linux-stable.git/tools/objtool, branch linux-5.8.y Linux kernel stable tree x86/copy_mc: Introduce copy_mc_enhanced_fast_string() 2020-11-01T11:45:37+00:00 Dan Williams dan.j.williams@intel.com 2020-10-06T03:40:25+00:00 61ececc852746242042da22059e8720317ad1424 commit 5da8e4a658109e3b7e1f45ae672b7c06ac3e7158 upstream. The motivations to go rework memcpy_mcsafe() are that the benefit of doing slow and careful copies is obviated on newer CPUs, and that the current opt-in list of CPUs to instrument recovery is broken relative to those CPUs. There is no need to keep an opt-in list up to date on an ongoing basis if pmem/dax operations are instrumented for recovery by default. With recovery enabled by default the old "mcsafe_key" opt-in to careful copying can be made a "fragile" opt-out. Where the "fragile" list takes steps to not consume poison across cachelines. The discussion with Linus made clear that the current "_mcsafe" suffix was imprecise to a fault. The operations that are needed by pmem/dax are to copy from a source address that might throw #MC to a destination that may write-fault, if it is a user page. So copy_to_user_mcsafe() becomes copy_mc_to_user() to indicate the separate precautions taken on source and destination. copy_mc_to_kernel() is introduced as a non-SMAP version that does not expect write-faults on the destination, but is still prepared to abort with an error code upon taking #MC. The original copy_mc_fragile() implementation had negative performance implications since it did not use the fast-string instruction sequence to perform copies. For this reason copy_mc_to_kernel() fell back to plain memcpy() to preserve performance on platforms that did not indicate the capability to recover from machine check exceptions. However, that capability detection was not architectural and now that some platforms can recover from fast-string consumption of memory errors the memcpy() fallback now causes these more capable platforms to fail. Introduce copy_mc_enhanced_fast_string() as the fast default implementation of copy_mc_to_kernel() and finalize the transition of copy_mc_fragile() to be a platform quirk to indicate 'copy-carefully'. With this in place, copy_mc_to_kernel() is fast and recovery-ready by default regardless of hardware capability. Thanks to Vivek for identifying that copy_user_generic() is not suitable as the copy_mc_to_user() backend since the #MC handler explicitly checks ex_has_fault_handler(). Thanks to the 0day robot for catching a performance bug in the x86/copy_mc_to_user implementation. [ bp: Add the "why" for this change from the 0/2th message, massage. ] Fixes: 92b0729c34ca ("x86/mm, x86/mce: Add memcpy_mcsafe()") Reported-by: Erwin Tsaur <erwin.tsaur@intel.com> Reported-by: 0day robot <lkp@intel.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Borislav Petkov <bp@suse.de> Reviewed-by: Tony Luck <tony.luck@intel.com> Tested-by: Erwin Tsaur <erwin.tsaur@intel.com> Cc: <stable@vger.kernel.org> Link: https://lkml.kernel.org/r/160195562556.2163339.18063423034951948973.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
commit 5da8e4a658109e3b7e1f45ae672b7c06ac3e7158 upstream.

The motivations to go rework memcpy_mcsafe() are that the benefit of
doing slow and careful copies is obviated on newer CPUs, and that the
current opt-in list of CPUs to instrument recovery is broken relative to
those CPUs.  There is no need to keep an opt-in list up to date on an
ongoing basis if pmem/dax operations are instrumented for recovery by
default. With recovery enabled by default the old "mcsafe_key" opt-in to
careful copying can be made a "fragile" opt-out. Where the "fragile"
list takes steps to not consume poison across cachelines.

The discussion with Linus made clear that the current "_mcsafe" suffix
was imprecise to a fault. The operations that are needed by pmem/dax are
to copy from a source address that might throw #MC to a destination that
may write-fault, if it is a user page.

So copy_to_user_mcsafe() becomes copy_mc_to_user() to indicate
the separate precautions taken on source and destination.
copy_mc_to_kernel() is introduced as a non-SMAP version that does not
expect write-faults on the destination, but is still prepared to abort
with an error code upon taking #MC.

The original copy_mc_fragile() implementation had negative performance
implications since it did not use the fast-string instruction sequence
to perform copies. For this reason copy_mc_to_kernel() fell back to
plain memcpy() to preserve performance on platforms that did not indicate
the capability to recover from machine check exceptions. However, that
capability detection was not architectural and now that some platforms
can recover from fast-string consumption of memory errors the memcpy()
fallback now causes these more capable platforms to fail.

Introduce copy_mc_enhanced_fast_string() as the fast default
implementation of copy_mc_to_kernel() and finalize the transition of
copy_mc_fragile() to be a platform quirk to indicate 'copy-carefully'.
With this in place, copy_mc_to_kernel() is fast and recovery-ready by
default regardless of hardware capability.

Thanks to Vivek for identifying that copy_user_generic() is not suitable
as the copy_mc_to_user() backend since the #MC handler explicitly checks
ex_has_fault_handler(). Thanks to the 0day robot for catching a
performance bug in the x86/copy_mc_to_user implementation.

 [ bp: Add the "why" for this change from the 0/2th message, massage. ]

Fixes: 92b0729c34ca ("x86/mm, x86/mce: Add memcpy_mcsafe()")
Reported-by: Erwin Tsaur <erwin.tsaur@intel.com>
Reported-by: 0day robot <lkp@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Tested-by: Erwin Tsaur <erwin.tsaur@intel.com>
Cc: <stable@vger.kernel.org>
Link: https://lkml.kernel.org/r/160195562556.2163339.18063423034951948973.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
x86, powerpc: Rename memcpy_mcsafe() to copy_mc_to_{user, kernel}() 2020-11-01T11:45:37+00:00 Dan Williams dan.j.williams@intel.com 2020-10-06T03:40:16+00:00 a092869e0351eae21cbe3f62a3cf254c6f9c000a commit ec6347bb43395cb92126788a1a5b25302543f815 upstream. In reaction to a proposal to introduce a memcpy_mcsafe_fast() implementation Linus points out that memcpy_mcsafe() is poorly named relative to communicating the scope of the interface. Specifically what addresses are valid to pass as source, destination, and what faults / exceptions are handled. Of particular concern is that even though x86 might be able to handle the semantics of copy_mc_to_user() with its common copy_user_generic() implementation other archs likely need / want an explicit path for this case: On Fri, May 1, 2020 at 11:28 AM Linus Torvalds <torvalds@linux-foundation.org> wrote: > > On Thu, Apr 30, 2020 at 6:21 PM Dan Williams <dan.j.williams@intel.com> wrote: > > > > However now I see that copy_user_generic() works for the wrong reason. > > It works because the exception on the source address due to poison > > looks no different than a write fault on the user address to the > > caller, it's still just a short copy. So it makes copy_to_user() work > > for the wrong reason relative to the name. > > Right. > > And it won't work that way on other architectures. On x86, we have a > generic function that can take faults on either side, and we use it > for both cases (and for the "in_user" case too), but that's an > artifact of the architecture oddity. > > In fact, it's probably wrong even on x86 - because it can hide bugs - > but writing those things is painful enough that everybody prefers > having just one function. Replace a single top-level memcpy_mcsafe() with either copy_mc_to_user(), or copy_mc_to_kernel(). Introduce an x86 copy_mc_fragile() name as the rename for the low-level x86 implementation formerly named memcpy_mcsafe(). It is used as the slow / careful backend that is supplanted by a fast copy_mc_generic() in a follow-on patch. One side-effect of this reorganization is that separating copy_mc_64.S to its own file means that perf no longer needs to track dependencies for its memcpy_64.S benchmarks. [ bp: Massage a bit. ] Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Borislav Petkov <bp@suse.de> Reviewed-by: Tony Luck <tony.luck@intel.com> Acked-by: Michael Ellerman <mpe@ellerman.id.au> Cc: <stable@vger.kernel.org> Link: http://lore.kernel.org/r/CAHk-=wjSqtXAqfUJxFtWNwmguFASTgB0dz1dT3V-78Quiezqbg@mail.gmail.com Link: https://lkml.kernel.org/r/160195561680.2163339.11574962055305783722.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
commit ec6347bb43395cb92126788a1a5b25302543f815 upstream.

In reaction to a proposal to introduce a memcpy_mcsafe_fast()
implementation Linus points out that memcpy_mcsafe() is poorly named
relative to communicating the scope of the interface. Specifically what
addresses are valid to pass as source, destination, and what faults /
exceptions are handled.

Of particular concern is that even though x86 might be able to handle
the semantics of copy_mc_to_user() with its common copy_user_generic()
implementation other archs likely need / want an explicit path for this
case:

  On Fri, May 1, 2020 at 11:28 AM Linus Torvalds <torvalds@linux-foundation.org> wrote:
  >
  > On Thu, Apr 30, 2020 at 6:21 PM Dan Williams <dan.j.williams@intel.com> wrote:
  > >
  > > However now I see that copy_user_generic() works for the wrong reason.
  > > It works because the exception on the source address due to poison
  > > looks no different than a write fault on the user address to the
  > > caller, it's still just a short copy. So it makes copy_to_user() work
  > > for the wrong reason relative to the name.
  >
  > Right.
  >
  > And it won't work that way on other architectures. On x86, we have a
  > generic function that can take faults on either side, and we use it
  > for both cases (and for the "in_user" case too), but that's an
  > artifact of the architecture oddity.
  >
  > In fact, it's probably wrong even on x86 - because it can hide bugs -
  > but writing those things is painful enough that everybody prefers
  > having just one function.

Replace a single top-level memcpy_mcsafe() with either
copy_mc_to_user(), or copy_mc_to_kernel().

Introduce an x86 copy_mc_fragile() name as the rename for the
low-level x86 implementation formerly named memcpy_mcsafe(). It is used
as the slow / careful backend that is supplanted by a fast
copy_mc_generic() in a follow-on patch.

One side-effect of this reorganization is that separating copy_mc_64.S
to its own file means that perf no longer needs to track dependencies
for its memcpy_64.S benchmarks.

 [ bp: Massage a bit. ]

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Acked-by: Michael Ellerman <mpe@ellerman.id.au>
Cc: <stable@vger.kernel.org>
Link: http://lore.kernel.org/r/CAHk-=wjSqtXAqfUJxFtWNwmguFASTgB0dz1dT3V-78Quiezqbg@mail.gmail.com
Link: https://lkml.kernel.org/r/160195561680.2163339.11574962055305783722.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
objtool: Fix noreturn detection for ignored functions 2020-10-01T15:36:25+00:00 Josh Poimboeuf jpoimboe@redhat.com 2020-09-10T15:24:57+00:00 337e96e14843d06e69c53858e86d4f97f4cb7274 [ Upstream commit db6c6a0df840e3f52c84cc302cc1a08ba11a4416 ] When a function is annotated with STACK_FRAME_NON_STANDARD, objtool doesn't validate its code paths. It also skips sibling call detection within the function. But sibling call detection is actually needed for the case where the ignored function doesn't have any return instructions. Otherwise objtool naively marks the function as implicit static noreturn, which affects the reachability of its callers, resulting in "unreachable instruction" warnings. Fix it by just enabling sibling call detection for ignored functions. The 'insn->ignore' check in add_jump_destinations() is no longer needed after e6da9567959e ("objtool: Don't use ignore flag for fake jumps"). Fixes the following warning: arch/x86/kvm/vmx/vmx.o: warning: objtool: vmx_handle_exit_irqoff()+0x142: unreachable instruction which triggers on an allmodconfig with CONFIG_GCOV_KERNEL unset. Reported-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com> Signed-off-by: Borislav Petkov <bp@suse.de> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Link: https://lkml.kernel.org/r/5b1e2536cdbaa5246b60d7791b76130a74082c62.1599751464.git.jpoimboe@redhat.com Signed-off-by: Sasha Levin <sashal@kernel.org> 
[ Upstream commit db6c6a0df840e3f52c84cc302cc1a08ba11a4416 ]

When a function is annotated with STACK_FRAME_NON_STANDARD, objtool
doesn't validate its code paths.  It also skips sibling call detection
within the function.

But sibling call detection is actually needed for the case where the
ignored function doesn't have any return instructions.  Otherwise
objtool naively marks the function as implicit static noreturn, which
affects the reachability of its callers, resulting in "unreachable
instruction" warnings.

Fix it by just enabling sibling call detection for ignored functions.
The 'insn->ignore' check in add_jump_destinations() is no longer needed
after

  e6da9567959e ("objtool: Don't use ignore flag for fake jumps").

Fixes the following warning:

  arch/x86/kvm/vmx/vmx.o: warning: objtool: vmx_handle_exit_irqoff()+0x142: unreachable instruction

which triggers on an allmodconfig with CONFIG_GCOV_KERNEL unset.

Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lkml.kernel.org/r/5b1e2536cdbaa5246b60d7791b76130a74082c62.1599751464.git.jpoimboe@redhat.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
Merge tag 'objtool_urgent_for_5.8_rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2020-06-28T17:16:15+00:00 Linus Torvalds torvalds@linux-foundation.org 2020-06-28T17:16:15+00:00 7ecb59a56666506ebb1197f89ca7d587bd83309e Pull objtool fixes from Borislav Petkov: "Three fixes from Peter Zijlstra suppressing KCOV instrumentation in noinstr sections. Peter Zijlstra says: "Address KCOV vs noinstr. There is no function attribute to selectively suppress KCOV instrumentation, instead teach objtool to NOP out the calls in noinstr functions" This cures a bunch of KCOV crashes (as used by syzcaller)" * tag 'objtool_urgent_for_5.8_rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: objtool: Fix noinstr vs KCOV objtool: Provide elf_write_{insn,reloc}() objtool: Clean up elf_write() condition 
Pull objtool fixes from Borislav Petkov:
 "Three fixes from Peter Zijlstra suppressing KCOV instrumentation in
  noinstr sections.

  Peter Zijlstra says:
    "Address KCOV vs noinstr. There is no function attribute to
     selectively suppress KCOV instrumentation, instead teach objtool
     to NOP out the calls in noinstr functions"

  This cures a bunch of KCOV crashes (as used by syzcaller)"

* tag 'objtool_urgent_for_5.8_rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  objtool: Fix noinstr vs KCOV
  objtool: Provide elf_write_{insn,reloc}()
  objtool: Clean up elf_write() condition
objtool: Don't consider vmlinux a C-file 2020-06-25T11:45:39+00:00 Peter Zijlstra peterz@infradead.org 2020-06-17T16:22:31+00:00 734d099ba644f5a92c70efa3d54d0ba2500ce162 Avoids issuing C-file warnings for vmlinux. Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lkml.kernel.org/r/20200618144801.701257527@infradead.org 
Avoids issuing C-file warnings for vmlinux.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200618144801.701257527@infradead.org
objtool: Fix noinstr vs KCOV 2020-06-18T15:36:33+00:00 Peter Zijlstra peterz@infradead.org 2020-06-12T14:05:26+00:00 0f1441b44e823a74f3f3780902a113e07c73fbf6 Since many compilers cannot disable KCOV with a function attribute, help it to NOP out any __sanitizer_cov_*() calls injected in noinstr code. This turns: 12: e8 00 00 00 00 callq 17 <lockdep_hardirqs_on+0x17> 13: R_X86_64_PLT32 __sanitizer_cov_trace_pc-0x4 into: 12: 0f 1f 44 00 00 nopl 0x0(%rax,%rax,1) 13: R_X86_64_NONE __sanitizer_cov_trace_pc-0x4 Just like recordmcount does. Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Dmitry Vyukov <dvyukov@google.com> 
Since many compilers cannot disable KCOV with a function attribute,
help it to NOP out any __sanitizer_cov_*() calls injected in noinstr
code.

This turns:

12:   e8 00 00 00 00          callq  17 <lockdep_hardirqs_on+0x17>
		13: R_X86_64_PLT32      __sanitizer_cov_trace_pc-0x4

into:

12:   0f 1f 44 00 00          nopl   0x0(%rax,%rax,1)
		13: R_X86_64_NONE      __sanitizer_cov_trace_pc-0x4

Just like recordmcount does.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Dmitry Vyukov <dvyukov@google.com>
objtool: Provide elf_write_{insn,reloc}() 2020-06-18T15:36:33+00:00 Peter Zijlstra peterz@infradead.org 2020-06-12T13:43:00+00:00 fdabdd0b05e0bdf232340d5da86563ed142a99a7 This provides infrastructure to rewrite instructions; this is immediately useful for helping out with KCOV-vs-noinstr, but will also come in handy for a bunch of variable sized jump-label patches that are still on ice. Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> 
This provides infrastructure to rewrite instructions; this is
immediately useful for helping out with KCOV-vs-noinstr, but will
also come in handy for a bunch of variable sized jump-label patches
that are still on ice.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
objtool: Clean up elf_write() condition 2020-06-18T15:36:33+00:00 Peter Zijlstra peterz@infradead.org 2020-04-17T21:15:00+00:00 2b10be23ac0f8e107fd575397361ddbaebc2944b With there being multiple ways to change the ELF data, let's more concisely track modification. Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> 
With there being multiple ways to change the ELF data, let's more
concisely track modification.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
x86/entry, ubsan, objtool: Whitelist __ubsan_handle_*() 2020-06-15T12:10:09+00:00 Peter Zijlstra peterz@infradead.org 2020-06-03T18:09:06+00:00 6b643a07a7e41f9e11cfbb9bba4c5c9791ac2997 The UBSAN instrumentation only inserts external CALLs when things go 'BAD', much like WARN(). So treat them similar to WARN()s for noinstr, that is: allow them, at the risk of taking the machine down, to get their message out. Suggested-by: Marco Elver <elver@google.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Marco Elver <elver@google.com> 
The UBSAN instrumentation only inserts external CALLs when things go
'BAD', much like WARN(). So treat them similar to WARN()s for noinstr,
that is: allow them, at the risk of taking the machine down, to get
their message out.

Suggested-by: Marco Elver <elver@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Marco Elver <elver@google.com>
Rebase locking/kcsan to locking/urgent 2020-06-11T18:02:46+00:00 Thomas Gleixner tglx@linutronix.de 2020-06-11T18:02:46+00:00 37d1a04b13a6d2fec91a6813fc034947a27db034 Merge the state of the locking kcsan branch before the read/write_once() and the atomics modifications got merged. Squash the fallout of the rebase on top of the read/write once and atomic fallback work into the merge. The history of the original branch is preserved in tag locking-kcsan-2020-06-02. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> 
Merge the state of the locking kcsan branch before the read/write_once()
and the atomics modifications got merged.

Squash the fallout of the rebase on top of the read/write once and atomic
fallback work into the merge. The history of the original branch is
preserved in tag locking-kcsan-2020-06-02.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>