the latest inode(x). * So, call recover_inode for the inode update. */ - if (entry->last_inode == blkaddr) + if (IS_INODE(page)) 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 +538,8 @@ 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 +550,14 @@ 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 +566,7 @@ 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); @@ -547,25 +575,26 @@ 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), - (loff_t)MAIN_BLKADDR(sbi) << PAGE_CACHE_SHIFT, -1); + (loff_t)MAIN_BLKADDR(sbi) << PAGE_SHIFT, -1); if (err) { truncate_inode_pages_final(NODE_MAPPING(sbi)); @@ -573,31 +602,20 @@ 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, 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); + err = write_checkpoint(sbi, &cpc); } - 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 7965957dd0e6..a288de069164 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -86,6 +86,7 @@ static inline unsigned long __reverse_ffs(unsigned long word) /* * __find_rev_next(_zero)_bit is copied from lib/find_next_bit.c because * f2fs_set_bit makes MSB and LSB reversed in a byte. + * @size must be integral times of unsigned long. * Example: * MSB <--> LSB * f2fs_set_bit(0, bitmap) => 1000 0000 @@ -95,94 +96,73 @@ static unsigned long __find_rev_next_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { const unsigned long *p = addr + BIT_WORD(offset); - unsigned long result = offset & ~(BITS_PER_LONG - 1); + unsigned long result = size; unsigned long tmp; if (offset >= size) return size; - size -= result; + size -= (offset & ~(BITS_PER_LONG - 1)); offset %= BITS_PER_LONG; - if (!offset) - goto aligned; - - tmp = __reverse_ulong((unsigned char *)p); - tmp &= ~0UL >> offset; - - if (size < BITS_PER_LONG) - goto found_first; - if (tmp) - goto found_middle; - - size -= BITS_PER_LONG; - result += BITS_PER_LONG; - p++; -aligned: - while (size & ~(BITS_PER_LONG-1)) { + + while (1) { + if (*p == 0) + goto pass; + tmp = __reverse_ulong((unsigned char *)p); + + tmp &= ~0UL >> offset; + if (size < BITS_PER_LONG) + tmp &= (~0UL << (BITS_PER_LONG - size)); if (tmp) - goto found_middle; - result += BITS_PER_LONG; + goto found; +pass: + if (size <= BITS_PER_LONG) + break; size -= BITS_PER_LONG; + offset = 0; p++; } - if (!size) - return result; - - tmp = __reverse_ulong((unsigned char *)p); -found_first: - tmp &= (~0UL << (BITS_PER_LONG - size)); - if (!tmp) /* Are any bits set? */ - return result + size; /* Nope. */ -found_middle: - return result + __reverse_ffs(tmp); + return result; +found: + return result - size + __reverse_ffs(tmp); } static unsigned long __find_rev_next_zero_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { const unsigned long *p = addr + BIT_WORD(offset); - unsigned long result = offset & ~(BITS_PER_LONG - 1); + unsigned long result = size; unsigned long tmp; if (offset >= size) return size; - size -= result; + size -= (offset & ~(BITS_PER_LONG - 1)); offset %= BITS_PER_LONG; - if (!offset) - goto aligned; - - tmp = __reverse_ulong((unsigned char *)p); - tmp |= ~((~0UL << offset) >> offset); - - if (size < BITS_PER_LONG) - goto found_first; - if (tmp != ~0UL) - goto found_middle; - - size -= BITS_PER_LONG; - result += BITS_PER_LONG; - p++; -aligned: - while (size & ~(BITS_PER_LONG - 1)) { + + while (1) { + if (*p == ~0UL) + goto pass; + tmp = __reverse_ulong((unsigned char *)p); + + if (offset) + tmp |= ~0UL << (BITS_PER_LONG - offset); + if (size < BITS_PER_LONG) + tmp |= ~0UL >> size; if (tmp != ~0UL) - goto found_middle; - result += BITS_PER_LONG; + goto found; +pass: + if (size <= BITS_PER_LONG) + break; size -= BITS_PER_LONG; + offset = 0; p++; } - if (!size) - return result; - - tmp = __reverse_ulong((unsigned char *)p); -found_first: - tmp |= ~(~0UL << (BITS_PER_LONG - size)); - if (tmp == ~0UL) /* Are any bits zero? */ - return result + size; /* Nope. */ -found_middle: - return result + __reverse_ffz(tmp); + return result; +found: + return result - size + __reverse_ffz(tmp); } void register_inmem_page(struct inode *inode, struct page *page) @@ -211,69 +191,150 @@ void register_inmem_page(struct inode *inode, struct page *page) trace_f2fs_register_inmem_page(page, INMEM); } -int commit_inmem_pages(struct inode *inode, bool abort) +static int __revoke_inmem_pages(struct inode *inode, + struct list_head *head, bool drop, bool recover) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct inmem_pages *cur, *tmp; + int err = 0; + + list_for_each_entry_safe(cur, tmp, head, list) { + struct page *page = cur->page; + + if (drop) + trace_f2fs_commit_inmem_page(page, INMEM_DROP); + + lock_page(page); + + if (recover) { + struct dnode_of_data dn; + struct node_info ni; + + trace_f2fs_commit_inmem_page(page, INMEM_REVOKE); + + set_new_dnode(&dn, inode, NULL, NULL, 0); + if (get_dnode_of_data(&dn, page->index, LOOKUP_NODE)) { + err = -EAGAIN; + goto next; + } + get_node_info(sbi, dn.nid, &ni); + f2fs_replace_block(sbi, &dn, dn.data_blkaddr, + cur->old_addr, ni.version, true, true); + f2fs_put_dnode(&dn); + } +next: + /* we don't need to invalidate this in the sccessful status */ + if (drop || recover) + ClearPageUptodate(page); + set_page_private(page, 0); + ClearPagePrivate(page); + f2fs_put_page(page, 1); + + list_del(&cur->list); + kmem_cache_free(inmem_entry_slab, cur); + dec_page_count(F2FS_I_SB(inode), F2FS_INMEM_PAGES); + } + return err; +} + +void drop_inmem_pages(struct inode *inode) +{ + struct f2fs_inode_info *fi = F2FS_I(inode); + + clear_inode_flag(inode, FI_ATOMIC_FILE); + + mutex_lock(&fi->inmem_lock); + __revoke_inmem_pages(inode, &fi->inmem_pages, true, false); + mutex_unlock(&fi->inmem_lock); +} + +static int __commit_inmem_pages(struct inode *inode, + struct list_head *revoke_list) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct f2fs_inode_info *fi = F2FS_I(inode); struct inmem_pages *cur, *tmp; - bool submit_bio = false; struct f2fs_io_info fio = { .sbi = sbi, .type = DATA, .rw = WRITE_SYNC | REQ_PRIO, .encrypted_page = NULL, }; + bool submit_bio = false; int err = 0; - /* - * The abort is true only when f2fs_evict_inode is called. - * Basically, the f2fs_evict_inode doesn't produce any data writes, so - * that we don't need to call f2fs_balance_fs. - * Otherwise, f2fs_gc in f2fs_balance_fs can wait forever until this - * inode becomes free by iget_locked in f2fs_iget. - */ - if (!abort) { - f2fs_balance_fs(sbi); - f2fs_lock_op(sbi); - } - - mutex_lock(&fi->inmem_lock); list_for_each_entry_safe(cur, tmp, &fi->inmem_pages, list) { - lock_page(cur->page); - if (!abort) { - if (cur->page->mapping == inode->i_mapping) { - set_page_dirty(cur->page); - f2fs_wait_on_page_writeback(cur->page, DATA); - if (clear_page_dirty_for_io(cur->page)) - inode_dec_dirty_pages(inode); - trace_f2fs_commit_inmem_page(cur->page, INMEM); - fio.page = cur->page; - err = do_write_data_page(&fio); - if (err) { - unlock_page(cur->page); - break; - } - clear_cold_data(cur->page); - submit_bio = true; + struct page *page = cur->page; + + lock_page(page); + if (page->mapping == inode->i_mapping) { + trace_f2fs_commit_inmem_page(page, INMEM); + + set_page_dirty(page); + f2fs_wait_on_page_writeback(page, DATA, true); + if (clear_page_dirty_for_io(page)) { + inode_dec_dirty_pages(inode); + remove_dirty_inode(inode); } - } else { - trace_f2fs_commit_inmem_page(cur->page, INMEM_DROP); + + fio.page = page; + err = do_write_data_page(&fio); + if (err) { + unlock_page(page); + break; + } + + /* record old blkaddr for revoking */ + cur->old_addr = fio.old_blkaddr; + + submit_bio = true; } - set_page_private(cur->page, 0); - ClearPagePrivate(cur->page); - f2fs_put_page(cur->page, 1); + unlock_page(page); + list_move_tail(&cur->list, revoke_list); + } - list_del(&cur->list); - kmem_cache_free(inmem_entry_slab, cur); - dec_page_count(F2FS_I_SB(inode), F2FS_INMEM_PAGES); + if (submit_bio) + f2fs_submit_merged_bio_cond(sbi, inode, NULL, 0, DATA, WRITE); + + if (!err) + __revoke_inmem_pages(inode, revoke_list, false, false); + + return err; +} + +int commit_inmem_pages(struct inode *inode) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct f2fs_inode_info *fi = F2FS_I(inode); + struct list_head revoke_list; + int err; + + INIT_LIST_HEAD(&revoke_list); + f2fs_balance_fs(sbi, true); + f2fs_lock_op(sbi); + + mutex_lock(&fi->inmem_lock); + err = __commit_inmem_pages(inode, &revoke_list); + if (err) { + int ret; + /* + * try to revoke all committed pages, but still we could fail + * due to no memory or other reason, if that happened, EAGAIN + * will be returned, which means in such case, transaction is + * already not integrity, caller should use journal to do the + * recovery or rewrite & commit last transaction. For other + * error number, revoking was done by filesystem itself. + */ + ret = __revoke_inmem_pages(inode, &revoke_list, false, true); + if (ret) + err = ret; + + /* drop all uncommitted pages */ + __revoke_inmem_pages(inode, &fi->inmem_pages, true, false); } mutex_unlock(&fi->inmem_lock); - if (!abort) { - f2fs_unlock_op(sbi); - if (submit_bio) - f2fs_submit_merged_bio(sbi, DATA, WRITE); - } + f2fs_unlock_op(sbi); return err; } @@ -281,15 +342,27 @@ int commit_inmem_pages(struct inode *inode, bool abort) * This function balances dirty node and dentry pages. * In addition, it controls garbage collection. */ -void f2fs_balance_fs(struct f2fs_sb_info *sbi) +void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need) { +#ifdef CONFIG_F2FS_FAULT_INJECTION + if (time_to_inject(sbi, FAULT_CHECKPOINT)) + f2fs_stop_checkpoint(sbi, false); +#endif + + if (!need) + return; + + /* balance_fs_bg is able to be pending */ + if (excess_cached_nats(sbi)) + f2fs_balance_fs_bg(sbi); + /* * We should do GC or end up with checkpoint, if there are so many dirty * dir/node pages without enough free segments. */ - if (has_not_enough_free_secs(sbi, 0)) { + if (has_not_enough_free_secs(sbi, 0, 0)) { mutex_lock(&sbi->gc_mutex); - f2fs_gc(sbi, false); + f2fs_gc(sbi, false, false); } } @@ -304,14 +377,55 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi) try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK); if (!available_free_memory(sbi, FREE_NIDS)) - try_to_free_nids(sbi, NAT_ENTRY_PER_BLOCK * FREE_NID_PAGES); + try_to_free_nids(sbi, MAX_FREE_NIDS); + else + build_free_nids(sbi, false); + + if (!is_idle(sbi)) + return; /* checkpoint is the only way to shrink partial cached entries */ if (!available_free_memory(sbi, NAT_ENTRIES) || - excess_prefree_segs(sbi) || !available_free_memory(sbi, INO_ENTRIES) || - jiffies > sbi->cp_expires) + excess_prefree_segs(sbi) || + excess_dirty_nats(sbi) || + f2fs_time_over(sbi, CP_TIME)) { + if (test_opt(sbi, DATA_FLUSH)) { + struct blk_plug plug; + + blk_start_plug(&plug); + sync_dirty_inodes(sbi, FILE_INODE); + blk_finish_plug(&plug); + } f2fs_sync_fs(sbi->sb, true); + stat_inc_bg_cp_count(sbi->stat_info); + } +} + +static int __submit_flush_wait(struct block_device *bdev) +{ + struct bio *bio = f2fs_bio_alloc(0); + int ret; + + bio->bi_bdev = bdev; + ret = submit_bio_wait(WRITE_FLUSH, bio); + bio_put(bio); + return ret; +} + +static int submit_flush_wait(struct f2fs_sb_info *sbi) +{ + int ret = __submit_flush_wait(sbi->sb->s_bdev); + int i; + + if (sbi->s_ndevs && !ret) { + for (i = 1; i < sbi->s_ndevs; i++) { + ret = __submit_flush_wait(FDEV(i).bdev); + if (ret) + break; + } + } + return ret; } static int issue_flush_thread(void *data) @@ -324,24 +438,18 @@ repeat: return 0; if (!llist_empty(&fcc->issue_list)) { - struct bio *bio; struct flush_cmd *cmd, *next; int ret; - bio = f2fs_bio_alloc(0); - fcc->dispatch_list = llist_del_all(&fcc->issue_list); fcc->dispatch_list = llist_reverse_order(fcc->dispatch_list); - bio->bi_bdev = sbi->sb->s_bdev; - ret = submit_bio_wait(WRITE_FLUSH, bio); - + ret = submit_flush_wait(sbi); llist_for_each_entry_safe(cmd, next, fcc->dispatch_list, llnode) { cmd->ret = ret; complete(&cmd->wait); } - bio_put(bio); fcc->dispatch_list = NULL; } @@ -361,24 +469,30 @@ int f2fs_issue_flush(struct f2fs_sb_info *sbi) if (test_opt(sbi, NOBARRIER)) return 0; - if (!test_opt(sbi, FLUSH_MERGE)) { - struct bio *bio = f2fs_bio_alloc(0); + if (!test_opt(sbi, FLUSH_MERGE) || !atomic_read(&fcc->submit_flush)) { int ret; - bio->bi_bdev = sbi->sb->s_bdev; - ret = submit_bio_wait(WRITE_FLUSH, bio); - bio_put(bio); + atomic_inc(&fcc->submit_flush); + ret = submit_flush_wait(sbi); + atomic_dec(&fcc->submit_flush); return ret; } init_completion(&cmd.wait); + atomic_inc(&fcc->submit_flush); llist_add(&cmd.llnode, &fcc->issue_list); if (!fcc->dispatch_list) wake_up(&fcc->flush_wait_queue); - wait_for_completion(&cmd.wait); + if (fcc->f2fs_issue_flush) { + wait_for_completion(&cmd.wait); + atomic_dec(&fcc->submit_flush); + } else { + llist_del_all(&fcc->issue_list); + atomic_set(&fcc->submit_flush, 0); + } return cmd.ret; } @@ -389,12 +503,19 @@ int create_flush_cmd_control(struct f2fs_sb_info *sbi) struct flush_cmd_control *fcc; int err = 0; + if (SM_I(sbi)->cmd_control_info) { + fcc = SM_I(sbi)->cmd_control_info; + goto init_thread; + } + fcc = kzalloc(sizeof(struct flush_cmd_control), GFP_KERNEL); if (!fcc) return -ENOMEM; + atomic_set(&fcc->submit_flush, 0); init_waitqueue_head(&fcc->flush_wait_queue); init_llist_head(&fcc->issue_list); SM_I(sbi)->cmd_control_info = fcc; +init_thread: fcc->f2fs_issue_flush = kthread_run(issue_flush_thread, sbi, "f2fs_flush-%u:%u", MAJOR(dev), MINOR(dev)); if (IS_ERR(fcc->f2fs_issue_flush)) { @@ -407,14 +528,20 @@ int create_flush_cmd_control(struct f2fs_sb_info *sbi) return err; } -void destroy_flush_cmd_control(struct f2fs_sb_info *sbi) +void destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free) { struct flush_cmd_control *fcc = SM_I(sbi)->cmd_control_info; - if (fcc && fcc->f2fs_issue_flush) - kthread_stop(fcc->f2fs_issue_flush); - kfree(fcc); - SM_I(sbi)->cmd_control_info = NULL; + if (fcc && fcc->f2fs_issue_flush) { + struct task_struct *flush_thread = fcc->f2fs_issue_flush; + + fcc->f2fs_issue_flush = NULL; + kthread_stop(flush_thread); + } + if (free) { + kfree(fcc); + SM_I(sbi)->cmd_control_info = NULL; + } } static void __locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno, @@ -493,46 +620,107 @@ static void locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno) mutex_unlock(&dirty_i->seglist_lock); } -static int f2fs_issue_discard(struct f2fs_sb_info *sbi, - block_t blkstart, block_t blklen) +#ifdef CONFIG_BLK_DEV_ZONED +static int __f2fs_issue_discard_zone(struct f2fs_sb_info *sbi, + struct block_device *bdev, block_t blkstart, block_t blklen) +{ + sector_t nr_sects = SECTOR_FROM_BLOCK(blklen); + sector_t sector; + int devi = 0; + + if (sbi->s_ndevs) { + devi = f2fs_target_device_index(sbi, blkstart); + blkstart -= FDEV(devi).start_blk; + } + sector = SECTOR_FROM_BLOCK(blkstart); + + if (sector & (bdev_zone_size(bdev) - 1) || + nr_sects != bdev_zone_size(bdev)) { + f2fs_msg(sbi->sb, KERN_INFO, + "(%d) %s: Unaligned discard attempted (block %x + %x)", + devi, sbi->s_ndevs ? FDEV(devi).path: "", + blkstart, blklen); + return -EIO; + } + + /* + * We need to know the type of the zone: for conventional zones, + * use regular discard if the drive supports it. For sequential + * zones, reset the zone write pointer. + */ + switch (get_blkz_type(sbi, bdev, blkstart)) { + + case BLK_ZONE_TYPE_CONVENTIONAL: + if (!blk_queue_discard(bdev_get_queue(bdev))) + return 0; + return blkdev_issue_discard(bdev, sector, nr_sects, + GFP_NOFS, 0); + case BLK_ZONE_TYPE_SEQWRITE_REQ: + case BLK_ZONE_TYPE_SEQWRITE_PREF: + trace_f2fs_issue_reset_zone(sbi->sb, blkstart); + return blkdev_reset_zones(bdev, sector, + nr_sects, GFP_NOFS); + default: + /* Unknown zone type: broken device ? */ + return -EIO; + } +} +#endif + +static int __issue_discard_async(struct f2fs_sb_info *sbi, + struct block_device *bdev, block_t blkstart, block_t blklen) { sector_t start = SECTOR_FROM_BLOCK(blkstart); sector_t len = SECTOR_FROM_BLOCK(blklen); + +#ifdef CONFIG_BLK_DEV_ZONED + if (f2fs_sb_mounted_blkzoned(sbi->sb) && + bdev_zoned_model(bdev) != BLK_ZONED_NONE) + return __f2fs_issue_discard_zone(sbi, bdev, blkstart, blklen); +#endif + return blkdev_issue_discard(bdev, start, len, GFP_NOFS, 0); +} + +static int f2fs_issue_discard(struct f2fs_sb_info *sbi, + block_t blkstart, block_t blklen) +{ + sector_t start = blkstart, len = 0; + struct block_device *bdev; struct seg_entry *se; unsigned int offset; block_t i; + int err = 0; + + bdev = f2fs_target_device(sbi, blkstart, NULL); + + for (i = blkstart; i < blkstart + blklen; i++, len++) { + if (i != start) { + struct block_device *bdev2 = + f2fs_target_device(sbi, i, NULL); + + if (bdev2 != bdev) { + err = __issue_discard_async(sbi, bdev, + start, len); + if (err) + return err; + bdev = bdev2; + start = i; + len = 0; + } + } - for (i = blkstart; i < blkstart + blklen; i++) { se = get_seg_entry(sbi, GET_SEGNO(sbi, i)); offset = GET_BLKOFF_FROM_SEG0(sbi, i); if (!f2fs_test_and_set_bit(offset, se->discard_map)) sbi->discard_blks--; } - trace_f2fs_issue_discard(sbi->sb, blkstart, blklen); - 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 (len) + err = __issue_discard_async(sbi, bdev, start, len); - if (err) { - update_meta_page(sbi, NULL, blkaddr); - return true; - } - return false; + trace_f2fs_issue_discard(sbi->sb, blkstart, blklen); + return err; } static void __add_discard_entry(struct f2fs_sb_info *sbi, @@ -573,7 +761,7 @@ static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc) bool force = (cpc->reason == CP_DISCARD); int i; - if (se->valid_blocks == max_blocks) + if (se->valid_blocks == max_blocks || !f2fs_discard_en(sbi)) return; if (!force) { @@ -593,6 +781,10 @@ static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc) break; end = __find_rev_next_zero_bit(dmap, max_blocks, start + 1); + if (force && start && end != max_blocks + && (end - start) < cpc->trim_minlen) + continue; + __add_discard_entry(sbi, cpc, se, start, end); } } @@ -630,6 +822,8 @@ void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc) struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); unsigned long *prefree_map = dirty_i->dirty_segmap[PRE]; unsigned int start = 0, end = -1; + unsigned int secno, start_segno; + bool force = (cpc->reason == CP_DISCARD); mutex_lock(&dirty_i->seglist_lock); @@ -646,17 +840,31 @@ void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc) dirty_i->nr_dirty[PRE] -= end - start; - if (!test_opt(sbi, DISCARD)) + if (force || !test_opt(sbi, DISCARD)) continue; - f2fs_issue_discard(sbi, START_BLOCK(sbi, start), + if (!test_opt(sbi, LFS) || sbi->segs_per_sec == 1) { + f2fs_issue_discard(sbi, START_BLOCK(sbi, start), (end - start) << sbi->log_blocks_per_seg); + continue; + } +next: + secno = GET_SECNO(sbi, start); + start_segno = secno * sbi->segs_per_sec; + if (!IS_CURSEC(sbi, secno) && + !get_valid_blocks(sbi, start, sbi->segs_per_sec)) + f2fs_issue_discard(sbi, START_BLOCK(sbi, start_segno), + sbi->segs_per_sec << sbi->log_blocks_per_seg); + + start = start_segno + sbi->segs_per_sec; + if (start < end) + goto next; } mutex_unlock(&dirty_i->seglist_lock); /* send small discards */ list_for_each_entry_safe(entry, this, head, list) { - if (cpc->reason == CP_DISCARD && entry->len < cpc->trim_minlen) + if (force && entry->len < cpc->trim_minlen) goto skip; f2fs_issue_discard(sbi, entry->blkaddr, entry->len); cpc->trimmed += entry->len; @@ -711,12 +919,14 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del) if (del > 0) { if (f2fs_test_and_set_bit(offset, se->cur_valid_map)) f2fs_bug_on(sbi, 1); - if (!f2fs_test_and_set_bit(offset, se->discard_map)) + if (f2fs_discard_en(sbi) && + !f2fs_test_and_set_bit(offset, se->discard_map)) sbi->discard_blks--; } else { if (!f2fs_test_and_clear_bit(offset, se->cur_valid_map)) f2fs_bug_on(sbi, 1); - if (f2fs_test_and_clear_bit(offset, se->discard_map)) + if (f2fs_discard_en(sbi) && + f2fs_test_and_clear_bit(offset, se->discard_map)) sbi->discard_blks++; } if (!f2fs_test_bit(offset, se->ckpt_valid_map)) @@ -817,12 +1027,12 @@ int npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra) } } - sum_in_page = (PAGE_CACHE_SIZE - 2 * SUM_JOURNAL_SIZE - + sum_in_page = (PAGE_SIZE - 2 * SUM_JOURNAL_SIZE - SUM_FOOTER_SIZE) / SUMMARY_SIZE; if (valid_sum_count <= sum_in_page) return 1; else if ((valid_sum_count - sum_in_page) <= - (PAGE_CACHE_SIZE - SUM_FOOTER_SIZE) / SUMMARY_SIZE) + (PAGE_SIZE - SUM_FOOTER_SIZE) / SUMMARY_SIZE) return 2; return 3; } @@ -841,9 +1051,9 @@ void update_meta_page(struct f2fs_sb_info *sbi, void *src, block_t blk_addr) void *dst = page_address(page); if (src) - memcpy(dst, src, PAGE_CACHE_SIZE); + memcpy(dst, src, PAGE_SIZE); else - memset(dst, 0, PAGE_CACHE_SIZE); + memset(dst, 0, PAGE_SIZE); set_page_dirty(page); f2fs_put_page(page, 1); } @@ -854,6 +1064,31 @@ static void write_sum_page(struct f2fs_sb_info *sbi, update_meta_page(sbi, (void *)sum_blk, blk_addr); } +static void write_current_sum_page(struct f2fs_sb_info *sbi, + int type, block_t blk_addr) +{ + struct curseg_info *curseg = CURSEG_I(sbi, type); + struct page *page = grab_meta_page(sbi, blk_addr); + struct f2fs_summary_block *src = curseg->sum_blk; + struct f2fs_summary_block *dst; + + dst = (struct f2fs_summary_block *)page_address(page); + + mutex_lock(&curseg->curseg_mutex); + + down_read(&curseg->journal_rwsem); + memcpy(&dst->journal, curseg->journal, SUM_JOURNAL_SIZE); + up_read(&curseg->journal_rwsem); + + memcpy(dst->entries, src->entries, SUM_ENTRY_SIZE); + memcpy(&dst->footer, &src->footer, SUM_FOOTER_SIZE); + + mutex_unlock(&curseg->curseg_mutex); + + set_page_dirty(page); + f2fs_put_page(page, 1); +} + static int is_next_segment_free(struct f2fs_sb_info *sbi, int type) { struct curseg_info *curseg = CURSEG_I(sbi, type); @@ -886,9 +1121,8 @@ static void get_new_segment(struct f2fs_sb_info *sbi, if (!new_sec && ((*newseg + 1) % sbi->segs_per_sec)) { segno = find_next_zero_bit(free_i->free_segmap, - MAIN_SEGS(sbi), *newseg + 1); - if (segno - *newseg < sbi->segs_per_sec - - (*newseg % sbi->segs_per_sec)) + (hint + 1) * sbi->segs_per_sec, *newseg + 1); + if (segno < (hint + 1) * sbi->segs_per_sec) goto got_it; } find_other_zone: @@ -1071,7 +1305,7 @@ static int get_ssr_segment(struct f2fs_sb_info *sbi, int type) struct curseg_info *curseg = CURSEG_I(sbi, type); const struct victim_selection *v_ops = DIRTY_I(sbi)->v_ops; - if (IS_NODESEG(type) || !has_not_enough_free_secs(sbi, 0)) + if (IS_NODESEG(type) || !has_not_enough_free_secs(sbi, 0, 0)) return v_ops->get_victim(sbi, &(curseg)->next_segno, BG_GC, type, SSR); @@ -1106,22 +1340,21 @@ static void allocate_segment_by_default(struct f2fs_sb_info *sbi, stat_inc_seg_type(sbi, curseg); } -static void __allocate_new_segments(struct f2fs_sb_info *sbi, int type) -{ - struct curseg_info *curseg = CURSEG_I(sbi, type); - unsigned int old_segno; - - old_segno = curseg->segno; - SIT_I(sbi)->s_ops->allocate_segment(sbi, type, true); - locate_dirty_segment(sbi, old_segno); -} - void allocate_new_segments(struct f2fs_sb_info *sbi) { + struct curseg_info *curseg; + unsigned int old_segno; int i; - for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) - __allocate_new_segments(sbi, i); + if (test_opt(sbi, LFS)) + return; + + for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) { + curseg = CURSEG_I(sbi, i); + old_segno = curseg->segno; + SIT_I(sbi)->s_ops->allocate_segment(sbi, i, true); + locate_dirty_segment(sbi, old_segno); + } } static const struct segment_allocation default_salloc_ops = { @@ -1134,6 +1367,7 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range) __u64 end = start + F2FS_BYTES_TO_BLK(range->len) - 1; unsigned int start_segno, end_segno; struct cp_control cpc; + int err = 0; if (start >= MAX_BLKADDR(sbi) || range->len < sbi->blocksize) return -EINVAL; @@ -1142,6 +1376,12 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range) if (end <= MAIN_BLKADDR(sbi)) goto out; + if (is_sbi_flag_set(sbi, SBI_NEED_FSCK)) { + f2fs_msg(sbi->sb, KERN_WARNING, + "Found FS corruption, run fsck to fix."); + goto out; + } + /* start/end segment number in main_area */ start_segno = (start <= MAIN_BLKADDR(sbi)) ? 0 : GET_SEGNO(sbi, start); end_segno = (end >= MAX_BLKADDR(sbi)) ? MAIN_SEGS(sbi) - 1 : @@ -1164,12 +1404,16 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range) sbi->segs_per_sec) - 1, end_segno); mutex_lock(&sbi->gc_mutex); - write_checkpoint(sbi, &cpc); + err = write_checkpoint(sbi, &cpc); mutex_unlock(&sbi->gc_mutex); + if (err) + break; + + schedule(); } out: range->len = F2FS_BLK_TO_BYTES(cpc.trimmed); - return 0; + return err; } static bool __has_curseg_space(struct f2fs_sb_info *sbi, int type) @@ -1244,21 +1488,11 @@ void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, struct f2fs_summary *sum, int type) { struct sit_info *sit_i = SIT_I(sbi); - struct curseg_info *curseg; - bool direct_io = (type == CURSEG_DIRECT_IO); - - type = direct_io ? CURSEG_WARM_DATA : type; - - curseg = CURSEG_I(sbi, type); + struct curseg_info *curseg = CURSEG_I(sbi, type); mutex_lock(&curseg->curseg_mutex); mutex_lock(&sit_i->sentry_lock); - /* direct_io'ed data is aligned to the segment for better performance */ - if (direct_io && curseg->next_blkoff && - !has_not_enough_free_secs(sbi, 0)) - __allocate_new_segments(sbi, type); - *new_blkaddr = NEXT_FREE_BLKADDR(sbi, curseg); /* @@ -1292,11 +1526,17 @@ static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio) { int type = __get_segment_type(fio->page, fio->type); - allocate_data_block(fio->sbi, fio->page, fio->blk_addr, - &fio->blk_addr, sum, type); + if (fio->type == NODE || fio->type == DATA) + mutex_lock(&fio->sbi->wio_mutex[fio->type]); + + allocate_data_block(fio->sbi, fio->page, fio->old_blkaddr, + &fio->new_blkaddr, sum, type); /* writeout dirty page into bdev */ f2fs_submit_page_mbio(fio); + + if (fio->type == NODE || fio->type == DATA) + mutex_unlock(&fio->sbi->wio_mutex[fio->type]); } void write_meta_page(struct f2fs_sb_info *sbi, struct page *page) @@ -1305,7 +1545,8 @@ void write_meta_page(struct f2fs_sb_info *sbi, struct page *page) .sbi = sbi, .type = META, .rw = WRITE_SYNC | REQ_META | REQ_PRIO, - .blk_addr = page->index, + .old_blkaddr = page->index, + .new_blkaddr = page->index, .page = page, .encrypted_page = NULL, }; @@ -1335,19 +1576,19 @@ void write_data_page(struct dnode_of_data *dn, struct f2fs_io_info *fio) get_node_info(sbi, dn->nid, &ni); set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version); do_write_page(&sum, fio); - dn->data_blkaddr = fio->blk_addr; + f2fs_update_data_blkaddr(dn, fio->new_blkaddr); } void rewrite_data_page(struct f2fs_io_info *fio) { + fio->new_blkaddr = fio->old_blkaddr; stat_inc_inplace_blocks(fio->sbi); f2fs_submit_page_mbio(fio); } -static void __f2fs_replace_block(struct f2fs_sb_info *sbi, - struct f2fs_summary *sum, +void __f2fs_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, block_t old_blkaddr, block_t new_blkaddr, - bool recover_curseg) + bool recover_curseg, bool recover_newaddr) { struct sit_info *sit_i = SIT_I(sbi); struct curseg_info *curseg; @@ -1390,7 +1631,7 @@ static void __f2fs_replace_block(struct f2fs_sb_info *sbi, curseg->next_blkoff = GET_BLKOFF_FROM_SEG0(sbi, new_blkaddr); __add_sum_entry(sbi, type, sum); - if (!recover_curseg) + if (!recover_curseg || recover_newaddr) update_sit_entry(sbi, new_blkaddr, 1); if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO) update_sit_entry(sbi, old_blkaddr, -1); @@ -1414,66 +1655,30 @@ static void __f2fs_replace_block(struct f2fs_sb_info *sbi, void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn, block_t old_addr, block_t new_addr, - unsigned char version, bool recover_curseg) + unsigned char version, bool recover_curseg, + bool recover_newaddr) { struct f2fs_summary sum; set_summary(&sum, dn->nid, dn->ofs_in_node, version); - __f2fs_replace_block(sbi, &sum, old_addr, new_addr, recover_curseg); - - dn->data_blkaddr = new_addr; - set_data_blkaddr(dn); - f2fs_update_extent_cache(dn); -} - -static inline bool is_merged_page(struct f2fs_sb_info *sbi, - struct page *page, enum page_type type) -{ - enum page_type btype = PAGE_TYPE_OF_BIO(type); - struct f2fs_bio_info *io = &sbi->write_io[btype]; - struct bio_vec *bvec; - struct page *target; - int i; - - down_read(&io->io_rwsem); - if (!io->bio) { - up_read(&io->io_rwsem); - return false; - } - - bio_for_each_segment_all(bvec, io->bio, i) { - - if (bvec->bv_page->mapping) { - target = bvec->bv_page; - } else { - struct f2fs_crypto_ctx *ctx; - - /* encrypted page */ - ctx = (struct f2fs_crypto_ctx *)page_private( - bvec->bv_page); - target = ctx->w.control_page; - } - - if (page == target) { - up_read(&io->io_rwsem); - return true; - } - } + __f2fs_replace_block(sbi, &sum, old_addr, new_addr, + recover_curseg, recover_newaddr); - up_read(&io->io_rwsem); - return false; + f2fs_update_data_blkaddr(dn, new_addr); } void f2fs_wait_on_page_writeback(struct page *page, - enum page_type type) + enum page_type type, bool ordered) { if (PageWriteback(page)) { struct f2fs_sb_info *sbi = F2FS_P_SB(page); - if (is_merged_page(sbi, page, type)) - f2fs_submit_merged_bio(sbi, type, WRITE); - wait_on_page_writeback(page); + f2fs_submit_merged_bio_cond(sbi, NULL, page, 0, type, WRITE); + if (ordered) + wait_on_page_writeback(page); + else + wait_for_stable_page(page); } } @@ -1482,14 +1687,12 @@ void f2fs_wait_on_encrypted_page_writeback(struct f2fs_sb_info *sbi, { struct page *cpage; - if (blkaddr == NEW_ADDR) + if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR) return; - f2fs_bug_on(sbi, blkaddr == NULL_ADDR); - cpage = find_lock_page(META_MAPPING(sbi), blkaddr); if (cpage) { - f2fs_wait_on_page_writeback(cpage, DATA); + f2fs_wait_on_page_writeback(cpage, DATA, true); f2fs_put_page(cpage, 1); } } @@ -1510,12 +1713,11 @@ static int read_compacted_summaries(struct f2fs_sb_info *sbi) /* Step 1: restore nat cache */ seg_i = CURSEG_I(sbi, CURSEG_HOT_DATA); - memcpy(&seg_i->sum_blk->n_nats, kaddr, SUM_JOURNAL_SIZE); + memcpy(seg_i->journal, kaddr, SUM_JOURNAL_SIZE); /* Step 2: restore sit cache */ seg_i = CURSEG_I(sbi, CURSEG_COLD_DATA); - memcpy(&seg_i->sum_blk->n_sits, kaddr + SUM_JOURNAL_SIZE, - SUM_JOURNAL_SIZE); + memcpy(seg_i->journal, kaddr + SUM_JOURNAL_SIZE, SUM_JOURNAL_SIZE); offset = 2 * SUM_JOURNAL_SIZE; /* Step 3: restore summary entries */ @@ -1539,7 +1741,7 @@ static int read_compacted_summaries(struct f2fs_sb_info *sbi) s = (struct f2fs_summary *)(kaddr + offset); seg_i->sum_blk->entries[j] = *s; offset += SUMMARY_SIZE; - if (offset + SUMMARY_SIZE <= PAGE_CACHE_SIZE - + if (offset + SUMMARY_SIZE <= PAGE_SIZE - SUM_FOOTER_SIZE) continue; @@ -1611,7 +1813,14 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type) /* set uncompleted segment to curseg */ curseg = CURSEG_I(sbi, type); mutex_lock(&curseg->curseg_mutex); - memcpy(curseg->sum_blk, sum, PAGE_CACHE_SIZE); + + /* update journal info */ + down_write(&curseg->journal_rwsem); + memcpy(curseg->journal, &sum->journal, SUM_JOURNAL_SIZE); + up_write(&curseg->journal_rwsem); + + memcpy(curseg->sum_blk->entries, sum->entries, SUM_ENTRY_SIZE); + memcpy(&curseg->sum_blk->footer, &sum->footer, SUM_FOOTER_SIZE); curseg->next_segno = segno; reset_curseg(sbi, type, 0); curseg->alloc_type = ckpt->alloc_type[type]; @@ -1623,14 +1832,10 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type) static int restore_curseg_summaries(struct f2fs_sb_info *sbi) { - struct f2fs_summary_block *s_sits = - CURSEG_I(sbi, CURSEG_COLD_DATA)->sum_blk; - struct f2fs_summary_block *s_nats = - CURSEG_I(sbi, CURSEG_HOT_DATA)->sum_blk; int type = CURSEG_HOT_DATA; int err; - if (is_set_ckpt_flags(F2FS_CKPT(sbi), CP_COMPACT_SUM_FLAG)) { + if (is_set_ckpt_flags(sbi, CP_COMPACT_SUM_FLAG)) { int npages = npages_for_summary_flush(sbi, true); if (npages >= 2) @@ -1653,11 +1858,6 @@ static int restore_curseg_summaries(struct f2fs_sb_info *sbi) return err; } - /* sanity check for summary blocks */ - if (nats_in_cursum(s_nats) > NAT_JOURNAL_ENTRIES || - sits_in_cursum(s_sits) > SIT_JOURNAL_ENTRIES) - return -EINVAL; - return 0; } @@ -1675,13 +1875,12 @@ static void write_compacted_summaries(struct f2fs_sb_info *sbi, block_t blkaddr) /* Step 1: write nat cache */ seg_i = CURSEG_I(sbi, CURSEG_HOT_DATA); - memcpy(kaddr, &seg_i->sum_blk->n_nats, SUM_JOURNAL_SIZE); + memcpy(kaddr, seg_i->journal, SUM_JOURNAL_SIZE); written_size += SUM_JOURNAL_SIZE; /* Step 2: write sit cache */ seg_i = CURSEG_I(sbi, CURSEG_COLD_DATA); - memcpy(kaddr + written_size, &seg_i->sum_blk->n_sits, - SUM_JOURNAL_SIZE); + memcpy(kaddr + written_size, seg_i->journal, SUM_JOURNAL_SIZE); written_size += SUM_JOURNAL_SIZE; /* Step 3: write summary entries */ @@ -1703,7 +1902,7 @@ static void write_compacted_summaries(struct f2fs_sb_info *sbi, block_t blkaddr) *summary = seg_i->sum_blk->entries[j]; written_size += SUMMARY_SIZE; - if (written_size + SUMMARY_SIZE <= PAGE_CACHE_SIZE - + if (written_size + SUMMARY_SIZE <= PAGE_SIZE - SUM_FOOTER_SIZE) continue; @@ -1727,17 +1926,13 @@ static void write_normal_summaries(struct f2fs_sb_info *sbi, else end = type + NR_CURSEG_NODE_TYPE; - for (i = type; i < end; i++) { - struct curseg_info *sum = CURSEG_I(sbi, i); - mutex_lock(&sum->curseg_mutex); - write_sum_page(sbi, sum->sum_blk, blkaddr + (i - type)); - mutex_unlock(&sum->curseg_mutex); - } + for (i = type; i < end; i++) + write_current_sum_page(sbi, i, blkaddr + (i - type)); } void write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk) { - if (is_set_ckpt_flags(F2FS_CKPT(sbi), CP_COMPACT_SUM_FLAG)) + if (is_set_ckpt_flags(sbi, CP_COMPACT_SUM_FLAG)) write_compacted_summaries(sbi, start_blk); else write_normal_summaries(sbi, start_blk, CURSEG_HOT_DATA); @@ -1748,24 +1943,24 @@ void write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk) write_normal_summaries(sbi, start_blk, CURSEG_HOT_NODE); } -int lookup_journal_in_cursum(struct f2fs_summary_block *sum, int type, +int lookup_journal_in_cursum(struct f2fs_journal *journal, int type, unsigned int val, int alloc) { int i; if (type == NAT_JOURNAL) { - for (i = 0; i < nats_in_cursum(sum); i++) { - if (le32_to_cpu(nid_in_journal(sum, i)) == val) + for (i = 0; i < nats_in_cursum(journal); i++) { + if (le32_to_cpu(nid_in_journal(journal, i)) == val) return i; } - if (alloc && nats_in_cursum(sum) < NAT_JOURNAL_ENTRIES) - return update_nats_in_cursum(sum, 1); + if (alloc && __has_cursum_space(journal, 1, NAT_JOURNAL)) + return update_nats_in_cursum(journal, 1); } else if (type == SIT_JOURNAL) { - for (i = 0; i < sits_in_cursum(sum); i++) - if (le32_to_cpu(segno_in_journal(sum, i)) == val) + for (i = 0; i < sits_in_cursum(journal); i++) + if (le32_to_cpu(segno_in_journal(journal, i)) == val) return i; - if (alloc && sits_in_cursum(sum) < SIT_JOURNAL_ENTRIES) - return update_sits_in_cursum(sum, 1); + if (alloc && __has_cursum_space(journal, 1, SIT_JOURNAL)) + return update_sits_in_cursum(journal, 1); } return -1; } @@ -1794,7 +1989,7 @@ static struct page *get_next_sit_page(struct f2fs_sb_info *sbi, src_addr = page_address(src_page); dst_addr = page_address(dst_page); - memcpy(dst_addr, src_addr, PAGE_CACHE_SIZE); + memcpy(dst_addr, src_addr, PAGE_SIZE); set_page_dirty(dst_page); f2fs_put_page(src_page, 1); @@ -1869,20 +2064,22 @@ static void add_sits_in_set(struct f2fs_sb_info *sbi) static void remove_sits_in_journal(struct f2fs_sb_info *sbi) { struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_COLD_DATA); - struct f2fs_summary_block *sum = curseg->sum_blk; + struct f2fs_journal *journal = curseg->journal; int i; - for (i = sits_in_cursum(sum) - 1; i >= 0; i--) { + down_write(&curseg->journal_rwsem); + for (i = 0; i < sits_in_cursum(journal); i++) { unsigned int segno; bool dirtied; - segno = le32_to_cpu(segno_in_journal(sum, i)); + segno = le32_to_cpu(segno_in_journal(journal, i)); dirtied = __mark_sit_entry_dirty(sbi, segno); if (!dirtied) add_sit_entry(segno, &SM_I(sbi)->sit_entry_set); } - update_sits_in_cursum(sum, -sits_in_cursum(sum)); + update_sits_in_cursum(journal, -i); + up_write(&curseg->journal_rwsem); } /* @@ -1894,13 +2091,12 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) struct sit_info *sit_i = SIT_I(sbi); unsigned long *bitmap = sit_i->dirty_sentries_bitmap; struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_COLD_DATA); - struct f2fs_summary_block *sum = curseg->sum_blk; + struct f2fs_journal *journal = curseg->journal; struct sit_entry_set *ses, *tmp; struct list_head *head = &SM_I(sbi)->sit_entry_set; bool to_journal = true; struct seg_entry *se; - mutex_lock(&curseg->curseg_mutex); mutex_lock(&sit_i->sentry_lock); if (!sit_i->dirty_sentries) @@ -1917,7 +2113,7 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) * entries, remove all entries from journal and add and account * them in sit entry set. */ - if (!__has_cursum_space(sum, sit_i->dirty_sentries, SIT_JOURNAL)) + if (!__has_cursum_space(journal, sit_i->dirty_sentries, SIT_JOURNAL)) remove_sits_in_journal(sbi); /* @@ -1934,10 +2130,12 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) unsigned int segno = start_segno; if (to_journal && - !__has_cursum_space(sum, ses->entry_cnt, SIT_JOURNAL)) + !__has_cursum_space(journal, ses->entry_cnt, SIT_JOURNAL)) to_journal = false; - if (!to_journal) { + if (to_journal) { + down_write(&curseg->journal_rwsem); + } else { page = get_next_sit_page(sbi, start_segno); raw_sit = page_address(page); } @@ -1955,13 +2153,13 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) } if (to_journal) { - offset = lookup_journal_in_cursum(sum, + offset = lookup_journal_in_cursum(journal, SIT_JOURNAL, segno, 1); f2fs_bug_on(sbi, offset < 0); - segno_in_journal(sum, offset) = + segno_in_journal(journal, offset) = cpu_to_le32(segno); seg_info_to_raw_sit(se, - &sit_in_journal(sum, offset)); + &sit_in_journal(journal, offset)); } else { sit_offset = SIT_ENTRY_OFFSET(sit_i, segno); seg_info_to_raw_sit(se, @@ -1973,7 +2171,9 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) ses->entry_cnt--; } - if (!to_journal) + if (to_journal) + up_write(&curseg->journal_rwsem); + else f2fs_put_page(page, 1); f2fs_bug_on(sbi, ses->entry_cnt); @@ -1988,7 +2188,6 @@ out: add_discard_addrs(sbi, cpc); } mutex_unlock(&sit_i->sentry_lock); - mutex_unlock(&curseg->curseg_mutex); set_prefree_as_free_segments(sbi); } @@ -1996,7 +2195,6 @@ out: static int build_sit_info(struct f2fs_sb_info *sbi) { struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi); - struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); struct sit_info *sit_i; unsigned int sit_segs, start; char *src_bitmap, *dst_bitmap; @@ -2024,12 +2222,16 @@ static int build_sit_info(struct f2fs_sb_info *sbi) = kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL); sit_i->sentries[start].ckpt_valid_map = kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL); - sit_i->sentries[start].discard_map - = kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL); if (!sit_i->sentries[start].cur_valid_map || - !sit_i->sentries[start].ckpt_valid_map || - !sit_i->sentries[start].discard_map) + !sit_i->sentries[start].ckpt_valid_map) return -ENOMEM; + + if (f2fs_discard_en(sbi)) { + sit_i->sentries[start].discard_map + = kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL); + if (!sit_i->sentries[start].discard_map) + return -ENOMEM; + } } sit_i->tmp_map = kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL); @@ -2059,7 +2261,7 @@ static int build_sit_info(struct f2fs_sb_info *sbi) sit_i->sit_base_addr = le32_to_cpu(raw_super->sit_blkaddr); sit_i->sit_blocks = sit_segs << sbi->log_blocks_per_seg; - sit_i->written_valid_blocks = le64_to_cpu(ckpt->valid_block_count); + sit_i->written_valid_blocks = 0; sit_i->sit_bitmap = dst_bitmap; sit_i->bitmap_size = bitmap_size; sit_i->dirty_sentries = 0; @@ -2117,9 +2319,14 @@ static int build_curseg(struct f2fs_sb_info *sbi) for (i = 0; i < NR_CURSEG_TYPE; i++) { mutex_init(&array[i].curseg_mutex); - array[i].sum_blk = kzalloc(PAGE_CACHE_SIZE, GFP_KERNEL); + array[i].sum_blk = kzalloc(PAGE_SIZE, GFP_KERNEL); if (!array[i].sum_blk) return -ENOMEM; + init_rwsem(&array[i].journal_rwsem); + array[i].journal = kzalloc(sizeof(struct f2fs_journal), + GFP_KERNEL); + if (!array[i].journal) + return -ENOMEM; array[i].segno = NULL_SEGNO; array[i].next_blkoff = 0; } @@ -2130,54 +2337,73 @@ static void 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); - struct f2fs_summary_block *sum = curseg->sum_blk; + struct f2fs_journal *journal = curseg->journal; + struct seg_entry *se; + struct f2fs_sit_entry sit; int sit_blk_cnt = SIT_BLK_CNT(sbi); unsigned int i, start, end; unsigned int readed, start_blk = 0; - int nrpages = MAX_BIO_BLOCKS(sbi); do { - readed = ra_meta_pages(sbi, start_blk, nrpages, META_SIT, true); + readed = ra_meta_pages(sbi, start_blk, BIO_MAX_PAGES, + META_SIT, true); start = start_blk * sit_i->sents_per_block; end = (start_blk + readed) * sit_i->sents_per_block; for (; start < end && start < MAIN_SEGS(sbi); start++) { - struct seg_entry *se = &sit_i->sentries[start]; struct f2fs_sit_block *sit_blk; - 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); - + se = &sit_i->sentries[start]; 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); 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 (f2fs_discard_en(sbi)) { + 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) + get_sec_entry(sbi, start)->valid_blocks += + se->valid_blocks; } start_blk += readed; } while (start_blk < sit_blk_cnt); + + down_read(&curseg->journal_rwsem); + for (i = 0; i < sits_in_cursum(journal); i++) { + unsigned int old_valid_blocks; + + start = le32_to_cpu(segno_in_journal(journal, i)); + se = &sit_i->sentries[start]; + sit = sit_in_journal(journal, i); + + old_valid_blocks = se->valid_blocks; + + check_block_count(sbi, start, &sit); + seg_info_from_raw_sit(se, &sit); + + if (f2fs_discard_en(sbi)) { + 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; + } + up_read(&curseg->journal_rwsem); } static void init_free_segmap(struct f2fs_sb_info *sbi) @@ -2189,6 +2415,9 @@ static void init_free_segmap(struct f2fs_sb_info *sbi) struct seg_entry *sentry = get_seg_entry(sbi, start); if (!sentry->valid_blocks) __set_free(sbi, start); + else + SIT_I(sbi)->written_valid_blocks += + sentry->valid_blocks; } /* set use the current segments */ @@ -2310,7 +2539,11 @@ int build_segment_manager(struct f2fs_sb_info *sbi) sm_info->ssa_blkaddr = le32_to_cpu(raw_super->ssa_blkaddr); sm_info->rec_prefree_segments = sm_info->main_segments * DEF_RECLAIM_PREFREE_SEGMENTS / 100; - sm_info->ipu_policy = 1 << F2FS_IPU_FSYNC; + if (sm_info->rec_prefree_segments > DEF_MAX_RECLAIM_PREFREE_SEGMENTS) + sm_info->rec_prefree_segments = DEF_MAX_RECLAIM_PREFREE_SEGMENTS; + + if (!test_opt(sbi, LFS)) + sm_info->ipu_policy = 1 << F2FS_IPU_FSYNC; sm_info->min_ipu_util = DEF_MIN_IPU_UTIL; sm_info->min_fsync_blocks = DEF_MIN_FSYNC_BLOCKS; @@ -2392,8 +2625,10 @@ static void destroy_curseg(struct f2fs_sb_info *sbi) if (!array) return; SM_I(sbi)->curseg_array = NULL; - for (i = 0; i < NR_CURSEG_TYPE; i++) + for (i = 0; i < NR_CURSEG_TYPE; i++) { kfree(array[i].sum_blk); + kfree(array[i].journal); + } kfree(array); } @@ -2440,7 +2675,7 @@ void destroy_segment_manager(struct f2fs_sb_info *sbi) if (!sm_info) return; - destroy_flush_cmd_control(sbi); + destroy_flush_cmd_control(sbi, true); destroy_dirty_segmap(sbi); destroy_curseg(sbi); destroy_free_segmap(sbi); @@ -2459,7 +2694,7 @@ int __init create_segment_manager_caches(void) sit_entry_set_slab = f2fs_kmem_cache_create("sit_entry_set", sizeof(struct sit_entry_set)); if (!sit_entry_set_slab) - goto destory_discard_entry; + goto destroy_discard_entry; inmem_entry_slab = f2fs_kmem_cache_create("inmem_page_entry", sizeof(struct inmem_pages)); @@ -2469,7 +2704,7 @@ int __init create_segment_manager_caches(void) destroy_sit_entry_set: kmem_cache_destroy(sit_entry_set_slab); -destory_discard_entry: +destroy_discard_entry: kmem_cache_destroy(discard_entry_slab); fail: return -ENOMEM; diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index ee44d346ea44..9d44ce83acb2 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -16,6 +16,9 @@ #define NULL_SECNO ((unsigned int)(~0)) #define DEF_RECLAIM_PREFREE_SEGMENTS 5 /* 5% over total segments */ +#define DEF_MAX_RECLAIM_PREFREE_SEGMENTS 4096 /* 8GB in maximum */ + +#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) @@ -101,8 +104,6 @@ (((sector_t)blk_addr) << F2FS_LOG_SECTORS_PER_BLOCK) #define SECTOR_TO_BLOCK(sectors) \ (sectors >> F2FS_LOG_SECTORS_PER_BLOCK) -#define MAX_BIO_BLOCKS(sbi) \ - ((int)min((int)max_hw_blocks(sbi), BIO_MAX_PAGES)) /* * indicate a block allocation direction: RIGHT and LEFT. @@ -158,16 +159,17 @@ struct victim_sel_policy { }; struct seg_entry { - unsigned short valid_blocks; /* # of valid blocks */ + unsigned int type:6; /* segment type like CURSEG_XXX_TYPE */ + unsigned int valid_blocks:10; /* # of valid blocks */ + unsigned int ckpt_valid_blocks:10; /* # of valid blocks last cp */ + unsigned int padding:6; /* padding */ unsigned char *cur_valid_map; /* validity bitmap of blocks */ /* * # of valid blocks and the validity bitmap stored in the the last * checkpoint pack. This information is used by the SSR mode. */ - unsigned short ckpt_valid_blocks; - unsigned char *ckpt_valid_map; + unsigned char *ckpt_valid_map; /* validity bitmap of blocks last cp */ unsigned char *discard_map; - unsigned char type; /* segment type like CURSEG_XXX_TYPE */ unsigned long long mtime; /* modification time of the segment */ }; @@ -183,7 +185,7 @@ struct segment_allocation { * this value is set in page as a private data which indicate that * the page is atomically written, and it is in inmem_pages list. */ -#define ATOMIC_WRITTEN_PAGE 0x0000ffff +#define ATOMIC_WRITTEN_PAGE ((unsigned long)-1) #define IS_ATOMIC_WRITTEN_PAGE(page) \ (page_private(page) == (unsigned long)ATOMIC_WRITTEN_PAGE) @@ -191,6 +193,7 @@ struct segment_allocation { struct inmem_pages { struct list_head list; struct page *page; + block_t old_addr; /* for revoking when fail to commit */ }; struct sit_info { @@ -257,6 +260,8 @@ struct victim_selection { struct curseg_info { struct mutex curseg_mutex; /* lock for consistency */ struct f2fs_summary_block *sum_blk; /* cached summary block */ + struct rw_semaphore journal_rwsem; /* protect journal area */ + struct f2fs_journal *journal; /* cached journal info */ unsigned char alloc_type; /* current allocation type */ unsigned int segno; /* current segment number */ unsigned short next_blkoff; /* next block offset to write */ @@ -466,20 +471,28 @@ static inline bool need_SSR(struct f2fs_sb_info *sbi) { int node_secs = get_blocktype_secs(sbi, F2FS_DIRTY_NODES); int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS); - return free_sections(sbi) <= (node_secs + 2 * dent_secs + + int imeta_secs = get_blocktype_secs(sbi, F2FS_DIRTY_IMETA); + + if (test_opt(sbi, LFS)) + return false; + + return free_sections(sbi) <= (node_secs + 2 * dent_secs + imeta_secs + reserved_sections(sbi) + 1); } -static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi, int freed) +static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi, + int freed, int needed) { int node_secs = get_blocktype_secs(sbi, F2FS_DIRTY_NODES); int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS); + int imeta_secs = get_blocktype_secs(sbi, F2FS_DIRTY_IMETA); if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) return false; - return (free_sections(sbi) + freed) <= (node_secs + 2 * dent_secs + - reserved_sections(sbi)); + return (free_sections(sbi) + freed) <= + (node_secs + 2 * dent_secs + imeta_secs + + reserved_sections(sbi) + needed); } static inline bool excess_prefree_segs(struct f2fs_sb_info *sbi) @@ -527,6 +540,9 @@ static inline bool need_inplace_update(struct inode *inode) if (S_ISDIR(inode->i_mode) || f2fs_is_atomic_file(inode)) return false; + if (test_opt(sbi, LFS)) + return false; + if (policy & (0x1 << F2FS_IPU_FORCE)) return true; if (policy & (0x1 << F2FS_IPU_SSR) && need_SSR(sbi)) @@ -540,7 +556,7 @@ static inline bool need_inplace_update(struct inode *inode) /* this is only set during fdatasync */ if (policy & (0x1 << F2FS_IPU_FSYNC) && - is_inode_flag_set(F2FS_I(inode), FI_NEED_IPU)) + is_inode_flag_set(inode, FI_NEED_IPU)) return true; return false; @@ -573,8 +589,8 @@ static inline void check_seg_range(struct f2fs_sb_info *sbi, unsigned int segno) static inline void verify_block_addr(struct f2fs_sb_info *sbi, block_t blk_addr) { - f2fs_bug_on(sbi, blk_addr < SEG0_BLKADDR(sbi) - || blk_addr >= MAX_BLKADDR(sbi)); + BUG_ON(blk_addr < SEG0_BLKADDR(sbi) + || blk_addr >= MAX_BLKADDR(sbi)); } /* @@ -680,13 +696,6 @@ static inline bool sec_usage_check(struct f2fs_sb_info *sbi, unsigned int secno) return false; } -static inline unsigned int max_hw_blocks(struct f2fs_sb_info *sbi) -{ - struct block_device *bdev = sbi->sb->s_bdev; - struct request_queue *q = bdev_get_queue(bdev); - return SECTOR_TO_BLOCK(queue_max_sectors(q)); -} - /* * It is very important to gather dirty pages and write at once, so that we can * submit a big bio without interfering other data writes. @@ -702,9 +711,9 @@ static inline int nr_pages_to_skip(struct f2fs_sb_info *sbi, int type) if (type == DATA) return sbi->blocks_per_seg; else if (type == NODE) - return 3 * sbi->blocks_per_seg; + return 8 * sbi->blocks_per_seg; else if (type == META) - return MAX_BIO_BLOCKS(sbi); + return 8 * BIO_MAX_PAGES; else return 0; } @@ -721,13 +730,9 @@ static inline long nr_pages_to_write(struct f2fs_sb_info *sbi, int type, return 0; nr_to_write = wbc->nr_to_write; - - if (type == DATA) - desired = 4096; - else if (type == NODE) - desired = 3 * max_hw_blocks(sbi); - else - desired = MAX_BIO_BLOCKS(sbi); + desired = BIO_MAX_PAGES; + if (type == NODE) + desired <<= 1; wbc->nr_to_write = desired; return desired - nr_to_write; diff --git a/fs/f2fs/shrinker.c b/fs/f2fs/shrinker.c index da0d8e0b55a5..5c60fc28ec75 100644 --- a/fs/f2fs/shrinker.c +++ b/fs/f2fs/shrinker.c @@ -13,6 +13,7 @@ #include <linux/f2fs_fs.h> #include "f2fs.h" +#include "node.h" static LIST_HEAD(f2fs_list); static DEFINE_SPINLOCK(f2fs_list_lock); @@ -20,19 +21,22 @@ static unsigned int shrinker_run_no; static unsigned long __count_nat_entries(struct f2fs_sb_info *sbi) { - return NM_I(sbi)->nat_cnt - NM_I(sbi)->dirty_nat_cnt; + long count = NM_I(sbi)->nat_cnt - NM_I(sbi)->dirty_nat_cnt; + + return count > 0 ? count : 0; } static unsigned long __count_free_nids(struct f2fs_sb_info *sbi) { - if (NM_I(sbi)->fcnt > NAT_ENTRY_PER_BLOCK) - return NM_I(sbi)->fcnt - NAT_ENTRY_PER_BLOCK; - return 0; + long count = NM_I(sbi)->nid_cnt[FREE_NID_LIST] - MAX_FREE_NIDS; + + return count > 0 ? count : 0; } static unsigned long __count_extent_cache(struct f2fs_sb_info *sbi) { - return sbi->total_ext_tree + atomic_read(&sbi->total_ext_node); + return atomic_read(&sbi->total_zombie_tree) + + atomic_read(&sbi->total_ext_node); } unsigned long f2fs_shrink_count(struct shrinker *shrink, diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 5d3e745d33ae..e6d8d011786c 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -39,6 +39,35 @@ static struct proc_dir_entry *f2fs_proc_root; static struct kmem_cache *f2fs_inode_cachep; static struct kset *f2fs_kset; +#ifdef CONFIG_F2FS_FAULT_INJECTION + +char *fault_name[FAULT_MAX] = { + [FAULT_KMALLOC] = "kmalloc", + [FAULT_PAGE_ALLOC] = "page alloc", + [FAULT_ALLOC_NID] = "alloc nid", + [FAULT_ORPHAN] = "orphan", + [FAULT_BLOCK] = "no more block", + [FAULT_DIR_DEPTH] = "too big dir depth", + [FAULT_EVICT_INODE] = "evict_inode fail", + [FAULT_IO] = "IO error", + [FAULT_CHECKPOINT] = "checkpoint error", +}; + +static void f2fs_build_fault_attr(struct f2fs_sb_info *sbi, + unsigned int rate) +{ + struct f2fs_fault_info *ffi = &sbi->fault_info; + + if (rate) { + atomic_set(&ffi->inject_ops, 0); + ffi->inject_rate = rate; + ffi->inject_type = (1 << FAULT_MAX) - 1; + } else { + memset(ffi, 0, sizeof(struct f2fs_fault_info)); + } +} +#endif + /* f2fs-wide shrinker description */ static struct shrinker f2fs_shrinker_info = { .scan_objects = f2fs_shrink_scan, @@ -51,6 +80,7 @@ enum { Opt_disable_roll_forward, Opt_norecovery, Opt_discard, + Opt_nodiscard, Opt_noheap, Opt_user_xattr, Opt_nouser_xattr, @@ -61,12 +91,19 @@ enum { Opt_inline_xattr, Opt_inline_data, Opt_inline_dentry, + Opt_noinline_dentry, Opt_flush_merge, + Opt_noflush_merge, Opt_nobarrier, Opt_fastboot, Opt_extent_cache, Opt_noextent_cache, Opt_noinline_data, + Opt_data_flush, + Opt_mode, + Opt_fault_injection, + Opt_lazytime, + Opt_nolazytime, Opt_err, }; @@ -75,6 +112,7 @@ static match_table_t f2fs_tokens = { {Opt_disable_roll_forward, "disable_roll_forward"}, {Opt_norecovery, "norecovery"}, {Opt_discard, "discard"}, + {Opt_nodiscard, "nodiscard"}, {Opt_noheap, "no_heap"}, {Opt_user_xattr, "user_xattr"}, {Opt_nouser_xattr, "nouser_xattr"}, @@ -85,12 +123,19 @@ static match_table_t f2fs_tokens = { {Opt_inline_xattr, "inline_xattr"}, {Opt_inline_data, "inline_data"}, {Opt_inline_dentry, "inline_dentry"}, + {Opt_noinline_dentry, "noinline_dentry"}, {Opt_flush_merge, "flush_merge"}, + {Opt_noflush_merge, "noflush_merge"}, {Opt_nobarrier, "nobarrier"}, {Opt_fastboot, "fastboot"}, {Opt_extent_cache, "extent_cache"}, {Opt_noextent_cache, "noextent_cache"}, {Opt_noinline_data, "noinline_data"}, + {Opt_data_flush, "data_flush"}, + {Opt_mode, "mode=%s"}, + {Opt_fault_injection, "fault_injection=%u"}, + {Opt_lazytime, "lazytime"}, + {Opt_nolazytime, "nolazytime"}, {Opt_err, NULL}, }; @@ -100,6 +145,10 @@ enum { SM_INFO, /* struct f2fs_sm_info */ NM_INFO, /* struct f2fs_nm_info */ F2FS_SBI, /* struct f2fs_sb_info */ +#ifdef CONFIG_F2FS_FAULT_INJECTION + FAULT_INFO_RATE, /* struct f2fs_fault_info */ + FAULT_INFO_TYPE, /* struct f2fs_fault_info */ +#endif }; struct f2fs_attr { @@ -121,9 +170,27 @@ static unsigned char *__struct_ptr(struct f2fs_sb_info *sbi, int struct_type) return (unsigned char *)NM_I(sbi); else if (struct_type == F2FS_SBI) return (unsigned char *)sbi; +#ifdef CONFIG_F2FS_FAULT_INJECTION + else if (struct_type == FAULT_INFO_RATE || + struct_type == FAULT_INFO_TYPE) + return (unsigned char *)&sbi->fault_info; +#endif return NULL; } +static ssize_t lifetime_write_kbytes_show(struct f2fs_attr *a, + struct f2fs_sb_info *sbi, char *buf) +{ + struct super_block *sb = sbi->sb; + + if (!sb->s_bdev->bd_part) + return snprintf(buf, PAGE_SIZE, "0\n"); + + return snprintf(buf, PAGE_SIZE, "%llu\n", + (unsigned long long)(sbi->kbytes_written + + BD_PART_WRITTEN(sbi))); +} + static ssize_t f2fs_sbi_show(struct f2fs_attr *a, struct f2fs_sb_info *sbi, char *buf) { @@ -157,6 +224,10 @@ static ssize_t f2fs_sbi_store(struct f2fs_attr *a, ret = kstrtoul(skip_spaces(buf), 0, &t); if (ret < 0) return ret; +#ifdef CONFIG_F2FS_FAULT_INJECTION + if (a->struct_type == FAULT_INFO_TYPE && t >= (1 << FAULT_MAX)) + return -EINVAL; +#endif *ui = t; return count; } @@ -202,6 +273,9 @@ static struct f2fs_attr f2fs_attr_##_name = { \ f2fs_sbi_show, f2fs_sbi_store, \ offsetof(struct struct_name, elname)) +#define F2FS_GENERAL_RO_ATTR(name) \ +static struct f2fs_attr f2fs_attr_##name = __ATTR(name, 0444, name##_show, NULL) + F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_min_sleep_time, min_sleep_time); F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_max_sleep_time, max_sleep_time); F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_no_gc_sleep_time, no_gc_sleep_time); @@ -214,9 +288,16 @@ F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_ipu_util, min_ipu_util); F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_fsync_blocks, min_fsync_blocks); F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ram_thresh, ram_thresh); F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ra_nid_pages, ra_nid_pages); +F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, dirty_nats_ratio, dirty_nats_ratio); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_victim_search, max_victim_search); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, dir_level, dir_level); -F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, cp_interval, cp_interval); +F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, cp_interval, interval_time[CP_TIME]); +F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, idle_interval, interval_time[REQ_TIME]); +#ifdef CONFIG_F2FS_FAULT_INJECTION +F2FS_RW_ATTR(FAULT_INFO_RATE, f2fs_fault_info, inject_rate, inject_rate); +F2FS_RW_ATTR(FAULT_INFO_TYPE, f2fs_fault_info, inject_type, inject_type); +#endif +F2FS_GENERAL_RO_ATTR(lifetime_write_kbytes); #define ATTR_LIST(name) (&f2fs_attr_##name.attr) static struct attribute *f2fs_attrs[] = { @@ -234,7 +315,14 @@ static struct attribute *f2fs_attrs[] = { ATTR_LIST(dir_level), ATTR_LIST(ram_thresh), ATTR_LIST(ra_nid_pages), + ATTR_LIST(dirty_nats_ratio), ATTR_LIST(cp_interval), + ATTR_LIST(idle_interval), +#ifdef CONFIG_F2FS_FAULT_INJECTION + ATTR_LIST(inject_rate), + ATTR_LIST(inject_type), +#endif + ATTR_LIST(lifetime_write_kbytes), NULL, }; @@ -324,12 +412,20 @@ static int parse_options(struct super_block *sb, char *options) q = bdev_get_queue(sb->s_bdev); if (blk_queue_discard(q)) { set_opt(sbi, DISCARD); - } else { + } else if (!f2fs_sb_mounted_blkzoned(sb)) { f2fs_msg(sb, KERN_WARNING, "mounting with \"discard\" option, but " "the device does not support discard"); } break; + case Opt_nodiscard: + if (f2fs_sb_mounted_blkzoned(sb)) { + f2fs_msg(sb, KERN_WARNING, + "discard is required for zoned block devices"); + return -EINVAL; + } + clear_opt(sbi, DISCARD); + break; case Opt_noheap: set_opt(sbi, NOHEAP); break; @@ -388,9 +484,15 @@ static int parse_options(struct super_block *sb, char *options) case Opt_inline_dentry: set_opt(sbi, INLINE_DENTRY); break; + case Opt_noinline_dentry: + clear_opt(sbi, INLINE_DENTRY); + break; case Opt_flush_merge: set_opt(sbi, FLUSH_MERGE); break; + case Opt_noflush_merge: + clear_opt(sbi, FLUSH_MERGE); + break; case Opt_nobarrier: set_opt(sbi, NOBARRIER); break; @@ -406,6 +508,49 @@ static int parse_options(struct super_block *sb, char *options) case Opt_noinline_data: clear_opt(sbi, INLINE_DATA); break; + case Opt_data_flush: + set_opt(sbi, DATA_FLUSH); + break; + case Opt_mode: + name = match_strdup(&args[0]); + + if (!name) + return -ENOMEM; + if (strlen(name) == 8 && + !strncmp(name, "adaptive", 8)) { + if (f2fs_sb_mounted_blkzoned(sb)) { + f2fs_msg(sb, KERN_WARNING, + "adaptive mode is not allowed with " + "zoned block device feature"); + kfree(name); + return -EINVAL; + } + set_opt_mode(sbi, F2FS_MOUNT_ADAPTIVE); + } else if (strlen(name) == 3 && + !strncmp(name, "lfs", 3)) { + set_opt_mode(sbi, F2FS_MOUNT_LFS); + } else { + kfree(name); + return -EINVAL; + } + kfree(name); + break; + case Opt_fault_injection: + if (args->from && match_int(args, &arg)) + return -EINVAL; +#ifdef CONFIG_F2FS_FAULT_INJECTION + f2fs_build_fault_attr(sbi, arg); +#else + f2fs_msg(sb, KERN_INFO, + "FAULT_INJECTION was not selected"); +#endif + break; + case Opt_lazytime: + sb->s_flags |= MS_LAZYTIME; + break; + case Opt_nolazytime: + sb->s_flags &= ~MS_LAZYTIME; + break; default: f2fs_msg(sb, KERN_ERR, "Unrecognized mount option \"%s\" or missing value", @@ -432,20 +577,15 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb) fi->i_current_depth = 1; fi->i_advise = 0; init_rwsem(&fi->i_sem); + INIT_LIST_HEAD(&fi->dirty_list); + INIT_LIST_HEAD(&fi->gdirty_list); INIT_LIST_HEAD(&fi->inmem_pages); mutex_init(&fi->inmem_lock); - - set_inode_flag(fi, FI_NEW_INODE); - - if (test_opt(F2FS_SB(sb), INLINE_XATTR)) - set_inode_flag(fi, FI_INLINE_XATTR); + init_rwsem(&fi->dio_rwsem[READ]); + init_rwsem(&fi->dio_rwsem[WRITE]); /* Will be used by directory only */ fi->i_dir_level = F2FS_SB(sb)->dir_level; - -#ifdef CONFIG_F2FS_FS_ENCRYPTION - fi->i_crypt_info = NULL; -#endif return &fi->vfs_inode; } @@ -458,7 +598,7 @@ static int f2fs_drop_inode(struct inode *inode) * - f2fs_gc -> iput -> evict * - inode_wait_for_writeback(inode) */ - if (!inode_unhashed(inode) && inode->i_state & I_SYNC) { + if ((!inode_unhashed(inode) && inode->i_state & I_SYNC)) { if (!inode->i_nlink && !is_bad_inode(inode)) { /* to avoid evict_inode call simultaneously */ atomic_inc(&inode->i_count); @@ -466,32 +606,69 @@ static int f2fs_drop_inode(struct inode *inode) /* some remained atomic pages should discarded */ if (f2fs_is_atomic_file(inode)) - commit_inmem_pages(inode, true); + drop_inmem_pages(inode); /* should remain fi->extent_tree for writepage */ f2fs_destroy_extent_node(inode); sb_start_intwrite(inode->i_sb); - i_size_write(inode, 0); + f2fs_i_size_write(inode, 0); if (F2FS_HAS_BLOCKS(inode)) - f2fs_truncate(inode, true); + f2fs_truncate(inode); sb_end_intwrite(inode->i_sb); -#ifdef CONFIG_F2FS_FS_ENCRYPTION - if (F2FS_I(inode)->i_crypt_info) - f2fs_free_encryption_info(inode, - F2FS_I(inode)->i_crypt_info); -#endif + fscrypt_put_encryption_info(inode, NULL); spin_lock(&inode->i_lock); atomic_dec(&inode->i_count); } return 0; } + return generic_drop_inode(inode); } +int f2fs_inode_dirtied(struct inode *inode, bool sync) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + int ret = 0; + + spin_lock(&sbi->inode_lock[DIRTY_META]); + if (is_inode_flag_set(inode, FI_DIRTY_INODE)) { + ret = 1; + } else { + set_inode_flag(inode, FI_DIRTY_INODE); + stat_inc_dirty_inode(sbi, DIRTY_META); + } + if (sync && list_empty(&F2FS_I(inode)->gdirty_list)) { + list_add_tail(&F2FS_I(inode)->gdirty_list, + &sbi->inode_list[DIRTY_META]); + inc_page_count(sbi, F2FS_DIRTY_IMETA); + } + spin_unlock(&sbi->inode_lock[DIRTY_META]); + return ret; +} + +void f2fs_inode_synced(struct inode *inode) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + + spin_lock(&sbi->inode_lock[DIRTY_META]); + if (!is_inode_flag_set(inode, FI_DIRTY_INODE)) { + spin_unlock(&sbi->inode_lock[DIRTY_META]); + return; + } + if (!list_empty(&F2FS_I(inode)->gdirty_list)) { + list_del_init(&F2FS_I(inode)->gdirty_list); + dec_page_count(sbi, F2FS_DIRTY_IMETA); + } + clear_inode_flag(inode, FI_DIRTY_INODE); + clear_inode_flag(inode, FI_AUTO_RECOVER); + stat_dec_dirty_inode(F2FS_I_SB(inode), DIRTY_META); + spin_unlock(&sbi->inode_lock[DIRTY_META]); +} + /* * f2fs_dirty_inode() is called from __mark_inode_dirty() * @@ -499,7 +676,19 @@ static int f2fs_drop_inode(struct inode *inode) */ static void f2fs_dirty_inode(struct inode *inode, int flags) { - set_inode_flag(F2FS_I(inode), FI_DIRTY_INODE); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + + if (inode->i_ino == F2FS_NODE_INO(sbi) || + inode->i_ino == F2FS_META_INO(sbi)) + return; + + if (flags == I_DIRTY_TIME) + return; + + if (is_inode_flag_set(inode, FI_AUTO_RECOVER)) + clear_inode_flag(inode, FI_AUTO_RECOVER); + + f2fs_inode_dirtied(inode, false); } static void f2fs_i_callback(struct rcu_head *head) @@ -513,12 +702,32 @@ static void f2fs_destroy_inode(struct inode *inode) call_rcu(&inode->i_rcu, f2fs_i_callback); } +static void destroy_percpu_info(struct f2fs_sb_info *sbi) +{ + percpu_counter_destroy(&sbi->alloc_valid_block_count); + percpu_counter_destroy(&sbi->total_valid_inode_count); +} + +static void destroy_device_list(struct f2fs_sb_info *sbi) +{ + int i; + + for (i = 0; i < sbi->s_ndevs; i++) { + blkdev_put(FDEV(i).bdev, FMODE_EXCL); +#ifdef CONFIG_BLK_DEV_ZONED + kfree(FDEV(i).blkz_type); +#endif + } + kfree(sbi->devs); +} + static void f2fs_put_super(struct super_block *sb) { struct f2fs_sb_info *sbi = F2FS_SB(sb); if (sbi->s_proc) { remove_proc_entry("segment_info", sbi->s_proc); + remove_proc_entry("segment_bits", sbi->s_proc); remove_proc_entry(sb->s_id, f2fs_proc_root); } kobject_del(&sbi->s_kobj); @@ -534,7 +743,7 @@ static void f2fs_put_super(struct super_block *sb) * clean checkpoint again. */ if (is_sbi_flag_set(sbi, SBI_IS_DIRTY) || - !is_set_ckpt_flags(F2FS_CKPT(sbi), CP_UMOUNT_FLAG)) { + !is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG)) { struct cp_control cpc = { .reason = CP_UMOUNT, }; @@ -548,12 +757,14 @@ static void f2fs_put_super(struct super_block *sb) * normally superblock is clean, so we need to release this. * In addition, EIO will skip do checkpoint, we need this as well. */ - release_dirty_inode(sbi); - release_discard_addrs(sbi); + release_ino_entry(sbi, true); f2fs_leave_shrinker(sbi); mutex_unlock(&sbi->umount_mutex); + /* our cp_error case, we can wait for any writeback page */ + f2fs_flush_merged_bios(sbi); + iput(sbi->node_inode); iput(sbi->meta_inode); @@ -566,13 +777,20 @@ static void f2fs_put_super(struct super_block *sb) wait_for_completion(&sbi->s_kobj_unregister); sb->s_fs_info = NULL; - brelse(sbi->raw_super_buf); + if (sbi->s_chksum_driver) + crypto_free_shash(sbi->s_chksum_driver); + kfree(sbi->raw_super); + + destroy_device_list(sbi); + + destroy_percpu_info(sbi); kfree(sbi); } int f2fs_sync_fs(struct super_block *sb, int sync) { struct f2fs_sb_info *sbi = F2FS_SB(sb); + int err = 0; trace_f2fs_sync_fs(sb, sync); @@ -582,25 +800,27 @@ int f2fs_sync_fs(struct super_block *sb, int sync) cpc.reason = __get_cp_reason(sbi); mutex_lock(&sbi->gc_mutex); - write_checkpoint(sbi, &cpc); + err = write_checkpoint(sbi, &cpc); mutex_unlock(&sbi->gc_mutex); - } else { - f2fs_balance_fs(sbi); } f2fs_trace_ios(NULL, 1); - return 0; + return err; } static int f2fs_freeze(struct super_block *sb) { - int err; - if (f2fs_readonly(sb)) return 0; - err = f2fs_sync_fs(sb, 1); - return err; + /* IO error happened before */ + if (unlikely(f2fs_cp_error(F2FS_SB(sb)))) + return -EIO; + + /* must be clean, since sync_filesystem() was already called */ + if (is_sbi_flag_set(F2FS_SB(sb), SBI_IS_DIRTY)) + return -EINVAL; + return 0; } static int f2fs_unfreeze(struct super_block *sb) @@ -623,11 +843,12 @@ static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_bsize = sbi->blocksize; buf->f_blocks = total_count - start_count; - buf->f_bfree = buf->f_blocks - valid_user_blocks(sbi) - ovp_count; + buf->f_bfree = user_block_count - valid_user_blocks(sbi) + ovp_count; buf->f_bavail = user_block_count - valid_user_blocks(sbi); buf->f_files = sbi->total_node_count - F2FS_RESERVED_NODE_NUM; - buf->f_ffree = buf->f_files - valid_inode_count(sbi); + buf->f_ffree = min(buf->f_files - valid_node_count(sbi), + buf->f_bavail); buf->f_namelen = F2FS_NAME_LEN; buf->f_fsid.val[0] = (u32)id; @@ -676,6 +897,8 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) seq_puts(seq, ",noinline_data"); if (test_opt(sbi, INLINE_DENTRY)) seq_puts(seq, ",inline_dentry"); + else + seq_puts(seq, ",noinline_dentry"); if (!f2fs_readonly(sbi->sb) && test_opt(sbi, FLUSH_MERGE)) seq_puts(seq, ",flush_merge"); if (test_opt(sbi, NOBARRIER)) @@ -686,6 +909,14 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) seq_puts(seq, ",extent_cache"); else seq_puts(seq, ",noextent_cache"); + if (test_opt(sbi, DATA_FLUSH)) + seq_puts(seq, ",data_flush"); + + seq_puts(seq, ",mode="); + if (test_opt(sbi, ADAPTIVE)) + seq_puts(seq, "adaptive"); + else if (test_opt(sbi, LFS)) + seq_puts(seq, "lfs"); seq_printf(seq, ",active_logs=%u", sbi->active_logs); return 0; @@ -718,19 +949,47 @@ static int segment_info_seq_show(struct seq_file *seq, void *offset) return 0; } -static int segment_info_open_fs(struct inode *inode, struct file *file) +static int segment_bits_seq_show(struct seq_file *seq, void *offset) { - return single_open(file, segment_info_seq_show, PDE_DATA(inode)); + struct super_block *sb = seq->private; + struct f2fs_sb_info *sbi = F2FS_SB(sb); + unsigned int total_segs = + le32_to_cpu(sbi->raw_super->segment_count_main); + int i, j; + + seq_puts(seq, "format: segment_type|valid_blocks|bitmaps\n" + "segment_type(0:HD, 1:WD, 2:CD, 3:HN, 4:WN, 5:CN)\n"); + + for (i = 0; i < total_segs; i++) { + struct seg_entry *se = get_seg_entry(sbi, i); + + seq_printf(seq, "%-10d", i); + seq_printf(seq, "%d|%-3u|", se->type, + get_valid_blocks(sbi, i, 1)); + for (j = 0; j < SIT_VBLOCK_MAP_SIZE; j++) + seq_printf(seq, " %.2x", se->cur_valid_map[j]); + seq_putc(seq, '\n'); + } + return 0; } -static const struct file_operations f2fs_seq_segment_info_fops = { - .owner = THIS_MODULE, - .open = segment_info_open_fs, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, +#define F2FS_PROC_FILE_DEF(_name) \ +static int _name##_open_fs(struct inode *inode, struct file *file) \ +{ \ + return single_open(file, _name##_seq_show, PDE_DATA(inode)); \ +} \ + \ +static const struct file_operations f2fs_seq_##_name##_fops = { \ + .owner = THIS_MODULE, \ + .open = _name##_open_fs, \ + .read = seq_read, \ + .llseek = seq_lseek, \ + .release = single_release, \ }; +F2FS_PROC_FILE_DEF(segment_info); +F2FS_PROC_FILE_DEF(segment_bits); + static void default_options(struct f2fs_sb_info *sbi) { /* init some FS parameters */ @@ -738,7 +997,16 @@ static void default_options(struct f2fs_sb_info *sbi) set_opt(sbi, BG_GC); set_opt(sbi, INLINE_DATA); + set_opt(sbi, INLINE_DENTRY); set_opt(sbi, EXTENT_CACHE); + sbi->sb->s_flags |= MS_LAZYTIME; + set_opt(sbi, FLUSH_MERGE); + if (f2fs_sb_mounted_blkzoned(sbi->sb)) { + set_opt_mode(sbi, F2FS_MOUNT_LFS); + set_opt(sbi, DISCARD); + } else { + set_opt_mode(sbi, F2FS_MOUNT_ADAPTIVE); + } #ifdef CONFIG_F2FS_FS_XATTR set_opt(sbi, XATTR_USER); @@ -746,6 +1014,10 @@ static void default_options(struct f2fs_sb_info *sbi) #ifdef CONFIG_F2FS_FS_POSIX_ACL set_opt(sbi, POSIX_ACL); #endif + +#ifdef CONFIG_F2FS_FAULT_INJECTION + f2fs_build_fault_attr(sbi, 0); +#endif } static int f2fs_remount(struct super_block *sb, int *flags, char *data) @@ -756,8 +1028,9 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) bool need_restart_gc = false; bool need_stop_gc = false; bool no_extent_cache = !test_opt(sbi, EXTENT_CACHE); - - sync_filesystem(sb); +#ifdef CONFIG_F2FS_FAULT_INJECTION + struct f2fs_fault_info ffi = sbi->fault_info; +#endif /* * Save the old mount options in case we @@ -766,6 +1039,15 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) org_mount_opt = sbi->mount_opt; active_logs = sbi->active_logs; + /* recover superblocks we couldn't write due to previous RO mount */ + if (!(*flags & MS_RDONLY) && is_sbi_flag_set(sbi, SBI_NEED_SB_WRITE)) { + err = f2fs_commit_super(sbi, false); + f2fs_msg(sb, KERN_INFO, + "Try to recover all the superblocks, ret: %d", err); + if (!err) + clear_sbi_flag(sbi, SBI_NEED_SB_WRITE); + } + sbi->mount_opt.opt = 0; default_options(sbi); @@ -797,7 +1079,6 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) if ((*flags & MS_RDONLY) || !test_opt(sbi, BG_GC)) { if (sbi->gc_thread) { stop_gc_thread(sbi); - f2fs_sync_fs(sb, 1); need_restart_gc = true; } } else if (!sbi->gc_thread) { @@ -807,21 +1088,33 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) need_stop_gc = true; } + if (*flags & MS_RDONLY) { + writeback_inodes_sb(sb, WB_REASON_SYNC); + sync_inodes_sb(sb); + + set_sbi_flag(sbi, SBI_IS_DIRTY); + set_sbi_flag(sbi, SBI_IS_CLOSE); + f2fs_sync_fs(sb, 1); + clear_sbi_flag(sbi, SBI_IS_CLOSE); + } + /* * We stop issue flush thread if FS is mounted as RO * or if flush_merge is not passed in mount option. */ if ((*flags & MS_RDONLY) || !test_opt(sbi, FLUSH_MERGE)) { - destroy_flush_cmd_control(sbi); - } else if (!SM_I(sbi)->cmd_control_info) { + clear_opt(sbi, FLUSH_MERGE); + destroy_flush_cmd_control(sbi, false); + } else { err = create_flush_cmd_control(sbi); if (err) goto restore_gc; } skip: /* Update the POSIXACL Flag */ - sb->s_flags = (sb->s_flags & ~MS_POSIXACL) | + sb->s_flags = (sb->s_flags & ~MS_POSIXACL) | (test_opt(sbi, POSIX_ACL) ? MS_POSIXACL : 0); + return 0; restore_gc: if (need_restart_gc) { @@ -834,6 +1127,9 @@ restore_gc: restore_opts: sbi->mount_opt = org_mount_opt; sbi->active_logs = active_logs; +#ifdef CONFIG_F2FS_FAULT_INJECTION + sbi->fault_info = ffi; +#endif return err; } @@ -853,6 +1149,48 @@ static struct super_operations f2fs_sops = { .remount_fs = f2fs_remount, }; +#ifdef CONFIG_F2FS_FS_ENCRYPTION +static int f2fs_get_context(struct inode *inode, void *ctx, size_t len) +{ + return f2fs_getxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION, + F2FS_XATTR_NAME_ENCRYPTION_CONTEXT, + ctx, len, NULL); +} + +static int f2fs_key_prefix(struct inode *inode, u8 **key) +{ + *key = F2FS_I_SB(inode)->key_prefix; + return F2FS_I_SB(inode)->key_prefix_size; +} + +static int f2fs_set_context(struct inode *inode, const void *ctx, size_t len, + void *fs_data) +{ + return f2fs_setxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION, + F2FS_XATTR_NAME_ENCRYPTION_CONTEXT, + ctx, len, fs_data, XATTR_CREATE); +} + +static unsigned f2fs_max_namelen(struct inode *inode) +{ + return S_ISLNK(inode->i_mode) ? + inode->i_sb->s_blocksize : F2FS_NAME_LEN; +} + +static struct fscrypt_operations f2fs_cryptops = { + .get_context = f2fs_get_context, + .key_prefix = f2fs_key_prefix, + .set_context = f2fs_set_context, + .is_encrypted = f2fs_encrypted_inode, + .empty_dir = f2fs_empty_dir, + .max_namelen = f2fs_max_namelen, +}; +#else +static struct fscrypt_operations f2fs_cryptops = { + .is_encrypted = f2fs_encrypted_inode, +}; +#endif + static struct inode *f2fs_nfs_get_inode(struct super_block *sb, u64 ino, u32 generation) { @@ -898,7 +1236,7 @@ static const struct export_operations f2fs_export_ops = { .get_parent = f2fs_get_parent, }; -loff_t max_file_size(unsigned bits) +static loff_t max_file_blocks(void) { loff_t result = (DEF_ADDRS_PER_INODE - F2FS_INLINE_XATTR_ADDRS); loff_t leaf_count = ADDRS_PER_BLOCK; @@ -914,13 +1252,29 @@ loff_t max_file_size(unsigned bits) leaf_count *= NIDS_PER_BLOCK; result += leaf_count; - result <<= bits; return result; } -static inline bool sanity_check_area_boundary(struct super_block *sb, - struct f2fs_super_block *raw_super) +static int __f2fs_commit_super(struct buffer_head *bh, + struct f2fs_super_block *super) { + lock_buffer(bh); + if (super) + memcpy(bh->b_data + F2FS_SUPER_OFFSET, super, sizeof(*super)); + set_buffer_uptodate(bh); + set_buffer_dirty(bh); + unlock_buffer(bh); + + /* it's rare case, we can do fua all the time */ + return __sync_dirty_buffer(bh, WRITE_FLUSH_FUA); +} + +static inline bool sanity_check_area_boundary(struct f2fs_sb_info *sbi, + struct buffer_head *bh) +{ + struct f2fs_super_block *raw_super = (struct f2fs_super_block *) + (bh->b_data + F2FS_SUPER_OFFSET); + struct super_block *sb = sbi->sb; u32 segment0_blkaddr = le32_to_cpu(raw_super->segment0_blkaddr); u32 cp_blkaddr = le32_to_cpu(raw_super->cp_blkaddr); u32 sit_blkaddr = le32_to_cpu(raw_super->sit_blkaddr); @@ -934,6 +1288,10 @@ static inline bool sanity_check_area_boundary(struct super_block *sb, u32 segment_count_main = le32_to_cpu(raw_super->segment_count_main); u32 segment_count = le32_to_cpu(raw_super->segment_count); u32 log_blocks_per_seg = le32_to_cpu(raw_super->log_blocks_per_seg); + u64 main_end_blkaddr = main_blkaddr + + (segment_count_main << log_blocks_per_seg); + u64 seg_end_blkaddr = segment0_blkaddr + + (segment_count << log_blocks_per_seg); if (segment0_blkaddr != cp_blkaddr) { f2fs_msg(sb, KERN_INFO, @@ -978,22 +1336,47 @@ static inline bool sanity_check_area_boundary(struct super_block *sb, return true; } - if (main_blkaddr + (segment_count_main << log_blocks_per_seg) != - segment0_blkaddr + (segment_count << log_blocks_per_seg)) { + if (main_end_blkaddr > seg_end_blkaddr) { f2fs_msg(sb, KERN_INFO, - "Wrong MAIN_AREA boundary, start(%u) end(%u) blocks(%u)", + "Wrong MAIN_AREA boundary, start(%u) end(%u) block(%u)", main_blkaddr, - segment0_blkaddr + (segment_count << log_blocks_per_seg), + segment0_blkaddr + + (segment_count << log_blocks_per_seg), segment_count_main << log_blocks_per_seg); return true; - } + } else if (main_end_blkaddr < seg_end_blkaddr) { + int err = 0; + char *res; + + /* fix in-memory information all the time */ + raw_super->segment_count = cpu_to_le32((main_end_blkaddr - + segment0_blkaddr) >> log_blocks_per_seg); + if (f2fs_readonly(sb) || bdev_read_only(sb->s_bdev)) { + set_sbi_flag(sbi, SBI_NEED_SB_WRITE); + res = "internally"; + } else { + err = __f2fs_commit_super(bh, NULL); + res = err ? "failed" : "done"; + } + f2fs_msg(sb, KERN_INFO, + "Fix alignment : %s, start(%u) end(%u) block(%u)", + res, main_blkaddr, + segment0_blkaddr + + (segment_count << log_blocks_per_seg), + segment_count_main << log_blocks_per_seg); + if (err) + return true; + } return false; } -static int sanity_check_raw_super(struct super_block *sb, - struct f2fs_super_block *raw_super) +static int sanity_check_raw_super(struct f2fs_sb_info *sbi, + struct buffer_head *bh) { + struct f2fs_super_block *raw_super = (struct f2fs_super_block *) + (bh->b_data + F2FS_SUPER_OFFSET); + struct super_block *sb = sbi->sb; unsigned int blocksize; if (F2FS_SUPER_MAGIC != le32_to_cpu(raw_super->magic)) { @@ -1004,10 +1387,10 @@ static int sanity_check_raw_super(struct super_block *sb, } /* Currently, support only 4KB page cache size */ - if (F2FS_BLKSIZE != PAGE_CACHE_SIZE) { + if (F2FS_BLKSIZE != PAGE_SIZE) { f2fs_msg(sb, KERN_INFO, "Invalid page_cache_size (%lu), supports only 4KB\n", - PAGE_CACHE_SIZE); + PAGE_SIZE); return 1; } @@ -1059,27 +1442,19 @@ 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)) + if (sanity_check_area_boundary(sbi, bh)) return 1; 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 main_segs, blocks_per_seg; - int i; + unsigned int ovp_segments, reserved_segments; total = le32_to_cpu(raw_super->segment_count); fsmeta = le32_to_cpu(raw_super->segment_count_ckpt); @@ -1091,20 +1466,14 @@ static int sanity_check_ckpt(struct f2fs_sb_info *sbi) if (unlikely(fsmeta >= total)) return 1; - main_segs = le32_to_cpu(sbi->raw_super->segment_count_main); - blocks_per_seg = sbi->blocks_per_seg; + ovp_segments = le32_to_cpu(ckpt->overprov_segment_count); + reserved_segments = le32_to_cpu(ckpt->rsvd_segment_count); - for (i = 0; i < NR_CURSEG_NODE_TYPE; i++) { - if (le32_to_cpu(ckpt->cur_node_segno[i]) >= main_segs || - le16_to_cpu(ckpt->cur_node_blkoff[i]) >= blocks_per_seg) { - return 1; - } - } - for (i = 0; i < NR_CURSEG_DATA_TYPE; i++) { - if (le32_to_cpu(ckpt->cur_data_segno[i]) >= main_segs || - le16_to_cpu(ckpt->cur_data_blkoff[i]) >= blocks_per_seg) { - return 1; - } + 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; } if (unlikely(f2fs_cp_error(sbi))) { @@ -1137,129 +1506,282 @@ static void init_sb_info(struct f2fs_sb_info *sbi) sbi->cur_victim_sec = NULL_SECNO; sbi->max_victim_search = DEF_MAX_VICTIM_SEARCH; - for (i = 0; i < NR_COUNT_TYPE; i++) - atomic_set(&sbi->nr_pages[i], 0); - sbi->dir_level = DEF_DIR_LEVEL; - sbi->cp_interval = DEF_CP_INTERVAL; + sbi->interval_time[CP_TIME] = DEF_CP_INTERVAL; + sbi->interval_time[REQ_TIME] = DEF_IDLE_INTERVAL; clear_sbi_flag(sbi, SBI_NEED_FSCK); + for (i = 0; i < NR_COUNT_TYPE; i++) + atomic_set(&sbi->nr_pages[i], 0); + INIT_LIST_HEAD(&sbi->s_list); mutex_init(&sbi->umount_mutex); + mutex_init(&sbi->wio_mutex[NODE]); + mutex_init(&sbi->wio_mutex[DATA]); + spin_lock_init(&sbi->cp_lock); + +#ifdef CONFIG_F2FS_FS_ENCRYPTION + memcpy(sbi->key_prefix, F2FS_KEY_DESC_PREFIX, + F2FS_KEY_DESC_PREFIX_SIZE); + sbi->key_prefix_size = F2FS_KEY_DESC_PREFIX_SIZE; +#endif } +static int init_percpu_info(struct f2fs_sb_info *sbi) +{ + int err; + + err = percpu_counter_init(&sbi->alloc_valid_block_count, 0, GFP_KERNEL); + if (err) + return err; + + return percpu_counter_init(&sbi->total_valid_inode_count, 0, + GFP_KERNEL); +} + +#ifdef CONFIG_BLK_DEV_ZONED +static int init_blkz_info(struct f2fs_sb_info *sbi, int devi) +{ + struct block_device *bdev = FDEV(devi).bdev; + sector_t nr_sectors = bdev->bd_part->nr_sects; + sector_t sector = 0; + struct blk_zone *zones; + unsigned int i, nr_zones; + unsigned int n = 0; + int err = -EIO; + + if (!f2fs_sb_mounted_blkzoned(sbi->sb)) + return 0; + + if (sbi->blocks_per_blkz && sbi->blocks_per_blkz != + SECTOR_TO_BLOCK(bdev_zone_size(bdev))) + return -EINVAL; + sbi->blocks_per_blkz = SECTOR_TO_BLOCK(bdev_zone_size(bdev)); + if (sbi->log_blocks_per_blkz && sbi->log_blocks_per_blkz != + __ilog2_u32(sbi->blocks_per_blkz)) + return -EINVAL; + sbi->log_blocks_per_blkz = __ilog2_u32(sbi->blocks_per_blkz); + FDEV(devi).nr_blkz = SECTOR_TO_BLOCK(nr_sectors) >> + sbi->log_blocks_per_blkz; + if (nr_sectors & (bdev_zone_size(bdev) - 1)) + FDEV(devi).nr_blkz++; + + FDEV(devi).blkz_type = kmalloc(FDEV(devi).nr_blkz, GFP_KERNEL); + if (!FDEV(devi).blkz_type) + return -ENOMEM; + +#define F2FS_REPORT_NR_ZONES 4096 + + zones = kcalloc(F2FS_REPORT_NR_ZONES, sizeof(struct blk_zone), + GFP_KERNEL); + if (!zones) + return -ENOMEM; + + /* Get block zones type */ + while (zones && sector < nr_sectors) { + + nr_zones = F2FS_REPORT_NR_ZONES; + err = blkdev_report_zones(bdev, sector, + zones, &nr_zones, + GFP_KERNEL); + if (err) + break; + if (!nr_zones) { + err = -EIO; + break; + } + + for (i = 0; i < nr_zones; i++) { + FDEV(devi).blkz_type[n] = zones[i].type; + sector += zones[i].len; + n++; + } + } + + kfree(zones); + + return err; +} +#endif + /* * Read f2fs raw super block. - * Because we have two copies of super block, so read the first one at first, - * if the first one is invalid, move to read the second one. + * Because we have two copies of super block, so read both of them + * to get the first valid one. If any one of them is broken, we pass + * them recovery flag back to the caller. */ -static int read_raw_super_block(struct super_block *sb, +static int read_raw_super_block(struct f2fs_sb_info *sbi, struct f2fs_super_block **raw_super, - struct buffer_head **raw_super_buf, - int *recovery) + int *valid_super_block, int *recovery) { - int block = 0; - struct buffer_head *buffer; + struct super_block *sb = sbi->sb; + int block; + struct buffer_head *bh; struct f2fs_super_block *super; int err = 0; -retry: - buffer = sb_bread(sb, block); - if (!buffer) { - *recovery = 1; - f2fs_msg(sb, KERN_ERR, "Unable to read %dth superblock", + super = kzalloc(sizeof(struct f2fs_super_block), GFP_KERNEL); + if (!super) + return -ENOMEM; + + for (block = 0; block < 2; block++) { + bh = sb_bread(sb, block); + if (!bh) { + f2fs_msg(sb, KERN_ERR, "Unable to read %dth superblock", block + 1); - if (block == 0) { - block++; - goto retry; - } else { err = -EIO; - goto out; + continue; } - } - - super = (struct f2fs_super_block *) - ((char *)(buffer)->b_data + F2FS_SUPER_OFFSET); - /* sanity checking of raw super */ - if (sanity_check_raw_super(sb, super)) { - brelse(buffer); - *recovery = 1; - f2fs_msg(sb, KERN_ERR, - "Can't find valid F2FS filesystem in %dth superblock", - block + 1); - if (block == 0) { - block++; - goto retry; - } else { + /* sanity checking of raw super */ + if (sanity_check_raw_super(sbi, bh)) { + f2fs_msg(sb, KERN_ERR, + "Can't find valid F2FS filesystem in %dth superblock", + block + 1); err = -EINVAL; - goto out; + brelse(bh); + continue; } - } - if (!*raw_super) { - *raw_super_buf = buffer; - *raw_super = super; - } else { - /* already have a valid superblock */ - brelse(buffer); + if (!*raw_super) { + memcpy(super, bh->b_data + F2FS_SUPER_OFFSET, + sizeof(*super)); + *valid_super_block = block; + *raw_super = super; + } + brelse(bh); } - /* check the validity of the second superblock */ - if (block == 0) { - block++; - goto retry; - } + /* Fail to read any one of the superblocks*/ + if (err < 0) + *recovery = 1; -out: /* No valid superblock */ if (!*raw_super) - return err; + kfree(super); + else + err = 0; - return 0; + return err; } int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover) { - struct buffer_head *sbh = sbi->raw_super_buf; - sector_t block = sbh->b_blocknr; + struct buffer_head *bh; int err; - /* write back-up superblock first */ - sbh->b_blocknr = block ? 0 : 1; - mark_buffer_dirty(sbh); - err = sync_dirty_buffer(sbh); + if ((recover && f2fs_readonly(sbi->sb)) || + bdev_read_only(sbi->sb->s_bdev)) { + set_sbi_flag(sbi, SBI_NEED_SB_WRITE); + return -EROFS; + } - sbh->b_blocknr = block; + /* write back-up superblock first */ + bh = sb_getblk(sbi->sb, sbi->valid_super_block ? 0: 1); + if (!bh) + return -EIO; + err = __f2fs_commit_super(bh, F2FS_RAW_SUPER(sbi)); + brelse(bh); /* if we are in recovery path, skip writing valid superblock */ if (recover || err) - goto out; + return err; /* write current valid superblock */ - mark_buffer_dirty(sbh); - err = sync_dirty_buffer(sbh); -out: - clear_buffer_write_io_error(sbh); - set_buffer_uptodate(sbh); + bh = sb_getblk(sbi->sb, sbi->valid_super_block); + if (!bh) + return -EIO; + err = __f2fs_commit_super(bh, F2FS_RAW_SUPER(sbi)); + brelse(bh); return err; } +static int f2fs_scan_devices(struct f2fs_sb_info *sbi) +{ + struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi); + int i; + + for (i = 0; i < MAX_DEVICES; i++) { + if (!RDEV(i).path[0]) + return 0; + + if (i == 0) { + sbi->devs = kzalloc(sizeof(struct f2fs_dev_info) * + MAX_DEVICES, GFP_KERNEL); + if (!sbi->devs) + return -ENOMEM; + } + + memcpy(FDEV(i).path, RDEV(i).path, MAX_PATH_LEN); + FDEV(i).total_segments = le32_to_cpu(RDEV(i).total_segments); + if (i == 0) { + FDEV(i).start_blk = 0; + FDEV(i).end_blk = FDEV(i).start_blk + + (FDEV(i).total_segments << + sbi->log_blocks_per_seg) - 1 + + le32_to_cpu(raw_super->segment0_blkaddr); + } else { + FDEV(i).start_blk = FDEV(i - 1).end_blk + 1; + FDEV(i).end_blk = FDEV(i).start_blk + + (FDEV(i).total_segments << + sbi->log_blocks_per_seg) - 1; + } + + FDEV(i).bdev = blkdev_get_by_path(FDEV(i).path, + sbi->sb->s_mode, sbi->sb->s_type); + if (IS_ERR(FDEV(i).bdev)) + return PTR_ERR(FDEV(i).bdev); + + /* to release errored devices */ + sbi->s_ndevs = i + 1; + +#ifdef CONFIG_BLK_DEV_ZONED + if (bdev_zoned_model(FDEV(i).bdev) == BLK_ZONED_HM && + !f2fs_sb_mounted_blkzoned(sbi->sb)) { + f2fs_msg(sbi->sb, KERN_ERR, + "Zoned block device feature not enabled\n"); + return -EINVAL; + } + if (bdev_zoned_model(FDEV(i).bdev) != BLK_ZONED_NONE) { + if (init_blkz_info(sbi, i)) { + f2fs_msg(sbi->sb, KERN_ERR, + "Failed to initialize F2FS blkzone information"); + return -EINVAL; + } + f2fs_msg(sbi->sb, KERN_INFO, + "Mount Device [%2d]: %20s, %8u, %8x - %8x (zone: %s)", + i, FDEV(i).path, + FDEV(i).total_segments, + FDEV(i).start_blk, FDEV(i).end_blk, + bdev_zoned_model(FDEV(i).bdev) == BLK_ZONED_HA ? + "Host-aware" : "Host-managed"); + continue; + } +#endif + f2fs_msg(sbi->sb, KERN_INFO, + "Mount Device [%2d]: %20s, %8u, %8x - %8x", + i, FDEV(i).path, + FDEV(i).total_segments, + FDEV(i).start_blk, FDEV(i).end_blk); + } + return 0; +} + static int f2fs_fill_super(struct super_block *sb, void *data, int silent) { struct f2fs_sb_info *sbi; struct f2fs_super_block *raw_super; - struct buffer_head *raw_super_buf; struct inode *root; - long err; + int err; bool retry = true, need_fsck = false; char *options = NULL; - int recovery, i; + int recovery, i, valid_super_block; + struct curseg_info *seg_i; try_onemore: err = -EINVAL; raw_super = NULL; - raw_super_buf = NULL; + valid_super_block = -1; recovery = 0; /* allocate memory for f2fs-specific super block info */ @@ -1267,17 +1789,43 @@ try_onemore: if (!sbi) return -ENOMEM; + sbi->sb = sb; + + /* Load the checksum driver */ + sbi->s_chksum_driver = crypto_alloc_shash("crc32", 0, 0); + if (IS_ERR(sbi->s_chksum_driver)) { + f2fs_msg(sb, KERN_ERR, "Cannot load crc32 driver."); + err = PTR_ERR(sbi->s_chksum_driver); + sbi->s_chksum_driver = NULL; + goto free_sbi; + } + /* set a block size */ if (unlikely(!sb_set_blocksize(sb, F2FS_BLKSIZE))) { f2fs_msg(sb, KERN_ERR, "unable to set blocksize"); goto free_sbi; } - err = read_raw_super_block(sb, &raw_super, &raw_super_buf, &recovery); + err = read_raw_super_block(sbi, &raw_super, &valid_super_block, + &recovery); if (err) goto free_sbi; sb->s_fs_info = sbi; + sbi->raw_super = raw_super; + + /* + * The BLKZONED feature indicates that the drive was formatted with + * zone alignment optimization. This is optional for host-aware + * devices, but mandatory for host-managed zoned block devices. + */ +#ifndef CONFIG_BLK_DEV_ZONED + if (f2fs_sb_mounted_blkzoned(sb)) { + f2fs_msg(sb, KERN_ERR, + "Zoned block device support is not enabled\n"); + goto free_sb_buf; + } +#endif default_options(sbi); /* parse mount options */ options = kstrdup((const char *)data, GFP_KERNEL); @@ -1290,11 +1838,14 @@ try_onemore: if (err) goto free_options; - sb->s_maxbytes = max_file_size(le32_to_cpu(raw_super->log_blocksize)); + sbi->max_file_blocks = max_file_blocks(); + sb->s_maxbytes = sbi->max_file_blocks << + le32_to_cpu(raw_super->log_blocksize); sb->s_max_links = F2FS_LINK_MAX; get_random_bytes(&sbi->s_next_generation, sizeof(u32)); sb->s_op = &f2fs_sops; + sb->s_cop = &f2fs_cryptops; sb->s_xattr = f2fs_xattr_handlers; sb->s_export_op = &f2fs_export_ops; sb->s_magic = F2FS_SUPER_MAGIC; @@ -1304,11 +1855,8 @@ try_onemore: memcpy(sb->s_uuid, raw_super->uuid, sizeof(raw_super->uuid)); /* init f2fs-specific super block info */ - sbi->sb = sb; - sbi->raw_super = raw_super; - sbi->raw_super_buf = raw_super_buf; + sbi->valid_super_block = valid_super_block; mutex_init(&sbi->gc_mutex); - mutex_init(&sbi->writepages); mutex_init(&sbi->cp_mutex); init_rwsem(&sbi->node_write); @@ -1329,6 +1877,10 @@ try_onemore: init_waitqueue_head(&sbi->cp_wait); init_sb_info(sbi); + err = init_percpu_info(sbi); + if (err) + goto free_options; + /* get an inode for meta space */ sbi->meta_inode = f2fs_iget(sb, F2FS_META_INO(sbi)); if (IS_ERR(sbi->meta_inode)) { @@ -1343,24 +1895,26 @@ 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; + /* Initialize device list */ + err = f2fs_scan_devices(sbi); + if (err) { + f2fs_msg(sb, KERN_ERR, "Failed to find devices"); + goto free_devices; } sbi->total_valid_node_count = le32_to_cpu(sbi->ckpt->valid_node_count); - sbi->total_valid_inode_count = - le32_to_cpu(sbi->ckpt->valid_inode_count); + percpu_counter_set(&sbi->total_valid_inode_count, + le32_to_cpu(sbi->ckpt->valid_inode_count)); sbi->user_block_count = le64_to_cpu(sbi->ckpt->user_block_count); sbi->total_valid_block_count = le64_to_cpu(sbi->ckpt->valid_block_count); sbi->last_valid_block_count = sbi->total_valid_block_count; - sbi->alloc_valid_block_count = 0; - INIT_LIST_HEAD(&sbi->dir_inode_list); - spin_lock_init(&sbi->dir_inode_lock); + + for (i = 0; i < NR_INODE_TYPE; i++) { + INIT_LIST_HEAD(&sbi->inode_list[i]); + spin_lock_init(&sbi->inode_lock[i]); + } init_extent_cache_info(sbi); @@ -1380,6 +1934,17 @@ try_onemore: goto free_nm; } + /* For write statistics */ + if (sb->s_bdev->bd_part) + sbi->sectors_written_start = + (u64)part_stat_read(sb->s_bdev->bd_part, sectors[1]); + + /* Read accumulated write IO statistics if exists */ + seg_i = CURSEG_I(sbi, CURSEG_HOT_NODE); + if (__exist_node_summaries(sbi)) + sbi->kbytes_written = + le64_to_cpu(seg_i->journal->info.kbytes_written); + build_gc_manager(sbi); /* get an inode for node space */ @@ -1423,9 +1988,12 @@ try_onemore: if (f2fs_proc_root) sbi->s_proc = proc_mkdir(sb->s_id, f2fs_proc_root); - if (sbi->s_proc) + if (sbi->s_proc) { proc_create_data("segment_info", S_IRUGO, sbi->s_proc, &f2fs_seq_segment_info_fops, sb); + proc_create_data("segment_bits", S_IRUGO, sbi->s_proc, + &f2fs_seq_segment_bits_fops, sb); + } sbi->s_kobj.kset = f2fs_kset; init_completion(&sbi->s_kobj_unregister); @@ -1441,7 +2009,7 @@ try_onemore: * previous checkpoint was not done by clean system shutdown. */ if (bdev_read_only(sb->s_bdev) && - !is_set_ckpt_flags(sbi->ckpt, CP_UMOUNT_FLAG)) { + !is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG)) { err = -EROFS; goto free_kobj; } @@ -1449,14 +2017,27 @@ 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); + "Cannot recover all fsync data errno=%d", 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); @@ -1473,20 +2054,26 @@ try_onemore: kfree(options); /* recover broken superblock */ - if (recovery && !f2fs_readonly(sb) && !bdev_read_only(sb->s_bdev)) { - f2fs_msg(sb, KERN_INFO, "Recover invalid superblock"); - f2fs_commit_super(sbi, true); + if (recovery) { + err = f2fs_commit_super(sbi, true); + f2fs_msg(sb, KERN_INFO, + "Try to recover %dth superblock, ret: %d", + sbi->valid_super_block ? 1 : 2, err); } - sbi->cp_expires = round_jiffies_up(jiffies); - + f2fs_update_time(sbi, CP_TIME); + f2fs_update_time(sbi, REQ_TIME); return 0; free_kobj: + f2fs_sync_inode_meta(sbi); kobject_del(&sbi->s_kobj); + kobject_put(&sbi->s_kobj); + wait_for_completion(&sbi->s_kobj_unregister); free_proc: if (sbi->s_proc) { remove_proc_entry("segment_info", sbi->s_proc); + remove_proc_entry("segment_bits", sbi->s_proc); remove_proc_entry(sb->s_id, f2fs_proc_root); } f2fs_destroy_stats(sbi); @@ -1494,24 +2081,37 @@ free_root_inode: dput(sb->s_root); sb->s_root = NULL; free_node_inode: + truncate_inode_pages_final(NODE_MAPPING(sbi)); mutex_lock(&sbi->umount_mutex); + release_ino_entry(sbi, true); f2fs_leave_shrinker(sbi); + /* + * Some dirty meta pages can be produced by recover_orphan_inodes() + * failed by EIO. Then, iput(node_inode) can trigger balance_fs_bg() + * followed by write_checkpoint() through f2fs_write_node_pages(), which + * falls into an infinite loop in sync_meta_pages(). + */ + truncate_inode_pages_final(META_MAPPING(sbi)); iput(sbi->node_inode); mutex_unlock(&sbi->umount_mutex); free_nm: destroy_node_manager(sbi); free_sm: destroy_segment_manager(sbi); -free_cp: +free_devices: + destroy_device_list(sbi); kfree(sbi->ckpt); free_meta_inode: make_bad_inode(sbi->meta_inode); iput(sbi->meta_inode); free_options: + destroy_percpu_info(sbi); kfree(options); free_sb_buf: - brelse(raw_super_buf); + kfree(raw_super); free_sbi: + if (sbi->s_chksum_driver) + crypto_free_shash(sbi->s_chksum_driver); kfree(sbi); /* give only one another chance */ @@ -1547,8 +2147,9 @@ MODULE_ALIAS_FS("f2fs"); static int __init init_inodecache(void) { - f2fs_inode_cachep = f2fs_kmem_cache_create("f2fs_inode_cache", - sizeof(struct f2fs_inode_info)); + f2fs_inode_cachep = kmem_cache_create("f2fs_inode_cache", + sizeof(struct f2fs_inode_info), 0, + SLAB_RECLAIM_ACCOUNT, NULL); if (!f2fs_inode_cachep) return -ENOMEM; return 0; @@ -1590,25 +2191,23 @@ static int __init init_f2fs_fs(void) err = -ENOMEM; goto free_extent_cache; } - err = f2fs_init_crypto(); - if (err) - goto free_kset; - err = register_shrinker(&f2fs_shrinker_info); if (err) - goto free_crypto; + goto free_kset; err = register_filesystem(&f2fs_fs_type); if (err) goto free_shrinker; - f2fs_create_root_stats(); + err = f2fs_create_root_stats(); + if (err) + goto free_filesystem; f2fs_proc_root = proc_mkdir("fs/f2fs", NULL); return 0; +free_filesystem: + unregister_filesystem(&f2fs_fs_type); free_shrinker: unregister_shrinker(&f2fs_shrinker_info); -free_crypto: - f2fs_exit_crypto(); free_kset: kset_unregister(f2fs_kset); free_extent_cache: @@ -1629,15 +2228,14 @@ static void __exit exit_f2fs_fs(void) { remove_proc_entry("fs/f2fs", NULL); f2fs_destroy_root_stats(); - unregister_shrinker(&f2fs_shrinker_info); unregister_filesystem(&f2fs_fs_type); - f2fs_exit_crypto(); + unregister_shrinker(&f2fs_shrinker_info); + kset_unregister(f2fs_kset); destroy_extent_cache(); destroy_checkpoint_caches(); destroy_segment_manager_caches(); destroy_node_manager_caches(); destroy_inodecache(); - kset_unregister(f2fs_kset); f2fs_destroy_trace_ios(); } @@ -1647,3 +2245,4 @@ module_exit(exit_f2fs_fs) MODULE_AUTHOR("Samsung Electronics's Praesto Team"); MODULE_DESCRIPTION("Flash Friendly File System"); MODULE_LICENSE("GPL"); + diff --git a/fs/f2fs/trace.c b/fs/f2fs/trace.c index 145fb659ad44..562ce0821559 100644 --- a/fs/f2fs/trace.c +++ b/fs/f2fs/trace.c @@ -29,7 +29,8 @@ static inline void __print_last_io(void) last_io.major, last_io.minor, last_io.pid, "----------------", last_io.type, - last_io.fio.rw, last_io.fio.blk_addr, + last_io.fio.rw, + last_io.fio.new_blkaddr, last_io.len); memset(&last_io, 0, sizeof(last_io)); } @@ -101,7 +102,8 @@ void f2fs_trace_ios(struct f2fs_io_info *fio, int flush) last_io.pid == pid && last_io.type == __file_type(inode, pid) && last_io.fio.rw == fio->rw && - last_io.fio.blk_addr + last_io.len == fio->blk_addr) { + last_io.fio.new_blkaddr + last_io.len == + fio->new_blkaddr) { last_io.len++; return; } diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c index 862368a32e53..1c4d5e39586c 100644 --- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -151,7 +151,7 @@ static int f2fs_xattr_advise_set(const struct xattr_handler *handler, return -EINVAL; F2FS_I(inode)->i_advise |= *(char *)value; - mark_inode_dirty(inode); + f2fs_mark_inode_dirty_sync(inode, true); return 0; } @@ -264,18 +264,20 @@ static struct f2fs_xattr_entry *__find_xattr(void *base_addr, int index, return entry; } -static void *read_all_xattrs(struct inode *inode, struct page *ipage) +static int read_all_xattrs(struct inode *inode, struct page *ipage, + void **base_addr) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct f2fs_xattr_header *header; size_t size = PAGE_SIZE, inline_size = 0; void *txattr_addr; + int err; inline_size = inline_xattr_size(inode); txattr_addr = kzalloc(inline_size + size, GFP_F2FS_ZERO); if (!txattr_addr) - return NULL; + return -ENOMEM; /* read from inline xattr */ if (inline_size) { @@ -286,8 +288,10 @@ static void *read_all_xattrs(struct inode *inode, struct page *ipage) inline_addr = inline_xattr_addr(ipage); } else { page = get_node_page(sbi, inode->i_ino); - if (IS_ERR(page)) + if (IS_ERR(page)) { + err = PTR_ERR(page); goto fail; + } inline_addr = inline_xattr_addr(page); } memcpy(txattr_addr, inline_addr, inline_size); @@ -301,8 +305,10 @@ static void *read_all_xattrs(struct inode *inode, struct page *ipage) /* The inode already has an extended attribute block. */ xpage = get_node_page(sbi, F2FS_I(inode)->i_xattr_nid); - if (IS_ERR(xpage)) + if (IS_ERR(xpage)) { + err = PTR_ERR(xpage); goto fail; + } xattr_addr = page_address(xpage); memcpy(txattr_addr + inline_size, xattr_addr, PAGE_SIZE); @@ -316,10 +322,11 @@ static void *read_all_xattrs(struct inode *inode, struct page *ipage) header->h_magic = cpu_to_le32(F2FS_XATTR_MAGIC); header->h_refcount = cpu_to_le32(1); } - return txattr_addr; + *base_addr = txattr_addr; + return 0; fail: kzfree(txattr_addr); - return NULL; + return err; } static inline int write_all_xattrs(struct inode *inode, __u32 hsize, @@ -345,7 +352,8 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize, if (ipage) { inline_addr = inline_xattr_addr(ipage); - f2fs_wait_on_page_writeback(ipage, NODE); + f2fs_wait_on_page_writeback(ipage, NODE, true); + set_page_dirty(ipage); } else { page = get_node_page(sbi, inode->i_ino); if (IS_ERR(page)) { @@ -353,7 +361,7 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize, return PTR_ERR(page); } inline_addr = inline_xattr_addr(page); - f2fs_wait_on_page_writeback(page, NODE); + f2fs_wait_on_page_writeback(page, NODE, true); } memcpy(inline_addr, txattr_addr, inline_size); f2fs_put_page(page, 1); @@ -374,7 +382,7 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize, return PTR_ERR(xpage); } f2fs_bug_on(sbi, new_nid); - f2fs_wait_on_page_writeback(xpage, NODE); + f2fs_wait_on_page_writeback(xpage, NODE, true); } else { struct dnode_of_data dn; set_new_dnode(&dn, inode, NULL, NULL, new_nid); @@ -412,9 +420,9 @@ int f2fs_getxattr(struct inode *inode, int index, const char *name, if (len > F2FS_NAME_LEN) return -ERANGE; - base_addr = read_all_xattrs(inode, ipage); - if (!base_addr) - return -ENOMEM; + error = read_all_xattrs(inode, ipage, &base_addr); + if (error) + return error; entry = __find_xattr(base_addr, index, len, name); if (IS_XATTR_LAST_ENTRY(entry)) { @@ -448,9 +456,9 @@ ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) int error = 0; size_t rest = buffer_size; - base_addr = read_all_xattrs(inode, NULL); - if (!base_addr) - return -ENOMEM; + error = read_all_xattrs(inode, NULL, &base_addr); + if (error) + return error; list_for_each_xattr(entry, base_addr) { const struct xattr_handler *handler = @@ -481,13 +489,12 @@ static int __f2fs_setxattr(struct inode *inode, int index, const char *name, const void *value, size_t size, struct page *ipage, int flags) { - struct f2fs_inode_info *fi = F2FS_I(inode); struct f2fs_xattr_entry *here, *last; void *base_addr; int found, newsize; size_t len; __u32 new_hsize; - int error = -ENOMEM; + int error = 0; if (name == NULL) return -EINVAL; @@ -503,9 +510,9 @@ static int __f2fs_setxattr(struct inode *inode, int index, if (size > MAX_VALUE_LEN(inode)) return -E2BIG; - base_addr = read_all_xattrs(inode, ipage); - if (!base_addr) - goto exit; + error = read_all_xattrs(inode, ipage, &base_addr); + if (error) + return error; /* find entry with wanted name. */ here = __find_xattr(base_addr, index, len, name); @@ -538,7 +545,7 @@ static int __f2fs_setxattr(struct inode *inode, int index, free = free + ENTRY_SIZE(here); if (unlikely(free < newsize)) { - error = -ENOSPC; + error = -E2BIG; goto exit; } } @@ -566,7 +573,6 @@ static int __f2fs_setxattr(struct inode *inode, int index, * Before we come here, old entry is removed. * We just write new entry. */ - memset(last, 0, newsize); last->e_name_index = index; last->e_name_len = len; memcpy(last->e_name, name, len); @@ -580,19 +586,17 @@ static int __f2fs_setxattr(struct inode *inode, int index, if (error) goto exit; - if (is_inode_flag_set(fi, FI_ACL_MODE)) { - inode->i_mode = fi->i_acl_mode; - inode->i_ctime = CURRENT_TIME; - clear_inode_flag(fi, FI_ACL_MODE); + if (is_inode_flag_set(inode, FI_ACL_MODE)) { + inode->i_mode = F2FS_I(inode)->i_acl_mode; + inode->i_ctime = current_time(inode); + clear_inode_flag(inode, FI_ACL_MODE); } if (index == F2FS_XATTR_INDEX_ENCRYPTION && !strcmp(name, F2FS_XATTR_NAME_ENCRYPTION_CONTEXT)) f2fs_set_encrypted_inode(inode); - - if (ipage) - update_inode(inode, ipage); - else - update_inode_page(inode); + f2fs_mark_inode_dirty_sync(inode, true); + if (!error && S_ISDIR(inode->i_mode)) + set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_CP); exit: kzfree(base_addr); return error; @@ -609,7 +613,7 @@ int f2fs_setxattr(struct inode *inode, int index, const char *name, if (ipage) return __f2fs_setxattr(inode, index, name, value, size, ipage, flags); - f2fs_balance_fs(sbi); + f2fs_balance_fs(sbi, true); f2fs_lock_op(sbi); /* protect xattr_ver */ @@ -618,5 +622,6 @@ int f2fs_setxattr(struct inode *inode, int index, const char *name, up_write(&F2FS_I(inode)->i_sem); f2fs_unlock_op(sbi); + f2fs_update_time(sbi, REQ_TIME); return err; } diff --git a/fs/f2fs/xattr.h b/fs/f2fs/xattr.h index 71a7100d5492..d2fd0387a3c7 100644 --- a/fs/f2fs/xattr.h +++ b/fs/f2fs/xattr.h @@ -126,7 +126,8 @@ extern ssize_t f2fs_listxattr(struct dentry *, char *, size_t); #define f2fs_xattr_handlers NULL static inline int f2fs_setxattr(struct inode *inode, int index, - const char *name, const void *value, size_t size, int flags) + const char *name, const void *value, size_t size, + struct page *page, int flags) { return -EOPNOTSUPP; } diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index c7f1ce41442a..9e5a6842346e 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1145,9 +1145,7 @@ static void put_ol_stateid_locked(struct nfs4_ol_stateid *stp, static bool unhash_lock_stateid(struct nfs4_ol_stateid *stp) { - struct nfs4_openowner *oo = openowner(stp->st_openstp->st_stateowner); - - lockdep_assert_held(&oo->oo_owner.so_client->cl_lock); + lockdep_assert_held(&stp->st_stid.sc_client->cl_lock); list_del_init(&stp->st_locks); nfs4_unhash_stid(&stp->st_stid); @@ -1156,12 +1154,12 @@ static bool unhash_lock_stateid(struct nfs4_ol_stateid *stp) static void release_lock_stateid(struct nfs4_ol_stateid *stp) { - struct nfs4_openowner *oo = openowner(stp->st_openstp->st_stateowner); + struct nfs4_client *clp = stp->st_stid.sc_client; bool unhashed; - spin_lock(&oo->oo_owner.so_client->cl_lock); + spin_lock(&clp->cl_lock); unhashed = unhash_lock_stateid(stp); - spin_unlock(&oo->oo_owner.so_client->cl_lock); + spin_unlock(&clp->cl_lock); if (unhashed) nfs4_put_stid(&stp->st_stid); } diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 01448e01b40d..c066f6b56e58 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -229,6 +229,7 @@ struct dentry_operations { #define DCACHE_MAY_FREE 0x00800000 #define DCACHE_FALLTHRU 0x01000000 /* Fall through to lower layer */ #define DCACHE_OP_SELECT_INODE 0x02000000 /* Unioned entry: dcache op selects inode */ +#define DCACHE_ENCRYPTED_WITH_KEY 0x04000000 /* dir is encrypted with a valid key */ #define DCACHE_OP_REAL 0x08000000 extern seqlock_t rename_lock; diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 3d6e6ce44c5c..3e5972ef5019 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -21,7 +21,7 @@ #define F2FS_BLKSIZE 4096 /* support only 4KB block */ #define F2FS_BLKSIZE_BITS 12 /* bits for F2FS_BLKSIZE */ #define F2FS_MAX_EXTENSION 64 /* # of extension entries */ -#define F2FS_BLK_ALIGN(x) (((x) + F2FS_BLKSIZE - 1) / F2FS_BLKSIZE) +#define F2FS_BLK_ALIGN(x) (((x) + F2FS_BLKSIZE - 1) >> F2FS_BLKSIZE_BITS) #define NULL_ADDR ((block_t)0) /* used as block_t addresses */ #define NEW_ADDR ((block_t)-1) /* used as block_t addresses */ @@ -51,10 +51,18 @@ #define MAX_ACTIVE_DATA_LOGS 8 #define VERSION_LEN 256 +#define MAX_VOLUME_NAME 512 +#define MAX_PATH_LEN 64 +#define MAX_DEVICES 8 /* * For superblock */ +struct f2fs_device { + __u8 path[MAX_PATH_LEN]; + __le32 total_segments; +} __packed; + struct f2fs_super_block { __le32 magic; /* Magic Number */ __le16 major_ver; /* Major Version */ @@ -84,7 +92,7 @@ struct f2fs_super_block { __le32 node_ino; /* node inode number */ __le32 meta_ino; /* meta inode number */ __u8 uuid[16]; /* 128-bit uuid for volume */ - __le16 volume_name[512]; /* volume name */ + __le16 volume_name[MAX_VOLUME_NAME]; /* volume name */ __le32 extension_count; /* # of extensions below */ __u8 extension_list[F2FS_MAX_EXTENSION][8]; /* extension array */ __le32 cp_payload; @@ -93,12 +101,14 @@ struct f2fs_super_block { __le32 feature; /* defined features */ __u8 encryption_level; /* versioning level for encryption */ __u8 encrypt_pw_salt[16]; /* Salt used for string2key algorithm */ - __u8 reserved[871]; /* valid reserved region */ + struct f2fs_device devs[MAX_DEVICES]; /* device list */ + __u8 reserved[327]; /* valid reserved region */ } __packed; /* * For checkpoint */ +#define CP_CRC_RECOVERY_FLAG 0x00000040 #define CP_FASTBOOT_FLAG 0x00000020 #define CP_FSCK_FLAG 0x00000010 #define CP_ERROR_FLAG 0x00000008 @@ -169,12 +179,12 @@ struct f2fs_extent { #define F2FS_INLINE_XATTR_ADDRS 50 /* 200 bytes for inline xattrs */ #define DEF_ADDRS_PER_INODE 923 /* Address Pointers in an Inode */ #define DEF_NIDS_PER_INODE 5 /* Node IDs in an Inode */ -#define ADDRS_PER_INODE(fi) addrs_per_inode(fi) +#define ADDRS_PER_INODE(inode) addrs_per_inode(inode) #define ADDRS_PER_BLOCK 1018 /* Address Pointers in a Direct Block */ #define NIDS_PER_BLOCK 1018 /* Node IDs in an Indirect Block */ -#define ADDRS_PER_PAGE(page, fi) \ - (IS_INODE(page) ? ADDRS_PER_INODE(fi) : ADDRS_PER_BLOCK) +#define ADDRS_PER_PAGE(page, inode) \ + (IS_INODE(page) ? ADDRS_PER_INODE(inode) : ADDRS_PER_BLOCK) #define NODE_DIR1_BLOCK (DEF_ADDRS_PER_INODE + 1) #define NODE_DIR2_BLOCK (DEF_ADDRS_PER_INODE + 2) @@ -261,7 +271,7 @@ struct f2fs_node { /* * For NAT entries */ -#define NAT_ENTRY_PER_BLOCK (PAGE_CACHE_SIZE / sizeof(struct f2fs_nat_entry)) +#define NAT_ENTRY_PER_BLOCK (PAGE_SIZE / sizeof(struct f2fs_nat_entry)) struct f2fs_nat_entry { __u8 version; /* latest version of cached nat entry */ @@ -281,7 +291,7 @@ struct f2fs_nat_block { * Not allow to change this. */ #define SIT_VBLOCK_MAP_SIZE 64 -#define SIT_ENTRY_PER_BLOCK (PAGE_CACHE_SIZE / sizeof(struct f2fs_sit_entry)) +#define SIT_ENTRY_PER_BLOCK (PAGE_SIZE / sizeof(struct f2fs_sit_entry)) /* * F2FS uses 4 bytes to represent block address. As a result, supported size of @@ -350,7 +360,7 @@ struct f2fs_summary { struct summary_footer { unsigned char entry_type; /* SUM_TYPE_XXX */ - __u32 check_sum; /* summary checksum */ + __le32 check_sum; /* summary checksum */ } __packed; #define SUM_JOURNAL_SIZE (F2FS_BLKSIZE - SUM_FOOTER_SIZE -\ @@ -363,6 +373,12 @@ struct summary_footer { sizeof(struct sit_journal_entry)) #define SIT_JOURNAL_RESERVED ((SUM_JOURNAL_SIZE - 2) %\ sizeof(struct sit_journal_entry)) + +/* Reserved area should make size of f2fs_extra_info equals to + * that of nat_journal and sit_journal. + */ +#define EXTRA_INFO_RESERVED (SUM_JOURNAL_SIZE - 2 - 8) + /* * frequently updated NAT/SIT entries can be stored in the spare area in * summary blocks @@ -392,18 +408,28 @@ struct sit_journal { __u8 reserved[SIT_JOURNAL_RESERVED]; } __packed; -/* 4KB-sized summary block structure */ -struct f2fs_summary_block { - struct f2fs_summary entries[ENTRIES_IN_SUM]; +struct f2fs_extra_info { + __le64 kbytes_written; + __u8 reserved[EXTRA_INFO_RESERVED]; +} __packed; + +struct f2fs_journal { union { __le16 n_nats; __le16 n_sits; }; - /* spare area is used by NAT or SIT journals */ + /* spare area is used by NAT or SIT journals or extra info */ union { struct nat_journal nat_j; struct sit_journal sit_j; + struct f2fs_extra_info info; }; +} __packed; + +/* 4KB-sized summary block structure */ +struct f2fs_summary_block { + struct f2fs_summary entries[ENTRIES_IN_SUM]; + struct f2fs_journal journal; struct summary_footer footer; } __packed; @@ -497,4 +523,6 @@ enum { F2FS_FT_MAX }; +#define S_SHIFT 12 + #endif /* _LINUX_F2FS_FS_H */ diff --git a/include/linux/fs.h b/include/linux/fs.h index df1171bada01..c6de40668e08 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -52,6 +52,8 @@ struct swap_info_struct; struct seq_file; struct workqueue_struct; struct iov_iter; +struct fscrypt_info; +struct fscrypt_operations; extern void __init inode_init(void); extern void __init inode_init_early(void); @@ -686,6 +688,9 @@ struct inode { struct hlist_head i_fsnotify_marks; #endif +#if IS_ENABLED(CONFIG_FS_ENCRYPTION) + struct fscrypt_info *i_crypt_info; +#endif void *i_private; /* fs or device private pointer */ }; @@ -1350,6 +1355,8 @@ struct super_block { #endif const struct xattr_handler **s_xattr; + const struct fscrypt_operations *s_cop; + struct hlist_bl_head s_anon; /* anonymous dentries for (nfs) exporting */ struct list_head s_mounts; /* list of mounts; _not_ for fs use */ struct block_device *s_bdev; diff --git a/include/linux/fscrypto.h b/include/linux/fscrypto.h new file mode 100644 index 000000000000..ff8b11b26f31 --- /dev/null +++ b/include/linux/fscrypto.h @@ -0,0 +1,411 @@ +/* + * General per-file encryption definition + * + * Copyright (C) 2015, Google, Inc. + * + * Written by Michael Halcrow, 2015. + * Modified by Jaegeuk Kim, 2015. + */ + +#ifndef _LINUX_FSCRYPTO_H +#define _LINUX_FSCRYPTO_H + +#include <linux/key.h> +#include <linux/fs.h> +#include <linux/mm.h> +#include <linux/bio.h> +#include <linux/dcache.h> +#include <crypto/skcipher.h> +#include <uapi/linux/fs.h> + +#define FS_KEY_DERIVATION_NONCE_SIZE 16 +#define FS_ENCRYPTION_CONTEXT_FORMAT_V1 1 + +#define FS_POLICY_FLAGS_PAD_4 0x00 +#define FS_POLICY_FLAGS_PAD_8 0x01 +#define FS_POLICY_FLAGS_PAD_16 0x02 +#define FS_POLICY_FLAGS_PAD_32 0x03 +#define FS_POLICY_FLAGS_PAD_MASK 0x03 +#define FS_POLICY_FLAGS_VALID 0x03 + +/* Encryption algorithms */ +#define FS_ENCRYPTION_MODE_INVALID 0 +#define FS_ENCRYPTION_MODE_AES_256_XTS 1 +#define FS_ENCRYPTION_MODE_AES_256_GCM 2 +#define FS_ENCRYPTION_MODE_AES_256_CBC 3 +#define FS_ENCRYPTION_MODE_AES_256_CTS 4 + +/** + * Encryption context for inode + * + * Protector format: + * 1 byte: Protector format (1 = this version) + * 1 byte: File contents encryption mode + * 1 byte: File names encryption mode + * 1 byte: Flags + * 8 bytes: Master Key descriptor + * 16 bytes: Encryption Key derivation nonce + */ +struct fscrypt_context { + u8 format; + u8 contents_encryption_mode; + u8 filenames_encryption_mode; + u8 flags; + u8 master_key_descriptor[FS_KEY_DESCRIPTOR_SIZE]; + u8 nonce[FS_KEY_DERIVATION_NONCE_SIZE]; +} __packed; + +/* Encryption parameters */ +#define FS_XTS_TWEAK_SIZE 16 +#define FS_AES_128_ECB_KEY_SIZE 16 +#define FS_AES_256_GCM_KEY_SIZE 32 +#define FS_AES_256_CBC_KEY_SIZE 32 +#define FS_AES_256_CTS_KEY_SIZE 32 +#define FS_AES_256_XTS_KEY_SIZE 64 +#define FS_MAX_KEY_SIZE 64 + +#define FS_KEY_DESC_PREFIX "fscrypt:" +#define FS_KEY_DESC_PREFIX_SIZE 8 + +/* This is passed in from userspace into the kernel keyring */ +struct fscrypt_key { + u32 mode; + u8 raw[FS_MAX_KEY_SIZE]; + u32 size; +} __packed; + +struct fscrypt_info { + u8 ci_data_mode; + u8 ci_filename_mode; + u8 ci_flags; + struct crypto_skcipher *ci_ctfm; + struct key *ci_keyring_key; + u8 ci_master_key[FS_KEY_DESCRIPTOR_SIZE]; +}; + +#define FS_CTX_REQUIRES_FREE_ENCRYPT_FL 0x00000001 +#define FS_WRITE_PATH_FL 0x00000002 + +struct fscrypt_ctx { + union { + struct { + struct page *bounce_page; /* Ciphertext page */ + struct page *control_page; /* Original page */ + } w; + struct { + struct bio *bio; + struct work_struct work; + } r; + struct list_head free_list; /* Free list */ + }; + u8 flags; /* Flags */ + u8 mode; /* Encryption mode for tfm */ +}; + +struct fscrypt_completion_result { + struct completion completion; + int res; +}; + +#define DECLARE_FS_COMPLETION_RESULT(ecr) \ + struct fscrypt_completion_result ecr = { \ + COMPLETION_INITIALIZER((ecr).completion), 0 } + +#define FS_FNAME_NUM_SCATTER_ENTRIES 4 +#define FS_CRYPTO_BLOCK_SIZE 16 +#define FS_FNAME_CRYPTO_DIGEST_SIZE 32 + +/** + * For encrypted symlinks, the ciphertext length is stored at the beginning + * of the string in little-endian format. + */ +struct fscrypt_symlink_data { + __le16 len; + char encrypted_path[1]; +} __packed; + +/** + * This function is used to calculate the disk space required to + * store a filename of length l in encrypted symlink format. + */ +static inline u32 fscrypt_symlink_data_len(u32 l) +{ + if (l < FS_CRYPTO_BLOCK_SIZE) + l = FS_CRYPTO_BLOCK_SIZE; + return (l + sizeof(struct fscrypt_symlink_data) - 1); +} + +struct fscrypt_str { + unsigned char *name; + u32 len; +}; + +struct fscrypt_name { + const struct qstr *usr_fname; + struct fscrypt_str disk_name; + u32 hash; + u32 minor_hash; + struct fscrypt_str crypto_buf; +}; + +#define FSTR_INIT(n, l) { .name = n, .len = l } +#define FSTR_TO_QSTR(f) QSTR_INIT((f)->name, (f)->len) +#define fname_name(p) ((p)->disk_name.name) +#define fname_len(p) ((p)->disk_name.len) + +/* + * crypto opertions for filesystems + */ +struct fscrypt_operations { + int (*get_context)(struct inode *, void *, size_t); + int (*key_prefix)(struct inode *, u8 **); + int (*prepare_context)(struct inode *); + int (*set_context)(struct inode *, const void *, size_t, void *); + int (*dummy_context)(struct inode *); + bool (*is_encrypted)(struct inode *); + bool (*empty_dir)(struct inode *); + unsigned (*max_namelen)(struct inode *); +}; + +static inline bool fscrypt_dummy_context_enabled(struct inode *inode) +{ + if (inode->i_sb->s_cop->dummy_context && + inode->i_sb->s_cop->dummy_context(inode)) + return true; + return false; +} + +static inline bool fscrypt_valid_contents_enc_mode(u32 mode) +{ + return (mode == FS_ENCRYPTION_MODE_AES_256_XTS); +} + +static inline bool fscrypt_valid_filenames_enc_mode(u32 mode) +{ + return (mode == FS_ENCRYPTION_MODE_AES_256_CTS); +} + +static inline bool fscrypt_is_dot_dotdot(const struct qstr *str) +{ + if (str->len == 1 && str->name[0] == '.') + return true; + + if (str->len == 2 && str->name[0] == '.' && str->name[1] == '.') + return true; + + return false; +} + +static inline struct page *fscrypt_control_page(struct page *page) +{ +#if IS_ENABLED(CONFIG_FS_ENCRYPTION) + return ((struct fscrypt_ctx *)page_private(page))->w.control_page; +#else + WARN_ON_ONCE(1); + return ERR_PTR(-EINVAL); +#endif +} + +static inline int fscrypt_has_encryption_key(struct inode *inode) +{ +#if IS_ENABLED(CONFIG_FS_ENCRYPTION) + return (inode->i_crypt_info != NULL); +#else + return 0; +#endif +} + +static inline void fscrypt_set_encrypted_dentry(struct dentry *dentry) +{ +#if IS_ENABLED(CONFIG_FS_ENCRYPTION) + spin_lock(&dentry->d_lock); + dentry->d_flags |= DCACHE_ENCRYPTED_WITH_KEY; + spin_unlock(&dentry->d_lock); +#endif +} + +#if IS_ENABLED(CONFIG_FS_ENCRYPTION) +extern const struct dentry_operations fscrypt_d_ops; +#endif + +static inline void fscrypt_set_d_op(struct dentry *dentry) +{ +#if IS_ENABLED(CONFIG_FS_ENCRYPTION) + d_set_d_op(dentry, &fscrypt_d_ops); +#endif +} + +#if IS_ENABLED(CONFIG_FS_ENCRYPTION) +/* crypto.c */ +extern struct kmem_cache *fscrypt_info_cachep; +int fscrypt_initialize(void); + +extern struct fscrypt_ctx *fscrypt_get_ctx(struct inode *, gfp_t); +extern void fscrypt_release_ctx(struct fscrypt_ctx *); +extern struct page *fscrypt_encrypt_page(struct inode *, struct page *, gfp_t); +extern int fscrypt_decrypt_page(struct page *); +extern void fscrypt_decrypt_bio_pages(struct fscrypt_ctx *, struct bio *); +extern void fscrypt_pullback_bio_page(struct page **, bool); +extern void fscrypt_restore_control_page(struct page *); +extern int fscrypt_zeroout_range(struct inode *, pgoff_t, sector_t, + unsigned int); +/* policy.c */ +extern int fscrypt_process_policy(struct file *, const struct fscrypt_policy *); +extern int fscrypt_get_policy(struct inode *, struct fscrypt_policy *); +extern int fscrypt_has_permitted_context(struct inode *, struct inode *); +extern int fscrypt_inherit_context(struct inode *, struct inode *, + void *, bool); +/* keyinfo.c */ +extern int get_crypt_info(struct inode *); +extern int fscrypt_get_encryption_info(struct inode *); +extern void fscrypt_put_encryption_info(struct inode *, struct fscrypt_info *); + +/* fname.c */ +extern int fscrypt_setup_filename(struct inode *, const struct qstr *, + int lookup, struct fscrypt_name *); +extern void fscrypt_free_filename(struct fscrypt_name *); +extern u32 fscrypt_fname_encrypted_size(struct inode *, u32); +extern int fscrypt_fname_alloc_buffer(struct inode *, u32, + struct fscrypt_str *); +extern void fscrypt_fname_free_buffer(struct fscrypt_str *); +extern int fscrypt_fname_disk_to_usr(struct inode *, u32, u32, + const struct fscrypt_str *, struct fscrypt_str *); +extern int fscrypt_fname_usr_to_disk(struct inode *, const struct qstr *, + struct fscrypt_str *); +#endif + +/* crypto.c */ +static inline struct fscrypt_ctx *fscrypt_notsupp_get_ctx(struct inode *i, + gfp_t f) +{ + return ERR_PTR(-EOPNOTSUPP); +} + +static inline void fscrypt_notsupp_release_ctx(struct fscrypt_ctx *c) +{ + return; +} + +static inline struct page *fscrypt_notsupp_encrypt_page(struct inode *i, + struct page *p, gfp_t f) +{ + return ERR_PTR(-EOPNOTSUPP); +} + +static inline int fscrypt_notsupp_decrypt_page(struct page *p) +{ + return -EOPNOTSUPP; +} + +static inline void fscrypt_notsupp_decrypt_bio_pages(struct fscrypt_ctx *c, + struct bio *b) +{ + return; +} + +static inline void fscrypt_notsupp_pullback_bio_page(struct page **p, bool b) +{ + return; +} + +static inline void fscrypt_notsupp_restore_control_page(struct page *p) +{ + return; +} + +static inline int fscrypt_notsupp_zeroout_range(struct inode *i, pgoff_t p, + sector_t s, unsigned int f) +{ + return -EOPNOTSUPP; +} + +/* policy.c */ +static inline int fscrypt_notsupp_process_policy(struct file *f, + const struct fscrypt_policy *p) +{ + return -EOPNOTSUPP; +} + +static inline int fscrypt_notsupp_get_policy(struct inode *i, + struct fscrypt_policy *p) +{ + return -EOPNOTSUPP; +} + +static inline int fscrypt_notsupp_has_permitted_context(struct inode *p, + struct inode *i) +{ + return 0; +} + +static inline int fscrypt_notsupp_inherit_context(struct inode *p, + struct inode *i, void *v, bool b) +{ + return -EOPNOTSUPP; +} + +/* keyinfo.c */ +static inline int fscrypt_notsupp_get_encryption_info(struct inode *i) +{ + return -EOPNOTSUPP; +} + +static inline void fscrypt_notsupp_put_encryption_info(struct inode *i, + struct fscrypt_info *f) +{ + return; +} + + /* fname.c */ +static inline int fscrypt_notsupp_setup_filename(struct inode *dir, + const struct qstr *iname, + int lookup, struct fscrypt_name *fname) +{ + if (dir->i_sb->s_cop->is_encrypted(dir)) + return -EOPNOTSUPP; + + memset(fname, 0, sizeof(struct fscrypt_name)); + fname->usr_fname = iname; + fname->disk_name.name = (unsigned char *)iname->name; + fname->disk_name.len = iname->len; + return 0; +} + +static inline void fscrypt_notsupp_free_filename(struct fscrypt_name *fname) +{ + return; +} + +static inline u32 fscrypt_notsupp_fname_encrypted_size(struct inode *i, u32 s) +{ + /* never happens */ + WARN_ON(1); + return 0; +} + +static inline int fscrypt_notsupp_fname_alloc_buffer(struct inode *inode, + u32 ilen, struct fscrypt_str *crypto_str) +{ + return -EOPNOTSUPP; +} + +static inline void fscrypt_notsupp_fname_free_buffer(struct fscrypt_str *c) +{ + return; +} + +static inline int fscrypt_notsupp_fname_disk_to_usr(struct inode *inode, + u32 hash, u32 minor_hash, + const struct fscrypt_str *iname, + struct fscrypt_str *oname) +{ + return -EOPNOTSUPP; +} + +static inline int fscrypt_notsupp_fname_usr_to_disk(struct inode *inode, + const struct qstr *iname, + struct fscrypt_str *oname) +{ + return -EOPNOTSUPP; +} +#endif /* _LINUX_FSCRYPTO_H */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 33316a1ae98f..fe0a5de1eda5 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -12,6 +12,7 @@ #include <linux/cpumask.h> #include <linux/uprobes.h> #include <linux/page-flags-layout.h> +#include <linux/workqueue.h> #include <asm/page.h> #include <asm/mmu.h> @@ -531,6 +532,7 @@ struct mm_struct { int app_setting; #endif + struct work_struct async_put_work; }; static inline void mm_init_cpumask(struct mm_struct *mm) diff --git a/include/linux/sched.h b/include/linux/sched.h index 2716faadc618..7299540fe1ec 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2969,6 +2969,11 @@ static inline void mmdrop(struct mm_struct * mm) /* mmput gets rid of the mappings and all user-space */ extern int mmput(struct mm_struct *); +/* same as above but performs the slow path from the async kontext. Can + * be called from the atomic context as well + */ +extern void mmput_async(struct mm_struct *); + /* Grab a reference to a task's mm, if it is not already going away */ extern struct mm_struct *get_task_mm(struct task_struct *task); /* diff --git a/include/linux/tty_flip.h b/include/linux/tty_flip.h index c28dd523f96e..d43837f2ce3a 100644 --- a/include/linux/tty_flip.h +++ b/include/linux/tty_flip.h @@ -12,6 +12,7 @@ extern int tty_prepare_flip_string(struct tty_port *port, unsigned char **chars, size_t size); extern void tty_flip_buffer_push(struct tty_port *port); void tty_schedule_flip(struct tty_port *port); +int __tty_insert_flip_char(struct tty_port *port, unsigned char ch, char flag); static inline int tty_insert_flip_char(struct tty_port *port, unsigned char ch, char flag) @@ -26,7 +27,7 @@ static inline int tty_insert_flip_char(struct tty_port *port, *char_buf_ptr(tb, tb->used++) = ch; return 1; } - return tty_insert_flip_string_flags(port, &ch, &flag, 1); + return __tty_insert_flip_char(port, ch, flag); } static inline int tty_insert_flip_string(struct tty_port *port, diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index ac42bbb37b2d..c26a6e4dc306 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -1,14 +1,9 @@ #ifndef __NET_FRAG_H__ #define __NET_FRAG_H__ -#include <linux/percpu_counter.h> - struct netns_frags { - /* The percpu_counter "mem" need to be cacheline aligned. - * mem.count must not share cacheline with other writers - */ - struct percpu_counter mem ____cacheline_aligned_in_smp; - + /* Keep atomic mem on separate cachelines in structs that include it */ + atomic_t mem ____cacheline_aligned_in_smp; /* sysctls */ int timeout; int high_thresh; @@ -108,15 +103,10 @@ struct inet_frags { int inet_frags_init(struct inet_frags *); void inet_frags_fini(struct inet_frags *); -static inline int inet_frags_init_net(struct netns_frags *nf) -{ - return percpu_counter_init(&nf->mem, 0, GFP_KERNEL); -} -static inline void inet_frags_uninit_net(struct netns_frags *nf) +static inline void inet_frags_init_net(struct netns_frags *nf) { - percpu_counter_destroy(&nf->mem); + atomic_set(&nf->mem, 0); } - void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f); void inet_frag_kill(struct inet_frag_queue *q, struct inet_frags *f); @@ -140,37 +130,24 @@ static inline bool inet_frag_evicting(struct inet_frag_queue *q) /* Memory Tracking Functions. */ -/* The default percpu_counter batch size is not big enough to scale to - * fragmentation mem acct sizes. - * The mem size of a 64K fragment is approx: - * (44 fragments * 2944 truesize) + frag_queue struct(200) = 129736 bytes - */ -static unsigned int frag_percpu_counter_batch = 130000; - static inline int frag_mem_limit(struct netns_frags *nf) { - return percpu_counter_read(&nf->mem); + return atomic_read(&nf->mem); } static inline void sub_frag_mem_limit(struct netns_frags *nf, int i) { - __percpu_counter_add(&nf->mem, -i, frag_percpu_counter_batch); + atomic_sub(i, &nf->mem); } static inline void add_frag_mem_limit(struct netns_frags *nf, int i) { - __percpu_counter_add(&nf->mem, i, frag_percpu_counter_batch); + atomic_add(i, &nf->mem); } -static inline unsigned int sum_frag_mem_limit(struct netns_frags *nf) +static inline int sum_frag_mem_limit(struct netns_frags *nf) { - unsigned int res; - - local_bh_disable(); - res = percpu_counter_sum_positive(&nf->mem); - local_bh_enable(); - - return res; + return atomic_read(&nf->mem); } /* RFC 3168 support : diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index fb961a576abe..fa5e703a14ed 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -68,6 +68,7 @@ struct fib6_node { __u16 fn_flags; int fn_sernum; struct rt6_info *rr_ptr; + struct rcu_head rcu; }; #ifndef CONFIG_IPV6_SUBTREES @@ -102,7 +103,7 @@ struct rt6_info { * the same cache line. */ struct fib6_table *rt6i_table; - struct fib6_node *rt6i_node; + struct fib6_node __rcu *rt6i_node; struct in6_addr rt6i_gateway; @@ -165,13 +166,40 @@ static inline void rt6_update_expires(struct rt6_info *rt0, int timeout) rt0->rt6i_flags |= RTF_EXPIRES; } +/* Function to safely get fn->sernum for passed in rt + * and store result in passed in cookie. + * Return true if we can get cookie safely + * Return false if not + */ +static inline bool rt6_get_cookie_safe(const struct rt6_info *rt, + u32 *cookie) +{ + struct fib6_node *fn; + bool status = false; + + rcu_read_lock(); + fn = rcu_dereference(rt->rt6i_node); + + if (fn) { + *cookie = fn->fn_sernum; + status = true; + } + + rcu_read_unlock(); + return status; +} + static inline u32 rt6_get_cookie(const struct rt6_info *rt) { + u32 cookie = 0; + if (rt->rt6i_flags & RTF_PCPU || (unlikely(rt->dst.flags & DST_NOCACHE) && rt->dst.from)) rt = (struct rt6_info *)(rt->dst.from); - return rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0; + rt6_get_cookie_safe(rt, &cookie); + + return cookie; } static inline void ip6_rt_put(struct rt6_info *rt) diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index 00b4a6308249..90d6ad49a9c5 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -52,6 +52,7 @@ TRACE_DEFINE_ENUM(CP_DISCARD); { META_FLUSH, "META_FLUSH" }, \ { INMEM, "INMEM" }, \ { INMEM_DROP, "INMEM_DROP" }, \ + { INMEM_REVOKE, "INMEM_REVOKE" }, \ { IPU, "IN-PLACE" }, \ { OPU, "OUT-OF-PLACE" }) @@ -693,28 +694,32 @@ TRACE_EVENT(f2fs_direct_IO_exit, __entry->ret) ); -TRACE_EVENT(f2fs_reserve_new_block, +TRACE_EVENT(f2fs_reserve_new_blocks, - TP_PROTO(struct inode *inode, nid_t nid, unsigned int ofs_in_node), + TP_PROTO(struct inode *inode, nid_t nid, unsigned int ofs_in_node, + blkcnt_t count), - TP_ARGS(inode, nid, ofs_in_node), + TP_ARGS(inode, nid, ofs_in_node, count), TP_STRUCT__entry( __field(dev_t, dev) __field(nid_t, nid) __field(unsigned int, ofs_in_node) + __field(blkcnt_t, count) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->nid = nid; __entry->ofs_in_node = ofs_in_node; + __entry->count = count; ), - TP_printk("dev = (%d,%d), nid = %u, ofs_in_node = %u", + TP_printk("dev = (%d,%d), nid = %u, ofs_in_node = %u, count = %llu", show_dev(__entry), (unsigned int)__entry->nid, - __entry->ofs_in_node) + __entry->ofs_in_node, + (unsigned long long)__entry->count) ); DECLARE_EVENT_CLASS(f2fs__submit_page_bio, @@ -727,7 +732,8 @@ DECLARE_EVENT_CLASS(f2fs__submit_page_bio, __field(dev_t, dev) __field(ino_t, ino) __field(pgoff_t, index) - __field(block_t, blkaddr) + __field(block_t, old_blkaddr) + __field(block_t, new_blkaddr) __field(int, rw) __field(int, type) ), @@ -736,16 +742,18 @@ DECLARE_EVENT_CLASS(f2fs__submit_page_bio, __entry->dev = page->mapping->host->i_sb->s_dev; __entry->ino = page->mapping->host->i_ino; __entry->index = page->index; - __entry->blkaddr = fio->blk_addr; + __entry->old_blkaddr = fio->old_blkaddr; + __entry->new_blkaddr = fio->new_blkaddr; __entry->rw = fio->rw; __entry->type = fio->type; ), TP_printk("dev = (%d,%d), ino = %lu, page_index = 0x%lx, " - "blkaddr = 0x%llx, rw = %s%s, type = %s", + "oldaddr = 0x%llx, newaddr = 0x%llx rw = %s%s, type = %s", show_dev_ino(__entry), (unsigned long)__entry->index, - (unsigned long long)__entry->blkaddr, + (unsigned long long)__entry->old_blkaddr, + (unsigned long long)__entry->new_blkaddr, show_bio_type(__entry->rw), show_block_type(__entry->type)) ); @@ -1102,6 +1110,27 @@ TRACE_EVENT(f2fs_issue_discard, (unsigned long long)__entry->blklen) ); +TRACE_EVENT(f2fs_issue_reset_zone, + + TP_PROTO(struct super_block *sb, block_t blkstart), + + TP_ARGS(sb, blkstart), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(block_t, blkstart) + ), + + TP_fast_assign( + __entry->dev = sb->s_dev; + __entry->blkstart = blkstart; + ), + + TP_printk("dev = (%d,%d), reset zone at block = 0x%llx", + show_dev(__entry), + (unsigned long long)__entry->blkstart) +); + TRACE_EVENT(f2fs_issue_flush, TP_PROTO(struct super_block *sb, unsigned int nobarrier, @@ -1265,6 +1294,44 @@ TRACE_EVENT(f2fs_destroy_extent_tree, __entry->node_cnt) ); +DECLARE_EVENT_CLASS(f2fs_sync_dirty_inodes, + + TP_PROTO(struct super_block *sb, int type, s64 count), + + TP_ARGS(sb, type, count), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(int, type) + __field(s64, count) + ), + + TP_fast_assign( + __entry->dev = sb->s_dev; + __entry->type = type; + __entry->count = count; + ), + + TP_printk("dev = (%d,%d), %s, dirty count = %lld", + show_dev(__entry), + show_file_type(__entry->type), + __entry->count) +); + +DEFINE_EVENT(f2fs_sync_dirty_inodes, f2fs_sync_dirty_inodes_enter, + + TP_PROTO(struct super_block *sb, int type, s64 count), + + TP_ARGS(sb, type, count) +); + +DEFINE_EVENT(f2fs_sync_dirty_inodes, f2fs_sync_dirty_inodes_exit, + + TP_PROTO(struct super_block *sb, int type, s64 count), + + TP_ARGS(sb, type, count) +); + #endif /* _TRACE_F2FS_H */ /* This part must be outside protection */ diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index cd0c1a1a9ccf..15048097910f 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -173,6 +173,24 @@ struct inodes_stat_t { #define FS_IOC32_SETVERSION _IOW('v', 2, int) /* + * File system encryption support + */ +/* Policy provided via an ioctl on the topmost directory */ +#define FS_KEY_DESCRIPTOR_SIZE 8 + +struct fscrypt_policy { + __u8 version; + __u8 contents_encryption_mode; + __u8 filenames_encryption_mode; + __u8 flags; + __u8 master_key_descriptor[FS_KEY_DESCRIPTOR_SIZE]; +} __packed; + +#define FS_IOC_SET_ENCRYPTION_POLICY _IOR('f', 19, struct fscrypt_policy) +#define FS_IOC_GET_ENCRYPTION_PWSALT _IOW('f', 20, __u8[16]) +#define FS_IOC_GET_ENCRYPTION_POLICY _IOW('f', 21, struct fscrypt_policy) + +/* * Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS) */ #define FS_SECRM_FL 0x00000001 /* Secure deletion */ diff --git a/kernel/fork.c b/kernel/fork.c index 07cd0d68ee02..1d168ba55118 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -178,13 +178,13 @@ static inline void free_thread_stack(unsigned long *stack) # else static struct kmem_cache *thread_stack_cache; -static struct thread_info *alloc_thread_stack_node(struct task_struct *tsk, +static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node) { return kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node); } -static void free_stack(unsigned long *stack) +static void free_thread_stack(unsigned long *stack) { kmem_cache_free(thread_stack_cache, stack); } @@ -697,6 +697,26 @@ void __mmdrop(struct mm_struct *mm) } EXPORT_SYMBOL_GPL(__mmdrop); +static inline void __mmput(struct mm_struct *mm) +{ + VM_BUG_ON(atomic_read(&mm->mm_users)); + + uprobe_clear_state(mm); + exit_aio(mm); + ksm_exit(mm); + khugepaged_exit(mm); /* must run before exit_mmap */ + exit_mmap(mm); + set_mm_exe_file(mm, NULL); + if (!list_empty(&mm->mmlist)) { + spin_lock(&mmlist_lock); + list_del(&mm->mmlist); + spin_unlock(&mmlist_lock); + } + if (mm->binfmt) + module_put(mm->binfmt->module); + mmdrop(mm); +} + /* * Decrement the use count and release all resources for an mm. */ @@ -706,26 +726,27 @@ int mmput(struct mm_struct *mm) might_sleep(); if (atomic_dec_and_test(&mm->mm_users)) { - uprobe_clear_state(mm); - exit_aio(mm); - ksm_exit(mm); - khugepaged_exit(mm); /* must run before exit_mmap */ - exit_mmap(mm); - set_mm_exe_file(mm, NULL); - if (!list_empty(&mm->mmlist)) { - spin_lock(&mmlist_lock); - list_del(&mm->mmlist); - spin_unlock(&mmlist_lock); - } - if (mm->binfmt) - module_put(mm->binfmt->module); - mmdrop(mm); + __mmput(mm); mm_freed = 1; } return mm_freed; } EXPORT_SYMBOL_GPL(mmput); +static void mmput_async_fn(struct work_struct *work) +{ + struct mm_struct *mm = container_of(work, struct mm_struct, async_put_work); + __mmput(mm); +} + +void mmput_async(struct mm_struct *mm) +{ + if (atomic_dec_and_test(&mm->mm_users)) { + INIT_WORK(&mm->async_put_work, mmput_async_fn); + schedule_work(&mm->async_put_work); + } +} + /** * set_mm_exe_file - change a reference to the mm's executable file * diff --git a/kernel/sched/tune.c b/kernel/sched/tune.c index a71e94cecdb6..9c56841227cc 100644 --- a/kernel/sched/tune.c +++ b/kernel/sched/tune.c @@ -829,7 +829,6 @@ schedtune_boostgroup_init(struct schedtune *st) bg = &per_cpu(cpu_boost_groups, cpu); bg->group[st->idx].boost = 0; bg->group[st->idx].tasks = 0; - raw_spin_lock_init(&bg->lock); } return 0; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index eba904bae48c..38d73a6e2857 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -2667,13 +2667,14 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command) if (!command || !ftrace_enabled) { /* - * If these are control ops, they still need their - * per_cpu field freed. Since, function tracing is + * If these are dynamic or control ops, they still + * need their data freed. Since, function tracing is * not currently active, we can just free them * without synchronizing all CPUs. */ - if (ops->flags & FTRACE_OPS_FL_CONTROL) - control_ops_free(ops); + if (ops->flags & (FTRACE_OPS_FL_DYNAMIC | FTRACE_OPS_FL_CONTROL)) + goto free_ops; + return 0; } @@ -2728,6 +2729,7 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command) if (ops->flags & (FTRACE_OPS_FL_DYNAMIC | FTRACE_OPS_FL_CONTROL)) { schedule_on_each_cpu(ftrace_sync); + free_ops: arch_ftrace_trampoline_free(ops); if (ops->flags & FTRACE_OPS_FL_CONTROL) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index a579a874045b..35613a2a5164 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -5397,7 +5397,7 @@ static int tracing_set_clock(struct trace_array *tr, const char *clockstr) tracing_reset_online_cpus(&tr->trace_buffer); #ifdef CONFIG_TRACER_MAX_TRACE - if (tr->flags & TRACE_ARRAY_FL_GLOBAL && tr->max_buffer.buffer) + if (tr->max_buffer.buffer) ring_buffer_set_clock(tr->max_buffer.buffer, trace_clocks[i].func); tracing_reset_online_cpus(&tr->max_buffer); #endif diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index b0f86ea77881..ca70d11b8aa7 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -272,7 +272,7 @@ static int trace_selftest_ops(struct trace_array *tr, int cnt) goto out_free; if (cnt > 1) { if (trace_selftest_test_global_cnt == 0) - goto out; + goto out_free; } if (trace_selftest_test_dyn_cnt == 0) goto out_free; diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c index 6b437e8760d3..12e8cf4bda9f 100644 --- a/net/ieee802154/6lowpan/reassembly.c +++ b/net/ieee802154/6lowpan/reassembly.c @@ -580,19 +580,14 @@ static int __net_init lowpan_frags_init_net(struct net *net) { struct netns_ieee802154_lowpan *ieee802154_lowpan = net_ieee802154_lowpan(net); - int res; ieee802154_lowpan->frags.high_thresh = IPV6_FRAG_HIGH_THRESH; ieee802154_lowpan->frags.low_thresh = IPV6_FRAG_LOW_THRESH; ieee802154_lowpan->frags.timeout = IPV6_FRAG_TIMEOUT; - res = inet_frags_init_net(&ieee802154_lowpan->frags); - if (res) - return res; - res = lowpan_frags_ns_sysctl_register(net); - if (res) - inet_frags_uninit_net(&ieee802154_lowpan->frags); - return res; + inet_frags_init_net(&ieee802154_lowpan->frags); + + return lowpan_frags_ns_sysctl_register(net); } static void __net_exit lowpan_frags_exit_net(struct net *net) diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index fe144dae7372..c5fb2f694ed0 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -234,10 +234,8 @@ evict_again: cond_resched(); if (read_seqretry(&f->rnd_seqlock, seq) || - percpu_counter_sum(&nf->mem)) + sum_frag_mem_limit(nf)) goto evict_again; - - percpu_counter_destroy(&nf->mem); } EXPORT_SYMBOL(inet_frags_exit_net); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index b8a0607dab96..e2e162432aa3 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -840,8 +840,6 @@ static void __init ip4_frags_ctl_register(void) static int __net_init ipv4_frags_init_net(struct net *net) { - int res; - /* Fragment cache limits. * * The fragment memory accounting code, (tries to) account for @@ -865,13 +863,9 @@ static int __net_init ipv4_frags_init_net(struct net *net) */ net->ipv4.frags.timeout = IP_FRAG_TIME; - res = inet_frags_init_net(&net->ipv4.frags); - if (res) - return res; - res = ip4_frags_ns_ctl_register(net); - if (res) - inet_frags_uninit_net(&net->ipv4.frags); - return res; + inet_frags_init_net(&net->ipv4.frags); + + return ip4_frags_ns_ctl_register(net); } static void __net_exit ipv4_frags_exit_net(struct net *net) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 9bdd7847ef3a..79203972bfc6 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2269,6 +2269,10 @@ int tcp_disconnect(struct sock *sk, int flags) tcp_set_ca_state(sk, TCP_CA_Open); tcp_clear_retrans(tp); inet_csk_delack_init(sk); + /* Initialize rcv_mss to TCP_MIN_MSS to avoid division by 0 + * issue in __tcp_select_window() + */ + icsk->icsk_ack.rcv_mss = TCP_MIN_MSS; tcp_init_send_head(sk); memset(&tp->rx_opt, 0, sizeof(tp->rx_opt)); __sk_dst_reset(sk); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 4b707ad4ffbd..40c29712f32a 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -5230,7 +5230,7 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) * our DAD process, so we don't need * to do it again */ - if (!(ifp->rt->rt6i_node)) + if (!rcu_access_pointer(ifp->rt->rt6i_node)) ip6_ins_rt(ifp->rt); if (ifp->idev->cnf.forwarding) addrconf_join_anycast(ifp); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index aad8cdf15472..c23e02a7ccb0 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -150,11 +150,23 @@ static struct fib6_node *node_alloc(void) return fn; } -static void node_free(struct fib6_node *fn) +static void node_free_immediate(struct fib6_node *fn) +{ + kmem_cache_free(fib6_node_kmem, fn); +} + +static void node_free_rcu(struct rcu_head *head) { + struct fib6_node *fn = container_of(head, struct fib6_node, rcu); + kmem_cache_free(fib6_node_kmem, fn); } +static void node_free(struct fib6_node *fn) +{ + call_rcu(&fn->rcu, node_free_rcu); +} + static void rt6_rcu_free(struct rt6_info *rt) { call_rcu(&rt->dst.rcu_head, dst_rcu_free); @@ -191,6 +203,12 @@ static void rt6_release(struct rt6_info *rt) } } +static void fib6_free_table(struct fib6_table *table) +{ + inetpeer_invalidate_tree(&table->tb6_peers); + kfree(table); +} + static void fib6_link_table(struct net *net, struct fib6_table *tb) { unsigned int h; @@ -588,9 +606,9 @@ insert_above: if (!in || !ln) { if (in) - node_free(in); + node_free_immediate(in); if (ln) - node_free(ln); + node_free_immediate(ln); return ERR_PTR(-ENOMEM); } @@ -857,7 +875,7 @@ add: rt->dst.rt6_next = iter; *ins = rt; - rt->rt6i_node = fn; + rcu_assign_pointer(rt->rt6i_node, fn); atomic_inc(&rt->rt6i_ref); inet6_rt_notify(RTM_NEWROUTE, rt, info, 0); info->nl_net->ipv6.rt6_stats->fib_rt_entries++; @@ -882,7 +900,7 @@ add: return err; *ins = rt; - rt->rt6i_node = fn; + rcu_assign_pointer(rt->rt6i_node, fn); rt->dst.rt6_next = iter->dst.rt6_next; atomic_inc(&rt->rt6i_ref); inet6_rt_notify(RTM_NEWROUTE, rt, info, NLM_F_REPLACE); @@ -1015,7 +1033,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, root, and then (in failure) stale node in main tree. */ - node_free(sfn); + node_free_immediate(sfn); err = PTR_ERR(sn); goto failure; } @@ -1442,8 +1460,9 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp, int fib6_del(struct rt6_info *rt, struct nl_info *info) { + struct fib6_node *fn = rcu_dereference_protected(rt->rt6i_node, + lockdep_is_held(&rt->rt6i_table->tb6_lock)); struct net *net = info->nl_net; - struct fib6_node *fn = rt->rt6i_node; struct rt6_info **rtp; #if RT6_DEBUG >= 2 @@ -1632,7 +1651,9 @@ static int fib6_clean_node(struct fib6_walker *w) if (res) { #if RT6_DEBUG >= 2 pr_debug("%s: del failed: rt=%p@%p err=%d\n", - __func__, rt, rt->rt6i_node, res); + __func__, rt, + rcu_access_pointer(rt->rt6i_node), + res); #endif continue; } @@ -1870,15 +1891,22 @@ out_timer: static void fib6_net_exit(struct net *net) { + unsigned int i; + rt6_ifdown(net, NULL); del_timer_sync(&net->ipv6.ip6_fib_timer); -#ifdef CONFIG_IPV6_MULTIPLE_TABLES - inetpeer_invalidate_tree(&net->ipv6.fib6_local_tbl->tb6_peers); - kfree(net->ipv6.fib6_local_tbl); -#endif - inetpeer_invalidate_tree(&net->ipv6.fib6_main_tbl->tb6_peers); - kfree(net->ipv6.fib6_main_tbl); + for (i = 0; i < FIB6_TABLE_HASHSZ; i++) { + struct hlist_head *head = &net->ipv6.fib_table_hash[i]; + struct hlist_node *tmp; + struct fib6_table *tb; + + hlist_for_each_entry_safe(tb, tmp, head, tb6_hlist) { + hlist_del(&tb->tb6_hlist); + fib6_free_table(tb); + } + } + kfree(net->ipv6.fib_table_hash); kfree(net->ipv6.rt6_stats); } diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index bab4441ed4e4..eb2dc39f7066 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -649,18 +649,12 @@ EXPORT_SYMBOL_GPL(nf_ct_frag6_consume_orig); static int nf_ct_net_init(struct net *net) { - int res; - net->nf_frag.frags.high_thresh = IPV6_FRAG_HIGH_THRESH; net->nf_frag.frags.low_thresh = IPV6_FRAG_LOW_THRESH; net->nf_frag.frags.timeout = IPV6_FRAG_TIMEOUT; - res = inet_frags_init_net(&net->nf_frag.frags); - if (res) - return res; - res = nf_ct_frag6_sysctl_register(net); - if (res) - inet_frags_uninit_net(&net->nf_frag.frags); - return res; + inet_frags_init_net(&net->nf_frag.frags); + + return nf_ct_frag6_sysctl_register(net); } static void nf_ct_net_exit(struct net *net) diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index f9f02581c4ca..f99a04674419 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -86,7 +86,6 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) while (offset <= packet_len) { struct ipv6_opt_hdr *exthdr; - unsigned int len; switch (**nexthdr) { @@ -112,10 +111,9 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) exthdr = (struct ipv6_opt_hdr *)(skb_network_header(skb) + offset); - len = ipv6_optlen(exthdr); - if (len + offset >= IPV6_MAXPLEN) + offset += ipv6_optlen(exthdr); + if (offset > IPV6_MAXPLEN) return -EINVAL; - offset += len; *nexthdr = &exthdr->nexthdr; } diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index a234552a7e3d..58f2139ebb5e 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -708,19 +708,13 @@ static void ip6_frags_sysctl_unregister(void) static int __net_init ipv6_frags_init_net(struct net *net) { - int res; - net->ipv6.frags.high_thresh = IPV6_FRAG_HIGH_THRESH; net->ipv6.frags.low_thresh = IPV6_FRAG_LOW_THRESH; net->ipv6.frags.timeout = IPV6_FRAG_TIMEOUT; - res = inet_frags_init_net(&net->ipv6.frags); - if (res) - return res; - res = ip6_frags_ns_sysctl_register(net); - if (res) - inet_frags_uninit_net(&net->ipv6.frags); - return res; + inet_frags_init_net(&net->ipv6.frags); + + return ip6_frags_ns_sysctl_register(net); } static void __net_exit ipv6_frags_exit_net(struct net *net) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index dd37fe0b6a49..2e249d4a2bf3 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1241,7 +1241,9 @@ static void rt6_dst_from_metrics_check(struct rt6_info *rt) static struct dst_entry *rt6_check(struct rt6_info *rt, u32 cookie) { - if (!rt->rt6i_node || (rt->rt6i_node->fn_sernum != cookie)) + u32 rt_cookie; + + if (!rt6_get_cookie_safe(rt, &rt_cookie) || rt_cookie != cookie) return NULL; if (rt6_check_expired(rt)) @@ -1309,8 +1311,14 @@ static void ip6_link_failure(struct sk_buff *skb) if (rt->rt6i_flags & RTF_CACHE) { dst_hold(&rt->dst); ip6_del_rt(rt); - } else if (rt->rt6i_node && (rt->rt6i_flags & RTF_DEFAULT)) { - rt->rt6i_node->fn_sernum = -1; + } else { + struct fib6_node *fn; + + rcu_read_lock(); + fn = rcu_dereference(rt->rt6i_node); + if (fn && (rt->rt6i_flags & RTF_DEFAULT)) + fn->fn_sernum = -1; + rcu_read_unlock(); } } } @@ -1327,7 +1335,8 @@ static void rt6_do_update_pmtu(struct rt6_info *rt, u32 mtu) static bool rt6_cache_allowed_for_pmtu(const struct rt6_info *rt) { return !(rt->rt6i_flags & RTF_CACHE) && - (rt->rt6i_flags & RTF_PCPU || rt->rt6i_node); + (rt->rt6i_flags & RTF_PCPU || + rcu_access_pointer(rt->rt6i_node)); } static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, |