linux.git/arch/x86/kernel/process.c, branch v6.15 Linux kernel source tree x86/tdx: Fix arch_safe_halt() execution for TDX VMs 2025-03-26T07:51:20+00:00 Vishal Annapurve vannapurve@google.com 2025-02-28T01:44:15+00:00 9f98a4f4e7216dbe366010b4cdcab6b220f229c4 Direct HLT instruction execution causes #VEs for TDX VMs which is routed to hypervisor via TDCALL. If HLT is executed in STI-shadow, resulting #VE handler will enable interrupts before TDCALL is routed to hypervisor leading to missed wakeup events, as current TDX spec doesn't expose interruptibility state information to allow #VE handler to selectively enable interrupts. Commit bfe6ed0c6727 ("x86/tdx: Add HLT support for TDX guests") prevented the idle routines from executing HLT instruction in STI-shadow. But it missed the paravirt routine which can be reached via this path as an example: kvm_wait() => safe_halt() => raw_safe_halt() => arch_safe_halt() => irq.safe_halt() => pv_native_safe_halt() To reliably handle arch_safe_halt() for TDX VMs, introduce explicit dependency on CONFIG_PARAVIRT and override paravirt halt()/safe_halt() routines with TDX-safe versions that execute direct TDCALL and needed interrupt flag updates. Executing direct TDCALL brings in additional benefit of avoiding HLT related #VEs altogether. As tested by Ryan Afranji: "Tested with the specjbb2015 benchmark. It has heavy lock contention which leads to many halt calls. TDX VMs suffered a poor score before this patchset. Verified the major performance improvement with this patchset applied." Fixes: bfe6ed0c6727 ("x86/tdx: Add HLT support for TDX guests") Signed-off-by: Vishal Annapurve <vannapurve@google.com> Signed-off-by: Ingo Molnar <mingo@kernel.org> Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Tested-by: Ryan Afranji <afranji@google.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Brian Gerst <brgerst@gmail.com> Cc: Juergen Gross <jgross@suse.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20250228014416.3925664-3-vannapurve@google.com 
Direct HLT instruction execution causes #VEs for TDX VMs which is routed
to hypervisor via TDCALL. If HLT is executed in STI-shadow, resulting #VE
handler will enable interrupts before TDCALL is routed to hypervisor
leading to missed wakeup events, as current TDX spec doesn't expose
interruptibility state information to allow #VE handler to selectively
enable interrupts.

Commit bfe6ed0c6727 ("x86/tdx: Add HLT support for TDX guests")
prevented the idle routines from executing HLT instruction in STI-shadow.
But it missed the paravirt routine which can be reached via this path
as an example:

	kvm_wait()       =>
        safe_halt()      =>
        raw_safe_halt()  =>
        arch_safe_halt() =>
        irq.safe_halt()  =>
        pv_native_safe_halt()

To reliably handle arch_safe_halt() for TDX VMs, introduce explicit
dependency on CONFIG_PARAVIRT and override paravirt halt()/safe_halt()
routines with TDX-safe versions that execute direct TDCALL and needed
interrupt flag updates. Executing direct TDCALL brings in additional
benefit of avoiding HLT related #VEs altogether.

As tested by Ryan Afranji:

  "Tested with the specjbb2015 benchmark. It has heavy lock contention which leads
   to many halt calls. TDX VMs suffered a poor score before this patchset.

   Verified the major performance improvement with this patchset applied."

Fixes: bfe6ed0c6727 ("x86/tdx: Add HLT support for TDX guests")
Signed-off-by: Vishal Annapurve <vannapurve@google.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Tested-by: Ryan Afranji <afranji@google.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250228014416.3925664-3-vannapurve@google.com
Merge tag 'x86-fpu-2025-03-22' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2025-03-25T05:27:18+00:00 Linus Torvalds torvalds@linux-foundation.org 2025-03-25T05:27:18+00:00 71b639af06ef1c422df87be36ad411bc31abf1ce Pull x86/fpu updates from Ingo Molnar: - Improve crypto performance by making kernel-mode FPU reliably usable in softirqs ((Eric Biggers) - Fully optimize out WARN_ON_FPU() (Eric Biggers) - Initial steps to support Support Intel APX (Advanced Performance Extensions) (Chang S. Bae) - Fix KASAN for arch_dup_task_struct() (Benjamin Berg) - Refine and simplify the FPU magic number check during signal return (Chang S. Bae) - Fix inconsistencies in guest FPU xfeatures (Chao Gao, Stanislav Spassov) - selftests/x86/xstate: Introduce common code for testing extended states (Chang S. Bae) - Misc fixes and cleanups (Borislav Petkov, Colin Ian King, Uros Bizjak) * tag 'x86-fpu-2025-03-22' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: x86/fpu/xstate: Fix inconsistencies in guest FPU xfeatures x86/fpu: Clarify the "xa" symbolic name used in the XSTATE* macros x86/fpu: Use XSAVE{,OPT,C,S} and XRSTOR{,S} mnemonics in xstate.h x86/fpu: Improve crypto performance by making kernel-mode FPU reliably usable in softirqs x86/fpu/xstate: Simplify print_xstate_features() x86/fpu: Refine and simplify the magic number check during signal return selftests/x86/xstate: Fix spelling mistake "hader" -> "header" x86/fpu: Avoid copying dynamic FP state from init_task in arch_dup_task_struct() vmlinux.lds.h: Remove entry to place init_task onto init_stack selftests/x86/avx: Add AVX tests selftests/x86/xstate: Clarify supported xstates selftests/x86/xstate: Consolidate test invocations into a single entry selftests/x86/xstate: Introduce signal ABI test selftests/x86/xstate: Refactor ptrace ABI test selftests/x86/xstate: Refactor context switching test selftests/x86/xstate: Enumerate and name xstate components selftests/x86/xstate: Refactor XSAVE helpers for general use selftests/x86: Consolidate redundant signal helper functions x86/fpu: Fix guest FPU state buffer allocation size x86/fpu: Fully optimize out WARN_ON_FPU() 
Pull x86/fpu updates from Ingo Molnar:

 - Improve crypto performance by making kernel-mode FPU reliably usable
   in softirqs ((Eric Biggers)

 - Fully optimize out WARN_ON_FPU() (Eric Biggers)

 - Initial steps to support Support Intel APX (Advanced Performance
   Extensions) (Chang S. Bae)

 - Fix KASAN for arch_dup_task_struct() (Benjamin Berg)

 - Refine and simplify the FPU magic number check during signal return
   (Chang S. Bae)

 - Fix inconsistencies in guest FPU xfeatures (Chao Gao, Stanislav
   Spassov)

 - selftests/x86/xstate: Introduce common code for testing extended
   states (Chang S. Bae)

 - Misc fixes and cleanups (Borislav Petkov, Colin Ian King, Uros
   Bizjak)

* tag 'x86-fpu-2025-03-22' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/fpu/xstate: Fix inconsistencies in guest FPU xfeatures
  x86/fpu: Clarify the "xa" symbolic name used in the XSTATE* macros
  x86/fpu: Use XSAVE{,OPT,C,S} and XRSTOR{,S} mnemonics in xstate.h
  x86/fpu: Improve crypto performance by making kernel-mode FPU reliably usable in softirqs
  x86/fpu/xstate: Simplify print_xstate_features()
  x86/fpu: Refine and simplify the magic number check during signal return
  selftests/x86/xstate: Fix spelling mistake "hader" -> "header"
  x86/fpu: Avoid copying dynamic FP state from init_task in arch_dup_task_struct()
  vmlinux.lds.h: Remove entry to place init_task onto init_stack
  selftests/x86/avx: Add AVX tests
  selftests/x86/xstate: Clarify supported xstates
  selftests/x86/xstate: Consolidate test invocations into a single entry
  selftests/x86/xstate: Introduce signal ABI test
  selftests/x86/xstate: Refactor ptrace ABI test
  selftests/x86/xstate: Refactor context switching test
  selftests/x86/xstate: Enumerate and name xstate components
  selftests/x86/xstate: Refactor XSAVE helpers for general use
  selftests/x86: Consolidate redundant signal helper functions
  x86/fpu: Fix guest FPU state buffer allocation size
  x86/fpu: Fully optimize out WARN_ON_FPU()
x86/syscall: Move sys_ni_syscall() 2025-03-19T10:19:17+00:00 Brian Gerst brgerst@gmail.com 2025-03-14T15:12:18+00:00 9a93e29f16bbba90a63faad0abbc6dea3b2f0c63 Move sys_ni_syscall() to kernel/process.c, and remove the now empty entry/common.c No functional changes. Signed-off-by: Brian Gerst <brgerst@gmail.com> Signed-off-by: Ingo Molnar <mingo@kernel.org> Reviewed-by: Sohil Mehta <sohil.mehta@intel.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Link: https://lore.kernel.org/r/20250314151220.862768-6-brgerst@gmail.com 
Move sys_ni_syscall() to kernel/process.c, and remove the now empty
entry/common.c

No functional changes.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Sohil Mehta <sohil.mehta@intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Link: https://lore.kernel.org/r/20250314151220.862768-6-brgerst@gmail.com
x86/fpu: Avoid copying dynamic FP state from init_task in arch_dup_task_struct() 2025-02-26T14:32:34+00:00 Benjamin Berg benjamin.berg@intel.com 2025-02-26T13:31:36+00:00 5d3b81d4d8520efe888536b6906dc10fd1a228a8 The init_task instance of struct task_struct is statically allocated and may not contain the full FP state for userspace. As such, limit the copy to the valid area of both init_task and 'dst' and ensure all memory is initialized. Note that the FP state is only needed for userspace, and as such it is entirely reasonable for init_task to not contain parts of it. Fixes: 5aaeb5c01c5b ("x86/fpu, sched: Introduce CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT and use it on x86") Signed-off-by: Benjamin Berg <benjamin.berg@intel.com> Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: Andy Lutomirski <luto@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Oleg Nesterov <oleg@redhat.com> Link: https://lore.kernel.org/r/20250226133136.816901-1-benjamin@sipsolutions.net ---- v2: - Fix code if arch_task_struct_size < sizeof(init_task) by using memcpy_and_pad. 
The init_task instance of struct task_struct is statically allocated and
may not contain the full FP state for userspace. As such, limit the copy
to the valid area of both init_task and 'dst' and ensure all memory is
initialized.

Note that the FP state is only needed for userspace, and as such it is
entirely reasonable for init_task to not contain parts of it.

Fixes: 5aaeb5c01c5b ("x86/fpu, sched: Introduce CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT and use it on x86")
Signed-off-by: Benjamin Berg <benjamin.berg@intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Link: https://lore.kernel.org/r/20250226133136.816901-1-benjamin@sipsolutions.net
----

v2:
- Fix code if arch_task_struct_size < sizeof(init_task) by using
  memcpy_and_pad.
x86/arch_prctl: Simplify sys_arch_prctl() 2025-02-21T21:32:25+00:00 Brian Gerst brgerst@gmail.com 2025-02-02T20:23:22+00:00 2df1ad0d25803399056d439425e271802cd243f6 Use in_ia32_syscall() instead of a compat syscall entry. No change in functionality intended. Signed-off-by: Brian Gerst <brgerst@gmail.com> Signed-off-by: Ingo Molnar <mingo@kernel.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Link: https://lore.kernel.org/r/20250202202323.422113-2-brgerst@gmail.com 
Use in_ia32_syscall() instead of a compat syscall entry.

No change in functionality intended.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Link: https://lore.kernel.org/r/20250202202323.422113-2-brgerst@gmail.com
Merge tag 'objtool-core-2025-01-20' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2025-01-21T18:13:11+00:00 Linus Torvalds torvalds@linux-foundation.org 2025-01-21T18:13:11+00:00 a6640c8c2fc029f015c87672585931c6106971c1 Pull objtool updates from Ingo Molnar: - Introduce the generic section-based annotation infrastructure a.k.a. ASM_ANNOTATE/ANNOTATE (Peter Zijlstra) - Convert various facilities to ASM_ANNOTATE/ANNOTATE: (Peter Zijlstra) - ANNOTATE_NOENDBR - ANNOTATE_RETPOLINE_SAFE - instrumentation_{begin,end}() - VALIDATE_UNRET_BEGIN - ANNOTATE_IGNORE_ALTERNATIVE - ANNOTATE_INTRA_FUNCTION_CALL - {.UN}REACHABLE - Optimize the annotation-sections parsing code (Peter Zijlstra) - Centralize annotation definitions in <linux/objtool.h> - Unify & simplify the barrier_before_unreachable()/unreachable() definitions (Peter Zijlstra) - Convert unreachable() calls to BUG() in x86 code, as unreachable() has unreliable code generation (Peter Zijlstra) - Remove annotate_reachable() and annotate_unreachable(), as it's unreliable against compiler optimizations (Peter Zijlstra) - Fix non-standard ANNOTATE_REACHABLE annotation order (Peter Zijlstra) - Robustify the annotation code by warning about unknown annotation types (Peter Zijlstra) - Allow arch code to discover jump table size, in preparation of annotated jump table support (Ard Biesheuvel) * tag 'objtool-core-2025-01-20' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: x86/mm: Convert unreachable() to BUG() objtool: Allow arch code to discover jump table size objtool: Warn about unknown annotation types objtool: Fix ANNOTATE_REACHABLE to be a normal annotation objtool: Convert {.UN}REACHABLE to ANNOTATE objtool: Remove annotate_{,un}reachable() loongarch: Use ASM_REACHABLE x86: Convert unreachable() to BUG() unreachable: Unify objtool: Collect more annotations in objtool.h objtool: Collapse annotate sequences objtool: Convert ANNOTATE_INTRA_FUNCTION_CALL to ANNOTATE objtool: Convert ANNOTATE_IGNORE_ALTERNATIVE to ANNOTATE objtool: Convert VALIDATE_UNRET_BEGIN to ANNOTATE objtool: Convert instrumentation_{begin,end}() to ANNOTATE objtool: Convert ANNOTATE_RETPOLINE_SAFE to ANNOTATE objtool: Convert ANNOTATE_NOENDBR to ANNOTATE objtool: Generic annotation infrastructure 
Pull objtool updates from Ingo Molnar:

 - Introduce the generic section-based annotation infrastructure a.k.a.
   ASM_ANNOTATE/ANNOTATE (Peter Zijlstra)

 - Convert various facilities to ASM_ANNOTATE/ANNOTATE: (Peter Zijlstra)
    - ANNOTATE_NOENDBR
    - ANNOTATE_RETPOLINE_SAFE
    - instrumentation_{begin,end}()
    - VALIDATE_UNRET_BEGIN
    - ANNOTATE_IGNORE_ALTERNATIVE
    - ANNOTATE_INTRA_FUNCTION_CALL
    - {.UN}REACHABLE

 - Optimize the annotation-sections parsing code (Peter Zijlstra)

 - Centralize annotation definitions in <linux/objtool.h>

 - Unify & simplify the barrier_before_unreachable()/unreachable()
   definitions (Peter Zijlstra)

 - Convert unreachable() calls to BUG() in x86 code, as unreachable()
   has unreliable code generation (Peter Zijlstra)

 - Remove annotate_reachable() and annotate_unreachable(), as it's
   unreliable against compiler optimizations (Peter Zijlstra)

 - Fix non-standard ANNOTATE_REACHABLE annotation order (Peter Zijlstra)

 - Robustify the annotation code by warning about unknown annotation
   types (Peter Zijlstra)

 - Allow arch code to discover jump table size, in preparation of
   annotated jump table support (Ard Biesheuvel)

* tag 'objtool-core-2025-01-20' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/mm: Convert unreachable() to BUG()
  objtool: Allow arch code to discover jump table size
  objtool: Warn about unknown annotation types
  objtool: Fix ANNOTATE_REACHABLE to be a normal annotation
  objtool: Convert {.UN}REACHABLE to ANNOTATE
  objtool: Remove annotate_{,un}reachable()
  loongarch: Use ASM_REACHABLE
  x86: Convert unreachable() to BUG()
  unreachable: Unify
  objtool: Collect more annotations in objtool.h
  objtool: Collapse annotate sequences
  objtool: Convert ANNOTATE_INTRA_FUNCTION_CALL to ANNOTATE
  objtool: Convert ANNOTATE_IGNORE_ALTERNATIVE to ANNOTATE
  objtool: Convert VALIDATE_UNRET_BEGIN to ANNOTATE
  objtool: Convert instrumentation_{begin,end}() to ANNOTATE
  objtool: Convert ANNOTATE_RETPOLINE_SAFE to ANNOTATE
  objtool: Convert ANNOTATE_NOENDBR to ANNOTATE
  objtool: Generic annotation infrastructure
x86/cpu: Make all all CPUID leaf names consistent 2024-12-18T14:17:46+00:00 Dave Hansen dave.hansen@linux.intel.com 2024-12-13T20:50:40+00:00 e5d3a57891ba500503df075b99b78d6e61f2694e The leaf names are not consistent. Give them all a CPUID_LEAF_ prefix for consistency and vertical alignment. Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Acked-by: Dave Jiang <dave.jiang@intel.com> # for ioatdma bits Link: https://lore.kernel.org/all/20241213205040.7B0C3241%40davehans-spike.ostc.intel.com 
The leaf names are not consistent.  Give them all a CPUID_LEAF_ prefix
for consistency and vertical alignment.

Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Acked-by: Dave Jiang <dave.jiang@intel.com> # for ioatdma bits
Link: https://lore.kernel.org/all/20241213205040.7B0C3241%40davehans-spike.ostc.intel.com
x86/cpu: Move MWAIT leaf definition to common header 2024-12-18T14:17:24+00:00 Dave Hansen dave.hansen@linux.intel.com 2024-12-13T20:50:28+00:00 497f70284695bbb9b875e182554ef3f18b4a56e2 Begin constructing a common place to keep all CPUID leaf definitions. Move CPUID_MWAIT_LEAF to the CPUID header and include it where needed. Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Reviewed-by: Zhao Liu <zhao1.liu@intel.com> Link: https://lore.kernel.org/all/20241213205028.EE94D02A%40davehans-spike.ostc.intel.com 
Begin constructing a common place to keep all CPUID leaf definitions.
Move CPUID_MWAIT_LEAF to the CPUID header and include it where
needed.

Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Zhao Liu <zhao1.liu@intel.com>
Link: https://lore.kernel.org/all/20241213205028.EE94D02A%40davehans-spike.ostc.intel.com
x86/paravirt: Remove the WBINVD callback 2024-12-06T10:01:36+00:00 Juergen Gross jgross@suse.com 2024-12-03T07:15:50+00:00 29188c16006176caee6cb6729103be51a29c1a93 The pv_ops::cpu.wbinvd paravirt callback is a leftover of lguest times. Today it is no longer needed, as all users use the native WBINVD implementation. Remove the callback and rename native_wbinvd() to wbinvd(). Signed-off-by: Juergen Gross <jgross@suse.com> Signed-off-by: Ingo Molnar <mingo@kernel.org> Link: https://lore.kernel.org/r/20241203071550.26487-1-jgross@suse.com 
The pv_ops::cpu.wbinvd paravirt callback is a leftover of lguest times.
Today it is no longer needed, as all users use the native WBINVD
implementation.

Remove the callback and rename native_wbinvd() to wbinvd().

Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20241203071550.26487-1-jgross@suse.com
x86: Convert unreachable() to BUG() 2024-12-02T11:01:43+00:00 Peter Zijlstra peterz@infradead.org 2024-11-28T09:39:02+00:00 2190966fbc14ca2cd4ea76eefeb96a47d8e390df Avoid unreachable() as it can (and will in the absence of UBSAN) generate fallthrough code. Use BUG() so we get a UD2 trap (with unreachable annotation). Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Josh Poimboeuf <jpoimboe@kernel.org> Link: https://lore.kernel.org/r/20241128094312.028316261@infradead.org 
Avoid unreachable() as it can (and will in the absence of UBSAN)
generate fallthrough code. Use BUG() so we get a UD2 trap (with
unreachable annotation).

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Josh Poimboeuf <jpoimboe@kernel.org>
Link: https://lore.kernel.org/r/20241128094312.028316261@infradead.org