select ARCH_HAS_GIGANTIC_PAGE
select ARCH_SUPPORTS_INT128 if CC_HAS_INT128
select ARCH_SUPPORTS_PER_VMA_LOCK
- select ARCH_USE_CMPXCHG_LOCKREF
select HAVE_ARCH_SOFT_DIRTY
select MODULES_USE_ELF_RELA
select NEED_DMA_MAP_STATE
#
select ACPI_LEGACY_TABLES_LOOKUP if ACPI
select ACPI_SYSTEM_POWER_STATES_SUPPORT if ACPI
+ select ACPI_HOTPLUG_CPU if ACPI_PROCESSOR && HOTPLUG_CPU
select ARCH_32BIT_OFF_T if X86_32
select ARCH_CLOCKSOURCE_INIT
select ARCH_CORRECT_STACKTRACE_ON_KRETPROBE
select ARCH_HAS_CACHE_LINE_SIZE
select ARCH_HAS_CPU_CACHE_INVALIDATE_MEMREGION
select ARCH_HAS_CPU_FINALIZE_INIT
+ select ARCH_HAS_CPU_PASID if IOMMU_SVA
select ARCH_HAS_CURRENT_STACK_POINTER
select ARCH_HAS_DEBUG_VIRTUAL
select ARCH_HAS_DEBUG_VM_PGTABLE if !X86_PAE
select ARCH_HAS_PMEM_API if X86_64
select ARCH_HAS_PTE_DEVMAP if X86_64
select ARCH_HAS_PTE_SPECIAL
+ select ARCH_HAS_HW_PTE_YOUNG
select ARCH_HAS_NONLEAF_PMD_YOUNG if PGTABLE_LEVELS > 2
select ARCH_HAS_UACCESS_FLUSHCACHE if X86_64
select ARCH_HAS_COPY_MC if X86_64
select ARCH_SUPPORTS_LTO_CLANG
select ARCH_SUPPORTS_LTO_CLANG_THIN
select ARCH_USE_BUILTIN_BSWAP
+ select ARCH_USE_CMPXCHG_LOCKREF if X86_CMPXCHG64
select ARCH_USE_MEMTEST
select ARCH_USE_QUEUED_RWLOCKS
select ARCH_USE_QUEUED_SPINLOCKS
select GENERIC_CLOCKEVENTS_MIN_ADJUST
select GENERIC_CMOS_UPDATE
select GENERIC_CPU_AUTOPROBE
+ select GENERIC_CPU_DEVICES
select GENERIC_CPU_VULNERABILITIES
select GENERIC_EARLY_IOREMAP
select GENERIC_ENTRY
select HAS_IOPORT
select HAVE_ACPI_APEI if ACPI
select HAVE_ACPI_APEI_NMI if ACPI
- select HAVE_ALIGNED_STRUCT_PAGE if SLUB
+ select HAVE_ALIGNED_STRUCT_PAGE
select HAVE_ARCH_AUDITSYSCALL
select HAVE_ARCH_HUGE_VMAP if X86_64 || X86_PAE
select HAVE_ARCH_HUGE_VMALLOC if X86_64
def_bool y
depends on INTEL_IOMMU && ACPI
- config X86_32_SMP
- def_bool y
- depends on X86_32 && SMP
-
config X86_64_SMP
def_bool y
depends on X86_64 && SMP
def_bool y
depends on CPU_SUP_AMD || CPU_SUP_INTEL
+ config MICROCODE_INITRD32
+ def_bool y
+ depends on MICROCODE && X86_32 && BLK_DEV_INITRD
+
config MICROCODE_LATE_LOADING
bool "Late microcode loading (DANGEROUS)"
default n
- depends on MICROCODE
+ depends on MICROCODE && SMP
help
Loading microcode late, when the system is up and executing instructions
is a tricky business and should be avoided if possible. Just the sequence
of synchronizing all cores and SMT threads is one fragile dance which does
not guarantee that cores might not softlock after the loading. Therefore,
- use this at your own risk. Late loading taints the kernel too.
+ use this at your own risk. Late loading taints the kernel unless the
+ microcode header indicates that it is safe for late loading via the
+ minimal revision check. This minimal revision check can be enforced on
+ the kernel command line with "microcode.minrev=Y".
+
+ config MICROCODE_LATE_FORCE_MINREV
+ bool "Enforce late microcode loading minimal revision check"
+ default n
+ depends on MICROCODE_LATE_LOADING
+ help
+ To prevent that users load microcode late which modifies already
+ in use features, newer microcode patches have a minimum revision field
+ in the microcode header, which tells the kernel which minimum
+ revision must be active in the CPU to safely load that new microcode
+ late into the running system. If disabled the check will not
+ be enforced but the kernel will be tainted when the minimal
+ revision check fails.
+
+ This minimal revision check can also be controlled via the
+ "microcode.minrev" parameter on the kernel command line.
+
+ If unsure say Y.
config X86_MSR
tristate "/dev/cpu/*/msr - Model-specific register support"
config HIGHMEM64G
bool "64GB"
- depends on !M486SX && !M486 && !M586 && !M586TSC && !M586MMX && !MGEODE_LX && !MGEODEGX1 && !MCYRIXIII && !MELAN && !MWINCHIPC6 && !MWINCHIP3D && !MK6
+ depends on X86_HAVE_PAE
select X86_PAE
help
Select this if you have a 32-bit processor and more than 4
config X86_PAE
bool "PAE (Physical Address Extension) Support"
- depends on X86_32 && !HIGHMEM4G
+ depends on X86_32 && X86_HAVE_PAE
select PHYS_ADDR_T_64BIT
select SWIOTLB
help
depends on X86_64 || (X86_32 && HIGHMEM64G && X86_BIGSMP)
default y if X86_BIGSMP
select USE_PERCPU_NUMA_NODE_ID
+ select OF_NUMA if OF
help
Enable NUMA (Non-Uniform Memory Access) support.
If unsure, say N.
+ config INTEL_TDX_HOST
+ bool "Intel Trust Domain Extensions (TDX) host support"
+ depends on CPU_SUP_INTEL
+ depends on X86_64
+ depends on KVM_INTEL
+ depends on X86_X2APIC
+ select ARCH_KEEP_MEMBLOCK
+ depends on CONTIG_ALLOC
+ depends on !KEXEC_CORE
+ depends on X86_MCE
+ help
+ Intel Trust Domain Extensions (TDX) protects guest VMs from malicious
+ host and certain physical attacks. This option enables necessary TDX
+ support in the host kernel to run confidential VMs.
+
+ If unsure, say N.
+
config EFI
bool "EFI runtime service support"
depends on ACPI
select UCS2_STRING
select EFI_RUNTIME_WRAPPERS
select ARCH_USE_MEMREMAP_PROT
+ select EFI_RUNTIME_MAP if KEXEC_CORE
help
This enables the kernel to use EFI runtime services that are
available (such as the EFI variable services).
config EFI_RUNTIME_MAP
bool "Export EFI runtime maps to sysfs" if EXPERT
depends on EFI
- default KEXEC_CORE
help
Export EFI runtime memory regions to /sys/firmware/efi/runtime-map.
That memory map is required by the 2nd kernel to set up EFI virtual
def_bool y
config ARCH_SUPPORTS_KEXEC_FILE
- def_bool X86_64 && CRYPTO && CRYPTO_SHA256
+ def_bool X86_64
config ARCH_SELECTS_KEXEC_FILE
def_bool y
select HAVE_IMA_KEXEC if IMA
config ARCH_SUPPORTS_KEXEC_PURGATORY
- def_bool KEXEC_FILE
+ def_bool y
config ARCH_SUPPORTS_KEXEC_SIG
def_bool y
config ARCH_SUPPORTS_CRASH_HOTPLUG
def_bool y
+ config ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION
+ def_bool CRASH_CORE
+
config PHYSICAL_START
hex "Physical address where the kernel is loaded" if (EXPERT || CRASH_DUMP)
default "0x1000000"
endmenu
+config CC_HAS_NAMED_AS
+ def_bool CC_IS_GCC && GCC_VERSION >= 120100
+
+config USE_X86_SEG_SUPPORT
+ def_bool y
+ depends on CC_HAS_NAMED_AS
+ #
+ # -fsanitize=kernel-address (KASAN) is at the moment incompatible
+ # with named address spaces - see GCC PR sanitizer/111736.
+ #
+ depends on !KASAN
+
config CC_HAS_SLS
def_bool $(cc-option,-mharden-sls=all)
64-bit kernel. You should likely turn this on, unless you're
100% sure that you don't have any 32-bit programs left.
+ config IA32_EMULATION_DEFAULT_DISABLED
+ bool "IA32 emulation disabled by default"
+ default n
+ depends on IA32_EMULATION
+ help
+ Make IA32 emulation disabled by default. This prevents loading 32-bit
+ processes and access to 32-bit syscalls. If unsure, leave it to its
+ default value.
+
config X86_X32_ABI
bool "x32 ABI for 64-bit mode"
depends on X86_64
.endm
#define THIS_CPU_user_pcid_flush_mask \
- PER_CPU_VAR(cpu_tlbstate) + TLB_STATE_user_pcid_flush_mask
+ PER_CPU_VAR(cpu_tlbstate + TLB_STATE_user_pcid_flush_mask)
- .macro SWITCH_TO_USER_CR3_NOSTACK scratch_reg:req scratch_reg2:req
- ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
+ .macro SWITCH_TO_USER_CR3 scratch_reg:req scratch_reg2:req
mov %cr3, \scratch_reg
ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID
/* Flip the PGD to the user version */
orq $(PTI_USER_PGTABLE_MASK), \scratch_reg
mov \scratch_reg, %cr3
+ .endm
+
+ .macro SWITCH_TO_USER_CR3_NOSTACK scratch_reg:req scratch_reg2:req
+ ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
+ SWITCH_TO_USER_CR3 \scratch_reg \scratch_reg2
.Lend_\@:
.endm
.macro SWITCH_TO_USER_CR3_STACK scratch_reg:req
+ ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
pushq %rax
- SWITCH_TO_USER_CR3_NOSTACK scratch_reg=\scratch_reg scratch_reg2=%rax
+ SWITCH_TO_USER_CR3 scratch_reg=\scratch_reg scratch_reg2=%rax
popq %rax
+ .Lend_\@:
.endm
.macro SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg:req save_reg:req
.macro CHECK_AND_APPLY_ESPFIX
#ifdef CONFIG_X86_ESPFIX32
#define GDT_ESPFIX_OFFSET (GDT_ENTRY_ESPFIX_SS * 8)
-#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + GDT_ESPFIX_OFFSET
+#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page + GDT_ESPFIX_OFFSET)
ALTERNATIVE "jmp .Lend_\@", "", X86_BUG_ESPFIX
movl %esp, %eax
call do_SYSENTER_32
- testl %eax, %eax
+ testb %al, %al
jz .Lsyscall_32_done
STACKLEAK_ERASE
* - SYM_FUNC_START/END:Define functions in the symbol table.
* - idtentry: Define exception entry points.
*/
+ #include <linux/export.h>
#include <linux/linkage.h>
#include <asm/segment.h>
#include <asm/cache.h>
#include <asm/asm.h>
#include <asm/smap.h>
#include <asm/pgtable_types.h>
- #include <asm/export.h>
#include <asm/frame.h>
#include <asm/trapnr.h>
#include <asm/nospec-branch.h>
* In the Xen PV case we must use iret anyway.
*/
- ALTERNATIVE "", "jmp swapgs_restore_regs_and_return_to_usermode", \
- X86_FEATURE_XENPV
-
- movq RCX(%rsp), %rcx
- movq RIP(%rsp), %r11
-
- cmpq %rcx, %r11 /* SYSRET requires RCX == RIP */
- jne swapgs_restore_regs_and_return_to_usermode
-
- /*
- * On Intel CPUs, SYSRET with non-canonical RCX/RIP will #GP
- * in kernel space. This essentially lets the user take over
- * the kernel, since userspace controls RSP.
- *
- * If width of "canonical tail" ever becomes variable, this will need
- * to be updated to remain correct on both old and new CPUs.
- *
- * Change top bits to match most significant bit (47th or 56th bit
- * depending on paging mode) in the address.
- */
- #ifdef CONFIG_X86_5LEVEL
- ALTERNATIVE "shl $(64 - 48), %rcx; sar $(64 - 48), %rcx", \
- "shl $(64 - 57), %rcx; sar $(64 - 57), %rcx", X86_FEATURE_LA57
- #else
- shl $(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx
- sar $(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx
- #endif
-
- /* If this changed %rcx, it was not canonical */
- cmpq %rcx, %r11
- jne swapgs_restore_regs_and_return_to_usermode
-
- cmpq $__USER_CS, CS(%rsp) /* CS must match SYSRET */
- jne swapgs_restore_regs_and_return_to_usermode
-
- movq R11(%rsp), %r11
- cmpq %r11, EFLAGS(%rsp) /* R11 == RFLAGS */
- jne swapgs_restore_regs_and_return_to_usermode
-
- /*
- * SYSCALL clears RF when it saves RFLAGS in R11 and SYSRET cannot
- * restore RF properly. If the slowpath sets it for whatever reason, we
- * need to restore it correctly.
- *
- * SYSRET can restore TF, but unlike IRET, restoring TF results in a
- * trap from userspace immediately after SYSRET. This would cause an
- * infinite loop whenever #DB happens with register state that satisfies
- * the opportunistic SYSRET conditions. For example, single-stepping
- * this user code:
- *
- * movq $stuck_here, %rcx
- * pushfq
- * popq %r11
- * stuck_here:
- *
- * would never get past 'stuck_here'.
- */
- testq $(X86_EFLAGS_RF|X86_EFLAGS_TF), %r11
- jnz swapgs_restore_regs_and_return_to_usermode
-
- /* nothing to check for RSP */
-
- cmpq $__USER_DS, SS(%rsp) /* SS must match SYSRET */
- jne swapgs_restore_regs_and_return_to_usermode
+ ALTERNATIVE "testb %al, %al; jz swapgs_restore_regs_and_return_to_usermode", \
+ "jmp swapgs_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV
/*
* We win! This label is here just for ease of understanding
#ifdef CONFIG_STACKPROTECTOR
movq TASK_stack_canary(%rsi), %rbx
- movq %rbx, PER_CPU_VAR(fixed_percpu_data) + FIXED_stack_canary
+ movq %rbx, PER_CPU_VAR(fixed_percpu_data + FIXED_stack_canary)
#endif
/*
SYM_CODE_START_LOCAL(common_interrupt_return)
SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL)
IBRS_EXIT
- #ifdef CONFIG_DEBUG_ENTRY
- /* Assert that pt_regs indicates user mode. */
- testb $3, CS(%rsp)
- jnz 1f
- ud2
- 1:
- #endif
#ifdef CONFIG_XEN_PV
ALTERNATIVE "", "jmp xenpv_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV
#endif
+ #ifdef CONFIG_PAGE_TABLE_ISOLATION
+ ALTERNATIVE "", "jmp .Lpti_restore_regs_and_return_to_usermode", X86_FEATURE_PTI
+ #endif
+
+ STACKLEAK_ERASE
+ POP_REGS
+ add $8, %rsp /* orig_ax */
+ UNWIND_HINT_IRET_REGS
+ .Lswapgs_and_iret:
+ swapgs
+ /* Assert that the IRET frame indicates user mode. */
+ testb $3, 8(%rsp)
+ jnz .Lnative_iret
+ ud2
+
+ #ifdef CONFIG_PAGE_TABLE_ISOLATION
+ .Lpti_restore_regs_and_return_to_usermode:
POP_REGS pop_rdi=0
/*
*/
STACKLEAK_ERASE_NOCLOBBER
- SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi
+ push %rax
+ SWITCH_TO_USER_CR3 scratch_reg=%rdi scratch_reg2=%rax
+ pop %rax
/* Restore RDI. */
popq %rdi
- swapgs
- jmp .Lnative_iret
-
+ jmp .Lswapgs_and_iret
+ #endif
SYM_INNER_LABEL(restore_regs_and_return_to_kernel, SYM_L_GLOBAL)
#ifdef CONFIG_DEBUG_ENTRY
iretq
SYM_CODE_END(asm_exc_nmi)
- #ifndef CONFIG_IA32_EMULATION
/*
* This handles SYSCALL from 32-bit code. There is no way to program
* MSRs to fully disable 32-bit SYSCALL.
*/
- SYM_CODE_START(ignore_sysret)
+ SYM_CODE_START(entry_SYSCALL32_ignore)
UNWIND_HINT_END_OF_STACK
ENDBR
mov $-ENOSYS, %eax
sysretl
- SYM_CODE_END(ignore_sysret)
- #endif
+ SYM_CODE_END(entry_SYSCALL32_ignore)
.pushsection .text, "ax"
__FUNC_ALIGN
#ifndef _ASM_X86_CURRENT_H
#define _ASM_X86_CURRENT_H
+ #include <linux/build_bug.h>
#include <linux/compiler.h>
#ifndef __ASSEMBLY__
DECLARE_PER_CPU_ALIGNED(struct pcpu_hot, pcpu_hot);
+/* const-qualified alias to pcpu_hot, aliased by linker. */
+DECLARE_PER_CPU_ALIGNED(const struct pcpu_hot __percpu_seg_override,
+ const_pcpu_hot);
+
static __always_inline struct task_struct *get_current(void)
{
+ if (IS_ENABLED(CONFIG_USE_X86_SEG_SUPPORT))
+ return this_cpu_read_const(const_pcpu_hot.current_task);
+
return this_cpu_read_stable(pcpu_hot.current_task);
}
* but there is still a cushion vs. the RSB depth. The algorithm does not
* claim to be perfect and it can be speculated around by the CPU, but it
* is considered that it obfuscates the problem enough to make exploitation
- * extremly difficult.
+ * extremely difficult.
*/
#define RET_DEPTH_SHIFT 5
#define RSB_RET_STUFF_LOOPS 16
#ifdef CONFIG_CALL_THUNKS_DEBUG
# define CALL_THUNKS_DEBUG_INC_CALLS \
- incq %gs:__x86_call_count;
+ incq PER_CPU_VAR(__x86_call_count);
# define CALL_THUNKS_DEBUG_INC_RETS \
- incq %gs:__x86_ret_count;
+ incq PER_CPU_VAR(__x86_ret_count);
# define CALL_THUNKS_DEBUG_INC_STUFFS \
- incq %gs:__x86_stuffs_count;
+ incq PER_CPU_VAR(__x86_stuffs_count);
# define CALL_THUNKS_DEBUG_INC_CTXSW \
- incq %gs:__x86_ctxsw_count;
+ incq PER_CPU_VAR(__x86_ctxsw_count);
#else
# define CALL_THUNKS_DEBUG_INC_CALLS
# define CALL_THUNKS_DEBUG_INC_RETS
#define CREDIT_CALL_DEPTH \
movq $-1, PER_CPU_VAR(pcpu_hot + X86_call_depth);
-#define ASM_CREDIT_CALL_DEPTH \
- movq $-1, PER_CPU_VAR(pcpu_hot + X86_call_depth);
-
#define RESET_CALL_DEPTH \
xor %eax, %eax; \
bts $63, %rax; \
CALL_THUNKS_DEBUG_INC_CALLS
#define INCREMENT_CALL_DEPTH \
- sarq $5, %gs:pcpu_hot + X86_call_depth; \
- CALL_THUNKS_DEBUG_INC_CALLS
-
-#define ASM_INCREMENT_CALL_DEPTH \
sarq $5, PER_CPU_VAR(pcpu_hot + X86_call_depth); \
CALL_THUNKS_DEBUG_INC_CALLS
#else
#define CREDIT_CALL_DEPTH
-#define ASM_CREDIT_CALL_DEPTH
#define RESET_CALL_DEPTH
-#define INCREMENT_CALL_DEPTH
-#define ASM_INCREMENT_CALL_DEPTH
#define RESET_CALL_DEPTH_FROM_CALL
+#define INCREMENT_CALL_DEPTH
#endif
/*
jnz 771b; \
/* barrier for jnz misprediction */ \
lfence; \
- ASM_CREDIT_CALL_DEPTH \
+ CREDIT_CALL_DEPTH \
CALL_THUNKS_DEBUG_INC_CTXSW
#else
/*
.macro ANNOTATE_RETPOLINE_SAFE
.Lhere_\@:
.pushsection .discard.retpoline_safe
- .long .Lhere_\@ - .
+ .long .Lhere_\@
.popsection
.endm
/*
* Abuse ANNOTATE_RETPOLINE_SAFE on a NOP to indicate UNRET_END, should
- * eventually turn into it's own annotation.
+ * eventually turn into its own annotation.
*/
.macro VALIDATE_UNRET_END
#if defined(CONFIG_NOINSTR_VALIDATION) && \
.Lskip_rsb_\@:
.endm
- #ifdef CONFIG_CPU_UNRET_ENTRY
+ #if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO)
#define CALL_UNTRAIN_RET "call entry_untrain_ret"
#else
#define CALL_UNTRAIN_RET ""
* As such, this must be placed after every *SWITCH_TO_KERNEL_CR3 at a point
* where we have a stack but before any RET instruction.
*/
- .macro UNTRAIN_RET
- #if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) || \
- defined(CONFIG_CALL_DEPTH_TRACKING) || defined(CONFIG_CPU_SRSO)
+ .macro __UNTRAIN_RET ibpb_feature, call_depth_insns
+ #if defined(CONFIG_RETHUNK) || defined(CONFIG_CPU_IBPB_ENTRY)
VALIDATE_UNRET_END
ALTERNATIVE_3 "", \
CALL_UNTRAIN_RET, X86_FEATURE_UNRET, \
- "call entry_ibpb", X86_FEATURE_ENTRY_IBPB, \
- __stringify(RESET_CALL_DEPTH), X86_FEATURE_CALL_DEPTH
+ "call entry_ibpb", \ibpb_feature, \
+ __stringify(\call_depth_insns), X86_FEATURE_CALL_DEPTH
#endif
.endm
- .macro UNTRAIN_RET_VM
- #if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) || \
- defined(CONFIG_CALL_DEPTH_TRACKING) || defined(CONFIG_CPU_SRSO)
- VALIDATE_UNRET_END
- ALTERNATIVE_3 "", \
- CALL_UNTRAIN_RET, X86_FEATURE_UNRET, \
- "call entry_ibpb", X86_FEATURE_IBPB_ON_VMEXIT, \
- __stringify(RESET_CALL_DEPTH), X86_FEATURE_CALL_DEPTH
- #endif
- .endm
+ #define UNTRAIN_RET \
+ __UNTRAIN_RET X86_FEATURE_ENTRY_IBPB, __stringify(RESET_CALL_DEPTH)
- .macro UNTRAIN_RET_FROM_CALL
- #if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) || \
- defined(CONFIG_CALL_DEPTH_TRACKING)
- VALIDATE_UNRET_END
- ALTERNATIVE_3 "", \
- CALL_UNTRAIN_RET, X86_FEATURE_UNRET, \
- "call entry_ibpb", X86_FEATURE_ENTRY_IBPB, \
- __stringify(RESET_CALL_DEPTH_FROM_CALL), X86_FEATURE_CALL_DEPTH
- #endif
- .endm
+ #define UNTRAIN_RET_VM \
+ __UNTRAIN_RET X86_FEATURE_IBPB_ON_VMEXIT, __stringify(RESET_CALL_DEPTH)
+
+ #define UNTRAIN_RET_FROM_CALL \
+ __UNTRAIN_RET X86_FEATURE_ENTRY_IBPB, __stringify(RESET_CALL_DEPTH_FROM_CALL)
.macro CALL_DEPTH_ACCOUNT
#ifdef CONFIG_CALL_DEPTH_TRACKING
ALTERNATIVE "", \
- __stringify(ASM_INCREMENT_CALL_DEPTH), X86_FEATURE_CALL_DEPTH
+ __stringify(INCREMENT_CALL_DEPTH), X86_FEATURE_CALL_DEPTH
#endif
.endm
#define ANNOTATE_RETPOLINE_SAFE \
"999:\n\t" \
".pushsection .discard.retpoline_safe\n\t" \
- ".long 999b - .\n\t" \
+ ".long 999b\n\t" \
".popsection\n\t"
typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE];
static inline void __x86_return_thunk(void) {}
#endif
+ #ifdef CONFIG_CPU_UNRET_ENTRY
extern void retbleed_return_thunk(void);
+ #else
+ static inline void retbleed_return_thunk(void) {}
+ #endif
+
+ #ifdef CONFIG_CPU_SRSO
extern void srso_return_thunk(void);
extern void srso_alias_return_thunk(void);
+ #else
+ static inline void srso_return_thunk(void) {}
+ static inline void srso_alias_return_thunk(void) {}
+ #endif
- extern void retbleed_untrain_ret(void);
- extern void srso_untrain_ret(void);
- extern void srso_alias_untrain_ret(void);
+ extern void retbleed_return_thunk(void);
+ extern void srso_return_thunk(void);
+ extern void srso_alias_return_thunk(void);
extern void entry_untrain_ret(void);
extern void entry_ibpb(void);
extern void (*x86_return_thunk)(void);
#ifdef CONFIG_CALL_DEPTH_TRACKING
- extern void __x86_return_skl(void);
-
- static inline void x86_set_skl_return_thunk(void)
- {
- x86_return_thunk = &__x86_return_skl;
- }
+ extern void call_depth_return_thunk(void);
#define CALL_DEPTH_ACCOUNT \
ALTERNATIVE("", \
DECLARE_PER_CPU(u64, __x86_stuffs_count);
DECLARE_PER_CPU(u64, __x86_ctxsw_count);
#endif
- #else
- static inline void x86_set_skl_return_thunk(void) {}
+ #else /* !CONFIG_CALL_DEPTH_TRACKING */
+ static inline void call_depth_return_thunk(void) {}
#define CALL_DEPTH_ACCOUNT ""
- #endif
+ #endif /* CONFIG_CALL_DEPTH_TRACKING */
#ifdef CONFIG_RETPOLINE
#ifdef CONFIG_X86_64
#define __percpu_seg gs
+#define __percpu_rel (%rip)
#else
#define __percpu_seg fs
+#define __percpu_rel
#endif
#ifdef __ASSEMBLY__
#ifdef CONFIG_SMP
-#define PER_CPU_VAR(var) %__percpu_seg:var
-#else /* ! SMP */
-#define PER_CPU_VAR(var) var
-#endif /* SMP */
+#define __percpu %__percpu_seg:
+#else
+#define __percpu
+#endif
+
+#define PER_CPU_VAR(var) __percpu(var)__percpu_rel
#ifdef CONFIG_X86_64_SMP
#define INIT_PER_CPU_VAR(var) init_per_cpu__##var
#else /* ...!ASSEMBLY */
- #include <linux/kernel.h>
+#include <linux/build_bug.h>
#include <linux/stringify.h>
+ #include <asm/asm.h>
#ifdef CONFIG_SMP
+
+#ifdef CONFIG_CC_HAS_NAMED_AS
+
+#ifdef __CHECKER__
+#define __seg_gs __attribute__((address_space(__seg_gs)))
+#define __seg_fs __attribute__((address_space(__seg_fs)))
+#endif
+
+#ifdef CONFIG_X86_64
+#define __percpu_seg_override __seg_gs
+#else
+#define __percpu_seg_override __seg_fs
+#endif
+
+#define __percpu_prefix ""
+
+#else /* CONFIG_CC_HAS_NAMED_AS */
+
+#define __percpu_seg_override
#define __percpu_prefix "%%"__stringify(__percpu_seg)":"
+
+#endif /* CONFIG_CC_HAS_NAMED_AS */
+
+#define __force_percpu_prefix "%%"__stringify(__percpu_seg)":"
#define __my_cpu_offset this_cpu_read(this_cpu_off)
+#ifdef CONFIG_USE_X86_SEG_SUPPORT
+/*
+ * Efficient implementation for cases in which the compiler supports
+ * named address spaces. Allows the compiler to perform additional
+ * optimizations that can save more instructions.
+ */
+#define arch_raw_cpu_ptr(ptr) \
+({ \
+ unsigned long tcp_ptr__; \
+ tcp_ptr__ = __raw_cpu_read(, this_cpu_off); \
+ \
+ tcp_ptr__ += (unsigned long)(ptr); \
+ (typeof(*(ptr)) __kernel __force *)tcp_ptr__; \
+})
+#else /* CONFIG_USE_X86_SEG_SUPPORT */
/*
* Compared to the generic __my_cpu_offset version, the following
* saves one instruction and avoids clobbering a temp register.
*/
-#define arch_raw_cpu_ptr(ptr) \
-({ \
- unsigned long tcp_ptr__; \
- asm ("add " __percpu_arg(1) ", %0" \
- : "=r" (tcp_ptr__) \
- : "m" (this_cpu_off), "0" (ptr)); \
- (typeof(*(ptr)) __kernel __force *)tcp_ptr__; \
+#define arch_raw_cpu_ptr(ptr) \
+({ \
+ unsigned long tcp_ptr__; \
+ asm ("mov " __percpu_arg(1) ", %0" \
+ : "=r" (tcp_ptr__) \
+ : "m" (__my_cpu_var(this_cpu_off))); \
+ \
+ tcp_ptr__ += (unsigned long)(ptr); \
+ (typeof(*(ptr)) __kernel __force *)tcp_ptr__; \
})
-#else
+#endif /* CONFIG_USE_X86_SEG_SUPPORT */
+
+#define PER_CPU_VAR(var) %__percpu_seg:(var)__percpu_rel
+
+#else /* CONFIG_SMP */
+#define __percpu_seg_override
#define __percpu_prefix ""
-#endif
+#define __force_percpu_prefix ""
+
+#define PER_CPU_VAR(var) (var)__percpu_rel
+#endif /* CONFIG_SMP */
+
+#define __my_cpu_type(var) typeof(var) __percpu_seg_override
+#define __my_cpu_ptr(ptr) (__my_cpu_type(*ptr) *)(uintptr_t)(ptr)
+#define __my_cpu_var(var) (*__my_cpu_ptr(&var))
#define __percpu_arg(x) __percpu_prefix "%" #x
+#define __force_percpu_arg(x) __force_percpu_prefix "%" #x
/*
* Initialized pointers to per-cpu variables needed for the boot
(void)pto_tmp__; \
} \
asm qual(__pcpu_op2_##size(op, "%[val]", __percpu_arg([var])) \
- : [var] "+m" (_var) \
+ : [var] "+m" (__my_cpu_var(_var)) \
: [val] __pcpu_reg_imm_##size(pto_val__)); \
} while (0)
#define percpu_unary_op(size, qual, op, _var) \
({ \
asm qual (__pcpu_op1_##size(op, __percpu_arg([var])) \
- : [var] "+m" (_var)); \
+ : [var] "+m" (__my_cpu_var(_var))); \
})
/*
__pcpu_type_##size pfo_val__; \
asm qual (__pcpu_op2_##size(op, __percpu_arg([var]), "%[val]") \
: [val] __pcpu_reg_##size("=", pfo_val__) \
- : [var] "m" (_var)); \
+ : [var] "m" (__my_cpu_var(_var))); \
(typeof(_var))(unsigned long) pfo_val__; \
})
#define percpu_stable_op(size, op, _var) \
({ \
__pcpu_type_##size pfo_val__; \
- asm(__pcpu_op2_##size(op, __percpu_arg(P[var]), "%[val]") \
+ asm(__pcpu_op2_##size(op, __force_percpu_arg(a[var]), "%[val]") \
: [val] __pcpu_reg_##size("=", pfo_val__) \
- : [var] "p" (&(_var))); \
+ : [var] "i" (&(_var))); \
(typeof(_var))(unsigned long) pfo_val__; \
})
asm qual (__pcpu_op2_##size("xadd", "%[tmp]", \
__percpu_arg([var])) \
: [tmp] __pcpu_reg_##size("+", paro_tmp__), \
- [var] "+m" (_var) \
+ [var] "+m" (__my_cpu_var(_var)) \
: : "memory"); \
(typeof(_var))(unsigned long) (paro_tmp__ + _val); \
})
__percpu_arg([var])) \
"\n\tjnz 1b" \
: [oval] "=&a" (pxo_old__), \
- [var] "+m" (_var) \
+ [var] "+m" (__my_cpu_var(_var)) \
: [nval] __pcpu_reg_##size(, pxo_new__) \
: "memory"); \
(typeof(_var))(unsigned long) pxo_old__; \
asm qual (__pcpu_op2_##size("cmpxchg", "%[nval]", \
__percpu_arg([var])) \
: [oval] "+a" (pco_old__), \
- [var] "+m" (_var) \
+ [var] "+m" (__my_cpu_var(_var)) \
: [nval] __pcpu_reg_##size(, pco_new__) \
: "memory"); \
(typeof(_var))(unsigned long) pco_old__; \
CC_SET(z) \
: CC_OUT(z) (success), \
[oval] "+a" (pco_old__), \
- [var] "+m" (_var) \
+ [var] "+m" (__my_cpu_var(_var)) \
: [nval] __pcpu_reg_##size(, pco_new__) \
: "memory"); \
if (unlikely(!success)) \
\
asm qual (ALTERNATIVE("call this_cpu_cmpxchg8b_emu", \
"cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \
- : [var] "+m" (_var), \
+ : [var] "+m" (__my_cpu_var(_var)), \
"+a" (old__.low), \
"+d" (old__.high) \
: "b" (new__.low), \
"cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \
CC_SET(z) \
: CC_OUT(z) (success), \
- [var] "+m" (_var), \
+ [var] "+m" (__my_cpu_var(_var)), \
"+a" (old__.low), \
"+d" (old__.high) \
: "b" (new__.low), \
\
asm qual (ALTERNATIVE("call this_cpu_cmpxchg16b_emu", \
"cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \
- : [var] "+m" (_var), \
+ : [var] "+m" (__my_cpu_var(_var)), \
"+a" (old__.low), \
"+d" (old__.high) \
: "b" (new__.low), \
"cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \
CC_SET(z) \
: CC_OUT(z) (success), \
- [var] "+m" (_var), \
+ [var] "+m" (__my_cpu_var(_var)), \
"+a" (old__.low), \
"+d" (old__.high) \
: "b" (new__.low), \
* accessed while this_cpu_read_stable() allows the value to be cached.
* this_cpu_read_stable() is more efficient and can be used if its value
* is guaranteed to be valid across cpus. The current users include
- * get_current() and get_thread_info() both of which are actually
- * per-thread variables implemented as per-cpu variables and thus
- * stable for the duration of the respective task.
+ * pcpu_hot.current_task and pcpu_hot.top_of_stack, both of which are
+ * actually per-thread variables implemented as per-CPU variables and
+ * thus stable for the duration of the respective task.
*/
#define this_cpu_read_stable_1(pcp) percpu_stable_op(1, "mov", pcp)
#define this_cpu_read_stable_2(pcp) percpu_stable_op(2, "mov", pcp)
#define this_cpu_read_stable_8(pcp) percpu_stable_op(8, "mov", pcp)
#define this_cpu_read_stable(pcp) __pcpu_size_call_return(this_cpu_read_stable_, pcp)
+#ifdef CONFIG_USE_X86_SEG_SUPPORT
+
+#define __raw_cpu_read(qual, pcp) \
+({ \
+ *(qual __my_cpu_type(pcp) *)__my_cpu_ptr(&(pcp)); \
+})
+
+#define __raw_cpu_write(qual, pcp, val) \
+do { \
+ *(qual __my_cpu_type(pcp) *)__my_cpu_ptr(&(pcp)) = (val); \
+} while (0)
+
+#define raw_cpu_read_1(pcp) __raw_cpu_read(, pcp)
+#define raw_cpu_read_2(pcp) __raw_cpu_read(, pcp)
+#define raw_cpu_read_4(pcp) __raw_cpu_read(, pcp)
+#define raw_cpu_write_1(pcp, val) __raw_cpu_write(, pcp, val)
+#define raw_cpu_write_2(pcp, val) __raw_cpu_write(, pcp, val)
+#define raw_cpu_write_4(pcp, val) __raw_cpu_write(, pcp, val)
+
+#define this_cpu_read_1(pcp) __raw_cpu_read(volatile, pcp)
+#define this_cpu_read_2(pcp) __raw_cpu_read(volatile, pcp)
+#define this_cpu_read_4(pcp) __raw_cpu_read(volatile, pcp)
+#define this_cpu_write_1(pcp, val) __raw_cpu_write(volatile, pcp, val)
+#define this_cpu_write_2(pcp, val) __raw_cpu_write(volatile, pcp, val)
+#define this_cpu_write_4(pcp, val) __raw_cpu_write(volatile, pcp, val)
+
+#ifdef CONFIG_X86_64
+#define raw_cpu_read_8(pcp) __raw_cpu_read(, pcp)
+#define raw_cpu_write_8(pcp, val) __raw_cpu_write(, pcp, val)
+
+#define this_cpu_read_8(pcp) __raw_cpu_read(volatile, pcp)
+#define this_cpu_write_8(pcp, val) __raw_cpu_write(volatile, pcp, val)
+#endif
+
+#define this_cpu_read_const(pcp) __raw_cpu_read(, pcp)
+#else /* CONFIG_USE_X86_SEG_SUPPORT */
+
#define raw_cpu_read_1(pcp) percpu_from_op(1, , "mov", pcp)
#define raw_cpu_read_2(pcp) percpu_from_op(2, , "mov", pcp)
#define raw_cpu_read_4(pcp) percpu_from_op(4, , "mov", pcp)
-
#define raw_cpu_write_1(pcp, val) percpu_to_op(1, , "mov", (pcp), val)
#define raw_cpu_write_2(pcp, val) percpu_to_op(2, , "mov", (pcp), val)
#define raw_cpu_write_4(pcp, val) percpu_to_op(4, , "mov", (pcp), val)
+
+#define this_cpu_read_1(pcp) percpu_from_op(1, volatile, "mov", pcp)
+#define this_cpu_read_2(pcp) percpu_from_op(2, volatile, "mov", pcp)
+#define this_cpu_read_4(pcp) percpu_from_op(4, volatile, "mov", pcp)
+#define this_cpu_write_1(pcp, val) percpu_to_op(1, volatile, "mov", (pcp), val)
+#define this_cpu_write_2(pcp, val) percpu_to_op(2, volatile, "mov", (pcp), val)
+#define this_cpu_write_4(pcp, val) percpu_to_op(4, volatile, "mov", (pcp), val)
+
+#ifdef CONFIG_X86_64
+#define raw_cpu_read_8(pcp) percpu_from_op(8, , "mov", pcp)
+#define raw_cpu_write_8(pcp, val) percpu_to_op(8, , "mov", (pcp), val)
+
+#define this_cpu_read_8(pcp) percpu_from_op(8, volatile, "mov", pcp)
+#define this_cpu_write_8(pcp, val) percpu_to_op(8, volatile, "mov", (pcp), val)
+#endif
+
+/*
+ * The generic per-cpu infrastrucutre is not suitable for
+ * reading const-qualified variables.
+ */
+#define this_cpu_read_const(pcp) ({ BUILD_BUG(); (typeof(pcp))0; })
+#endif /* CONFIG_USE_X86_SEG_SUPPORT */
+
#define raw_cpu_add_1(pcp, val) percpu_add_op(1, , (pcp), val)
#define raw_cpu_add_2(pcp, val) percpu_add_op(2, , (pcp), val)
#define raw_cpu_add_4(pcp, val) percpu_add_op(4, , (pcp), val)
#define raw_cpu_xchg_2(pcp, val) raw_percpu_xchg_op(pcp, val)
#define raw_cpu_xchg_4(pcp, val) raw_percpu_xchg_op(pcp, val)
-#define this_cpu_read_1(pcp) percpu_from_op(1, volatile, "mov", pcp)
-#define this_cpu_read_2(pcp) percpu_from_op(2, volatile, "mov", pcp)
-#define this_cpu_read_4(pcp) percpu_from_op(4, volatile, "mov", pcp)
-#define this_cpu_write_1(pcp, val) percpu_to_op(1, volatile, "mov", (pcp), val)
-#define this_cpu_write_2(pcp, val) percpu_to_op(2, volatile, "mov", (pcp), val)
-#define this_cpu_write_4(pcp, val) percpu_to_op(4, volatile, "mov", (pcp), val)
#define this_cpu_add_1(pcp, val) percpu_add_op(1, volatile, (pcp), val)
#define this_cpu_add_2(pcp, val) percpu_add_op(2, volatile, (pcp), val)
#define this_cpu_add_4(pcp, val) percpu_add_op(4, volatile, (pcp), val)
* 32 bit must fall back to generic operations.
*/
#ifdef CONFIG_X86_64
-#define raw_cpu_read_8(pcp) percpu_from_op(8, , "mov", pcp)
-#define raw_cpu_write_8(pcp, val) percpu_to_op(8, , "mov", (pcp), val)
#define raw_cpu_add_8(pcp, val) percpu_add_op(8, , (pcp), val)
#define raw_cpu_and_8(pcp, val) percpu_to_op(8, , "and", (pcp), val)
#define raw_cpu_or_8(pcp, val) percpu_to_op(8, , "or", (pcp), val)
#define raw_cpu_cmpxchg_8(pcp, oval, nval) percpu_cmpxchg_op(8, , pcp, oval, nval)
#define raw_cpu_try_cmpxchg_8(pcp, ovalp, nval) percpu_try_cmpxchg_op(8, , pcp, ovalp, nval)
-#define this_cpu_read_8(pcp) percpu_from_op(8, volatile, "mov", pcp)
-#define this_cpu_write_8(pcp, val) percpu_to_op(8, volatile, "mov", (pcp), val)
#define this_cpu_add_8(pcp, val) percpu_add_op(8, volatile, (pcp), val)
#define this_cpu_and_8(pcp, val) percpu_to_op(8, volatile, "and", (pcp), val)
#define this_cpu_or_8(pcp, val) percpu_to_op(8, volatile, "or", (pcp), val)
asm volatile("btl "__percpu_arg(2)",%1"
CC_SET(c)
: CC_OUT(c) (oldbit)
- : "m" (*(unsigned long __percpu *)addr), "Ir" (nr));
+ : "m" (*__my_cpu_ptr((unsigned long __percpu *)(addr))), "Ir" (nr));
return oldbit;
}
#include <asm/percpu.h>
#include <asm/current.h>
- #include <linux/thread_info.h>
#include <linux/static_call_types.h>
/* We use the MSB mostly because its available */
*/
static __always_inline bool __preempt_count_dec_and_test(void)
{
- return GEN_UNARY_RMWcc("decl", pcpu_hot.preempt_count, e,
+ return GEN_UNARY_RMWcc("decl", __my_cpu_var(pcpu_hot.preempt_count), e,
__percpu_arg([var]));
}
extern u16 __read_mostly tlb_lld_1g[NR_INFO];
/*
- * CPU type and hardware bug flags. Kept separately for each CPU.
- * Members of this structure are referenced in head_32.S, so think twice
- * before touching them. [mj]
+ * CPU type and hardware bug flags. Kept separately for each CPU.
*/
+ struct cpuinfo_topology {
+ // Real APIC ID read from the local APIC
+ u32 apicid;
+ // The initial APIC ID provided by CPUID
+ u32 initial_apicid;
+
+ // Physical package ID
+ u32 pkg_id;
+
+ // Physical die ID on AMD, Relative on Intel
+ u32 die_id;
+
+ // Compute unit ID - AMD specific
+ u32 cu_id;
+
+ // Core ID relative to the package
+ u32 core_id;
+
+ // Logical ID mappings
+ u32 logical_pkg_id;
+ u32 logical_die_id;
+
+ // Cache level topology IDs
+ u32 llc_id;
+ u32 l2c_id;
+ };
+
struct cpuinfo_x86 {
__u8 x86; /* CPU family */
__u8 x86_vendor; /* CPU vendor */
__u8 x86_phys_bits;
/* CPUID returned core id bits: */
__u8 x86_coreid_bits;
- __u8 cu_id;
/* Max extended CPUID function supported: */
__u32 extended_cpuid_level;
/* Maximum supported CPUID level, -1=no CPUID: */
};
char x86_vendor_id[16];
char x86_model_id[64];
+ struct cpuinfo_topology topo;
/* in KB - valid for CPUS which support this call: */
unsigned int x86_cache_size;
int x86_cache_alignment; /* In bytes */
u64 ppin;
/* cpuid returned max cores value: */
u16 x86_max_cores;
- u16 apicid;
- u16 initial_apicid;
u16 x86_clflush_size;
/* number of cores as seen by the OS: */
u16 booted_cores;
- /* Physical processor id: */
- u16 phys_proc_id;
- /* Logical processor id: */
- u16 logical_proc_id;
- /* Core id: */
- u16 cpu_core_id;
- u16 cpu_die_id;
- u16 logical_die_id;
/* Index into per_cpu list: */
u16 cpu_index;
/* Is SMT active on this core? */
return (unsigned long)per_cpu(fixed_percpu_data.gs_base, cpu);
}
- extern asmlinkage void ignore_sysret(void);
+ extern asmlinkage void entry_SYSCALL32_ignore(void);
/* Save actual FS/GS selectors and bases to current->thread */
void current_save_fsgs(void);
* and around vm86 mode and sp0 on x86_64 is special because of the
* entry trampoline.
*/
+ if (IS_ENABLED(CONFIG_USE_X86_SEG_SUPPORT))
+ return this_cpu_read_const(const_pcpu_hot.top_of_stack);
+
return this_cpu_read_stable(pcpu_hot.top_of_stack);
}
DECLARE_PER_CPU(u64, msr_misc_features_shadow);
- extern u16 get_llc_id(unsigned int cpu);
+ static inline u32 per_cpu_llc_id(unsigned int cpu)
+ {
+ return per_cpu(cpu_info.topo.llc_id, cpu);
+ }
+
+ static inline u32 per_cpu_l2c_id(unsigned int cpu)
+ {
+ return per_cpu(cpu_info.topo.l2c_id, cpu);
+ }
#ifdef CONFIG_CPU_SUP_AMD
extern u32 amd_get_nodes_per_socket(void);
extern u32 amd_get_highest_perf(void);
- extern bool cpu_has_ibpb_brtype_microcode(void);
extern void amd_clear_divider(void);
extern void amd_check_microcode(void);
#else
static inline u32 amd_get_nodes_per_socket(void) { return 0; }
static inline u32 amd_get_highest_perf(void) { return 0; }
- static inline bool cpu_has_ibpb_brtype_microcode(void) { return false; }
static inline void amd_clear_divider(void) { }
static inline void amd_check_microcode(void) { }
#endif
MDS_MITIGATION_VMWERV,
};
- #ifdef CONFIG_X86_SGX
- int arch_memory_failure(unsigned long pfn, int flags);
- #define arch_memory_failure arch_memory_failure
-
- bool arch_is_platform_page(u64 paddr);
- #define arch_is_platform_page arch_is_platform_page
- #endif
-
extern bool gds_ucode_mitigated(void);
+ /*
+ * Make previous memory operations globally visible before
+ * a WRMSR.
+ *
+ * MFENCE makes writes visible, but only affects load/store
+ * instructions. WRMSR is unfortunately not a load/store
+ * instruction and is unaffected by MFENCE. The LFENCE ensures
+ * that the WRMSR is not reordered.
+ *
+ * Most WRMSRs are full serializing instructions themselves and
+ * do not require this barrier. This is only required for the
+ * IA32_TSC_DEADLINE and X2APIC MSRs.
+ */
+ static inline void weak_wrmsr_fence(void)
+ {
+ alternative("mfence; lfence", "", ALT_NOT(X86_FEATURE_APIC_MSRS_FENCE));
+ }
+
#endif /* _ASM_X86_PROCESSOR_H */
#include <linux/stddef.h>
#include <asm/ptrace.h>
- struct paravirt_patch_site;
- #ifdef CONFIG_PARAVIRT
- void apply_paravirt(struct paravirt_patch_site *start,
- struct paravirt_patch_site *end);
- #else
- static inline void apply_paravirt(struct paravirt_patch_site *start,
- struct paravirt_patch_site *end)
- {}
- #define __parainstructions NULL
- #define __parainstructions_end NULL
- #endif
-
- extern void apply_relocation(u8 *buf, size_t len, u8 *dest, u8 *src, size_t src_len);
-
/*
* Currently, the max observed size in the kernel code is
* JUMP_LABEL_NOP_SIZE/RELATIVEJUMP_SIZE, which are 5.
extern void text_poke_early(void *addr, const void *opcode, size_t len);
++extern void apply_relocation(u8 *buf, size_t len, u8 *dest, u8 *src, size_t src_len);
++
/*
* Clear and restore the kernel write-protection flag on the local CPU.
* Allows the kernel to edit read-only pages.
#include <asm/fixmap.h>
#include <asm/paravirt.h>
#include <asm/asm-prototypes.h>
+ #include <asm/cfi.h>
int __read_mostly alternatives_patched;
#define DA_ENDBR 0x08
#define DA_SMP 0x10
-static unsigned int __initdata_or_module debug_alternative;
+static unsigned int debug_alternative;
static int __init debug_alt(char *str)
{
* each single-byte NOPs). If @len to fill out is > ASM_NOP_MAX, pad with INT3 and
* *jump* over instead of executing long and daft NOPs.
*/
-static void __init_or_module add_nop(u8 *instr, unsigned int len)
+static void add_nop(u8 *instr, unsigned int len)
{
u8 *target = instr + len;
extern s32 __return_sites[], __return_sites_end[];
extern s32 __cfi_sites[], __cfi_sites_end[];
extern s32 __ibt_endbr_seal[], __ibt_endbr_seal_end[];
- extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
extern s32 __smp_locks[], __smp_locks_end[];
void text_poke_early(void *addr, const void *opcode, size_t len);
* Optimize a sequence of NOPs, possibly preceded by an unconditional jump
* to the end of the NOP sequence into a single NOP.
*/
-static bool __init_or_module
+static bool
__optimize_nops(u8 *instr, size_t len, struct insn *insn, int *next, int *prev, int *target)
{
int i = *next - insn->length;
}
}
+ static void __init_or_module noinline optimize_nops_inplace(u8 *instr, size_t len)
+ {
+ unsigned long flags;
+
+ local_irq_save(flags);
+ optimize_nops(instr, len);
+ sync_core();
+ local_irq_restore(flags);
+ }
+
/*
* In this context, "source" is where the instructions are placed in the
* section .altinstr_replacement, for example during kernel build by the
return (target < src || target > src + src_len);
}
-static void __init_or_module noinline
-apply_relocation(u8 *buf, size_t len, u8 *dest, u8 *src, size_t src_len)
+void apply_relocation(u8 *buf, size_t len, u8 *dest, u8 *src, size_t src_len)
{
int prev, target = 0;
}
}
+ /* Low-level backend functions usable from alternative code replacements. */
+ DEFINE_ASM_FUNC(nop_func, "", .entry.text);
+ EXPORT_SYMBOL_GPL(nop_func);
+
+ noinstr void BUG_func(void)
+ {
+ BUG();
+ }
+ EXPORT_SYMBOL(BUG_func);
+
+ #define CALL_RIP_REL_OPCODE 0xff
+ #define CALL_RIP_REL_MODRM 0x15
+
+ /*
+ * Rewrite the "call BUG_func" replacement to point to the target of the
+ * indirect pv_ops call "call *disp(%ip)".
+ */
+ static int alt_replace_call(u8 *instr, u8 *insn_buff, struct alt_instr *a)
+ {
+ void *target, *bug = &BUG_func;
+ s32 disp;
+
+ if (a->replacementlen != 5 || insn_buff[0] != CALL_INSN_OPCODE) {
+ pr_err("ALT_FLAG_DIRECT_CALL set for a non-call replacement instruction\n");
+ BUG();
+ }
+
+ if (a->instrlen != 6 ||
+ instr[0] != CALL_RIP_REL_OPCODE ||
+ instr[1] != CALL_RIP_REL_MODRM) {
+ pr_err("ALT_FLAG_DIRECT_CALL set for unrecognized indirect call\n");
+ BUG();
+ }
+
+ /* Skip CALL_RIP_REL_OPCODE and CALL_RIP_REL_MODRM */
+ disp = *(s32 *)(instr + 2);
+ #ifdef CONFIG_X86_64
+ /* ff 15 00 00 00 00 call *0x0(%rip) */
+ /* target address is stored at "next instruction + disp". */
+ target = *(void **)(instr + a->instrlen + disp);
+ #else
+ /* ff 15 00 00 00 00 call *0x0 */
+ /* target address is stored at disp. */
+ target = *(void **)disp;
+ #endif
+ if (!target)
+ target = bug;
+
+ /* (BUG_func - .) + (target - BUG_func) := target - . */
+ *(s32 *)(insn_buff + 1) += target - bug;
+
+ if (target == &nop_func)
+ return 0;
+
+ return 5;
+ }
+
/*
* Replace instructions with better alternatives for this CPU type. This runs
* before SMP is initialized to avoid SMP problems with self modifying code.
u8 insn_buff[MAX_PATCH_LEN];
DPRINTK(ALT, "alt table %px, -> %px", start, end);
+
+ /*
+ * In the case CONFIG_X86_5LEVEL=y, KASAN_SHADOW_START is defined using
+ * cpu_feature_enabled(X86_FEATURE_LA57) and is therefore patched here.
+ * During the process, KASAN becomes confused seeing partial LA57
+ * conversion and triggers a false-positive out-of-bound report.
+ *
+ * Disable KASAN until the patching is complete.
+ */
+ kasan_disable_current();
+
/*
* The scan order should be from start to end. A later scanned
* alternative code can overwrite previously scanned alternative code.
* patch if feature is *NOT* present.
*/
if (!boot_cpu_has(a->cpuid) == !(a->flags & ALT_FLAG_NOT)) {
- optimize_nops(instr, a->instrlen);
+ optimize_nops_inplace(instr, a->instrlen);
continue;
}
- DPRINTK(ALT, "feat: %s%d*32+%d, old: (%pS (%px) len: %d), repl: (%px, len: %d)",
- (a->flags & ALT_FLAG_NOT) ? "!" : "",
+ DPRINTK(ALT, "feat: %d*32+%d, old: (%pS (%px) len: %d), repl: (%px, len: %d) flags: 0x%x",
a->cpuid >> 5,
a->cpuid & 0x1f,
instr, instr, a->instrlen,
- replacement, a->replacementlen);
+ replacement, a->replacementlen, a->flags);
memcpy(insn_buff, replacement, a->replacementlen);
insn_buff_sz = a->replacementlen;
+ if (a->flags & ALT_FLAG_DIRECT_CALL) {
+ insn_buff_sz = alt_replace_call(instr, insn_buff, a);
+ if (insn_buff_sz < 0)
+ continue;
+ }
+
for (; insn_buff_sz < a->instrlen; insn_buff_sz++)
insn_buff[insn_buff_sz] = 0x90;
text_poke_early(instr, insn_buff, insn_buff_sz);
}
+
+ kasan_enable_current();
}
static inline bool is_jcc32(struct insn *insn)
{
s32 *s;
- /*
- * Do not patch out the default return thunks if those needed are the
- * ones generated by the compiler.
- */
- if (cpu_feature_enabled(X86_FEATURE_RETHUNK) &&
- (x86_return_thunk == __x86_return_thunk))
- return;
+ if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
+ static_call_force_reinit();
for (s = start; s < end; s++) {
void *dest = NULL, *addr = (void *)s + *s;
#endif /* CONFIG_X86_KERNEL_IBT */
#ifdef CONFIG_FINEIBT
+ #define __CFI_DEFAULT CFI_DEFAULT
+ #elif defined(CONFIG_CFI_CLANG)
+ #define __CFI_DEFAULT CFI_KCFI
+ #else
+ #define __CFI_DEFAULT CFI_OFF
+ #endif
- enum cfi_mode {
- CFI_DEFAULT,
- CFI_OFF,
- CFI_KCFI,
- CFI_FINEIBT,
- };
+ enum cfi_mode cfi_mode __ro_after_init = __CFI_DEFAULT;
+
+ #ifdef CONFIG_CFI_CLANG
+ struct bpf_insn;
+
+ /* Must match bpf_func_t / DEFINE_BPF_PROG_RUN() */
+ extern unsigned int __bpf_prog_runX(const void *ctx,
+ const struct bpf_insn *insn);
+
+ /*
+ * Force a reference to the external symbol so the compiler generates
+ * __kcfi_typid.
+ */
+ __ADDRESSABLE(__bpf_prog_runX);
+
+ /* u32 __ro_after_init cfi_bpf_hash = __kcfi_typeid___bpf_prog_runX; */
+ asm (
+ " .pushsection .data..ro_after_init,\"aw\",@progbits \n"
+ " .type cfi_bpf_hash,@object \n"
+ " .globl cfi_bpf_hash \n"
+ " .p2align 2, 0x0 \n"
+ "cfi_bpf_hash: \n"
+ " .long __kcfi_typeid___bpf_prog_runX \n"
+ " .size cfi_bpf_hash, 4 \n"
+ " .popsection \n"
+ );
+
+ /* Must match bpf_callback_t */
+ extern u64 __bpf_callback_fn(u64, u64, u64, u64, u64);
+
+ __ADDRESSABLE(__bpf_callback_fn);
+
+ /* u32 __ro_after_init cfi_bpf_subprog_hash = __kcfi_typeid___bpf_callback_fn; */
+ asm (
+ " .pushsection .data..ro_after_init,\"aw\",@progbits \n"
+ " .type cfi_bpf_subprog_hash,@object \n"
+ " .globl cfi_bpf_subprog_hash \n"
+ " .p2align 2, 0x0 \n"
+ "cfi_bpf_subprog_hash: \n"
+ " .long __kcfi_typeid___bpf_callback_fn \n"
+ " .size cfi_bpf_subprog_hash, 4 \n"
+ " .popsection \n"
+ );
+
+ u32 cfi_get_func_hash(void *func)
+ {
+ u32 hash;
+
+ func -= cfi_get_offset();
+ switch (cfi_mode) {
+ case CFI_FINEIBT:
+ func += 7;
+ break;
+ case CFI_KCFI:
+ func += 1;
+ break;
+ default:
+ return 0;
+ }
+
+ if (get_kernel_nofault(hash, func))
+ return 0;
+
+ return hash;
+ }
+ #endif
+
+ #ifdef CONFIG_FINEIBT
- static enum cfi_mode cfi_mode __ro_after_init = CFI_DEFAULT;
static bool cfi_rand __ro_after_init = true;
static u32 cfi_seed __ro_after_init;
goto err;
if (cfi_rand) {
- if (builtin)
+ if (builtin) {
cfi_seed = get_random_u32();
+ cfi_bpf_hash = cfi_rehash(cfi_bpf_hash);
+ cfi_bpf_subprog_hash = cfi_rehash(cfi_bpf_subprog_hash);
+ }
ret = cfi_rand_preamble(start_cfi, end_cfi);
if (ret)
}
#endif /* CONFIG_SMP */
- #ifdef CONFIG_PARAVIRT
-
- /* Use this to add nops to a buffer, then text_poke the whole buffer. */
- static void __init_or_module add_nops(void *insns, unsigned int len)
- {
- while (len > 0) {
- unsigned int noplen = len;
- if (noplen > ASM_NOP_MAX)
- noplen = ASM_NOP_MAX;
- memcpy(insns, x86_nops[noplen], noplen);
- insns += noplen;
- len -= noplen;
- }
- }
-
- void __init_or_module apply_paravirt(struct paravirt_patch_site *start,
- struct paravirt_patch_site *end)
- {
- struct paravirt_patch_site *p;
- char insn_buff[MAX_PATCH_LEN];
-
- for (p = start; p < end; p++) {
- unsigned int used;
-
- BUG_ON(p->len > MAX_PATCH_LEN);
- /* prep the buffer with the original instructions */
- memcpy(insn_buff, p->instr, p->len);
- used = paravirt_patch(p->type, insn_buff, (unsigned long)p->instr, p->len);
-
- BUG_ON(used > p->len);
-
- /* Pad the rest with nops */
- add_nops(insn_buff + used, p->len - used);
- text_poke_early(p->instr, insn_buff, p->len);
- }
- }
- extern struct paravirt_patch_site __start_parainstructions[],
- __stop_parainstructions[];
- #endif /* CONFIG_PARAVIRT */
-
/*
* Self-test for the INT3 based CALL emulation code.
*
*/
/*
- * Paravirt patching and alternative patching can be combined to
- * replace a function call with a short direct code sequence (e.g.
- * by setting a constant return value instead of doing that in an
- * external function).
- * In order to make this work the following sequence is required:
- * 1. set (artificial) features depending on used paravirt
- * functions which can later influence alternative patching
- * 2. apply paravirt patching (generally replacing an indirect
- * function call with a direct one)
- * 3. apply alternative patching (e.g. replacing a direct function
- * call with a custom code sequence)
- * Doing paravirt patching after alternative patching would clobber
- * the optimization of the custom code with a function call again.
+ * Make sure to set (artificial) features depending on used paravirt
+ * functions which can later influence alternative patching.
*/
paravirt_set_cap();
- /*
- * First patch paravirt functions, such that we overwrite the indirect
- * call with the direct call.
- */
- apply_paravirt(__parainstructions, __parainstructions_end);
-
__apply_fineibt(__retpoline_sites, __retpoline_sites_end,
__cfi_sites, __cfi_sites_end, true);
apply_retpolines(__retpoline_sites, __retpoline_sites_end);
apply_returns(__return_sites, __return_sites_end);
- /*
- * Then patch alternatives, such that those paravirt calls that are in
- * alternatives can be overwritten by their immediate fragments.
- */
apply_alternatives(__alt_instructions, __alt_instructions_end);
/*
} else {
local_irq_save(flags);
memcpy(addr, opcode, len);
- local_irq_restore(flags);
sync_core();
+ local_irq_restore(flags);
/*
* Could also do a CLFLUSH here to speed up CPU recovery; but
* Note that the caller must ensure that if the modified code is part of a
* module, the module would not be removed during poking. This can be achieved
* by registering a module notifier, and ordering module removal and patching
- * trough a mutex.
+ * through a mutex.
*/
void *text_poke(void *addr, const void *opcode, size_t len)
{
static int __initdata_or_module debug_callthunks;
+#define MAX_PATCH_LEN (255-1)
+
#define prdbg(fmt, args...) \
do { \
if (debug_callthunks) \
extern s32 __call_sites[], __call_sites_end[];
- struct thunk_desc {
- void *template;
- unsigned int template_size;
- };
-
struct core_text {
unsigned long base;
unsigned long end;
static void *patch_dest(void *dest, bool direct)
{
unsigned int tsize = SKL_TMPL_SIZE;
+ u8 insn_buff[MAX_PATCH_LEN];
u8 *pad = dest - tsize;
+ memcpy(insn_buff, skl_call_thunk_template, tsize);
+ apply_relocation(insn_buff, tsize, pad,
+ skl_call_thunk_template, tsize);
+
/* Already patched? */
- if (!bcmp(pad, skl_call_thunk_template, tsize))
+ if (!bcmp(pad, insn_buff, tsize))
return pad;
/* Ensure there are nops */
}
if (direct)
- memcpy(pad, skl_call_thunk_template, tsize);
+ memcpy(pad, insn_buff, tsize);
else
- text_poke_copy_locked(pad, skl_call_thunk_template, tsize, true);
+ text_poke_copy_locked(pad, insn_buff, tsize, true);
return pad;
}
}
static __init_or_module void
- patch_paravirt_call_sites(struct paravirt_patch_site *start,
- struct paravirt_patch_site *end,
- const struct core_text *ct)
+ patch_alt_call_sites(struct alt_instr *start, struct alt_instr *end,
+ const struct core_text *ct)
{
- struct paravirt_patch_site *p;
+ struct alt_instr *a;
- for (p = start; p < end; p++)
- patch_call(p->instr, ct);
+ for (a = start; a < end; a++)
+ patch_call((void *)&a->instr_offset + a->instr_offset, ct);
}
static __init_or_module void
{
prdbg("Patching call sites %s\n", ct->name);
patch_call_sites(cs->call_start, cs->call_end, ct);
- patch_paravirt_call_sites(cs->pv_start, cs->pv_end, ct);
+ patch_alt_call_sites(cs->alt_start, cs->alt_end, ct);
prdbg("Patching call sites done%s\n", ct->name);
}
struct callthunk_sites cs = {
.call_start = __call_sites,
.call_end = __call_sites_end,
- .pv_start = __parainstructions,
- .pv_end = __parainstructions_end
+ .alt_start = __alt_instructions,
+ .alt_end = __alt_instructions_end
};
if (!cpu_feature_enabled(X86_FEATURE_CALL_DEPTH))
pr_info("Setting up call depth tracking\n");
mutex_lock(&text_mutex);
callthunks_setup(&cs, &builtin_coretext);
- static_call_force_reinit();
thunks_initialized = true;
mutex_unlock(&text_mutex);
}
static bool is_callthunk(void *addr)
{
unsigned int tmpl_size = SKL_TMPL_SIZE;
- void *tmpl = skl_call_thunk_template;
+ u8 insn_buff[MAX_PATCH_LEN];
unsigned long dest;
+ u8 *pad;
dest = roundup((unsigned long)addr, CONFIG_FUNCTION_ALIGNMENT);
if (!thunks_initialized || skip_addr((void *)dest))
return false;
- return !bcmp((void *)(dest - tmpl_size), tmpl, tmpl_size);
+ pad = (void *)(dest - tmpl_size);
+
+ memcpy(insn_buff, skl_call_thunk_template, tmpl_size);
+ apply_relocation(insn_buff, tmpl_size, pad,
+ skl_call_thunk_template, tmpl_size);
+
+ return !bcmp(pad, insn_buff, tmpl_size);
}
int x86_call_depth_emit_accounting(u8 **pprog, void *func)
{
unsigned int tmpl_size = SKL_TMPL_SIZE;
- void *tmpl = skl_call_thunk_template;
+ u8 insn_buff[MAX_PATCH_LEN];
if (!thunks_initialized)
return 0;
if (func && is_callthunk(func))
return 0;
- memcpy(*pprog, tmpl, tmpl_size);
+ memcpy(insn_buff, skl_call_thunk_template, tmpl_size);
+ apply_relocation(insn_buff, tmpl_size, *pprog,
+ skl_call_thunk_template, tmpl_size);
+
+ memcpy(*pprog, insn_buff, tmpl_size);
*pprog += tmpl_size;
return tmpl_size;
}
#include <asm/intel-family.h>
#include <asm/cpu_device_id.h>
#include <asm/uv/uv.h>
+ #include <asm/ia32.h>
#include <asm/set_memory.h>
#include <asm/traps.h>
#include <asm/sev.h>
+ #include <asm/tdx.h>
#include "cpu.h"
int smp_num_siblings = 1;
EXPORT_SYMBOL(smp_num_siblings);
- /* Last level cache ID of each logical CPU */
- DEFINE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id) = BAD_APICID;
-
- u16 get_llc_id(unsigned int cpu)
- {
- return per_cpu(cpu_llc_id, cpu);
- }
- EXPORT_SYMBOL_GPL(get_llc_id);
-
- /* L2 cache ID of each logical CPU */
- DEFINE_PER_CPU_READ_MOSTLY(u16, cpu_l2c_id) = BAD_APICID;
-
static struct ppin_info {
int feature;
int msr_ppin_ctl;
* TLS descriptors are currently at a different place compared to i386.
* Hopefully nobody expects them at a fixed place (Wine?)
*/
- [GDT_ENTRY_KERNEL32_CS] = GDT_ENTRY_INIT(0xc09b, 0, 0xfffff),
- [GDT_ENTRY_KERNEL_CS] = GDT_ENTRY_INIT(0xa09b, 0, 0xfffff),
- [GDT_ENTRY_KERNEL_DS] = GDT_ENTRY_INIT(0xc093, 0, 0xfffff),
- [GDT_ENTRY_DEFAULT_USER32_CS] = GDT_ENTRY_INIT(0xc0fb, 0, 0xfffff),
- [GDT_ENTRY_DEFAULT_USER_DS] = GDT_ENTRY_INIT(0xc0f3, 0, 0xfffff),
- [GDT_ENTRY_DEFAULT_USER_CS] = GDT_ENTRY_INIT(0xa0fb, 0, 0xfffff),
+ [GDT_ENTRY_KERNEL32_CS] = GDT_ENTRY_INIT(DESC_CODE32, 0, 0xfffff),
+ [GDT_ENTRY_KERNEL_CS] = GDT_ENTRY_INIT(DESC_CODE64, 0, 0xfffff),
+ [GDT_ENTRY_KERNEL_DS] = GDT_ENTRY_INIT(DESC_DATA64, 0, 0xfffff),
+ [GDT_ENTRY_DEFAULT_USER32_CS] = GDT_ENTRY_INIT(DESC_CODE32 | DESC_USER, 0, 0xfffff),
+ [GDT_ENTRY_DEFAULT_USER_DS] = GDT_ENTRY_INIT(DESC_DATA64 | DESC_USER, 0, 0xfffff),
+ [GDT_ENTRY_DEFAULT_USER_CS] = GDT_ENTRY_INIT(DESC_CODE64 | DESC_USER, 0, 0xfffff),
#else
- [GDT_ENTRY_KERNEL_CS] = GDT_ENTRY_INIT(0xc09a, 0, 0xfffff),
- [GDT_ENTRY_KERNEL_DS] = GDT_ENTRY_INIT(0xc092, 0, 0xfffff),
- [GDT_ENTRY_DEFAULT_USER_CS] = GDT_ENTRY_INIT(0xc0fa, 0, 0xfffff),
- [GDT_ENTRY_DEFAULT_USER_DS] = GDT_ENTRY_INIT(0xc0f2, 0, 0xfffff),
+ [GDT_ENTRY_KERNEL_CS] = GDT_ENTRY_INIT(DESC_CODE32, 0, 0xfffff),
+ [GDT_ENTRY_KERNEL_DS] = GDT_ENTRY_INIT(DESC_DATA32, 0, 0xfffff),
+ [GDT_ENTRY_DEFAULT_USER_CS] = GDT_ENTRY_INIT(DESC_CODE32 | DESC_USER, 0, 0xfffff),
+ [GDT_ENTRY_DEFAULT_USER_DS] = GDT_ENTRY_INIT(DESC_DATA32 | DESC_USER, 0, 0xfffff),
/*
* Segments used for calling PnP BIOS have byte granularity.
* They code segments and data segments have fixed 64k limits,
* the transfer segment sizes are set at run time.
*/
- /* 32-bit code */
- [GDT_ENTRY_PNPBIOS_CS32] = GDT_ENTRY_INIT(0x409a, 0, 0xffff),
- /* 16-bit code */
- [GDT_ENTRY_PNPBIOS_CS16] = GDT_ENTRY_INIT(0x009a, 0, 0xffff),
- /* 16-bit data */
- [GDT_ENTRY_PNPBIOS_DS] = GDT_ENTRY_INIT(0x0092, 0, 0xffff),
- /* 16-bit data */
- [GDT_ENTRY_PNPBIOS_TS1] = GDT_ENTRY_INIT(0x0092, 0, 0),
- /* 16-bit data */
- [GDT_ENTRY_PNPBIOS_TS2] = GDT_ENTRY_INIT(0x0092, 0, 0),
+ [GDT_ENTRY_PNPBIOS_CS32] = GDT_ENTRY_INIT(DESC_CODE32_BIOS, 0, 0xffff),
+ [GDT_ENTRY_PNPBIOS_CS16] = GDT_ENTRY_INIT(DESC_CODE16, 0, 0xffff),
+ [GDT_ENTRY_PNPBIOS_DS] = GDT_ENTRY_INIT(DESC_DATA16, 0, 0xffff),
+ [GDT_ENTRY_PNPBIOS_TS1] = GDT_ENTRY_INIT(DESC_DATA16, 0, 0),
+ [GDT_ENTRY_PNPBIOS_TS2] = GDT_ENTRY_INIT(DESC_DATA16, 0, 0),
/*
* The APM segments have byte granularity and their bases
* are set at run time. All have 64k limits.
*/
- /* 32-bit code */
- [GDT_ENTRY_APMBIOS_BASE] = GDT_ENTRY_INIT(0x409a, 0, 0xffff),
- /* 16-bit code */
- [GDT_ENTRY_APMBIOS_BASE+1] = GDT_ENTRY_INIT(0x009a, 0, 0xffff),
- /* data */
- [GDT_ENTRY_APMBIOS_BASE+2] = GDT_ENTRY_INIT(0x4092, 0, 0xffff),
-
- [GDT_ENTRY_ESPFIX_SS] = GDT_ENTRY_INIT(0xc092, 0, 0xfffff),
- [GDT_ENTRY_PERCPU] = GDT_ENTRY_INIT(0xc092, 0, 0xfffff),
+ [GDT_ENTRY_APMBIOS_BASE] = GDT_ENTRY_INIT(DESC_CODE32_BIOS, 0, 0xffff),
+ [GDT_ENTRY_APMBIOS_BASE+1] = GDT_ENTRY_INIT(DESC_CODE16, 0, 0xffff),
+ [GDT_ENTRY_APMBIOS_BASE+2] = GDT_ENTRY_INIT(DESC_DATA32_BIOS, 0, 0xffff),
+
+ [GDT_ENTRY_ESPFIX_SS] = GDT_ENTRY_INIT(DESC_DATA32, 0, 0xfffff),
+ [GDT_ENTRY_PERCPU] = GDT_ENTRY_INIT(DESC_DATA32, 0, 0xfffff),
#endif
} };
EXPORT_PER_CPU_SYMBOL_GPL(gdt_page);
return;
index_msb = get_count_order(smp_num_siblings);
- c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid, index_msb);
+ c->topo.pkg_id = apic->phys_pkg_id(c->topo.initial_apicid, index_msb);
smp_num_siblings = smp_num_siblings / c->x86_max_cores;
core_bits = get_count_order(c->x86_max_cores);
- c->cpu_core_id = apic->phys_pkg_id(c->initial_apicid, index_msb) &
- ((1 << core_bits) - 1);
+ c->topo.core_id = apic->phys_pkg_id(c->topo.initial_apicid, index_msb) &
+ ((1 << core_bits) - 1);
#endif
}
void get_cpu_address_sizes(struct cpuinfo_x86 *c)
{
u32 eax, ebx, ecx, edx;
+ bool vp_bits_from_cpuid = true;
- if (c->extended_cpuid_level >= 0x80000008) {
+ if (!cpu_has(c, X86_FEATURE_CPUID) ||
+ (c->extended_cpuid_level < 0x80000008))
+ vp_bits_from_cpuid = false;
+
+ if (vp_bits_from_cpuid) {
cpuid(0x80000008, &eax, &ebx, &ecx, &edx);
c->x86_virt_bits = (eax >> 8) & 0xff;
c->x86_phys_bits = eax & 0xff;
+ } else {
+ if (IS_ENABLED(CONFIG_X86_64)) {
+ c->x86_clflush_size = 64;
+ c->x86_phys_bits = 36;
+ c->x86_virt_bits = 48;
+ } else {
+ c->x86_clflush_size = 32;
+ c->x86_virt_bits = 32;
+ c->x86_phys_bits = 32;
+
+ if (cpu_has(c, X86_FEATURE_PAE) ||
+ cpu_has(c, X86_FEATURE_PSE36))
+ c->x86_phys_bits = 36;
+ }
}
- #ifdef CONFIG_X86_32
- else if (cpu_has(c, X86_FEATURE_PAE) || cpu_has(c, X86_FEATURE_PSE36))
- c->x86_phys_bits = 36;
- #endif
c->x86_cache_bits = c->x86_phys_bits;
+ c->x86_cache_alignment = c->x86_clflush_size;
}
static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
VULNBL_AMD(0x15, RETBLEED),
VULNBL_AMD(0x16, RETBLEED),
VULNBL_AMD(0x17, RETBLEED | SMT_RSB | SRSO),
- VULNBL_HYGON(0x18, RETBLEED | SMT_RSB),
+ VULNBL_HYGON(0x18, RETBLEED | SMT_RSB | SRSO),
VULNBL_AMD(0x19, SRSO),
{}
};
*/
static void __init early_identify_cpu(struct cpuinfo_x86 *c)
{
- #ifdef CONFIG_X86_64
- c->x86_clflush_size = 64;
- c->x86_phys_bits = 36;
- c->x86_virt_bits = 48;
- #else
- c->x86_clflush_size = 32;
- c->x86_phys_bits = 32;
- c->x86_virt_bits = 32;
- #endif
- c->x86_cache_alignment = c->x86_clflush_size;
-
memset(&c->x86_capability, 0, sizeof(c->x86_capability));
c->extended_cpuid_level = 0;
cpu_detect(c);
get_cpu_vendor(c);
get_cpu_cap(c);
- get_cpu_address_sizes(c);
setup_force_cpu_cap(X86_FEATURE_CPUID);
cpu_parse_early_param();
setup_clear_cpu_cap(X86_FEATURE_CPUID);
}
+ get_cpu_address_sizes(c);
+
setup_force_cpu_cap(X86_FEATURE_ALWAYS);
cpu_set_bug_bits(c);
get_cpu_address_sizes(c);
if (c->cpuid_level >= 0x00000001) {
- c->initial_apicid = (cpuid_ebx(1) >> 24) & 0xFF;
+ c->topo.initial_apicid = (cpuid_ebx(1) >> 24) & 0xFF;
#ifdef CONFIG_X86_32
# ifdef CONFIG_SMP
- c->apicid = apic->phys_pkg_id(c->initial_apicid, 0);
+ c->topo.apicid = apic->phys_pkg_id(c->topo.initial_apicid, 0);
# else
- c->apicid = c->initial_apicid;
+ c->topo.apicid = c->topo.initial_apicid;
# endif
#endif
- c->phys_proc_id = c->initial_apicid;
+ c->topo.pkg_id = c->topo.initial_apicid;
}
get_model_name(c); /* Default name */
static void validate_apic_and_package_id(struct cpuinfo_x86 *c)
{
#ifdef CONFIG_SMP
- unsigned int apicid, cpu = smp_processor_id();
+ unsigned int cpu = smp_processor_id();
+ u32 apicid;
apicid = apic->cpu_present_to_apicid(cpu);
- if (apicid != c->apicid) {
+ if (apicid != c->topo.apicid) {
pr_err(FW_BUG "CPU%u: APIC id mismatch. Firmware: %x APIC: %x\n",
- cpu, apicid, c->initial_apicid);
+ cpu, apicid, c->topo.initial_apicid);
}
- BUG_ON(topology_update_package_map(c->phys_proc_id, cpu));
- BUG_ON(topology_update_die_map(c->cpu_die_id, cpu));
+ BUG_ON(topology_update_package_map(c->topo.pkg_id, cpu));
+ BUG_ON(topology_update_die_map(c->topo.die_id, cpu));
#else
- c->logical_proc_id = 0;
+ c->topo.logical_pkg_id = 0;
#endif
}
c->x86_model_id[0] = '\0'; /* Unset */
c->x86_max_cores = 1;
c->x86_coreid_bits = 0;
- c->cu_id = 0xff;
+ c->topo.cu_id = 0xff;
+ c->topo.llc_id = BAD_APICID;
+ c->topo.l2c_id = BAD_APICID;
#ifdef CONFIG_X86_64
c->x86_clflush_size = 64;
c->x86_phys_bits = 36;
apply_forced_caps(c);
#ifdef CONFIG_X86_64
- c->apicid = apic->phys_pkg_id(c->initial_apicid, 0);
+ c->topo.apicid = apic->phys_pkg_id(c->topo.initial_apicid, 0);
#endif
+
+ /*
+ * Set default APIC and TSC_DEADLINE MSR fencing flag. AMD and
+ * Hygon will clear it in ->c_init() below.
+ */
+ set_cpu_cap(c, X86_FEATURE_APIC_MSRS_FENCE);
+
/*
* Vendor-specific initialization. In this section we
* canonicalize the feature flags, meaning if there are
setup_cr_pinning();
tsx_init();
+ tdx_init();
lkgs_init();
}
.top_of_stack = TOP_OF_INIT_STACK,
};
EXPORT_PER_CPU_SYMBOL(pcpu_hot);
+EXPORT_PER_CPU_SYMBOL(const_pcpu_hot);
#ifdef CONFIG_X86_64
DEFINE_PER_CPU_FIRST(struct fixed_percpu_data,
wrmsr(MSR_STAR, 0, (__USER32_CS << 16) | __KERNEL_CS);
wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64);
- #ifdef CONFIG_IA32_EMULATION
- wrmsrl_cstar((unsigned long)entry_SYSCALL_compat);
- /*
- * This only works on Intel CPUs.
- * On AMD CPUs these MSRs are 32-bit, CPU truncates MSR_IA32_SYSENTER_EIP.
- * This does not cause SYSENTER to jump to the wrong location, because
- * AMD doesn't allow SYSENTER in long mode (either 32- or 64-bit).
- */
- wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS);
- wrmsrl_safe(MSR_IA32_SYSENTER_ESP,
- (unsigned long)(cpu_entry_stack(smp_processor_id()) + 1));
- wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat);
- #else
- wrmsrl_cstar((unsigned long)ignore_sysret);
- wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)GDT_ENTRY_INVALID_SEG);
- wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL);
- wrmsrl_safe(MSR_IA32_SYSENTER_EIP, 0ULL);
- #endif
+ if (ia32_enabled()) {
+ wrmsrl_cstar((unsigned long)entry_SYSCALL_compat);
+ /*
+ * This only works on Intel CPUs.
+ * On AMD CPUs these MSRs are 32-bit, CPU truncates MSR_IA32_SYSENTER_EIP.
+ * This does not cause SYSENTER to jump to the wrong location, because
+ * AMD doesn't allow SYSENTER in long mode (either 32- or 64-bit).
+ */
+ wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS);
+ wrmsrl_safe(MSR_IA32_SYSENTER_ESP,
+ (unsigned long)(cpu_entry_stack(smp_processor_id()) + 1));
+ wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat);
+ } else {
+ wrmsrl_cstar((unsigned long)entry_SYSCALL32_ignore);
+ wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)GDT_ENTRY_INVALID_SEG);
+ wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL);
+ wrmsrl_safe(MSR_IA32_SYSENTER_EIP, 0ULL);
+ }
/*
* Flags to clear on syscall; clear as much as possible
}
#ifdef CONFIG_X86_64
- static inline void ucode_cpu_init(int cpu) { }
-
static inline void tss_setup_ist(struct tss_struct *tss)
{
/* Set up the per-CPU TSS IST stacks */
/* Only mapped when SEV-ES is active */
tss->x86_tss.ist[IST_INDEX_VC] = __this_cpu_ist_top_va(VC);
}
-
#else /* CONFIG_X86_64 */
-
- static inline void ucode_cpu_init(int cpu)
- {
- show_ucode_info_early();
- }
-
static inline void tss_setup_ist(struct tss_struct *tss) { }
-
#endif /* !CONFIG_X86_64 */
static inline void tss_setup_io_bitmap(struct tss_struct *tss)
struct task_struct *cur = current;
int cpu = raw_smp_processor_id();
- ucode_cpu_init(cpu);
-
#ifdef CONFIG_NUMA
if (this_cpu_read(numa_node) == 0 &&
early_cpu_to_node(cpu) != NUMA_NO_NODE)
* Copyright (C) 2005 Eric Biederman <ebiederm@xmission.com>
*/
-
+ #include <linux/export.h>
#include <linux/linkage.h>
#include <linux/threads.h>
#include <linux/init.h>
#include <asm/percpu.h>
#include <asm/nops.h>
#include "../entry/calling.h"
- #include <asm/export.h>
#include <asm/nospec-branch.h>
#include <asm/apicdef.h>
#include <asm/fixmap.h>
/* Form the CR3 value being sure to include the CR3 modifier */
addq $(early_top_pgt - __START_KERNEL_map), %rax
+
+ #ifdef CONFIG_AMD_MEM_ENCRYPT
+ mov %rax, %rdi
+ mov %rax, %r14
+
+ addq phys_base(%rip), %rdi
+
+ /*
+ * For SEV guests: Verify that the C-bit is correct. A malicious
+ * hypervisor could lie about the C-bit position to perform a ROP
+ * attack on the guest by writing to the unencrypted stack and wait for
+ * the next RET instruction.
+ */
+ call sev_verify_cbit
+
+ /*
+ * Restore CR3 value without the phys_base which will be added
+ * below, before writing %cr3.
+ */
+ mov %r14, %rax
+ #endif
+
jmp 1f
SYM_CODE_END(startup_64)
movl $0, %ecx
#endif
- /* Enable PAE mode, PGE and LA57 */
- orl $(X86_CR4_PAE | X86_CR4_PGE), %ecx
+ /* Enable PAE mode, PSE, PGE and LA57 */
+ orl $(X86_CR4_PAE | X86_CR4_PSE | X86_CR4_PGE), %ecx
#ifdef CONFIG_X86_5LEVEL
- testl $1, __pgtable_l5_enabled(%rip)
+ testb $1, __pgtable_l5_enabled(%rip)
jz 1f
orl $X86_CR4_LA57, %ecx
1:
/* Setup early boot stage 4-/5-level pagetables. */
addq phys_base(%rip), %rax
- /*
- * For SEV guests: Verify that the C-bit is correct. A malicious
- * hypervisor could lie about the C-bit position to perform a ROP
- * attack on the guest by writing to the unencrypted stack and wait for
- * the next RET instruction.
- */
- movq %rax, %rdi
- call sev_verify_cbit
-
/*
* Switch to new page-table
*
* For the boot CPU this switches to early_top_pgt which still has the
- * indentity mappings present. The secondary CPUs will switch to the
+ * identity mappings present. The secondary CPUs will switch to the
* init_top_pgt here, away from the trampoline_pgd and unmap the
- * indentity mapped ranges.
+ * identity mapped ranges.
*/
movq %rax, %cr3
testl $X2APIC_ENABLE, %eax
jnz .Lread_apicid_msr
+ #ifdef CONFIG_X86_X2APIC
+ /*
+ * If system is in X2APIC mode then MMIO base might not be
+ * mapped causing the MMIO read below to fault. Faults can't
+ * be handled at that point.
+ */
+ cmpl $0, x2apic_mode(%rip)
+ jz .Lread_apicid_mmio
+
+ /* Force the AP into X2APIC mode. */
+ orl $X2APIC_ENABLE, %eax
+ wrmsr
+ jmp .Lread_apicid_msr
+ #endif
+
+ .Lread_apicid_mmio:
/* Read the APIC ID from the fix-mapped MMIO space. */
movq apic_mmio_base(%rip), %rcx
addq $APIC_ID, %rcx
UNWIND_HINT_END_OF_STACK
/* Find the idle task stack */
- movq PER_CPU_VAR(pcpu_hot) + X86_current_task, %rcx
+ movq PER_CPU_VAR(pcpu_hot + X86_current_task), %rcx
movq TASK_threadsp(%rcx), %rsp
jmp .Ljump_to_C_code
}
/*
- * Disable virtualization, APIC etc. and park the CPU in a HLT loop
+ * this function calls the 'stop' function on all other CPUs in the system.
*/
DEFINE_IDTENTRY_SYSVEC(sysvec_reboot)
{
static void native_stop_other_cpus(int wait)
{
- unsigned int cpu = smp_processor_id();
+ unsigned int old_cpu, this_cpu;
unsigned long flags, timeout;
if (reboot_force)
return;
/* Only proceed if this is the first CPU to reach this code */
- if (atomic_cmpxchg(&stopping_cpu, -1, cpu) != -1)
+ old_cpu = -1;
+ this_cpu = smp_processor_id();
+ if (!atomic_try_cmpxchg(&stopping_cpu, &old_cpu, this_cpu))
return;
/* For kexec, ensure that offline CPUs are out of MWAIT and in HLT */
* 2) Wait for all other CPUs to report that they reached the
* HLT loop in stop_this_cpu()
*
- * 3) If the system uses INIT/STARTUP for CPU bringup, then
- * send all present CPUs an INIT vector, which brings them
- * completely out of the way.
+ * 3) If #2 timed out send an NMI to the CPUs which did not
+ * yet report
*
- * 4) If #3 is not possible and #2 timed out send an NMI to the
- * CPUs which did not yet report
- *
- * 5) Wait for all other CPUs to report that they reached the
+ * 4) Wait for all other CPUs to report that they reached the
* HLT loop in stop_this_cpu()
*
- * #4 can obviously race against a CPU reaching the HLT loop late.
+ * #3 can obviously race against a CPU reaching the HLT loop late.
* That CPU will have reported already and the "have all CPUs
* reached HLT" condition will be true despite the fact that the
* other CPU is still handling the NMI. Again, there is no
* NMIs.
*/
cpumask_copy(&cpus_stop_mask, cpu_online_mask);
- cpumask_clear_cpu(cpu, &cpus_stop_mask);
+ cpumask_clear_cpu(this_cpu, &cpus_stop_mask);
if (!cpumask_empty(&cpus_stop_mask)) {
apic_send_IPI_allbutself(REBOOT_VECTOR);
/*
* Don't wait longer than a second for IPI completion. The
* wait request is not checked here because that would
- * prevent an NMI/INIT shutdown in case that not all
+ * prevent an NMI shutdown attempt in case that not all
* CPUs reach shutdown state.
*/
timeout = USEC_PER_SEC;
udelay(1);
}
- /*
- * Park all other CPUs in INIT including "offline" CPUs, if
- * possible. That's a safe place where they can't resume execution
- * of HLT and then execute the HLT loop from overwritten text or
- * page tables.
- *
- * The only downside is a broadcast MCE, but up to the point where
- * the kexec() kernel brought all APs online again an MCE will just
- * make HLT resume and handle the MCE. The machine crashes and burns
- * due to overwritten text, page tables and data. So there is a
- * choice between fire and frying pan. The result is pretty much
- * the same. Chose frying pan until x86 provides a sane mechanism
- * to park a CPU.
- */
- if (smp_park_other_cpus_in_init())
- goto done;
-
- /*
- * If park with INIT was not possible and the REBOOT_VECTOR didn't
- * take all secondary CPUs offline, try with the NMI.
- */
+ /* if the REBOOT_VECTOR didn't work, try with the NMI */
if (!cpumask_empty(&cpus_stop_mask)) {
/*
* If NMI IPI is enabled, try to register the stop handler
* CPUs to stop.
*/
if (!smp_no_nmi_ipi && !register_stop_handler()) {
+ unsigned int cpu;
+
pr_emerg("Shutting down cpus with NMI\n");
for_each_cpu(cpu, &cpus_stop_mask)
udelay(1);
}
- done:
local_irq_save(flags);
disable_local_APIC();
mcheck_cpu_clear(this_cpu_ptr(&cpu_info));
#include <linux/nmi.h>
#include <linux/mm.h>
#include <linux/smp.h>
+ #include <linux/cpu.h>
#include <linux/io.h>
#include <linux/hardirq.h>
#include <linux/atomic.h>
*/
static bool try_fixup_enqcmd_gp(void)
{
- #ifdef CONFIG_IOMMU_SVA
+ #ifdef CONFIG_ARCH_HAS_CPU_PASID
u32 pasid;
/*
if (!mm_valid_pasid(current->mm))
return false;
- pasid = current->mm->pasid;
+ pasid = mm_get_enqcmd_pasid(current->mm);
/*
* Did this thread already have its PASID activated?
*/
asmlinkage __visible noinstr struct pt_regs *sync_regs(struct pt_regs *eregs)
{
- struct pt_regs *regs = (struct pt_regs *)this_cpu_read(pcpu_hot.top_of_stack) - 1;
+ struct pt_regs *regs = (struct pt_regs *)current_top_of_stack() - 1;
if (regs != eregs)
*regs = *eregs;
return regs;
* trust it and switch to the current kernel stack
*/
if (ip_within_syscall_gap(regs)) {
- sp = this_cpu_read(pcpu_hot.top_of_stack);
+ sp = current_top_of_stack();
goto sync;
}
#endif
jiffies = jiffies_64;
+const_pcpu_hot = pcpu_hot;
#if defined(CONFIG_X86_64)
/*
STATIC_CALL_TEXT
ALIGN_ENTRY_TEXT_BEGIN
- #ifdef CONFIG_CPU_SRSO
*(.text..__x86.rethunk_untrain)
- #endif
-
ENTRY_TEXT
#ifdef CONFIG_CPU_SRSO
ALIGN_ENTRY_TEXT_END
*(.gnu.warning)
- } :text =0xcccc
+ } :text = 0xcccccccc
/* End of text section, which should occupy whole number of pages */
_etext = .;
}
#endif
- /*
- * start address and size of operations which during runtime
- * can be patched with virtualization friendly instructions or
- * baremetal native ones. Think page table operations.
- * Details in paravirt_types.h
- */
- . = ALIGN(8);
- .parainstructions : AT(ADDR(.parainstructions) - LOAD_OFFSET) {
- __parainstructions = .;
- *(.parainstructions)
- __parainstructions_end = .;
- }
-
#ifdef CONFIG_RETPOLINE
/*
* List of instructions that call/jmp/jcc to retpoline thunks
"fixed_percpu_data is not at start of per-cpu area");
#endif
- #ifdef CONFIG_RETHUNK
+ #ifdef CONFIG_CPU_UNRET_ENTRY
. = ASSERT((retbleed_return_thunk & 0x3f) == 0, "retbleed_return_thunk not cacheline-aligned");
- . = ASSERT((srso_safe_ret & 0x3f) == 0, "srso_safe_ret not cacheline-aligned");
#endif
#ifdef CONFIG_CPU_SRSO
+ . = ASSERT((srso_safe_ret & 0x3f) == 0, "srso_safe_ret not cacheline-aligned");
/*
* GNU ld cannot do XOR until 2.41.
* https://sourceware.org/git/?p=binutils-gdb.git;a=commit;h=f6f78318fca803c4907fb8d7f6ded8295f1947b1
/* SPDX-License-Identifier: GPL-2.0-only */
+ #include <linux/export.h>
#include <linux/linkage.h>
- #include <asm/export.h>
#include <asm/percpu.h>
#include <asm/processor-flags.h>
pushfl
cli
- cmpl 0(%esi), %eax
+ cmpl (%esi), %eax
jne .Lnot_same
cmpl 4(%esi), %edx
jne .Lnot_same
- movl %ebx, 0(%esi)
+ movl %ebx, (%esi)
movl %ecx, 4(%esi)
orl $X86_EFLAGS_ZF, (%esp)
RET
.Lnot_same:
- movl 0(%esi), %eax
+ movl (%esi), %eax
movl 4(%esi), %edx
andl $(~X86_EFLAGS_ZF), (%esp)
#ifndef CONFIG_UML
+/*
+ * Emulate 'cmpxchg8b %fs:(%rsi)'
+ *
+ * Inputs:
+ * %esi : memory location to compare
+ * %eax : low 32 bits of old value
+ * %edx : high 32 bits of old value
+ * %ebx : low 32 bits of new value
+ * %ecx : high 32 bits of new value
+ *
+ * Notably this is not LOCK prefixed and is not safe against NMIs
+ */
SYM_FUNC_START(this_cpu_cmpxchg8b_emu)
pushfl
cli
- cmpl PER_CPU_VAR(0(%esi)), %eax
+ cmpl __percpu (%esi), %eax
jne .Lnot_same2
- cmpl PER_CPU_VAR(4(%esi)), %edx
+ cmpl __percpu 4(%esi), %edx
jne .Lnot_same2
- movl %ebx, PER_CPU_VAR(0(%esi))
- movl %ecx, PER_CPU_VAR(4(%esi))
+ movl %ebx, __percpu (%esi)
+ movl %ecx, __percpu 4(%esi)
orl $X86_EFLAGS_ZF, (%esp)
RET
.Lnot_same2:
- movl PER_CPU_VAR(0(%esi)), %eax
- movl PER_CPU_VAR(4(%esi)), %edx
+ movl __percpu (%esi), %eax
+ movl __percpu 4(%esi), %edx
andl $(~X86_EFLAGS_ZF), (%esp)
* non-zero.
*/
SYM_FUNC_START(xen_irq_disable_direct)
- movb $1, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
+ movb $1, PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_mask)
RET
SYM_FUNC_END(xen_irq_disable_direct)
SYM_FUNC_START(xen_irq_enable_direct)
FRAME_BEGIN
/* Unmask events */
- movb $0, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
+ movb $0, PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_mask)
/*
* Preempt here doesn't matter because that will deal with any
*/
/* Test for pending */
- testb $0xff, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_pending
+ testb $0xff, PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_pending)
jz 1f
call check_events
* x86 use opposite senses (mask vs enable).
*/
SYM_FUNC_START(xen_save_fl_direct)
- testb $0xff, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
+ testb $0xff, PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_mask)
setz %ah
addb %ah, %ah
RET
SYM_FUNC_START(xen_read_cr2_direct)
FRAME_BEGIN
- _ASM_MOV PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_arch_cr2, %_ASM_AX
+ _ASM_MOV PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_arch_cr2), %_ASM_AX
FRAME_END
RET
SYM_FUNC_END(xen_read_cr2_direct);
#endif /* CONFIG_X86_MCE */
xen_pv_trap asm_exc_simd_coprocessor_error
#ifdef CONFIG_IA32_EMULATION
- xen_pv_trap entry_INT80_compat
+ xen_pv_trap asm_int80_emulation
#endif
xen_pv_trap asm_exc_xen_unknown_trap
xen_pv_trap asm_exc_xen_hypervisor_callback
__asm__ ("" : "=r" (var) : "0" (var))
#endif
- /* Not-quite-unique ID. */
- #ifndef __UNIQUE_ID
- # define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __LINE__)
- #endif
+ #define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__)
/**
* data_race - mark an expression as containing intentional data races
*/
#define ___ADDRESSABLE(sym, __attrs) \
static void * __used __attrs \
- __UNIQUE_ID(__PASTE(__addressable_,sym)) = (void *)&sym;
+ __UNIQUE_ID(__PASTE(__addressable_,sym)) = (void *)(uintptr_t)&sym;
#define __ADDRESSABLE(sym) \
___ADDRESSABLE(sym, __section(".discard.addressable"))
/* &a[0] degrades to a pointer: a different type from an array */
#define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0]))
+ /*
+ * This returns a constant expression while determining if an argument is
+ * a constant expression, most importantly without evaluating the argument.
+ * Glory to Martin Uecker <Martin.Uecker@med.uni-goettingen.de>
+ */
+ #define __is_constexpr(x) \
+ (sizeof(int) == sizeof(*(8 ? ((void *)((long)(x) * 0l)) : (int *)8)))
+
/*
* Whether 'type' is a signed type or an unsigned type. Supports scalar types,
* bool and also pointer types.