diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2018-12-21 09:22:24 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2018-12-21 09:22:24 -0800 |
commit | 70ad6368e878857db315788dab36817aa992c86a (patch) | |
tree | 9de519c81dc24a2d416403ec38b944fbd6047163 /arch/x86 | |
parent | 96d6ee7d2f8110f6f3460eab5d3826a6f1ca058d (diff) | |
parent | 6ac389346e6964e1f6a1c675cebf8bd0912526a5 (diff) | |
download | linux-70ad6368e878857db315788dab36817aa992c86a.tar.gz linux-70ad6368e878857db315788dab36817aa992c86a.tar.bz2 linux-70ad6368e878857db315788dab36817aa992c86a.zip |
Merge branch 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 fixes from Ingo Molnar:
"The biggest part is a series of reverts for the macro based GCC
inlining workarounds. It caused regressions in distro build and other
kernel tooling environments, and the GCC project was very receptive to
fixing the underlying inliner weaknesses - so as time ran out we
decided to do a reasonably straightforward revert of the patches. The
plan is to rely on the 'asm inline' GCC 9 feature, which might be
backported to GCC 8 and could thus become reasonably widely available
on modern distros.
Other than those reverts, there's misc fixes from all around the
place.
I wish our final x86 pull request for v4.20 was smaller..."
* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
Revert "kbuild/Makefile: Prepare for using macros in inline assembly code to work around asm() related GCC inlining bugs"
Revert "x86/objtool: Use asm macros to work around GCC inlining bugs"
Revert "x86/refcount: Work around GCC inlining bug"
Revert "x86/alternatives: Macrofy lock prefixes to work around GCC inlining bugs"
Revert "x86/bug: Macrofy the BUG table section handling, to work around GCC inlining bugs"
Revert "x86/paravirt: Work around GCC inlining bugs when compiling paravirt ops"
Revert "x86/extable: Macrofy inline assembly code to work around GCC inlining bugs"
Revert "x86/cpufeature: Macrofy inline assembly code to work around GCC inlining bugs"
Revert "x86/jump-labels: Macrofy inline assembly code to work around GCC inlining bugs"
x86/mtrr: Don't copy uninitialized gentry fields back to userspace
x86/fsgsbase/64: Fix the base write helper functions
x86/mm/cpa: Fix cpa_flush_array() TLB invalidation
x86/vdso: Pass --eh-frame-hdr to the linker
x86/mm: Fix decoy address handling vs 32-bit builds
x86/intel_rdt: Ensure a CPU remains online for the region's pseudo-locking sequence
x86/dump_pagetables: Fix LDT remap address marker
x86/mm: Fix guard hole handling
Diffstat (limited to 'arch/x86')
-rw-r--r-- | arch/x86/Makefile | 7 | ||||
-rw-r--r-- | arch/x86/entry/calling.h | 2 | ||||
-rw-r--r-- | arch/x86/entry/vdso/Makefile | 3 | ||||
-rw-r--r-- | arch/x86/include/asm/alternative-asm.h | 20 | ||||
-rw-r--r-- | arch/x86/include/asm/alternative.h | 11 | ||||
-rw-r--r-- | arch/x86/include/asm/asm.h | 53 | ||||
-rw-r--r-- | arch/x86/include/asm/bug.h | 98 | ||||
-rw-r--r-- | arch/x86/include/asm/cpufeature.h | 82 | ||||
-rw-r--r-- | arch/x86/include/asm/fsgsbase.h | 15 | ||||
-rw-r--r-- | arch/x86/include/asm/jump_label.h | 72 | ||||
-rw-r--r-- | arch/x86/include/asm/paravirt_types.h | 56 | ||||
-rw-r--r-- | arch/x86/include/asm/pgtable_64_types.h | 5 | ||||
-rw-r--r-- | arch/x86/include/asm/refcount.h | 81 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c | 4 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/mtrr/if.c | 2 | ||||
-rw-r--r-- | arch/x86/kernel/macros.S | 16 | ||||
-rw-r--r-- | arch/x86/kernel/process_64.c | 99 | ||||
-rw-r--r-- | arch/x86/kernel/ptrace.c | 9 | ||||
-rw-r--r-- | arch/x86/mm/dump_pagetables.c | 15 | ||||
-rw-r--r-- | arch/x86/mm/pageattr.c | 24 | ||||
-rw-r--r-- | arch/x86/mm/pat.c | 13 | ||||
-rw-r--r-- | arch/x86/xen/mmu_pv.c | 11 |
22 files changed, 365 insertions, 333 deletions
diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 75ef499a66e2..85a66c4a8b65 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -232,13 +232,6 @@ archscripts: scripts_basic archheaders: $(Q)$(MAKE) $(build)=arch/x86/entry/syscalls all -archmacros: - $(Q)$(MAKE) $(build)=arch/x86/kernel arch/x86/kernel/macros.s - -ASM_MACRO_FLAGS = -Wa,arch/x86/kernel/macros.s -export ASM_MACRO_FLAGS -KBUILD_CFLAGS += $(ASM_MACRO_FLAGS) - ### # Kernel objects diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 25e5a6bda8c3..20d0885b00fb 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -352,7 +352,7 @@ For 32-bit we have the following conventions - kernel is built with .macro CALL_enter_from_user_mode #ifdef CONFIG_CONTEXT_TRACKING #ifdef HAVE_JUMP_LABEL - STATIC_BRANCH_JMP l_yes=.Lafter_call_\@, key=context_tracking_enabled, branch=1 + STATIC_JUMP_IF_FALSE .Lafter_call_\@, context_tracking_enabled, def=0 #endif call enter_from_user_mode .Lafter_call_\@: diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index 0624bf2266fd..5bfe2243a08f 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -171,7 +171,8 @@ quiet_cmd_vdso = VDSO $@ sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@' VDSO_LDFLAGS = -shared $(call ld-option, --hash-style=both) \ - $(call ld-option, --build-id) -Bsymbolic + $(call ld-option, --build-id) $(call ld-option, --eh-frame-hdr) \ + -Bsymbolic GCOV_PROFILE := n # diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h index 8e4ea39e55d0..31b627b43a8e 100644 --- a/arch/x86/include/asm/alternative-asm.h +++ b/arch/x86/include/asm/alternative-asm.h @@ -7,24 +7,16 @@ #include <asm/asm.h> #ifdef CONFIG_SMP -.macro LOCK_PREFIX_HERE + .macro LOCK_PREFIX +672: lock .pushsection .smp_locks,"a" .balign 4 - .long 671f - . # offset + .long 672b - . .popsection -671: -.endm - -.macro LOCK_PREFIX insn:vararg - LOCK_PREFIX_HERE - lock \insn -.endm + .endm #else -.macro LOCK_PREFIX_HERE -.endm - -.macro LOCK_PREFIX insn:vararg -.endm + .macro LOCK_PREFIX + .endm #endif /* diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index d7faa16622d8..4cd6a3b71824 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -31,8 +31,15 @@ */ #ifdef CONFIG_SMP -#define LOCK_PREFIX_HERE "LOCK_PREFIX_HERE\n\t" -#define LOCK_PREFIX "LOCK_PREFIX " +#define LOCK_PREFIX_HERE \ + ".pushsection .smp_locks,\"a\"\n" \ + ".balign 4\n" \ + ".long 671f - .\n" /* offset */ \ + ".popsection\n" \ + "671:" + +#define LOCK_PREFIX LOCK_PREFIX_HERE "\n\tlock; " + #else /* ! CONFIG_SMP */ #define LOCK_PREFIX_HERE "" #define LOCK_PREFIX "" diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index 21b086786404..6467757bb39f 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -120,25 +120,12 @@ /* Exception table entry */ #ifdef __ASSEMBLY__ # define _ASM_EXTABLE_HANDLE(from, to, handler) \ - ASM_EXTABLE_HANDLE from to handler - -.macro ASM_EXTABLE_HANDLE from:req to:req handler:req - .pushsection "__ex_table","a" - .balign 4 - .long (\from) - . - .long (\to) - . - .long (\handler) - . + .pushsection "__ex_table","a" ; \ + .balign 4 ; \ + .long (from) - . ; \ + .long (to) - . ; \ + .long (handler) - . ; \ .popsection -.endm -#else /* __ASSEMBLY__ */ - -# define _ASM_EXTABLE_HANDLE(from, to, handler) \ - "ASM_EXTABLE_HANDLE from=" #from " to=" #to \ - " handler=\"" #handler "\"\n\t" - -/* For C file, we already have NOKPROBE_SYMBOL macro */ - -#endif /* __ASSEMBLY__ */ # define _ASM_EXTABLE(from, to) \ _ASM_EXTABLE_HANDLE(from, to, ex_handler_default) @@ -161,7 +148,6 @@ _ASM_PTR (entry); \ .popsection -#ifdef __ASSEMBLY__ .macro ALIGN_DESTINATION /* check for bad alignment of destination */ movl %edi,%ecx @@ -185,7 +171,34 @@ _ASM_EXTABLE_UA(100b, 103b) _ASM_EXTABLE_UA(101b, 103b) .endm -#endif /* __ASSEMBLY__ */ + +#else +# define _EXPAND_EXTABLE_HANDLE(x) #x +# define _ASM_EXTABLE_HANDLE(from, to, handler) \ + " .pushsection \"__ex_table\",\"a\"\n" \ + " .balign 4\n" \ + " .long (" #from ") - .\n" \ + " .long (" #to ") - .\n" \ + " .long (" _EXPAND_EXTABLE_HANDLE(handler) ") - .\n" \ + " .popsection\n" + +# define _ASM_EXTABLE(from, to) \ + _ASM_EXTABLE_HANDLE(from, to, ex_handler_default) + +# define _ASM_EXTABLE_UA(from, to) \ + _ASM_EXTABLE_HANDLE(from, to, ex_handler_uaccess) + +# define _ASM_EXTABLE_FAULT(from, to) \ + _ASM_EXTABLE_HANDLE(from, to, ex_handler_fault) + +# define _ASM_EXTABLE_EX(from, to) \ + _ASM_EXTABLE_HANDLE(from, to, ex_handler_ext) + +# define _ASM_EXTABLE_REFCOUNT(from, to) \ + _ASM_EXTABLE_HANDLE(from, to, ex_handler_refcount) + +/* For C file, we already have NOKPROBE_SYMBOL macro */ +#endif #ifndef __ASSEMBLY__ /* diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h index 5090035e6d16..6804d6642767 100644 --- a/arch/x86/include/asm/bug.h +++ b/arch/x86/include/asm/bug.h @@ -4,8 +4,6 @@ #include <linux/stringify.h> -#ifndef __ASSEMBLY__ - /* * Despite that some emulators terminate on UD2, we use it for WARN(). * @@ -22,15 +20,53 @@ #define LEN_UD2 2 +#ifdef CONFIG_GENERIC_BUG + +#ifdef CONFIG_X86_32 +# define __BUG_REL(val) ".long " __stringify(val) +#else +# define __BUG_REL(val) ".long " __stringify(val) " - 2b" +#endif + +#ifdef CONFIG_DEBUG_BUGVERBOSE + +#define _BUG_FLAGS(ins, flags) \ +do { \ + asm volatile("1:\t" ins "\n" \ + ".pushsection __bug_table,\"aw\"\n" \ + "2:\t" __BUG_REL(1b) "\t# bug_entry::bug_addr\n" \ + "\t" __BUG_REL(%c0) "\t# bug_entry::file\n" \ + "\t.word %c1" "\t# bug_entry::line\n" \ + "\t.word %c2" "\t# bug_entry::flags\n" \ + "\t.org 2b+%c3\n" \ + ".popsection" \ + : : "i" (__FILE__), "i" (__LINE__), \ + "i" (flags), \ + "i" (sizeof(struct bug_entry))); \ +} while (0) + +#else /* !CONFIG_DEBUG_BUGVERBOSE */ + #define _BUG_FLAGS(ins, flags) \ do { \ - asm volatile("ASM_BUG ins=\"" ins "\" file=%c0 line=%c1 " \ - "flags=%c2 size=%c3" \ - : : "i" (__FILE__), "i" (__LINE__), \ - "i" (flags), \ + asm volatile("1:\t" ins "\n" \ + ".pushsection __bug_table,\"aw\"\n" \ + "2:\t" __BUG_REL(1b) "\t# bug_entry::bug_addr\n" \ + "\t.word %c0" "\t# bug_entry::flags\n" \ + "\t.org 2b+%c1\n" \ + ".popsection" \ + : : "i" (flags), \ "i" (sizeof(struct bug_entry))); \ } while (0) +#endif /* CONFIG_DEBUG_BUGVERBOSE */ + +#else + +#define _BUG_FLAGS(ins, flags) asm volatile(ins) + +#endif /* CONFIG_GENERIC_BUG */ + #define HAVE_ARCH_BUG #define BUG() \ do { \ @@ -46,54 +82,4 @@ do { \ #include <asm-generic/bug.h> -#else /* __ASSEMBLY__ */ - -#ifdef CONFIG_GENERIC_BUG - -#ifdef CONFIG_X86_32 -.macro __BUG_REL val:req - .long \val -.endm -#else -.macro __BUG_REL val:req - .long \val - 2b -.endm -#endif - -#ifdef CONFIG_DEBUG_BUGVERBOSE - -.macro ASM_BUG ins:req file:req line:req flags:req size:req -1: \ins - .pushsection __bug_table,"aw" -2: __BUG_REL val=1b # bug_entry::bug_addr - __BUG_REL val=\file # bug_entry::file - .word \line # bug_entry::line - .word \flags # bug_entry::flags - .org 2b+\size - .popsection -.endm - -#else /* !CONFIG_DEBUG_BUGVERBOSE */ - -.macro ASM_BUG ins:req file:req line:req flags:req size:req -1: \ins - .pushsection __bug_table,"aw" -2: __BUG_REL val=1b # bug_entry::bug_addr - .word \flags # bug_entry::flags - .org 2b+\size - .popsection -.endm - -#endif /* CONFIG_DEBUG_BUGVERBOSE */ - -#else /* CONFIG_GENERIC_BUG */ - -.macro ASM_BUG ins:req file:req line:req flags:req size:req - \ins -.endm - -#endif /* CONFIG_GENERIC_BUG */ - -#endif /* __ASSEMBLY__ */ - #endif /* _ASM_X86_BUG_H */ diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 7d442722ef24..aced6c9290d6 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -2,10 +2,10 @@ #ifndef _ASM_X86_CPUFEATURE_H #define _ASM_X86_CPUFEATURE_H -#ifdef __KERNEL__ -#ifndef __ASSEMBLY__ - #include <asm/processor.h> + +#if defined(__KERNEL__) && !defined(__ASSEMBLY__) + #include <asm/asm.h> #include <linux/bitops.h> @@ -161,10 +161,37 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit); */ static __always_inline __pure bool _static_cpu_has(u16 bit) { - asm_volatile_goto("STATIC_CPU_HAS bitnum=%[bitnum] " - "cap_byte=\"%[cap_byte]\" " - "feature=%P[feature] t_yes=%l[t_yes] " - "t_no=%l[t_no] always=%P[always]" + asm_volatile_goto("1: jmp 6f\n" + "2:\n" + ".skip -(((5f-4f) - (2b-1b)) > 0) * " + "((5f-4f) - (2b-1b)),0x90\n" + "3:\n" + ".section .altinstructions,\"a\"\n" + " .long 1b - .\n" /* src offset */ + " .long 4f - .\n" /* repl offset */ + " .word %P[always]\n" /* always replace */ + " .byte 3b - 1b\n" /* src len */ + " .byte 5f - 4f\n" /* repl len */ + " .byte 3b - 2b\n" /* pad len */ + ".previous\n" + ".section .altinstr_replacement,\"ax\"\n" + "4: jmp %l[t_no]\n" + "5:\n" + ".previous\n" + ".section .altinstructions,\"a\"\n" + " .long 1b - .\n" /* src offset */ + " .long 0\n" /* no replacement */ + " .word %P[feature]\n" /* feature bit */ + " .byte 3b - 1b\n" /* src len */ + " .byte 0\n" /* repl len */ + " .byte 0\n" /* pad len */ + ".previous\n" + ".section .altinstr_aux,\"ax\"\n" + "6:\n" + " testb %[bitnum],%[cap_byte]\n" + " jnz %l[t_yes]\n" + " jmp %l[t_no]\n" + ".previous\n" : : [feature] "i" (bit), [always] "i" (X86_FEATURE_ALWAYS), [bitnum] "i" (1 << (bit & 7)), @@ -199,44 +226,5 @@ t_no: #define CPU_FEATURE_TYPEVAL boot_cpu_data.x86_vendor, boot_cpu_data.x86, \ boot_cpu_data.x86_model -#else /* __ASSEMBLY__ */ - -.macro STATIC_CPU_HAS bitnum:req cap_byte:req feature:req t_yes:req t_no:req always:req -1: - jmp 6f -2: - .skip -(((5f-4f) - (2b-1b)) > 0) * ((5f-4f) - (2b-1b)),0x90 -3: - .section .altinstructions,"a" - .long 1b - . /* src offset */ - .long 4f - . /* repl offset */ - .word \always /* always replace */ - .byte 3b - 1b /* src len */ - .byte 5f - 4f /* repl len */ - .byte 3b - 2b /* pad len */ - .previous - .section .altinstr_replacement,"ax" -4: - jmp \t_no -5: - .previous - .section .altinstructions,"a" - .long 1b - . /* src offset */ - .long 0 /* no replacement */ - .word \feature /* feature bit */ - .byte 3b - 1b /* src len */ - .byte 0 /* repl len */ - .byte 0 /* pad len */ - .previous - .section .altinstr_aux,"ax" -6: - testb \bitnum,\cap_byte - jnz \t_yes - jmp \t_no - .previous -.endm - -#endif /* __ASSEMBLY__ */ - -#endif /* __KERNEL__ */ +#endif /* defined(__KERNEL__) && !defined(__ASSEMBLY__) */ #endif /* _ASM_X86_CPUFEATURE_H */ diff --git a/arch/x86/include/asm/fsgsbase.h b/arch/x86/include/asm/fsgsbase.h index eb377b6e9eed..bca4c743de77 100644 --- a/arch/x86/include/asm/fsgsbase.h +++ b/arch/x86/include/asm/fsgsbase.h @@ -16,8 +16,8 @@ */ extern unsigned long x86_fsbase_read_task(struct task_struct *task); extern unsigned long x86_gsbase_read_task(struct task_struct *task); -extern int x86_fsbase_write_task(struct task_struct *task, unsigned long fsbase); -extern int x86_gsbase_write_task(struct task_struct *task, unsigned long gsbase); +extern void x86_fsbase_write_task(struct task_struct *task, unsigned long fsbase); +extern void x86_gsbase_write_task(struct task_struct *task, unsigned long gsbase); /* Helper functions for reading/writing FS/GS base */ @@ -39,8 +39,15 @@ static inline unsigned long x86_gsbase_read_cpu_inactive(void) return gsbase; } -extern void x86_fsbase_write_cpu(unsigned long fsbase); -extern void x86_gsbase_write_cpu_inactive(unsigned long gsbase); +static inline void x86_fsbase_write_cpu(unsigned long fsbase) +{ + wrmsrl(MSR_FS_BASE, fsbase); +} + +static inline void x86_gsbase_write_cpu_inactive(unsigned long gsbase) +{ + wrmsrl(MSR_KERNEL_GS_BASE, gsbase); +} #endif /* CONFIG_X86_64 */ diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h index a5fb34fe56a4..21efc9d07ed9 100644 --- a/arch/x86/include/asm/jump_label.h +++ b/arch/x86/include/asm/jump_label.h @@ -2,6 +2,19 @@ #ifndef _ASM_X86_JUMP_LABEL_H #define _ASM_X86_JUMP_LABEL_H +#ifndef HAVE_JUMP_LABEL +/* + * For better or for worse, if jump labels (the gcc extension) are missing, + * then the entire static branch patching infrastructure is compiled out. + * If that happens, the code in here will malfunction. Raise a compiler + * error instead. + * + * In theory, jump labels and the static branch patching infrastructure + * could be decoupled to fix this. + */ +#error asm/jump_label.h included on a non-jump-label kernel +#endif + #define JUMP_LABEL_NOP_SIZE 5 #ifdef CONFIG_X86_64 @@ -20,9 +33,15 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto("STATIC_BRANCH_NOP l_yes=\"%l[l_yes]\" key=\"%c0\" " - "branch=\"%c1\"" - : : "i" (key), "i" (branch) : : l_yes); + asm_volatile_goto("1:" + ".byte " __stringify(STATIC_KEY_INIT_NOP) "\n\t" + ".pushsection __jump_table, \"aw\" \n\t" + _ASM_ALIGN "\n\t" + ".long 1b - ., %l[l_yes] - . \n\t" + _ASM_PTR "%c0 + %c1 - .\n\t" + ".popsection \n\t" + : : "i" (key), "i" (branch) : : l_yes); + return false; l_yes: return true; @@ -30,8 +49,14 @@ l_yes: static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm_volatile_goto("STATIC_BRANCH_JMP l_yes=\"%l[l_yes]\" key=\"%c0\" " - "branch=\"%c1\"" + asm_volatile_goto("1:" + ".byte 0xe9\n\t .long %l[l_yes] - 2f\n\t" + "2:\n\t" + ".pushsection __jump_table, \"aw\" \n\t" + _ASM_ALIGN "\n\t" + ".long 1b - ., %l[l_yes] - . \n\t" + _ASM_PTR "%c0 + %c1 - .\n\t" + ".popsection \n\t" : : "i" (key), "i" (branch) : : l_yes); return false; @@ -41,26 +66,37 @@ l_yes: #else /* __ASSEMBLY__ */ -.macro STATIC_BRANCH_NOP l_yes:req key:req branch:req -.Lstatic_branch_nop_\@: - .byte STATIC_KEY_INIT_NOP -.Lstatic_branch_no_after_\@: +.macro STATIC_JUMP_IF_TRUE target, key, def +.Lstatic_jump_\@: + .if \def + /* Equivalent to "jmp.d32 \target" */ + .byte 0xe9 + .long \target - .Lstatic_jump_after_\@ +.Lstatic_jump_after_\@: + .else + .byte STATIC_KEY_INIT_NOP + .endif .pushsection __jump_table, "aw" _ASM_ALIGN - .long .Lstatic_branch_nop_\@ - ., \l_yes - . - _ASM_PTR \key + \branch - . + .long .Lstatic_jump_\@ - ., \target - . + _ASM_PTR \key - . .popsection .endm -.macro STATIC_BRANCH_JMP l_yes:req key:req branch:req -.Lstatic_branch_jmp_\@: - .byte 0xe9 - .long \l_yes - .Lstatic_branch_jmp_after_\@ -.Lstatic_branch_jmp_after_\@: +.macro STATIC_JUMP_IF_FALSE target, key, def +.Lstatic_jump_\@: + .if \def + .byte STATIC_KEY_INIT_NOP + .else + /* Equivalent to "jmp.d32 \target" */ + .byte 0xe9 + .long \target - .Lstatic_jump_after_\@ +.Lstatic_jump_after_\@: + .endif .pushsection __jump_table, "aw" _ASM_ALIGN - .long .Lstatic_branch_jmp_\@ - ., \l_yes - . - _ASM_PTR \key + \branch - . + .long .Lstatic_jump_\@ - ., \target - . + _ASM_PTR \key + 1 - . .popsection .endm diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 26942ad63830..488c59686a73 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -348,11 +348,23 @@ extern struct paravirt_patch_template pv_ops; #define paravirt_clobber(clobber) \ [paravirt_clobber] "i" (clobber) +/* + * Generate some code, and mark it as patchable by the + * apply_paravirt() alternate instruction patcher. + */ +#define _paravirt_alt(insn_string, type, clobber) \ + "771:\n\t" insn_string "\n" "772:\n" \ + ".pushsection .parainstructions,\"a\"\n" \ + _ASM_ALIGN "\n" \ + _ASM_PTR " 771b\n" \ + " .byte " type "\n" \ + " .byte 772b-771b\n" \ + " .short " clobber "\n" \ + ".popsection\n" + /* Generate patchable code, with the default asm parameters. */ -#define paravirt_call \ - "PARAVIRT_CALL type=\"%c[paravirt_typenum]\"" \ - " clobber=\"%c[paravirt_clobber]\"" \ - " pv_opptr=\"%c[paravirt_opptr]\";" +#define paravirt_alt(insn_string) \ + _paravirt_alt(insn_string, "%c[paravirt_typenum]", "%c[paravirt_clobber]") /* Simple instruction patching code. */ #define NATIVE_LABEL(a,x,b) "\n\t.globl " a #x "_" #b "\n" a #x "_" #b ":\n\t" @@ -373,6 +385,16 @@ unsigned native_patch(u8 type, void *ibuf, unsigned long addr, unsigned len); int paravirt_disable_iospace(void); /* + * This generates an indirect call based on the operation type number. + * The type number, computed in PARAVIRT_PATCH, is derived from the + * offset into the paravirt_patch_template structure, and can therefore be + * freely converted back into a structure offset. + */ +#define PARAVIRT_CALL \ + ANNOTATE_RETPOLINE_SAFE \ + "call *%c[paravirt_opptr];" + +/* * These macros are intended to wrap calls through one of the paravirt * ops structs, so that they can be later identified and patched at * runtime. @@ -509,7 +531,7 @@ int paravirt_disable_iospace(void); /* since this condition will never hold */ \ if (sizeof(rettype) > sizeof(unsigned long)) { \ asm volatile(pre \ - paravirt_call \ + paravirt_alt(PARAVIRT_CALL) \ post \ : call_clbr, ASM_CALL_CONSTRAINT \ : paravirt_type(op), \ @@ -519,7 +541,7 @@ int paravirt_disable_iospace(void); __ret = (rettype)((((u64)__edx) << 32) | __eax); \ } else { \ asm volatile(pre \ - paravirt_call \ + paravirt_alt(PARAVIRT_CALL) \ post \ : call_clbr, ASM_CALL_CONSTRAINT \ : paravirt_type(op), \ @@ -546,7 +568,7 @@ int paravirt_disable_iospace(void); PVOP_VCALL_ARGS; \ PVOP_TEST_NULL(op); \ asm volatile(pre \ - paravirt_call \ + paravirt_alt(PARAVIRT_CALL) \ post \ : call_clbr, ASM_CALL_CONSTRAINT \ : paravirt_type(op), \ @@ -664,26 +686,6 @@ struct paravirt_patch_site { extern struct paravirt_patch_site __parainstructions[], __parainstructions_end[]; -#else /* __ASSEMBLY__ */ - -/* - * This generates an indirect call based on the operation type number. - * The type number, computed in PARAVIRT_PATCH, is derived from the - * offset into the paravirt_patch_template structure, and can therefore be - * freely converted back into a structure offset. - */ -.macro PARAVIRT_CALL type:req clobber:req pv_opptr:req -771: ANNOTATE_RETPOLINE_SAFE - call *\pv_opptr -772: .pushsection .parainstructions,"a" - _ASM_ALIGN - _ASM_PTR 771b - .byte \type - .byte 772b-771b - .short \clobber - .popsection -.endm - #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_PARAVIRT_TYPES_H */ diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h index 84bd9bdc1987..88bca456da99 100644 --- a/arch/x86/include/asm/pgtable_64_types.h +++ b/arch/x86/include/asm/pgtable_64_types.h @@ -111,6 +111,11 @@ extern unsigned int ptrs_per_p4d; */ #define MAXMEM (1UL << MAX_PHYSMEM_BITS) +#define GUARD_HOLE_PGD_ENTRY -256UL +#define GUARD_HOLE_SIZE (16UL << PGDIR_SHIFT) +#define GUARD_HOLE_BASE_ADDR (GUARD_HOLE_PGD_ENTRY << PGDIR_SHIFT) +#define GUARD_HOLE_END_ADDR (GUARD_HOLE_BASE_ADDR + GUARD_HOLE_SIZE) + #define LDT_PGD_ENTRY -240UL #define LDT_BASE_ADDR (LDT_PGD_ENTRY << PGDIR_SHIFT) #define LDT_END_ADDR (LDT_BASE_ADDR + PGDIR_SIZE) diff --git a/arch/x86/include/asm/refcount.h b/arch/x86/include/asm/refcount.h index a8b5e1e13319..dbaed55c1c24 100644 --- a/arch/x86/include/asm/refcount.h +++ b/arch/x86/include/asm/refcount.h @@ -4,41 +4,6 @@ * x86-specific implementation of refcount_t. Based on PAX_REFCOUNT from * PaX/grsecurity. */ - -#ifdef __ASSEMBLY__ - -#include <asm/asm.h> -#include <asm/bug.h> - -.macro REFCOUNT_EXCEPTION counter:req - .pushsection .text..refcount -111: lea \counter, %_ASM_CX -112: ud2 - ASM_UNREACHABLE - .popsection -113: _ASM_EXTABLE_REFCOUNT(112b, 113b) -.endm - -/* Trigger refcount exception if refcount result is negative. */ -.macro REFCOUNT_CHECK_LT_ZERO counter:req - js 111f - REFCOUNT_EXCEPTION counter="\counter" -.endm - -/* Trigger refcount exception if refcount result is zero or negative. */ -.macro REFCOUNT_CHECK_LE_ZERO counter:req - jz 111f - REFCOUNT_CHECK_LT_ZERO counter="\counter" -.endm - -/* Trigger refcount exception unconditionally. */ -.macro REFCOUNT_ERROR counter:req - jmp 111f - REFCOUNT_EXCEPTION counter="\counter" -.endm - -#else /* __ASSEMBLY__ */ - #include <linux/refcount.h> #include <asm/bug.h> @@ -50,12 +15,35 @@ * central refcount exception. The fixup address for the exception points * back to the regular execution flow in .text. */ +#define _REFCOUNT_EXCEPTION \ + ".pushsection .text..refcount\n" \ + "111:\tlea %[var], %%" _ASM_CX "\n" \ + "112:\t" ASM_UD2 "\n" \ + ASM_UNREACHABLE \ + ".popsection\n" \ + "113:\n" \ + _ASM_EXTABLE_REFCOUNT(112b, 113b) + +/* Trigger refcount exception if refcount result is negative. */ +#define REFCOUNT_CHECK_LT_ZERO \ + "js 111f\n\t" \ + _REFCOUNT_EXCEPTION + +/* Trigger refcount exception if refcount result is zero or negative. */ +#define REFCOUNT_CHECK_LE_ZERO \ + "jz 111f\n\t" \ + REFCOUNT_CHECK_LT_ZERO + +/* Trigger refcount exception unconditionally. */ +#define REFCOUNT_ERROR \ + "jmp 111f\n\t" \ + _REFCOUNT_EXCEPTION static __always_inline void refcount_add(unsigned int i, refcount_t *r) { asm volatile(LOCK_PREFIX "addl %1,%0\n\t" - "REFCOUNT_CHECK_LT_ZERO counter=\"%[counter]\"" - : [counter] "+m" (r->refs.counter) + REFCOUNT_CHECK_LT_ZERO + : [var] "+m" (r->refs.counter) : "ir" (i) : "cc", "cx"); } @@ -63,32 +51,31 @@ static __always_inline void refcount_add(unsigned int i, refcount_t *r) static __always_inline void refcount_inc(refcount_t *r) { asm volatile(LOCK_PREFIX "incl %0\n\t" - "REFCOUNT_CHECK_LT_ZERO counter=\"%[counter]\"" - : [counter] "+m" (r->refs.counter) + REFCOUNT_CHECK_LT_ZERO + : [var] "+m" (r->refs.counter) : : "cc", "cx"); } static __always_inline void refcount_dec(refcount_t *r) { asm volatile(LOCK_PREFIX "decl %0\n\t" - "REFCOUNT_CHECK_LE_ZERO counter=\"%[counter]\"" - : [counter] "+m" (r->refs.counter) + REFCOUNT_CHECK_LE_ZERO + : [var] "+m" (r->refs.counter) : : "cc", "cx"); } static __always_inline __must_check bool refcount_sub_and_test(unsigned int i, refcount_t *r) { - return GEN_BINARY_SUFFIXED_RMWcc(LOCK_PREFIX "subl", - "REFCOUNT_CHECK_LT_ZERO counter=\"%[var]\"", + REFCOUNT_CHECK_LT_ZERO, r->refs.counter, e, "er", i, "cx"); } static __always_inline __must_check bool refcount_dec_and_test(refcount_t *r) { return GEN_UNARY_SUFFIXED_RMWcc(LOCK_PREFIX "decl", - "REFCOUNT_CHECK_LT_ZERO counter=\"%[var]\"", + REFCOUNT_CHECK_LT_ZERO, r->refs.counter, e, "cx"); } @@ -106,8 +93,8 @@ bool refcount_add_not_zero(unsigned int i, refcount_t *r) /* Did we try to increment from/to an undesirable state? */ if (unlikely(c < 0 || c == INT_MAX || result < c)) { - asm volatile("REFCOUNT_ERROR counter=\"%[counter]\"" - : : [counter] "m" (r->refs.counter) + asm volatile(REFCOUNT_ERROR + : : [var] "m" (r->refs.counter) : "cc", "cx"); break; } @@ -122,6 +109,4 @@ static __always_inline __must_check bool refcount_inc_not_zero(refcount_t *r) return refcount_add_not_zero(1, r); } -#endif /* __ASSEMBLY__ */ - #endif diff --git a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c index 27937458c231..efa4a519f5e5 100644 --- a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c +++ b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c @@ -23,6 +23,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/cpu.h> #include <linux/kernfs.h> #include <linux/seq_file.h> #include <linux/slab.h> @@ -310,9 +311,11 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, return -EINVAL; buf[nbytes - 1] = '\0'; + cpus_read_lock(); rdtgrp = rdtgroup_kn_lock_live(of->kn); if (!rdtgrp) { rdtgroup_kn_unlock(of->kn); + cpus_read_unlock(); return -ENOENT; } rdt_last_cmd_clear(); @@ -367,6 +370,7 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, out: rdtgroup_kn_unlock(of->kn); + cpus_read_unlock(); return ret ?: nbytes; } diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c index 2e173d47b450..4d36dcc1cf87 100644 --- a/arch/x86/kernel/cpu/mtrr/if.c +++ b/arch/x86/kernel/cpu/mtrr/if.c @@ -165,6 +165,8 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg) struct mtrr_gentry gentry; void __user *arg = (void __user *) __arg; + memset(&gentry, 0, sizeof(gentry)); + switch (cmd) { case MTRRIOC_ADD_ENTRY: case MTRRIOC_SET_ENTRY: diff --git a/arch/x86/kernel/macros.S b/arch/x86/kernel/macros.S deleted file mode 100644 index 161c95059044..000000000000 --- a/arch/x86/kernel/macros.S +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ - -/* - * This file includes headers whose assembly part includes macros which are - * commonly used. The macros are precompiled into assmebly file which is later - * assembled together with each compiled file. - */ - -#include <linux/compiler.h> -#include <asm/refcount.h> -#include <asm/alternative-asm.h> -#include <asm/bug.h> -#include <asm/paravirt.h> -#include <asm/asm.h> -#include <asm/cpufeature.h> -#include <asm/jump_label.h> diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index bbfbf017065c..ddd4fa718c43 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -339,24 +339,6 @@ static unsigned long x86_fsgsbase_read_task(struct task_struct *task, return base; } -void x86_fsbase_write_cpu(unsigned long fsbase) -{ - /* - * Set the selector to 0 as a notion, that the segment base is - * overwritten, which will be checked for skipping the segment load - * during context switch. - */ - loadseg(FS, 0); - wrmsrl(MSR_FS_BASE, fsbase); -} - -void x86_gsbase_write_cpu_inactive(unsigned long gsbase) -{ - /* Set the selector to 0 for the same reason as %fs above. */ - loadseg(GS, 0); - wrmsrl(MSR_KERNEL_GS_BASE, gsbase); -} - unsigned long x86_fsbase_read_task(struct task_struct *task) { unsigned long fsbase; @@ -385,38 +367,18 @@ unsigned long x86_gsbase_read_task(struct task_struct *task) return gsbase; } -int x86_fsbase_write_task(struct task_struct *task, unsigned long fsbase) +void x86_fsbase_write_task(struct task_struct *task, unsigned long fsbase) { - /* - * Not strictly needed for %fs, but do it for symmetry - * with %gs - */ - if (unlikely(fsbase >= TASK_SIZE_MAX)) - return -EPERM; + WARN_ON_ONCE(task == current); - preempt_disable(); task->thread.fsbase = fsbase; - if (task == current) - x86_fsbase_write_cpu(fsbase); - task->thread.fsindex = 0; - preempt_enable(); - - return 0; } -int x86_gsbase_write_task(struct task_struct *task, unsigned long gsbase) +void x86_gsbase_write_task(struct task_struct *task, unsigned long gsbase) { - if (unlikely(gsbase >= TASK_SIZE_MAX)) - return -EPERM; + WARN_ON_ONCE(task == current); - preempt_disable(); task->thread.gsbase = gsbase; - if (task == current) - x86_gsbase_write_cpu_inactive(gsbase); - task->thread.gsindex = 0; - preempt_enable(); - - return 0; } int copy_thread_tls(unsigned long clone_flags, unsigned long sp, @@ -754,11 +716,60 @@ long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2) switch (option) { case ARCH_SET_GS: { - ret = x86_gsbase_write_task(task, arg2); + if (unlikely(arg2 >= TASK_SIZE_MAX)) + return -EPERM; + + preempt_disable(); + /* + * ARCH_SET_GS has always overwritten the index + * and the base. Zero is the most sensible value + * to put in the index, and is the only value that + * makes any sense if FSGSBASE is unavailable. + */ + if (task == current) { + loadseg(GS, 0); + x86_gsbase_write_cpu_inactive(arg2); + + /* + * On non-FSGSBASE systems, save_base_legacy() expects + * that we also fill in thread.gsbase. + */ + task->thread.gsbase = arg2; + + } else { + task->thread.gsindex = 0; + x86_gsbase_write_task(task, arg2); + } + preempt_enable(); break; } case ARCH_SET_FS: { - ret = x86_fsbase_write_task(task, arg2); + /* + * Not strictly needed for %fs, but do it for symmetry + * with %gs + */ + if (unlikely(arg2 >= TASK_SIZE_MAX)) + return -EPERM; + + preempt_disable(); + /* + * Set the selector to 0 for the same reason + * as %gs above. + */ + if (task == current) { + loadseg(FS, 0); + x86_fsbase_write_cpu(arg2); + + /* + * On non-FSGSBASE systems, save_base_legacy() expects + * that we also fill in thread.fsbase. + */ + task->thread.fsbase = arg2; + } else { + task->thread.fsindex = 0; + x86_fsbase_write_task(task, arg2); + } + preempt_enable(); break; } case ARCH_GET_FS: { diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index ffae9b9740fd..4b8ee05dd6ad 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -397,11 +397,12 @@ static int putreg(struct task_struct *child, if (value >= TASK_SIZE_MAX) return -EIO; /* - * When changing the FS base, use the same - * mechanism as for do_arch_prctl_64(). + * When changing the FS base, use do_arch_prctl_64() + * to set the index to zero and to set the base + * as requested. */ if (child->thread.fsbase != value) - return x86_fsbase_write_task(child, value); + return do_arch_prctl_64(child, ARCH_SET_FS, value); return 0; case offsetof(struct user_regs_struct,gs_base): /* @@ -410,7 +411,7 @@ static int putreg(struct task_struct *child, if (value >= TASK_SIZE_MAX) return -EIO; if (child->thread.gsbase != value) - return x86_gsbase_write_task(child, value); + return do_arch_prctl_64(child, ARCH_SET_GS, value); return 0; #endif } diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index fc37bbd23eb8..abcb8d00b014 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -55,10 +55,10 @@ struct addr_marker { enum address_markers_idx { USER_SPACE_NR = 0, KERNEL_SPACE_NR, - LOW_KERNEL_NR, -#if defined(CONFIG_MODIFY_LDT_SYSCALL) && defined(CONFIG_X86_5LEVEL) +#ifdef CONFIG_MODIFY_LDT_SYSCALL LDT_NR, #endif + LOW_KERNEL_NR, VMALLOC_START_NR, VMEMMAP_START_NR, #ifdef CONFIG_KASAN @@ -66,9 +66,6 @@ enum address_markers_idx { KASAN_SHADOW_END_NR, #endif CPU_ENTRY_AREA_NR, -#if defined(CONFIG_MODIFY_LDT_SYSCALL) && !defined(CONFIG_X86_5LEVEL) - LDT_NR, -#endif #ifdef CONFIG_X86_ESPFIX64 ESPFIX_START_NR, #endif @@ -512,11 +509,11 @@ static inline bool is_hypervisor_range(int idx) { #ifdef CONFIG_X86_64 /* - * ffff800000000000 - ffff87ffffffffff is reserved for - * the hypervisor. + * A hole in the beginning of kernel address space reserved + * for a hypervisor. */ - return (idx >= pgd_index(__PAGE_OFFSET) - 16) && - (idx < pgd_index(__PAGE_OFFSET)); + return (idx >= pgd_index(GUARD_HOLE_BASE_ADDR)) && + (idx < pgd_index(GUARD_HOLE_END_ADDR)); #else return false; #endif diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index db7a10082238..a1bcde35db4c 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -285,20 +285,16 @@ static void cpa_flush_all(unsigned long cache) on_each_cpu(__cpa_flush_all, (void *) cache, 1); } -static bool __cpa_flush_range(unsigned long start, int numpages, int cache) +static bool __inv_flush_all(int cache) { BUG_ON(irqs_disabled() && !early_boot_irqs_disabled); - WARN_ON(PAGE_ALIGN(start) != start); - if (cache && !static_cpu_has(X86_FEATURE_CLFLUSH)) { cpa_flush_all(cache); return true; } - flush_tlb_kernel_range(start, start + PAGE_SIZE * numpages); - - return !cache; + return false; } static void cpa_flush_range(unsigned long start, int numpages, int cache) @@ -306,7 +302,14 @@ static void cpa_flush_range(unsigned long start, int numpages, int cache) unsigned int i, level; unsigned long addr; - if (__cpa_flush_range(start, numpages, cache)) + WARN_ON(PAGE_ALIGN(start) != start); + + if (__inv_flush_all(cache)) + return; + + flush_tlb_kernel_range(start, start + PAGE_SIZE * numpages); + + if (!cache) return; /* @@ -332,7 +335,12 @@ static void cpa_flush_array(unsigned long baddr, unsigned long *start, { unsigned int i, level; - if (__cpa_flush_range(baddr, numpages, cache)) + if (__inv_flush_all(cache)) + return; + + flush_tlb_all(); + + if (!cache) return; /* diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 08013524fba1..4fe956a63b25 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -519,8 +519,13 @@ static u64 sanitize_phys(u64 address) * for a "decoy" virtual address (bit 63 clear) passed to * set_memory_X(). __pa() on a "decoy" address results in a * physical address with bit 63 set. + * + * Decoy addresses are not present for 32-bit builds, see + * set_mce_nospec(). */ - return address & __PHYSICAL_MASK; + if (IS_ENABLED(CONFIG_X86_64)) + return address & __PHYSICAL_MASK; + return address; } /* @@ -546,7 +551,11 @@ int reserve_memtype(u64 start, u64 end, enum page_cache_mode req_type, start = sanitize_phys(start); end = sanitize_phys(end); - BUG_ON(start >= end); /* end is exclusive */ + if (start >= end) { + WARN(1, "%s failed: [mem %#010Lx-%#010Lx], req %s\n", __func__, + start, end - 1, cattr_name(req_type)); + return -EINVAL; + } if (!pat_enabled()) { /* This is identical to page table setting without PAT */ diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index a5d7ed125337..0f4fe206dcc2 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -648,19 +648,20 @@ static int __xen_pgd_walk(struct mm_struct *mm, pgd_t *pgd, unsigned long limit) { int i, nr, flush = 0; - unsigned hole_low, hole_high; + unsigned hole_low = 0, hole_high = 0; /* The limit is the last byte to be touched */ limit--; BUG_ON(limit >= FIXADDR_TOP); +#ifdef CONFIG_X86_64 /* * 64-bit has a great big hole in the middle of the address - * space, which contains the Xen mappings. On 32-bit these - * will end up making a zero-sized hole and so is a no-op. + * space, which contains the Xen mappings. */ - hole_low = pgd_index(USER_LIMIT); - hole_high = pgd_index(PAGE_OFFSET); + hole_low = pgd_index(GUARD_HOLE_BASE_ADDR); + hole_high = pgd_index(GUARD_HOLE_END_ADDR); +#endif nr = pgd_index(limit) + 1; for (i = 0; i < nr; i++) { |