Skip to content

L
linux
Switch branch/tag
  1. 29 Apr, 2024 1 commit
  3. 25 Apr, 2024 3 commits
  5. 19 Apr, 2024 7 commits
  7. 14 Apr, 2024 2 commits
  9. 12 Apr, 2024 8 commits
  11. 09 Apr, 2024 1 commit
  13. 02 Apr, 2024 1 commit
  15. 29 Mar, 2024 4 commits
    • Yunlei He's avatar
      f2fs: remove clear SB_INLINECRYPT flag in default_options · ac5eecf4
      Yunlei He authored 
      In f2fs_remount, SB_INLINECRYPT flag will be clear and re-set.
If create new file or open file during this gap, these files
will not use inlinecrypt. Worse case, it may lead to data
corruption if wrappedkey_v0 is enable.

Thread A:                               Thread B:

-f2fs_remount				-f2fs_file_open or f2fs_new_inode
  -default_options
	<- clear SB_INLINECRYPT flag

                                          -fscrypt_select_encryption_impl

  -parse_options
	<- set SB_INLINECRYPT again
Signed-off-by: default avatarYunlei He <heyunlei@oppo.com>
Reviewed-by: default avatarChao Yu <chao@kernel.org>
Signed-off-by: default avatarJaegeuk Kim <jaegeuk@kernel.org>
      ac5eecf4
    • Chao Yu's avatar
      f2fs: fix to wait on page writeback in __clone_blkaddrs() · d3876e34
      Chao Yu authored 
      In below race condition, dst page may become writeback status
in __clone_blkaddrs(), it needs to wait writeback before update,
fix it.

Thread A				GC Thread
- f2fs_move_file_range
  - filemap_write_and_wait_range(dst)
					- gc_data_segment
					 - f2fs_down_write(dst)
					 - move_data_page
					  - set_page_writeback(dst_page)
					  - f2fs_submit_page_write
					 - f2fs_up_write(dst)
  - f2fs_down_write(dst)
  - __exchange_data_block
   - __clone_blkaddrs
    - f2fs_get_new_data_page
    - memcpy_page

Fixes: 0a2aa8fb ("f2fs: refactor __exchange_data_block for speed up")
Signed-off-by: default avatarChao Yu <chao@kernel.org>
Signed-off-by: default avatarJaegeuk Kim <jaegeuk@kernel.org>
      d3876e34
    • Chao Yu's avatar
      f2fs: support to map continuous holes or preallocated address · 9f0f6bf4
      Chao Yu authored 
      This patch supports to map continuous holes or preallocated addresses
to improve performace of lookuping mapping info during read DIO.

[testcase 1]
xfs_io -f /mnt/f2fs/hole -c "truncate 1m" -c "fsync"
xfs_io -d /mnt/f2fs/hole -c "pread -b 1m 0 1m"

[before]
f2fs_direct_IO_enter: dev = (253,16), ino = 6 pos = 0 len = 1048576 ki_flags = 20000 ki_ioprio = 0 rw = 0
f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 0, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0
f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 1, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0
f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 2, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0
f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 3, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0
f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 4, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0
f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 5, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0
f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 6, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0
f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 7, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0
f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 8, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0
f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 9, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0
f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 10, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0
f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 11, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0
f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 12, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0
f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 13, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0
f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 14, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0
f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 15, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0
f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 16, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0
......
f2fs_direct_IO_exit: dev = (253,16), ino = 6 pos = 0 len = 1048576 rw = 0 ret = 1048576

[after]
f2fs_direct_IO_enter: dev = (253,16), ino = 6 pos = 0 len = 1048576 ki_flags = 20000 ki_ioprio = 0 rw = 0
f2fs_map_blocks: dev = (253,16), ino = 6, file offset = 0, start blkaddr = 0x0, len = 0x100, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0
f2fs_direct_IO_exit: dev = (253,16), ino = 6 pos = 0 len = 1048576 rw = 0 ret = 1048576

[testcase 2]
xfs_io -f /mnt/f2fs/preallocated -c "falloc 0 1m" -c "fsync"
xfs_io -d /mnt/f2fs/preallocated -c "pread -b 1m 0 1m"

[before]
f2fs_direct_IO_enter: dev = (253,16), ino = 11 pos = 0 len = 1048576 ki_flags = 20000 ki_ioprio = 0 rw = 0
f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 0, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0
f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 1, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0
f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 2, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0
f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 3, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0
f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 4, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0
f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 5, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0
f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 6, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0
f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 7, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0
f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 8, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0
f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 9, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0
f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 10, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0
f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 11, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0
f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 12, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0
f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 13, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0
f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 14, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0
f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 15, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0
f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 16, start blkaddr = 0x0, len = 0x0, flags = 0, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0
......
f2fs_direct_IO_exit: dev = (253,16), ino = 11 pos = 0 len = 1048576 rw = 0 ret = 1048576

[after]
f2fs_direct_IO_enter: dev = (253,16), ino = 11 pos = 0 len = 1048576 ki_flags = 20000 ki_ioprio = 0 rw = 0
f2fs_map_blocks: dev = (253,16), ino = 11, file offset = 0, start blkaddr = 0xffffffff, len = 0x100, flags = 4, seg_type = 1, may_create = 0, multidevice = 0, flag = 3, err = 0
f2fs_direct_IO_exit: dev = (253,16), ino = 11 pos = 0 len = 1048576 rw = 0 ret = 1048576
Signed-off-by: default avatarChao Yu <chao@kernel.org>
Signed-off-by: default avatarJaegeuk Kim <jaegeuk@kernel.org>
      9f0f6bf4
    • Chao Yu's avatar
      f2fs: multidev: fix to recognize valid zero block address · 33e62cd7
      Chao Yu authored 
      As reported by Yi Zhang in mailing list [1], kernel warning was catched
during zbd/010 test as below:

./check zbd/010
zbd/010 (test gap zone support with F2FS)                    [failed]
    runtime    ...  3.752s
    something found in dmesg:
    [ 4378.146781] run blktests zbd/010 at 2024-02-18 11:31:13
    [ 4378.192349] null_blk: module loaded
    [ 4378.209860] null_blk: disk nullb0 created
    [ 4378.413285] scsi_debug:sdebug_driver_probe: scsi_debug: trim
poll_queues to 0. poll_q/nr_hw = (0/1)
    [ 4378.422334] scsi host15: scsi_debug: version 0191 [20210520]
                     dev_size_mb=1024, opts=0x0, submit_queues=1, statistics=0
    [ 4378.434922] scsi 15:0:0:0: Direct-Access-ZBC Linux
scsi_debug       0191 PQ: 0 ANSI: 7
    [ 4378.443343] scsi 15:0:0:0: Power-on or device reset occurred
    [ 4378.449371] sd 15:0:0:0: Attached scsi generic sg5 type 20
    [ 4378.449418] sd 15:0:0:0: [sdf] Host-managed zoned block device
    ...
    (See '/mnt/tests/gitlab.com/api/v4/projects/19168116/repository/archive.zip/storage/blktests/blk/blktests/results/nodev/zbd/010.dmesg'

WARNING: CPU: 22 PID: 44011 at fs/iomap/iter.c:51
CPU: 22 PID: 44011 Comm: fio Not tainted 6.8.0-rc3+ #1
RIP: 0010:iomap_iter+0x32b/0x350
Call Trace:
 <TASK>
 __iomap_dio_rw+0x1df/0x830
 f2fs_file_read_iter+0x156/0x3d0 [f2fs]
 aio_read+0x138/0x210
 io_submit_one+0x188/0x8c0
 __x64_sys_io_submit+0x8c/0x1a0
 do_syscall_64+0x86/0x170
 entry_SYSCALL_64_after_hwframe+0x6e/0x76

Shinichiro Kawasaki helps to analyse this issue and proposes a potential
fixing patch in [2].

Quoted from reply of Shinichiro Kawasaki:

"I confirmed that the trigger commit is dbf8e63f as Yi reported. I took a
look in the commit, but it looks fine to me. So I thought the cause is not
in the commit diff.

I found the WARN is printed when the f2fs is set up with multiple devices,
and read requests are mapped to the very first block of the second device in the
direct read path. In this case, f2fs_map_blocks() and f2fs_map_blocks_cached()
modify map->m_pblk as the physical block address from each block device. It
becomes zero when it is mapped to the first block of the device. However,
f2fs_iomap_begin() assumes that map->m_pblk is the physical block address of the
whole f2fs, across the all block devices. It compares map->m_pblk against
NULL_ADDR == 0, then go into the unexpected branch and sets the invalid
iomap->length. The WARN catches the invalid iomap->length.

This WARN is printed even for non-zoned block devices, by following steps.

 - Create two (non-zoned) null_blk devices memory backed with 128MB size each:
   nullb0 and nullb1.
 # mkfs.f2fs /dev/nullb0 -c /dev/nullb1
 # mount -t f2fs /dev/nullb0 "${mount_dir}"
 # dd if=/dev/zero of="${mount_dir}/test.dat" bs=1M count=192
 # dd if="${mount_dir}/test.dat" of=/dev/null bs=1M count=192 iflag=direct

..."

So, the root cause of this issue is: when multi-devices feature is on,
f2fs_map_blocks() may return zero blkaddr in non-primary device, which is
a verified valid block address, however, f2fs_iomap_begin() treats it as
an invalid block address, and then it triggers the warning in iomap
framework code.

Finally, as discussed, we decide to use a more simple and direct way that
checking (map.m_flags & F2FS_MAP_MAPPED) condition instead of
(map.m_pblk != NULL_ADDR) to fix this issue.

Thanks a lot for the effort of Yi Zhang and Shinichiro Kawasaki on this
issue.

[1] https://lore.kernel.org/linux-f2fs-devel/CAHj4cs-kfojYC9i0G73PRkYzcxCTex=-vugRFeP40g_URGvnfQ@mail.gmail.com/
[2] https://lore.kernel.org/linux-f2fs-devel/gngdj77k4picagsfdtiaa7gpgnup6fsgwzsltx6milmhegmjff@iax2n4wvrqye/Reported-by: default avatarYi Zhang <yi.zhang@redhat.com>
Closes: https://lore.kernel.org/linux-f2fs-devel/CAHj4cs-kfojYC9i0G73PRkYzcxCTex=-vugRFeP40g_URGvnfQ@mail.gmail.com/Tested-by: default avatarShin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Tested-by: default avatarYi Zhang <yi.zhang@redhat.com>
Fixes: 1517c1a7 ("f2fs: implement iomap operations")
Fixes: 8d3c1fa3 ("f2fs: don't rely on F2FS_MAP_* in f2fs_iomap_begin")
Signed-off-by: default avatarChao Yu <chao@kernel.org>
Signed-off-by: default avatarJaegeuk Kim <jaegeuk@kernel.org>
      33e62cd7
  17. 26 Mar, 2024 4 commits
  19. 25 Mar, 2024 2 commits
  21. 24 Mar, 2024 7 commits
    • Linus Torvalds's avatar
      Linux 6.9-rc1 · 4cece764
      Linus Torvalds authored
      4cece764
    • Linus Torvalds's avatar
      Merge tag 'efi-fixes-for-v6.9-2' of git://git.kernel.org/pub/scm/linux/kernel/git/efi/efi · ab8de2db
      Linus Torvalds authored 
      Pull EFI fixes from Ard Biesheuvel:

 - Fix logic that is supposed to prevent placement of the kernel image
   below LOAD_PHYSICAL_ADDR

 - Use the firmware stack in the EFI stub when running in mixed mode

 - Clear BSS only once when using mixed mode

 - Check efi.get_variable() function pointer for NULL before trying to
   call it

* tag 'efi-fixes-for-v6.9-2' of git://git.kernel.org/pub/scm/linux/kernel/git/efi/efi:
  efi: fix panic in kdump kernel
  x86/efistub: Don't clear BSS twice in mixed mode
  x86/efistub: Call mixed mode boot services on the firmware's stack
  efi/libstub: fix efi_random_alloc() to allocate memory at alloc_min or higher address
      ab8de2db
    • Linus Torvalds's avatar
      Merge tag 'x86-urgent-2024-03-24' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip · 5e74df2f
      Linus Torvalds authored 
      Pull x86 fixes from Thomas Gleixner:

 - Ensure that the encryption mask at boot is properly propagated on
   5-level page tables, otherwise the PGD entry is incorrectly set to
   non-encrypted, which causes system crashes during boot.

 - Undo the deferred 5-level page table setup as it cannot work with
   memory encryption enabled.

 - Prevent inconsistent XFD state on CPU hotplug, where the MSR is reset
   to the default value but the cached variable is not, so subsequent
   comparisons might yield the wrong result and as a consequence the
   result prevents updating the MSR.

 - Register the local APIC address only once in the MPPARSE enumeration
   to prevent triggering the related WARN_ONs() in the APIC and topology
   code.

 - Handle the case where no APIC is found gracefully by registering a
   fake APIC in the topology code. That makes all related topology
   functions work correctly and does not affect the actual APIC driver
   code at all.

 - Don't evaluate logical IDs during early boot as the local APIC IDs
   are not yet enumerated and the invoked function returns an error
   code. Nothing requires the logical IDs before the final CPUID
   enumeration takes place, which happens after the enumeration.

 - Cure the fallout of the per CPU rework on UP which misplaced the
   copying of boot_cpu_data to per CPU data so that the final update to
   boot_cpu_data got lost which caused inconsistent state and boot
   crashes.

 - Use copy_from_kernel_nofault() in the kprobes setup as there is no
   guarantee that the address can be safely accessed.

 - Reorder struct members in struct saved_context to work around another
   kmemleak false positive

 - Remove the buggy code which tries to update the E820 kexec table for
   setup_data as that is never passed to the kexec kernel.

 - Update the resource control documentation to use the proper units.

 - Fix a Kconfig warning observed with tinyconfig

* tag 'x86-urgent-2024-03-24' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/boot/64: Move 5-level paging global variable assignments back
  x86/boot/64: Apply encryption mask to 5-level pagetable update
  x86/cpu: Add model number for another Intel Arrow Lake mobile processor
  x86/fpu: Keep xfd_state in sync with MSR_IA32_XFD
  Documentation/x86: Document that resctrl bandwidth control units are MiB
  x86/mpparse: Register APIC address only once
  x86/topology: Handle the !APIC case gracefully
  x86/topology: Don't evaluate logical IDs during early boot
  x86/cpu: Ensure that CPU info updates are propagated on UP
  kprobes/x86: Use copy_from_kernel_nofault() to read from unsafe address
  x86/pm: Work around false positive kmemleak report in msr_build_context()
  x86/kexec: Do not update E820 kexec table for setup_data
  x86/config: Fix warning for 'make ARCH=x86_64 tinyconfig'
      5e74df2f
    • Linus Torvalds's avatar
      Merge tag 'sched-urgent-2024-03-24' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip · b136f68e
      Linus Torvalds authored 
      Pull scheduler doc clarification from Thomas Gleixner:
 "A single update for the documentation of the base_slice_ns tunable to
  clarify that any value which is less than the tick slice has no effect
  because the scheduler tick is not guaranteed to happen within the set
  time slice"

* tag 'sched-urgent-2024-03-24' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/doc: Update documentation for base_slice_ns and CONFIG_HZ relation
      b136f68e
    • Linus Torvalds's avatar
      Merge tag 'dma-mapping-6.9-2024-03-24' of git://git.infradead.org/users/hch/dma-mapping · 864ad046
      Linus Torvalds authored 
      Pull dma-mapping fixes from Christoph Hellwig:
 "This has a set of swiotlb alignment fixes for sometimes very long
  standing bugs from Will. We've been discussion them for a while and
  they should be solid now"

* tag 'dma-mapping-6.9-2024-03-24' of git://git.infradead.org/users/hch/dma-mapping:
  swiotlb: Reinstate page-alignment for mappings >= PAGE_SIZE
  iommu/dma: Force swiotlb_max_mapping_size on an untrusted device
  swiotlb: Fix alignment checks when both allocation and DMA masks are present
  swiotlb: Honour dma_alloc_coherent() alignment in swiotlb_alloc()
  swiotlb: Enforce page alignment in swiotlb_alloc()
  swiotlb: Fix double-allocation of slots due to broken alignment handling
      864ad046
    • Oleksandr Tymoshenko's avatar
      efi: fix panic in kdump kernel · 62b71cd7
      Oleksandr Tymoshenko authored 
      Check if get_next_variable() is actually valid pointer before
calling it. In kdump kernel this method is set to NULL that causes
panic during the kexec-ed kernel boot.

Tested with QEMU and OVMF firmware.

Fixes: bad267f9 ("efi: verify that variable services are supported")
Signed-off-by: default avatarOleksandr Tymoshenko <ovt@google.com>
Signed-off-by: default avatarArd Biesheuvel <ardb@kernel.org>
      62b71cd7
    • Ard Biesheuvel's avatar
      x86/efistub: Don't clear BSS twice in mixed mode · df7ecce8
      Ard Biesheuvel authored 
      Clearing BSS should only be done once, at the very beginning.
efi_pe_entry() is the entrypoint from the firmware, which may not clear
BSS and so it is done explicitly. However, efi_pe_entry() is also used
as an entrypoint by the mixed mode startup code, in which case BSS will
already have been cleared, and doing it again at this point will corrupt
global variables holding the firmware's GDT/IDT and segment selectors.

So make the memset() conditional on whether the EFI stub is running in
native mode.

Fixes: b3810c5a ("x86/efistub: Clear decompressor BSS in native EFI entrypoint")
Signed-off-by: default avatarArd Biesheuvel <ardb@kernel.org>
      df7ecce8
GitLab Nexedi Edition | About GitLab | About Nexedi | 沪ICP备2021021310号-2 | 沪ICP备2021021310号-7