From 5d020af76e6de17167293ded5b1b37bd766228f3 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Wed, 12 Sep 2018 09:16:07 +0800 Subject: f2fs: add SPDX license identifiers Remove the verbose license text from f2fs files and replace them with SPDX tags. This does not change the license of any of the code. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 8e6a18582566..8b2b48bb53ff 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /** * include/linux/f2fs_fs.h * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #ifndef _LINUX_F2FS_FS_H #define _LINUX_F2FS_FS_H -- cgit v1.2.3 From f6a7a0346c35a6477f7b09b3a2f074e93cdafd7d Mon Sep 17 00:00:00 2001 From: Junling Zheng Date: Fri, 28 Sep 2018 20:25:56 +0800 Subject: f2fs: support superblock checksum Now we support crc32 checksum for superblock. Reviewed-by: Chao Yu Signed-off-by: Junling Zheng Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 8b2b48bb53ff..a5a5bd94551e 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -109,7 +109,8 @@ struct f2fs_super_block { struct f2fs_device devs[MAX_DEVICES]; /* device list */ __le32 qf_ino[F2FS_MAX_QUOTAS]; /* quota inode numbers */ __u8 hot_ext_count; /* # of hot file extension */ - __u8 reserved[314]; /* valid reserved region */ + __u8 reserved[310]; /* valid reserved region */ + __le32 crc; /* checksum of superblock */ } __packed; /* -- cgit v1.2.3 From 99efe50ef6cf0ba523ee32274fe0d58bc16e175f Mon Sep 17 00:00:00 2001 From: Daniel Rosenberg Date: Mon, 20 Aug 2018 19:21:43 -0700 Subject: f2fs: checkpoint disabling Note that, it requires "f2fs: return correct errno in f2fs_gc". This adds a lightweight non-persistent snapshotting scheme to f2fs. To use, mount with the option checkpoint=disable, and to return to normal operation, remount with checkpoint=enable. If the filesystem is shut down before remounting with checkpoint=enable, it will revert back to its apparent state when it was first mounted with checkpoint=disable. This is useful for situations where you wish to be able to roll back the state of the disk in case of some critical failure. Signed-off-by: Daniel Rosenberg [Jaegeuk Kim: use SB_RDONLY instead of MS_RDONLY] Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index a5a5bd94551e..6c2786db5154 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -116,6 +116,7 @@ struct f2fs_super_block { /* * For checkpoint */ +#define CP_DISABLED_FLAG 0x00001000 #define CP_LARGE_NAT_BITMAP_FLAG 0x00000400 #define CP_NOCRC_RECOVERY_FLAG 0x00000200 #define CP_TRIMMED_FLAG 0x00000100 -- cgit v1.2.3 From 0eea3276eebca7f423de34093d04a2e3fc541212 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Thu, 20 Sep 2018 20:05:00 +0800 Subject: f2fs: guarantee journalled quota data by checkpoint For journalled quota mode, let checkpoint to flush dquot dirty data and quota file data to guarntee persistence of all quota sysfile in last checkpoint, by this way, we can avoid corrupting quota sysfile when encountering SPO. The implementation is as below: 1. add a global state SBI_QUOTA_NEED_FLUSH to indicate that there is cached dquot metadata changes in quota subsystem, and later checkpoint should: a) flush dquot metadata into quota file. b) flush quota file to storage to keep file usage be consistent. 2. add a global state SBI_QUOTA_NEED_REPAIR to indicate that quota operation failed due to -EIO or -ENOSPC, so later, a) checkpoint will skip syncing dquot metadata. b) CP_QUOTA_NEED_FSCK_FLAG will be set in last cp pack to give a hint for fsck repairing. 3. add a global state SBI_QUOTA_SKIP_FLUSH, in checkpoint, if quota data updating is very heavy, it may cause hungtask in block_operation(). To avoid this, if our retry time exceed threshold, let's just skip flushing and retry in next checkpoint(). Signed-off-by: Weichao Guo Signed-off-by: Chao Yu [Jaegeuk Kim: avoid warnings and set fsck flag] Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 6c2786db5154..162f83358abb 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -117,6 +117,7 @@ struct f2fs_super_block { * For checkpoint */ #define CP_DISABLED_FLAG 0x00001000 +#define CP_QUOTA_NEED_FSCK_FLAG 0x00000800 #define CP_LARGE_NAT_BITMAP_FLAG 0x00000400 #define CP_NOCRC_RECOVERY_FLAG 0x00000200 #define CP_TRIMMED_FLAG 0x00000100 -- cgit v1.2.3 From 11eea056980680aa4a24870165da340f4b32d06d Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Wed, 20 Jul 2016 15:45:00 -0700 Subject: radix-tree: fix radix_tree_iter_retry() for tagged iterators. [ Upstream commit 3cb9185c67304b2a7ea9be73e7d13df6fb2793a1 ] radix_tree_iter_retry() resets slot to NULL, but it doesn't reset tags. Then NULL slot and non-zero iter.tags passed to radix_tree_next_slot() leading to crash: RIP: radix_tree_next_slot include/linux/radix-tree.h:473 find_get_pages_tag+0x334/0x930 mm/filemap.c:1452 .... Call Trace: pagevec_lookup_tag+0x3a/0x80 mm/swap.c:960 mpage_prepare_extent_to_map+0x321/0xa90 fs/ext4/inode.c:2516 ext4_writepages+0x10be/0x2b20 fs/ext4/inode.c:2736 do_writepages+0x97/0x100 mm/page-writeback.c:2364 __filemap_fdatawrite_range+0x248/0x2e0 mm/filemap.c:300 filemap_write_and_wait_range+0x121/0x1b0 mm/filemap.c:490 ext4_sync_file+0x34d/0xdb0 fs/ext4/fsync.c:115 vfs_fsync_range+0x10a/0x250 fs/sync.c:195 vfs_fsync fs/sync.c:209 do_fsync+0x42/0x70 fs/sync.c:219 SYSC_fdatasync fs/sync.c:232 SyS_fdatasync+0x19/0x20 fs/sync.c:230 entry_SYSCALL_64_fastpath+0x23/0xc1 arch/x86/entry/entry_64.S:207 We must reset iterator's tags to bail out from radix_tree_next_slot() and go to the slow-path in radix_tree_next_chunk(). Fixes: 46437f9a554f ("radix-tree: fix race in gang lookup") Link: http://lkml.kernel.org/r/1468495196-10604-1-git-send-email-aryabinin@virtuozzo.com Signed-off-by: Andrey Ryabinin Reported-by: Dmitry Vyukov Acked-by: Konstantin Khlebnikov Cc: Matthew Wilcox Cc: Hugh Dickins Cc: Ross Zwisler Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- include/linux/radix-tree.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 5d5174b59802..673dee29a9b9 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -382,6 +382,7 @@ static inline __must_check void **radix_tree_iter_retry(struct radix_tree_iter *iter) { iter->next_index = iter->index; + iter->tags = 0; return NULL; } -- cgit v1.2.3 From e25dc63aa366fd0f61d1d9ba67b66f5d75fc4372 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 30 Jun 2016 17:24:43 +0200 Subject: bpf: generally move prog destruction to RCU deferral [ Upstream commit 1aacde3d22c42281236155c1ef6d7a5aa32a826b ] Jann Horn reported following analysis that could potentially result in a very hard to trigger (if not impossible) UAF race, to quote his event timeline: - Set up a process with threads T1, T2 and T3 - Let T1 set up a socket filter F1 that invokes another filter F2 through a BPF map [tail call] - Let T1 trigger the socket filter via a unix domain socket write, don't wait for completion - Let T2 call PERF_EVENT_IOC_SET_BPF with F2, don't wait for completion - Now T2 should be behind bpf_prog_get(), but before bpf_prog_put() - Let T3 close the file descriptor for F2, dropping the reference count of F2 to 2 - At this point, T1 should have looked up F2 from the map, but not finished executing it - Let T3 remove F2 from the BPF map, dropping the reference count of F2 to 1 - Now T2 should call bpf_prog_put() (wrong BPF program type), dropping the reference count of F2 to 0 and scheduling bpf_prog_free_deferred() via schedule_work() - At this point, the BPF program could be freed - BPF execution is still running in a freed BPF program While at PERF_EVENT_IOC_SET_BPF time it's only guaranteed that the perf event fd we're doing the syscall on doesn't disappear from underneath us for whole syscall time, it may not be the case for the bpf fd used as an argument only after we did the put. It needs to be a valid fd pointing to a BPF program at the time of the call to make the bpf_prog_get() and while T2 gets preempted, F2 must have dropped reference to 1 on the other CPU. The fput() from the close() in T3 should also add additionally delay to the reference drop via exit_task_work() when bpf_prog_release() gets called as well as scheduling bpf_prog_free_deferred(). That said, it makes nevertheless sense to move the BPF prog destruction generally after RCU grace period to guarantee that such scenario above, but also others as recently fixed in ceb56070359b ("bpf, perf: delay release of BPF prog after grace period") with regards to tail calls won't happen. Integrating bpf_prog_free_deferred() directly into the RCU callback is not allowed since the invocation might happen from either softirq or process context, so we're not permitted to block. Reviewing all bpf_prog_put() invocations from eBPF side (note, cBPF -> eBPF progs don't use this for their destruction) with call_rcu() look good to me. Since we don't know whether at the time of attaching the program, we're already part of a tail call map, we need to use RCU variant. However, due to this, there won't be severely more stress on the RCU callback queue: situations with above bpf_prog_get() and bpf_prog_put() combo in practice normally won't lead to releases, but even if they would, enough effort/ cycles have to be put into loading a BPF program into the kernel already. Reported-by: Jann Horn Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- include/linux/bpf.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 132585a7fbd8..bae3da5bcda0 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -177,7 +177,6 @@ void bpf_register_map_type(struct bpf_map_type_list *tl); struct bpf_prog *bpf_prog_get(u32 ufd); struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog); void bpf_prog_put(struct bpf_prog *prog); -void bpf_prog_put_rcu(struct bpf_prog *prog); struct bpf_map *bpf_map_get_with_uref(u32 ufd); struct bpf_map *__bpf_map_get(struct fd f); @@ -208,10 +207,6 @@ static inline struct bpf_prog *bpf_prog_get(u32 ufd) static inline void bpf_prog_put(struct bpf_prog *prog) { } - -static inline void bpf_prog_put_rcu(struct bpf_prog *prog) -{ -} #endif /* CONFIG_BPF_SYSCALL */ /* verifier prototypes for helper functions called from eBPF programs */ -- cgit v1.2.3 From 8a1d3de19b0afbf069baf704afecfbeba9059fce Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Wed, 1 Jun 2016 18:52:16 +0100 Subject: cpuidle: Do not access cpuidle_devices when !CONFIG_CPU_IDLE commit 9bd616e3dbedfc103f158197c8ad93678849b1ed upstream. The cpuidle_devices per-CPU variable is only defined when CPU_IDLE is enabled. Commit c8cc7d4de7a4 ("sched/idle: Reorganize the idle loop") removed the #ifdef CONFIG_CPU_IDLE around cpuidle_idle_call() with the compiler optimising away __this_cpu_read(cpuidle_devices). However, with CONFIG_UBSAN && !CONFIG_CPU_IDLE, this optimisation no longer happens and the kernel fails to link since cpuidle_devices is not defined. This patch introduces an accessor function for the current CPU cpuidle device (returning NULL when !CONFIG_CPU_IDLE) and uses it in cpuidle_idle_call(). Signed-off-by: Catalin Marinas Cc: 4.5+ # 4.5+ Signed-off-by: Rafael J. Wysocki Cc: Guenter Roeck Signed-off-by: Greg Kroah-Hartman --- include/linux/cpuidle.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 786ad32631a6..07b83d32f66c 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -152,6 +152,8 @@ extern void cpuidle_disable_device(struct cpuidle_device *dev); extern int cpuidle_play_dead(void); extern struct cpuidle_driver *cpuidle_get_cpu_driver(struct cpuidle_device *dev); +static inline struct cpuidle_device *cpuidle_get_device(void) +{return __this_cpu_read(cpuidle_devices); } #else static inline void disable_cpuidle(void) { } static inline bool cpuidle_not_available(struct cpuidle_driver *drv, @@ -187,6 +189,7 @@ static inline void cpuidle_disable_device(struct cpuidle_device *dev) { } static inline int cpuidle_play_dead(void) {return -ENODEV; } static inline struct cpuidle_driver *cpuidle_get_cpu_driver( struct cpuidle_device *dev) {return NULL; } +static inline struct cpuidle_device *cpuidle_get_device(void) {return NULL; } #endif #if defined(CONFIG_CPU_IDLE) && defined(CONFIG_SUSPEND) -- cgit v1.2.3