linux_dsm_epyc7002/arch/x86
Linus Torvalds 7b4ea9456d Revert "x86/mm/64: Do not sync vmalloc/ioremap mappings"
This reverts commit 8bb9bf242d.

It seems the vmalloc page tables aren't always preallocated in all
situations, because Jason Donenfeld reports an oops with this commit:

  BUG: unable to handle page fault for address: ffffe8ffffd00608
  #PF: supervisor read access in kernel mode
  #PF: error_code(0x0000) - not-present page
  PGD 0 P4D 0
  Oops: 0000 [#1] PREEMPT SMP
  CPU: 2 PID: 22 Comm: kworker/2:0 Not tainted 5.8.0+ #154
  RIP: process_one_work+0x2c/0x2d0
  Code: 41 56 41 55 41 54 55 48 89 f5 53 48 89 fb 48 83 ec 08 48 8b 06 4c 8b 67 40 49 89 c6 45 30 f6 a8 04 b8 00 00 00 00 4c 0f 44 f0 <49> 8b 46 08 44 8b a8 00 01 05
  Call Trace:
   worker_thread+0x4b/0x3b0
   ? rescuer_thread+0x360/0x360
   kthread+0x116/0x140
   ? __kthread_create_worker+0x110/0x110
   ret_from_fork+0x1f/0x30
  CR2: ffffe8ffffd00608

and that page fault address is right in that vmalloc space, and we
clearly don't have a PGD/P4D entry for it.

Looking at the "Code:" line, the actual fault seems to come from the
'pwq->wq' dereference at the top of the process_one_work() function:

        struct pool_workqueue *pwq = get_work_pwq(work);
        struct worker_pool *pool = worker->pool;
        bool cpu_intensive = pwq->wq->flags & WQ_CPU_INTENSIVE;

so 'struct pool_workqueue *pwq' is the allocation that hasn't been
synchronized across CPUs.

Just revert for now, while Joerg figures out the cause.

Reported-and-bisected-by: Jason A. Donenfeld <Jason@zx2c4.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-06 12:02:58 -07:00
..
boot x86: Add support for ZSTD compressed kernel 2020-07-31 11:49:09 +02:00
configs x86/defconfigs: Refresh defconfig files 2020-07-25 12:02:14 +02:00
crypto crypto: x86/curve25519 - Remove unused carry variables 2020-07-31 18:25:29 +10:00
entry Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next 2020-08-05 20:13:21 -07:00
events Misc cleanups all around the place. 2020-08-03 16:53:28 -07:00
hyperv vmalloc: fix the owner argument for the new __vmalloc_node_range callers 2020-07-03 16:15:25 -07:00
ia32 Merge branch 'exec-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace 2020-06-04 14:07:08 -07:00
include Revert "x86/mm/64: Do not sync vmalloc/ioremap mappings" 2020-08-06 12:02:58 -07:00
kernel drm next for 5.9-rc1 2020-08-05 19:50:06 -07:00
kvm Support for FSGSBASE. Almost 5 years after the first RFC to support it, 2020-08-04 21:16:22 -07:00
lib * AMD Memory bandwidth counter width fix, by Babu Moger. 2020-06-28 10:35:01 -07:00
math-emu x86: math-emu: Fix up 'cmp' insn for clang ias 2020-07-16 17:26:42 +02:00
mm Revert "x86/mm/64: Do not sync vmalloc/ioremap mappings" 2020-08-06 12:02:58 -07:00
net bpf, i386: Remove unneeded conversion to bool 2020-05-07 16:29:14 +02:00
oprofile
pci maccess: rename probe_kernel_address to get_kernel_nofault 2020-06-18 11:14:40 -07:00
platform The biggest change is the removal of SGI UV1 support, which allowed the 2020-08-03 17:38:43 -07:00
power x86/cpu: Reinitialize IA32_FEAT_CTL MSR on BSP during wakeup 2020-06-15 14:18:37 +02:00
purgatory x86/purgatory: Add -fno-stack-protector 2020-06-16 17:05:07 -07:00
ras treewide: replace '---help---' in Kconfig files with 'help' 2020-06-14 01:57:21 +09:00
realmode Rebase locking/kcsan to locking/urgent 2020-06-11 20:02:46 +02:00
tools
um mmap locking API: use coccinelle to convert mmap_sem rwsem call sites 2020-06-09 09:39:14 -07:00
video
xen A single commit which sets the X86_FEATURE_TSC_KNOWN_FREQ flag for Xen guests, 2020-08-03 17:41:06 -07:00
.gitignore
Kbuild
Kconfig The conversion of X86 syscall, interrupt and exception entry/exit handling 2020-08-04 21:05:46 -07:00
Kconfig.assembler x86/delay: Introduce TPAUSE delay 2020-05-07 16:06:20 +02:00
Kconfig.cpu treewide: replace '---help---' in Kconfig files with 'help' 2020-06-14 01:57:21 +09:00
Kconfig.debug locking/lockdep: Fix TRACE_IRQFLAGS vs. NMIs 2020-07-27 15:13:29 +02:00
Makefile x86/build: Move max-page-size option to LDFLAGS_vmlinux 2020-07-24 16:39:27 +02:00
Makefile_32.cpu
Makefile.um