forked from mirrors/linux
		
	 685d982112
			
		
	
	
		685d982112
		
	
	
	
	
		
			
			- The biggest change is the rework of the percpu code,
   to support the 'Named Address Spaces' GCC feature,
   by Uros Bizjak:
 
    - This allows C code to access GS and FS segment relative
      memory via variables declared with such attributes,
      which allows the compiler to better optimize those accesses
      than the previous inline assembly code.
 
    - The series also includes a number of micro-optimizations
      for various percpu access methods, plus a number of
      cleanups of %gs accesses in assembly code.
 
    - These changes have been exposed to linux-next testing for
      the last ~5 months, with no known regressions in this area.
 
 - Fix/clean up __switch_to()'s broken but accidentally
   working handling of FPU switching - which also generates
   better code.
 
 - Propagate more RIP-relative addressing in assembly code,
   to generate slightly better code.
 
 - Rework the CPU mitigations Kconfig space to be less idiosyncratic,
   to make it easier for distros to follow & maintain these options.
 
 - Rework the x86 idle code to cure RCU violations and
   to clean up the logic.
 
 - Clean up the vDSO Makefile logic.
 
 - Misc cleanups and fixes.
 
 [ Please note that there's a higher number of merge commits in
   this branch (three) than is usual in x86 topic trees. This happened
   due to the long testing lifecycle of the percpu changes that
   involved 3 merge windows, which generated a longer history
   and various interactions with other core x86 changes that we
   felt better about to carry in a single branch. ]
 
 Signed-off-by: Ingo Molnar <mingo@kernel.org>
 -----BEGIN PGP SIGNATURE-----
 
 iQJFBAABCgAvFiEEBpT5eoXrXCwVQwEKEnMQ0APhK1gFAmXvB0gRHG1pbmdvQGtl
 cm5lbC5vcmcACgkQEnMQ0APhK1jUqRAAqnEQPiabF5acQlHrwviX+cjSobDlqtH5
 9q2AQy9qaEHapzD0XMOxvFye6XIvehGOGxSPvk6CoviSxBND8rb56lvnsEZuLeBV
 Bo5QSIL2x42Zrvo11iPHwgXZfTIusU90sBuKDRFkYBAxY3HK2naMDZe8MAsYCUE9
 nwgHF8DDc/NYiSOXV8kosWoWpNIkoK/STyH5bvTQZMqZcwyZ49AIeP1jGZb/prbC
 e/rbnlrq5Eu6brpM7xo9kELO0Vhd34urV14KrrIpdkmUKytW2KIsyvW8D6fqgDBj
 NSaQLLcz0pCXbhF+8Nqvdh/1coR4L7Ymt08P1rfEjCsQgb/2WnSAGUQuC5JoGzaj
 ngkbFcZllIbD9gNzMQ1n4Aw5TiO+l9zxCqPC/r58Uuvstr+K9QKlwnp2+B3Q73Ft
 rojIJ04NJL6lCHdDgwAjTTks+TD2PT/eBWsDfJ/1pnUWttmv9IjMpnXD5sbHxoiU
 2RGGKnYbxXczYdq/ALYDWM6JXpfnJZcXL3jJi0IDcCSsb92xRvTANYFHnTfyzGfw
 EHkhbF4e4Vy9f6QOkSP3CvW5H26BmZS9DKG0J9Il5R3u2lKdfbb5vmtUmVTqHmAD
 Ulo5cWZjEznlWCAYSI/aIidmBsp9OAEvYd+X7Z5SBIgTfSqV7VWHGt0BfA1heiVv
 F/mednG0gGc=
 =3v4F
 -----END PGP SIGNATURE-----
Merge tag 'x86-core-2024-03-11' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull core x86 updates from Ingo Molnar:
 - The biggest change is the rework of the percpu code, to support the
   'Named Address Spaces' GCC feature, by Uros Bizjak:
      - This allows C code to access GS and FS segment relative memory
        via variables declared with such attributes, which allows the
        compiler to better optimize those accesses than the previous
        inline assembly code.
      - The series also includes a number of micro-optimizations for
        various percpu access methods, plus a number of cleanups of %gs
        accesses in assembly code.
      - These changes have been exposed to linux-next testing for the
        last ~5 months, with no known regressions in this area.
 - Fix/clean up __switch_to()'s broken but accidentally working handling
   of FPU switching - which also generates better code
 - Propagate more RIP-relative addressing in assembly code, to generate
   slightly better code
 - Rework the CPU mitigations Kconfig space to be less idiosyncratic, to
   make it easier for distros to follow & maintain these options
 - Rework the x86 idle code to cure RCU violations and to clean up the
   logic
 - Clean up the vDSO Makefile logic
 - Misc cleanups and fixes
* tag 'x86-core-2024-03-11' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (52 commits)
  x86/idle: Select idle routine only once
  x86/idle: Let prefer_mwait_c1_over_halt() return bool
  x86/idle: Cleanup idle_setup()
  x86/idle: Clean up idle selection
  x86/idle: Sanitize X86_BUG_AMD_E400 handling
  sched/idle: Conditionally handle tick broadcast in default_idle_call()
  x86: Increase brk randomness entropy for 64-bit systems
  x86/vdso: Move vDSO to mmap region
  x86/vdso/kbuild: Group non-standard build attributes and primary object file rules together
  x86/vdso: Fix rethunk patching for vdso-image-{32,64}.o
  x86/retpoline: Ensure default return thunk isn't used at runtime
  x86/vdso: Use CONFIG_COMPAT_32 to specify vdso32
  x86/vdso: Use $(addprefix ) instead of $(foreach )
  x86/vdso: Simplify obj-y addition
  x86/vdso: Consolidate targets and clean-files
  x86/bugs: Rename CONFIG_RETHUNK              => CONFIG_MITIGATION_RETHUNK
  x86/bugs: Rename CONFIG_CPU_SRSO             => CONFIG_MITIGATION_SRSO
  x86/bugs: Rename CONFIG_CPU_IBRS_ENTRY       => CONFIG_MITIGATION_IBRS_ENTRY
  x86/bugs: Rename CONFIG_CPU_UNRET_ENTRY      => CONFIG_MITIGATION_UNRET_ENTRY
  x86/bugs: Rename CONFIG_SLS                  => CONFIG_MITIGATION_SLS
  ...
		
	
			
		
			
				
	
	
		
			167 lines
		
	
	
	
		
			4.7 KiB
		
	
	
	
		
			C
		
	
	
	
	
	
			
		
		
	
	
			167 lines
		
	
	
	
		
			4.7 KiB
		
	
	
	
		
			C
		
	
	
	
	
	
| /* SPDX-License-Identifier: GPL-2.0 */
 | |
| #ifndef __LINUX_COMPILER_TYPES_H
 | |
| #error "Please don't include <linux/compiler-gcc.h> directly, include <linux/compiler.h> instead."
 | |
| #endif
 | |
| 
 | |
| /*
 | |
|  * Common definitions for all gcc versions go here.
 | |
|  */
 | |
| #define GCC_VERSION (__GNUC__ * 10000		\
 | |
| 		     + __GNUC_MINOR__ * 100	\
 | |
| 		     + __GNUC_PATCHLEVEL__)
 | |
| 
 | |
| /*
 | |
|  * This macro obfuscates arithmetic on a variable address so that gcc
 | |
|  * shouldn't recognize the original var, and make assumptions about it.
 | |
|  *
 | |
|  * This is needed because the C standard makes it undefined to do
 | |
|  * pointer arithmetic on "objects" outside their boundaries and the
 | |
|  * gcc optimizers assume this is the case. In particular they
 | |
|  * assume such arithmetic does not wrap.
 | |
|  *
 | |
|  * A miscompilation has been observed because of this on PPC.
 | |
|  * To work around it we hide the relationship of the pointer and the object
 | |
|  * using this macro.
 | |
|  *
 | |
|  * Versions of the ppc64 compiler before 4.1 had a bug where use of
 | |
|  * RELOC_HIDE could trash r30. The bug can be worked around by changing
 | |
|  * the inline assembly constraint from =g to =r, in this particular
 | |
|  * case either is valid.
 | |
|  */
 | |
| #define RELOC_HIDE(ptr, off)						\
 | |
| ({									\
 | |
| 	unsigned long __ptr;						\
 | |
| 	__asm__ ("" : "=r"(__ptr) : "0"(ptr));				\
 | |
| 	(typeof(ptr)) (__ptr + (off));					\
 | |
| })
 | |
| 
 | |
| #ifdef CONFIG_MITIGATION_RETPOLINE
 | |
| #define __noretpoline __attribute__((__indirect_branch__("keep")))
 | |
| #endif
 | |
| 
 | |
| #if defined(LATENT_ENTROPY_PLUGIN) && !defined(__CHECKER__)
 | |
| #define __latent_entropy __attribute__((latent_entropy))
 | |
| #endif
 | |
| 
 | |
| /*
 | |
|  * calling noreturn functions, __builtin_unreachable() and __builtin_trap()
 | |
|  * confuse the stack allocation in gcc, leading to overly large stack
 | |
|  * frames, see https://gcc.gnu.org/bugzilla/show_bug.cgi?id=82365
 | |
|  *
 | |
|  * Adding an empty inline assembly before it works around the problem
 | |
|  */
 | |
| #define barrier_before_unreachable() asm volatile("")
 | |
| 
 | |
| /*
 | |
|  * Mark a position in code as unreachable.  This can be used to
 | |
|  * suppress control flow warnings after asm blocks that transfer
 | |
|  * control elsewhere.
 | |
|  */
 | |
| #define unreachable() \
 | |
| 	do {					\
 | |
| 		annotate_unreachable();		\
 | |
| 		barrier_before_unreachable();	\
 | |
| 		__builtin_unreachable();	\
 | |
| 	} while (0)
 | |
| 
 | |
| /*
 | |
|  * GCC 'asm goto' with outputs miscompiles certain code sequences:
 | |
|  *
 | |
|  *   https://gcc.gnu.org/bugzilla/show_bug.cgi?id=113921
 | |
|  *
 | |
|  * Work around it via the same compiler barrier quirk that we used
 | |
|  * to use for the old 'asm goto' workaround.
 | |
|  *
 | |
|  * Also, always mark such 'asm goto' statements as volatile: all
 | |
|  * asm goto statements are supposed to be volatile as per the
 | |
|  * documentation, but some versions of gcc didn't actually do
 | |
|  * that for asms with outputs:
 | |
|  *
 | |
|  *    https://gcc.gnu.org/bugzilla/show_bug.cgi?id=98619
 | |
|  */
 | |
| #ifdef CONFIG_GCC_ASM_GOTO_OUTPUT_WORKAROUND
 | |
| #define asm_goto_output(x...) \
 | |
| 	do { asm volatile goto(x); asm (""); } while (0)
 | |
| #endif
 | |
| 
 | |
| #if defined(CONFIG_ARCH_USE_BUILTIN_BSWAP)
 | |
| #define __HAVE_BUILTIN_BSWAP32__
 | |
| #define __HAVE_BUILTIN_BSWAP64__
 | |
| #define __HAVE_BUILTIN_BSWAP16__
 | |
| #endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP */
 | |
| 
 | |
| #if GCC_VERSION >= 70000
 | |
| #define KASAN_ABI_VERSION 5
 | |
| #else
 | |
| #define KASAN_ABI_VERSION 4
 | |
| #endif
 | |
| 
 | |
| #ifdef CONFIG_SHADOW_CALL_STACK
 | |
| #define __noscs __attribute__((__no_sanitize__("shadow-call-stack")))
 | |
| #endif
 | |
| 
 | |
| #define __no_sanitize_address __attribute__((__no_sanitize_address__))
 | |
| 
 | |
| #if defined(__SANITIZE_THREAD__)
 | |
| #define __no_sanitize_thread __attribute__((__no_sanitize_thread__))
 | |
| #else
 | |
| #define __no_sanitize_thread
 | |
| #endif
 | |
| 
 | |
| #define __no_sanitize_undefined __attribute__((__no_sanitize_undefined__))
 | |
| 
 | |
| /*
 | |
|  * Only supported since gcc >= 12
 | |
|  */
 | |
| #if defined(CONFIG_KCOV) && __has_attribute(__no_sanitize_coverage__)
 | |
| #define __no_sanitize_coverage __attribute__((__no_sanitize_coverage__))
 | |
| #else
 | |
| #define __no_sanitize_coverage
 | |
| #endif
 | |
| 
 | |
| /*
 | |
|  * Treat __SANITIZE_HWADDRESS__ the same as __SANITIZE_ADDRESS__ in the kernel,
 | |
|  * matching the defines used by Clang.
 | |
|  */
 | |
| #ifdef __SANITIZE_HWADDRESS__
 | |
| #define __SANITIZE_ADDRESS__
 | |
| #endif
 | |
| 
 | |
| /*
 | |
|  * GCC does not support KMSAN.
 | |
|  */
 | |
| #define __no_sanitize_memory
 | |
| #define __no_kmsan_checks
 | |
| 
 | |
| /*
 | |
|  * Turn individual warnings and errors on and off locally, depending
 | |
|  * on version.
 | |
|  */
 | |
| #define __diag_GCC(version, severity, s) \
 | |
| 	__diag_GCC_ ## version(__diag_GCC_ ## severity s)
 | |
| 
 | |
| /* Severity used in pragma directives */
 | |
| #define __diag_GCC_ignore	ignored
 | |
| #define __diag_GCC_warn		warning
 | |
| #define __diag_GCC_error	error
 | |
| 
 | |
| #define __diag_str1(s)		#s
 | |
| #define __diag_str(s)		__diag_str1(s)
 | |
| #define __diag(s)		_Pragma(__diag_str(GCC diagnostic s))
 | |
| 
 | |
| #if GCC_VERSION >= 80000
 | |
| #define __diag_GCC_8(s)		__diag(s)
 | |
| #else
 | |
| #define __diag_GCC_8(s)
 | |
| #endif
 | |
| 
 | |
| #define __diag_ignore_all(option, comment) \
 | |
| 	__diag(__diag_GCC_ignore option)
 | |
| 
 | |
| /*
 | |
|  * Prior to 9.1, -Wno-alloc-size-larger-than (and therefore the "alloc_size"
 | |
|  * attribute) do not work, and must be disabled.
 | |
|  */
 | |
| #if GCC_VERSION < 90100
 | |
| #undef __alloc_size__
 | |
| #endif
 |