commit 420902c upstream.

If we hold the superblock lock while calling reiserfs_quota_on_mount(), we can
deadlock our own worker - mount blocks kworker/3:2, sleeps forever more.

crash> ps|grep UN
    715      2   3  ffff880220734d30  UN   0.0       0      0  [kworker/3:2]
   9369   9341   2  ffff88021ffb7560  UN   1.3  493404 123184  Xorg
   9665   9664   3  ffff880225b92ab0  UN   0.0   47368    812  udisks-daemon
  10635  10403   3  ffff880222f22c70  UN   0.0   14904    936  mount
crash> bt ffff880220734d30
PID: 715    TASK: ffff880220734d30  CPU: 3   COMMAND: "kworker/3:2"
 #0 [ffff8802244c3c20] schedule at ffffffff8144584b
 #1 [ffff8802244c3cc8] __rt_mutex_slowlock at ffffffff814472b3
 #2 [ffff8802244c3d28] rt_mutex_slowlock at ffffffff814473f5
 #3 [ffff8802244c3dc8] reiserfs_write_lock at ffffffffa05f28fd [reiserfs]
 #4 [ffff8802244c3de8] flush_async_commits at ffffffffa05ec91d [reiserfs]
 #5 [ffff8802244c3e08] process_one_work at ffffffff81073726
 #6 [ffff8802244c3e68] worker_thread at ffffffff81073eba
 #7 [ffff8802244c3ec8] kthread at ffffffff810782e0
 #8 [ffff8802244c3f48] kernel_thread_helper at ffffffff81450064
crash> rd ffff8802244c3cc8 10
ffff8802244c3cc8:  ffffffff814472b3 ffff880222f23250   .rD.....P2."....
ffff8802244c3cd8:  0000000000000000 0000000000000286   ................
ffff8802244c3ce8:  ffff8802244c3d30 ffff880220734d80   0=L$.....Ms ....
ffff8802244c3cf8:  ffff880222e8f628 0000000000000000   (.."............
ffff8802244c3d08:  0000000000000000 0000000000000002   ................
crash> struct rt_mutex ffff880222e8f628
struct rt_mutex {
  wait_lock = {
    raw_lock = {
      slock = 65537
    }
  },
  wait_list = {
    node_list = {
      next = 0xffff8802244c3d48,
      prev = 0xffff8802244c3d48
    }
  },
  owner = 0xffff880222f22c71,
  save_state = 0
}
crash> bt 0xffff880222f22c70
PID: 10635  TASK: ffff880222f22c70  CPU: 3   COMMAND: "mount"
 #0 [ffff8802216a9868] schedule at ffffffff8144584b
 #1 [ffff8802216a9910] schedule_timeout at ffffffff81446865
 #2 [ffff8802216a99a0] wait_for_common at ffffffff81445f74
 #3 [ffff8802216a9a30] flush_work at ffffffff810712d3
 #4 [ffff8802216a9ab0] schedule_on_each_cpu at ffffffff81074463
 #5 [ffff8802216a9ae0] invalidate_bdev at ffffffff81178aba
 #6 [ffff8802216a9af0] vfs_load_quota_inode at ffffffff811a3632
 #7 [ffff8802216a9b50] dquot_quota_on_mount at ffffffff811a375c
 #8 [ffff8802216a9b80] finish_unfinished at ffffffffa05dd8b0 [reiserfs]
 #9 [ffff8802216a9cc0] reiserfs_fill_super at ffffffffa05de825 [reiserfs]
    RIP: 00007f7b9303997a  RSP: 00007ffff443c7a8  RFLAGS: 00010202
    RAX: 00000000000000a5  RBX: ffffffff8144ef12  RCX: 00007f7b932e9ee0
    RDX: 00007f7b93d9a400  RSI: 00007f7b93d9a3e0  RDI: 00007f7b93d9a3c0
    RBP: 00007f7b93d9a2c0   R8: 00007f7b93d9a550   R9: 0000000000000001
    R10: ffffffffc0ed040e  R11: 0000000000000202  R12: 000000000000040e
    R13: 0000000000000000  R14: 00000000c0ed040e  R15: 00007ffff443ca20
    ORIG_RAX: 00000000000000a5  CS: 0033  SS: 002b

Signed-off-by: Mike Galbraith <efault@gmx.de>
Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Acked-by: Mike Galbraith <mgalbraith@suse.de>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

Function ib_create_qp() was failing to return an error when
rdma_rw_init_mrs() fails, causing a crash further down in ib_create_qp()
when trying to dereferece the qp pointer which was actually a negative
errno.

The crash:

crash> log|grep BUG
[  136.458121] BUG: unable to handle kernel NULL pointer dereference at 0000000000000098
crash> bt
PID: 3736   TASK: ffff8808543215c0  CPU: 2   COMMAND: "kworker/u64:2"
 #0 [ffff88084d323340] machine_kexec at ffffffff8105fbb0
 tiwai#1 [ffff88084d3233b0] __crash_kexec at ffffffff81116758
 tiwai#2 [ffff88084d323480] crash_kexec at ffffffff8111682d
 tiwai#3 [ffff88084d3234b0] oops_end at ffffffff81032bd6
 tiwai#4 [ffff88084d3234e0] no_context at ffffffff8106e431
 tiwai#5 [ffff88084d323530] __bad_area_nosemaphore at ffffffff8106e610
 tiwai#6 [ffff88084d323590] bad_area_nosemaphore at ffffffff8106e6f4
 tiwai#7 [ffff88084d3235a0] __do_page_fault at ffffffff8106ebdc
 torvalds#8 [ffff88084d323620] do_page_fault at ffffffff8106f057
 torvalds#9 [ffff88084d323660] page_fault at ffffffff816e3148
    [exception RIP: ib_create_qp+427]
    RIP: ffffffffa02554fb  RSP: ffff88084d323718  RFLAGS: 00010246
    RAX: 0000000000000004  RBX: fffffffffffffff4  RCX: 000000018020001f
    RDX: ffff880830997fc0  RSI: 0000000000000001  RDI: ffff88085f407200
    RBP: ffff88084d323778   R8: 0000000000000001   R9: ffffea0020bae210
    R10: ffffea0020bae218  R11: 0000000000000001  R12: ffff88084d3237c8
    R13: 00000000fffffff4  R14: ffff880859fa5000  R15: ffff88082eb89800
    ORIG_RAX: ffffffffffffffff  CS: 0010  SS: 0018
torvalds#10 [ffff88084d323780] rdma_create_qp at ffffffffa0782681 [rdma_cm]
torvalds#11 [ffff88084d3237b0] nvmet_rdma_create_queue_ib at ffffffffa07c43f3 [nvmet_rdma]
torvalds#12 [ffff88084d323860] nvmet_rdma_alloc_queue at ffffffffa07c5ba9 [nvmet_rdma]
torvalds#13 [ffff88084d323900] nvmet_rdma_queue_connect at ffffffffa07c5c96 [nvmet_rdma]
torvalds#14 [ffff88084d323980] nvmet_rdma_cm_handler at ffffffffa07c6450 [nvmet_rdma]
torvalds#15 [ffff88084d3239b0] iw_conn_req_handler at ffffffffa0787480 [rdma_cm]
torvalds#16 [ffff88084d323a60] cm_conn_req_handler at ffffffffa0775f06 [iw_cm]
torvalds#17 [ffff88084d323ab0] process_event at ffffffffa0776019 [iw_cm]
torvalds#18 [ffff88084d323af0] cm_work_handler at ffffffffa0776170 [iw_cm]
torvalds#19 [ffff88084d323cb0] process_one_work at ffffffff810a1483
torvalds#20 [ffff88084d323d90] worker_thread at ffffffff810a211d
torvalds#21 [ffff88084d323ec0] kthread at ffffffff810a6c5c
torvalds#22 [ffff88084d323f50] ret_from_fork at ffffffff816e1ebf

Fixes: 632bc3f ("IB/core, RDMA RW API: Do not exceed QP SGE send limit")
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Cc: stable@vger.kernel.org
Reviewed-by: Bart Van Assche <bart.vanassche@sandisk.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

Currently significant amount of memory is reserved only in kernel booted
to capture kernel dump using the fa_dump method.

Kernels compiled with CONFIG_DEFERRED_STRUCT_PAGE_INIT will initialize
only certain size memory per node.  The certain size takes into account
the dentry and inode cache sizes.  Currently the cache sizes are
calculated based on the total system memory including the reserved
memory.  However such a kernel when booting the same kernel as fadump
kernel will not be able to allocate the required amount of memory to
suffice for the dentry and inode caches.  This results in crashes like

Hence only implement arch_reserved_kernel_pages() for CONFIG_FA_DUMP
configurations.  The amount reserved will be reduced while calculating
the large caches and will avoid crashes like the below on large systems
such as 32 TB systems.

  Dentry cache hash table entries: 536870912 (order: 16, 4294967296 bytes)
  vmalloc: allocation failure, allocated 4097114112 of 17179934720 bytes
  swapper/0: page allocation failure: order:0, mode:0x2080020(GFP_ATOMIC)
  CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.6-master+ tiwai#3
  Call Trace:
     dump_stack+0xb0/0xf0 (unreliable)
     warn_alloc_failed+0x114/0x160
     __vmalloc_node_range+0x304/0x340
     __vmalloc+0x6c/0x90
     alloc_large_system_hash+0x1b8/0x2c0
     inode_init+0x94/0xe4
     vfs_caches_init+0x8c/0x13c
     start_kernel+0x50c/0x578
     start_here_common+0x20/0xa8

Link: http://lkml.kernel.org/r/1472476010-4709-4-git-send-email-srikar@linux.vnet.ibm.com
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Suggested-by: Mel Gorman <mgorman@techsingularity.net>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Cc: Hari Bathini <hbathini@linux.vnet.ibm.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

[ 3843.132217] WARNING: CPU: 20 PID: 1227 at kernel/softirq.c:150 __local_bh_enable_ip+0x6b/0x90
[ 3843.142815] Modules linked in:
...
[ 3843.294328] CPU: 20 PID: 1227 Comm: kworker/20:1H Tainted: G            E   4.8.0-rc1+ tiwai#3
[ 3843.304944] Hardware name: Dell Inc. PowerEdge R720/0X6H47, BIOS 1.4.8 10/25/2012
[ 3843.314798] Workqueue: kblockd blk_timeout_work
[ 3843.321350]  0000000000000086 00000000a32f4533 ffff8802216d7bd8 ffffffff8135c3cf
[ 3843.331146]  0000000000000000 0000000000000000 ffff8802216d7c18 ffffffff8108d661
[ 3843.340918]  00000096216d7c50 0000000000000200 ffff8802d07cc828 ffff8801b3632550
[ 3843.350687] Call Trace:
[ 3843.354866]  [<ffffffff8135c3cf>] dump_stack+0x63/0x84
[ 3843.362061]  [<ffffffff8108d661>] __warn+0xd1/0xf0
[ 3843.368851]  [<ffffffff8108d79d>] warn_slowpath_null+0x1d/0x20
[ 3843.376791]  [<ffffffff810930eb>] __local_bh_enable_ip+0x6b/0x90
[ 3843.384903]  [<ffffffff816fe7be>] _raw_spin_unlock_bh+0x1e/0x20
[ 3843.392940]  [<ffffffffa085f710>] beiscsi_alloc_pdu+0x2f0/0x6e0 [be2iscsi]
[ 3843.402076]  [<ffffffffa06bc358>] __iscsi_conn_send_pdu+0xf8/0x370 [libiscsi]
[ 3843.411549]  [<ffffffffa06bc6fe>] iscsi_send_nopout+0xbe/0x110 [libiscsi]
[ 3843.420639]  [<ffffffffa06bd98b>] iscsi_eh_cmd_timed_out+0x29b/0x2b0 [libiscsi]
[ 3843.430339]  [<ffffffff814cd1de>] scsi_times_out+0x5e/0x250
[ 3843.438119]  [<ffffffff813374af>] blk_rq_timed_out+0x1f/0x60
[ 3843.446009]  [<ffffffff8133759d>] blk_timeout_work+0xad/0x150
[ 3843.454010]  [<ffffffff810a6642>] process_one_work+0x152/0x400
[ 3843.462114]  [<ffffffff810a6f35>] worker_thread+0x125/0x4b0
[ 3843.469961]  [<ffffffff810a6e10>] ? rescuer_thread+0x380/0x380
[ 3843.478116]  [<ffffffff810aca28>] kthread+0xd8/0xf0
[ 3843.485212]  [<ffffffff816fedff>] ret_from_fork+0x1f/0x40
[ 3843.492908]  [<ffffffff810ac950>] ? kthread_park+0x60/0x60
[ 3843.500715] ---[ end trace 57ec0a1d8f0dd3a0 ]---
[ 3852.328667] NMI watchdog: Watchdog detected hard LOCKUP on cpu 1Kernel panic - not syncing: Hard LOCKUP

blk_timeout_work takes queue_lock spin_lock with interrupts disabled
before invoking iscsi_eh_cmd_timed_out. This causes a WARN_ON_ONCE in
spin_unlock_bh for wrb_lock/io_sgl_lock/mgmt_sgl_lock.

CPU was kept busy in lot of bottom half work with interrupts disabled
thus causing hard lock up.

Signed-off-by: Jitendra Bhivare <jitendra.bhivare@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Chris Leech <cleech@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

commit b6bc1c7 upstream.

Function ib_create_qp() was failing to return an error when
rdma_rw_init_mrs() fails, causing a crash further down in ib_create_qp()
when trying to dereferece the qp pointer which was actually a negative
errno.

The crash:

crash> log|grep BUG
[  136.458121] BUG: unable to handle kernel NULL pointer dereference at 0000000000000098
crash> bt
PID: 3736   TASK: ffff8808543215c0  CPU: 2   COMMAND: "kworker/u64:2"
 #0 [ffff88084d323340] machine_kexec at ffffffff8105fbb0
 #1 [ffff88084d3233b0] __crash_kexec at ffffffff81116758
 #2 [ffff88084d323480] crash_kexec at ffffffff8111682d
 #3 [ffff88084d3234b0] oops_end at ffffffff81032bd6
 #4 [ffff88084d3234e0] no_context at ffffffff8106e431
 #5 [ffff88084d323530] __bad_area_nosemaphore at ffffffff8106e610
 #6 [ffff88084d323590] bad_area_nosemaphore at ffffffff8106e6f4
 #7 [ffff88084d3235a0] __do_page_fault at ffffffff8106ebdc
 #8 [ffff88084d323620] do_page_fault at ffffffff8106f057
 #9 [ffff88084d323660] page_fault at ffffffff816e3148
    [exception RIP: ib_create_qp+427]
    RIP: ffffffffa02554fb  RSP: ffff88084d323718  RFLAGS: 00010246
    RAX: 0000000000000004  RBX: fffffffffffffff4  RCX: 000000018020001f
    RDX: ffff880830997fc0  RSI: 0000000000000001  RDI: ffff88085f407200
    RBP: ffff88084d323778   R8: 0000000000000001   R9: ffffea0020bae210
    R10: ffffea0020bae218  R11: 0000000000000001  R12: ffff88084d3237c8
    R13: 00000000fffffff4  R14: ffff880859fa5000  R15: ffff88082eb89800
    ORIG_RAX: ffffffffffffffff  CS: 0010  SS: 0018
#10 [ffff88084d323780] rdma_create_qp at ffffffffa0782681 [rdma_cm]
#11 [ffff88084d3237b0] nvmet_rdma_create_queue_ib at ffffffffa07c43f3 [nvmet_rdma]
#12 [ffff88084d323860] nvmet_rdma_alloc_queue at ffffffffa07c5ba9 [nvmet_rdma]
#13 [ffff88084d323900] nvmet_rdma_queue_connect at ffffffffa07c5c96 [nvmet_rdma]
#14 [ffff88084d323980] nvmet_rdma_cm_handler at ffffffffa07c6450 [nvmet_rdma]
#15 [ffff88084d3239b0] iw_conn_req_handler at ffffffffa0787480 [rdma_cm]
#16 [ffff88084d323a60] cm_conn_req_handler at ffffffffa0775f06 [iw_cm]
#17 [ffff88084d323ab0] process_event at ffffffffa0776019 [iw_cm]
#18 [ffff88084d323af0] cm_work_handler at ffffffffa0776170 [iw_cm]
#19 [ffff88084d323cb0] process_one_work at ffffffff810a1483
#20 [ffff88084d323d90] worker_thread at ffffffff810a211d
#21 [ffff88084d323ec0] kthread at ffffffff810a6c5c
#22 [ffff88084d323f50] ret_from_fork at ffffffff816e1ebf

Fixes: 632bc3f ("IB/core, RDMA RW API: Do not exceed QP SGE send limit")
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Reviewed-by: Bart Van Assche <bart.vanassche@sandisk.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

We shouldn't free cert->pub->key in x509_cert_parse() because
x509_free_certificate() also does this:
	BUG: Double free or freeing an invalid pointer
	...
	Call Trace:
	 [<ffffffff81896c20>] dump_stack+0x63/0x83
	 [<ffffffff81356571>] kasan_object_err+0x21/0x70
	 [<ffffffff81356ed9>] kasan_report_double_free+0x49/0x60
	 [<ffffffff813561ad>] kasan_slab_free+0x9d/0xc0
	 [<ffffffff81350b7a>] kfree+0x8a/0x1a0
	 [<ffffffff81844fbf>] public_key_free+0x1f/0x30
	 [<ffffffff818455d4>] x509_free_certificate+0x24/0x90
	 [<ffffffff818460bc>] x509_cert_parse+0x2bc/0x300
	 [<ffffffff81846cae>] x509_key_preparse+0x3e/0x330
	 [<ffffffff818444cf>] asymmetric_key_preparse+0x6f/0x100
	 [<ffffffff8178bec0>] key_create_or_update+0x260/0x5f0
	 [<ffffffff8178e6d9>] SyS_add_key+0x199/0x2a0
	 [<ffffffff821d823b>] entry_SYSCALL_64_fastpath+0x1e/0xad
	Object at ffff880110bd1900, in cache kmalloc-512 size: 512
	....
	Freed:
	PID = 2579
	[<ffffffff8104283b>] save_stack_trace+0x1b/0x20
	[<ffffffff813558f6>] save_stack+0x46/0xd0
	[<ffffffff81356183>] kasan_slab_free+0x73/0xc0
	[<ffffffff81350b7a>] kfree+0x8a/0x1a0
	[<ffffffff818460a3>] x509_cert_parse+0x2a3/0x300
	[<ffffffff81846cae>] x509_key_preparse+0x3e/0x330
	[<ffffffff818444cf>] asymmetric_key_preparse+0x6f/0x100
	[<ffffffff8178bec0>] key_create_or_update+0x260/0x5f0
	[<ffffffff8178e6d9>] SyS_add_key+0x199/0x2a0
	[<ffffffff821d823b>] entry_SYSCALL_64_fastpath+0x1e/0xad

Fixes: db6c43b ("crypto: KEYS: convert public key and digsig asym to the akcipher api")
Signed-off-by: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: James Morris <james.l.morris@oracle.com>

This fixes CVE-2016-8650.

If mpi_powm() is given a zero exponent, it wants to immediately return
either 1 or 0, depending on the modulus.  However, if the result was
initalised with zero limb space, no limbs space is allocated and a
NULL-pointer exception ensues.

Fix this by allocating a minimal amount of limb space for the result when
the 0-exponent case when the result is 1 and not touching the limb space
when the result is 0.

This affects the use of RSA keys and X.509 certificates that carry them.

BUG: unable to handle kernel NULL pointer dereference at           (null)
IP: [<ffffffff8138ce5d>] mpi_powm+0x32/0x7e6
PGD 0
Oops: 0002 [#1] SMP
Modules linked in:
CPU: 3 PID: 3014 Comm: keyctl Not tainted 4.9.0-rc6-fscache+ torvalds#278
Hardware name: ASUS All Series/H97-PLUS, BIOS 2306 10/09/2014
task: ffff8804011944c0 task.stack: ffff880401294000
RIP: 0010:[<ffffffff8138ce5d>]  [<ffffffff8138ce5d>] mpi_powm+0x32/0x7e6
RSP: 0018:ffff880401297ad8  EFLAGS: 00010212
RAX: 0000000000000000 RBX: ffff88040868bec0 RCX: ffff88040868bba0
RDX: ffff88040868b260 RSI: ffff88040868bec0 RDI: ffff88040868bee0
RBP: ffff880401297ba8 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000047 R11: ffffffff8183b210 R12: 0000000000000000
R13: ffff8804087c7600 R14: 000000000000001f R15: ffff880401297c50
FS:  00007f7a7918c700(0000) GS:ffff88041fb80000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000000000 CR3: 0000000401250000 CR4: 00000000001406e0
Stack:
 ffff88040868bec0 0000000000000020 ffff880401297b00 ffffffff81376cd4
 0000000000000100 ffff880401297b10 ffffffff81376d12 ffff880401297b30
 ffffffff81376f37 0000000000000100 0000000000000000 ffff880401297ba8
Call Trace:
 [<ffffffff81376cd4>] ? __sg_page_iter_next+0x43/0x66
 [<ffffffff81376d12>] ? sg_miter_get_next_page+0x1b/0x5d
 [<ffffffff81376f37>] ? sg_miter_next+0x17/0xbd
 [<ffffffff8138ba3a>] ? mpi_read_raw_from_sgl+0xf2/0x146
 [<ffffffff8132a95c>] rsa_verify+0x9d/0xee
 [<ffffffff8132acca>] ? pkcs1pad_sg_set_buf+0x2e/0xbb
 [<ffffffff8132af40>] pkcs1pad_verify+0xc0/0xe1
 [<ffffffff8133cb5e>] public_key_verify_signature+0x1b0/0x228
 [<ffffffff8133d974>] x509_check_for_self_signed+0xa1/0xc4
 [<ffffffff8133cdde>] x509_cert_parse+0x167/0x1a1
 [<ffffffff8133d609>] x509_key_preparse+0x21/0x1a1
 [<ffffffff8133c3d7>] asymmetric_key_preparse+0x34/0x61
 [<ffffffff812fc9f3>] key_create_or_update+0x145/0x399
 [<ffffffff812fe227>] SyS_add_key+0x154/0x19e
 [<ffffffff81001c2b>] do_syscall_64+0x80/0x191
 [<ffffffff816825e4>] entry_SYSCALL64_slow_path+0x25/0x25
Code: 56 41 55 41 54 53 48 81 ec a8 00 00 00 44 8b 71 04 8b 42 04 4c 8b 67 18 45 85 f6 89 45 80 0f 84 b4 06 00 00 85 c0 75 2f 41 ff ce <49> c7 04 24 01 00 00 00 b0 01 75 0b 48 8b 41 18 48 83 38 01 0f
RIP  [<ffffffff8138ce5d>] mpi_powm+0x32/0x7e6
 RSP <ffff880401297ad8>
CR2: 0000000000000000
---[ end trace d82015255d4a5d8d ]---

Basically, this is a backport of a libgcrypt patch:

	http://git.gnupg.org/cgi-bin/gitweb.cgi?p=libgcrypt.git;a=patch;h=6e1adb05d290aeeb1c230c763970695f4a538526

Fixes: cdec9cb ("crypto: GnuPG based MPI lib - source files (part 1)")
Signed-off-by: Andrey Ryabinin <aryabinin@virtuozzo.com>
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Dmitry Kasatkin <dmitry.kasatkin@gmail.com>
cc: linux-ima-devel@lists.sourceforge.net
cc: stable@vger.kernel.org
Signed-off-by: James Morris <james.l.morris@oracle.com>

…/git/jmorris/linux-security

Pull keys fixes from James Morris:
 "From David:

   - Fix mpi_powm()'s handling of a number with a zero exponent
     [CVE-2016-8650].

     Integrate my and Andrey's patches for mpi_powm() and use
     mpi_resize() instead of RESIZE_IF_NEEDED() - the latter adds a
     duplicate check into the execution path of a trivial case we
     don't normally expect to be taken.

   - Fix double free in X.509 error handling"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/linux-security:
  mpi: Fix NULL ptr dereference in mpi_powm() [ver #3]
  X.509: Fix double free in x509_cert_parse() [ver #3]

Guillaume Nault says:

====================
l2tp: fixes for l2tp_ip and l2tp_ip6 socket handling

This series addresses problems found while working on commit 32c2311
("l2tp: fix racy SOCK_ZAPPED flag check in l2tp_ip{,6}_bind()").

The first three patches fix races in socket's connect, recv and bind
operations. The last two ones fix scenarios where l2tp fails to
correctly lookup its userspace sockets.

Apart from the last patch, which is l2tp_ip6 specific, every patch
fixes the same problem in the L2TP IPv4 and IPv6 code.

All problems fixed by this series exist since the creation of the
l2tp_ip and l2tp_ip6 modules.

Changes since v1:
  * Patch #3: fix possible uninitialised use of 'ret' in l2tp_ip_bind().
====================

Acked-by: James Chapman <jchapman@katalix.com>

Since commit:

  4bcc595 ("printk: reinstate KERN_CONT for printing continuation lines")

printk() requires KERN_CONT to continue log messages. Lots of printk()
in lockdep.c and print_ip_sym() don't have it. As the result lockdep
reports are completely messed up.

Add missing KERN_CONT and inline print_ip_sym() where necessary.

Example of a messed up report:

  0-rc5+ torvalds#41 Not tainted
  -------------------------------------------------------
  syz-executor0/5036 is trying to acquire lock:
   (
  rtnl_mutex
  ){+.+.+.}
  , at:
  [<ffffffff86b3d6ac>] rtnl_lock+0x1c/0x20
  but task is already holding lock:
   (
  &net->packet.sklist_lock
  ){+.+...}
  , at:
  [<ffffffff873541a6>] packet_diag_dump+0x1a6/0x1920
  which lock already depends on the new lock.
  the existing dependency chain (in reverse order) is:
  -> #3
   (
  &net->packet.sklist_lock
  +.+...}
  ...

Without this patch all scripts that parse kernel bug reports are broken.

Signed-off-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: andreyknvl@google.com
Cc: aryabinin@virtuozzo.com
Cc: joe@perches.com
Cc: syzkaller@googlegroups.com
Link: http://lkml.kernel.org/r/1480343083-48731-1-git-send-email-dvyukov@google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

In blk_mq_map_swqueue, there is a memory optimization that frees the
tags of a queue that has gone unmapped.  Later, if that hctx is remapped
after another topology change, the tags need to be reallocated.

If this allocation fails, a simple WARN_ON triggers, but the block layer
ends up with an active hctx without any corresponding set of tags.
Then, any income IO to that hctx can trigger an Oops.

I can reproduce it consistently by running IO, flipping CPUs on and off
and eventually injecting a memory allocation failure in that path.

In the fix below, if the system experiences a failed allocation of any
hctx's tags, we remap all the ctxs of that queue to the hctx_0, which
should always keep it's tags.  There is a minor performance hit, since
our mapping just got worse after the error path, but this is
the simplest solution to handle this error path.  The performance hit
will disappear after another successful remap.

I considered dropping the memory optimization all together, but it
seemed a bad trade-off to handle this very specific error case.

This should apply cleanly on top of Jens' for-next branch.

The Oops is the one below:

SP (3fff935ce4d0) is in userspace
1:mon> e
cpu 0x1: Vector: 300 (Data Access) at [c000000fe99eb110]
    pc: c0000000005e868c: __sbitmap_queue_get+0x2c/0x180
    lr: c000000000575328: __bt_get+0x48/0xd0
    sp: c000000fe99eb390
   msr: 900000010280b033
   dar: 28
 dsisr: 40000000
  current = 0xc000000fe9966800
  paca    = 0xc000000007e80300   softe: 0        irq_happened: 0x01
    pid   = 11035, comm = aio-stress
Linux version 4.8.0-rc6+ (root@bean) (gcc version 5.4.0 20160609
(Ubuntu/IBM 5.4.0-6ubuntu1~16.04.2) ) #3 SMP Mon Oct 10 20:16:53 CDT 2016
1:mon> s
[c000000fe99eb3d0] c000000000575328 __bt_get+0x48/0xd0
[c000000fe99eb400] c000000000575838 bt_get.isra.1+0x78/0x2d0
[c000000fe99eb480] c000000000575cb4 blk_mq_get_tag+0x44/0x100
[c000000fe99eb4b0] c00000000056f6f4 __blk_mq_alloc_request+0x44/0x220
[c000000fe99eb500] c000000000570050 blk_mq_map_request+0x100/0x1f0
[c000000fe99eb580] c000000000574650 blk_mq_make_request+0xf0/0x540
[c000000fe99eb640] c000000000561c44 generic_make_request+0x144/0x230
[c000000fe99eb690] c000000000561e00 submit_bio+0xd0/0x200
[c000000fe99eb740] c0000000003ef740 ext4_io_submit+0x90/0xb0
[c000000fe99eb770] c0000000003e95d8 ext4_writepages+0x588/0xdd0
[c000000fe99eb910] c00000000025a9f0 do_writepages+0x60/0xc0
[c000000fe99eb940] c000000000246c88 __filemap_fdatawrite_range+0xf8/0x180
[c000000fe99eb9e0] c000000000246f90 filemap_write_and_wait_range+0x70/0xf0
[c000000fe99eba20] c0000000003dd844 ext4_sync_file+0x214/0x540
[c000000fe99eba80] c000000000364718 vfs_fsync_range+0x78/0x130
[c000000fe99ebad0] c0000000003dd46c ext4_file_write_iter+0x35c/0x430
[c000000fe99ebb90] c00000000038c280 aio_run_iocb+0x3b0/0x450
[c000000fe99ebce0] c00000000038dc28 do_io_submit+0x368/0x730
[c000000fe99ebe30] c000000000009404 system_call+0x38/0xec

Signed-off-by: Gabriel Krisman Bertazi <krisman@linux.vnet.ibm.com>
Cc: Brian King <brking@linux.vnet.ibm.com>
Cc: Douglas Miller <dougmill@linux.vnet.ibm.com>
Cc: linux-block@vger.kernel.org
Cc: linux-scsi@vger.kernel.org
Reviewed-by: Douglas Miller <dougmill@linux.vnet.ibm.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

Several people report seeing warnings about inconsistent radix tree
nodes followed by crashes in the workingset code, which all looked like
use-after-free access from the shadow node shrinker.

Dave Jones managed to reproduce the issue with a debug patch applied,
which confirmed that the radix tree shrinking indeed frees shadow nodes
while they are still linked to the shadow LRU:

  WARNING: CPU: 2 PID: 53 at lib/radix-tree.c:643 delete_node+0x1e4/0x200
  CPU: 2 PID: 53 Comm: kswapd0 Not tainted 4.10.0-rc2-think+ #3
  Call Trace:
     delete_node+0x1e4/0x200
     __radix_tree_delete_node+0xd/0x10
     shadow_lru_isolate+0xe6/0x220
     __list_lru_walk_one.isra.4+0x9b/0x190
     list_lru_walk_one+0x23/0x30
     scan_shadow_nodes+0x2e/0x40
     shrink_slab.part.44+0x23d/0x5d0
     shrink_node+0x22c/0x330
     kswapd+0x392/0x8f0

This is the WARN_ON_ONCE(!list_empty(&node->private_list)) placed in the
inlined radix_tree_shrink().

The problem is with 14b4687 ("mm: workingset: move shadow entry
tracking to radix tree exceptional tracking"), which passes an update
callback into the radix tree to link and unlink shadow leaf nodes when
tree entries change, but forgot to pass the callback when reclaiming a
shadow node.

While the reclaimed shadow node itself is unlinked by the shrinker, its
deletion from the tree can cause the left-most leaf node in the tree to
be shrunk.  If that happens to be a shadow node as well, we don't unlink
it from the LRU as we should.

Consider this tree, where the s are shadow entries:

       root->rnode
            |
       [0       n]
        |       |
     [s    ] [sssss]

Now the shadow node shrinker reclaims the rightmost leaf node through
the shadow node LRU:

       root->rnode
            |
       [0        ]
        |
    [s     ]

Because the parent of the deleted node is the first level below the
root and has only one child in the left-most slot, the intermediate
level is shrunk and the node containing the single shadow is put in
its place:

       root->rnode
            |
       [s        ]

The shrinker again sees a single left-most slot in a first level node
and thus decides to store the shadow in root->rnode directly and free
the node - which is a leaf node on the shadow node LRU.

  root->rnode
       |
       s

Without the update callback, the freed node remains on the shadow LRU,
where it causes later shrinker runs to crash.

Pass the node updater callback into __radix_tree_delete_node() in case
the deletion causes the left-most branch in the tree to collapse too.

Also add warnings when linked nodes are freed right away, rather than
wait for the use-after-free when the list is scanned much later.

Fixes: 14b4687 ("mm: workingset: move shadow entry tracking to radix tree exceptional tracking")
Reported-by: Dave Chinner <david@fromorbit.com>
Reported-by: Hugh Dickins <hughd@google.com>
Reported-by: Andrea Arcangeli <aarcange@redhat.com>
Reported-and-tested-by: Dave Jones <davej@codemonkey.org.uk>
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Chris Leech <cleech@redhat.com>
Cc: Lee Duncan <lduncan@suse.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Matthew Wilcox <mawilcox@linuxonhyperv.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Reported by syzkaller:

    BUG: unable to handle kernel NULL pointer dereference at 00000000000001b0
    IP: _raw_spin_lock+0xc/0x30
    PGD 3e28eb067
    PUD 3f0ac6067
    PMD 0
    Oops: 0002 [#1] SMP
    CPU: 0 PID: 2431 Comm: test Tainted: G           OE   4.10.0-rc1+ #3
    Call Trace:
     ? kvm_ioapic_scan_entry+0x3e/0x110 [kvm]
     kvm_arch_vcpu_ioctl_run+0x10a8/0x15f0 [kvm]
     ? pick_next_task_fair+0xe1/0x4e0
     ? kvm_arch_vcpu_load+0xea/0x260 [kvm]
     kvm_vcpu_ioctl+0x33a/0x600 [kvm]
     ? hrtimer_try_to_cancel+0x29/0x130
     ? do_nanosleep+0x97/0xf0
     do_vfs_ioctl+0xa1/0x5d0
     ? __hrtimer_init+0x90/0x90
     ? do_nanosleep+0x5b/0xf0
     SyS_ioctl+0x79/0x90
     do_syscall_64+0x6e/0x180
     entry_SYSCALL64_slow_path+0x25/0x25
    RIP: _raw_spin_lock+0xc/0x30 RSP: ffffa43688973cc0

The syzkaller folks reported a NULL pointer dereference due to
ENABLE_CAP succeeding even without an irqchip.  The Hyper-V
synthetic interrupt controller is activated, resulting in a
wrong request to rescan the ioapic and a NULL pointer dereference.

    #include <sys/ioctl.h>
    #include <sys/mman.h>
    #include <sys/types.h>
    #include <linux/kvm.h>
    #include <pthread.h>
    #include <stddef.h>
    #include <stdint.h>
    #include <stdlib.h>
    #include <string.h>
    #include <unistd.h>

    #ifndef KVM_CAP_HYPERV_SYNIC
    #define KVM_CAP_HYPERV_SYNIC 123
    #endif

    void* thr(void* arg)
    {
	struct kvm_enable_cap cap;
	cap.flags = 0;
	cap.cap = KVM_CAP_HYPERV_SYNIC;
	ioctl((long)arg, KVM_ENABLE_CAP, &cap);
	return 0;
    }

    int main()
    {
	void *host_mem = mmap(0, 0x1000, PROT_READ|PROT_WRITE,
			MAP_PRIVATE|MAP_ANONYMOUS, -1, 0);
	int kvmfd = open("/dev/kvm", 0);
	int vmfd = ioctl(kvmfd, KVM_CREATE_VM, 0);
	struct kvm_userspace_memory_region memreg;
	memreg.slot = 0;
	memreg.flags = 0;
	memreg.guest_phys_addr = 0;
	memreg.memory_size = 0x1000;
	memreg.userspace_addr = (unsigned long)host_mem;
	host_mem[0] = 0xf4;
	ioctl(vmfd, KVM_SET_USER_MEMORY_REGION, &memreg);
	int cpufd = ioctl(vmfd, KVM_CREATE_VCPU, 0);
	struct kvm_sregs sregs;
	ioctl(cpufd, KVM_GET_SREGS, &sregs);
	sregs.cr0 = 0;
	sregs.cr4 = 0;
	sregs.efer = 0;
	sregs.cs.selector = 0;
	sregs.cs.base = 0;
	ioctl(cpufd, KVM_SET_SREGS, &sregs);
	struct kvm_regs regs = { .rflags = 2 };
	ioctl(cpufd, KVM_SET_REGS, &regs);
	ioctl(vmfd, KVM_CREATE_IRQCHIP, 0);
	pthread_t th;
	pthread_create(&th, 0, thr, (void*)(long)cpufd);
	usleep(rand() % 10000);
	ioctl(cpufd, KVM_RUN, 0);
	pthread_join(th, 0);
	return 0;
    }

This patch fixes it by failing ENABLE_CAP if without an irqchip.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Fixes: 5c91941 (kvm/x86: Hyper-V synthetic interrupt controller)
Cc: stable@vger.kernel.org # 4.5+
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Hayes Wang says:

====================
r8152: fix scheduling napi

v3:
simply the argument for patch #3. Replace &tp->napi with napi.

v2:
Add smp_mb__after_atomic() for patch #1.

v1:
Scheduling the napi during the following periods would let it be ignored.
And the events wouldn't be handled until next napi_schedule() is called.

1. after napi_disable and before napi_enable().
2. after all actions of napi function is completed and before calling
   napi_complete().

If no next napi_schedule() is called, tx or rx would stop working.

In order to avoid these situations, the followings solutions are applied.

1. prevent start_xmit() from calling napi_schedule() during runtime suspend
   or after napi_disable().
2. re-schedule the napi for tx if it is necessary.
3. check if any rx is finished or not after napi_enable().
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

This patch reverts commit f80de88 and avoids that sending a
WRITE SAME command to the iSCSI initiator triggers the following:

BUG: unable to handle kernel NULL pointer dereference at 0000000000000014
TARGET_CORE[iSCSI]: Expected Transfer Length: 260096 does not match SCSI CDB Length: 512 for SAM Opcode: 0x41
IP: iscsi_tcp_segment_done+0x20b/0x310 [libiscsi_tcp]

Oops: 0000 [#1] SMP
Modules linked in: target_core_user uio target_core_iblock target_core_file iscsi_target_mod target_core_mod netconsole configfs crct10dif_pclmul crc32_pclmul ghash_clmulni_intel aesni_intel aes_x86_64 crypto_simd cryptd glue_helper virtio_console virtio_rng virtio_balloon serio_raw i2c_piix4 acpi_cpufreq button iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi ext4 jbd2 mbcache virtio_blk virtio_net psmouse floppy drm_kms_helper syscopyarea
sysfillrect sysimgblt fb_sys_fops ttm drm virtio_pci
CPU: 2 PID: 5 Comm: kworker/u8:0 Not tainted 4.10.0-rc5-debug+ #3
Workqueue: iscsi_q_0 iscsi_xmitworker [libiscsi]
RIP: 0010:iscsi_tcp_segment_done+0x20b/0x310 [libiscsi_tcp]
Call Trace:
 iscsi_sw_tcp_xmit_segment+0x84/0x120 [iscsi_tcp]
 iscsi_sw_tcp_pdu_xmit+0x51/0x180 [iscsi_tcp]
 iscsi_tcp_task_xmit+0xb3/0x290 [libiscsi_tcp]
 iscsi_xmit_task+0x4e/0xc0 [libiscsi]
 iscsi_xmitworker+0x243/0x330 [libiscsi]
 process_one_work+0x1d8/0x4b0
 worker_thread+0x49/0x4a0
 kthread+0x102/0x140

Fixes: f80de88 ("sd: remove __data_len hack for WRITE SAME")
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Sagi Grimberg <sagi@grimberg.me>
Cc: Jens Axboe <axboe@fb.com>
Cc: Lee Duncan <lduncan@suse.com>
Cc: Chris Leech <cleech@redhat.com>
Acked-by: Christoph Hellwig <hch@lst.de>
Acked-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

When we look for microcode blobs, we first try builtin and if that
doesn't succeed, we fallback to the initrd supplied to the kernel.

However, at some point doing boot, that initrd gets jettisoned and we
shouldn't access it anymore. But we do, as the below KASAN report shows.
That's because find_microcode_in_initrd() doesn't check whether the
initrd is still valid or not.

So do that.

  ==================================================================
  BUG: KASAN: use-after-free in find_cpio_data
  Read of size 1 by task swapper/1/0
  page:ffffea0000db9d40 count:0 mapcount:0 mapping:          (null) index:0x1
  flags: 0x100000000000000()
  raw: 0100000000000000 0000000000000000 0000000000000001 00000000ffffffff
  raw: dead000000000100 dead000000000200 0000000000000000 0000000000000000
  page dumped because: kasan: bad access detected
  CPU: 1 PID: 0 Comm: swapper/1 Tainted: G        W       4.10.0-rc5-debug-00075-g2dbde22 #3
  Hardware name: Dell Inc. XPS 13 9360/0839Y6, BIOS 1.2.3 12/01/2016
  Call Trace:
   dump_stack
   ? _atomic_dec_and_lock
   ? __dump_page
   kasan_report_error
   ? pointer
   ? find_cpio_data
   __asan_report_load1_noabort
   ? find_cpio_data
   find_cpio_data
   ? vsprintf
   ? dump_stack
   ? get_ucode_user
   ? print_usage_bug
   find_microcode_in_initrd
   __load_ucode_intel
   ? collect_cpu_info_early
   ? debug_check_no_locks_freed
   load_ucode_intel_ap
   ? collect_cpu_info
   ? trace_hardirqs_on
   ? flat_send_IPI_mask_allbutself
   load_ucode_ap
   ? get_builtin_firmware
   ? flush_tlb_func
   ? do_raw_spin_trylock
   ? cpumask_weight
   cpu_init
   ? trace_hardirqs_off
   ? play_dead_common
   ? native_play_dead
   ? hlt_play_dead
   ? syscall_init
   ? arch_cpu_idle_dead
   ? do_idle
   start_secondary
   start_cpu
  Memory state around the buggy address:
   ffff880036e74f00: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
   ffff880036e74f80: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
  >ffff880036e75000: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
                     ^
   ffff880036e75080: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
   ffff880036e75100: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
  ==================================================================

Reported-by: Andrey Ryabinin <aryabinin@virtuozzo.com>
Tested-by: Andrey Ryabinin <aryabinin@virtuozzo.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20170126165833.evjemhbqzaepirxo@pd.tnic
Signed-off-by: Ingo Molnar <mingo@kernel.org>

The Amlogic Meson GXBB/GXL/GXM secure monitor uses part of the memory space,
this patch adds these reserved zones.

Without such reserved memory zones, running the following stress command :
$ stress-ng --vm 16 --vm-bytes 128M --timeout 10s
multiple times:

Could lead to the following kernel crashes :
[   46.937975] Bad mode in Error handler detected on CPU1, code 0xbf000000 -- SError
...
[   47.058536] Internal error: Attempting to execute userspace memory: 8600000f [#3] PREEMPT SMP
...
Instead of the OOM killer.

Fixes: 4f24eda ("ARM64: dts: Prepare configs for Amlogic Meson GXBaby")
Signed-off-by: Neil Armstrong <narmstrong@baylibre.com>
Reviewed-by: Andreas Färber <afaerber@suse.de>
[khilman: added Fixes tag, added _reserved and unit addresses]
Signed-off-by: Kevin Hilman <khilman@baylibre.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>

Olof reported that on a machine which has a BIOS wreckaged TSC the
timestamps in dmesg are making a large jump because the TSC value is
jumping forward after resetting the TSC ADJUST register to a sane value.

This can be avoided by calling the TSC ADJUST saniziting function before
initializing the per cpu sched clock machinery. That takes the offset into
account and avoid the time jump.

What cannot be avoided is that the 'Firmware Bug' warnings on the secondary
CPUs are printed with the large time offsets because it would be too much
effort and ugly hackery to print those warnings into a buffer and emit them
after the adjustemt on the starting CPUs. It's a firmware bug and should be
fixed in firmware. The weird timestamps are collateral damage and just
illustrate the sillyness of the BIOS folks:

[    0.397445] smp: Bringing up secondary CPUs ...
[    0.402100] x86: Booting SMP configuration:
[    0.406343] .... node  #0, CPUs:      #1
[1265776479.930667] [Firmware Bug]: TSC ADJUST differs: Reference CPU0: -2978888639075328 CPU1: -2978888639183101
[1265776479.944664] TSC ADJUST synchronize: Reference CPU0: 0 CPU1: -2978888639183101
[    0.508119]  #2
[1265776480.032346] [Firmware Bug]: TSC ADJUST differs: Reference CPU0: -2978888639075328 CPU2: -2978888639183677
[1265776480.044192] TSC ADJUST synchronize: Reference CPU0: 0 CPU2: -2978888639183677
[    0.607643]  #3
[1265776480.131874] [Firmware Bug]: TSC ADJUST differs: Reference CPU0: -2978888639075328 CPU3: -2978888639184530
[1265776480.143720] TSC ADJUST synchronize: Reference CPU0: 0 CPU3: -2978888639184530
[    0.707108] smp: Brought up 1 node, 4 CPUs
[    0.711271] smpboot: Total of 4 processors activated (21698.88 BogoMIPS)

Reported-by: Olof Johansson <olof@lixom.net>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20170209151231.411460506@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

We cannot do printk() from tk_debug_account_sleep_time(), because
tk_debug_account_sleep_time() is called under tk_core seq lock.
The reason why printk() is unsafe there is that console_sem may
invoke scheduler (up()->wake_up_process()->activate_task()), which,
in turn, can return back to timekeeping code, for instance, via
get_time()->ktime_get(), deadlocking the system on tk_core seq lock.

[   48.950592] ======================================================
[   48.950622] [ INFO: possible circular locking dependency detected ]
[   48.950622] 4.10.0-rc7-next-20170213+ torvalds#101 Not tainted
[   48.950622] -------------------------------------------------------
[   48.950622] kworker/0:0/3 is trying to acquire lock:
[   48.950653]  (tk_core){----..}, at: [<c01cc624>] retrigger_next_event+0x4c/0x90
[   48.950683]
               but task is already holding lock:
[   48.950683]  (hrtimer_bases.lock){-.-...}, at: [<c01cc610>] retrigger_next_event+0x38/0x90
[   48.950714]
               which lock already depends on the new lock.

[   48.950714]
               the existing dependency chain (in reverse order) is:
[   48.950714]
               -> #5 (hrtimer_bases.lock){-.-...}:
[   48.950744]        _raw_spin_lock_irqsave+0x50/0x64
[   48.950775]        lock_hrtimer_base+0x28/0x58
[   48.950775]        hrtimer_start_range_ns+0x20/0x5c8
[   48.950775]        __enqueue_rt_entity+0x320/0x360
[   48.950805]        enqueue_rt_entity+0x2c/0x44
[   48.950805]        enqueue_task_rt+0x24/0x94
[   48.950836]        ttwu_do_activate+0x54/0xc0
[   48.950836]        try_to_wake_up+0x248/0x5c8
[   48.950836]        __setup_irq+0x420/0x5f0
[   48.950836]        request_threaded_irq+0xdc/0x184
[   48.950866]        devm_request_threaded_irq+0x58/0xa4
[   48.950866]        omap_i2c_probe+0x530/0x6a0
[   48.950897]        platform_drv_probe+0x50/0xb0
[   48.950897]        driver_probe_device+0x1f8/0x2cc
[   48.950897]        __driver_attach+0xc0/0xc4
[   48.950927]        bus_for_each_dev+0x6c/0xa0
[   48.950927]        bus_add_driver+0x100/0x210
[   48.950927]        driver_register+0x78/0xf4
[   48.950958]        do_one_initcall+0x3c/0x16c
[   48.950958]        kernel_init_freeable+0x20c/0x2d8
[   48.950958]        kernel_init+0x8/0x110
[   48.950988]        ret_from_fork+0x14/0x24
[   48.950988]
               -> #4 (&rt_b->rt_runtime_lock){-.-...}:
[   48.951019]        _raw_spin_lock+0x40/0x50
[   48.951019]        rq_offline_rt+0x9c/0x2bc
[   48.951019]        set_rq_offline.part.2+0x2c/0x58
[   48.951049]        rq_attach_root+0x134/0x144
[   48.951049]        cpu_attach_domain+0x18c/0x6f4
[   48.951049]        build_sched_domains+0xba4/0xd80
[   48.951080]        sched_init_smp+0x68/0x10c
[   48.951080]        kernel_init_freeable+0x160/0x2d8
[   48.951080]        kernel_init+0x8/0x110
[   48.951080]        ret_from_fork+0x14/0x24
[   48.951110]
               -> #3 (&rq->lock){-.-.-.}:
[   48.951110]        _raw_spin_lock+0x40/0x50
[   48.951141]        task_fork_fair+0x30/0x124
[   48.951141]        sched_fork+0x194/0x2e0
[   48.951141]        copy_process.part.5+0x448/0x1a20
[   48.951171]        _do_fork+0x98/0x7e8
[   48.951171]        kernel_thread+0x2c/0x34
[   48.951171]        rest_init+0x1c/0x18c
[   48.951202]        start_kernel+0x35c/0x3d4
[   48.951202]        0x8000807c
[   48.951202]
               -> #2 (&p->pi_lock){-.-.-.}:
[   48.951232]        _raw_spin_lock_irqsave+0x50/0x64
[   48.951232]        try_to_wake_up+0x30/0x5c8
[   48.951232]        up+0x4c/0x60
[   48.951263]        __up_console_sem+0x2c/0x58
[   48.951263]        console_unlock+0x3b4/0x650
[   48.951263]        vprintk_emit+0x270/0x474
[   48.951293]        vprintk_default+0x20/0x28
[   48.951293]        printk+0x20/0x30
[   48.951324]        kauditd_hold_skb+0x94/0xb8
[   48.951324]        kauditd_thread+0x1a4/0x56c
[   48.951324]        kthread+0x104/0x148
[   48.951354]        ret_from_fork+0x14/0x24
[   48.951354]
               -> #1 ((console_sem).lock){-.....}:
[   48.951385]        _raw_spin_lock_irqsave+0x50/0x64
[   48.951385]        down_trylock+0xc/0x2c
[   48.951385]        __down_trylock_console_sem+0x24/0x80
[   48.951385]        console_trylock+0x10/0x8c
[   48.951416]        vprintk_emit+0x264/0x474
[   48.951416]        vprintk_default+0x20/0x28
[   48.951416]        printk+0x20/0x30
[   48.951446]        tk_debug_account_sleep_time+0x5c/0x70
[   48.951446]        __timekeeping_inject_sleeptime.constprop.3+0x170/0x1a0
[   48.951446]        timekeeping_resume+0x218/0x23c
[   48.951477]        syscore_resume+0x94/0x42c
[   48.951477]        suspend_enter+0x554/0x9b4
[   48.951477]        suspend_devices_and_enter+0xd8/0x4b4
[   48.951507]        enter_state+0x934/0xbd4
[   48.951507]        pm_suspend+0x14/0x70
[   48.951507]        state_store+0x68/0xc8
[   48.951538]        kernfs_fop_write+0xf4/0x1f8
[   48.951538]        __vfs_write+0x1c/0x114
[   48.951538]        vfs_write+0xa0/0x168
[   48.951568]        SyS_write+0x3c/0x90
[   48.951568]        __sys_trace_return+0x0/0x10
[   48.951568]
               -> #0 (tk_core){----..}:
[   48.951599]        lock_acquire+0xe0/0x294
[   48.951599]        ktime_get_update_offsets_now+0x5c/0x1d4
[   48.951629]        retrigger_next_event+0x4c/0x90
[   48.951629]        on_each_cpu+0x40/0x7c
[   48.951629]        clock_was_set_work+0x14/0x20
[   48.951660]        process_one_work+0x2b4/0x808
[   48.951660]        worker_thread+0x3c/0x550
[   48.951660]        kthread+0x104/0x148
[   48.951690]        ret_from_fork+0x14/0x24
[   48.951690]
               other info that might help us debug this:

[   48.951690] Chain exists of:
                 tk_core --> &rt_b->rt_runtime_lock --> hrtimer_bases.lock

[   48.951721]  Possible unsafe locking scenario:

[   48.951721]        CPU0                    CPU1
[   48.951721]        ----                    ----
[   48.951721]   lock(hrtimer_bases.lock);
[   48.951751]                                lock(&rt_b->rt_runtime_lock);
[   48.951751]                                lock(hrtimer_bases.lock);
[   48.951751]   lock(tk_core);
[   48.951782]
                *** DEADLOCK ***

[   48.951782] 3 locks held by kworker/0:0/3:
[   48.951782]  #0:  ("events"){.+.+.+}, at: [<c0156590>] process_one_work+0x1f8/0x808
[   48.951812]  #1:  (hrtimer_work){+.+...}, at: [<c0156590>] process_one_work+0x1f8/0x808
[   48.951843]  #2:  (hrtimer_bases.lock){-.-...}, at: [<c01cc610>] retrigger_next_event+0x38/0x90
[   48.951843]   stack backtrace:
[   48.951873] CPU: 0 PID: 3 Comm: kworker/0:0 Not tainted 4.10.0-rc7-next-20170213+
[   48.951904] Workqueue: events clock_was_set_work
[   48.951904] [<c0110208>] (unwind_backtrace) from [<c010c224>] (show_stack+0x10/0x14)
[   48.951934] [<c010c224>] (show_stack) from [<c04ca6c0>] (dump_stack+0xac/0xe0)
[   48.951934] [<c04ca6c0>] (dump_stack) from [<c019b5cc>] (print_circular_bug+0x1d0/0x308)
[   48.951965] [<c019b5cc>] (print_circular_bug) from [<c019d2a8>] (validate_chain+0xf50/0x1324)
[   48.951965] [<c019d2a8>] (validate_chain) from [<c019ec18>] (__lock_acquire+0x468/0x7e8)
[   48.951995] [<c019ec18>] (__lock_acquire) from [<c019f634>] (lock_acquire+0xe0/0x294)
[   48.951995] [<c019f634>] (lock_acquire) from [<c01d0ea0>] (ktime_get_update_offsets_now+0x5c/0x1d4)
[   48.952026] [<c01d0ea0>] (ktime_get_update_offsets_now) from [<c01cc624>] (retrigger_next_event+0x4c/0x90)
[   48.952026] [<c01cc624>] (retrigger_next_event) from [<c01e4e24>] (on_each_cpu+0x40/0x7c)
[   48.952056] [<c01e4e24>] (on_each_cpu) from [<c01cafc4>] (clock_was_set_work+0x14/0x20)
[   48.952056] [<c01cafc4>] (clock_was_set_work) from [<c015664c>] (process_one_work+0x2b4/0x808)
[   48.952087] [<c015664c>] (process_one_work) from [<c0157774>] (worker_thread+0x3c/0x550)
[   48.952087] [<c0157774>] (worker_thread) from [<c015d644>] (kthread+0x104/0x148)
[   48.952087] [<c015d644>] (kthread) from [<c0107830>] (ret_from_fork+0x14/0x24)

Replace printk() with printk_deferred(), which does not call into
the scheduler.

Fixes: 0bf43f1 ("timekeeping: Prints the amounts of time spent during suspend")
Reported-and-tested-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Cc: Petr Mladek <pmladek@suse.com>
Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: "Rafael J . Wysocki" <rjw@rjwysocki.net>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: John Stultz <john.stultz@linaro.org>
Cc: "[4.9+]" <stable@vger.kernel.org>
Link: http://lkml.kernel.org/r/20170215044332.30449-1-sergey.senozhatsky@gmail.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

Commit 6664498 ("packet: call fanout_release, while UNREGISTERING a
netdev"), unfortunately, introduced the following issues.

1. calling mutex_lock(&fanout_mutex) (fanout_release()) from inside
rcu_read-side critical section. rcu_read_lock disables preemption, most often,
which prohibits calling sleeping functions.

[  ] include/linux/rcupdate.h:560 Illegal context switch in RCU read-side critical section!
[  ]
[  ] rcu_scheduler_active = 1, debug_locks = 0
[  ] 4 locks held by ovs-vswitchd/1969:
[  ]  #0:  (cb_lock){++++++}, at: [<ffffffff8158a6c9>] genl_rcv+0x19/0x40
[  ]  #1:  (ovs_mutex){+.+.+.}, at: [<ffffffffa04878ca>] ovs_vport_cmd_del+0x4a/0x100 [openvswitch]
[  ]  #2:  (rtnl_mutex){+.+.+.}, at: [<ffffffff81564157>] rtnl_lock+0x17/0x20
[  ]  #3:  (rcu_read_lock){......}, at: [<ffffffff81614165>] packet_notifier+0x5/0x3f0
[  ]
[  ] Call Trace:
[  ]  [<ffffffff813770c1>] dump_stack+0x85/0xc4
[  ]  [<ffffffff810c9077>] lockdep_rcu_suspicious+0x107/0x110
[  ]  [<ffffffff810a2da7>] ___might_sleep+0x57/0x210
[  ]  [<ffffffff810a2fd0>] __might_sleep+0x70/0x90
[  ]  [<ffffffff8162e80c>] mutex_lock_nested+0x3c/0x3a0
[  ]  [<ffffffff810de93f>] ? vprintk_default+0x1f/0x30
[  ]  [<ffffffff81186e88>] ? printk+0x4d/0x4f
[  ]  [<ffffffff816106dd>] fanout_release+0x1d/0xe0
[  ]  [<ffffffff81614459>] packet_notifier+0x2f9/0x3f0

2. calling mutex_lock(&fanout_mutex) inside spin_lock(&po->bind_lock).
"sleeping function called from invalid context"

[  ] BUG: sleeping function called from invalid context at kernel/locking/mutex.c:620
[  ] in_atomic(): 1, irqs_disabled(): 0, pid: 1969, name: ovs-vswitchd
[  ] INFO: lockdep is turned off.
[  ] Call Trace:
[  ]  [<ffffffff813770c1>] dump_stack+0x85/0xc4
[  ]  [<ffffffff810a2f52>] ___might_sleep+0x202/0x210
[  ]  [<ffffffff810a2fd0>] __might_sleep+0x70/0x90
[  ]  [<ffffffff8162e80c>] mutex_lock_nested+0x3c/0x3a0
[  ]  [<ffffffff816106dd>] fanout_release+0x1d/0xe0
[  ]  [<ffffffff81614459>] packet_notifier+0x2f9/0x3f0

3. calling dev_remove_pack(&fanout->prot_hook), from inside
spin_lock(&po->bind_lock) or rcu_read-side critical-section. dev_remove_pack()
-> synchronize_net(), which might sleep.

[  ] BUG: scheduling while atomic: ovs-vswitchd/1969/0x00000002
[  ] INFO: lockdep is turned off.
[  ] Call Trace:
[  ]  [<ffffffff813770c1>] dump_stack+0x85/0xc4
[  ]  [<ffffffff81186274>] __schedule_bug+0x64/0x73
[  ]  [<ffffffff8162b8cb>] __schedule+0x6b/0xd10
[  ]  [<ffffffff8162c5db>] schedule+0x6b/0x80
[  ]  [<ffffffff81630b1d>] schedule_timeout+0x38d/0x410
[  ]  [<ffffffff810ea3fd>] synchronize_sched_expedited+0x53d/0x810
[  ]  [<ffffffff810ea6de>] synchronize_rcu_expedited+0xe/0x10
[  ]  [<ffffffff8154eab5>] synchronize_net+0x35/0x50
[  ]  [<ffffffff8154eae3>] dev_remove_pack+0x13/0x20
[  ]  [<ffffffff8161077e>] fanout_release+0xbe/0xe0
[  ]  [<ffffffff81614459>] packet_notifier+0x2f9/0x3f0

4. fanout_release() races with calls from different CPU.

To fix the above problems, remove the call to fanout_release() under
rcu_read_lock(). Instead, call __dev_remove_pack(&fanout->prot_hook) and
netdev_run_todo will be happy that &dev->ptype_specific list is empty. In order
to achieve this, I moved dev_{add,remove}_pack() out of fanout_{add,release} to
__fanout_{link,unlink}. So, call to {,__}unregister_prot_hook() will make sure
fanout->prot_hook is removed as well.

Fixes: 6664498 ("packet: call fanout_release, while UNREGISTERING a netdev")
Reported-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Anoob Soman <anoob.soman@citrix.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The code where sk_clone() came from created a new socket and locked it,
but then, on the error path didn't unlock it.

This problem stayed there for a long while, till b0691c8 ("net:
Unlock sock before calling sk_free()") fixed it, but unfortunately the
callers of sk_clone() (now sk_clone_locked()) were not audited and the
one in dccp_create_openreq_child() remained.

Now in the age of the syskaller fuzzer, this was finally uncovered, as
reported by Dmitry:

 ---- 8< ----

I've got the following report while running syzkaller fuzzer on
86292b3 ("Merge branch 'akpm' (patches from Andrew)")

  [ BUG: held lock freed! ]
  4.10.0+ torvalds#234 Not tainted
  -------------------------
  syz-executor6/6898 is freeing memory
  ffff88006286cac0-ffff88006286d3b7, with a lock still held there!
   (slock-AF_INET6){+.-...}, at: [<ffffffff8362c2c9>] spin_lock
  include/linux/spinlock.h:299 [inline]
   (slock-AF_INET6){+.-...}, at: [<ffffffff8362c2c9>]
  sk_clone_lock+0x3d9/0x12c0 net/core/sock.c:1504
  5 locks held by syz-executor6/6898:
   #0:  (sk_lock-AF_INET6){+.+.+.}, at: [<ffffffff839a34b4>] lock_sock
  include/net/sock.h:1460 [inline]
   #0:  (sk_lock-AF_INET6){+.+.+.}, at: [<ffffffff839a34b4>]
  inet_stream_connect+0x44/0xa0 net/ipv4/af_inet.c:681
   tiwai#1:  (rcu_read_lock){......}, at: [<ffffffff83bc1c2a>]
  inet6_csk_xmit+0x12a/0x5d0 net/ipv6/inet6_connection_sock.c:126
   tiwai#2:  (rcu_read_lock){......}, at: [<ffffffff8369b424>] __skb_unlink
  include/linux/skbuff.h:1767 [inline]
   tiwai#2:  (rcu_read_lock){......}, at: [<ffffffff8369b424>] __skb_dequeue
  include/linux/skbuff.h:1783 [inline]
   tiwai#2:  (rcu_read_lock){......}, at: [<ffffffff8369b424>]
  process_backlog+0x264/0x730 net/core/dev.c:4835
   tiwai#3:  (rcu_read_lock){......}, at: [<ffffffff83aeb5c0>]
  ip6_input_finish+0x0/0x1700 net/ipv6/ip6_input.c:59
   tiwai#4:  (slock-AF_INET6){+.-...}, at: [<ffffffff8362c2c9>] spin_lock
  include/linux/spinlock.h:299 [inline]
   tiwai#4:  (slock-AF_INET6){+.-...}, at: [<ffffffff8362c2c9>]
  sk_clone_lock+0x3d9/0x12c0 net/core/sock.c:1504

Fix it just like was done by b0691c8 ("net: Unlock sock before calling
sk_free()").

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20170301153510.GE15145@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The locking in lirc needs improvement, but for now just fix this potential
deadlock.

======================================================
[ INFO: possible circular locking dependency detected ]
4.10.0-rc1+ tiwai#1 Not tainted
-------------------------------------------------------
bash/2502 is trying to acquire lock:
 (ir_raw_handler_lock){+.+.+.}, at: [<ffffffffc06f6a5e>] ir_raw_encode_scancode+0x3e/0xb0 [rc_core]

               but task is already holding lock:
 (&dev->lock){+.+.+.}, at: [<ffffffffc06f511f>] store_filter+0x9f/0x240 [rc_core]

               which lock already depends on the new lock.

               the existing dependency chain (in reverse order) is:

               -> tiwai#2 (&dev->lock){+.+.+.}:

[<ffffffffa110adad>] lock_acquire+0xfd/0x200
[<ffffffffa1921327>] mutex_lock_nested+0x77/0x6d0
[<ffffffffc06f436a>] rc_open+0x2a/0x80 [rc_core]
[<ffffffffc07114ca>] lirc_dev_fop_open+0xda/0x1e0 [lirc_dev]
[<ffffffffa12975e0>] chrdev_open+0xb0/0x210
[<ffffffffa128eb5a>] do_dentry_open+0x20a/0x2f0
[<ffffffffa128ffcc>] vfs_open+0x4c/0x80
[<ffffffffa12a35ec>] path_openat+0x5bc/0xc00
[<ffffffffa12a5271>] do_filp_open+0x91/0x100
[<ffffffffa12903f0>] do_sys_open+0x130/0x220
[<ffffffffa12904fe>] SyS_open+0x1e/0x20
[<ffffffffa19278c1>] entry_SYSCALL_64_fastpath+0x1f/0xc2
               -> tiwai#1 (lirc_dev_lock){+.+.+.}:
[<ffffffffa110adad>] lock_acquire+0xfd/0x200
[<ffffffffa1921327>] mutex_lock_nested+0x77/0x6d0
[<ffffffffc0711f47>] lirc_register_driver+0x67/0x59b [lirc_dev]
[<ffffffffc06db7f4>] ir_lirc_register+0x1f4/0x260 [ir_lirc_codec]
[<ffffffffc06f6cac>] ir_raw_handler_register+0x7c/0xb0 [rc_core]
[<ffffffffc0398010>] 0xffffffffc0398010
[<ffffffffa1002192>] do_one_initcall+0x52/0x1b0
[<ffffffffa11ef5c8>] do_init_module+0x5f/0x1fa
[<ffffffffa11566b5>] load_module+0x2675/0x2b00
[<ffffffffa1156dcf>] SYSC_finit_module+0xdf/0x110
[<ffffffffa1156e1e>] SyS_finit_module+0xe/0x10
[<ffffffffa1003f5c>] do_syscall_64+0x6c/0x1f0
[<ffffffffa1927989>] return_from_SYSCALL_64+0x0/0x7a
               -> #0 (ir_raw_handler_lock){+.+.+.}:
[<ffffffffa110a7b7>] __lock_acquire+0x10f7/0x1290
[<ffffffffa110adad>] lock_acquire+0xfd/0x200
[<ffffffffa1921327>] mutex_lock_nested+0x77/0x6d0
[<ffffffffc06f6a5e>] ir_raw_encode_scancode+0x3e/0xb0 [rc_core]
[<ffffffffc0b0f492>] loop_set_wakeup_filter+0x62/0xbd [rc_loopback]
[<ffffffffc06f522a>] store_filter+0x1aa/0x240 [rc_core]
[<ffffffffa15e46f8>] dev_attr_store+0x18/0x30
[<ffffffffa13318e5>] sysfs_kf_write+0x45/0x60
[<ffffffffa1330b55>] kernfs_fop_write+0x155/0x1e0
[<ffffffffa1290797>] __vfs_write+0x37/0x160
[<ffffffffa12921f8>] vfs_write+0xc8/0x1e0
[<ffffffffa12936e8>] SyS_write+0x58/0xc0
[<ffffffffa19278c1>] entry_SYSCALL_64_fastpath+0x1f/0xc2

               other info that might help us debug this:

Chain exists of:
                 ir_raw_handler_lock --> lirc_dev_lock --> &dev->lock

 Possible unsafe locking scenario:

       CPU0                    CPU1
       ----                    ----
  lock(&dev->lock);
                               lock(lirc_dev_lock);
                               lock(&dev->lock);
  lock(ir_raw_handler_lock);

                *** DEADLOCK ***

4 locks held by bash/2502:
 #0:  (sb_writers#4){.+.+.+}, at: [<ffffffffa12922c5>] vfs_write+0x195/0x1e0
 tiwai#1:  (&of->mutex){+.+.+.}, at: [<ffffffffa1330b1f>] kernfs_fop_write+0x11f/0x1e0
 tiwai#2:  (s_active#215){.+.+.+}, at: [<ffffffffa1330b28>] kernfs_fop_write+0x128/0x1e0
 tiwai#3:  (&dev->lock){+.+.+.}, at: [<ffffffffc06f511f>] store_filter+0x9f/0x240 [rc_core]

               stack backtrace:
CPU: 3 PID: 2502 Comm: bash Not tainted 4.10.0-rc1+ tiwai#1
Hardware name:                  /DG45ID, BIOS IDG4510H.86A.0135.2011.0225.1100 02/25/2011
Call Trace:
 dump_stack+0x86/0xc3
 print_circular_bug+0x1be/0x210
 __lock_acquire+0x10f7/0x1290
 lock_acquire+0xfd/0x200
 ? ir_raw_encode_scancode+0x3e/0xb0 [rc_core]
 ? ir_raw_encode_scancode+0x3e/0xb0 [rc_core]
 mutex_lock_nested+0x77/0x6d0
 ? ir_raw_encode_scancode+0x3e/0xb0 [rc_core]
 ? loop_set_wakeup_filter+0x44/0xbd [rc_loopback]
 ir_raw_encode_scancode+0x3e/0xb0 [rc_core]
 loop_set_wakeup_filter+0x62/0xbd [rc_loopback]
 ? loop_set_tx_duty_cycle+0x70/0x70 [rc_loopback]
 store_filter+0x1aa/0x240 [rc_core]
 dev_attr_store+0x18/0x30
 sysfs_kf_write+0x45/0x60
 kernfs_fop_write+0x155/0x1e0
 __vfs_write+0x37/0x160
 ? rcu_read_lock_sched_held+0x4a/0x80
 ? rcu_sync_lockdep_assert+0x2f/0x60
 ? __sb_start_write+0x10c/0x220
 ? vfs_write+0x195/0x1e0
 ? security_file_permission+0x3b/0xc0
 vfs_write+0xc8/0x1e0
 SyS_write+0x58/0xc0
 entry_SYSCALL_64_fastpath+0x1f/0xc2

Signed-off-by: Sean Young <sean@mess.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab@s-opensource.com>

This is a story about 4 distinct (and very old) btrfs bugs.

Commit c8b9781 ("Btrfs: Add zlib compression support") added
three data corruption bugs for inline extents (bugs #1-3).

Commit 93c82d5 ("Btrfs: zero page past end of inline file items")
fixed bug #1:  uncompressed inline extents followed by a hole and more
extents could get non-zero data in the hole as they were read.  The fix
was to add a memset in btrfs_get_extent to zero out the hole.

Commit 166ae5a ("btrfs: fix inline compressed read err corruption")
fixed bug #2:  compressed inline extents which contained non-zero bytes
might be replaced with zero bytes in some cases.  This patch removed an
unhelpful memset from uncompress_inline, but the case where memset is
required was missed.

There is also a memset in the decompression code, but this only covers
decompressed data that is shorter than the ram_bytes from the extent
ref record.  This memset doesn't cover the region between the end of the
decompressed data and the end of the page.  It has also moved around a
few times over the years, so there's no single patch to refer to.

This patch fixes bug #3:  compressed inline extents followed by a hole
and more extents could get non-zero data in the hole as they were read
(i.e. bug #3 is the same as bug #1, but s/uncompressed/compressed/).
The fix is the same:  zero out the hole in the compressed case too,
by putting a memset back in uncompress_inline, but this time with
correct parameters.

The last and oldest bug, bug #0, is the cause of the offending inline
extent/hole/extent pattern.  Bug #0 is a subtle and mostly-harmless quirk
of behavior somewhere in the btrfs write code.  In a few special cases,
an inline extent and hole are allowed to persist where they normally
would be combined with later extents in the file.

A fast reproducer for bug #0 is presented below.  A few offending extents
are also created in the wild during large rsync transfers with the -S
flag.  A Linux kernel build (git checkout; make allyesconfig; make -j8)
will produce a handful of offending files as well.  Once an offending
file is created, it can present different content to userspace each
time it is read.

Bug #0 is at least 4 and possibly 8 years old.  I verified every vX.Y
kernel back to v3.5 has this behavior.  There are fossil records of this
bug's effects in commits all the way back to v2.6.32.  I have no reason
to believe bug #0 wasn't present at the beginning of btrfs compression
support in v2.6.29, but I can't easily test kernels that old to be sure.

It is not clear whether bug #0 is worth fixing.  A fix would likely
require injecting extra reads into currently write-only paths, and most
of the exceptional cases caused by bug #0 are already handled now.

Whether we like them or not, bug #0's inline extents followed by holes
are part of the btrfs de-facto disk format now, and we need to be able
to read them without data corruption or an infoleak.  So enough about
bug #0, let's get back to bug #3 (this patch).

An example of on-disk structure leading to data corruption found in
the wild:

        item 61 key (606890 INODE_ITEM 0) itemoff 9662 itemsize 160
                inode generation 50 transid 50 size 47424 nbytes 49141
                block group 0 mode 100644 links 1 uid 0 gid 0
                rdev 0 flags 0x0(none)
        item 62 key (606890 INODE_REF 603050) itemoff 9642 itemsize 20
                inode ref index 3 namelen 10 name: DB_File.so
        item 63 key (606890 EXTENT_DATA 0) itemoff 8280 itemsize 1362
                inline extent data size 1341 ram 4085 compress(zlib)
        item 64 key (606890 EXTENT_DATA 4096) itemoff 8227 itemsize 53
                extent data disk byte 5367308288 nr 20480
                extent data offset 0 nr 45056 ram 45056
                extent compression(zlib)

Different data appears in userspace during each read of the 11 bytes
between 4085 and 4096.  The extent in item 63 is not long enough to
fill the first page of the file, so a memset is required to fill the
space between item 63 (ending at 4085) and item 64 (beginning at 4096)
with zero.

Here is a reproducer from Liu Bo, which demonstrates another method
of creating the same inline extent and hole pattern:

Using 'page_poison=on' kernel command line (or enable
CONFIG_PAGE_POISONING) run the following:

	# touch foo
	# chattr +c foo
	# xfs_io -f -c "pwrite -W 0 1000" foo
	# xfs_io -f -c "falloc 4 8188" foo
	# od -x foo
	# echo 3 >/proc/sys/vm/drop_caches
	# od -x foo

This produce the following on my box:

Correct output:  file contains 1000 data bytes followed
by zeros:

	0000000 cdcd cdcd cdcd cdcd cdcd cdcd cdcd cdcd
	*
	0001740 cdcd cdcd cdcd cdcd 0000 0000 0000 0000
	0001760 0000 0000 0000 0000 0000 0000 0000 0000
	*
	0020000

Actual output:  the data after the first 1000 bytes
will be different each run:

	0000000 cdcd cdcd cdcd cdcd cdcd cdcd cdcd cdcd
	*
	0001740 cdcd cdcd cdcd cdcd 6c63 7400 635f 006d
	0001760 5f74 6f43 7400 435f 0053 5f74 7363 7400
	0002000 435f 0056 5f74 6164 7400 645f 0062 5f74
	(...)

Signed-off-by: Zygo Blaxell <ce3g8jdj@umail.furryterror.org>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
Reviewed-by: Chris Mason <clm@fb.com>
Signed-off-by: Chris Mason <clm@fb.com>

The rcu_barrier() takes the cpu_hotplug mutex which itself is not
reclaim-safe, and so rcu_barrier() is illegal from inside the shrinker.

[  309.661373] =========================================================
[  309.661376] [ INFO: possible irq lock inversion dependency detected ]
[  309.661380] 4.11.0-rc1-CI-CI_DRM_2333+ #1 Tainted: G        W
[  309.661383] ---------------------------------------------------------
[  309.661386] gem_exec_gttfil/6435 just changed the state of lock:
[  309.661389]  (rcu_preempt_state.barrier_mutex){+.+.-.}, at: [<ffffffff81100731>] _rcu_barrier+0x31/0x160
[  309.661399] but this lock took another, RECLAIM_FS-unsafe lock in the past:
[  309.661402]  (cpu_hotplug.lock){+.+.+.}
[  309.661404]

               and interrupts could create inverse lock ordering between them.

[  309.661410]
               other info that might help us debug this:
[  309.661414]  Possible interrupt unsafe locking scenario:

[  309.661417]        CPU0                    CPU1
[  309.661419]        ----                    ----
[  309.661421]   lock(cpu_hotplug.lock);
[  309.661425]                                local_irq_disable();
[  309.661432]                                lock(rcu_preempt_state.barrier_mutex);
[  309.661441]                                lock(cpu_hotplug.lock);
[  309.661446]   <Interrupt>
[  309.661448]     lock(rcu_preempt_state.barrier_mutex);
[  309.661453]
                *** DEADLOCK ***

[  309.661460] 4 locks held by gem_exec_gttfil/6435:
[  309.661464]  #0:  (sb_writers#10){.+.+.+}, at: [<ffffffff8120d83d>] vfs_write+0x17d/0x1f0
[  309.661475]  #1:  (debugfs_srcu){......}, at: [<ffffffff81320491>] debugfs_use_file_start+0x41/0xa0
[  309.661486]  #2:  (&attr->mutex){+.+.+.}, at: [<ffffffff8123a3e7>] simple_attr_write+0x37/0xe0
[  309.661495]  #3:  (&dev->struct_mutex){+.+.+.}, at: [<ffffffffa0091b4a>] i915_drop_caches_set+0x3a/0x150 [i915]
[  309.661540]
               the shortest dependencies between 2nd lock and 1st lock:
[  309.661547]  -> (cpu_hotplug.lock){+.+.+.} ops: 829 {
[  309.661553]     HARDIRQ-ON-W at:
[  309.661560]                       __lock_acquire+0x5e5/0x1b50
[  309.661565]                       lock_acquire+0xc9/0x220
[  309.661572]                       __mutex_lock+0x6e/0x990
[  309.661576]                       mutex_lock_nested+0x16/0x20
[  309.661583]                       get_online_cpus+0x61/0x80
[  309.661590]                       kmem_cache_create+0x25/0x1d0
[  309.661596]                       debug_objects_mem_init+0x30/0x249
[  309.661602]                       start_kernel+0x341/0x3fe
[  309.661607]                       x86_64_start_reservations+0x2a/0x2c
[  309.661612]                       x86_64_start_kernel+0x173/0x186
[  309.661619]                       verify_cpu+0x0/0xfc
[  309.661622]     SOFTIRQ-ON-W at:
[  309.661627]                       __lock_acquire+0x611/0x1b50
[  309.661632]                       lock_acquire+0xc9/0x220
[  309.661636]                       __mutex_lock+0x6e/0x990
[  309.661641]                       mutex_lock_nested+0x16/0x20
[  309.661646]                       get_online_cpus+0x61/0x80
[  309.661650]                       kmem_cache_create+0x25/0x1d0
[  309.661655]                       debug_objects_mem_init+0x30/0x249
[  309.661660]                       start_kernel+0x341/0x3fe
[  309.661664]                       x86_64_start_reservations+0x2a/0x2c
[  309.661669]                       x86_64_start_kernel+0x173/0x186
[  309.661674]                       verify_cpu+0x0/0xfc
[  309.661677]     RECLAIM_FS-ON-W at:
[  309.661682]                          mark_held_locks+0x6f/0xa0
[  309.661687]                          lockdep_trace_alloc+0xb3/0x100
[  309.661693]                          kmem_cache_alloc_trace+0x31/0x2e0
[  309.661699]                          __smpboot_create_thread.part.1+0x27/0xe0
[  309.661704]                          smpboot_create_threads+0x61/0x90
[  309.661709]                          cpuhp_invoke_callback+0x9c/0x8a0
[  309.661713]                          cpuhp_up_callbacks+0x31/0xb0
[  309.661718]                          _cpu_up+0x7a/0xc0
[  309.661723]                          do_cpu_up+0x5f/0x80
[  309.661727]                          cpu_up+0xe/0x10
[  309.661734]                          smp_init+0x71/0xb3
[  309.661738]                          kernel_init_freeable+0x94/0x19e
[  309.661743]                          kernel_init+0x9/0xf0
[  309.661748]                          ret_from_fork+0x2e/0x40
[  309.661752]     INITIAL USE at:
[  309.661757]                      __lock_acquire+0x234/0x1b50
[  309.661761]                      lock_acquire+0xc9/0x220
[  309.661766]                      __mutex_lock+0x6e/0x990
[  309.661771]                      mutex_lock_nested+0x16/0x20
[  309.661775]                      get_online_cpus+0x61/0x80
[  309.661780]                      __cpuhp_setup_state+0x44/0x170
[  309.661785]                      page_alloc_init+0x23/0x3a
[  309.661790]                      start_kernel+0x124/0x3fe
[  309.661794]                      x86_64_start_reservations+0x2a/0x2c
[  309.661799]                      x86_64_start_kernel+0x173/0x186
[  309.661804]                      verify_cpu+0x0/0xfc
[  309.661807]   }
[  309.661813]   ... key      at: [<ffffffff81e37690>] cpu_hotplug+0xb0/0x100
[  309.661817]   ... acquired at:
[  309.661821]    lock_acquire+0xc9/0x220
[  309.661825]    __mutex_lock+0x6e/0x990
[  309.661829]    mutex_lock_nested+0x16/0x20
[  309.661833]    get_online_cpus+0x61/0x80
[  309.661837]    _rcu_barrier+0x9f/0x160
[  309.661841]    rcu_barrier+0x10/0x20
[  309.661847]    netdev_run_todo+0x5f/0x310
[  309.661852]    rtnl_unlock+0x9/0x10
[  309.661856]    default_device_exit_batch+0x133/0x150
[  309.661862]    ops_exit_list.isra.0+0x4d/0x60
[  309.661866]    cleanup_net+0x1d8/0x2c0
[  309.661872]    process_one_work+0x1f4/0x6d0
[  309.661876]    worker_thread+0x49/0x4a0
[  309.661881]    kthread+0x107/0x140
[  309.661884]    ret_from_fork+0x2e/0x40

[  309.661890] -> (rcu_preempt_state.barrier_mutex){+.+.-.} ops: 179 {
[  309.661896]    HARDIRQ-ON-W at:
[  309.661901]                     __lock_acquire+0x5e5/0x1b50
[  309.661905]                     lock_acquire+0xc9/0x220
[  309.661910]                     __mutex_lock+0x6e/0x990
[  309.661914]                     mutex_lock_nested+0x16/0x20
[  309.661919]                     _rcu_barrier+0x31/0x160
[  309.661923]                     rcu_barrier+0x10/0x20
[  309.661928]                     netdev_run_todo+0x5f/0x310
[  309.661932]                     rtnl_unlock+0x9/0x10
[  309.661936]                     default_device_exit_batch+0x133/0x150
[  309.661941]                     ops_exit_list.isra.0+0x4d/0x60
[  309.661946]                     cleanup_net+0x1d8/0x2c0
[  309.661951]                     process_one_work+0x1f4/0x6d0
[  309.661955]                     worker_thread+0x49/0x4a0
[  309.661960]                     kthread+0x107/0x140
[  309.661964]                     ret_from_fork+0x2e/0x40
[  309.661968]    SOFTIRQ-ON-W at:
[  309.661972]                     __lock_acquire+0x611/0x1b50
[  309.661977]                     lock_acquire+0xc9/0x220
[  309.661981]                     __mutex_lock+0x6e/0x990
[  309.661986]                     mutex_lock_nested+0x16/0x20
[  309.661990]                     _rcu_barrier+0x31/0x160
[  309.661995]                     rcu_barrier+0x10/0x20
[  309.661999]                     netdev_run_todo+0x5f/0x310
[  309.662003]                     rtnl_unlock+0x9/0x10
[  309.662008]                     default_device_exit_batch+0x133/0x150
[  309.662013]                     ops_exit_list.isra.0+0x4d/0x60
[  309.662017]                     cleanup_net+0x1d8/0x2c0
[  309.662022]                     process_one_work+0x1f4/0x6d0
[  309.662027]                     worker_thread+0x49/0x4a0
[  309.662031]                     kthread+0x107/0x140
[  309.662035]                     ret_from_fork+0x2e/0x40
[  309.662039]    IN-RECLAIM_FS-W at:
[  309.662043]                        __lock_acquire+0x638/0x1b50
[  309.662048]                        lock_acquire+0xc9/0x220
[  309.662053]                        __mutex_lock+0x6e/0x990
[  309.662058]                        mutex_lock_nested+0x16/0x20
[  309.662062]                        _rcu_barrier+0x31/0x160
[  309.662067]                        rcu_barrier+0x10/0x20
[  309.662089]                        i915_gem_shrink_all+0x33/0x40 [i915]
[  309.662109]                        i915_drop_caches_set+0x141/0x150 [i915]
[  309.662114]                        simple_attr_write+0xc7/0xe0
[  309.662119]                        full_proxy_write+0x4f/0x70
[  309.662124]                        __vfs_write+0x23/0x120
[  309.662128]                        vfs_write+0xc6/0x1f0
[  309.662133]                        SyS_write+0x44/0xb0
[  309.662138]                        entry_SYSCALL_64_fastpath+0x1c/0xb1
[  309.662142]    INITIAL USE at:
[  309.662147]                    __lock_acquire+0x234/0x1b50
[  309.662151]                    lock_acquire+0xc9/0x220
[  309.662156]                    __mutex_lock+0x6e/0x990
[  309.662160]                    mutex_lock_nested+0x16/0x20
[  309.662165]                    _rcu_barrier+0x31/0x160
[  309.662169]                    rcu_barrier+0x10/0x20
[  309.662174]                    netdev_run_todo+0x5f/0x310
[  309.662178]                    rtnl_unlock+0x9/0x10
[  309.662183]                    default_device_exit_batch+0x133/0x150
[  309.662188]                    ops_exit_list.isra.0+0x4d/0x60
[  309.662192]                    cleanup_net+0x1d8/0x2c0
[  309.662197]                    process_one_work+0x1f4/0x6d0
[  309.662202]                    worker_thread+0x49/0x4a0
[  309.662206]                    kthread+0x107/0x140
[  309.662210]                    ret_from_fork+0x2e/0x40
[  309.662214]  }
[  309.662220]  ... key      at: [<ffffffff81e4e1c8>] rcu_preempt_state+0x508/0x780
[  309.662225]  ... acquired at:
[  309.662229]    check_usage_forwards+0x12b/0x130
[  309.662233]    mark_lock+0x360/0x6f0
[  309.662237]    __lock_acquire+0x638/0x1b50
[  309.662241]    lock_acquire+0xc9/0x220
[  309.662245]    __mutex_lock+0x6e/0x990
[  309.662249]    mutex_lock_nested+0x16/0x20
[  309.662253]    _rcu_barrier+0x31/0x160
[  309.662257]    rcu_barrier+0x10/0x20
[  309.662279]    i915_gem_shrink_all+0x33/0x40 [i915]
[  309.662298]    i915_drop_caches_set+0x141/0x150 [i915]
[  309.662303]    simple_attr_write+0xc7/0xe0
[  309.662307]    full_proxy_write+0x4f/0x70
[  309.662311]    __vfs_write+0x23/0x120
[  309.662315]    vfs_write+0xc6/0x1f0
[  309.662319]    SyS_write+0x44/0xb0
[  309.662323]    entry_SYSCALL_64_fastpath+0x1c/0xb1

[  309.662329]
               stack backtrace:
[  309.662335] CPU: 1 PID: 6435 Comm: gem_exec_gttfil Tainted: G        W       4.11.0-rc1-CI-CI_DRM_2333+ #1
[  309.662342] Hardware name: Hewlett-Packard HP Compaq 8100 Elite SFF PC/304Ah, BIOS 786H1 v01.13 07/14/2011
[  309.662348] Call Trace:
[  309.662354]  dump_stack+0x67/0x92
[  309.662359]  print_irq_inversion_bug.part.19+0x1a4/0x1b0
[  309.662365]  check_usage_forwards+0x12b/0x130
[  309.662369]  mark_lock+0x360/0x6f0
[  309.662374]  ? print_shortest_lock_dependencies+0x1a0/0x1a0
[  309.662379]  __lock_acquire+0x638/0x1b50
[  309.662383]  ? __mutex_unlock_slowpath+0x3e/0x2e0
[  309.662388]  ? trace_hardirqs_on+0xd/0x10
[  309.662392]  ? _rcu_barrier+0x31/0x160
[  309.662396]  lock_acquire+0xc9/0x220
[  309.662400]  ? _rcu_barrier+0x31/0x160
[  309.662404]  ? _rcu_barrier+0x31/0x160
[  309.662409]  __mutex_lock+0x6e/0x990
[  309.662412]  ? _rcu_barrier+0x31/0x160
[  309.662416]  ? _rcu_barrier+0x31/0x160
[  309.662421]  ? synchronize_rcu_expedited+0x35/0xb0
[  309.662426]  ? _raw_spin_unlock_irqrestore+0x52/0x60
[  309.662434]  mutex_lock_nested+0x16/0x20
[  309.662438]  _rcu_barrier+0x31/0x160
[  309.662442]  rcu_barrier+0x10/0x20
[  309.662464]  i915_gem_shrink_all+0x33/0x40 [i915]
[  309.662484]  i915_drop_caches_set+0x141/0x150 [i915]
[  309.662489]  simple_attr_write+0xc7/0xe0
[  309.662494]  full_proxy_write+0x4f/0x70
[  309.662498]  __vfs_write+0x23/0x120
[  309.662503]  ? rcu_read_lock_sched_held+0x75/0x80
[  309.662507]  ? rcu_sync_lockdep_assert+0x2a/0x50
[  309.662512]  ? __sb_start_write+0x102/0x210
[  309.662516]  ? vfs_write+0x17d/0x1f0
[  309.662520]  vfs_write+0xc6/0x1f0
[  309.662524]  ? trace_hardirqs_on_caller+0xe7/0x200
[  309.662529]  SyS_write+0x44/0xb0
[  309.662533]  entry_SYSCALL_64_fastpath+0x1c/0xb1
[  309.662537] RIP: 0033:0x7f507eac24a0
[  309.662541] RSP: 002b:00007fffda8720e8 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
[  309.662548] RAX: ffffffffffffffda RBX: ffffffff81482bd3 RCX: 00007f507eac24a0
[  309.662552] RDX: 0000000000000005 RSI: 00007fffda8720f0 RDI: 0000000000000005
[  309.662557] RBP: ffffc9000048bf88 R08: 0000000000000000 R09: 000000000000002c
[  309.662561] R10: 0000000000000014 R11: 0000000000000246 R12: 00007fffda872230
[  309.662566] R13: 00007fffda872228 R14: 0000000000000201 R15: 00007fffda8720f0
[  309.662572]  ? __this_cpu_preempt_check+0x13/0x20

Fixes: 0eafec6 ("drm/i915: Enable lockless lookup of request tracking via RCU")
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=100192
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: <stable@vger.kernel.org> # v4.9+
Link: http://patchwork.freedesktop.org/patch/msgid/20170314115019.18127-1-chris@chris-wilson.co.uk
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
(cherry picked from commit bd784b7)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20170321144531.12344-1-chris@chris-wilson.co.uk

Dmitry reported a lockdep splat [1] (false positive) that we can fix
by releasing the spinlock before calling icmp_send() from ip_expire()

This is a false positive because sending an ICMP message can not
possibly re-enter the IP frag engine.

[1]
[ INFO: possible circular locking dependency detected ]
4.10.0+ torvalds#29 Not tainted
-------------------------------------------------------
modprobe/12392 is trying to acquire lock:
 (_xmit_ETHER#2){+.-...}, at: [<ffffffff837a8182>] spin_lock
include/linux/spinlock.h:299 [inline]
 (_xmit_ETHER#2){+.-...}, at: [<ffffffff837a8182>] __netif_tx_lock
include/linux/netdevice.h:3486 [inline]
 (_xmit_ETHER#2){+.-...}, at: [<ffffffff837a8182>]
sch_direct_xmit+0x282/0x6d0 net/sched/sch_generic.c:180

but task is already holding lock:
 (&(&q->lock)->rlock){+.-...}, at: [<ffffffff8389a4d1>] spin_lock
include/linux/spinlock.h:299 [inline]
 (&(&q->lock)->rlock){+.-...}, at: [<ffffffff8389a4d1>]
ip_expire+0x51/0x6c0 net/ipv4/ip_fragment.c:201

which lock already depends on the new lock.

the existing dependency chain (in reverse order) is:

-> #1 (&(&q->lock)->rlock){+.-...}:
       validate_chain kernel/locking/lockdep.c:2267 [inline]
       __lock_acquire+0x2149/0x3430 kernel/locking/lockdep.c:3340
       lock_acquire+0x2a1/0x630 kernel/locking/lockdep.c:3755
       __raw_spin_lock include/linux/spinlock_api_smp.h:142 [inline]
       _raw_spin_lock+0x33/0x50 kernel/locking/spinlock.c:151
       spin_lock include/linux/spinlock.h:299 [inline]
       ip_defrag+0x3a2/0x4130 net/ipv4/ip_fragment.c:669
       ip_check_defrag+0x4e3/0x8b0 net/ipv4/ip_fragment.c:713
       packet_rcv_fanout+0x282/0x800 net/packet/af_packet.c:1459
       deliver_skb net/core/dev.c:1834 [inline]
       dev_queue_xmit_nit+0x294/0xa90 net/core/dev.c:1890
       xmit_one net/core/dev.c:2903 [inline]
       dev_hard_start_xmit+0x16b/0xab0 net/core/dev.c:2923
       sch_direct_xmit+0x31f/0x6d0 net/sched/sch_generic.c:182
       __dev_xmit_skb net/core/dev.c:3092 [inline]
       __dev_queue_xmit+0x13e5/0x1e60 net/core/dev.c:3358
       dev_queue_xmit+0x17/0x20 net/core/dev.c:3423
       neigh_resolve_output+0x6b9/0xb10 net/core/neighbour.c:1308
       neigh_output include/net/neighbour.h:478 [inline]
       ip_finish_output2+0x8b8/0x15a0 net/ipv4/ip_output.c:228
       ip_do_fragment+0x1d93/0x2720 net/ipv4/ip_output.c:672
       ip_fragment.constprop.54+0x145/0x200 net/ipv4/ip_output.c:545
       ip_finish_output+0x82d/0xe10 net/ipv4/ip_output.c:314
       NF_HOOK_COND include/linux/netfilter.h:246 [inline]
       ip_output+0x1f0/0x7a0 net/ipv4/ip_output.c:404
       dst_output include/net/dst.h:486 [inline]
       ip_local_out+0x95/0x170 net/ipv4/ip_output.c:124
       ip_send_skb+0x3c/0xc0 net/ipv4/ip_output.c:1492
       ip_push_pending_frames+0x64/0x80 net/ipv4/ip_output.c:1512
       raw_sendmsg+0x26de/0x3a00 net/ipv4/raw.c:655
       inet_sendmsg+0x164/0x5b0 net/ipv4/af_inet.c:761
       sock_sendmsg_nosec net/socket.c:633 [inline]
       sock_sendmsg+0xca/0x110 net/socket.c:643
       ___sys_sendmsg+0x4a3/0x9f0 net/socket.c:1985
       __sys_sendmmsg+0x25c/0x750 net/socket.c:2075
       SYSC_sendmmsg net/socket.c:2106 [inline]
       SyS_sendmmsg+0x35/0x60 net/socket.c:2101
       do_syscall_64+0x2e8/0x930 arch/x86/entry/common.c:281
       return_from_SYSCALL_64+0x0/0x7a

-> #0 (_xmit_ETHER#2){+.-...}:
       check_prev_add kernel/locking/lockdep.c:1830 [inline]
       check_prevs_add+0xa8f/0x19f0 kernel/locking/lockdep.c:1940
       validate_chain kernel/locking/lockdep.c:2267 [inline]
       __lock_acquire+0x2149/0x3430 kernel/locking/lockdep.c:3340
       lock_acquire+0x2a1/0x630 kernel/locking/lockdep.c:3755
       __raw_spin_lock include/linux/spinlock_api_smp.h:142 [inline]
       _raw_spin_lock+0x33/0x50 kernel/locking/spinlock.c:151
       spin_lock include/linux/spinlock.h:299 [inline]
       __netif_tx_lock include/linux/netdevice.h:3486 [inline]
       sch_direct_xmit+0x282/0x6d0 net/sched/sch_generic.c:180
       __dev_xmit_skb net/core/dev.c:3092 [inline]
       __dev_queue_xmit+0x13e5/0x1e60 net/core/dev.c:3358
       dev_queue_xmit+0x17/0x20 net/core/dev.c:3423
       neigh_hh_output include/net/neighbour.h:468 [inline]
       neigh_output include/net/neighbour.h:476 [inline]
       ip_finish_output2+0xf6c/0x15a0 net/ipv4/ip_output.c:228
       ip_finish_output+0xa29/0xe10 net/ipv4/ip_output.c:316
       NF_HOOK_COND include/linux/netfilter.h:246 [inline]
       ip_output+0x1f0/0x7a0 net/ipv4/ip_output.c:404
       dst_output include/net/dst.h:486 [inline]
       ip_local_out+0x95/0x170 net/ipv4/ip_output.c:124
       ip_send_skb+0x3c/0xc0 net/ipv4/ip_output.c:1492
       ip_push_pending_frames+0x64/0x80 net/ipv4/ip_output.c:1512
       icmp_push_reply+0x372/0x4d0 net/ipv4/icmp.c:394
       icmp_send+0x156c/0x1c80 net/ipv4/icmp.c:754
       ip_expire+0x40e/0x6c0 net/ipv4/ip_fragment.c:239
       call_timer_fn+0x241/0x820 kernel/time/timer.c:1268
       expire_timers kernel/time/timer.c:1307 [inline]
       __run_timers+0x960/0xcf0 kernel/time/timer.c:1601
       run_timer_softirq+0x21/0x80 kernel/time/timer.c:1614
       __do_softirq+0x31f/0xbe7 kernel/softirq.c:284
       invoke_softirq kernel/softirq.c:364 [inline]
       irq_exit+0x1cc/0x200 kernel/softirq.c:405
       exiting_irq arch/x86/include/asm/apic.h:657 [inline]
       smp_apic_timer_interrupt+0x76/0xa0 arch/x86/kernel/apic/apic.c:962
       apic_timer_interrupt+0x93/0xa0 arch/x86/entry/entry_64.S:707
       __read_once_size include/linux/compiler.h:254 [inline]
       atomic_read arch/x86/include/asm/atomic.h:26 [inline]
       rcu_dynticks_curr_cpu_in_eqs kernel/rcu/tree.c:350 [inline]
       __rcu_is_watching kernel/rcu/tree.c:1133 [inline]
       rcu_is_watching+0x83/0x110 kernel/rcu/tree.c:1147
       rcu_read_lock_held+0x87/0xc0 kernel/rcu/update.c:293
       radix_tree_deref_slot include/linux/radix-tree.h:238 [inline]
       filemap_map_pages+0x6d4/0x1570 mm/filemap.c:2335
       do_fault_around mm/memory.c:3231 [inline]
       do_read_fault mm/memory.c:3265 [inline]
       do_fault+0xbd5/0x2080 mm/memory.c:3370
       handle_pte_fault mm/memory.c:3600 [inline]
       __handle_mm_fault+0x1062/0x2cb0 mm/memory.c:3714
       handle_mm_fault+0x1e2/0x480 mm/memory.c:3751
       __do_page_fault+0x4f6/0xb60 arch/x86/mm/fault.c:1397
       do_page_fault+0x54/0x70 arch/x86/mm/fault.c:1460
       page_fault+0x28/0x30 arch/x86/entry/entry_64.S:1011

other info that might help us debug this:

 Possible unsafe locking scenario:

       CPU0                    CPU1
       ----                    ----
  lock(&(&q->lock)->rlock);
                               lock(_xmit_ETHER#2);
                               lock(&(&q->lock)->rlock);
  lock(_xmit_ETHER#2);

 *** DEADLOCK ***

10 locks held by modprobe/12392:
 #0:  (&mm->mmap_sem){++++++}, at: [<ffffffff81329758>]
__do_page_fault+0x2b8/0xb60 arch/x86/mm/fault.c:1336
 #1:  (rcu_read_lock){......}, at: [<ffffffff8188cab6>]
filemap_map_pages+0x1e6/0x1570 mm/filemap.c:2324
 #2:  (&(ptlock_ptr(page))->rlock#2){+.+...}, at: [<ffffffff81984a78>]
spin_lock include/linux/spinlock.h:299 [inline]
 #2:  (&(ptlock_ptr(page))->rlock#2){+.+...}, at: [<ffffffff81984a78>]
pte_alloc_one_map mm/memory.c:2944 [inline]
 #2:  (&(ptlock_ptr(page))->rlock#2){+.+...}, at: [<ffffffff81984a78>]
alloc_set_pte+0x13b8/0x1b90 mm/memory.c:3072
 #3:  (((&q->timer))){+.-...}, at: [<ffffffff81627e72>]
lockdep_copy_map include/linux/lockdep.h:175 [inline]
 #3:  (((&q->timer))){+.-...}, at: [<ffffffff81627e72>]
call_timer_fn+0x1c2/0x820 kernel/time/timer.c:1258
 #4:  (&(&q->lock)->rlock){+.-...}, at: [<ffffffff8389a4d1>] spin_lock
include/linux/spinlock.h:299 [inline]
 #4:  (&(&q->lock)->rlock){+.-...}, at: [<ffffffff8389a4d1>]
ip_expire+0x51/0x6c0 net/ipv4/ip_fragment.c:201
 #5:  (rcu_read_lock){......}, at: [<ffffffff8389a633>]
ip_expire+0x1b3/0x6c0 net/ipv4/ip_fragment.c:216
 #6:  (slock-AF_INET){+.-...}, at: [<ffffffff839b3313>] spin_trylock
include/linux/spinlock.h:309 [inline]
 #6:  (slock-AF_INET){+.-...}, at: [<ffffffff839b3313>] icmp_xmit_lock
net/ipv4/icmp.c:219 [inline]
 #6:  (slock-AF_INET){+.-...}, at: [<ffffffff839b3313>]
icmp_send+0x803/0x1c80 net/ipv4/icmp.c:681
 #7:  (rcu_read_lock_bh){......}, at: [<ffffffff838ab9a1>]
ip_finish_output2+0x2c1/0x15a0 net/ipv4/ip_output.c:198
 torvalds#8:  (rcu_read_lock_bh){......}, at: [<ffffffff836d1dee>]
__dev_queue_xmit+0x23e/0x1e60 net/core/dev.c:3324
 torvalds#9:  (dev->qdisc_running_key ?: &qdisc_running_key){+.....}, at:
[<ffffffff836d3a27>] dev_queue_xmit+0x17/0x20 net/core/dev.c:3423

stack backtrace:
CPU: 0 PID: 12392 Comm: modprobe Not tainted 4.10.0+ torvalds#29
Hardware name: Google Google Compute Engine/Google Compute Engine,
BIOS Google 01/01/2011
Call Trace:
 <IRQ>
 __dump_stack lib/dump_stack.c:16 [inline]
 dump_stack+0x2ee/0x3ef lib/dump_stack.c:52
 print_circular_bug+0x307/0x3b0 kernel/locking/lockdep.c:1204
 check_prev_add kernel/locking/lockdep.c:1830 [inline]
 check_prevs_add+0xa8f/0x19f0 kernel/locking/lockdep.c:1940
 validate_chain kernel/locking/lockdep.c:2267 [inline]
 __lock_acquire+0x2149/0x3430 kernel/locking/lockdep.c:3340
 lock_acquire+0x2a1/0x630 kernel/locking/lockdep.c:3755
 __raw_spin_lock include/linux/spinlock_api_smp.h:142 [inline]
 _raw_spin_lock+0x33/0x50 kernel/locking/spinlock.c:151
 spin_lock include/linux/spinlock.h:299 [inline]
 __netif_tx_lock include/linux/netdevice.h:3486 [inline]
 sch_direct_xmit+0x282/0x6d0 net/sched/sch_generic.c:180
 __dev_xmit_skb net/core/dev.c:3092 [inline]
 __dev_queue_xmit+0x13e5/0x1e60 net/core/dev.c:3358
 dev_queue_xmit+0x17/0x20 net/core/dev.c:3423
 neigh_hh_output include/net/neighbour.h:468 [inline]
 neigh_output include/net/neighbour.h:476 [inline]
 ip_finish_output2+0xf6c/0x15a0 net/ipv4/ip_output.c:228
 ip_finish_output+0xa29/0xe10 net/ipv4/ip_output.c:316
 NF_HOOK_COND include/linux/netfilter.h:246 [inline]
 ip_output+0x1f0/0x7a0 net/ipv4/ip_output.c:404
 dst_output include/net/dst.h:486 [inline]
 ip_local_out+0x95/0x170 net/ipv4/ip_output.c:124
 ip_send_skb+0x3c/0xc0 net/ipv4/ip_output.c:1492
 ip_push_pending_frames+0x64/0x80 net/ipv4/ip_output.c:1512
 icmp_push_reply+0x372/0x4d0 net/ipv4/icmp.c:394
 icmp_send+0x156c/0x1c80 net/ipv4/icmp.c:754
 ip_expire+0x40e/0x6c0 net/ipv4/ip_fragment.c:239
 call_timer_fn+0x241/0x820 kernel/time/timer.c:1268
 expire_timers kernel/time/timer.c:1307 [inline]
 __run_timers+0x960/0xcf0 kernel/time/timer.c:1601
 run_timer_softirq+0x21/0x80 kernel/time/timer.c:1614
 __do_softirq+0x31f/0xbe7 kernel/softirq.c:284
 invoke_softirq kernel/softirq.c:364 [inline]
 irq_exit+0x1cc/0x200 kernel/softirq.c:405
 exiting_irq arch/x86/include/asm/apic.h:657 [inline]
 smp_apic_timer_interrupt+0x76/0xa0 arch/x86/kernel/apic/apic.c:962
 apic_timer_interrupt+0x93/0xa0 arch/x86/entry/entry_64.S:707
RIP: 0010:__read_once_size include/linux/compiler.h:254 [inline]
RIP: 0010:atomic_read arch/x86/include/asm/atomic.h:26 [inline]
RIP: 0010:rcu_dynticks_curr_cpu_in_eqs kernel/rcu/tree.c:350 [inline]
RIP: 0010:__rcu_is_watching kernel/rcu/tree.c:1133 [inline]
RIP: 0010:rcu_is_watching+0x83/0x110 kernel/rcu/tree.c:1147
RSP: 0000:ffff8801c391f120 EFLAGS: 00000a03 ORIG_RAX: ffffffffffffff10
RAX: dffffc0000000000 RBX: ffff8801c391f148 RCX: 0000000000000000
RDX: 0000000000000000 RSI: 000055edd4374000 RDI: ffff8801dbe1ae0c
RBP: ffff8801c391f1a0 R08: 0000000000000002 R09: 0000000000000000
R10: dffffc0000000000 R11: 0000000000000002 R12: 1ffff10038723e25
R13: ffff8801dbe1ae00 R14: ffff8801c391f680 R15: dffffc0000000000
 </IRQ>
 rcu_read_lock_held+0x87/0xc0 kernel/rcu/update.c:293
 radix_tree_deref_slot include/linux/radix-tree.h:238 [inline]
 filemap_map_pages+0x6d4/0x1570 mm/filemap.c:2335
 do_fault_around mm/memory.c:3231 [inline]
 do_read_fault mm/memory.c:3265 [inline]
 do_fault+0xbd5/0x2080 mm/memory.c:3370
 handle_pte_fault mm/memory.c:3600 [inline]
 __handle_mm_fault+0x1062/0x2cb0 mm/memory.c:3714
 handle_mm_fault+0x1e2/0x480 mm/memory.c:3751
 __do_page_fault+0x4f6/0xb60 arch/x86/mm/fault.c:1397
 do_page_fault+0x54/0x70 arch/x86/mm/fault.c:1460
 page_fault+0x28/0x30 arch/x86/entry/entry_64.S:1011
RIP: 0033:0x7f83172f2786
RSP: 002b:00007fffe859ae80 EFLAGS: 00010293
RAX: 000055edd4373040 RBX: 00007f83175111c8 RCX: 000055edd4373238
RDX: 0000000000000000 RSI: 0000000000000000 RDI: 00007f8317510970
RBP: 00007fffe859afd0 R08: 0000000000000009 R09: 0000000000000000
R10: 0000000000000064 R11: 0000000000000000 R12: 000055edd4373040
R13: 0000000000000000 R14: 00007fffe859afe8 R15: 0000000000000000

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

mipsxx_pmu_handle_shared_irq() calls irq_work_run() while holding the
pmuint_rwlock for read.  irq_work_run() can, via perf_pending_event(),
call try_to_wake_up() which can try to take rq->lock.

However, perf can also call perf_pmu_enable() (and thus take the
pmuint_rwlock for write) while holding the rq->lock, from
finish_task_switch() via perf_event_context_sched_in().

This leads to an ABBA deadlock:

 PID: 3855   TASK: 8f7ce288  CPU: 2   COMMAND: "process"
  #0 [89c39ac8] __delay at 803b5be4
  #1 [89c39ac8] do_raw_spin_lock at 8008fdcc
  #2 [89c39af8] try_to_wake_up at 8006e47c
  #3 [89c39b38] pollwake at 8018eab0
  #4 [89c39b68] __wake_up_common at 800879f4
  #5 [89c39b98] __wake_up at 800880e4
  #6 [89c39bc8] perf_event_wakeup at 8012109c
  #7 [89c39be8] perf_pending_event at 80121184
  torvalds#8 [89c39c08] irq_work_run_list at 801151f0
  torvalds#9 [89c39c38] irq_work_run at 80115274
 torvalds#10 [89c39c50] mipsxx_pmu_handle_shared_irq at 8002cc7c

 PID: 1481   TASK: 8eaac6a8  CPU: 3   COMMAND: "process"
  #0 [8de7f900] do_raw_write_lock at 800900e0
  #1 [8de7f918] perf_event_context_sched_in at 80122310
  #2 [8de7f938] __perf_event_task_sched_in at 80122608
  #3 [8de7f958] finish_task_switch at 8006b8a4
  #4 [8de7f998] __schedule at 805e4dc4
  #5 [8de7f9f8] schedule at 805e5558
  #6 [8de7fa10] schedule_hrtimeout_range_clock at 805e9984
  #7 [8de7fa70] poll_schedule_timeout at 8018e8f8
  torvalds#8 [8de7fa88] do_select at 8018f338
  torvalds#9 [8de7fd88] core_sys_select at 8018f5cc
 torvalds#10 [8de7fee0] sys_select at 8018f854
 torvalds#11 [8de7ff28] syscall_common at 80028fc8

The lock seems to be there to protect the hardware counters so there is
no need to hold it across irq_work_run().

Signed-off-by: Rabin Vincent <rabinv@axis.com>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>

The driver with nvme had this routine stubbed.

Right now XRI_ABORTED_CQE is not handled and the FC NVMET
Transport has a new API for the driver.

Missing code path, new NVME abort API
Update ABORT processing for NVMET

There are 3 new FC NVMET Transport API/ template routines for NVMET:

lpfc_nvmet_xmt_fcp_release
This NVMET template callback routine called to release context
associated with an IO This routine is ALWAYS called last, even
if the IO was aborted or completed in error.

lpfc_nvmet_xmt_fcp_abort
This NVMET template callback routine called to abort an exchange that
has an IO in progress

nvmet_fc_rcv_fcp_req
When the lpfc driver receives an ABTS, this NVME FC transport layer
callback routine is called. For this case there are 2 paths thru the
driver: the driver either has an outstanding exchange / context for the
XRI to be aborted or not.  If not, a BA_RJT is issued otherwise a BA_ACC

NVMET Driver abort paths:

There are 2 paths for aborting an IO. The first one is we receive an IO and
decide not to process it because of lack of resources. An unsolicated ABTS
is immediately sent back to the initiator as a response.
lpfc_nvmet_unsol_fcp_buffer
            lpfc_nvmet_unsol_issue_abort  (XMIT_SEQUENCE_WQE)

The second one is we sent the IO up to the NVMET transport layer to
process, and for some reason the NVME Transport layer decided to abort the
IO before it completes all its phases. For this case there are 2 paths
thru the driver:
the driver either has an outstanding TSEND/TRECEIVE/TRSP WQE or no
outstanding WQEs are present for the exchange / context.
lpfc_nvmet_xmt_fcp_abort
    if (LPFC_NVMET_IO_INP)
        lpfc_nvmet_sol_fcp_issue_abort  (ABORT_WQE)
                lpfc_nvmet_sol_fcp_abort_cmp
    else
        lpfc_nvmet_unsol_fcp_issue_abort
                lpfc_nvmet_unsol_issue_abort  (XMIT_SEQUENCE_WQE)
                        lpfc_nvmet_unsol_fcp_abort_cmp

Context flags:
LPFC_NVMET_IOP - his flag signifies an IO is in progress on the exchange.
LPFC_NVMET_XBUSY  - this flag indicates the IO completed but the firmware
is still busy with the corresponding exchange. The exchange should not be
reused until after a XRI_ABORTED_CQE is received for that exchange.
LPFC_NVMET_ABORT_OP - this flag signifies an ABORT_WQE was issued on the
exchange.
LPFC_NVMET_CTX_RLS  - this flag signifies a context free was requested,
but we are deferring it due to an XBUSY or ABORT in progress.

A ctxlock is added to the context structure that is used whenever these
flags are set/read  within the context of an IO.
The LPFC_NVMET_CTX_RLS flag is only set in the defer_relase routine when
the transport has resolved all IO associated with the buffer. The flag is
cleared when the CTX is associated with a new IO.

An exchange can has both an LPFC_NVMET_XBUSY and a LPFC_NVMET_ABORT_OP
condition active simultaneously. Both conditions must complete before the
exchange is freed.
When the abort callback (lpfc_nvmet_xmt_fcp_abort) is envoked:
If there is an outstanding IO, the driver will issue an ABORT_WQE. This
should result in 3 completions for the exchange:
1) IO cmpl with XB bit set
2) Abort WQE cmpl
3) XRI_ABORTED_CQE cmpl
For this scenerio, after completion #1, the NVMET Transport IO rsp
callback is called.  After completion #2, no action is taken with respect
to the exchange / context.  After completion #3, the exchange context is
free for re-use on another IO.

If there is no outstanding activity on the exchange, the driver will send a
ABTS to the Initiator. Upon completion of this WQE, the exchange / context
is freed for re-use on another IO.

Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <james.smart@broadcom.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>

When the instruction right before the branch destination is
a 64 bit load immediate, we currently calculate the wrong
jump offset in the ctx->offset[] array as we only account
one instruction slot for the 64 bit load immediate although
it uses two BPF instructions. Fix it up by setting the offset
into the right slot after we incremented the index.

Before (ldimm64 test 1):

  [...]
  00000020:  52800007  mov w7, #0x0 // #0
  00000024:  d2800060  mov x0, #0x3 // tiwai#3
  00000028:  d2800041  mov x1, #0x2 // tiwai#2
  0000002c:  eb01001f  cmp x0, x1
  00000030:  54ffff82  b.cs 0x00000020
  00000034:  d29fffe7  mov x7, #0xffff // #65535
  00000038:  f2bfffe7  movk x7, #0xffff, lsl torvalds#16
  0000003c:  f2dfffe7  movk x7, #0xffff, lsl torvalds#32
  00000040:  f2ffffe7  movk x7, #0xffff, lsl torvalds#48
  00000044:  d29dddc7  mov x7, #0xeeee // #61166
  00000048:  f2bdddc7  movk x7, #0xeeee, lsl torvalds#16
  0000004c:  f2ddddc7  movk x7, #0xeeee, lsl torvalds#32
  00000050:  f2fdddc7  movk x7, #0xeeee, lsl torvalds#48
  [...]

After (ldimm64 test 1):

  [...]
  00000020:  52800007  mov w7, #0x0 // #0
  00000024:  d2800060  mov x0, #0x3 // tiwai#3
  00000028:  d2800041  mov x1, #0x2 // tiwai#2
  0000002c:  eb01001f  cmp x0, x1
  00000030:  540000a2  b.cs 0x00000044
  00000034:  d29fffe7  mov x7, #0xffff // #65535
  00000038:  f2bfffe7  movk x7, #0xffff, lsl torvalds#16
  0000003c:  f2dfffe7  movk x7, #0xffff, lsl torvalds#32
  00000040:  f2ffffe7  movk x7, #0xffff, lsl torvalds#48
  00000044:  d29dddc7  mov x7, #0xeeee // #61166
  00000048:  f2bdddc7  movk x7, #0xeeee, lsl torvalds#16
  0000004c:  f2ddddc7  movk x7, #0xeeee, lsl torvalds#32
  00000050:  f2fdddc7  movk x7, #0xeeee, lsl torvalds#48
  [...]

Also, add a couple of test cases to make sure JITs pass
this test. Tested on Cavium ThunderX ARMv8. The added
test cases all pass after the fix.

Fixes: 8eee539 ("arm64: bpf: fix out-of-bounds read in bpf2a64_offset()")
Reported-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Cc: Xi Wang <xi.wang@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Patch series "scope GFP_NOFS api", v5.

This patch (of 7):

Commit 21caf2f ("mm: teach mm by current context info to not do I/O
during memory allocation") added the memalloc_noio_(save|restore)
functions to enable people to modify the MM behavior by disabling I/O
during memory allocation.

This was further extended in commit 934f307 ("mm: clear __GFP_FS
when PF_MEMALLOC_NOIO is set").

memalloc_noio_* functions prevent allocation paths recursing back into
the filesystem without explicitly changing the flags for every
allocation site.

However, lockdep hasn't been keeping up with the changes and it entirely
misses handling the memalloc_noio adjustments.  Instead, it is left to
the callers of __lockdep_trace_alloc to call the function after they
have shaven the respective GFP flags which can lead to false positives:

  =================================
   [ INFO: inconsistent lock state ]
   4.10.0-nbor torvalds#134 Not tainted
   ---------------------------------
   inconsistent {IN-RECLAIM_FS-W} -> {RECLAIM_FS-ON-W} usage.
   fsstress/3365 [HC0[0]:SC0[0]:HE1:SE1] takes:
    (&xfs_nondir_ilock_class){++++?.}, at: xfs_ilock+0x141/0x230
   {IN-RECLAIM_FS-W} state was registered at:
     __lock_acquire+0x62a/0x17c0
     lock_acquire+0xc5/0x220
     down_write_nested+0x4f/0x90
     xfs_ilock+0x141/0x230
     xfs_reclaim_inode+0x12a/0x320
     xfs_reclaim_inodes_ag+0x2c8/0x4e0
     xfs_reclaim_inodes_nr+0x33/0x40
     xfs_fs_free_cached_objects+0x19/0x20
     super_cache_scan+0x191/0x1a0
     shrink_slab+0x26f/0x5f0
     shrink_node+0xf9/0x2f0
     kswapd+0x356/0x920
     kthread+0x10c/0x140
     ret_from_fork+0x31/0x40
   irq event stamp: 173777
   hardirqs last  enabled at (173777): __local_bh_enable_ip+0x70/0xc0
   hardirqs last disabled at (173775): __local_bh_enable_ip+0x37/0xc0
   softirqs last  enabled at (173776): _xfs_buf_find+0x67a/0xb70
   softirqs last disabled at (173774): _xfs_buf_find+0x5db/0xb70

   other info that might help us debug this:
    Possible unsafe locking scenario:

          CPU0
          ----
     lock(&xfs_nondir_ilock_class);
     <Interrupt>
       lock(&xfs_nondir_ilock_class);

    *** DEADLOCK ***

   4 locks held by fsstress/3365:
    #0:  (sb_writers#10){++++++}, at: mnt_want_write+0x24/0x50
    tiwai#1:  (&sb->s_type->i_mutex_key#12){++++++}, at: vfs_setxattr+0x6f/0xb0
    tiwai#2:  (sb_internal#2){++++++}, at: xfs_trans_alloc+0xfc/0x140
    tiwai#3:  (&xfs_nondir_ilock_class){++++?.}, at: xfs_ilock+0x141/0x230

   stack backtrace:
   CPU: 0 PID: 3365 Comm: fsstress Not tainted 4.10.0-nbor torvalds#134
   Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014
   Call Trace:
    kmem_cache_alloc_node_trace+0x3a/0x2c0
    vm_map_ram+0x2a1/0x510
    _xfs_buf_map_pages+0x77/0x140
    xfs_buf_get_map+0x185/0x2a0
    xfs_attr_rmtval_set+0x233/0x430
    xfs_attr_leaf_addname+0x2d2/0x500
    xfs_attr_set+0x214/0x420
    xfs_xattr_set+0x59/0xb0
    __vfs_setxattr+0x76/0xa0
    __vfs_setxattr_noperm+0x5e/0xf0
    vfs_setxattr+0xae/0xb0
    setxattr+0x15e/0x1a0
    path_setxattr+0x8f/0xc0
    SyS_lsetxattr+0x11/0x20
    entry_SYSCALL_64_fastpath+0x23/0xc6

Let's fix this by making lockdep explicitly do the shaving of respective
GFP flags.

Fixes: 934f307 ("mm: clear __GFP_FS when PF_MEMALLOC_NOIO is set")
Link: http://lkml.kernel.org/r/20170306131408.9828-2-mhocko@kernel.org
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Michal Hocko <mhocko@suse.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: Chris Mason <clm@fb.com>
Cc: David Sterba <dsterba@suse.cz>
Cc: Jan Kara <jack@suse.cz>
Cc: Brian Foster <bfoster@redhat.com>
Cc: Darrick J. Wong <darrick.wong@oracle.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

When tries to demote 1G hugetlb folios, a lockdep warning is observed:

============================================
WARNING: possible recursive locking detected
6.10.0-rc6-00452-ga4d0275fa660-dirty torvalds#79 Not tainted
--------------------------------------------
bash/710 is trying to acquire lock:
ffffffff8f0a7850 (&h->resize_lock){+.+.}-{3:3}, at: demote_store+0x244/0x460

but task is already holding lock:
ffffffff8f0a6f48 (&h->resize_lock){+.+.}-{3:3}, at: demote_store+0xae/0x460

other info that might help us debug this:
 Possible unsafe locking scenario:

       CPU0
       ----
  lock(&h->resize_lock);
  lock(&h->resize_lock);

 *** DEADLOCK ***

 May be due to missing lock nesting notation

4 locks held by bash/710:
 #0: ffff8f118439c3f0 (sb_writers#5){.+.+}-{0:0}, at: ksys_write+0x64/0xe0
 #1: ffff8f11893b9e88 (&of->mutex#2){+.+.}-{3:3}, at: kernfs_fop_write_iter+0xf8/0x1d0
 #2: ffff8f1183dc4428 (kn->active#98){.+.+}-{0:0}, at: kernfs_fop_write_iter+0x100/0x1d0
 #3: ffffffff8f0a6f48 (&h->resize_lock){+.+.}-{3:3}, at: demote_store+0xae/0x460

stack backtrace:
CPU: 3 PID: 710 Comm: bash Not tainted 6.10.0-rc6-00452-ga4d0275fa660-dirty torvalds#79
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014
Call Trace:
 <TASK>
 dump_stack_lvl+0x68/0xa0
 __lock_acquire+0x10f2/0x1ca0
 lock_acquire+0xbe/0x2d0
 __mutex_lock+0x6d/0x400
 demote_store+0x244/0x460
 kernfs_fop_write_iter+0x12c/0x1d0
 vfs_write+0x380/0x540
 ksys_write+0x64/0xe0
 do_syscall_64+0xb9/0x1d0
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7fa61db14887
RSP: 002b:00007ffc56c48358 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
RAX: ffffffffffffffda RBX: 0000000000000002 RCX: 00007fa61db14887
RDX: 0000000000000002 RSI: 000055a030050220 RDI: 0000000000000001
RBP: 000055a030050220 R08: 00007fa61dbd1460 R09: 000000007fffffff
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000002
R13: 00007fa61dc1b780 R14: 00007fa61dc17600 R15: 00007fa61dc16a00
 </TASK>

Lockdep considers this an AA deadlock because the different resize_lock
mutexes reside in the same lockdep class, but this is a false positive.
Place them in distinct classes to avoid these warnings.

Link: https://lkml.kernel.org/r/20240712031314.2570452-1-linmiaohe@huawei.com
Fixes: 8531fc6 ("hugetlb: add hugetlb demote page support")
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Acked-by: Muchun Song <muchun.song@linux.dev>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

When using cachefiles, lockdep may emit something similar to the circular
locking dependency notice below.  The problem appears to stem from the
following:

 (1) Cachefiles manipulates xattrs on the files in its cache when called
     from ->writepages().

 (2) The setxattr() and removexattr() system call handlers get the name
     (and value) from userspace after taking the sb_writers lock, putting
     accesses of the vma->vm_lock and mm->mmap_lock inside of that.

 (3) The afs filesystem uses a per-inode lock to prevent multiple
     revalidation RPCs and in writeback vs truncate to prevent parallel
     operations from deadlocking against the server on one side and local
     page locks on the other.

Fix this by moving the getting of the name and value in {get,remove}xattr()
outside of the sb_writers lock.  This also has the minor benefits that we
don't need to reget these in the event of a retry and we never try to take
the sb_writers lock in the event we can't pull the name and value into the
kernel.

Alternative approaches that might fix this include moving the dispatch of a
write to the cache off to a workqueue or trying to do without the
validation lock in afs.  Note that this might also affect other filesystems
that use netfslib and/or cachefiles.

 ======================================================
 WARNING: possible circular locking dependency detected
 6.10.0-build2+ torvalds#956 Not tainted
 ------------------------------------------------------
 fsstress/6050 is trying to acquire lock:
 ffff888138fd82f0 (mapping.invalidate_lock#3){++++}-{3:3}, at: filemap_fault+0x26e/0x8b0

 but task is already holding lock:
 ffff888113f26d18 (&vma->vm_lock->lock){++++}-{3:3}, at: lock_vma_under_rcu+0x165/0x250

 which lock already depends on the new lock.

 the existing dependency chain (in reverse order) is:

 -> #4 (&vma->vm_lock->lock){++++}-{3:3}:
        __lock_acquire+0xaf0/0xd80
        lock_acquire.part.0+0x103/0x280
        down_write+0x3b/0x50
        vma_start_write+0x6b/0xa0
        vma_link+0xcc/0x140
        insert_vm_struct+0xb7/0xf0
        alloc_bprm+0x2c1/0x390
        kernel_execve+0x65/0x1a0
        call_usermodehelper_exec_async+0x14d/0x190
        ret_from_fork+0x24/0x40
        ret_from_fork_asm+0x1a/0x30

 -> #3 (&mm->mmap_lock){++++}-{3:3}:
        __lock_acquire+0xaf0/0xd80
        lock_acquire.part.0+0x103/0x280
        __might_fault+0x7c/0xb0
        strncpy_from_user+0x25/0x160
        removexattr+0x7f/0x100
        __do_sys_fremovexattr+0x7e/0xb0
        do_syscall_64+0x9f/0x100
        entry_SYSCALL_64_after_hwframe+0x76/0x7e

 -> #2 (sb_writers#14){.+.+}-{0:0}:
        __lock_acquire+0xaf0/0xd80
        lock_acquire.part.0+0x103/0x280
        percpu_down_read+0x3c/0x90
        vfs_iocb_iter_write+0xe9/0x1d0
        __cachefiles_write+0x367/0x430
        cachefiles_issue_write+0x299/0x2f0
        netfs_advance_write+0x117/0x140
        netfs_write_folio.isra.0+0x5ca/0x6e0
        netfs_writepages+0x230/0x2f0
        afs_writepages+0x4d/0x70
        do_writepages+0x1e8/0x3e0
        filemap_fdatawrite_wbc+0x84/0xa0
        __filemap_fdatawrite_range+0xa8/0xf0
        file_write_and_wait_range+0x59/0x90
        afs_release+0x10f/0x270
        __fput+0x25f/0x3d0
        __do_sys_close+0x43/0x70
        do_syscall_64+0x9f/0x100
        entry_SYSCALL_64_after_hwframe+0x76/0x7e

 -> #1 (&vnode->validate_lock){++++}-{3:3}:
        __lock_acquire+0xaf0/0xd80
        lock_acquire.part.0+0x103/0x280
        down_read+0x95/0x200
        afs_writepages+0x37/0x70
        do_writepages+0x1e8/0x3e0
        filemap_fdatawrite_wbc+0x84/0xa0
        filemap_invalidate_inode+0x167/0x1e0
        netfs_unbuffered_write_iter+0x1bd/0x2d0
        vfs_write+0x22e/0x320
        ksys_write+0xbc/0x130
        do_syscall_64+0x9f/0x100
        entry_SYSCALL_64_after_hwframe+0x76/0x7e

 -> #0 (mapping.invalidate_lock#3){++++}-{3:3}:
        check_noncircular+0x119/0x160
        check_prev_add+0x195/0x430
        __lock_acquire+0xaf0/0xd80
        lock_acquire.part.0+0x103/0x280
        down_read+0x95/0x200
        filemap_fault+0x26e/0x8b0
        __do_fault+0x57/0xd0
        do_pte_missing+0x23b/0x320
        __handle_mm_fault+0x2d4/0x320
        handle_mm_fault+0x14f/0x260
        do_user_addr_fault+0x2a2/0x500
        exc_page_fault+0x71/0x90
        asm_exc_page_fault+0x22/0x30

 other info that might help us debug this:

 Chain exists of:
   mapping.invalidate_lock#3 --> &mm->mmap_lock --> &vma->vm_lock->lock

  Possible unsafe locking scenario:

        CPU0                    CPU1
        ----                    ----
   rlock(&vma->vm_lock->lock);
                                lock(&mm->mmap_lock);
                                lock(&vma->vm_lock->lock);
   rlock(mapping.invalidate_lock#3);

  *** DEADLOCK ***

 1 lock held by fsstress/6050:
  #0: ffff888113f26d18 (&vma->vm_lock->lock){++++}-{3:3}, at: lock_vma_under_rcu+0x165/0x250

 stack backtrace:
 CPU: 0 PID: 6050 Comm: fsstress Not tainted 6.10.0-build2+ torvalds#956
 Hardware name: ASUS All Series/H97-PLUS, BIOS 2306 10/09/2014
 Call Trace:
  <TASK>
  dump_stack_lvl+0x57/0x80
  check_noncircular+0x119/0x160
  ? queued_spin_lock_slowpath+0x4be/0x510
  ? __pfx_check_noncircular+0x10/0x10
  ? __pfx_queued_spin_lock_slowpath+0x10/0x10
  ? mark_lock+0x47/0x160
  ? init_chain_block+0x9c/0xc0
  ? add_chain_block+0x84/0xf0
  check_prev_add+0x195/0x430
  __lock_acquire+0xaf0/0xd80
  ? __pfx___lock_acquire+0x10/0x10
  ? __lock_release.isra.0+0x13b/0x230
  lock_acquire.part.0+0x103/0x280
  ? filemap_fault+0x26e/0x8b0
  ? __pfx_lock_acquire.part.0+0x10/0x10
  ? rcu_is_watching+0x34/0x60
  ? lock_acquire+0xd7/0x120
  down_read+0x95/0x200
  ? filemap_fault+0x26e/0x8b0
  ? __pfx_down_read+0x10/0x10
  ? __filemap_get_folio+0x25/0x1a0
  filemap_fault+0x26e/0x8b0
  ? __pfx_filemap_fault+0x10/0x10
  ? find_held_lock+0x7c/0x90
  ? __pfx___lock_release.isra.0+0x10/0x10
  ? __pte_offset_map+0x99/0x110
  __do_fault+0x57/0xd0
  do_pte_missing+0x23b/0x320
  __handle_mm_fault+0x2d4/0x320
  ? __pfx___handle_mm_fault+0x10/0x10
  handle_mm_fault+0x14f/0x260
  do_user_addr_fault+0x2a2/0x500
  exc_page_fault+0x71/0x90
  asm_exc_page_fault+0x22/0x30

Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://lore.kernel.org/r/2136178.1721725194@warthog.procyon.org.uk
cc: Alexander Viro <viro@zeniv.linux.org.uk>
cc: Christian Brauner <brauner@kernel.org>
cc: Jan Kara <jack@suse.cz>
cc: Jeff Layton <jlayton@kernel.org>
cc: Gao Xiang <xiang@kernel.org>
cc: Matthew Wilcox <willy@infradead.org>
cc: netfs@lists.linux.dev
cc: linux-erofs@lists.ozlabs.org
cc: linux-fsdevel@vger.kernel.org
[brauner: fix minor issues]
Signed-off-by: Christian Brauner <brauner@kernel.org>

When l2tp tunnels use a socket provided by userspace, we can hit
lockdep splats like the below when data is transmitted through another
(unrelated) userspace socket which then gets routed over l2tp.

This issue was previously discussed here:
https://lore.kernel.org/netdev/87sfialu2n.fsf@cloudflare.com/

The solution is to have lockdep treat socket locks of l2tp tunnel
sockets separately than those of standard INET sockets. To do so, use
a different lockdep subclass where lock nesting is possible.

  ============================================
  WARNING: possible recursive locking detected
  6.10.0+ torvalds#34 Not tainted
  --------------------------------------------
  iperf3/771 is trying to acquire lock:
  ffff8881027601d8 (slock-AF_INET/1){+.-.}-{2:2}, at: l2tp_xmit_skb+0x243/0x9d0

  but task is already holding lock:
  ffff888102650d98 (slock-AF_INET/1){+.-.}-{2:2}, at: tcp_v4_rcv+0x1848/0x1e10

  other info that might help us debug this:
   Possible unsafe locking scenario:

         CPU0
         ----
    lock(slock-AF_INET/1);
    lock(slock-AF_INET/1);

   *** DEADLOCK ***

   May be due to missing lock nesting notation

  10 locks held by iperf3/771:
   #0: ffff888102650258 (sk_lock-AF_INET){+.+.}-{0:0}, at: tcp_sendmsg+0x1a/0x40
   #1: ffffffff822ac220 (rcu_read_lock){....}-{1:2}, at: __ip_queue_xmit+0x4b/0xbc0
   #2: ffffffff822ac220 (rcu_read_lock){....}-{1:2}, at: ip_finish_output2+0x17a/0x1130
   #3: ffffffff822ac220 (rcu_read_lock){....}-{1:2}, at: process_backlog+0x28b/0x9f0
   #4: ffffffff822ac220 (rcu_read_lock){....}-{1:2}, at: ip_local_deliver_finish+0xf9/0x260
   #5: ffff888102650d98 (slock-AF_INET/1){+.-.}-{2:2}, at: tcp_v4_rcv+0x1848/0x1e10
   #6: ffffffff822ac220 (rcu_read_lock){....}-{1:2}, at: __ip_queue_xmit+0x4b/0xbc0
   #7: ffffffff822ac220 (rcu_read_lock){....}-{1:2}, at: ip_finish_output2+0x17a/0x1130
   torvalds#8: ffffffff822ac1e0 (rcu_read_lock_bh){....}-{1:2}, at: __dev_queue_xmit+0xcc/0x1450
   torvalds#9: ffff888101f33258 (dev->qdisc_tx_busylock ?: &qdisc_tx_busylock#2){+...}-{2:2}, at: __dev_queue_xmit+0x513/0x1450

  stack backtrace:
  CPU: 2 UID: 0 PID: 771 Comm: iperf3 Not tainted 6.10.0+ torvalds#34
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014
  Call Trace:
   <IRQ>
   dump_stack_lvl+0x69/0xa0
   dump_stack+0xc/0x20
   __lock_acquire+0x135d/0x2600
   ? srso_alias_return_thunk+0x5/0xfbef5
   lock_acquire+0xc4/0x2a0
   ? l2tp_xmit_skb+0x243/0x9d0
   ? __skb_checksum+0xa3/0x540
   _raw_spin_lock_nested+0x35/0x50
   ? l2tp_xmit_skb+0x243/0x9d0
   l2tp_xmit_skb+0x243/0x9d0
   l2tp_eth_dev_xmit+0x3c/0xc0
   dev_hard_start_xmit+0x11e/0x420
   sch_direct_xmit+0xc3/0x640
   __dev_queue_xmit+0x61c/0x1450
   ? ip_finish_output2+0xf4c/0x1130
   ip_finish_output2+0x6b6/0x1130
   ? srso_alias_return_thunk+0x5/0xfbef5
   ? __ip_finish_output+0x217/0x380
   ? srso_alias_return_thunk+0x5/0xfbef5
   __ip_finish_output+0x217/0x380
   ip_output+0x99/0x120
   __ip_queue_xmit+0xae4/0xbc0
   ? srso_alias_return_thunk+0x5/0xfbef5
   ? srso_alias_return_thunk+0x5/0xfbef5
   ? tcp_options_write.constprop.0+0xcb/0x3e0
   ip_queue_xmit+0x34/0x40
   __tcp_transmit_skb+0x1625/0x1890
   __tcp_send_ack+0x1b8/0x340
   tcp_send_ack+0x23/0x30
   __tcp_ack_snd_check+0xa8/0x530
   ? srso_alias_return_thunk+0x5/0xfbef5
   tcp_rcv_established+0x412/0xd70
   tcp_v4_do_rcv+0x299/0x420
   tcp_v4_rcv+0x1991/0x1e10
   ip_protocol_deliver_rcu+0x50/0x220
   ip_local_deliver_finish+0x158/0x260
   ip_local_deliver+0xc8/0xe0
   ip_rcv+0xe5/0x1d0
   ? __pfx_ip_rcv+0x10/0x10
   __netif_receive_skb_one_core+0xce/0xe0
   ? process_backlog+0x28b/0x9f0
   __netif_receive_skb+0x34/0xd0
   ? process_backlog+0x28b/0x9f0
   process_backlog+0x2cb/0x9f0
   __napi_poll.constprop.0+0x61/0x280
   net_rx_action+0x332/0x670
   ? srso_alias_return_thunk+0x5/0xfbef5
   ? find_held_lock+0x2b/0x80
   ? srso_alias_return_thunk+0x5/0xfbef5
   ? srso_alias_return_thunk+0x5/0xfbef5
   handle_softirqs+0xda/0x480
   ? __dev_queue_xmit+0xa2c/0x1450
   do_softirq+0xa1/0xd0
   </IRQ>
   <TASK>
   __local_bh_enable_ip+0xc8/0xe0
   ? __dev_queue_xmit+0xa2c/0x1450
   __dev_queue_xmit+0xa48/0x1450
   ? ip_finish_output2+0xf4c/0x1130
   ip_finish_output2+0x6b6/0x1130
   ? srso_alias_return_thunk+0x5/0xfbef5
   ? __ip_finish_output+0x217/0x380
   ? srso_alias_return_thunk+0x5/0xfbef5
   __ip_finish_output+0x217/0x380
   ip_output+0x99/0x120
   __ip_queue_xmit+0xae4/0xbc0
   ? srso_alias_return_thunk+0x5/0xfbef5
   ? srso_alias_return_thunk+0x5/0xfbef5
   ? tcp_options_write.constprop.0+0xcb/0x3e0
   ip_queue_xmit+0x34/0x40
   __tcp_transmit_skb+0x1625/0x1890
   tcp_write_xmit+0x766/0x2fb0
   ? __entry_text_end+0x102ba9/0x102bad
   ? srso_alias_return_thunk+0x5/0xfbef5
   ? __might_fault+0x74/0xc0
   ? srso_alias_return_thunk+0x5/0xfbef5
   __tcp_push_pending_frames+0x56/0x190
   tcp_push+0x117/0x310
   tcp_sendmsg_locked+0x14c1/0x1740
   tcp_sendmsg+0x28/0x40
   inet_sendmsg+0x5d/0x90
   sock_write_iter+0x242/0x2b0
   vfs_write+0x68d/0x800
   ? __pfx_sock_write_iter+0x10/0x10
   ksys_write+0xc8/0xf0
   __x64_sys_write+0x3d/0x50
   x64_sys_call+0xfaf/0x1f50
   do_syscall_64+0x6d/0x140
   entry_SYSCALL_64_after_hwframe+0x76/0x7e
  RIP: 0033:0x7f4d143af992
  Code: c3 8b 07 85 c0 75 24 49 89 fb 48 89 f0 48 89 d7 48 89 ce 4c 89 c2 4d 89 ca 4c 8b 44 24 08 4c 8b 4c 24 10 4c 89 5c 24 08 0f 05 <c3> e9 01 cc ff ff 41 54 b8 02 00 00 0
  RSP: 002b:00007ffd65032058 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
  RAX: ffffffffffffffda RBX: 0000000000000001 RCX: 00007f4d143af992
  RDX: 0000000000000025 RSI: 00007f4d143f3bcc RDI: 0000000000000005
  RBP: 00007f4d143f2b28 R08: 0000000000000000 R09: 0000000000000000
  R10: 0000000000000000 R11: 0000000000000246 R12: 00007f4d143f3bcc
  R13: 0000000000000005 R14: 0000000000000000 R15: 00007ffd650323f0
   </TASK>

Fixes: 0b2c597 ("l2tp: close all race conditions in l2tp_tunnel_register()")
Suggested-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot+6acef9e0a4d1f46c83d4@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=6acef9e0a4d1f46c83d4
CC: gnault@redhat.com
CC: cong.wang@bytedance.com
Signed-off-by: James Chapman <jchapman@katalix.com>
Signed-off-by: Tom Parkin <tparkin@katalix.com>
Link: https://patch.msgid.link/20240806160626.1248317-1-jchapman@katalix.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

Lockdep reported a warning in Linux version 6.6:

[  414.344659] ================================
[  414.345155] WARNING: inconsistent lock state
[  414.345658] 6.6.0-07439-gba2303cacfda #6 Not tainted
[  414.346221] --------------------------------
[  414.346712] inconsistent {IN-SOFTIRQ-W} -> {SOFTIRQ-ON-W} usage.
[  414.347545] kworker/u10:3/1152 [HC0[0]:SC0[0]:HE0:SE1] takes:
[  414.349245] ffff88810edd1098 (&sbq->ws[i].wait){+.?.}-{2:2}, at: blk_mq_dispatch_rq_list+0x131c/0x1ee0
[  414.351204] {IN-SOFTIRQ-W} state was registered at:
[  414.351751]   lock_acquire+0x18d/0x460
[  414.352218]   _raw_spin_lock_irqsave+0x39/0x60
[  414.352769]   __wake_up_common_lock+0x22/0x60
[  414.353289]   sbitmap_queue_wake_up+0x375/0x4f0
[  414.353829]   sbitmap_queue_clear+0xdd/0x270
[  414.354338]   blk_mq_put_tag+0xdf/0x170
[  414.354807]   __blk_mq_free_request+0x381/0x4d0
[  414.355335]   blk_mq_free_request+0x28b/0x3e0
[  414.355847]   __blk_mq_end_request+0x242/0xc30
[  414.356367]   scsi_end_request+0x2c1/0x830
[  414.345155] WARNING: inconsistent lock state
[  414.345658] 6.6.0-07439-gba2303cacfda #6 Not tainted
[  414.346221] --------------------------------
[  414.346712] inconsistent {IN-SOFTIRQ-W} -> {SOFTIRQ-ON-W} usage.
[  414.347545] kworker/u10:3/1152 [HC0[0]:SC0[0]:HE0:SE1] takes:
[  414.349245] ffff88810edd1098 (&sbq->ws[i].wait){+.?.}-{2:2}, at: blk_mq_dispatch_rq_list+0x131c/0x1ee0
[  414.351204] {IN-SOFTIRQ-W} state was registered at:
[  414.351751]   lock_acquire+0x18d/0x460
[  414.352218]   _raw_spin_lock_irqsave+0x39/0x60
[  414.352769]   __wake_up_common_lock+0x22/0x60
[  414.353289]   sbitmap_queue_wake_up+0x375/0x4f0
[  414.353829]   sbitmap_queue_clear+0xdd/0x270
[  414.354338]   blk_mq_put_tag+0xdf/0x170
[  414.354807]   __blk_mq_free_request+0x381/0x4d0
[  414.355335]   blk_mq_free_request+0x28b/0x3e0
[  414.355847]   __blk_mq_end_request+0x242/0xc30
[  414.356367]   scsi_end_request+0x2c1/0x830
[  414.356863]   scsi_io_completion+0x177/0x1610
[  414.357379]   scsi_complete+0x12f/0x260
[  414.357856]   blk_complete_reqs+0xba/0xf0
[  414.358338]   __do_softirq+0x1b0/0x7a2
[  414.358796]   irq_exit_rcu+0x14b/0x1a0
[  414.359262]   sysvec_call_function_single+0xaf/0xc0
[  414.359828]   asm_sysvec_call_function_single+0x1a/0x20
[  414.360426]   default_idle+0x1e/0x30
[  414.360873]   default_idle_call+0x9b/0x1f0
[  414.361390]   do_idle+0x2d2/0x3e0
[  414.361819]   cpu_startup_entry+0x55/0x60
[  414.362314]   start_secondary+0x235/0x2b0
[  414.362809]   secondary_startup_64_no_verify+0x18f/0x19b
[  414.363413] irq event stamp: 428794
[  414.363825] hardirqs last  enabled at (428793): [<ffffffff816bfd1c>] ktime_get+0x1dc/0x200
[  414.364694] hardirqs last disabled at (428794): [<ffffffff85470177>] _raw_spin_lock_irq+0x47/0x50
[  414.365629] softirqs last  enabled at (428444): [<ffffffff85474780>] __do_softirq+0x540/0x7a2
[  414.366522] softirqs last disabled at (428419): [<ffffffff813f65ab>] irq_exit_rcu+0x14b/0x1a0
[  414.367425]
               other info that might help us debug this:
[  414.368194]  Possible unsafe locking scenario:
[  414.368900]        CPU0
[  414.369225]        ----
[  414.369548]   lock(&sbq->ws[i].wait);
[  414.370000]   <Interrupt>
[  414.370342]     lock(&sbq->ws[i].wait);
[  414.370802]
                *** DEADLOCK ***
[  414.371569] 5 locks held by kworker/u10:3/1152:
[  414.372088]  #0: ffff88810130e938 ((wq_completion)writeback){+.+.}-{0:0}, at: process_scheduled_works+0x357/0x13f0
[  414.373180]  #1: ffff88810201fdb8 ((work_completion)(&(&wb->dwork)->work)){+.+.}-{0:0}, at: process_scheduled_works+0x3a3/0x13f0
[  414.374384]  #2: ffffffff86ffbdc0 (rcu_read_lock){....}-{1:2}, at: blk_mq_run_hw_queue+0x637/0xa00
[  414.375342]  #3: ffff88810edd1098 (&sbq->ws[i].wait){+.?.}-{2:2}, at: blk_mq_dispatch_rq_list+0x131c/0x1ee0
[  414.376377]  #4: ffff888106205a08 (&hctx->dispatch_wait_lock){+.-.}-{2:2}, at: blk_mq_dispatch_rq_list+0x1337/0x1ee0
[  414.378607]
               stack backtrace:
[  414.379177] CPU: 0 PID: 1152 Comm: kworker/u10:3 Not tainted 6.6.0-07439-gba2303cacfda #6
[  414.380032] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014
[  414.381177] Workqueue: writeback wb_workfn (flush-253:0)
[  414.381805] Call Trace:
[  414.382136]  <TASK>
[  414.382429]  dump_stack_lvl+0x91/0xf0
[  414.382884]  mark_lock_irq+0xb3b/0x1260
[  414.383367]  ? __pfx_mark_lock_irq+0x10/0x10
[  414.383889]  ? stack_trace_save+0x8e/0xc0
[  414.384373]  ? __pfx_stack_trace_save+0x10/0x10
[  414.384903]  ? graph_lock+0xcf/0x410
[  414.385350]  ? save_trace+0x3d/0xc70
[  414.385808]  mark_lock.part.20+0x56d/0xa90
[  414.386317]  mark_held_locks+0xb0/0x110
[  414.386791]  ? __pfx_do_raw_spin_lock+0x10/0x10
[  414.387320]  lockdep_hardirqs_on_prepare+0x297/0x3f0
[  414.387901]  ? _raw_spin_unlock_irq+0x28/0x50
[  414.388422]  trace_hardirqs_on+0x58/0x100
[  414.388917]  _raw_spin_unlock_irq+0x28/0x50
[  414.389422]  __blk_mq_tag_busy+0x1d6/0x2a0
[  414.389920]  __blk_mq_get_driver_tag+0x761/0x9f0
[  414.390899]  blk_mq_dispatch_rq_list+0x1780/0x1ee0
[  414.391473]  ? __pfx_blk_mq_dispatch_rq_list+0x10/0x10
[  414.392070]  ? sbitmap_get+0x2b8/0x450
[  414.392533]  ? __blk_mq_get_driver_tag+0x210/0x9f0
[  414.393095]  __blk_mq_sched_dispatch_requests+0xd99/0x1690
[  414.393730]  ? elv_attempt_insert_merge+0x1b1/0x420
[  414.394302]  ? __pfx___blk_mq_sched_dispatch_requests+0x10/0x10
[  414.394970]  ? lock_acquire+0x18d/0x460
[  414.395456]  ? blk_mq_run_hw_queue+0x637/0xa00
[  414.395986]  ? __pfx_lock_acquire+0x10/0x10
[  414.396499]  blk_mq_sched_dispatch_requests+0x109/0x190
[  414.397100]  blk_mq_run_hw_queue+0x66e/0xa00
[  414.397616]  blk_mq_flush_plug_list.part.17+0x614/0x2030
[  414.398244]  ? __pfx_blk_mq_flush_plug_list.part.17+0x10/0x10
[  414.398897]  ? writeback_sb_inodes+0x241/0xcc0
[  414.399429]  blk_mq_flush_plug_list+0x65/0x80
[  414.399957]  __blk_flush_plug+0x2f1/0x530
[  414.400458]  ? __pfx___blk_flush_plug+0x10/0x10
[  414.400999]  blk_finish_plug+0x59/0xa0
[  414.401467]  wb_writeback+0x7cc/0x920
[  414.401935]  ? __pfx_wb_writeback+0x10/0x10
[  414.402442]  ? mark_held_locks+0xb0/0x110
[  414.402931]  ? __pfx_do_raw_spin_lock+0x10/0x10
[  414.403462]  ? lockdep_hardirqs_on_prepare+0x297/0x3f0
[  414.404062]  wb_workfn+0x2b3/0xcf0
[  414.404500]  ? __pfx_wb_workfn+0x10/0x10
[  414.404989]  process_scheduled_works+0x432/0x13f0
[  414.405546]  ? __pfx_process_scheduled_works+0x10/0x10
[  414.406139]  ? do_raw_spin_lock+0x101/0x2a0
[  414.406641]  ? assign_work+0x19b/0x240
[  414.407106]  ? lock_is_held_type+0x9d/0x110
[  414.407604]  worker_thread+0x6f2/0x1160
[  414.408075]  ? __kthread_parkme+0x62/0x210
[  414.408572]  ? lockdep_hardirqs_on_prepare+0x297/0x3f0
[  414.409168]  ? __kthread_parkme+0x13c/0x210
[  414.409678]  ? __pfx_worker_thread+0x10/0x10
[  414.410191]  kthread+0x33c/0x440
[  414.410602]  ? __pfx_kthread+0x10/0x10
[  414.411068]  ret_from_fork+0x4d/0x80
[  414.411526]  ? __pfx_kthread+0x10/0x10
[  414.411993]  ret_from_fork_asm+0x1b/0x30
[  414.412489]  </TASK>

When interrupt is turned on while a lock holding by spin_lock_irq it
throws a warning because of potential deadlock.

blk_mq_prep_dispatch_rq
 blk_mq_get_driver_tag
  __blk_mq_get_driver_tag
   __blk_mq_alloc_driver_tag
    blk_mq_tag_busy -> tag is already busy
    // failed to get driver tag
 blk_mq_mark_tag_wait
  spin_lock_irq(&wq->lock) -> lock A (&sbq->ws[i].wait)
  __add_wait_queue(wq, wait) -> wait queue active
  blk_mq_get_driver_tag
  __blk_mq_tag_busy
-> 1) tag must be idle, which means there can't be inflight IO
   spin_lock_irq(&tags->lock) -> lock B (hctx->tags)
   spin_unlock_irq(&tags->lock) -> unlock B, turn on interrupt accidentally
-> 2) context must be preempt by IO interrupt to trigger deadlock.

As shown above, the deadlock is not possible in theory, but the warning
still need to be fixed.

Fix it by using spin_lock_irqsave to get lockB instead of spin_lock_irq.

Fixes: 4f1731d ("blk-mq: fix potential io hang by wrong 'wake_batch'")
Signed-off-by: Li Lingfeng <lilingfeng3@huawei.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Yu Kuai <yukuai3@huawei.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20240815024736.2040971-1-lilingfeng@huaweicloud.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

…git/netfilter/nf

Pablo Neira Ayuso says:

====================
Netfilter fixes for net

The following patchset contains Netfilter fixes for net:

Patch #1 disable BH when collecting stats via hardware offload to ensure
         concurrent updates from packet path do not result in losing stats.
         From Sebastian Andrzej Siewior.

Patch #2 uses write seqcount to reset counters serialize against reader.
         Also from Sebastian Andrzej Siewior.

Patch #3 ensures vlan header is in place before accessing its fields,
         according to KMSAN splat triggered by syzbot.

* tag 'nf-24-08-22' of git://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf:
  netfilter: flowtable: validate vlan header
  netfilter: nft_counter: Synchronize nft_counter_reset() against reader.
  netfilter: nft_counter: Disable BH in nft_counter_offload_stats().
====================

Link: https://patch.msgid.link/20240822101842.4234-1-pablo@netfilter.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

…git/netfilter/nf

Pablo Neira Ayuso says:

====================
Netfilter fixes for net

v2: with kdoc fixes per Paolo Abeni.

The following patchset contains Netfilter fixes for net:

Patch #1 and #2 handle an esoteric scenario: Given two tasks sending UDP
packets to one another, two packets of the same flow in each direction
handled by different CPUs that result in two conntrack objects in NEW
state, where reply packet loses race. Then, patch #3 adds a testcase for
this scenario. Series from Florian Westphal.

1) NAT engine can falsely detect a port collision if it happens to pick
   up a reply packet as NEW rather than ESTABLISHED. Add extra code to
   detect this and suppress port reallocation in this case.

2) To complete the clash resolution in the reply direction, extend conntrack
   logic to detect clashing conntrack in the reply direction to existing entry.

3) Adds a test case.

Then, an assorted list of fixes follow:

4) Add a selftest for tproxy, from Antonio Ojea.

5) Guard ctnetlink_*_size() functions under
   #if defined(CONFIG_NETFILTER_NETLINK_GLUE_CT) || defined(CONFIG_NF_CONNTRACK_EVENTS)
   From Andy Shevchenko.

6) Use -m socket --transparent in iptables tproxy documentation.
   From XIE Zhibang.

7) Call kfree_rcu() when releasing flowtable hooks to address race with
   netlink dump path, from Phil Sutter.

8) Fix compilation warning in nf_reject with CONFIG_BRIDGE_NETFILTER=n.
   From Simon Horman.

9) Guard ctnetlink_label_size() under CONFIG_NF_CONNTRACK_EVENTS which
   is its only user, to address a compilation warning. From Simon Horman.

10) Use rcu-protected list iteration over basechain hooks from netlink
    dump path.

11) Fix memcg for nf_tables, use GFP_KERNEL_ACCOUNT is not complete.

12) Remove old nfqueue conntrack clash resolution. Instead trying to
    use same destination address consistently which requires double DNAT,
    use the existing clash resolution which allows clashing packets
    go through with different destination. Antonio Ojea originally
    reported an issue from the postrouting chain, I proposed a fix:
    https://lore.kernel.org/netfilter-devel/ZuwSwAqKgCB2a51-@calendula/T/
    which he reported it did not work for him.

13) Adds a selftest for patch 12.

14) Fixes ipvs.sh selftest.

netfilter pull request 24-09-26

* tag 'nf-24-09-26' of git://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf:
  selftests: netfilter: Avoid hanging ipvs.sh
  kselftest: add test for nfqueue induced conntrack race
  netfilter: nfnetlink_queue: remove old clash resolution logic
  netfilter: nf_tables: missing objects with no memcg accounting
  netfilter: nf_tables: use rcu chain hook list iterator from netlink dump path
  netfilter: ctnetlink: compile ctnetlink_label_size with CONFIG_NF_CONNTRACK_EVENTS
  netfilter: nf_reject: Fix build warning when CONFIG_BRIDGE_NETFILTER=n
  netfilter: nf_tables: Keep deleted flowtable hooks until after RCU
  docs: tproxy: ignore non-transparent sockets in iptables
  netfilter: ctnetlink: Guard possible unused functions
  selftests: netfilter: nft_tproxy.sh: add tcp tests
  selftests: netfilter: add reverse-clash resolution test case
  netfilter: conntrack: add clash resolution for reverse collisions
  netfilter: nf_nat: don't try nat source port reallocation for reverse dir clash
====================

Link: https://patch.msgid.link/20240926110717.102194-1-pablo@netfilter.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

On the node of an NFS client, some files saved in the mountpoint of the
NFS server were copied to another location of the same NFS server.
Accidentally, the nfs42_complete_copies() got a NULL-pointer dereference
crash with the following syslog:

[232064.838881] NFSv4: state recovery failed for open file nfs/pvc-12b5200d-cd0f-46a3-b9f0-af8f4fe0ef64.qcow2, error = -116
[232064.839360] NFSv4: state recovery failed for open file nfs/pvc-12b5200d-cd0f-46a3-b9f0-af8f4fe0ef64.qcow2, error = -116
[232066.588183] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000058
[232066.588586] Mem abort info:
[232066.588701]   ESR = 0x0000000096000007
[232066.588862]   EC = 0x25: DABT (current EL), IL = 32 bits
[232066.589084]   SET = 0, FnV = 0
[232066.589216]   EA = 0, S1PTW = 0
[232066.589340]   FSC = 0x07: level 3 translation fault
[232066.589559] Data abort info:
[232066.589683]   ISV = 0, ISS = 0x00000007
[232066.589842]   CM = 0, WnR = 0
[232066.589967] user pgtable: 64k pages, 48-bit VAs, pgdp=00002000956ff400
[232066.590231] [0000000000000058] pgd=08001100ae100003, p4d=08001100ae100003, pud=08001100ae100003, pmd=08001100b3c00003, pte=0000000000000000
[232066.590757] Internal error: Oops: 96000007 [#1] SMP
[232066.590958] Modules linked in: rpcsec_gss_krb5 auth_rpcgss nfsv4 dns_resolver nfs lockd grace fscache netfs ocfs2_dlmfs ocfs2_stack_o2cb ocfs2_dlm vhost_net vhost vhost_iotlb tap tun ipt_rpfilter xt_multiport ip_set_hash_ip ip_set_hash_net xfrm_interface xfrm6_tunnel tunnel4 tunnel6 esp4 ah4 wireguard libcurve25519_generic veth xt_addrtype xt_set nf_conntrack_netlink ip_set_hash_ipportnet ip_set_hash_ipportip ip_set_bitmap_port ip_set_hash_ipport dummy ip_set ip_vs_sh ip_vs_wrr ip_vs_rr ip_vs iptable_filter sch_ingress nfnetlink_cttimeout vport_gre ip_gre ip_tunnel gre vport_geneve geneve vport_vxlan vxlan ip6_udp_tunnel udp_tunnel openvswitch nf_conncount dm_round_robin dm_service_time dm_multipath xt_nat xt_MASQUERADE nft_chain_nat nf_nat xt_mark xt_conntrack xt_comment nft_compat nft_counter nf_tables nfnetlink ocfs2 ocfs2_nodemanager ocfs2_stackglue iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi ipmi_ssif nbd overlay 8021q garp mrp bonding tls rfkill sunrpc ext4 mbcache jbd2
[232066.591052]  vfat fat cas_cache cas_disk ses enclosure scsi_transport_sas sg acpi_ipmi ipmi_si ipmi_devintf ipmi_msghandler ip_tables vfio_pci vfio_pci_core vfio_virqfd vfio_iommu_type1 vfio dm_mirror dm_region_hash dm_log dm_mod nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 br_netfilter bridge stp llc fuse xfs libcrc32c ast drm_vram_helper qla2xxx drm_kms_helper syscopyarea crct10dif_ce sysfillrect ghash_ce sysimgblt sha2_ce fb_sys_fops cec sha256_arm64 sha1_ce drm_ttm_helper ttm nvme_fc igb sbsa_gwdt nvme_fabrics drm nvme_core i2c_algo_bit i40e scsi_transport_fc megaraid_sas aes_neon_bs
[232066.596953] CPU: 6 PID: 4124696 Comm: 10.253.166.125- Kdump: loaded Not tainted 5.15.131-9.cl9_ocfs2.aarch64 #1
[232066.597356] Hardware name: Great Wall .\x93\x8e...RF6260 V5/GWMSSE2GL1T, BIOS T656FBE_V3.0.18 2024-01-06
[232066.597721] pstate: 20400009 (nzCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
[232066.598034] pc : nfs4_reclaim_open_state+0x220/0x800 [nfsv4]
[232066.598327] lr : nfs4_reclaim_open_state+0x12c/0x800 [nfsv4]
[232066.598595] sp : ffff8000f568fc70
[232066.598731] x29: ffff8000f568fc70 x28: 0000000000001000 x27: ffff21003db33000
[232066.599030] x26: ffff800005521ae0 x25: ffff0100f98fa3f0 x24: 0000000000000001
[232066.599319] x23: ffff800009920008 x22: ffff21003db33040 x21: ffff21003db33050
[232066.599628] x20: ffff410172fe9e40 x19: ffff410172fe9e00 x18: 0000000000000000
[232066.599914] x17: 0000000000000000 x16: 0000000000000004 x15: 0000000000000000
[232066.600195] x14: 0000000000000000 x13: ffff800008e685a8 x12: 00000000eac0c6e6
[232066.600498] x11: 0000000000000000 x10: 0000000000000008 x9 : ffff8000054e5828
[232066.600784] x8 : 00000000ffffffbf x7 : 0000000000000001 x6 : 000000000a9eb14a
[232066.601062] x5 : 0000000000000000 x4 : ffff70ff8a14a800 x3 : 0000000000000058
[232066.601348] x2 : 0000000000000001 x1 : 54dce46366daa6c6 x0 : 0000000000000000
[232066.601636] Call trace:
[232066.601749]  nfs4_reclaim_open_state+0x220/0x800 [nfsv4]
[232066.601998]  nfs4_do_reclaim+0x1b8/0x28c [nfsv4]
[232066.602218]  nfs4_state_manager+0x928/0x10f0 [nfsv4]
[232066.602455]  nfs4_run_state_manager+0x78/0x1b0 [nfsv4]
[232066.602690]  kthread+0x110/0x114
[232066.602830]  ret_from_fork+0x10/0x20
[232066.602985] Code: 1400000d f9403f20 f9402e61 91016003 (f9402c00)
[232066.603284] SMP: stopping secondary CPUs
[232066.606936] Starting crashdump kernel...
[232066.607146] Bye!

Analysing the vmcore, we know that nfs4_copy_state listed by destination
nfs_server->ss_copies was added by the field copies in handle_async_copy(),
and we found a waiting copy process with the stack as:
PID: 3511963  TASK: ffff710028b47e00  CPU: 0   COMMAND: "cp"
 #0 [ffff8001116ef740] __switch_to at ffff8000081b92f4
 #1 [ffff8001116ef760] __schedule at ffff800008dd0650
 #2 [ffff8001116ef7c0] schedule at ffff800008dd0a00
 #3 [ffff8001116ef7e0] schedule_timeout at ffff800008dd6aa0
 #4 [ffff8001116ef860] __wait_for_common at ffff800008dd166c
 #5 [ffff8001116ef8e0] wait_for_completion_interruptible at ffff800008dd1898
 #6 [ffff8001116ef8f0] handle_async_copy at ffff8000055142f4 [nfsv4]
 #7 [ffff8001116ef970] _nfs42_proc_copy at ffff8000055147c8 [nfsv4]
 torvalds#8 [ffff8001116efa80] nfs42_proc_copy at ffff800005514cf0 [nfsv4]
 torvalds#9 [ffff8001116efc50] __nfs4_copy_file_range.constprop.0 at ffff8000054ed694 [nfsv4]

The NULL-pointer dereference was due to nfs42_complete_copies() listed
the nfs_server->ss_copies by the field ss_copies of nfs4_copy_state.
So the nfs4_copy_state address ffff0100f98fa3f0 was offset by 0x10 and
the data accessed through this pointer was also incorrect. Generally,
the ordered list nfs4_state_owner->so_states indicate open(O_RDWR) or
open(O_WRITE) states are reclaimed firstly by nfs4_reclaim_open_state().
When destination state reclaim is failed with NFS_STATE_RECOVERY_FAILED
and copies are not deleted in nfs_server->ss_copies, the source state
may be passed to the nfs42_complete_copies() process earlier, resulting
in this crash scene finally. To solve this issue, we add a list_head
nfs_server->ss_src_copies for a server-to-server copy specially.

Fixes: 0e65a32 ("NFS: handle source server reboot")
Signed-off-by: Yanjun Zhang <zhangyanjun@cestc.cn>
Reviewed-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Anna Schumaker <anna.schumaker@oracle.com>

Syzkaller reported a lockdep splat:

  ============================================
  WARNING: possible recursive locking detected
  6.11.0-rc6-syzkaller-00019-g67784a74e258 #0 Not tainted
  --------------------------------------------
  syz-executor364/5113 is trying to acquire lock:
  ffff8880449f1958 (k-slock-AF_INET){+.-.}-{2:2}, at: spin_lock include/linux/spinlock.h:351 [inline]
  ffff8880449f1958 (k-slock-AF_INET){+.-.}-{2:2}, at: sk_clone_lock+0x2cd/0xf40 net/core/sock.c:2328

  but task is already holding lock:
  ffff88803fe3cb58 (k-slock-AF_INET){+.-.}-{2:2}, at: spin_lock include/linux/spinlock.h:351 [inline]
  ffff88803fe3cb58 (k-slock-AF_INET){+.-.}-{2:2}, at: sk_clone_lock+0x2cd/0xf40 net/core/sock.c:2328

  other info that might help us debug this:
   Possible unsafe locking scenario:

         CPU0
         ----
    lock(k-slock-AF_INET);
    lock(k-slock-AF_INET);

   *** DEADLOCK ***

   May be due to missing lock nesting notation

  7 locks held by syz-executor364/5113:
   #0: ffff8880449f0e18 (sk_lock-AF_INET){+.+.}-{0:0}, at: lock_sock include/net/sock.h:1607 [inline]
   #0: ffff8880449f0e18 (sk_lock-AF_INET){+.+.}-{0:0}, at: mptcp_sendmsg+0x153/0x1b10 net/mptcp/protocol.c:1806
   #1: ffff88803fe39ad8 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: lock_sock include/net/sock.h:1607 [inline]
   #1: ffff88803fe39ad8 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: mptcp_sendmsg_fastopen+0x11f/0x530 net/mptcp/protocol.c:1727
   #2: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: rcu_lock_acquire include/linux/rcupdate.h:326 [inline]
   #2: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: rcu_read_lock include/linux/rcupdate.h:838 [inline]
   #2: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: __ip_queue_xmit+0x5f/0x1b80 net/ipv4/ip_output.c:470
   #3: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: rcu_lock_acquire include/linux/rcupdate.h:326 [inline]
   #3: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: rcu_read_lock include/linux/rcupdate.h:838 [inline]
   #3: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: ip_finish_output2+0x45f/0x1390 net/ipv4/ip_output.c:228
   #4: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: local_lock_acquire include/linux/local_lock_internal.h:29 [inline]
   #4: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: process_backlog+0x33b/0x15b0 net/core/dev.c:6104
   #5: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: rcu_lock_acquire include/linux/rcupdate.h:326 [inline]
   #5: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: rcu_read_lock include/linux/rcupdate.h:838 [inline]
   #5: ffffffff8e938320 (rcu_read_lock){....}-{1:2}, at: ip_local_deliver_finish+0x230/0x5f0 net/ipv4/ip_input.c:232
   #6: ffff88803fe3cb58 (k-slock-AF_INET){+.-.}-{2:2}, at: spin_lock include/linux/spinlock.h:351 [inline]
   #6: ffff88803fe3cb58 (k-slock-AF_INET){+.-.}-{2:2}, at: sk_clone_lock+0x2cd/0xf40 net/core/sock.c:2328

  stack backtrace:
  CPU: 0 UID: 0 PID: 5113 Comm: syz-executor364 Not tainted 6.11.0-rc6-syzkaller-00019-g67784a74e258 #0
  Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2~bpo12+1 04/01/2014
  Call Trace:
   <IRQ>
   __dump_stack lib/dump_stack.c:93 [inline]
   dump_stack_lvl+0x241/0x360 lib/dump_stack.c:119
   check_deadlock kernel/locking/lockdep.c:3061 [inline]
   validate_chain+0x15d3/0x5900 kernel/locking/lockdep.c:3855
   __lock_acquire+0x137a/0x2040 kernel/locking/lockdep.c:5142
   lock_acquire+0x1ed/0x550 kernel/locking/lockdep.c:5759
   __raw_spin_lock include/linux/spinlock_api_smp.h:133 [inline]
   _raw_spin_lock+0x2e/0x40 kernel/locking/spinlock.c:154
   spin_lock include/linux/spinlock.h:351 [inline]
   sk_clone_lock+0x2cd/0xf40 net/core/sock.c:2328
   mptcp_sk_clone_init+0x32/0x13c0 net/mptcp/protocol.c:3279
   subflow_syn_recv_sock+0x931/0x1920 net/mptcp/subflow.c:874
   tcp_check_req+0xfe4/0x1a20 net/ipv4/tcp_minisocks.c:853
   tcp_v4_rcv+0x1c3e/0x37f0 net/ipv4/tcp_ipv4.c:2267
   ip_protocol_deliver_rcu+0x22e/0x440 net/ipv4/ip_input.c:205
   ip_local_deliver_finish+0x341/0x5f0 net/ipv4/ip_input.c:233
   NF_HOOK+0x3a4/0x450 include/linux/netfilter.h:314
   NF_HOOK+0x3a4/0x450 include/linux/netfilter.h:314
   __netif_receive_skb_one_core net/core/dev.c:5661 [inline]
   __netif_receive_skb+0x2bf/0x650 net/core/dev.c:5775
   process_backlog+0x662/0x15b0 net/core/dev.c:6108
   __napi_poll+0xcb/0x490 net/core/dev.c:6772
   napi_poll net/core/dev.c:6841 [inline]
   net_rx_action+0x89b/0x1240 net/core/dev.c:6963
   handle_softirqs+0x2c4/0x970 kernel/softirq.c:554
   do_softirq+0x11b/0x1e0 kernel/softirq.c:455
   </IRQ>
   <TASK>
   __local_bh_enable_ip+0x1bb/0x200 kernel/softirq.c:382
   local_bh_enable include/linux/bottom_half.h:33 [inline]
   rcu_read_unlock_bh include/linux/rcupdate.h:908 [inline]
   __dev_queue_xmit+0x1763/0x3e90 net/core/dev.c:4450
   dev_queue_xmit include/linux/netdevice.h:3105 [inline]
   neigh_hh_output include/net/neighbour.h:526 [inline]
   neigh_output include/net/neighbour.h:540 [inline]
   ip_finish_output2+0xd41/0x1390 net/ipv4/ip_output.c:235
   ip_local_out net/ipv4/ip_output.c:129 [inline]
   __ip_queue_xmit+0x118c/0x1b80 net/ipv4/ip_output.c:535
   __tcp_transmit_skb+0x2544/0x3b30 net/ipv4/tcp_output.c:1466
   tcp_rcv_synsent_state_process net/ipv4/tcp_input.c:6542 [inline]
   tcp_rcv_state_process+0x2c32/0x4570 net/ipv4/tcp_input.c:6729
   tcp_v4_do_rcv+0x77d/0xc70 net/ipv4/tcp_ipv4.c:1934
   sk_backlog_rcv include/net/sock.h:1111 [inline]
   __release_sock+0x214/0x350 net/core/sock.c:3004
   release_sock+0x61/0x1f0 net/core/sock.c:3558
   mptcp_sendmsg_fastopen+0x1ad/0x530 net/mptcp/protocol.c:1733
   mptcp_sendmsg+0x1884/0x1b10 net/mptcp/protocol.c:1812
   sock_sendmsg_nosec net/socket.c:730 [inline]
   __sock_sendmsg+0x1a6/0x270 net/socket.c:745
   ____sys_sendmsg+0x525/0x7d0 net/socket.c:2597
   ___sys_sendmsg net/socket.c:2651 [inline]
   __sys_sendmmsg+0x3b2/0x740 net/socket.c:2737
   __do_sys_sendmmsg net/socket.c:2766 [inline]
   __se_sys_sendmmsg net/socket.c:2763 [inline]
   __x64_sys_sendmmsg+0xa0/0xb0 net/socket.c:2763
   do_syscall_x64 arch/x86/entry/common.c:52 [inline]
   do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83
   entry_SYSCALL_64_after_hwframe+0x77/0x7f
  RIP: 0033:0x7f04fb13a6b9
  Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 01 1a 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b8 ff ff ff f7 d8 64 89 01 48
  RSP: 002b:00007ffd651f42d8 EFLAGS: 00000246 ORIG_RAX: 0000000000000133
  RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00007f04fb13a6b9
  RDX: 0000000000000001 RSI: 0000000020000d00 RDI: 0000000000000004
  RBP: 00007ffd651f4310 R08: 0000000000000001 R09: 0000000000000001
  R10: 0000000020000080 R11: 0000000000000246 R12: 00000000000f4240
  R13: 00007f04fb187449 R14: 00007ffd651f42f4 R15: 00007ffd651f4300
   </TASK>

As noted by Cong Wang, the splat is false positive, but the code
path leading to the report is an unexpected one: a client is
attempting an MPC handshake towards the in-kernel listener created
by the in-kernel PM for a port based signal endpoint.

Such connection will be never accepted; many of them can make the
listener queue full and preventing the creation of MPJ subflow via
such listener - its intended role.

Explicitly detect this scenario at initial-syn time and drop the
incoming MPC request.

Fixes: 1729cf1 ("mptcp: create the listening socket for new port")
Cc: stable@vger.kernel.org
Reported-by: syzbot+f4aacdfef2c6a6529c3e@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=f4aacdfef2c6a6529c3e
Cc: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20241014-net-mptcp-mpc-port-endp-v2-1-7faea8e6b6ae@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

…/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm64 fixes for 6.12, take #3

- Stop wasting space in the HYP idmap, as we are dangerously close
  to the 4kB limit, and this has already exploded in -next

- Fix another race in vgic_init()

- Fix a UBSAN error when faking the cache topology with MTE
  enabled

Hou Tao says:

====================
The patch set fixes several issues in bits iterator. Patch #1 fixes the
kmemleak problem of bits iterator. Patch #2~#3 fix the overflow problem
of nr_bits. Patch #4 fixes the potential stack corruption when bits
iterator is used on 32-bit host. Patch #5 adds more test cases for bits
iterator.

Please see the individual patches for more details. And comments are
always welcome.
---
v4:
 * patch #1: add ack from Yafang
 * patch #3: revert code-churn like changes:
   (1) compute nr_bytes and nr_bits before the check of nr_words.
   (2) use nr_bits == 64 to check for single u64, preventing build
       warning on 32-bit hosts.
 * patch #4: use "BITS_PER_LONG == 32" instead of "!defined(CONFIG_64BIT)"

v3: https://lore.kernel.org/bpf/20241025013233.804027-1-houtao@huaweicloud.com/T/#t
  * split the bits-iterator related patches from "Misc fixes for bpf"
    patch set
  * patch #1: use "!nr_bits || bits >= nr_bits" to stop the iteration
  * patch #2: add a new helper for the overflow problem
  * patch #3: decrease the limitation from 512 to 511 and check whether
    nr_bytes is too large for bpf memory allocator explicitly
  * patch #5: add two more test cases for bit iterator

v2: http://lore.kernel.org/bpf/d49fa2f4-f743-c763-7579-c3cab4dd88cb@huaweicloud.com
====================

Link: https://lore.kernel.org/r/20241030100516.3633640-1-houtao@huaweicloud.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

Petr Machata says:

====================
mlxsw: Fixes

In this patchset:

- Tx header should be pushed for each packet which is transmitted via
  Spectrum ASICs. Patch #1 adds a missing call to skb_cow_head() to make
  sure that there is both enough room to push the Tx header and that the
  SKB header is not cloned and can be modified.

- Commit b5b60bb ("mlxsw: pci: Use page pool for Rx buffers
  allocation") converted mlxsw to use page pool for Rx buffers allocation.
  Sync for CPU and for device should be done for Rx pages. In patches #2
  and #3, add the missing calls to sync pages for, respectively, CPU and
  the device.

- Patch #4 then fixes a bug to IPv6 GRE forwarding offload. Patch #5 adds
  a generic forwarding test that fails with mlxsw ports prior to the fix.
====================

Link: https://patch.msgid.link/cover.1729866134.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

The function blk_revalidate_disk_zones() calls the function
disk_update_zone_resources() after freezing the device queue. In turn,
disk_update_zone_resources() calls queue_limits_start_update() which
takes a queue limits mutex lock, resulting in the ordering:
q->q_usage_counter check -> q->limits_lock. However, the usual ordering
is to always take a queue limit lock before freezing the queue to commit
the limits updates, e.g., the code pattern:

lim = queue_limits_start_update(q);
...
blk_mq_freeze_queue(q);
ret = queue_limits_commit_update(q, &lim);
blk_mq_unfreeze_queue(q);

Thus, blk_revalidate_disk_zones() introduces a potential circular
locking dependency deadlock that lockdep sometimes catches with the
splat:

[   51.934109] ======================================================
[   51.935916] WARNING: possible circular locking dependency detected
[   51.937561] 6.12.0+ #2107 Not tainted
[   51.938648] ------------------------------------------------------
[   51.940351] kworker/u16:4/157 is trying to acquire lock:
[   51.941805] ffff9fff0aa0bea8 (&q->limits_lock){+.+.}-{4:4}, at: disk_update_zone_resources+0x86/0x170
[   51.944314]
               but task is already holding lock:
[   51.945688] ffff9fff0aa0b890 (&q->q_usage_counter(queue)#3){++++}-{0:0}, at: blk_revalidate_disk_zones+0x15f/0x340
[   51.948527]
               which lock already depends on the new lock.

[   51.951296]
               the existing dependency chain (in reverse order) is:
[   51.953708]
               -> #1 (&q->q_usage_counter(queue)#3){++++}-{0:0}:
[   51.956131]        blk_queue_enter+0x1c9/0x1e0
[   51.957290]        blk_mq_alloc_request+0x187/0x2a0
[   51.958365]        scsi_execute_cmd+0x78/0x490 [scsi_mod]
[   51.959514]        read_capacity_16+0x111/0x410 [sd_mod]
[   51.960693]        sd_revalidate_disk.isra.0+0x872/0x3240 [sd_mod]
[   51.962004]        sd_probe+0x2d7/0x520 [sd_mod]
[   51.962993]        really_probe+0xd5/0x330
[   51.963898]        __driver_probe_device+0x78/0x110
[   51.964925]        driver_probe_device+0x1f/0xa0
[   51.965916]        __driver_attach_async_helper+0x60/0xe0
[   51.967017]        async_run_entry_fn+0x2e/0x140
[   51.968004]        process_one_work+0x21f/0x5a0
[   51.968987]        worker_thread+0x1dc/0x3c0
[   51.969868]        kthread+0xe0/0x110
[   51.970377]        ret_from_fork+0x31/0x50
[   51.970983]        ret_from_fork_asm+0x11/0x20
[   51.971587]
               -> #0 (&q->limits_lock){+.+.}-{4:4}:
[   51.972479]        __lock_acquire+0x1337/0x2130
[   51.973133]        lock_acquire+0xc5/0x2d0
[   51.973691]        __mutex_lock+0xda/0xcf0
[   51.974300]        disk_update_zone_resources+0x86/0x170
[   51.975032]        blk_revalidate_disk_zones+0x16c/0x340
[   51.975740]        sd_zbc_revalidate_zones+0x73/0x160 [sd_mod]
[   51.976524]        sd_revalidate_disk.isra.0+0x465/0x3240 [sd_mod]
[   51.977824]        sd_probe+0x2d7/0x520 [sd_mod]
[   51.978917]        really_probe+0xd5/0x330
[   51.979915]        __driver_probe_device+0x78/0x110
[   51.981047]        driver_probe_device+0x1f/0xa0
[   51.982143]        __driver_attach_async_helper+0x60/0xe0
[   51.983282]        async_run_entry_fn+0x2e/0x140
[   51.984319]        process_one_work+0x21f/0x5a0
[   51.985873]        worker_thread+0x1dc/0x3c0
[   51.987289]        kthread+0xe0/0x110
[   51.988546]        ret_from_fork+0x31/0x50
[   51.989926]        ret_from_fork_asm+0x11/0x20
[   51.991376]
               other info that might help us debug this:

[   51.994127]  Possible unsafe locking scenario:

[   51.995651]        CPU0                    CPU1
[   51.996694]        ----                    ----
[   51.997716]   lock(&q->q_usage_counter(queue)#3);
[   51.998817]                                lock(&q->limits_lock);
[   52.000043]                                lock(&q->q_usage_counter(queue)#3);
[   52.001638]   lock(&q->limits_lock);
[   52.002485]
                *** DEADLOCK ***

Prevent this issue by moving the calls to blk_mq_freeze_queue() and
blk_mq_unfreeze_queue() around the call to queue_limits_commit_update()
in disk_update_zone_resources(). In case of revalidation failure, the
call to disk_free_zone_resources() in blk_revalidate_disk_zones()
is still done with the queue frozen as before.

Fixes: 843283e ("block: Fake max open zones limit when there is no limit")
Cc: stable@vger.kernel.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20241126104705.183996-1-dlemoal@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Kernel will hang on destroy admin_q while we create ctrl failed, such
as following calltrace:

PID: 23644    TASK: ff2d52b40f439fc0  CPU: 2    COMMAND: "nvme"
 #0 [ff61d23de260fb78] __schedule at ffffffff8323bc15
 #1 [ff61d23de260fc08] schedule at ffffffff8323c014
 #2 [ff61d23de260fc28] blk_mq_freeze_queue_wait at ffffffff82a3dba1
 #3 [ff61d23de260fc78] blk_freeze_queue at ffffffff82a4113a
 #4 [ff61d23de260fc90] blk_cleanup_queue at ffffffff82a33006
 #5 [ff61d23de260fcb0] nvme_rdma_destroy_admin_queue at ffffffffc12686ce
 #6 [ff61d23de260fcc8] nvme_rdma_setup_ctrl at ffffffffc1268ced
 #7 [ff61d23de260fd28] nvme_rdma_create_ctrl at ffffffffc126919b
 torvalds#8 [ff61d23de260fd68] nvmf_dev_write at ffffffffc024f362
 torvalds#9 [ff61d23de260fe38] vfs_write at ffffffff827d5f25
    RIP: 00007fda7891d574  RSP: 00007ffe2ef06958  RFLAGS: 00000202
    RAX: ffffffffffffffda  RBX: 000055e8122a4d90  RCX: 00007fda7891d574
    RDX: 000000000000012b  RSI: 000055e8122a4d90  RDI: 0000000000000004
    RBP: 00007ffe2ef079c0   R8: 000000000000012b   R9: 000055e8122a4d90
    R10: 0000000000000000  R11: 0000000000000202  R12: 0000000000000004
    R13: 000055e8122923c0  R14: 000000000000012b  R15: 00007fda78a54500
    ORIG_RAX: 0000000000000001  CS: 0033  SS: 002b

This due to we have quiesced admi_q before cancel requests, but forgot
to unquiesce before destroy it, as a result we fail to drain the
pending requests, and hang on blk_mq_freeze_queue_wait() forever. Here
try to reuse nvme_rdma_teardown_admin_queue() to fix this issue and
simplify the code.

Fixes: 958dc1d ("nvme-rdma: add clean action for failed reconnection")
Reported-by: Yingfu.zhou <yingfu.zhou@shopee.com>
Signed-off-by: Chunguang.xu <chunguang.xu@shopee.com>
Signed-off-by: Yue.zhao <yue.zhao@shopee.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>

Konstantin Shkolnyy says:

====================
vsock/test: fix wrong setsockopt() parameters

Parameters were created using wrong C types, which caused them to be of
wrong size on some architectures, causing problems.

The problem with SO_RCVLOWAT was found on s390 (big endian), while x86-64
didn't show it. After the fix, all tests pass on s390.
Then Stefano Garzarella pointed out that SO_VM_SOCKETS_* calls might have
a similar problem, which turned out to be true, hence, the second patch.

Changes for v8:
- Fix whitespace warnings from "checkpatch.pl --strict"
- Add maintainers to Cc:
Changes for v7:
- Rebase on top of https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git
- Add the "net" tags to the subjects
Changes for v6:
- rework the patch #3 to avoid creating a new file for new functions,
and exclude vsock_perf from calling the new functions.
- add "Reviewed-by:" to the patch #2.
Changes for v5:
- in the patch #2 replace the introduced uint64_t with unsigned long long
to match documentation
- add a patch #3 that verifies every setsockopt() call.
Changes for v4:
- add "Reviewed-by:" to the first patch, and add a second patch fixing
SO_VM_SOCKETS_* calls, which depends on the first one (hence, it's now
a patch series.)
Changes for v3:
- fix the same problem in vsock_perf and update commit message
Changes for v2:
- add "Fixes:" lines to the commit message
====================

Link: https://patch.msgid.link/20241203150656.287028-1-kshk@linux.ibm.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

Hou Tao says:

====================
This patch set fixes several issues for LPM trie. These issues were
found during adding new test cases or were reported by syzbot.

The patch set is structured as follows:

Patch #1~#2 are clean-ups for lpm_trie_update_elem().
Patch #3 handles BPF_EXIST and BPF_NOEXIST correctly for LPM trie.
Patch #4 fixes the accounting of n_entries when doing in-place update.
Patch #5 fixes the exact match condition in trie_get_next_key() and it
may skip keys when the passed key is not found in the map.
Patch #6~#7 switch from kmalloc() to bpf memory allocator for LPM trie
to fix several lock order warnings reported by syzbot. It also enables
raw_spinlock_t for LPM trie again. After these changes, the LPM trie will
be closer to being usable in any context (though the reentrance check of
trie->lock is still missing, but it is on my todo list).
Patch torvalds#8: move test_lpm_map to map_tests to make it run regularly.
Patch torvalds#9: add test cases for the issues fixed by patch #3~#5.

Please see individual patches for more details. Comments are always
welcome.

Change Log:
v3:
  * patch #2: remove the unnecessary NULL-init for im_node
  * patch #6: alloc the leaf node before disabling IRQ to low
    the possibility of -ENOMEM when leaf_size is large; Free
    these nodes outside the trie lock (Suggested by Alexei)
  * collect review and ack tags (Thanks for Toke & Daniel)

v2: https://lore.kernel.org/bpf/20241127004641.1118269-1-houtao@huaweicloud.com/
  * collect review tags (Thanks for Toke)
  * drop "Add bpf_mem_cache_is_mergeable() helper" patch
  * patch #3~#4: add fix tag
  * patch #4: rename the helper to trie_check_add_elem() and increase
    n_entries in it.
  * patch #6: use one bpf mem allocator and update commit message to
    clarify that using bpf mem allocator is more appropriate.
  * patch #7: update commit message to add the possible max running time
    for update operation.
  * patch torvalds#9: update commit message to specify the purpose of these test
    cases.

v1: https://lore.kernel.org/bpf/20241118010808.2243555-1-houtao@huaweicloud.com/
====================

Link: https://lore.kernel.org/all/20241206110622.1161752-1-houtao@huaweicloud.com/
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

Its used from trace__run(), for the 'perf trace' live mode, i.e. its
strace-like, non-perf.data file processing mode, the most common one.

The trace__run() function will set trace->host using machine__new_host()
that is supposed to give a machine instance representing the running
machine, and since we'll use perf_env__arch_strerrno() to get the right
errno -> string table, we need to use machine->env, so initialize it in
machine__new_host().

Before the patch:

  (gdb) run trace --errno-summary -a sleep 1
  <SNIP>
   Summary of events:

   gvfs-afc-volume (3187), 2 events, 0.0%

     syscall            calls  errors  total       min       avg       max       stddev
                                       (msec)    (msec)    (msec)    (msec)        (%)
     --------------- --------  ------ -------- --------- --------- ---------     ------
     pselect6               1      0     0.000     0.000     0.000     0.000      0.00%

   GUsbEventThread (3519), 2 events, 0.0%

     syscall            calls  errors  total       min       avg       max       stddev
                                       (msec)    (msec)    (msec)    (msec)        (%)
     --------------- --------  ------ -------- --------- --------- ---------     ------
     poll                   1      0     0.000     0.000     0.000     0.000      0.00%
  <SNIP>
  Program received signal SIGSEGV, Segmentation fault.
  0x00000000005caba0 in perf_env__arch_strerrno (env=0x0, err=110) at util/env.c:478
  478		if (env->arch_strerrno == NULL)
  (gdb) bt
  #0  0x00000000005caba0 in perf_env__arch_strerrno (env=0x0, err=110) at util/env.c:478
  #1  0x00000000004b75d2 in thread__dump_stats (ttrace=0x14f58f0, trace=0x7fffffffa5b0, fp=0x7ffff6ff74e0 <_IO_2_1_stderr_>) at builtin-trace.c:4673
  #2  0x00000000004b78bf in trace__fprintf_thread (fp=0x7ffff6ff74e0 <_IO_2_1_stderr_>, thread=0x10fa0b0, trace=0x7fffffffa5b0) at builtin-trace.c:4708
  #3  0x00000000004b7ad9 in trace__fprintf_thread_summary (trace=0x7fffffffa5b0, fp=0x7ffff6ff74e0 <_IO_2_1_stderr_>) at builtin-trace.c:4747
  #4  0x00000000004b656e in trace__run (trace=0x7fffffffa5b0, argc=2, argv=0x7fffffffde60) at builtin-trace.c:4456
  #5  0x00000000004ba43e in cmd_trace (argc=2, argv=0x7fffffffde60) at builtin-trace.c:5487
  #6  0x00000000004c0414 in run_builtin (p=0xec3068 <commands+648>, argc=5, argv=0x7fffffffde60) at perf.c:351
  #7  0x00000000004c06bb in handle_internal_command (argc=5, argv=0x7fffffffde60) at perf.c:404
  torvalds#8  0x00000000004c0814 in run_argv (argcp=0x7fffffffdc4c, argv=0x7fffffffdc40) at perf.c:448
  torvalds#9  0x00000000004c0b5d in main (argc=5, argv=0x7fffffffde60) at perf.c:560
  (gdb)

After:

  root@number:~# perf trace -a --errno-summary sleep 1
  <SNIP>
     pw-data-loop (2685), 1410 events, 16.0%

     syscall            calls  errors  total       min       avg       max       stddev
                                       (msec)    (msec)    (msec)    (msec)        (%)
     --------------- --------  ------ -------- --------- --------- ---------     ------
     epoll_wait           188      0   983.428     0.000     5.231    15.595      8.68%
     ioctl                 94      0     0.811     0.004     0.009     0.016      2.82%
     read                 188      0     0.322     0.001     0.002     0.006      5.15%
     write                141      0     0.280     0.001     0.002     0.018      8.39%
     timerfd_settime       94      0     0.138     0.001     0.001     0.007      6.47%

   gnome-control-c (179406), 1848 events, 20.9%

     syscall            calls  errors  total       min       avg       max       stddev
                                       (msec)    (msec)    (msec)    (msec)        (%)
     --------------- --------  ------ -------- --------- --------- ---------     ------
     poll                 222      0   959.577     0.000     4.322    21.414     11.40%
     recvmsg              150      0     0.539     0.001     0.004     0.013      5.12%
     write                300      0     0.442     0.001     0.001     0.007      3.29%
     read                 150      0     0.183     0.001     0.001     0.009      5.53%
     getpid               102      0     0.101     0.000     0.001     0.008      7.82%

  root@number:~#

Fixes: 54373b5 ("perf env: Introduce perf_env__arch_strerrno()")
Reported-by: Veronika Molnarova <vmolnaro@redhat.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Veronika Molnarova <vmolnaro@redhat.com>
Acked-by: Michael Petlan <mpetlan@redhat.com>
Tested-by: Michael Petlan <mpetlan@redhat.com>
Link: https://lore.kernel.org/r/Z0XffUgNSv_9OjOi@x1
Signed-off-by: Namhyung Kim <namhyung@kernel.org>

This reworks hci_cb_list to not use mutex hci_cb_list_lock to avoid bugs
like the bellow:

BUG: sleeping function called from invalid context at kernel/locking/mutex.c:585
in_atomic(): 0, irqs_disabled(): 0, non_block: 0, pid: 5070, name: kworker/u9:2
preempt_count: 0, expected: 0
RCU nest depth: 1, expected: 0
4 locks held by kworker/u9:2/5070:
 #0: ffff888015be3948 ((wq_completion)hci0#2){+.+.}-{0:0}, at: process_one_work kernel/workqueue.c:3229 [inline]
 #0: ffff888015be3948 ((wq_completion)hci0#2){+.+.}-{0:0}, at: process_scheduled_works+0x8e0/0x1770 kernel/workqueue.c:3335
 #1: ffffc90003b6fd00 ((work_completion)(&hdev->rx_work)){+.+.}-{0:0}, at: process_one_work kernel/workqueue.c:3230 [inline]
 #1: ffffc90003b6fd00 ((work_completion)(&hdev->rx_work)){+.+.}-{0:0}, at: process_scheduled_works+0x91b/0x1770 kernel/workqueue.c:3335
 #2: ffff8880665d0078 (&hdev->lock){+.+.}-{3:3}, at: hci_le_create_big_complete_evt+0xcf/0xae0 net/bluetooth/hci_event.c:6914
 #3: ffffffff8e132020 (rcu_read_lock){....}-{1:2}, at: rcu_lock_acquire include/linux/rcupdate.h:298 [inline]
 #3: ffffffff8e132020 (rcu_read_lock){....}-{1:2}, at: rcu_read_lock include/linux/rcupdate.h:750 [inline]
 #3: ffffffff8e132020 (rcu_read_lock){....}-{1:2}, at: hci_le_create_big_complete_evt+0xdb/0xae0 net/bluetooth/hci_event.c:6915
CPU: 0 PID: 5070 Comm: kworker/u9:2 Not tainted 6.8.0-syzkaller-08073-g480e035fc4c7 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/27/2024
Workqueue: hci0 hci_rx_work
Call Trace:
 <TASK>
 __dump_stack lib/dump_stack.c:88 [inline]
 dump_stack_lvl+0x241/0x360 lib/dump_stack.c:114
 __might_resched+0x5d4/0x780 kernel/sched/core.c:10187
 __mutex_lock_common kernel/locking/mutex.c:585 [inline]
 __mutex_lock+0xc1/0xd70 kernel/locking/mutex.c:752
 hci_connect_cfm include/net/bluetooth/hci_core.h:2004 [inline]
 hci_le_create_big_complete_evt+0x3d9/0xae0 net/bluetooth/hci_event.c:6939
 hci_event_func net/bluetooth/hci_event.c:7514 [inline]
 hci_event_packet+0xa53/0x1540 net/bluetooth/hci_event.c:7569
 hci_rx_work+0x3e8/0xca0 net/bluetooth/hci_core.c:4171
 process_one_work kernel/workqueue.c:3254 [inline]
 process_scheduled_works+0xa00/0x1770 kernel/workqueue.c:3335
 worker_thread+0x86d/0xd70 kernel/workqueue.c:3416
 kthread+0x2f0/0x390 kernel/kthread.c:388
 ret_from_fork+0x4b/0x80 arch/x86/kernel/process.c:147
 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:243
 </TASK>

Reported-by: syzbot+2fb0835e0c9cefc34614@syzkaller.appspotmail.com
Tested-by: syzbot+2fb0835e0c9cefc34614@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=2fb0835e0c9cefc34614
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>

This fixes the circular locking dependency warning below, by
releasing the socket lock before enterning iso_listen_bis, to
avoid any potential deadlock with hdev lock.

[   75.307983] ======================================================
[   75.307984] WARNING: possible circular locking dependency detected
[   75.307985] 6.12.0-rc6+ torvalds#22 Not tainted
[   75.307987] ------------------------------------------------------
[   75.307987] kworker/u81:2/2623 is trying to acquire lock:
[   75.307988] ffff8fde1769da58 (sk_lock-AF_BLUETOOTH-BTPROTO_ISO)
               at: iso_connect_cfm+0x253/0x840 [bluetooth]
[   75.308021]
               but task is already holding lock:
[   75.308022] ffff8fdd61a10078 (&hdev->lock)
               at: hci_le_per_adv_report_evt+0x47/0x2f0 [bluetooth]
[   75.308053]
               which lock already depends on the new lock.

[   75.308054]
               the existing dependency chain (in reverse order) is:
[   75.308055]
               -> #1 (&hdev->lock){+.+.}-{3:3}:
[   75.308057]        __mutex_lock+0xad/0xc50
[   75.308061]        mutex_lock_nested+0x1b/0x30
[   75.308063]        iso_sock_listen+0x143/0x5c0 [bluetooth]
[   75.308085]        __sys_listen_socket+0x49/0x60
[   75.308088]        __x64_sys_listen+0x4c/0x90
[   75.308090]        x64_sys_call+0x2517/0x25f0
[   75.308092]        do_syscall_64+0x87/0x150
[   75.308095]        entry_SYSCALL_64_after_hwframe+0x76/0x7e
[   75.308098]
               -> #0 (sk_lock-AF_BLUETOOTH-BTPROTO_ISO){+.+.}-{0:0}:
[   75.308100]        __lock_acquire+0x155e/0x25f0
[   75.308103]        lock_acquire+0xc9/0x300
[   75.308105]        lock_sock_nested+0x32/0x90
[   75.308107]        iso_connect_cfm+0x253/0x840 [bluetooth]
[   75.308128]        hci_connect_cfm+0x6c/0x190 [bluetooth]
[   75.308155]        hci_le_per_adv_report_evt+0x27b/0x2f0 [bluetooth]
[   75.308180]        hci_le_meta_evt+0xe7/0x200 [bluetooth]
[   75.308206]        hci_event_packet+0x21f/0x5c0 [bluetooth]
[   75.308230]        hci_rx_work+0x3ae/0xb10 [bluetooth]
[   75.308254]        process_one_work+0x212/0x740
[   75.308256]        worker_thread+0x1bd/0x3a0
[   75.308258]        kthread+0xe4/0x120
[   75.308259]        ret_from_fork+0x44/0x70
[   75.308261]        ret_from_fork_asm+0x1a/0x30
[   75.308263]
               other info that might help us debug this:

[   75.308264]  Possible unsafe locking scenario:

[   75.308264]        CPU0                CPU1
[   75.308265]        ----                ----
[   75.308265]   lock(&hdev->lock);
[   75.308267]                            lock(sk_lock-
                                                AF_BLUETOOTH-BTPROTO_ISO);
[   75.308268]                            lock(&hdev->lock);
[   75.308269]   lock(sk_lock-AF_BLUETOOTH-BTPROTO_ISO);
[   75.308270]
                *** DEADLOCK ***

[   75.308271] 4 locks held by kworker/u81:2/2623:
[   75.308272]  #0: ffff8fdd66e52148 ((wq_completion)hci0#2){+.+.}-{0:0},
                at: process_one_work+0x443/0x740
[   75.308276]  #1: ffffafb488b7fe48 ((work_completion)(&hdev->rx_work)),
                at: process_one_work+0x1ce/0x740
[   75.308280]  #2: ffff8fdd61a10078 (&hdev->lock){+.+.}-{3:3}
                at: hci_le_per_adv_report_evt+0x47/0x2f0 [bluetooth]
[   75.308304]  #3: ffffffffb6ba4900 (rcu_read_lock){....}-{1:2},
                at: hci_connect_cfm+0x29/0x190 [bluetooth]

Fixes: 02171da ("Bluetooth: ISO: Add hcon for listening bis sk")
Signed-off-by: Iulia Tanasescu <iulia.tanasescu@nxp.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>

…s_lock

For storing a value to a queue attribute, the queue_attr_store function
first freezes the queue (->q_usage_counter(io)) and then acquire
->sysfs_lock. This seems not correct as the usual ordering should be to
acquire ->sysfs_lock before freezing the queue. This incorrect ordering
causes the following lockdep splat which we are able to reproduce always
simply by accessing /sys/kernel/debug file using ls command:

[   57.597146] WARNING: possible circular locking dependency detected
[   57.597154] 6.12.0-10553-gb86545e02e8c torvalds#20 Tainted: G        W
[   57.597162] ------------------------------------------------------
[   57.597168] ls/4605 is trying to acquire lock:
[   57.597176] c00000003eb56710 (&mm->mmap_lock){++++}-{4:4}, at: __might_fault+0x58/0xc0
[   57.597200]
               but task is already holding lock:
[   57.597207] c0000018e27c6810 (&sb->s_type->i_mutex_key#3){++++}-{4:4}, at: iterate_dir+0x94/0x1d4
[   57.597226]
               which lock already depends on the new lock.

[   57.597233]
               the existing dependency chain (in reverse order) is:
[   57.597241]
               -> #5 (&sb->s_type->i_mutex_key#3){++++}-{4:4}:
[   57.597255]        down_write+0x6c/0x18c
[   57.597264]        start_creating+0xb4/0x24c
[   57.597274]        debugfs_create_dir+0x2c/0x1e8
[   57.597283]        blk_register_queue+0xec/0x294
[   57.597292]        add_disk_fwnode+0x2e4/0x548
[   57.597302]        brd_alloc+0x2c8/0x338
[   57.597309]        brd_init+0x100/0x178
[   57.597317]        do_one_initcall+0x88/0x3e4
[   57.597326]        kernel_init_freeable+0x3cc/0x6e0
[   57.597334]        kernel_init+0x34/0x1cc
[   57.597342]        ret_from_kernel_user_thread+0x14/0x1c
[   57.597350]
               -> #4 (&q->debugfs_mutex){+.+.}-{4:4}:
[   57.597362]        __mutex_lock+0xfc/0x12a0
[   57.597370]        blk_register_queue+0xd4/0x294
[   57.597379]        add_disk_fwnode+0x2e4/0x548
[   57.597388]        brd_alloc+0x2c8/0x338
[   57.597395]        brd_init+0x100/0x178
[   57.597402]        do_one_initcall+0x88/0x3e4
[   57.597410]        kernel_init_freeable+0x3cc/0x6e0
[   57.597418]        kernel_init+0x34/0x1cc
[   57.597426]        ret_from_kernel_user_thread+0x14/0x1c
[   57.597434]
               -> #3 (&q->sysfs_lock){+.+.}-{4:4}:
[   57.597446]        __mutex_lock+0xfc/0x12a0
[   57.597454]        queue_attr_store+0x9c/0x110
[   57.597462]        sysfs_kf_write+0x70/0xb0
[   57.597471]        kernfs_fop_write_iter+0x1b0/0x2ac
[   57.597480]        vfs_write+0x3dc/0x6e8
[   57.597488]        ksys_write+0x84/0x140
[   57.597495]        system_call_exception+0x130/0x360
[   57.597504]        system_call_common+0x160/0x2c4
[   57.597516]
               -> #2 (&q->q_usage_counter(io)torvalds#21){++++}-{0:0}:
[   57.597530]        __submit_bio+0x5ec/0x828
[   57.597538]        submit_bio_noacct_nocheck+0x1e4/0x4f0
[   57.597547]        iomap_readahead+0x2a0/0x448
[   57.597556]        xfs_vm_readahead+0x28/0x3c
[   57.597564]        read_pages+0x88/0x41c
[   57.597571]        page_cache_ra_unbounded+0x1ac/0x2d8
[   57.597580]        filemap_get_pages+0x188/0x984
[   57.597588]        filemap_read+0x13c/0x4bc
[   57.597596]        xfs_file_buffered_read+0x88/0x17c
[   57.597605]        xfs_file_read_iter+0xac/0x158
[   57.597614]        vfs_read+0x2d4/0x3b4
[   57.597622]        ksys_read+0x84/0x144
[   57.597629]        system_call_exception+0x130/0x360
[   57.597637]        system_call_common+0x160/0x2c4
[   57.597647]
               -> #1 (mapping.invalidate_lock#2){++++}-{4:4}:
[   57.597661]        down_read+0x6c/0x220
[   57.597669]        filemap_fault+0x870/0x100c
[   57.597677]        xfs_filemap_fault+0xc4/0x18c
[   57.597684]        __do_fault+0x64/0x164
[   57.597693]        __handle_mm_fault+0x1274/0x1dac
[   57.597702]        handle_mm_fault+0x248/0x484
[   57.597711]        ___do_page_fault+0x428/0xc0c
[   57.597719]        hash__do_page_fault+0x30/0x68
[   57.597727]        do_hash_fault+0x90/0x35c
[   57.597736]        data_access_common_virt+0x210/0x220
[   57.597745]        _copy_from_user+0xf8/0x19c
[   57.597754]        sel_write_load+0x178/0xd54
[   57.597762]        vfs_write+0x108/0x6e8
[   57.597769]        ksys_write+0x84/0x140
[   57.597777]        system_call_exception+0x130/0x360
[   57.597785]        system_call_common+0x160/0x2c4
[   57.597794]
               -> #0 (&mm->mmap_lock){++++}-{4:4}:
[   57.597806]        __lock_acquire+0x17cc/0x2330
[   57.597814]        lock_acquire+0x138/0x400
[   57.597822]        __might_fault+0x7c/0xc0
[   57.597830]        filldir64+0xe8/0x390
[   57.597839]        dcache_readdir+0x80/0x2d4
[   57.597846]        iterate_dir+0xd8/0x1d4
[   57.597855]        sys_getdents64+0x88/0x2d4
[   57.597864]        system_call_exception+0x130/0x360
[   57.597872]        system_call_common+0x160/0x2c4
[   57.597881]
               other info that might help us debug this:

[   57.597888] Chain exists of:
                 &mm->mmap_lock --> &q->debugfs_mutex --> &sb->s_type->i_mutex_key#3

[   57.597905]  Possible unsafe locking scenario:

[   57.597911]        CPU0                    CPU1
[   57.597917]        ----                    ----
[   57.597922]   rlock(&sb->s_type->i_mutex_key#3);
[   57.597932]                                lock(&q->debugfs_mutex);
[   57.597940]                                lock(&sb->s_type->i_mutex_key#3);
[   57.597950]   rlock(&mm->mmap_lock);
[   57.597958]
                *** DEADLOCK ***

[   57.597965] 2 locks held by ls/4605:
[   57.597971]  #0: c0000000137c12f8 (&f->f_pos_lock){+.+.}-{4:4}, at: fdget_pos+0xcc/0x154
[   57.597989]  #1: c0000018e27c6810 (&sb->s_type->i_mutex_key#3){++++}-{4:4}, at: iterate_dir+0x94/0x1d4

Prevent the above lockdep warning by acquiring ->sysfs_lock before
freezing the queue while storing a queue attribute in queue_attr_store
function. Later, we also found[1] another function __blk_mq_update_nr_
hw_queues where we first freeze queue and then acquire the ->sysfs_lock.
So we've also updated lock ordering in __blk_mq_update_nr_hw_queues
function and ensured that in all code paths we follow the correct lock
ordering i.e. acquire ->sysfs_lock before freezing the queue.

[1] https://lore.kernel.org/all/CAFj5m9Ke8+EHKQBs_Nk6hqd=LGXtk4mUxZUN5==ZcCjnZSBwHw@mail.gmail.com/

Reported-by: kjain@linux.ibm.com
Fixes: af28141 ("block: freeze the queue in queue_attr_store")
Tested-by: kjain@linux.ibm.com
Cc: hch@lst.de
Cc: axboe@kernel.dk
Cc: ritesh.list@gmail.com
Cc: ming.lei@redhat.com
Cc: gjoyce@linux.ibm.com
Signed-off-by: Nilay Shroff <nilay@linux.ibm.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20241210144222.1066229-1-nilay@linux.ibm.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

syzbot reports that a recent fix causes nesting issues between the (now)
raw timeoutlock and the eventfd locking:

=============================
[ BUG: Invalid wait context ]
6.13.0-rc4-00080-g9828a4c0901f torvalds#29 Not tainted
-----------------------------
kworker/u32:0/68094 is trying to lock:
ffff000014d7a520 (&ctx->wqh#2){..-.}-{3:3}, at: eventfd_signal_mask+0x64/0x180
other info that might help us debug this:
context-{5:5}
6 locks held by kworker/u32:0/68094:
 #0: ffff0000c1d98148 ((wq_completion)iou_exit){+.+.}-{0:0}, at: process_one_work+0x4e8/0xfc0
 #1: ffff80008d927c78 ((work_completion)(&ctx->exit_work)){+.+.}-{0:0}, at: process_one_work+0x53c/0xfc0
 #2: ffff0000c59bc3d8 (&ctx->completion_lock){+.+.}-{3:3}, at: io_kill_timeouts+0x40/0x180
 #3: ffff0000c59bc358 (&ctx->timeout_lock){-.-.}-{2:2}, at: io_kill_timeouts+0x48/0x180
 #4: ffff800085127aa0 (rcu_read_lock){....}-{1:3}, at: rcu_lock_acquire+0x8/0x38
 #5: ffff800085127aa0 (rcu_read_lock){....}-{1:3}, at: rcu_lock_acquire+0x8/0x38
stack backtrace:
CPU: 7 UID: 0 PID: 68094 Comm: kworker/u32:0 Not tainted 6.13.0-rc4-00080-g9828a4c0901f torvalds#29
Hardware name: linux,dummy-virt (DT)
Workqueue: iou_exit io_ring_exit_work
Call trace:
 show_stack+0x1c/0x30 (C)
 __dump_stack+0x24/0x30
 dump_stack_lvl+0x60/0x80
 dump_stack+0x14/0x20
 __lock_acquire+0x19f8/0x60c8
 lock_acquire+0x1a4/0x540
 _raw_spin_lock_irqsave+0x90/0xd0
 eventfd_signal_mask+0x64/0x180
 io_eventfd_signal+0x64/0x108
 io_req_local_work_add+0x294/0x430
 __io_req_task_work_add+0x1c0/0x270
 io_kill_timeout+0x1f0/0x288
 io_kill_timeouts+0xd4/0x180
 io_uring_try_cancel_requests+0x2e8/0x388
 io_ring_exit_work+0x150/0x550
 process_one_work+0x5e8/0xfc0
 worker_thread+0x7ec/0xc80
 kthread+0x24c/0x300
 ret_from_fork+0x10/0x20

because after the preempt-rt fix for the timeout lock nesting inside
the io-wq lock, we now have the eventfd spinlock nesting inside the
raw timeout spinlock.

Rather than play whack-a-mole with other nesting on the timeout lock,
split the deletion and killing of timeouts so queueing the task_work
for the timeout cancelations can get done outside of the timeout lock.

Reported-by: syzbot+b1fc199a40b65d601b65@syzkaller.appspotmail.com
Fixes: 020b40f ("io_uring: make ctx->timeout_lock a raw spinlock")
Signed-off-by: Jens Axboe <axboe@kernel.dk>

…le_direct_reclaim()

The task sometimes continues looping in throttle_direct_reclaim() because
allow_direct_reclaim(pgdat) keeps returning false.  

 #0 [ffff80002cb6f8d0] __switch_to at ffff8000080095ac
 #1 [ffff80002cb6f900] __schedule at ffff800008abbd1c
 #2 [ffff80002cb6f990] schedule at ffff800008abc50c
 #3 [ffff80002cb6f9b0] throttle_direct_reclaim at ffff800008273550
 #4 [ffff80002cb6fa20] try_to_free_pages at ffff800008277b68
 #5 [ffff80002cb6fae0] __alloc_pages_nodemask at ffff8000082c4660
 #6 [ffff80002cb6fc50] alloc_pages_vma at ffff8000082e4a98
 #7 [ffff80002cb6fca0] do_anonymous_page at ffff80000829f5a8
 torvalds#8 [ffff80002cb6fce0] __handle_mm_fault at ffff8000082a5974
 torvalds#9 [ffff80002cb6fd90] handle_mm_fault at ffff8000082a5bd4

At this point, the pgdat contains the following two zones:

        NODE: 4  ZONE: 0  ADDR: ffff00817fffe540  NAME: "DMA32"
          SIZE: 20480  MIN/LOW/HIGH: 11/28/45
          VM_STAT:
                NR_FREE_PAGES: 359
        NR_ZONE_INACTIVE_ANON: 18813
          NR_ZONE_ACTIVE_ANON: 0
        NR_ZONE_INACTIVE_FILE: 50
          NR_ZONE_ACTIVE_FILE: 0
          NR_ZONE_UNEVICTABLE: 0
        NR_ZONE_WRITE_PENDING: 0
                     NR_MLOCK: 0
                    NR_BOUNCE: 0
                   NR_ZSPAGES: 0
            NR_FREE_CMA_PAGES: 0

        NODE: 4  ZONE: 1  ADDR: ffff00817fffec00  NAME: "Normal"
          SIZE: 8454144  PRESENT: 98304  MIN/LOW/HIGH: 68/166/264
          VM_STAT:
                NR_FREE_PAGES: 146
        NR_ZONE_INACTIVE_ANON: 94668
          NR_ZONE_ACTIVE_ANON: 3
        NR_ZONE_INACTIVE_FILE: 735
          NR_ZONE_ACTIVE_FILE: 78
          NR_ZONE_UNEVICTABLE: 0
        NR_ZONE_WRITE_PENDING: 0
                     NR_MLOCK: 0
                    NR_BOUNCE: 0
                   NR_ZSPAGES: 0
            NR_FREE_CMA_PAGES: 0

In allow_direct_reclaim(), while processing ZONE_DMA32, the sum of
inactive/active file-backed pages calculated in zone_reclaimable_pages()
based on the result of zone_page_state_snapshot() is zero.  

Additionally, since this system lacks swap, the calculation of inactive/
active anonymous pages is skipped.

        crash> p nr_swap_pages
        nr_swap_pages = $1937 = {
          counter = 0
        }

As a result, ZONE_DMA32 is deemed unreclaimable and skipped, moving on to
the processing of the next zone, ZONE_NORMAL, despite ZONE_DMA32 having
free pages significantly exceeding the high watermark.

The problem is that the pgdat->kswapd_failures hasn't been incremented.

        crash> px ((struct pglist_data *) 0xffff00817fffe540)->kswapd_failures
        $1935 = 0x0

This is because the node deemed balanced.  The node balancing logic in
balance_pgdat() evaluates all zones collectively.  If one or more zones
(e.g., ZONE_DMA32) have enough free pages to meet their watermarks, the
entire node is deemed balanced.  This causes balance_pgdat() to exit early
before incrementing the kswapd_failures, as it considers the overall
memory state acceptable, even though some zones (like ZONE_NORMAL) remain
under significant pressure.


The patch ensures that zone_reclaimable_pages() includes free pages
(NR_FREE_PAGES) in its calculation when no other reclaimable pages are
available (e.g., file-backed or anonymous pages).  This change prevents
zones like ZONE_DMA32, which have sufficient free pages, from being
mistakenly deemed unreclaimable.  By doing so, the patch ensures proper
node balancing, avoids masking pressure on other zones like ZONE_NORMAL,
and prevents infinite loops in throttle_direct_reclaim() caused by
allow_direct_reclaim(pgdat) repeatedly returning false.


The kernel hangs due to a task stuck in throttle_direct_reclaim(), caused
by a node being incorrectly deemed balanced despite pressure in certain
zones, such as ZONE_NORMAL.  This issue arises from
zone_reclaimable_pages() returning 0 for zones without reclaimable file-
backed or anonymous pages, causing zones like ZONE_DMA32 with sufficient
free pages to be skipped.

The lack of swap or reclaimable pages results in ZONE_DMA32 being ignored
during reclaim, masking pressure in other zones.  Consequently,
pgdat->kswapd_failures remains 0 in balance_pgdat(), preventing fallback
mechanisms in allow_direct_reclaim() from being triggered, leading to an
infinite loop in throttle_direct_reclaim().

This patch modifies zone_reclaimable_pages() to account for free pages
(NR_FREE_PAGES) when no other reclaimable pages exist.  This ensures zones
with sufficient free pages are not skipped, enabling proper balancing and
reclaim behavior.

[akpm@linux-foundation.org: coding-style cleanups]
Link: https://lkml.kernel.org/r/20241130164346.436469-1-snishika@redhat.com
Link: https://lkml.kernel.org/r/20241130161236.433747-2-snishika@redhat.com
Fixes: 5a1c84b ("mm: remove reclaim and compaction retry approximations")
Signed-off-by: Seiji Nishikawa <snishika@redhat.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

…nt message

Address a bug in the kernel that triggers a "sleeping function called from
invalid context" warning when /sys/kernel/debug/kmemleak is printed under
specific conditions:
- CONFIG_PREEMPT_RT=y
- Set SELinux as the LSM for the system
- Set kptr_restrict to 1
- kmemleak buffer contains at least one item

BUG: sleeping function called from invalid context at kernel/locking/spinlock_rt.c:48
in_atomic(): 1, irqs_disabled(): 1, non_block: 0, pid: 136, name: cat
preempt_count: 1, expected: 0
RCU nest depth: 2, expected: 2
6 locks held by cat/136:
 #0: ffff32e64bcbf950 (&p->lock){+.+.}-{3:3}, at: seq_read_iter+0xb8/0xe30
 #1: ffffafe6aaa9dea0 (scan_mutex){+.+.}-{3:3}, at: kmemleak_seq_start+0x34/0x128
 #3: ffff32e6546b1cd0 (&object->lock){....}-{2:2}, at: kmemleak_seq_show+0x3c/0x1e0
 #4: ffffafe6aa8d8560 (rcu_read_lock){....}-{1:2}, at: has_ns_capability_noaudit+0x8/0x1b0
 #5: ffffafe6aabbc0f8 (notif_lock){+.+.}-{2:2}, at: avc_compute_av+0xc4/0x3d0
irq event stamp: 136660
hardirqs last  enabled at (136659): [<ffffafe6a80fd7a0>] _raw_spin_unlock_irqrestore+0xa8/0xd8
hardirqs last disabled at (136660): [<ffffafe6a80fd85c>] _raw_spin_lock_irqsave+0x8c/0xb0
softirqs last  enabled at (0): [<ffffafe6a5d50b28>] copy_process+0x11d8/0x3df8
softirqs last disabled at (0): [<0000000000000000>] 0x0
Preemption disabled at:
[<ffffafe6a6598a4c>] kmemleak_seq_show+0x3c/0x1e0
CPU: 1 UID: 0 PID: 136 Comm: cat Tainted: G            E      6.11.0-rt7+ torvalds#34
Tainted: [E]=UNSIGNED_MODULE
Hardware name: linux,dummy-virt (DT)
Call trace:
 dump_backtrace+0xa0/0x128
 show_stack+0x1c/0x30
 dump_stack_lvl+0xe8/0x198
 dump_stack+0x18/0x20
 rt_spin_lock+0x8c/0x1a8
 avc_perm_nonode+0xa0/0x150
 cred_has_capability.isra.0+0x118/0x218
 selinux_capable+0x50/0x80
 security_capable+0x7c/0xd0
 has_ns_capability_noaudit+0x94/0x1b0
 has_capability_noaudit+0x20/0x30
 restricted_pointer+0x21c/0x4b0
 pointer+0x298/0x760
 vsnprintf+0x330/0xf70
 seq_printf+0x178/0x218
 print_unreferenced+0x1a4/0x2d0
 kmemleak_seq_show+0xd0/0x1e0
 seq_read_iter+0x354/0xe30
 seq_read+0x250/0x378
 full_proxy_read+0xd8/0x148
 vfs_read+0x190/0x918
 ksys_read+0xf0/0x1e0
 __arm64_sys_read+0x70/0xa8
 invoke_syscall.constprop.0+0xd4/0x1d8
 el0_svc+0x50/0x158
 el0t_64_sync+0x17c/0x180

%pS and %pK, in the same back trace line, are redundant, and %pS can void
%pK service in certain contexts.

%pS alone already provides the necessary information, and if it cannot
resolve the symbol, it falls back to printing the raw address voiding
the original intent behind the %pK.

Additionally, %pK requires a privilege check CAP_SYSLOG enforced through
the LSM, which can trigger a "sleeping function called from invalid
context" warning under RT_PREEMPT kernels when the check occurs in an
atomic context. This issue may also affect other LSMs.

This change avoids the unnecessary privilege check and resolves the
sleeping function warning without any loss of information.

Link: https://lkml.kernel.org/r/20241217142032.55793-1-acarmina@redhat.com
Fixes: 3a6f33d ("mm/kmemleak: use %pK to display kernel pointers in backtrace")
Signed-off-by: Alessandro Carminati <acarmina@redhat.com>
Acked-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Clément Léger <clement.leger@bootlin.com>
Cc: Alessandro Carminati <acarmina@redhat.com>
Cc: Eric Chanudet <echanude@redhat.com>
Cc: Gabriele Paoloni <gpaoloni@redhat.com>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

If GuC fails to load, the driver wedges, but in the process it tries to
do stuff that may not be initialized yet. This moves the
xe_gt_tlb_invalidation_init() to be done earlier: as its own doc says,
it's a software-only initialization and should had been named with the
_early() suffix.

Move it to be called by xe_gt_init_early(), so the locks and seqno are
initialized, avoiding a NULL ptr deref when wedging:

	xe 0000:03:00.0: [drm] *ERROR* GT0: load failed: status: Reset = 0, BootROM = 0x50, UKernel = 0x00, MIA = 0x00, Auth = 0x01
	xe 0000:03:00.0: [drm] *ERROR* GT0: firmware signature verification failed
	xe 0000:03:00.0: [drm] *ERROR* CRITICAL: Xe has declared device 0000:03:00.0 as wedged.
	...
	BUG: kernel NULL pointer dereference, address: 0000000000000000
	#PF: supervisor read access in kernel mode
	#PF: error_code(0x0000) - not-present page
	PGD 0 P4D 0
	Oops: Oops: 0000 [#1] PREEMPT SMP NOPTI
	CPU: 9 UID: 0 PID: 3908 Comm: modprobe Tainted: G     U  W          6.13.0-rc4-xe+ #3
	Tainted: [U]=USER, [W]=WARN
	Hardware name: Intel Corporation Alder Lake Client Platform/AlderLake-S ADP-S DDR5 UDIMM CRB, BIOS ADLSFWI1.R00.3275.A00.2207010640 07/01/2022
	RIP: 0010:xe_gt_tlb_invalidation_reset+0x75/0x110 [xe]

This can be easily triggered by poking the GuC binary to force a
signature failure. There will still be an extra message,

	xe 0000:03:00.0: [drm] *ERROR* GT0: GuC mmio request 0x4100: no reply 0x4100

but that's better than a NULL ptr deref.

Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/3956
Fixes: c9474b7 ("drm/xe: Wedge the entire device")
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250103001111.331684-2-lucas.demarchi@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
(cherry picked from commit 5001ef3)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>

We found a timeout problem with the pldm command on our system.  The
reason is that the MCTP-I3C driver has a race condition when receiving
multiple-packet messages in multi-thread, resulting in a wrong packet
order problem.

We identified this problem by adding a debug message to the
mctp_i3c_read function.

According to the MCTP spec, a multiple-packet message must be composed
in sequence, and if there is a wrong sequence, the whole message will be
discarded and wait for the next SOM.
For example, SOM → Pkt Seq #2 → Pkt Seq #1 → Pkt Seq #3 → EOM.

Therefore, we try to solve this problem by adding a mutex to the
mctp_i3c_read function.  Before the modification, when a command
requesting a multiple-packet message response is sent consecutively, an
error usually occurs within 100 loops.  After the mutex, it can go
through 40000 loops without any error, and it seems to run well.

Fixes: c8755b2 ("mctp i3c: MCTP I3C driver")
Signed-off-by: Leo Yang <Leo-Yang@quantatw.com>
Link: https://patch.msgid.link/20250107031529.3296094-1-Leo-Yang@quantatw.com
[pabeni@redhat.com: dropped already answered question from changelog]
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

…ux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm64 changes for 6.13, part #3

 - Always check page state in hyp_ack_unshare()

 - Align set_id_regs selftest with the fact that ASIDBITS field is RO

 - Various vPMU fixes for bugs that only affect nested virt

irq_chip functions may be called in raw spinlock context. Therefore, we
must also use a raw spinlock for our own internal locking.

This fixes the following lockdep splat:

[    5.349336] =============================
[    5.353349] [ BUG: Invalid wait context ]
[    5.357361] 6.13.0-rc5+ torvalds#69 Tainted: G        W
[    5.363031] -----------------------------
[    5.367045] kworker/u17:1/44 is trying to lock:
[    5.371587] ffffff88018b02c0 (&chip->gpio_lock){....}-{3:3}, at: xgpio_irq_unmask (drivers/gpio/gpio-xilinx.c:433 (discriminator 8))
[    5.380079] other info that might help us debug this:
[    5.385138] context-{5:5}
[    5.387762] 5 locks held by kworker/u17:1/44:
[    5.392123] #0: ffffff8800014958 ((wq_completion)events_unbound){+.+.}-{0:0}, at: process_one_work (kernel/workqueue.c:3204)
[    5.402260] #1: ffffffc082fcbdd8 (deferred_probe_work){+.+.}-{0:0}, at: process_one_work (kernel/workqueue.c:3205)
[    5.411528] #2: ffffff880172c900 (&dev->mutex){....}-{4:4}, at: __device_attach (drivers/base/dd.c:1006)
[    5.419929] #3: ffffff88039c8268 (request_class#2){+.+.}-{4:4}, at: __setup_irq (kernel/irq/internals.h:156 kernel/irq/manage.c:1596)
[    5.428331] #4: ffffff88039c80c8 (lock_class#2){....}-{2:2}, at: __setup_irq (kernel/irq/manage.c:1614)
[    5.436472] stack backtrace:
[    5.439359] CPU: 2 UID: 0 PID: 44 Comm: kworker/u17:1 Tainted: G        W          6.13.0-rc5+ torvalds#69
[    5.448690] Tainted: [W]=WARN
[    5.451656] Hardware name: xlnx,zynqmp (DT)
[    5.455845] Workqueue: events_unbound deferred_probe_work_func
[    5.461699] Call trace:
[    5.464147] show_stack+0x18/0x24 C
[    5.467821] dump_stack_lvl (lib/dump_stack.c:123)
[    5.471501] dump_stack (lib/dump_stack.c:130)
[    5.474824] __lock_acquire (kernel/locking/lockdep.c:4828 kernel/locking/lockdep.c:4898 kernel/locking/lockdep.c:5176)
[    5.478758] lock_acquire (arch/arm64/include/asm/percpu.h:40 kernel/locking/lockdep.c:467 kernel/locking/lockdep.c:5851 kernel/locking/lockdep.c:5814)
[    5.482429] _raw_spin_lock_irqsave (include/linux/spinlock_api_smp.h:111 kernel/locking/spinlock.c:162)
[    5.486797] xgpio_irq_unmask (drivers/gpio/gpio-xilinx.c:433 (discriminator 8))
[    5.490737] irq_enable (kernel/irq/internals.h:236 kernel/irq/chip.c:170 kernel/irq/chip.c:439 kernel/irq/chip.c:432 kernel/irq/chip.c:345)
[    5.494060] __irq_startup (kernel/irq/internals.h:241 kernel/irq/chip.c:180 kernel/irq/chip.c:250)
[    5.497645] irq_startup (kernel/irq/chip.c:270)
[    5.501143] __setup_irq (kernel/irq/manage.c:1807)
[    5.504728] request_threaded_irq (kernel/irq/manage.c:2208)

Fixes: a32c7ca ("gpio: gpio-xilinx: Add interrupt support")
Signed-off-by: Sean Anderson <sean.anderson@linux.dev>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250110163354.2012654-1-sean.anderson@linux.dev
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>

This commit addresses a circular locking dependency issue within the GFX
isolation mechanism. The problem was identified by a warning indicating
a potential deadlock due to inconsistent lock acquisition order.

- The `amdgpu_gfx_enforce_isolation_ring_begin_use` and
  `amdgpu_gfx_enforce_isolation_ring_end_use` functions previously
  acquired `enforce_isolation_mutex` and called `amdgpu_gfx_kfd_sch_ctrl`,
  leading to potential deadlocks. ie., If `amdgpu_gfx_kfd_sch_ctrl` is
  called while `enforce_isolation_mutex` is held, and
  `amdgpu_gfx_enforce_isolation_handler` is called while `kfd_sch_mutex` is
  held, it can create a circular dependency.

By ensuring consistent lock usage, this fix resolves the issue:

[  606.297333] ======================================================
[  606.297343] WARNING: possible circular locking dependency detected
[  606.297353] 6.10.0-amd-mlkd-610-311224-lof torvalds#19 Tainted: G           OE
[  606.297365] ------------------------------------------------------
[  606.297375] kworker/u96:3/3825 is trying to acquire lock:
[  606.297385] ffff9aa64e431cb8 ((work_completion)(&(&adev->gfx.enforce_isolation[i].work)->work)){+.+.}-{0:0}, at: __flush_work+0x232/0x610
[  606.297413]
               but task is already holding lock:
[  606.297423] ffff9aa64e432338 (&adev->gfx.kfd_sch_mutex){+.+.}-{3:3}, at: amdgpu_gfx_kfd_sch_ctrl+0x51/0x4d0 [amdgpu]
[  606.297725]
               which lock already depends on the new lock.

[  606.297738]
               the existing dependency chain (in reverse order) is:
[  606.297749]
               -> #2 (&adev->gfx.kfd_sch_mutex){+.+.}-{3:3}:
[  606.297765]        __mutex_lock+0x85/0x930
[  606.297776]        mutex_lock_nested+0x1b/0x30
[  606.297786]        amdgpu_gfx_kfd_sch_ctrl+0x51/0x4d0 [amdgpu]
[  606.298007]        amdgpu_gfx_enforce_isolation_ring_begin_use+0x2a4/0x5d0 [amdgpu]
[  606.298225]        amdgpu_ring_alloc+0x48/0x70 [amdgpu]
[  606.298412]        amdgpu_ib_schedule+0x176/0x8a0 [amdgpu]
[  606.298603]        amdgpu_job_run+0xac/0x1e0 [amdgpu]
[  606.298866]        drm_sched_run_job_work+0x24f/0x430 [gpu_sched]
[  606.298880]        process_one_work+0x21e/0x680
[  606.298890]        worker_thread+0x190/0x350
[  606.298899]        kthread+0xe7/0x120
[  606.298908]        ret_from_fork+0x3c/0x60
[  606.298919]        ret_from_fork_asm+0x1a/0x30
[  606.298929]
               -> #1 (&adev->enforce_isolation_mutex){+.+.}-{3:3}:
[  606.298947]        __mutex_lock+0x85/0x930
[  606.298956]        mutex_lock_nested+0x1b/0x30
[  606.298966]        amdgpu_gfx_enforce_isolation_handler+0x87/0x370 [amdgpu]
[  606.299190]        process_one_work+0x21e/0x680
[  606.299199]        worker_thread+0x190/0x350
[  606.299208]        kthread+0xe7/0x120
[  606.299217]        ret_from_fork+0x3c/0x60
[  606.299227]        ret_from_fork_asm+0x1a/0x30
[  606.299236]
               -> #0 ((work_completion)(&(&adev->gfx.enforce_isolation[i].work)->work)){+.+.}-{0:0}:
[  606.299257]        __lock_acquire+0x16f9/0x2810
[  606.299267]        lock_acquire+0xd1/0x300
[  606.299276]        __flush_work+0x250/0x610
[  606.299286]        cancel_delayed_work_sync+0x71/0x80
[  606.299296]        amdgpu_gfx_kfd_sch_ctrl+0x287/0x4d0 [amdgpu]
[  606.299509]        amdgpu_gfx_enforce_isolation_ring_begin_use+0x2a4/0x5d0 [amdgpu]
[  606.299723]        amdgpu_ring_alloc+0x48/0x70 [amdgpu]
[  606.299909]        amdgpu_ib_schedule+0x176/0x8a0 [amdgpu]
[  606.300101]        amdgpu_job_run+0xac/0x1e0 [amdgpu]
[  606.300355]        drm_sched_run_job_work+0x24f/0x430 [gpu_sched]
[  606.300369]        process_one_work+0x21e/0x680
[  606.300378]        worker_thread+0x190/0x350
[  606.300387]        kthread+0xe7/0x120
[  606.300396]        ret_from_fork+0x3c/0x60
[  606.300406]        ret_from_fork_asm+0x1a/0x30
[  606.300416]
               other info that might help us debug this:

[  606.300428] Chain exists of:
                 (work_completion)(&(&adev->gfx.enforce_isolation[i].work)->work) --> &adev->enforce_isolation_mutex --> &adev->gfx.kfd_sch_mutex

[  606.300458]  Possible unsafe locking scenario:

[  606.300468]        CPU0                    CPU1
[  606.300476]        ----                    ----
[  606.300484]   lock(&adev->gfx.kfd_sch_mutex);
[  606.300494]                                lock(&adev->enforce_isolation_mutex);
[  606.300508]                                lock(&adev->gfx.kfd_sch_mutex);
[  606.300521]   lock((work_completion)(&(&adev->gfx.enforce_isolation[i].work)->work));
[  606.300536]
                *** DEADLOCK ***

[  606.300546] 5 locks held by kworker/u96:3/3825:
[  606.300555]  #0: ffff9aa5aa1f5d58 ((wq_completion)comp_1.1.0){+.+.}-{0:0}, at: process_one_work+0x3f5/0x680
[  606.300577]  #1: ffffaa53c3c97e40 ((work_completion)(&sched->work_run_job)){+.+.}-{0:0}, at: process_one_work+0x1d6/0x680
[  606.300600]  #2: ffff9aa64e463c98 (&adev->enforce_isolation_mutex){+.+.}-{3:3}, at: amdgpu_gfx_enforce_isolation_ring_begin_use+0x1c3/0x5d0 [amdgpu]
[  606.300837]  #3: ffff9aa64e432338 (&adev->gfx.kfd_sch_mutex){+.+.}-{3:3}, at: amdgpu_gfx_kfd_sch_ctrl+0x51/0x4d0 [amdgpu]
[  606.301062]  #4: ffffffff8c1a5660 (rcu_read_lock){....}-{1:2}, at: __flush_work+0x70/0x610
[  606.301083]
               stack backtrace:
[  606.301092] CPU: 14 PID: 3825 Comm: kworker/u96:3 Tainted: G           OE      6.10.0-amd-mlkd-610-311224-lof torvalds#19
[  606.301109] Hardware name: Gigabyte Technology Co., Ltd. X570S GAMING X/X570S GAMING X, BIOS F7 03/22/2024
[  606.301124] Workqueue: comp_1.1.0 drm_sched_run_job_work [gpu_sched]
[  606.301140] Call Trace:
[  606.301146]  <TASK>
[  606.301154]  dump_stack_lvl+0x9b/0xf0
[  606.301166]  dump_stack+0x10/0x20
[  606.301175]  print_circular_bug+0x26c/0x340
[  606.301187]  check_noncircular+0x157/0x170
[  606.301197]  ? register_lock_class+0x48/0x490
[  606.301213]  __lock_acquire+0x16f9/0x2810
[  606.301230]  lock_acquire+0xd1/0x300
[  606.301239]  ? __flush_work+0x232/0x610
[  606.301250]  ? srso_alias_return_thunk+0x5/0xfbef5
[  606.301261]  ? mark_held_locks+0x54/0x90
[  606.301274]  ? __flush_work+0x232/0x610
[  606.301284]  __flush_work+0x250/0x610
[  606.301293]  ? __flush_work+0x232/0x610
[  606.301305]  ? __pfx_wq_barrier_func+0x10/0x10
[  606.301318]  ? mark_held_locks+0x54/0x90
[  606.301331]  ? srso_alias_return_thunk+0x5/0xfbef5
[  606.301345]  cancel_delayed_work_sync+0x71/0x80
[  606.301356]  amdgpu_gfx_kfd_sch_ctrl+0x287/0x4d0 [amdgpu]
[  606.301661]  amdgpu_gfx_enforce_isolation_ring_begin_use+0x2a4/0x5d0 [amdgpu]
[  606.302050]  ? srso_alias_return_thunk+0x5/0xfbef5
[  606.302069]  amdgpu_ring_alloc+0x48/0x70 [amdgpu]
[  606.302452]  amdgpu_ib_schedule+0x176/0x8a0 [amdgpu]
[  606.302862]  ? drm_sched_entity_error+0x82/0x190 [gpu_sched]
[  606.302890]  amdgpu_job_run+0xac/0x1e0 [amdgpu]
[  606.303366]  drm_sched_run_job_work+0x24f/0x430 [gpu_sched]
[  606.303388]  process_one_work+0x21e/0x680
[  606.303409]  worker_thread+0x190/0x350
[  606.303424]  ? __pfx_worker_thread+0x10/0x10
[  606.303437]  kthread+0xe7/0x120
[  606.303449]  ? __pfx_kthread+0x10/0x10
[  606.303463]  ret_from_fork+0x3c/0x60
[  606.303476]  ? __pfx_kthread+0x10/0x10
[  606.303489]  ret_from_fork_asm+0x1a/0x30
[  606.303512]  </TASK>

v2: Refactor lock handling to resolve circular dependency (Alex)

- Introduced a `sched_work` flag to defer the call to
  `amdgpu_gfx_kfd_sch_ctrl` until after releasing
  `enforce_isolation_mutex`.
- This change ensures that `amdgpu_gfx_kfd_sch_ctrl` is called outside
  the critical section, preventing the circular dependency and deadlock.
- The `sched_work` flag is set within the mutex-protected section if
  conditions are met, and the actual function call is made afterward.
- This approach ensures consistent lock acquisition order.

Fixes: afefd6f ("drm/amdgpu: Implement Enforce Isolation Handler for KGD/KFD serialization")
Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Suggested-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 0b6b2dd)
Cc: stable@vger.kernel.org

Fix a lockdep warning [1] observed during the write combining test.

The warning indicates a potential nested lock scenario that could lead
to a deadlock.

However, this is a false positive alarm because the SF lock and its
parent lock are distinct ones.

The lockdep confusion arises because the locks belong to the same object
class (i.e., struct mlx5_core_dev).

To resolve this, the code has been refactored to avoid taking both
locks. Instead, only the parent lock is acquired.

[1]
raw_ethernet_bw/2118 is trying to acquire lock:
[  213.619032] ffff88811dd75e08 (&dev->wc_state_lock){+.+.}-{3:3}, at:
               mlx5_wc_support_get+0x18c/0x210 [mlx5_core]
[  213.620270]
[  213.620270] but task is already holding lock:
[  213.620943] ffff88810b585e08 (&dev->wc_state_lock){+.+.}-{3:3}, at:
               mlx5_wc_support_get+0x10c/0x210 [mlx5_core]
[  213.622045]
[  213.622045] other info that might help us debug this:
[  213.622778]  Possible unsafe locking scenario:
[  213.622778]
[  213.623465]        CPU0
[  213.623815]        ----
[  213.624148]   lock(&dev->wc_state_lock);
[  213.624615]   lock(&dev->wc_state_lock);
[  213.625071]
[  213.625071]  *** DEADLOCK ***
[  213.625071]
[  213.625805]  May be due to missing lock nesting notation
[  213.625805]
[  213.626522] 4 locks held by raw_ethernet_bw/2118:
[  213.627019]  #0: ffff88813f80d578 (&uverbs_dev->disassociate_srcu){.+.+}-{0:0},
                at: ib_uverbs_ioctl+0xc4/0x170 [ib_uverbs]
[  213.628088]  #1: ffff88810fb23930 (&file->hw_destroy_rwsem){.+.+}-{3:3},
                at: ib_init_ucontext+0x2d/0xf0 [ib_uverbs]
[  213.629094]  #2: ffff88810fb23878 (&file->ucontext_lock){+.+.}-{3:3},
                at: ib_init_ucontext+0x49/0xf0 [ib_uverbs]
[  213.630106]  #3: ffff88810b585e08 (&dev->wc_state_lock){+.+.}-{3:3},
                at: mlx5_wc_support_get+0x10c/0x210 [mlx5_core]
[  213.631185]
[  213.631185] stack backtrace:
[  213.631718] CPU: 1 UID: 0 PID: 2118 Comm: raw_ethernet_bw Not tainted
               6.12.0-rc7_internal_net_next_mlx5_89a0ad0 #1
[  213.632722] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS
               rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
[  213.633785] Call Trace:
[  213.634099]
[  213.634393]  dump_stack_lvl+0x7e/0xc0
[  213.634806]  print_deadlock_bug+0x278/0x3c0
[  213.635265]  __lock_acquire+0x15f4/0x2c40
[  213.635712]  lock_acquire+0xcd/0x2d0
[  213.636120]  ? mlx5_wc_support_get+0x18c/0x210 [mlx5_core]
[  213.636722]  ? mlx5_ib_enable_lb+0x24/0xa0 [mlx5_ib]
[  213.637277]  __mutex_lock+0x81/0xda0
[  213.637697]  ? mlx5_wc_support_get+0x18c/0x210 [mlx5_core]
[  213.638305]  ? mlx5_wc_support_get+0x18c/0x210 [mlx5_core]
[  213.638902]  ? rcu_read_lock_sched_held+0x3f/0x70
[  213.639400]  ? mlx5_wc_support_get+0x18c/0x210 [mlx5_core]
[  213.640016]  mlx5_wc_support_get+0x18c/0x210 [mlx5_core]
[  213.640615]  set_ucontext_resp+0x68/0x2b0 [mlx5_ib]
[  213.641144]  ? debug_mutex_init+0x33/0x40
[  213.641586]  mlx5_ib_alloc_ucontext+0x18e/0x7b0 [mlx5_ib]
[  213.642145]  ib_init_ucontext+0xa0/0xf0 [ib_uverbs]
[  213.642679]  ib_uverbs_handler_UVERBS_METHOD_GET_CONTEXT+0x95/0xc0
                [ib_uverbs]
[  213.643426]  ? _copy_from_user+0x46/0x80
[  213.643878]  ib_uverbs_cmd_verbs+0xa6b/0xc80 [ib_uverbs]
[  213.644426]  ? ib_uverbs_handler_UVERBS_METHOD_INVOKE_WRITE+0x130/0x130
               [ib_uverbs]
[  213.645213]  ? __lock_acquire+0xa99/0x2c40
[  213.645675]  ? lock_acquire+0xcd/0x2d0
[  213.646101]  ? ib_uverbs_ioctl+0xc4/0x170 [ib_uverbs]
[  213.646625]  ? reacquire_held_locks+0xcf/0x1f0
[  213.647102]  ? do_user_addr_fault+0x45d/0x770
[  213.647586]  ib_uverbs_ioctl+0xe0/0x170 [ib_uverbs]
[  213.648102]  ? ib_uverbs_ioctl+0xc4/0x170 [ib_uverbs]
[  213.648632]  __x64_sys_ioctl+0x4d3/0xaa0
[  213.649060]  ? do_user_addr_fault+0x4a8/0x770
[  213.649528]  do_syscall_64+0x6d/0x140
[  213.649947]  entry_SYSCALL_64_after_hwframe+0x4b/0x53
[  213.650478] RIP: 0033:0x7fa179b0737b
[  213.650893] Code: ff ff ff 85 c0 79 9b 49 c7 c4 ff ff ff ff 5b 5d 4c
               89 e0 41 5c c3 66 0f 1f 84 00 00 00 00 00 f3 0f 1e fa b8
               10 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d
               7d 2a 0f 00 f7 d8 64 89 01 48
[  213.652619] RSP: 002b:00007ffd2e6d46e8 EFLAGS: 00000246 ORIG_RAX:
               0000000000000010
[  213.653390] RAX: ffffffffffffffda RBX: 00007ffd2e6d47f8 RCX:
               00007fa179b0737b
[  213.654084] RDX: 00007ffd2e6d47e0 RSI: 00000000c0181b01 RDI:
               0000000000000003
[  213.654767] RBP: 00007ffd2e6d47c0 R08: 00007fa1799be010 R09:
               0000000000000002
[  213.655453] R10: 00007ffd2e6d4960 R11: 0000000000000246 R12:
               00007ffd2e6d487c
[  213.656170] R13: 0000000000000027 R14: 0000000000000001 R15:
               00007ffd2e6d4f70

Fixes: d98995b ("net/mlx5: Reimplement write combining test")
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Reviewed-by: Michael Guralnik <michaelgur@nvidia.com>
Reviewed-by: Larysa Zaremba <larysa.zaremba@intel.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

libtraceevent parses and returns an array of argument fields, sometimes
larger than RAW_SYSCALL_ARGS_NUM (6) because it includes "__syscall_nr",
idx will traverse to index 6 (7th element) whereas sc->fmt->arg holds 6
elements max, creating an out-of-bounds access. This runtime error is
found by UBsan. The error message:

  $ sudo UBSAN_OPTIONS=print_stacktrace=1 ./perf trace -a --max-events=1
  builtin-trace.c:1966:35: runtime error: index 6 out of bounds for type 'syscall_arg_fmt [6]'
    #0 0x5c04956be5fe in syscall__alloc_arg_fmts /home/howard/hw/linux-perf/tools/perf/builtin-trace.c:1966
    #1 0x5c04956c0510 in trace__read_syscall_info /home/howard/hw/linux-perf/tools/perf/builtin-trace.c:2110
    #2 0x5c04956c372b in trace__syscall_info /home/howard/hw/linux-perf/tools/perf/builtin-trace.c:2436
    #3 0x5c04956d2f39 in trace__init_syscalls_bpf_prog_array_maps /home/howard/hw/linux-perf/tools/perf/builtin-trace.c:3897
    #4 0x5c04956d6d25 in trace__run /home/howard/hw/linux-perf/tools/perf/builtin-trace.c:4335
    #5 0x5c04956e112e in cmd_trace /home/howard/hw/linux-perf/tools/perf/builtin-trace.c:5502
    #6 0x5c04956eda7d in run_builtin /home/howard/hw/linux-perf/tools/perf/perf.c:351
    #7 0x5c04956ee0a8 in handle_internal_command /home/howard/hw/linux-perf/tools/perf/perf.c:404
    torvalds#8 0x5c04956ee37f in run_argv /home/howard/hw/linux-perf/tools/perf/perf.c:448
    torvalds#9 0x5c04956ee8e9 in main /home/howard/hw/linux-perf/tools/perf/perf.c:556
    torvalds#10 0x79eb3622a3b7 in __libc_start_call_main ../sysdeps/nptl/libc_start_call_main.h:58
    torvalds#11 0x79eb3622a47a in __libc_start_main_impl ../csu/libc-start.c:360
    torvalds#12 0x5c04955422d4 in _start (/home/howard/hw/linux-perf/tools/perf/perf+0x4e02d4) (BuildId: 5b6cab2d59e96a4341741765ad6914a4d784dbc6)

     0.000 ( 0.014 ms): Chrome_ChildIO/117244 write(fd: 238, buf: !, count: 1)                                      = 1

Fixes: 5e58fcf ("perf trace: Allow allocating sc->arg_fmt even without the syscall tracepoint")
Signed-off-by: Howard Chu <howardchu95@gmail.com>
Link: https://lore.kernel.org/r/20250122025519.361873-1-howardchu95@gmail.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>

This fixes the following hard lockup in isolate_lru_folios() during memory
reclaim.  If the LRU mostly contains ineligible folios this may trigger
watchdog.

watchdog: Watchdog detected hard LOCKUP on cpu 173
RIP: 0010:native_queued_spin_lock_slowpath+0x255/0x2a0
Call Trace:
	_raw_spin_lock_irqsave+0x31/0x40
	folio_lruvec_lock_irqsave+0x5f/0x90
	folio_batch_move_lru+0x91/0x150
	lru_add_drain_per_cpu+0x1c/0x40
	process_one_work+0x17d/0x350
	worker_thread+0x27b/0x3a0
	kthread+0xe8/0x120
	ret_from_fork+0x34/0x50
	ret_from_fork_asm+0x1b/0x30

lruvec->lru_lock owner：

PID: 2865     TASK: ffff888139214d40  CPU: 40   COMMAND: "kswapd0"
 #0 [fffffe0000945e60] crash_nmi_callback at ffffffffa567a555
 #1 [fffffe0000945e68] nmi_handle at ffffffffa563b171
 #2 [fffffe0000945eb0] default_do_nmi at ffffffffa6575920
 #3 [fffffe0000945ed0] exc_nmi at ffffffffa6575af4
 #4 [fffffe0000945ef0] end_repeat_nmi at ffffffffa6601dde
    [exception RIP: isolate_lru_folios+403]
    RIP: ffffffffa597df53  RSP: ffffc90006fb7c28  RFLAGS: 00000002
    RAX: 0000000000000001  RBX: ffffc90006fb7c60  RCX: ffffea04a2196f88
    RDX: ffffc90006fb7c60  RSI: ffffc90006fb7c60  RDI: ffffea04a2197048
    RBP: ffff88812cbd3010   R8: ffffea04a2197008   R9: 0000000000000001
    R10: 0000000000000000  R11: 0000000000000001  R12: ffffea04a2197008
    R13: ffffea04a2197048  R14: ffffc90006fb7de8  R15: 0000000003e3e937
    ORIG_RAX: ffffffffffffffff  CS: 0010  SS: 0018
    <NMI exception stack>
 #5 [ffffc90006fb7c28] isolate_lru_folios at ffffffffa597df53
 #6 [ffffc90006fb7cf8] shrink_active_list at ffffffffa597f788
 #7 [ffffc90006fb7da8] balance_pgdat at ffffffffa5986db0
 torvalds#8 [ffffc90006fb7ec0] kswapd at ffffffffa5987354
 torvalds#9 [ffffc90006fb7ef8] kthread at ffffffffa5748238
crash>

Scenario:
User processe are requesting a large amount of memory and keep page active.
Then a module continuously requests memory from ZONE_DMA32 area.
Memory reclaim will be triggered due to ZONE_DMA32 watermark alarm reached.
However pages in the LRU(active_anon) list are mostly from
the ZONE_NORMAL area.

Reproduce:
Terminal 1: Construct to continuously increase pages active(anon).
mkdir /tmp/memory
mount -t tmpfs -o size=1024000M tmpfs /tmp/memory
dd if=/dev/zero of=/tmp/memory/block bs=4M
tail /tmp/memory/block

Terminal 2:
vmstat -a 1
active will increase.
procs ---memory--- ---swap-- ---io---- -system-- ---cpu--- ...
 r  b   swpd   free  inact active   si   so    bi    bo
 1  0   0 1445623076 45898836 83646008    0    0     0
 1  0   0 1445623076 43450228 86094616    0    0     0
 1  0   0 1445623076 41003480 88541364    0    0     0
 1  0   0 1445623076 38557088 90987756    0    0     0
 1  0   0 1445623076 36109688 93435156    0    0     0
 1  0   0 1445619552 33663256 95881632    0    0     0
 1  0   0 1445619804 31217140 98327792    0    0     0
 1  0   0 1445619804 28769988 100774944    0    0     0
 1  0   0 1445619804 26322348 103222584    0    0     0
 1  0   0 1445619804 23875592 105669340    0    0     0

cat /proc/meminfo | head
Active(anon) increase.
MemTotal:       1579941036 kB
MemFree:        1445618500 kB
MemAvailable:   1453013224 kB
Buffers:            6516 kB
Cached:         128653956 kB
SwapCached:            0 kB
Active:         118110812 kB
Inactive:       11436620 kB
Active(anon):   115345744 kB
Inactive(anon):   945292 kB

When the Active(anon) is 115345744 kB, insmod module triggers
the ZONE_DMA32 watermark.

perf record -e vmscan:mm_vmscan_lru_isolate -aR
perf script
isolate_mode=0 classzone=1 order=1 nr_requested=32 nr_scanned=2
nr_skipped=2 nr_taken=0 lru=active_anon
isolate_mode=0 classzone=1 order=1 nr_requested=32 nr_scanned=0
nr_skipped=0 nr_taken=0 lru=active_anon
isolate_mode=0 classzone=1 order=0 nr_requested=32 nr_scanned=28835844
nr_skipped=28835844 nr_taken=0 lru=active_anon
isolate_mode=0 classzone=1 order=1 nr_requested=32 nr_scanned=28835844
nr_skipped=28835844 nr_taken=0 lru=active_anon
isolate_mode=0 classzone=1 order=0 nr_requested=32 nr_scanned=29
nr_skipped=29 nr_taken=0 lru=active_anon
isolate_mode=0 classzone=1 order=0 nr_requested=32 nr_scanned=0
nr_skipped=0 nr_taken=0 lru=active_anon

See nr_scanned=28835844.
28835844 * 4k = 115343376KB approximately equal to 115345744 kB.

If increase Active(anon) to 1000G then insmod module triggers
the ZONE_DMA32 watermark. hard lockup will occur.

In my device nr_scanned = 0000000003e3e937 when hard lockup.
Convert to memory size 0x0000000003e3e937 * 4KB = 261072092 KB.

   [ffffc90006fb7c28] isolate_lru_folios at ffffffffa597df53
    ffffc90006fb7c30: 0000000000000020 0000000000000000
    ffffc90006fb7c40: ffffc90006fb7d40 ffff88812cbd3000
    ffffc90006fb7c50: ffffc90006fb7d30 0000000106fb7de8
    ffffc90006fb7c60: ffffea04a2197008 ffffea0006ed4a48
    ffffc90006fb7c70: 0000000000000000 0000000000000000
    ffffc90006fb7c80: 0000000000000000 0000000000000000
    ffffc90006fb7c90: 0000000000000000 0000000000000000
    ffffc90006fb7ca0: 0000000000000000 0000000003e3e937
    ffffc90006fb7cb0: 0000000000000000 0000000000000000
    ffffc90006fb7cc0: 8d7c0b56b7874b00 ffff88812cbd3000

About the Fixes:
Why did it take eight years to be discovered?

The problem requires the following conditions to occur:
1. The device memory should be large enough.
2. Pages in the LRU(active_anon) list are mostly from the ZONE_NORMAL area.
3. The memory in ZONE_DMA32 needs to reach the watermark.

If the memory is not large enough, or if the usage design of ZONE_DMA32
area memory is reasonable, this problem is difficult to detect.

notes:
The problem is most likely to occur in ZONE_DMA32 and ZONE_NORMAL,
but other suitable scenarios may also trigger the problem.

Link: https://lkml.kernel.org/r/20241119060842.274072-1-liuye@kylinos.cn
Fixes: b2e1875 ("mm, vmscan: begin reclaiming pages on a per-node basis")
Signed-off-by: liuye <liuye@kylinos.cn>
Cc: Hugh Dickins <hughd@google.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Yang Shi <yang@os.amperecomputing.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>