Except for waiting_for_gp list, there are no concurrent operations on
free_by_rcu, free_llist and free_llist_extra lists, so use
__llist_del_all() instead of llist_del_all(). waiting_for_gp list can be
deleted by RCU callback concurrently, so still use llist_del_all().

Acked-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/r/20221021114913.60508-3-houtao@huaweicloud.com


Signed-off-by: Alexei Starovoitov <ast@kernel.org>

A busy irq work is an unfinished irq work and it can be either in the
pending state or in the running state. When destroying bpf memory
allocator, refill_work may be busy for PREEMPT_RT kernel in which irq
work is invoked in a per-CPU RT-kthread. It is also possible for kernel
with arch_irq_work_has_interrupt() being false (e.g. 1-cpu arm32 host or
mips) and irq work is inovked in timer interrupt.

The busy refill_work leads to various issues. The obvious one is that
there will be concurrent operations on free_by_rcu and free_list between
irq work and memory draining. Another one is call_rcu_in_progress will
not be reliable for the checking of pending RCU callback because
do_call_rcu() may have not been invoked by irq work yet. The other is
there will be use-after-free if irq work is freed before the callback
of irq work is invoked as shown below:

 BUG: kernel NULL pointer dereference, address: 0000000000000000
 #PF: supervisor instruction fetch in kernel mode
 #PF: error_code(0x0010) - not-present page
 PGD 12ab94067 P4D 12ab94067 PUD 1796b4067 PMD 0
 Oops: 0010 [#1] PREEMPT_RT SMP
 CPU: 5 PID: 64 Comm: irq_work/5 Not tainted 6.0.0-rt11+ #1
 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996)
 RIP: 0010:0x0
 Code: Unable to access opcode bytes at 0xffffffffffffffd6.
 RSP: 0018:ffffadc080293e78 EFLAGS: 00010286
 RAX: 0000000000000000 RBX: ffffcdc07fb6a388 RCX: ffffa05000a2e000
 RDX: ffffa05000a2e000 RSI: ffffffff96cc9827 RDI: ffffcdc07fb6a388
 ......
 Call Trace:
  <TASK>
  irq_work_single+0x24/0x60
  irq_work_run_list+0x24/0x30
  run_irq_workd+0x23/0x30
  smpboot_thread_fn+0x203/0x300
  kthread+0x126/0x150
  ret_from_fork+0x1f/0x30
  </TASK>

Considering the ease of concurrency handling, no overhead for
irq_work_sync() under non-PREEMPT_RT kernel and has-irq-work-interrupt
kernel and the short wait time used for irq_work_sync() under PREEMPT_RT
(When running two test_maps on PREEMPT_RT kernel and 72-cpus host, the
max wait time is about 8ms and the 99th percentile is 10us), just using
irq_work_sync() to wait for busy refill_work to complete before memory
draining and memory freeing.

Fixes: 7c8199e2

 ("bpf: Introduce any context BPF specific memory allocator.")
Acked-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/r/20221021114913.60508-2-houtao@huaweicloud.com


Signed-off-by: Alexei Starovoitov <ast@kernel.org>

The patchable_function_entry(5) might output 5 single nop
instructions (depends on toolchain), which will clash with
bpf_arch_text_poke check for 5 bytes nop instruction.

Adding early init call for dispatcher that checks and change
the patchable entry into expected 5 nop instruction if needed.

There's no need to take text_mutex, because we are using it
in early init call which is called at pre-smp time.

Fixes: ceea991a

 ("bpf: Move bpf_dispatcher function out of ftrace locations")
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20221018075934.574415-1-jolsa@kernel.org


Signed-off-by: Alexei Starovoitov <ast@kernel.org>

Syzkaller was able to hit the following issue:

------------[ cut here ]------------
WARNING: CPU: 0 PID: 3609 at kernel/bpf/btf.c:1946
btf_type_id_size+0x2d5/0x9d0 kernel/bpf/btf.c:1946
Modules linked in:
CPU: 0 PID: 3609 Comm: syz-executor361 Not tainted
6.0.0-syzkaller-02734-g0326074f #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
Google 09/22/2022
RIP: 0010:btf_type_id_size+0x2d5/0x9d0 kernel/bpf/btf.c:1946
Code: ef e8 7f 8e e4 ff 41 83 ff 0b 77 28 f6 44 24 10 18 75 3f e8 6d 91
e4 ff 44 89 fe bf 0e 00 00 00 e8 20 8e e4 ff e8 5b 91 e4 ff <0f> 0b 45
31 f6 e9 98 02 00 00 41 83 ff 12 74 18 e8 46 91 e4 ff 44
RSP: 0018:ffffc90003cefb40 EFLAGS: 00010293
RAX: 0000000000000000 RBX: 0000000000000002 RCX: 0000000000000000
RDX: ffff8880259c0000 RSI: ffffffff81968415 RDI: 0000000000000005
RBP: ffff88801270ca00 R08: 0000000000000005 R09: 000000000000000e
R10: 0000000000000011 R11: 0000000000000000 R12: 0000000000000000
R13: 0000000000000011 R14: ffff888026ee6424 R15: 0000000000000011
FS:  000055555641b300(0000) GS:ffff8880b9a00000(0000)
knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000f2e258 CR3: 000000007110e000 CR4: 00000000003506f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 <TASK>
 btf_func_proto_check kernel/bpf/btf.c:4447 [inline]
 btf_check_all_types kernel/bpf/btf.c:4723 [inline]
 btf_parse_type_sec kernel/bpf/btf.c:4752 [inline]
 btf_parse kernel/bpf/btf.c:5026 [inline]
 btf_new_fd+0x1926/0x1e70 kernel/bpf/btf.c:6892
 bpf_btf_load kernel/bpf/syscall.c:4324 [inline]
 __sys_bpf+0xb7d/0x4cf0 kernel/bpf/syscall.c:5010
 __do_sys_bpf kernel/bpf/syscall.c:5069 [inline]
 __se_sys_bpf kernel/bpf/syscall.c:5067 [inline]
 __x64_sys_bpf+0x75/0xb0 kernel/bpf/syscall.c:5067
 do_syscall_x64 arch/x86/entry/common.c:50 [inline]
 do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80
 entry_SYSCALL_64_after_hwframe+0x63/0xcd
RIP: 0033:0x7f0fbae41c69
Code: 28 c3 e8 2a 14 00 00 66 2e 0f 1f 84 00 00 00 00 00 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 c0 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007ffc8aeb6228 EFLAGS: 00000246 ORIG_RAX: 0000000000000141
RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f0fbae41c69
RDX: 0000000000000020 RSI: 0000000020000140 RDI: 0000000000000012
RBP: 00007f0fbae05e10 R08: 0000000000000000 R09: 0000000000000000
R10: 00000000ffffffff R11: 0000000000000246 R12: 00007f0fbae05ea0
R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
 </TASK>

Looks like it tries to create a func_proto which return type is
decl_tag. For the details, see Martin's spot on analysis in [0].

0: https://lore.kernel.org/bpf/CAKH8qBuQDLva_hHxxBuZzyAcYNO4ejhovz6TQeVSk8HY-2SO6g@mail.gmail.com/T/#mea6524b3fcd6298347432226e81b1e6155efc62c

Cc: Yonghong Song <yhs@fb.com>
Cc: Martin KaFai Lau <martin.lau@kernel.org>
Fixes: bd16dee6

 ("bpf: Add BTF_KIND_DECL_TAG typedef support")
Reported-by:  <syzbot+d8bd751aef7c6b39a344@syzkaller.appspotmail.com>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/r/20221015002444.2680969-2-sdf@google.com


Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>

It should trigger a WARN_ON_ONCE in btf_type_id_size.

     btf_func_proto_check kernel/bpf/btf.c:4447 [inline]
     btf_check_all_types kernel/bpf/btf.c:4723 [inline]
     btf_parse_type_sec kernel/bpf/btf.c:4752 [inline]
     btf_parse kernel/bpf/btf.c:5026 [inline]
     btf_new_fd+0x1926/0x1e70 kernel/bpf/btf.c:6892
     bpf_btf_load kernel/bpf/syscall.c:4324 [inline]
     __sys_bpf+0xb7d/0x4cf0 kernel/bpf/syscall.c:5010
     __do_sys_bpf kernel/bpf/syscall.c:5069 [inline]
     __se_sys_bpf kernel/bpf/syscall.c:5067 [inline]
     __x64_sys_bpf+0x75/0xb0 kernel/bpf/syscall.c:5067
     do_syscall_x64 arch/x86/entry/common.c:50 [inline]
     do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80
     entry_SYSCALL_64_after_hwframe+0x63/0xcd

Cc: Yonghong Song <yhs@fb.com>
Cc: Martin KaFai Lau <martin.lau@kernel.org>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/r/20221015002444.2680969-1-sdf@google.com


Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>

David Vernet says:

====================
The bpf_user_ringbuf_drain() helper function allows a BPF program to
specify a callback that is invoked when draining entries from a
BPF_MAP_TYPE_USER_RINGBUF ring buffer map. The API is meant to allow the
callback to return 0 if it wants to continue draining samples, and 1 if
it's done draining. Unfortunately, bpf_user_ringbuf_drain() landed shortly
after commit 1bfe26fb

 ("bpf: Add verifier support for custom
callback return range"), which changed the default behavior of callbacks
to only support returning 0, and the corresponding necessary change to
bpf_user_ringbuf_drain() callbacks was missed.

This patch set fixes this oversight, and updates the user_ringbuf
selftests to return 1 in a callback to catch future instances of
regression.
====================

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>

In commit 1bfe26fb ("bpf: Add verifier support for custom callback
return range"), the verifier was updated to require callbacks to BPF
helpers to explicitly specify the range of values that can be returned.
bpf_user_ringbuf_drain() was merged after this in commit 20571567


("bpf: Add bpf_user_ringbuf_drain() helper"), and this change in default
behavior was missed. This patch updates the BPF_MAP_TYPE_USER_RINGBUF
selftests to also return 1 from a bpf_user_ringbuf_drain() callback so
as to properly test this going forward.

Signed-off-by: David Vernet <void@manifault.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20221012232015.1510043-3-void@manifault.com

The bpf_user_ringbuf_drain() helper function allows a BPF program to
specify a callback that is invoked when draining entries from a
BPF_MAP_TYPE_USER_RINGBUF ring buffer map. The API is meant to allow the
callback to return 0 if it wants to continue draining samples, and 1 if
it's done draining. Unfortunately, bpf_user_ringbuf_drain() landed shortly
after commit 1bfe26fb ("bpf: Add verifier support for custom
callback return range"), which changed the default behavior of callbacks
to only support returning 0.

This patch corrects that oversight by allowing bpf_user_ringbuf_drain()
callbacks to return 0 or 1. A follow-on patch will update the
user_ringbuf selftests to also return 1 from a bpf_user_ringbuf_drain()
callback to prevent this from regressing in the future.

Fixes: 20571567

 ("bpf: Add bpf_user_ringbuf_drain() helper")
Signed-off-by: David Vernet <void@manifault.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20221012232015.1510043-2-void@manifault.com

Pull networking updates from Jakub Kicinski:
 "Core:

   - Introduce and use a single page frag cache for allocating small skb
     heads, clawing back the 10-20% performance regression in UDP flood
     test from previous fixes.

   - Run packets which already went thru HW coalescing thru SW GRO. This
     significantly improves TCP segment coalescing and simplifies
     deployments as different workloads benefit from HW or SW GRO.

   - Shrink the size of the base zero-copy send structure.

   - Move TCP init under a new slow / sleepable version of DO_ONCE().

  BPF:

   - Add BPF-specific, any-context-safe memory allocator.

   - Add helpers/kfuncs for PKCS#7 signature verification from BPF
     programs.

   - Define a new map type and related helpers for user space -> kernel
     communication over a ring buffer (BPF_MAP_TYPE_USER_RINGBUF).

   - Allow targeting BPF iterators to loop through resources of one
   ...

Pull landlock updates from Mickaël Salaün:
 "Improve user help for Landlock (documentation and sample)"

* tag 'landlock-6.1-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/mic/linux:
  landlock: Fix documentation style
  landlock: Slightly improve documentation and fix spelling
  samples/landlock: Print hints about ABI versions

Pull audit updates from Paul Moore:
 "Six audit patches for v6.1, most are pretty trivial, but a quick list
  of the highlights are below:

   - Only free the audit proctitle information on task exit. This allows
     us to cache the information and improve performance slightly.

   - Use the time_after() macro to do time comparisons instead of doing
     it directly and potentially causing ourselves problems when the
     timer wraps.

   - Convert an audit_context state comparison from a relative enum
     comparison, e.g. (x < y), to a not-equal comparison to ensure that
     we are not caught out at some unknown point in the future by an
     enum shuffle.

   - A handful of small cleanups such as tidying up comments and
     removing unused declarations"

* tag 'audit-pr-20221003' of git://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/audit:
  audit: remove selinux_audit_rule_update() declaration
  audit: use time_after to compare time
  audit: free audit_proctitle only on task exit
  audit: explicitly check audit_context->context enum value
  audit: audit_context pid unused, context enum comment fix
  audit: fix repeated words in comments

Pull x86 cleanups from Borislav Petkov:

 - The usual round of smaller fixes and cleanups all over the tree

* tag 'x86_cleanups_for_v6.1_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/cpu: Include the header of init_ia32_feat_ctl()'s prototype
  x86/uaccess: Improve __try_cmpxchg64_user_asm() for x86_32
  x86: Fix various duplicate-word comment typos
  x86/boot: Remove superfluous type casting from arch/x86/boot/bitops.h

Pull x86 cache resource control updates from Borislav Petkov:

 - More work by James Morse to disentangle the resctrl filesystem
   generic code from the architectural one with the endgoal of plugging
   ARM's MPAM implementation into it too so that the user interface
   remains the same

 - Properly restore the MSR_MISC_FEATURE_CONTROL value instead of
   blindly overwriting it to 0

* tag 'x86_cache_for_v6.1_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (22 commits)
  x86/resctrl: Make resctrl_arch_rmid_read() return values in bytes
  x86/resctrl: Add resctrl_rmid_realloc_limit to abstract x86's boot_cpu_data
  x86/resctrl: Rename and change the units of resctrl_cqm_threshold
  x86/resctrl: Move get_corrected_mbm_count() into resctrl_arch_rmid_read()
  x86/resctrl: Move mbm_overflow_count() into resctrl_arch_rmid_read()
  x86/resctrl: Pass the required parameters into resctrl_arch_rmid_read()
  x86/resctrl: Abstract __rmid_read()
  x86/resctrl: Allow per-rmid arch private storage to be reset
  x86/resctrl: Add per-rmid arch private storage for overflow and chunks
  x86/resctrl: Calculate bandwidth from the previous __mon_event_count() chunks
  x86/resctrl: Allow update_mba_bw() to update controls directly
  x86/resctrl: Remove architecture copy of mbps_val
  x86/resctrl: Switch over to the resctrl mbps_val list
  x86/resctrl: Create mba_sc configuration in the rdt_domain
  x86/resctrl: Abstract and use supports_mba_mbps()
  x86/resctrl: Remove set_mba_sc()s control array re-initialisation
  x86/resctrl: Add domain offline callback for resctrl work
  x86/resctrl: Group struct rdt_hw_domain cleanup
  x86/resctrl: Add domain online callback for resctrl work
  x86/resctrl: Merge mon_capable and mon_enabled
  ...

Pull x75 microcode loader updates from Borislav Petkov:

 - Get rid of a single ksize() usage

 - By popular demand, print the previous microcode revision an update
   was done over

 - Remove more code related to the now gone MICROCODE_OLD_INTERFACE

 - Document the problems stemming from microcode late loading

* tag 'x86_microcode_for_v6.1_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/microcode/AMD: Track patch allocation size explicitly
  x86/microcode: Print previous version of microcode after reload
  x86/microcode: Remove ->request_microcode_user()
  x86/microcode: Document the whole late loading problem

Pull x86 paravirt fix from Borislav Petkov:

 - Ensure paravirt patching site descriptors are aligned properly so
   that code can do proper arithmetic with their addresses

* tag 'x86_paravirt_for_v6.1_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/paravirt: Ensure proper alignment

Pull misc x86 fixes from Borislav Petkov:

 - Drop misleading "RIP" from the opcodes dumping message

 - Correct APM entry's Konfig help text

* tag 'x86_misc_for_v6.1_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/dumpstack: Don't mention RIP in "Code: "
  x86/Kconfig: Specify idle=poll instead of no-hlt

Pull x86 asm update from Borislav Petkov:

 - Use the __builtin_ffs/ctzl() compiler builtins for the constant
   argument case in the kernel's optimized ffs()/ffz() helpers in order
   to make use of the compiler's constant folding optmization passes.

* tag 'x86_asm_for_v6.1_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/asm/bitops: Use __builtin_ctzl() to evaluate constant expressions
  x86/asm/bitops: Use __builtin_ffs() to evaluate constant expressions

Pull x86 core fixes from Borislav Petkov:

 - Make sure an INT3 is slapped after every unconditional retpoline JMP
   as both vendors suggest

 - Clean up pciserial a bit

* tag 'x86_core_for_v6.1_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86,retpoline: Be sure to emit INT3 after JMP *%\reg
  x86/earlyprintk: Clean up pciserial

Pull x86 APIC update from Borislav Petkov:

 - Add support for locking the APIC in X2APIC mode to prevent SGX
   enclave leaks

* tag 'x86_apic_for_v6.1_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/apic: Don't disable x2APIC if locked

Pull x86 RAS updates from Borislav Petkov:

 - Fix the APEI MCE callback handler to consult the hardware about the
   granularity of the memory error instead of hard-coding it

 - Offline memory pages on Intel machines after 2 errors reported per
   page

* tag 'ras_core_for_v6.1_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/mce: Retrieve poison range from hardware
  RAS/CEC: Reduce offline page threshold for Intel systems

Pull x86 cpu updates from Borislav Petkov:

 - Print the CPU number at segfault time.

   The number printed is not always accurate (preemption is enabled at
   that time) but the print string contains "likely" and after a lot of
   back'n'forth on this, this was the consensus that was reached. See
   thread at [1].

 - After a *lot* of testing and polishing, finally the clear_user()
   improvements to inline REP; STOSB by default

Link: https://lore.kernel.org/r/5d62c1d0-7425-d5bb-ecb5-1dc3b4d7d245@intel.com [1]

* tag 'x86_cpu_for_v6.1_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/mm: Print likely CPU at segfault time
  x86/clear_user: Make it faster

Pull x86 SGX update from Borislav Petkov:

 - Improve the documentation of a couple of SGX functions handling
   backing storage

* tag 'x86_sgx_for_v6.1_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/sgx: Improve comments for sgx_encl_lookup/alloc_backing()

Pull x86 RTC cleanups from Borislav Petkov:

 - Cleanup x86/rtc.c and delete duplicated functionality in favor of
   using the respective functionality from the RTC library

* tag 'x86_timers_for_v6.1_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/rtc: Rename mach_set_rtc_mmss() to mach_set_cmos_time()
  x86/rtc: Rewrite & simplify mach_get_cmos_time() by deleting duplicated functionality

Pull x86 platform update from Borislav Petkov:
 "A single x86/platform improvement when the kernel is running as an
  ACRN guest:

   - Get TSC and CPU frequency from CPUID leaf 0x40000010 when the
     kernel is running as a guest on the ACRN hypervisor"

* tag 'x86_platform_for_v6.1_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/acrn: Set up timekeeping

Pull EDAC updates from Borislav Petkov:

 - Add support for Skylake-S CPUs to ie31200_edac

 - Improve error decoding speed of the Intel drivers by avoiding the
   ACPI facilities but doing decoding in the driver itself

 - Other misc improvements to the Intel drivers

 - The usual cleanups and fixlets all over EDAC land

* tag 'edac_updates_for_v6.1' of git://git.kernel.org/pub/scm/linux/kernel/git/ras/ras:
  EDAC/i7300: Correct the i7300_exit() function name in comment
  x86/sb_edac: Add row column translation for Broadwell
  EDAC/i10nm: Print an extra register set of retry_rd_err_log
  EDAC/i10nm: Retrieve and print retry_rd_err_log registers for HBM
  EDAC/skx_common: Add ChipSelect ADXL component
  EDAC/ppc_4xx: Reorder symbols to get rid of a few forward declarations
  EDAC: Remove obsolete declarations in edac_module.h
  EDAC/i10nm: Add driver decoder for Ice Lake and Tremont CPUs
  EDAC/skx_common: Make output format similar
  EDAC/skx_common: Use driver decoder first
  EDAC/mc: Drop duplicated dimm->nr_pages debug printout
  EDAC/mc: Replace spaces with tabs in memtype flags definition
  EDAC/wq: Remove unneeded flush_workqueue()
  EDAC/ie31200: Add Skylake-S support

Combine all queued EDAC changes for submission into v6.1:

* edac-drivers:
  EDAC/ie31200: Add Skylake-S support

* edac-misc:
  EDAC/i7300: Correct the i7300_exit() function name in comment
  x86/sb_edac: Add row column translation for Broadwell
  EDAC/i10nm: Print an extra register set of retry_rd_err_log
  EDAC/i10nm: Retrieve and print retry_rd_err_log registers for HBM
  EDAC/skx_common: Add ChipSelect ADXL component
  EDAC/ppc_4xx: Reorder symbols to get rid of a few forward declarations
  EDAC: Remove obsolete declarations in edac_module.h
  EDAC/i10nm: Add driver decoder for Ice Lake and Tremont CPUs
  EDAC/skx_common: Make output format similar
  EDAC/skx_common: Use driver decoder first
  EDAC/mc: Drop duplicated dimm->nr_pages debug printout
  EDAC/mc: Replace spaces with tabs in memtype flags definition
  EDAC/wq: Remove unneeded flush_workqueue()

Signed-off-by: Borislav Petkov <bp@suse.de>

build bot reports missing 'static inline' qualifiers in the header.

Reported-by: kernel test robot <lkp@intel.com>
Fixes: 18ff0bcd

 ("ethtool: add interface to interact with Ethernet Power Equipment")
Reviewed-by: Oleksij Rempel <o.rempel@pengutronix.de>
Link: https://lore.kernel.org/r/20221004040327.2034878-1-kuba@kernel.org


Signed-off-by: Jakub Kicinski <kuba@kernel.org>

Merge tag 'statx-dioalign-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiggers/linux

Pull STATX_DIOALIGN support from Eric Biggers:
 "Make statx() support reporting direct I/O (DIO) alignment information.

  This provides a generic interface for userspace programs to determine
  whether a file supports DIO, and if so with what alignment
  restrictions. Specifically, STATX_DIOALIGN works on block devices, and
  on regular files when their containing filesystem has implemented
  support.

  An interface like this has been requested for years, since the
  conditions for when DIO is supported in Linux have gotten increasingly
  complex over time. Today, DIO support and alignment requirements can
  be affected by various filesystem features such as multi-device
  support, data journalling, inline data, encryption, verity,
  compression, checkpoint disabling, log-structured mode, etc.

  Further complicating things, Linux v6.0 relaxed the traditional rule
  of DIO needing to be aligned to the bl...

Pull fsverity updates from Eric Biggers:
 "Minor changes to convert uses of kmap() to kmap_local_page()"

* tag 'fsverity-for-linus' of git://git.kernel.org/pub/scm/fs/fscrypt/fscrypt:
  fs-verity: use kmap_local_page() instead of kmap()
  fs-verity: use memcpy_from_page()

Pull fscrypt updates from Eric Biggers:
 "This release contains some implementation changes, but no new
  features:

   - Rework the implementation of the fscrypt filesystem-level keyring
     to not be as tightly coupled to the keyrings subsystem. This
     resolves several issues.

   - Eliminate most direct uses of struct request_queue from fs/crypto/,
     since struct request_queue is considered to be a block layer
     implementation detail.

   - Stop using the PG_error flag to track decryption failures. This is
     a prerequisite for freeing up PG_error for other uses"

* tag 'fscrypt-for-linus' of git://git.kernel.org/pub/scm/fs/fscrypt/fscrypt:
  fscrypt: work on block_devices instead of request_queues
  fscrypt: stop holding extra request_queue references
  fscrypt: stop using keyrings subsystem for fscrypt_master_key
  fscrypt: stop using PG_error to track error status
  fscrypt: remove fscrypt_set_test_dummy_encryption()

Pull dlm updates from David Teigland:

 - Fix a couple races found with a new torture test

 - Improve errors when api functions are used incorrectly

 - Improve tracing for lock requests from user space

 - Fix use after free in recently added tracing cod.

 - Small internal code cleanups

* tag 'dlm-6.1' of git://git.kernel.org/pub/scm/linux/kernel/git/teigland/linux-dlm:
  fs: dlm: fix possible use after free if tracing
  fs: dlm: const void resource name parameter
  fs: dlm: LSFL_CB_DELAY only for kernel lockspaces
  fs: dlm: remove DLM_LSFL_FS from uapi
  fs: dlm: trace user space callbacks
  fs: dlm: change ls_clear_proc_locks to spinlock
  fs: dlm: remove dlm_del_ast prototype
  fs: dlm: handle rcom in else if branch
  fs: dlm: allow lockspaces have zero lvblen
  fs: dlm: fix invalid derefence of sb_lvbptr
  fs: dlm: handle -EINVAL as log_error()
  fs: dlm: use __func__ for function name
  fs: dlm: handle -EBUSY first in unlock validation
  fs: dlm: handle -EBUSY first in lock arg validation
  fs: dlm: fix race between test_bit() and queue_work()
  fs: dlm: fix race in lowcomms

Pull nfsd updates from Chuck Lever:
 "This release is mostly bug fixes, clean-ups, and optimizations.

  One notable set of fixes addresses a subtle buffer overflow issue that
  occurs if a small RPC Call message arrives in an oversized RPC record.
  This is only possible on a framed RPC transport such as TCP.

  Because NFSD shares the receive and send buffers in one set of pages,
  an oversized RPC record steals pages from the send buffer that will be
  used to construct the RPC Reply message. NFSD must not assume that a
  full-sized buffer is always available to it; otherwise, it will walk
  off the end of the send buffer while constructing its reply.

  In this release, we also introduce the ability for the server to wait
  a moment for clients to return delegations before it responds with
  NFS4ERR_DELAY. This saves a retransmit and a network round- trip when
  a delegation recall is needed. This work will be built upon in future
  releases.

  The NFS server adds another shrinker to its collection. Because
  courtesy clients can linger for quite some time, they might be
  freeable when the server host comes under memory pressure. A new
  shrinker has been added that releases courtesy client resources during
  low memory scenarios.

  Lastly, of note: the maximum number of operations per NFSv4 COMPOUND
  that NFSD can handle is increased from 16 to 50. There are NFSv4
  client implementations that need more than 16 to successfully perform
  a mount operation that uses a pathname with many components"

* tag 'nfsd-6.1' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux: (53 commits)
  nfsd: extra checks when freeing delegation stateids
  nfsd: make nfsd4_run_cb a bool return function
  nfsd: fix comments about spinlock handling with delegations
  nfsd: only fill out return pointer on success in nfsd4_lookup_stateid
  NFSD: fix use-after-free on source server when doing inter-server copy
  NFSD: Cap rsize_bop result based on send buffer size
  NFSD: Rename the fields in copy_stateid_t
  nfsd: use DEFINE_SHOW_ATTRIBUTE to define nfsd_file_cache_stats_fops
  nfsd: use DEFINE_SHOW_ATTRIBUTE to define nfsd_reply_cache_stats_fops
  nfsd: use DEFINE_SHOW_ATTRIBUTE to define client_info_fops
  nfsd: use DEFINE_SHOW_ATTRIBUTE to define export_features_fops and supported_enctypes_fops
  nfsd: use DEFINE_PROC_SHOW_ATTRIBUTE to define nfsd_proc_ops
  NFSD: Pack struct nfsd4_compoundres
  NFSD: Remove unused nfsd4_compoundargs::cachetype field
  NFSD: Remove "inline" directives on op_rsize_bop helpers
  NFSD: Clean up nfs4svc_encode_compoundres()
  SUNRPC: Fix typo in xdr_buf_subsegment's kdoc comment
  NFSD: Clean up WRITE arg decoders
  NFSD: Use xdr_inline_decode() to decode NFSv3 symlinks
  NFSD: Refactor common code out of dirlist helpers
  ...

Pull erofs updates from Gao Xiang:
 "In this cycle, for container use cases, fscache-based shared domain is
  introduced [1] so that data blobs in the same domain will be storage
  deduplicated and it will also be used for page cache sharing later.

  Also, a special packed inode is now introduced to record inode
  fragments which keep the tail part of files by Yue Hu [2]. You can
  keep arbitary length or (at will) the whole file as a fragment and
  then fragments can be optionally compressed in the packed inode
  together and even deduplicated for smaller image sizes.

  In addition to that, global compressed data deduplication by sharing
  partial-referenced pclusters is also supported in this cycle.

  Summary:

   - Introduce fscache-based domain to share blobs between images

   - Support recording fragments in a special packed inode

   - Support partial-referenced pclusters for global compressed data
     deduplication

   - Fix an order >= MAX_ORDER warning due to crafted negative i_size

   - Several cleanups"

Link: https://lore.kernel.org/r/20220916085940.89392-1-zhujia.zj@bytedance.com [1]
Link: https://lore.kernel.org/r/cover.1663065968.git.huyue2@coolpad.com [2]

* tag 'erofs-for-6.1-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/xiang/erofs:
  erofs: clean up erofs_iget()
  erofs: clean up unnecessary code and comments
  erofs: fold in z_erofs_reload_indexes()
  erofs: introduce partial-referenced pclusters
  erofs: support on-disk compressed fragments data
  erofs: support interlaced uncompressed data for compressed files
  erofs: clean up .read_folio() and .readahead() in fscache mode
  erofs: introduce 'domain_id' mount option
  erofs: Support sharing cookies in the same domain
  erofs: introduce a pseudo mnt to manage shared cookies
  erofs: introduce fscache-based domain
  erofs: code clean up for fscache
  erofs: use kill_anon_super() to kill super in fscache mode
  erofs: fix order >= MAX_ORDER warning due to crafted negative i_size

Pull fatfs vfsuid conversion from Christian Brauner:
 "Last cycle we introduced the new vfs{g,u}id_t types that we had agreed
  on. The most important parts of the vfs have been converted but there
  are a few more places we need to switch before we can remove the old
  helpers completely.

  This cycle we converted all filesystems that called idmapped mount
  helpers directly. The affected filesystems are f2fs, fat, fuse, ksmbd,
  overlayfs, and xfs. We've sent patches for all of them. Looking at
  -next f2fs, ksmbd, overlayfs, and xfs have all picked up these patches
  and they should land in mainline during the v6.1 merge window.

  So all filesystems that have a separate tree should send the vfsuid
  conversion themselves. Onle the fat conversion is going through this
  generic fs trees because there is no fat tree.

  In order to change time settings on an inode fat checks that the
  caller either is the owner of the inode or the inode's group is in the
  caller's group list. If fat is on an idmapped mount we compare whether
  the inode mapped into the mount is equivalent to the caller's fsuid.
  If it isn't we compare whether the inode's group mapped into the mount
  is in the caller's group list.

  We now use the new vfsuid based helpers for that"

* tag 'fs.vfsuid.fat.v6.1' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/idmapping:
  fat: port to vfs{g,u}id_t and associated helpers

Pull vfs acl updates from Christian Brauner:
 "These are general fixes and preparatory changes related to the ongoing
  posix acl rework. The actual rework where we build a type safe posix
  acl api wasn't ready for this merge window but we're hopeful for the
  next merge window.

  General fixes:

   - Some filesystems like 9p and cifs have to implement custom posix
     acl handlers because they require access to the dentry in order to
     set and get posix acls while the set and get inode operations
     currently don't. But the ntfs3 filesystem has no such requirement
     and thus implemented custom posix acl xattr handlers when it really
     didn't have to. So this pr contains patch that just implements set
     and get inode operations for ntfs3 and switches it to rely on the
     generic posix acl xattr handlers. (We would've appreciated reviews
     from the ntfs3 maintainers but we didn't get any. But hey, if we
     really broke it we'll fix it. But fstests for ntfs3 said it's
     fine.)

   - The posix_acl_fix_xattr_common() helper has been adapted so it can
     be used by a few more callers and avoiding open-coding the same
     checks over and over.

  Other than the two general fixes this series introduces a new helper
  vfs_set_acl_prepare(). The reason for this helper is so that we can
  mitigate one of the source that change {g,u}id values directly in the
  uapi struct. With the vfs_set_acl_prepare() helper we can move the
  idmapped mount fixup into the generic posix acl set handler.

  The advantage of this is that it allows us to remove the
  posix_acl_setxattr_idmapped_mnt() helper which so far we had to call
  in vfs_setxattr() to account for idmapped mounts. While semantically
  correct the problem with this approach was that we had to keep the
  value parameter of the generic vfs_setxattr() call as non-const. This
  is rectified in this series.

  Ultimately, we will get rid of all the extreme kludges and type
  unsafety once we have merged the posix api - hopefully during the next
  merge window - built solely around get and set inode operations. Which
  incidentally will also improve handling of posix acls in security and
  especially in integrity modesl. While this will come with temporarily
  having two inode operation for posix acls that is nothing compared to
  the problems we have right now and so well worth it. We'll end up with
  something that we can actually reason about instead of needing to
  write novels to explain what's going on"

* tag 'fs.acl.rework.prep.v6.1' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/idmapping:
  xattr: always us is_posix_acl_xattr() helper
  acl: fix the comments of posix_acl_xattr_set
  xattr: constify value argument in vfs_setxattr()
  ovl: use vfs_set_acl_prepare()
  acl: move idmapping handling into posix_acl_xattr_set()
  acl: add vfs_set_acl_prepare()
  acl: return EOPNOTSUPP in posix_acl_fix_xattr_common()
  ntfs3: rework xattr handlers and switch to POSIX ACL VFS helpers

Pull coredump fix from Al Viro:
 "Brown paper bag bug fix for the coredumping fix late in the 6.0
  release cycle"

* tag 'pull-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  [brown paperbag] fix coredump breakage

Pull LSM updates from Paul Moore:
 "Seven patches for the LSM layer and we've got a mix of trivial and
  significant patches. Highlights below, starting with the smaller bits
  first so they don't get lost in the discussion of the larger items:

   - Remove some redundant NULL pointer checks in the common LSM audit
     code.

   - Ratelimit the lockdown LSM's access denial messages.

     With this change there is a chance that the last visible lockdown
     message on the console is outdated/old, but it does help preserve
     the initial series of lockdown denials that started the denial
     message flood and my gut feeling is that these might be the more
     valuable messages.

   - Open userfaultfds as readonly instead of read/write.

     While this code obviously lives outside the LSM, it does have a
     noticeable impact on the LSMs with Ondrej explaining the situation
     in the commit description. It is worth noting that this patch
     languished on the VFS list for over a year without any comments
     (objections or otherwise) so I took the liberty of pulling it into
     the LSM tree after giving fair notice. It has been in linux-next
     since the end of August without any noticeable problems.

   - Add a LSM hook for user namespace creation, with implementations
     for both the BPF LSM and SELinux.

     Even though the changes are fairly small, this is the bulk of the
     diffstat as we are also including BPF LSM selftests for the new
     hook.

     It's also the most contentious of the changes in this pull request
     with Eric Biederman NACK'ing the LSM hook multiple times during its
     development and discussion upstream. While I've never taken NACK's
     lightly, I'm sending these patches to you because it is my belief
     that they are of good quality, satisfy a long-standing need of
     users and distros, and are in keeping with the existing nature of
     the LSM layer and the Linux Kernel as a whole.

     The patches in implement a LSM hook for user namespace creation
     that allows for a granular approach, configurable at runtime, which
     enables both monitoring and control of user namespaces. The general
     consensus has been that this is far preferable to the other
     solutions that have been adopted downstream including outright
     removal from the kernel, disabling via system wide sysctls, or
     various other out-of-tree mechanisms that users have been forced to
     adopt since we haven't been able to provide them an upstream
     solution for their requests. Eric has been steadfast in his
     objections to this LSM hook, explaining that any restrictions on
     the user namespace could have significant impact on userspace.
     While there is the possibility of impacting userspace, it is
     important to note that this solution only impacts userspace when it
     is requested based on the runtime configuration supplied by the
     distro/admin/user. Frederick (the pathset author), the LSM/security
     community, and myself have tried to work with Eric during
     development of this patchset to find a mutually acceptable
     solution, but Eric's approach and unwillingness to engage in a
     meaningful way have made this impossible. I have CC'd Eric directly
     on this pull request so he has a chance to provide his side of the
     story; there have been no objections outside of Eric's"

* tag 'lsm-pr-20221003' of git://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/lsm:
  lockdown: ratelimit denial messages
  userfaultfd: open userfaultfds with O_RDONLY
  selinux: Implement userns_create hook
  selftests/bpf: Add tests verifying bpf lsm userns_create hook
  bpf-lsm: Make bpf_lsm_userns_create() sleepable
  security, lsm: Introduce security_create_user_ns()
  lsm: clean up redundant NULL pointer check

Pull SELinux updates from Paul Moore:
 "Six SELinux patches, all are simple and easily understood, but a list
  of the highlights is below:

   - Use 'grep -E' instead of 'egrep' in the SELinux policy install
     script.

     Fun fact, this seems to be GregKH's *second* dedicated SELinux
     patch since we transitioned to git (ignoring merges, the SPDX
     stuff, and a trivial fs reference removal when lustre was yanked);
     the first was back in 2011 when selinuxfs was placed in
     /sys/fs/selinux. Oh, the memories ...

   - Convert the SELinux policy boolean values to use signed integer
     types throughout the SELinux kernel code.

     Prior to this we were using a mix of signed and unsigned integers
     which was probably okay in this particular case, but it is
     definitely not a good idea in general.

   - Remove a reference to the SELinux runtime disable functionality in
     /etc/selinux/config as we are in the process of deprecating that.

     See [1] for more background on this if you missed the previous
     notes on the deprecation.

   - Minor cleanups: remove unneeded variables and function parameter
     constification"

Link: https://github.com/SELinuxProject/selinux-kernel/wiki/DEPRECATE-runtime-disable [1]

* tag 'selinux-pr-20221003' of git://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/selinux:
  selinux: remove runtime disable message in the install_policy.sh script
  selinux: use "grep -E" instead of "egrep"
  selinux: remove the unneeded result variable
  selinux: declare read-only parameters const
  selinux: use int arrays for boolean values
  selinux: remove an unneeded variable in sel_make_class_dir_entries()

Merge in the left-over fixes before the net-next pull-request.

Conflicts:

drivers/net/ethernet/mediatek/mtk_ppe.c
  ae3ed15d ("net: ethernet: mtk_eth_soc: fix state in __mtk_foe_entry_clear")
  9d8cb4c0 ("net: ethernet: mtk_eth_soc: add foe_entry_size to mtk_eth_soc")
https://lore.kernel.org/all/6cb6893b-4921-a068-4c30-1109795110bb@tessares.net/

kernel/bpf/helpers.c
  8addbfc7 ("bpf: Gate dynptr API behind CAP_BPF")
  5679ff2f ("bpf: Move bpf_loop and bpf_for_each_map_elem under CAP_BPF")
  8a67f2de ("bpf: expose bpf_strtol and bpf_strtoul to all program types")
https://lore.kernel.org/all/20221003201957.13149-1-daniel@iogearbox.net/



Signed-off-by: Jakub Kicinski <kuba@kernel.org>

Pull integrity updates from Mimi Zohar:
 "Just two bug fixes"

* tag 'integrity-v6.1' of git://git.kernel.org/pub/scm/linux/kernel/git/zohar/linux-integrity:
  efi: Correct Macmini DMI match in uefi cert quirk
  ima: fix blocking of security.ima xattrs of unsupported algorithms