diff options
Diffstat (limited to 'arch/x86')
135 files changed, 2986 insertions, 2205 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index e876b3a087f9..835d93006bd6 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -215,6 +215,8 @@ config X86 select HAVE_FUNCTION_ARG_ACCESS_API select HAVE_STACKPROTECTOR if CC_HAS_SANE_STACKPROTECTOR select HAVE_STACK_VALIDATION if X86_64 + select HAVE_STATIC_CALL + select HAVE_STATIC_CALL_INLINE if HAVE_STACK_VALIDATION select HAVE_RSEQ select HAVE_SYSCALL_TRACEPOINTS select HAVE_UNSTABLE_SCHED_CLOCK @@ -230,6 +232,7 @@ config X86 select RTC_MC146818_LIB select SPARSE_IRQ select SRCU + select STACK_VALIDATION if HAVE_STACK_VALIDATION && (HAVE_STATIC_CALL_INLINE || RETPOLINE) select SYSCTL_EXCEPTION_TRACE select THREAD_INFO_IN_TASK select USER_STACKTRACE_SUPPORT @@ -451,7 +454,6 @@ config GOLDFISH config RETPOLINE bool "Avoid speculative indirect branches in kernel" default y - select STACK_VALIDATION if HAVE_STACK_VALIDATION help Compile kernel with the retpoline compiler options to guard against kernel-to-user data leaks by avoiding speculative indirect diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 4346ffb2e39f..154259f18b8b 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -209,6 +209,10 @@ ifdef CONFIG_X86_64 LDFLAGS_vmlinux += -z max-page-size=0x200000 endif +# We never want expected sections to be placed heuristically by the +# linker. All sections should be explicitly named in the linker script. +LDFLAGS_vmlinux += $(call ld-option, --orphan-handling=warn) + archscripts: scripts_basic $(Q)$(MAKE) $(build)=arch/x86/tools relocs diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index ff7894f39e0e..4fb989ef5665 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -29,7 +29,7 @@ targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma \ vmlinux.bin.xz vmlinux.bin.lzo vmlinux.bin.lz4 vmlinux.bin.zst KBUILD_CFLAGS := -m$(BITS) -O2 -KBUILD_CFLAGS += -fno-strict-aliasing $(call cc-option, -fPIE, -fPIC) +KBUILD_CFLAGS += -fno-strict-aliasing -fPIE KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING cflags-$(CONFIG_X86_32) := -march=i386 cflags-$(CONFIG_X86_64) := -mcmodel=small @@ -45,24 +45,19 @@ KBUILD_CFLAGS += -fno-asynchronous-unwind-tables KBUILD_CFLAGS += -D__DISABLE_EXPORTS # Disable relocation relaxation in case the link is not PIE. KBUILD_CFLAGS += $(call as-option,-Wa$(comma)-mrelax-relocations=no) +KBUILD_CFLAGS += -include $(srctree)/include/linux/hidden.h KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__ GCOV_PROFILE := n UBSAN_SANITIZE :=n KBUILD_LDFLAGS := -m elf_$(UTS_MACHINE) +KBUILD_LDFLAGS += $(call ld-option,--no-ld-generated-unwind-info) # Compressed kernel should be built as PIE since it may be loaded at any # address by the bootloader. -ifeq ($(CONFIG_X86_32),y) -KBUILD_LDFLAGS += $(call ld-option, -pie) $(call ld-option, --no-dynamic-linker) -else -# To build 64-bit compressed kernel as PIE, we disable relocation -# overflow check to avoid relocation overflow error with a new linker -# command-line option, -z noreloc-overflow. -KBUILD_LDFLAGS += $(shell $(LD) --help 2>&1 | grep -q "\-z noreloc-overflow" \ - && echo "-z noreloc-overflow -pie --no-dynamic-linker") -endif -LDFLAGS_vmlinux := -T +LDFLAGS_vmlinux := -pie $(call ld-option, --no-dynamic-linker) +LDFLAGS_vmlinux += $(call ld-option, --orphan-handling=warn) +LDFLAGS_vmlinux += -T hostprogs := mkpiggy HOST_EXTRACFLAGS += -I$(srctree)/tools/include @@ -96,30 +91,8 @@ vmlinux-objs-$(CONFIG_ACPI) += $(obj)/acpi.o vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_thunk_$(BITS).o efi-obj-$(CONFIG_EFI_STUB) = $(objtree)/drivers/firmware/efi/libstub/lib.a -# The compressed kernel is built with -fPIC/-fPIE so that a boot loader -# can place it anywhere in memory and it will still run. However, since -# it is executed as-is without any ELF relocation processing performed -# (and has already had all relocation sections stripped from the binary), -# none of the code can use data relocations (e.g. static assignments of -# pointer values), since they will be meaningless at runtime. This check -# will refuse to link the vmlinux if any of these relocations are found. -quiet_cmd_check_data_rel = DATAREL $@ -define cmd_check_data_rel - for obj in $(filter %.o,$^); do \ - $(READELF) -S $$obj | grep -qF .rel.local && { \ - echo "error: $$obj has data relocations!" >&2; \ - exit 1; \ - } || true; \ - done -endef - -# We need to run two commands under "if_changed", so merge them into a -# single invocation. -quiet_cmd_check-and-link-vmlinux = LD $@ - cmd_check-and-link-vmlinux = $(cmd_check_data_rel); $(cmd_ld) - $(obj)/vmlinux: $(vmlinux-objs-y) $(efi-obj-y) FORCE - $(call if_changed,check-and-link-vmlinux) + $(call if_changed,ld) OBJCOPYFLAGS_vmlinux.bin := -R .comment -S $(obj)/vmlinux.bin: vmlinux FORCE diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S index 03557f2174bf..659fad53ca82 100644 --- a/arch/x86/boot/compressed/head_32.S +++ b/arch/x86/boot/compressed/head_32.S @@ -33,32 +33,13 @@ #include <asm/bootparam.h> /* - * The 32-bit x86 assembler in binutils 2.26 will generate R_386_GOT32X - * relocation to get the symbol address in PIC. When the compressed x86 - * kernel isn't built as PIC, the linker optimizes R_386_GOT32X - * relocations to their fixed symbol addresses. However, when the - * compressed x86 kernel is loaded at a different address, it leads - * to the following load failure: - * - * Failed to allocate space for phdrs - * - * during the decompression stage. - * - * If the compressed x86 kernel is relocatable at run-time, it should be - * compiled with -fPIE, instead of -fPIC, if possible and should be built as - * Position Independent Executable (PIE) so that linker won't optimize - * R_386_GOT32X relocation to its fixed symbol address. Older - * linkers generate R_386_32 relocations against locally defined symbols, - * _bss, _ebss, _got, _egot and _end, in PIE. It isn't wrong, just less - * optimal than R_386_RELATIVE. But the x86 kernel fails to properly handle - * R_386_32 relocations when relocating the kernel. To generate - * R_386_RELATIVE relocations, we mark _bss, _ebss, _got, _egot and _end as - * hidden: + * These symbols needed to be marked as .hidden to prevent the BFD linker from + * generating R_386_32 (rather than R_386_RELATIVE) relocations for them when + * the 32-bit compressed kernel is linked as PIE. This is no longer necessary, + * but it doesn't hurt to keep them .hidden. */ .hidden _bss .hidden _ebss - .hidden _got - .hidden _egot .hidden _end __HEAD @@ -77,10 +58,10 @@ SYM_FUNC_START(startup_32) leal (BP_scratch+4)(%esi), %esp call 1f 1: popl %edx - subl $1b, %edx + addl $_GLOBAL_OFFSET_TABLE_+(.-1b), %edx /* Load new GDT */ - leal gdt(%edx), %eax + leal gdt@GOTOFF(%edx), %eax movl %eax, 2(%eax) lgdt (%eax) @@ -93,14 +74,16 @@ SYM_FUNC_START(startup_32) movl %eax, %ss /* - * %edx contains the address we are loaded at by the boot loader and %ebx - * contains the address where we should move the kernel image temporarily - * for safe in-place decompression. %ebp contains the address that the kernel - * will be decompressed to. + * %edx contains the address we are loaded at by the boot loader (plus the + * offset to the GOT). The below code calculates %ebx to be the address where + * we should move the kernel image temporarily for safe in-place decompression + * (again, plus the offset to the GOT). + * + * %ebp is calculated to be the address that the kernel will be decompressed to. */ #ifdef CONFIG_RELOCATABLE - movl %edx, %ebx + leal startup_32@GOTOFF(%edx), %ebx #ifdef CONFIG_EFI_STUB /* @@ -111,7 +94,7 @@ SYM_FUNC_START(startup_32) * image_offset = startup_32 - image_base * Otherwise image_offset will be zero and has no effect on the calculations. */ - subl image_offset(%edx), %ebx + subl image_offset@GOTOFF(%edx), %ebx #endif movl BP_kernel_alignment(%esi), %eax @@ -128,10 +111,10 @@ SYM_FUNC_START(startup_32) movl %ebx, %ebp // Save the output address for later /* Target address to relocate to for decompression */ addl BP_init_size(%esi), %ebx - subl $_end, %ebx + subl $_end@GOTOFF, %ebx /* Set up the stack */ - leal boot_stack_end(%ebx), %esp + leal boot_stack_end@GOTOFF(%ebx), %esp /* Zero EFLAGS */ pushl $0 @@ -142,8 +125,8 @@ SYM_FUNC_START(startup_32) * where decompression in place becomes safe. */ pushl %esi - leal (_bss-4)(%edx), %esi - leal (_bss-4)(%ebx), %edi + leal (_bss@GOTOFF-4)(%edx), %esi + leal (_bss@GOTOFF-4)(%ebx), %edi movl $(_bss - startup_32), %ecx shrl $2, %ecx std @@ -156,14 +139,14 @@ SYM_FUNC_START(startup_32) * during extract_kernel below. To avoid any issues, repoint the GDTR * to the new copy of the GDT. */ - leal gdt(%ebx), %eax + leal gdt@GOTOFF(%ebx), %eax movl %eax, 2(%eax) lgdt (%eax) /* * Jump to the relocated address. */ - leal .Lrelocated(%ebx), %eax + leal .Lrelocated@GOTOFF(%ebx), %eax jmp *%eax SYM_FUNC_END(startup_32) @@ -173,7 +156,7 @@ SYM_FUNC_START_ALIAS(efi_stub_entry) add $0x4, %esp movl 8(%esp), %esi /* save boot_params pointer */ call efi_main - leal startup_32(%eax), %eax + /* efi_main returns the possibly relocated address of startup_32 */ jmp *%eax SYM_FUNC_END(efi32_stub_entry) SYM_FUNC_END_ALIAS(efi_stub_entry) @@ -186,40 +169,26 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated) * Clear BSS (stack is currently empty) */ xorl %eax, %eax - leal _bss(%ebx), %edi - leal _ebss(%ebx), %ecx + leal _bss@GOTOFF(%ebx), %edi + leal _ebss@GOTOFF(%ebx), %ecx subl %edi, %ecx shrl $2, %ecx rep stosl /* - * Adjust our own GOT - */ - leal _got(%ebx), %edx - leal _egot(%ebx), %ecx -1: - cmpl %ecx, %edx - jae 2f - addl %ebx, (%edx) - addl $4, %edx - jmp 1b -2: - -/* * Do the extraction, and jump to the new kernel.. */ - /* push arguments for extract_kernel: */ - pushl $z_output_len /* decompressed length, end of relocs */ - - pushl %ebp /* output address */ - - pushl $z_input_len /* input_len */ - leal input_data(%ebx), %eax - pushl %eax /* input_data */ - leal boot_heap(%ebx), %eax - pushl %eax /* heap area */ - pushl %esi /* real mode pointer */ - call extract_kernel /* returns kernel location in %eax */ + /* push arguments for extract_kernel: */ + + pushl output_len@GOTOFF(%ebx) /* decompressed length, end of relocs */ + pushl %ebp /* output address */ + pushl input_len@GOTOFF(%ebx) /* input_len */ + leal input_data@GOTOFF(%ebx), %eax + pushl %eax /* input_data */ + leal boot_heap@GOTOFF(%ebx), %eax + pushl %eax /* heap area */ + pushl %esi /* real mode pointer */ + call extract_kernel /* returns kernel location in %eax */ addl $24, %esp /* diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index 97d37f0a34f5..9e46729cf162 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -40,11 +40,35 @@ */ .hidden _bss .hidden _ebss - .hidden _got - .hidden _egot .hidden _end __HEAD + +/* + * This macro gives the relative virtual address of X, i.e. the offset of X + * from startup_32. This is the same as the link-time virtual address of X, + * since startup_32 is at 0, but defining it this way tells the + * assembler/linker that we do not want the actual run-time address of X. This + * prevents the linker from trying to create unwanted run-time relocation + * entries for the reference when the compressed kernel is linked as PIE. + * + * A reference X(%reg) will result in the link-time VA of X being stored with + * the instruction, and a run-time R_X86_64_RELATIVE relocation entry that + * adds the 64-bit base address where the kernel is loaded. + * + * Replacing it with (X-startup_32)(%reg) results in the offset being stored, + * and no run-time relocation. + * + * The macro should be used as a displacement with a base register containing + * the run-time address of startup_32 [i.e. rva(X)(%reg)], or as an immediate + * [$ rva(X)]. + * + * This macro can only be used from within the .head.text section, since the + * expression requires startup_32 to be in the same section as the code being + * assembled. + */ +#define rva(X) ((X) - startup_32) + .code32 SYM_FUNC_START(startup_32) /* @@ -67,10 +91,10 @@ SYM_FUNC_START(startup_32) leal (BP_scratch+4)(%esi), %esp call 1f 1: popl %ebp - subl $1b, %ebp + subl $ rva(1b), %ebp /* Load new GDT with the 64bit segments using 32bit descriptor */ - leal gdt(%ebp), %eax + leal rva(gdt)(%ebp), %eax movl %eax, 2(%eax) lgdt (%eax) @@ -83,7 +107,7 @@ SYM_FUNC_START(startup_32) movl %eax, %ss /* setup a stack and make sure cpu supports long mode. */ - leal boot_stack_end(%ebp), %esp + leal rva(boot_stack_end)(%ebp), %esp call verify_cpu testl %eax, %eax @@ -110,7 +134,7 @@ SYM_FUNC_START(startup_32) * image_offset = startup_32 - image_base * Otherwise image_offset will be zero and has no effect on the calculations. */ - subl image_offset(%ebp), %ebx + subl rva(image_offset)(%ebp), %ebx #endif movl BP_kernel_alignment(%esi), %eax @@ -126,7 +150,7 @@ SYM_FUNC_START(startup_32) /* Target address to relocate to for decompression */ addl BP_init_size(%esi), %ebx - subl $_end, %ebx + subl $ rva(_end), %ebx /* * Prepare for entering 64 bit mode @@ -154,19 +178,19 @@ SYM_FUNC_START(startup_32) 1: /* Initialize Page tables to 0 */ - leal pgtable(%ebx), %edi + leal rva(pgtable)(%ebx), %edi xorl %eax, %eax movl $(BOOT_INIT_PGT_SIZE/4), %ecx rep stosl /* Build Level 4 */ - leal pgtable + 0(%ebx), %edi + leal rva(pgtable + 0)(%ebx), %edi leal 0x1007 (%edi), %eax movl %eax, 0(%edi) addl %edx, 4(%edi) /* Build Level 3 */ - leal pgtable + 0x1000(%ebx), %edi + leal rva(pgtable + 0x1000)(%ebx), %edi leal 0x1007(%edi), %eax movl $4, %ecx 1: movl %eax, 0x00(%edi) @@ -177,7 +201,7 @@ SYM_FUNC_START(startup_32) jnz 1b /* Build Level 2 */ - leal pgtable + 0x2000(%ebx), %edi + leal rva(pgtable + 0x2000)(%ebx), %edi movl $0x00000183, %eax movl $2048, %ecx 1: movl %eax, 0(%edi) @@ -188,7 +212,7 @@ SYM_FUNC_START(startup_32) jnz 1b /* Enable the boot page tables */ - leal pgtable(%ebx), %eax + leal rva(pgtable)(%ebx), %eax movl %eax, %cr3 /* Enable Long mode in EFER (Extended Feature Enable Register) */ @@ -213,14 +237,14 @@ SYM_FUNC_START(startup_32) * We place all of the values on our mini stack so lret can * used to perform that far jump. */ - leal startup_64(%ebp), %eax + leal rva(startup_64)(%ebp), %eax #ifdef CONFIG_EFI_MIXED - movl efi32_boot_args(%ebp), %edi + movl rva(efi32_boot_args)(%ebp), %edi cmp $0, %edi jz 1f - leal efi64_stub_entry(%ebp), %eax - movl efi32_boot_args+4(%ebp), %esi - movl efi32_boot_args+8(%ebp), %edx // saved bootparams pointer + leal rva(efi64_stub_entry)(%ebp), %eax + movl rva(efi32_boot_args+4)(%ebp), %esi + movl rva(efi32_boot_args+8)(%ebp), %edx // saved bootparams pointer cmpl $0, %edx jnz 1f /* @@ -231,7 +255,7 @@ SYM_FUNC_START(startup_32) * the correct stack alignment for entry. */ subl $40, %esp - leal efi_pe_entry(%ebp), %eax + leal rva(efi_pe_entry)(%ebp), %eax movl %edi, %ecx // MS calling convention movl %esi, %edx 1: @@ -257,18 +281,18 @@ SYM_FUNC_START(efi32_stub_entry) call 1f 1: pop %ebp - subl $1b, %ebp + subl $ rva(1b), %ebp - movl %esi, efi32_boot_args+8(%ebp) + movl %esi, rva(efi32_boot_args+8)(%ebp) SYM_INNER_LABEL(efi32_pe_stub_entry, SYM_L_LOCAL) - movl %ecx, efi32_boot_args(%ebp) - movl %edx, efi32_boot_args+4(%ebp) - movb $0, efi_is64(%ebp) + movl %ecx, rva(efi32_boot_args)(%ebp) + movl %edx, rva(efi32_boot_args+4)(%ebp) + movb $0, rva(efi_is64)(%ebp) /* Save firmware GDTR and code/data selectors */ - sgdtl efi32_boot_gdt(%ebp) - movw %cs, efi32_boot_cs(%ebp) - movw %ds, efi32_boot_ds(%ebp) + sgdtl rva(efi32_boot_gdt)(%ebp) + movw %cs, rva(efi32_boot_cs)(%ebp) + movw %ds, rva(efi32_boot_ds)(%ebp) /* Disable paging */ movl %cr0, %eax @@ -347,30 +371,11 @@ SYM_CODE_START(startup_64) /* Target address to relocate to for decompression */ movl BP_init_size(%rsi), %ebx - subl $_end, %ebx + subl $ rva(_end), %ebx addq %rbp, %rbx /* Set up the stack */ - leaq boot_stack_end(%rbx), %rsp - - /* - * paging_prepare() and cleanup_trampoline() below can have GOT - * references. Adjust the table with address we are running at. - * - * Zero RAX for adjust_got: the GOT was not adjusted before; - * there's no adjustment to undo. - */ - xorq %rax, %rax - - /* - * Calculate the address the binary is loaded at and use it as - * a GOT adjustment. - */ - call 1f -1: popq %rdi - subq $1b, %rdi - - call .Ladjust_got + leaq rva(boot_stack_end)(%rbx), %rsp /* * At this point we are in long mode with 4-level paging enabled, @@ -444,7 +449,7 @@ SYM_CODE_START(startup_64) lretq trampoline_return: /* Restore the stack, the 32-bit trampoline uses its own stack */ - leaq boot_stack_end(%rbx), %rsp + leaq rva(boot_stack_end)(%rbx), %rsp /* * cleanup_trampoline() would restore trampoline memory. @@ -456,7 +461,7 @@ trampoline_return: * this function call. */ pushq %rsi - leaq top_pgtable(%rbx), %rdi + leaq rva(top_pgtable)(%rbx), %rdi call cleanup_trampoline popq %rsi @@ -464,30 +469,15 @@ trampoline_return: pushq $0 popfq - /* - * Previously we've adjusted the GOT with address the binary was - * loaded at. Now we need to re-adjust for relocation address. - * - * Calculate the address the binary is loaded at, so that we can - * undo the previous GOT adjustment. - */ - call 1f -1: popq %rax - subq $1b, %rax - - /* The new adjustment is the relocation address */ - movq %rbx, %rdi - call .Ladjust_got - /* * Copy the compressed kernel to the end of our buffer * where decompression in place becomes safe. */ pushq %rsi leaq (_bss-8)(%rip), %rsi - leaq (_bss-8)(%rbx), %rdi - movq $_bss /* - $startup_32 */, %rcx - shrq $3, %rcx + leaq rva(_bss-8)(%rbx), %rdi + movl $(_bss - startup_32), %ecx + shrl $3, %ecx std rep movsq cld @@ -498,15 +488,15 @@ trampoline_return: * during extract_kernel below. To avoid any issues, repoint the GDTR * to the new copy of the GDT. */ - leaq gdt64(%rbx), %rax - leaq gdt(%rbx), %rdx + leaq rva(gdt64)(%rbx), %rax + leaq rva(gdt)(%rbx), %rdx movq %rdx, 2(%rax) lgdt (%rax) /* * Jump to the relocated address. */ - leaq .Lrelocated(%rbx), %rax + leaq rva(.Lrelocated)(%rbx), %rax jmp *%rax SYM_CODE_END(startup_64) @@ -518,7 +508,7 @@ SYM_FUNC_START_ALIAS(efi_stub_entry) movq %rdx, %rbx /* save boot_params pointer */ call efi_main movq %rbx,%rsi - leaq startup_64(%rax), %rax + leaq rva(startup_64)(%rax), %rax jmp *%rax SYM_FUNC_END(efi64_stub_entry) SYM_FUNC_END_ALIAS(efi_stub_entry) @@ -544,9 +534,9 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated) movq %rsi, %rdi /* real mode address */ leaq boot_heap(%rip), %rsi /* malloc area for uncompression */ leaq input_data(%rip), %rdx /* input_data */ - movl $z_input_len, %ecx /* input_len */ + movl input_len(%rip), %ecx /* input_len */ movq %rbp, %r8 /* output target address */ - movl $z_output_len, %r9d /* decompressed length, end of relocs */ + movl output_len(%rip), %r9d /* decompressed length, end of relocs */ call extract_kernel /* returns kernel location in %rax */ popq %rsi @@ -556,27 +546,6 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated) jmp *%rax SYM_FUNC_END(.Lrelocated) -/* - * Adjust the global offset table - * - * RAX is the previous adjustment of the table to undo (use 0 if it's the - * first time we touch GOT). - * RDI is the new adjustment to apply. - */ -.Ladjust_got: - /* Walk through the GOT adding the address to the entries */ - leaq _got(%rip), %rdx - leaq _egot(%rip), %rcx -1: - cmpq %rcx, %rdx - jae 2f - subq %rax, (%rdx) /* Undo previous adjustment */ - addq %rdi, (%rdx) /* Apply the new adjustment */ - addq $8, %rdx - jmp 1b -2: - ret - .code32 /* * This is the 32-bit trampoline that will be copied over to low memory. @@ -702,7 +671,7 @@ SYM_DATA(efi_is64, .byte 1) #define BS32_handle_protocol 88 // offsetof(efi_boot_services_32_t, handle_protocol) #define LI32_image_base 32 // offsetof(efi_loaded_image_32_t, image_base) - .text + __HEAD .code32 SYM_FUNC_START(efi32_pe_entry) /* @@ -724,12 +693,12 @@ SYM_FUNC_START(efi32_pe_entry) call 1f 1: pop %ebx - subl $1b, %ebx + subl $ rva(1b), %ebx /* Get the loaded image protocol pointer from the image handle */ leal -4(%ebp), %eax pushl %eax // &loaded_image - leal loaded_image_proto(%ebx), %eax + leal rva(loaded_image_proto)(%ebx), %eax pushl %eax // pass the GUID address pushl 8(%ebp) // pass the image handle @@ -764,7 +733,7 @@ SYM_FUNC_START(efi32_pe_entry) * use it before we get to the 64-bit efi_pe_entry() in C code. */ subl %esi, %ebx - movl %ebx, image_offset(%ebp) // save image_offset + movl %ebx, rva(image_offset)(%ebp) // save image_offset jmp efi32_pe_stub_entry 2: popl %edi // restore callee-save registers diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index dde7cb3724df..877970d76249 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -36,6 +36,10 @@ #define STATIC #include <linux/decompress/mm.h> +#define _SETUP +#include <asm/setup.h> /* For COMMAND_LINE_SIZE */ +#undef _SETUP + #ifdef CONFIG_X86_5LEVEL unsigned int __pgtable_l5_enabled; unsigned int pgdir_shift __ro_after_init = 39; @@ -87,8 +91,11 @@ static unsigned long get_boot_seed(void) static bool memmap_too_large; -/* Store memory limit specified by "mem=nn[KMG]" or "memmap=nn[KMG]" */ -static unsigned long long mem_limit = ULLONG_MAX; +/* + * Store memory limit: MAXMEM on 64-bit and KERNEL_IMAGE_SIZE on 32-bit. + * It may be reduced by "mem=nn[KMG]" or "memmap=nn[KMG]" command line options. + */ +static u64 mem_limit; /* Number of immovable memory regions */ static int num_immovable_mem; @@ -131,8 +138,7 @@ enum parse_mode { }; static int -parse_memmap(char *p, unsigned long long *start, unsigned long long *size, - enum parse_mode mode) +parse_memmap(char *p, u64 *start, u64 *size, enum parse_mode mode) { char *oldp; @@ -162,7 +168,7 @@ parse_memmap(char *p, unsigned long long *start, unsigned long long *size, */ *size = 0; } else { - unsigned long long flags; + u64 flags; /* * efi_fake_mem=nn@ss:attr the attr specifies @@ -201,7 +207,7 @@ static void mem_avoid_memmap(enum parse_mode mode, char *str) while (str && (i < MAX_MEMMAP_REGIONS)) { int rc; - unsigned long long start, size; + u64 start, size; char *k = strchr(str, ','); if (k) @@ -214,7 +220,7 @@ static void mem_avoid_memmap(enum parse_mode mode, char *str) if (start == 0) { /* Store the specified memory limit if size > 0 */ - if (size > 0) + if (size > 0 && size < mem_limit) mem_limit = size; continue; @@ -261,15 +267,15 @@ static void parse_gb_huge_pages(char *param, char *val) static void handle_mem_options(void) { char *args = (char *)get_cmd_line_ptr(); - size_t len = strlen((char *)args); + size_t len; char *tmp_cmdline; char *param, *val; u64 mem_size; - if (!strstr(args, "memmap=") && !strstr(args, "mem=") && - !strstr(args, "hugepages")) + if (!args) return; + len = strnlen(args, COMMAND_LINE_SIZE-1); tmp_cmdline = malloc(len + 1); if (!tmp_cmdline) error("Failed to allocate space for tmp_cmdline"); @@ -284,14 +290,12 @@ static void handle_mem_options(void) while (*args) { args = next_arg(args, ¶m, &val); /* Stop at -- */ - if (!val && strcmp(param, "--") == 0) { - warn("Only '--' specified in cmdline"); - goto out; - } + if (!val && strcmp(param, "--") == 0) + break; if (!strcmp(param, "memmap")) { mem_avoid_memmap(PARSE_MEMMAP, val); - } else if (strstr(param, "hugepages")) { + } else if (IS_ENABLED(CONFIG_X86_64) && strstr(param, "hugepages")) { parse_gb_huge_pages(param, val); } else if (!strcmp(param, "mem")) { char *p = val; @@ -300,21 +304,23 @@ static void handle_mem_options(void) continue; mem_size = memparse(p, &p); if (mem_size == 0) - goto out; + break; - mem_limit = mem_size; + if (mem_size < mem_limit) + mem_limit = mem_size; } else if (!strcmp(param, "efi_fake_mem")) { mem_avoid_memmap(PARSE_EFI, val); } } -out: free(tmp_cmdline); return; } /* - * In theory, KASLR can put the kernel anywhere in the range of [16M, 64T). + * In theory, KASLR can put the kernel anywhere in the range of [16M, MAXMEM) + * on 64-bit, and [16M, KERNEL_IMAGE_SIZE) on 32-bit. + * * The mem_avoid array is used to store the ranges that need to be avoided * when KASLR searches for an appropriate random address. We must avoid any * regions that are unsafe to overlap with during decompression, and other @@ -392,8 +398,7 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size, { unsigned long init_size = boot_params->hdr.init_size; u64 initrd_start, initrd_size; - u64 cmd_line, cmd_line_size; - char *ptr; + unsigned long cmd_line, cmd_line_size; /* * Avoid the region that is unsafe to overlap during @@ -414,16 +419,15 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size, /* No need to set mapping for initrd, it will be handled in VO. */ /* Avoid kernel command line. */ - cmd_line = (u64)boot_params->ext_cmd_line_ptr << 32; - cmd_line |= boot_params->hdr.cmd_line_ptr; + cmd_line = get_cmd_line_ptr(); /* Calculate size of cmd_line. */ - ptr = (char *)(unsigned long)cmd_line; - for (cmd_line_size = 0; ptr[cmd_line_size++];) - ; - mem_avoid[MEM_AVOID_CMDLINE].start = cmd_line; - mem_avoid[MEM_AVOID_CMDLINE].size = cmd_line_size; - add_identity_map(mem_avoid[MEM_AVOID_CMDLINE].start, - mem_avoid[MEM_AVOID_CMDLINE].size); + if (cmd_line) { + cmd_line_size = strnlen((char *)cmd_line, COMMAND_LINE_SIZE-1) + 1; + mem_avoid[MEM_AVOID_CMDLINE].start = cmd_line; + mem_avoid[MEM_AVOID_CMDLINE].size = cmd_line_size; + add_identity_map(mem_avoid[MEM_AVOID_CMDLINE].start, + mem_avoid[MEM_AVOID_CMDLINE].size); + } /* Avoid boot parameters. */ mem_avoid[MEM_AVOID_BOOTPARAMS].start = (unsigned long)boot_params; @@ -454,7 +458,7 @@ static bool mem_avoid_overlap(struct mem_vector *img, { int i; struct setup_data *ptr; - unsigned long earliest = img->start + img->size; + u64 earliest = img->start + img->size; bool is_overlapping = false; for (i = 0; i < MEM_AVOID_MAX; i++) { @@ -499,18 +503,16 @@ static bool mem_avoid_overlap(struct mem_vector *img, } struct slot_area { - unsigned long addr; - int num; + u64 addr; + unsigned long num; }; #define MAX_SLOT_AREA 100 static struct slot_area slot_areas[MAX_SLOT_AREA]; - +static unsigned int slot_area_index; static unsigned long slot_max; -static unsigned long slot_area_index; - static void store_slot_info(struct mem_vector *region, unsigned long image_size) { struct slot_area slot_area; @@ -519,13 +521,10 @@ static void store_slot_info(struct mem_vector *region, unsigned long image_size) return; slot_area.addr = region->start; - slot_area.num = (region->size - image_size) / - CONFIG_PHYSICAL_ALIGN + 1; + slot_area.num = 1 + (region->size - image_size) / CONFIG_PHYSICAL_ALIGN; - if (slot_area.num > 0) { - slot_areas[slot_area_index++] = slot_area; - slot_max += slot_area.num; - } + slot_areas[slot_area_index++] = slot_area; + slot_max += slot_area.num; } /* @@ -535,57 +534,53 @@ static void store_slot_info(struct mem_vector *region, unsigned long image_size) static void process_gb_huge_pages(struct mem_vector *region, unsigned long image_size) { - unsigned long addr, size = 0; + u64 pud_start, pud_end; + unsigned long gb_huge_pages; struct mem_vector tmp; - int i = 0; - if (!max_gb_huge_pages) { + if (!IS_ENABLED(CONFIG_X86_64) || !max_gb_huge_pages) { store_slot_info(region, image_size); return; } - addr = ALIGN(region->start, PUD_SIZE); - /* Did we raise the address above the passed in memory entry? */ - if (addr < region->start + region->size) - size = region->size - (addr - region->start); - - /* Check how many 1GB huge pages can be filtered out: */ - while (size > PUD_SIZE && max_gb_huge_pages) { - size -= PUD_SIZE; - max_gb_huge_pages--; - i++; - } + /* Are there any 1GB pages in the region? */ + pud_start = ALIGN(region->start, PUD_SIZE); + pud_end = ALIGN_DOWN(region->start + region->size, PUD_SIZE); /* No good 1GB huge pages found: */ - if (!i) { + if (pud_start >= pud_end) { store_slot_info(region, image_size); return; } - /* - * Skip those 'i'*1GB good huge pages, and continue checking and - * processing the remaining head or tail part of the passed region - * if available. - */ - - if (addr >= region->start + image_size) { + /* Check if the head part of the region is usable. */ + if (pud_start >= region->start + image_size) { tmp.start = region->start; - tmp.size = addr - region->start; + tmp.size = pud_start - region->start; store_slot_info(&tmp, image_size); } - size = region->size - (addr - region->start) - i * PUD_SIZE; - if (size >= image_size) { - tmp.start = addr + i * PUD_SIZE; - tmp.size = size; + /* Skip the good 1GB pages. */ + gb_huge_pages = (pud_end - pud_start) >> PUD_SHIFT; + if (gb_huge_pages > max_gb_huge_pages) { + pud_end = pud_start + (max_gb_huge_pages << PUD_SHIFT); + max_gb_huge_pages = 0; + } else { + max_gb_huge_pages -= gb_huge_pages; + } + + /* Check if the tail part of the region is usable. */ + if (region->start + region->size >= pud_end + image_size) { + tmp.start = pud_end; + tmp.size = region->start + region->size - pud_end; store_slot_info(&tmp, image_size); } } -static unsigned long slots_fetch_random(void) +static u64 slots_fetch_random(void) { unsigned long slot; - int i; + unsigned int i; /* Handle case of no slots stored. */ if (slot_max == 0) @@ -598,7 +593,7 @@ static unsigned long slots_fetch_random(void) slot -= slot_areas[i].num; continue; } - return slot_areas[i].addr + slot * CONFIG_PHYSICAL_ALIGN; + return slot_areas[i].addr + ((u64)slot * CONFIG_PHYSICAL_ALIGN); } if (i == slot_area_index) @@ -611,49 +606,23 @@ static void __process_mem_region(struct mem_vector *entry, unsigned long image_size) { struct mem_vector region, overlap; - unsigned long start_orig, end; - struct mem_vector cur_entry; - - /* On 32-bit, ignore entries entirely above our maximum. */ - if (IS_ENABLED(CONFIG_X86_32) && entry->start >= KERNEL_IMAGE_SIZE) - return; + u64 region_end; - /* Ignore entries entirely below our minimum. */ - if (entry->start + entry->size < minimum) - return; - - /* Ignore entries above memory limit */ - end = min(entry->size + entry->start, mem_limit); - if (entry->start >= end) - return; - cur_entry.start = entry->start; - cur_entry.size = end - entry->start; - - region.start = cur_entry.start; - region.size = cur_entry.size; + /* Enforce minimum and memory limit. */ + region.start = max_t(u64, entry->start, minimum); + region_end = min(entry->start + entry->size, mem_limit); /* Give up if slot area array is full. */ while (slot_area_index < MAX_SLOT_AREA) { - start_orig = region.start; - - /* Potentially raise address to minimum location. */ - if (region.start < minimum) - region.start = minimum; - /* Potentially raise address to meet alignment needs. */ region.start = ALIGN(region.start, CONFIG_PHYSICAL_ALIGN); /* Did we raise the address above the passed in memory entry? */ - if (region.start > cur_entry.start + cur_entry.size) + if (region.start > region_end) return; /* Reduce size by any delta from the original address. */ - region.size -= region.start - start_orig; - - /* On 32-bit, reduce region size to fit within max size. */ - if (IS_ENABLED(CONFIG_X86_32) && - region.start + region.size > KERNEL_IMAGE_SIZE) - region.size = KERNEL_IMAGE_SIZE - region.start; + region.size = region_end - region.start; /* Return if region can't contain decompressed kernel */ if (region.size < image_size) @@ -666,27 +635,19 @@ static void __process_mem_region(struct mem_vector *entry, } /* Store beginning of region if holds at least image_size. */ - if (overlap.start > region.start + image_size) { - struct mem_vector beginning; - - beginning.start = region.start; - beginning.size = overlap.start - region.start; - process_gb_huge_pages(&beginning, image_size); + if (overlap.start >= region.start + image_size) { + region.size = overlap.start - region.start; + process_gb_huge_pages(®ion, image_size); } - /* Return if overlap extends to or past end of region. */ - if (overlap.start + overlap.size >= region.start + region.size) - return; - /* Clip off the overlapping region and start over. */ - region.size -= overlap.start - region.start + overlap.size; region.start = overlap.start + overlap.size; } } static bool process_mem_region(struct mem_vector *region, - unsigned long long minimum, - unsigned long long image_size) + unsigned long minimum, + unsigned long image_size) { int i; /* @@ -709,7 +670,7 @@ static bool process_mem_region(struct mem_vector *region, * immovable memory and @region. */ for (i = 0; i < num_immovable_mem; i++) { - unsigned long long start, end, entry_end, region_end; + u64 start, end, entry_end, region_end; struct mem_vector entry; if (!mem_overlaps(region, &immovable_mem[i])) @@ -736,8 +697,8 @@ static bool process_mem_region(struct mem_vector *region, #ifdef CONFIG_EFI /* - * Returns true if mirror region found (and must have been processed - * for slots adding) + * Returns true if we processed the EFI memmap, which we prefer over the E820 + * table if it is available. */ static bool process_efi_entries(unsigned long minimum, unsigned long image_size) @@ -839,20 +800,30 @@ static void process_e820_entries(unsigned long minimum, static unsigned long find_random_phys_addr(unsigned long minimum, unsigned long image_size) { + u64 phys_addr; + + /* Bail out early if it's impossible to succeed. */ + if (minimum + image_size > mem_limit) + return 0; + /* Check if we had too many memmaps. */ if (memmap_too_large) { debug_putstr("Aborted memory entries scan (more than 4 memmap= args)!\n"); return 0; } - /* Make sure minimum is aligned. */ - minimum = ALIGN(minimum, CONFIG_PHYSICAL_ALIGN); + if (!process_efi_entries(minimum, image_size)) + process_e820_entries(minimum, image_size); - if (process_efi_entries(minimum, image_size)) - return slots_fetch_random(); + phys_addr = slots_fetch_random(); - process_e820_entries(minimum, image_size); - return slots_fetch_random(); + /* Perform a final check to make sure the address is in range. */ + if (phys_addr < minimum || phys_addr + image_size > mem_limit) { + warn("Invalid physical address chosen!\n"); + return 0; + } + + return (unsigned long)phys_addr; } static unsigned long find_random_virt_addr(unsigned long minimum, @@ -860,18 +831,12 @@ static unsigned long find_random_virt_addr(unsigned long minimum, { unsigned long slots, random_addr; - /* Make sure minimum is aligned. */ - minimum = ALIGN(minimum, CONFIG_PHYSICAL_ALIGN); - /* Align image_size for easy slot calculations. */ - image_size = ALIGN(image_size, CONFIG_PHYSICAL_ALIGN); - /* * There are how many CONFIG_PHYSICAL_ALIGN-sized slots * that can hold image_size within the range of minimum to * KERNEL_IMAGE_SIZE? */ - slots = (KERNEL_IMAGE_SIZE - minimum - image_size) / - CONFIG_PHYSICAL_ALIGN + 1; + slots = 1 + (KERNEL_IMAGE_SIZE - minimum - image_size) / CONFIG_PHYSICAL_ALIGN; random_addr = kaslr_get_random_long("Virtual") % slots; @@ -908,6 +873,11 @@ void choose_random_location(unsigned long input, /* Prepare to add new identity pagetables on demand. */ initialize_identity_maps(); + if (IS_ENABLED(CONFIG_X86_32)) + mem_limit = KERNEL_IMAGE_SIZE; + else + mem_limit = MAXMEM; + /* Record the various known unsafe memory ranges. */ mem_avoid_init(input, input_size, *output); @@ -917,6 +887,8 @@ void choose_random_location(unsigned long input, * location: */ min_addr = min(*output, 512UL << 20); + /* Make sure minimum is aligned. */ + min_addr = ALIGN(min_addr, CONFIG_PHYSICAL_ALIGN); /* Walk available memory entries to find a random address. */ random_addr = find_random_phys_addr(min_addr, output_size); diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 726e264410ff..3efce27ba35c 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -70,8 +70,8 @@ int cmdline_find_option(const char *option, char *buffer, int bufsize); int cmdline_find_option_bool(const char *option); struct mem_vector { - unsigned long long start; - unsigned long long size; + u64 start; + u64 size; }; #if CONFIG_RANDOMIZE_BASE diff --git a/arch/x86/boot/compressed/mkpiggy.c b/arch/x86/boot/compressed/mkpiggy.c index 7e01248765b2..52aa56cdbacc 100644 --- a/arch/x86/boot/compressed/mkpiggy.c +++ b/arch/x86/boot/compressed/mkpiggy.c @@ -60,6 +60,12 @@ int main(int argc, char *argv[]) printf(".incbin \"%s\"\n", argv[1]); printf("input_data_end:\n"); + printf(".section \".rodata\",\"a\",@progbits\n"); + printf(".globl input_len\n"); + printf("input_len:\n\t.long %lu\n", ilen); + printf(".globl output_len\n"); + printf("output_len:\n\t.long %lu\n", (unsigned long)olen); + retval = 0; bail: if (f) diff --git a/arch/x86/boot/compressed/vmlinux.lds.S b/arch/x86/boot/compressed/vmlinux.lds.S index 8f1025d1f681..112b2375d021 100644 --- a/arch/x86/boot/compressed/vmlinux.lds.S +++ b/arch/x86/boot/compressed/vmlinux.lds.S @@ -42,12 +42,6 @@ SECTIONS *(.rodata.*) _erodata = . ; } - .got : { - _got = .; - KEEP(*(.got.plt)) - KEEP(*(.got)) - _egot = .; - } .data : { _data = . ; *(.data) @@ -75,5 +69,49 @@ SECTIONS . = ALIGN(PAGE_SIZE); /* keep ZO size page aligned */ _end = .; + STABS_DEBUG + DWARF_DEBUG + ELF_DETAILS + DISCARDS + /DISCARD/ : { + *(.dynamic) *(.dynsym) *(.dynstr) *(.dynbss) + *(.hash) *(.gnu.hash) + *(.note.*) + } + + .got.plt (INFO) : { + *(.got.plt) + } + ASSERT(SIZEOF(.got.plt) == 0 || +#ifdef CONFIG_X86_64 + SIZEOF(.got.plt) == 0x18, +#else + SIZEOF(.got.plt) == 0xc, +#endif + "Unexpected GOT/PLT entries detected!") + + /* + * Sections that should stay zero sized, which is safer to + * explicitly check instead of blindly discarding. + */ + .got : { + *(.got) + } + ASSERT(SIZEOF(.got) == 0, "Unexpected GOT entries detected!") + + .plt : { + *(.plt) *(.plt.*) + } + ASSERT(SIZEOF(.plt) == 0, "Unexpected run-time procedure linkages detected!") + + .rel.dyn : { + *(.rel.*) *(.rel_*) + } + ASSERT(SIZEOF(.rel.dyn) == 0, "Unexpected run-time relocations (.rel) detected!") + + .rela.dyn : { + *(.rela.*) *(.rela_*) + } + ASSERT(SIZEOF(.rela.dyn) == 0, "Unexpected run-time relocations (.rela) detected!") } diff --git a/arch/x86/boot/setup.ld b/arch/x86/boot/setup.ld index 24c95522f231..49546c247ae2 100644 --- a/arch/x86/boot/setup.ld +++ b/arch/x86/boot/setup.ld @@ -20,7 +20,7 @@ SECTIONS .initdata : { *(.initdata) } __end_init = .; - .text : { *(.text) } + .text : { *(.text .text.*) } .text32 : { *(.text32) } . = ALIGN(16); diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c index c8b8c1a8d1fc..a3725ad46c5a 100644 --- a/arch/x86/boot/tools/build.c +++ b/arch/x86/boot/tools/build.c @@ -416,8 +416,6 @@ int main(int argc, char ** argv) /* Set the default root device */ put_unaligned_le16(DEFAULT_ROOT_DEV, &buf[508]); - printf("Setup is %d bytes (padded to %d bytes).\n", c, i); - /* Open and stat the kernel file */ fd = open(argv[2], O_RDONLY); if (fd < 0) @@ -425,7 +423,6 @@ int main(int argc, char ** argv) if (fstat(fd, &sb)) die("Unable to stat `%s': %m", argv[2]); sz = sb.st_size; - printf("System is %d kB\n", (sz+1023)/1024); kernel = mmap(NULL, sz, PROT_READ, MAP_SHARED, fd, 0); if (kernel == MAP_FAILED) die("Unable to mmap '%s': %m", argv[2]); @@ -488,7 +485,6 @@ int main(int argc, char ** argv) } /* Write the CRC */ - printf("CRC %x\n", crc); put_unaligned_le32(crc, buf); if (fwrite(buf, 1, 4, dest) != 4) die("Writing CRC failed"); diff --git a/arch/x86/crypto/blake2s-glue.c b/arch/x86/crypto/blake2s-glue.c index 6737bcea1fa1..c025a01cf708 100644 --- a/arch/x86/crypto/blake2s-glue.c +++ b/arch/x86/crypto/blake2s-glue.c @@ -11,6 +11,7 @@ #include <linux/jump_label.h> #include <linux/kernel.h> #include <linux/module.h> +#include <linux/sizes.h> #include <asm/cpufeature.h> #include <asm/fpu/api.h> diff --git a/arch/x86/crypto/chacha_glue.c b/arch/x86/crypto/chacha_glue.c index e67a59130025..7b3a1cf0984b 100644 --- a/arch/x86/crypto/chacha_glue.c +++ b/arch/x86/crypto/chacha_glue.c @@ -12,6 +12,7 @@ #include <crypto/internal/skcipher.h> #include <linux/kernel.h> #include <linux/module.h> +#include <linux/sizes.h> #include <asm/simd.h> asmlinkage void chacha_block_xor_ssse3(u32 *state, u8 *dst, const u8 *src, diff --git a/arch/x86/crypto/crc32c-intel_glue.c b/arch/x86/crypto/crc32c-intel_glue.c index d2d069bd459b..feccb5254c7e 100644 --- a/arch/x86/crypto/crc32c-intel_glue.c +++ b/arch/x86/crypto/crc32c-intel_glue.c @@ -28,9 +28,9 @@ #define SCALE_F sizeof(unsigned long) #ifdef CONFIG_X86_64 -#define REX_PRE "0x48, " +#define CRC32_INST "crc32q %1, %q0" #else -#define REX_PRE +#define CRC32_INST "crc32l %1, %0" #endif #ifdef CONFIG_X86_64 @@ -48,11 +48,8 @@ asmlinkage unsigned int crc_pcl(const u8 *buffer, int len, static u32 crc32c_intel_le_hw_byte(u32 crc, unsigned char const *data, size_t length) { while (length--) { - __asm__ __volatile__( - ".byte 0xf2, 0xf, 0x38, 0xf0, 0xf1" - :"=S"(crc) - :"0"(crc), "c"(*data) - ); + asm("crc32b %1, %0" + : "+r" (crc) : "rm" (*data)); data++; } @@ -66,11 +63,8 @@ static u32 __pure crc32c_intel_le_hw(u32 crc, unsigned char const *p, size_t len unsigned long *ptmp = (unsigned long *)p; while (iquotient--) { - __asm__ __volatile__( - ".byte 0xf2, " REX_PRE "0xf, 0x38, 0xf1, 0xf1;" - :"=S"(crc) - :"0"(crc), "c"(*ptmp) - ); + asm(CRC32_INST + : "+r" (crc) : "rm" (*ptmp)); ptmp++; } diff --git a/arch/x86/crypto/curve25519-x86_64.c b/arch/x86/crypto/curve25519-x86_64.c index 8acbb6584a37..5af8021b98ce 100644 --- a/arch/x86/crypto/curve25519-x86_64.c +++ b/arch/x86/crypto/curve25519-x86_64.c @@ -11,6 +11,7 @@ #include <linux/jump_label.h> #include <linux/kernel.h> #include <linux/module.h> +#include <linux/scatterlist.h> #include <asm/cpufeature.h> #include <asm/processor.h> @@ -45,11 +46,11 @@ static inline u64 add_scalar(u64 *out, const u64 *f1, u64 f2) asm volatile( /* Clear registers to propagate the carry bit */ - " xor %%r8, %%r8;" - " xor %%r9, %%r9;" - " xor %%r10, %%r10;" - " xor %%r11, %%r11;" - " xor %1, %1;" + " xor %%r8d, %%r8d;" + " xor %%r9d, %%r9d;" + " xor %%r10d, %%r10d;" + " xor %%r11d, %%r11d;" + " xor %k1, %k1;" /* Begin addition chain */ " addq 0(%3), %0;" @@ -93,7 +94,7 @@ static inline void fadd(u64 *out, const u64 *f1, const u64 *f2) " cmovc %0, %%rax;" /* Step 2: Add carry*38 to the original sum */ - " xor %%rcx, %%rcx;" + " xor %%ecx, %%ecx;" " add %%rax, %%r8;" " adcx %%rcx, %%r9;" " movq %%r9, 8(%1);" @@ -165,28 +166,28 @@ static inline void fmul(u64 *out, const u64 *f1, const u64 *f2, u64 *tmp) /* Compute src1[0] * src2 */ " movq 0(%1), %%rdx;" - " mulxq 0(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " movq %%r8, 0(%0);" + " mulxq 0(%3), %%r8, %%r9;" " xor %%r10d, %%r10d;" " movq %%r8, 0(%0);" " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " movq %%r10, 8(%0);" " mulxq 16(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" " mulxq 24(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " mov $0, %%rax;" " adox %%rdx, %%rax;" /* Compute src1[1] * src2 */ " movq 8(%1), %%rdx;" - " mulxq 0(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " adcxq 8(%0), %%r8;" " movq %%r8, 8(%0);" + " mulxq 0(%3), %%r8, %%r9;" " xor %%r10d, %%r10d;" " adcxq 8(%0), %%r8;" " movq %%r8, 8(%0);" " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 16(%0);" " mulxq 16(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " mov $0, %%r8;" " mulxq 24(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " mov $0, %%rax;" " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" /* Compute src1[2] * src2 */ " movq 16(%1), %%rdx;" - " mulxq 0(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " adcxq 16(%0), %%r8;" " movq %%r8, 16(%0);" + " mulxq 0(%3), %%r8, %%r9;" " xor %%r10d, %%r10d;" " adcxq 16(%0), %%r8;" " movq %%r8, 16(%0);" " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 24(%0);" " mulxq 16(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " mov $0, %%r8;" " mulxq 24(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " mov $0, %%rax;" " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" /* Compute src1[3] * src2 */ " movq 24(%1), %%rdx;" - " mulxq 0(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " adcxq 24(%0), %%r8;" " movq %%r8, 24(%0);" + " mulxq 0(%3), %%r8, %%r9;" " xor %%r10d, %%r10d;" " adcxq 24(%0), %%r8;" " movq %%r8, 24(%0);" " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 32(%0);" " mulxq 16(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " movq %%rbx, 40(%0);" " mov $0, %%r8;" " mulxq 24(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " movq %%r14, 48(%0);" " mov $0, %%rax;" @@ -200,7 +201,7 @@ static inline void fmul(u64 *out, const u64 *f1, const u64 *f2, u64 *tmp) /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */ " mov $38, %%rdx;" " mulxq 32(%1), %%r8, %%r13;" - " xor %3, %3;" + " xor %k3, %k3;" " adoxq 0(%1), %%r8;" " mulxq 40(%1), %%r9, %%rbx;" " adcx %%r13, %%r9;" @@ -246,28 +247,28 @@ static inline void fmul2(u64 *out, const u64 *f1, const u64 *f2, u64 *tmp) /* Compute src1[0] * src2 */ " movq 0(%1), %%rdx;" - " mulxq 0(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " movq %%r8, 0(%0);" + " mulxq 0(%3), %%r8, %%r9;" " xor %%r10d, %%r10d;" " movq %%r8, 0(%0);" " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " movq %%r10, 8(%0);" " mulxq 16(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" " mulxq 24(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " mov $0, %%rax;" " adox %%rdx, %%rax;" /* Compute src1[1] * src2 */ " movq 8(%1), %%rdx;" - " mulxq 0(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " adcxq 8(%0), %%r8;" " movq %%r8, 8(%0);" + " mulxq 0(%3), %%r8, %%r9;" " xor %%r10d, %%r10d;" " adcxq 8(%0), %%r8;" " movq %%r8, 8(%0);" " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 16(%0);" " mulxq 16(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " mov $0, %%r8;" " mulxq 24(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " mov $0, %%rax;" " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" /* Compute src1[2] * src2 */ " movq 16(%1), %%rdx;" - " mulxq 0(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " adcxq 16(%0), %%r8;" " movq %%r8, 16(%0);" + " mulxq 0(%3), %%r8, %%r9;" " xor %%r10d, %%r10d;" " adcxq 16(%0), %%r8;" " movq %%r8, 16(%0);" " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 24(%0);" " mulxq 16(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " mov $0, %%r8;" " mulxq 24(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " mov $0, %%rax;" " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" /* Compute src1[3] * src2 */ " movq 24(%1), %%rdx;" - " mulxq 0(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " adcxq 24(%0), %%r8;" " movq %%r8, 24(%0);" + " mulxq 0(%3), %%r8, %%r9;" " xor %%r10d, %%r10d;" " adcxq 24(%0), %%r8;" " movq %%r8, 24(%0);" " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 32(%0);" " mulxq 16(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " movq %%rbx, 40(%0);" " mov $0, %%r8;" " mulxq 24(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " movq %%r14, 48(%0);" " mov $0, %%rax;" @@ -277,29 +278,29 @@ static inline void fmul2(u64 *out, const u64 *f1, const u64 *f2, u64 *tmp) /* Compute src1[0] * src2 */ " movq 32(%1), %%rdx;" - " mulxq 32(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " movq %%r8, 64(%0);" - " mulxq 40(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " movq %%r10, 72(%0);" + " mulxq 32(%3), %%r8, %%r9;" " xor %%r10d, %%r10d;" " movq %%r8, 64(%0);" + " mulxq 40(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " movq %%r10, 72(%0);" " mulxq 48(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" " mulxq 56(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " mov $0, %%rax;" " adox %%rdx, %%rax;" /* Compute src1[1] * src2 */ " movq 40(%1), %%rdx;" - " mulxq 32(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " adcxq 72(%0), %%r8;" " movq %%r8, 72(%0);" - " mulxq 40(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 80(%0);" + " mulxq 32(%3), %%r8, %%r9;" " xor %%r10d, %%r10d;" " adcxq 72(%0), %%r8;" " movq %%r8, 72(%0);" + " mulxq 40(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 80(%0);" " mulxq 48(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " mov $0, %%r8;" " mulxq 56(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " mov $0, %%rax;" " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" /* Compute src1[2] * src2 */ " movq 48(%1), %%rdx;" - " mulxq 32(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " adcxq 80(%0), %%r8;" " movq %%r8, 80(%0);" - " mulxq 40(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 88(%0);" + " mulxq 32(%3), %%r8, %%r9;" " xor %%r10d, %%r10d;" " adcxq 80(%0), %%r8;" " movq %%r8, 80(%0);" + " mulxq 40(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 88(%0);" " mulxq 48(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " mov $0, %%r8;" " mulxq 56(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " mov $0, %%rax;" " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" /* Compute src1[3] * src2 */ " movq 56(%1), %%rdx;" - " mulxq 32(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " adcxq 88(%0), %%r8;" " movq %%r8, 88(%0);" - " mulxq 40(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 96(%0);" + " mulxq 32(%3), %%r8, %%r9;" " xor %%r10d, %%r10d;" " adcxq 88(%0), %%r8;" " movq %%r8, 88(%0);" + " mulxq 40(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 96(%0);" " mulxq 48(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " movq %%rbx, 104(%0);" " mov $0, %%r8;" " mulxq 56(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " movq %%r14, 112(%0);" " mov $0, %%rax;" " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" " movq %%rax, 120(%0);" @@ -312,7 +313,7 @@ static inline void fmul2(u64 *out, const u64 *f1, const u64 *f2, u64 *tmp) /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */ " mov $38, %%rdx;" " mulxq 32(%1), %%r8, %%r13;" - " xor %3, %3;" + " xor %k3, %k3;" " adoxq 0(%1), %%r8;" " mulxq 40(%1), %%r9, %%rbx;" " adcx %%r13, %%r9;" @@ -345,7 +346,7 @@ static inline void fmul2(u64 *out, const u64 *f1, const u64 *f2, u64 *tmp) /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */ " mov $38, %%rdx;" " mulxq 96(%1), %%r8, %%r13;" - " xor %3, %3;" + " xor %k3, %k3;" " adoxq 64(%1), %%r8;" " mulxq 104(%1), %%r9, %%rbx;" " adcx %%r13, %%r9;" @@ -516,7 +517,7 @@ static inline void fsqr(u64 *out, const u64 *f, u64 *tmp) /* Step 1: Compute all partial products */ " movq 0(%1), %%rdx;" /* f[0] */ - " mulxq 8(%1), %%r8, %%r14;" " xor %%r15, %%r15;" /* f[1]*f[0] */ + " mulxq 8(%1), %%r8, %%r14;" " xor %%r15d, %%r15d;" /* f[1]*f[0] */ " mulxq 16(%1), %%r9, %%r10;" " adcx %%r14, %%r9;" /* f[2]*f[0] */ " mulxq 24(%1), %%rax, %%rcx;" " adcx %%rax, %%r10;" /* f[3]*f[0] */ " movq 24(%1), %%rdx;" /* f[3] */ @@ -526,7 +527,7 @@ static inline void fsqr(u64 *out, const u64 *f, u64 *tmp) " mulxq 16(%1), %%rax, %%rcx;" " mov $0, %%r14;" /* f[2]*f[1] */ /* Step 2: Compute two parallel carry chains */ - " xor %%r15, %%r15;" + " xor %%r15d, %%r15d;" " adox %%rax, %%r10;" " adcx %%r8, %%r8;" " adox %%rcx, %%r11;" @@ -563,7 +564,7 @@ static inline void fsqr(u64 *out, const u64 *f, u64 *tmp) /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */ " mov $38, %%rdx;" " mulxq 32(%1), %%r8, %%r13;" - " xor %%rcx, %%rcx;" + " xor %%ecx, %%ecx;" " adoxq 0(%1), %%r8;" " mulxq 40(%1), %%r9, %%rbx;" " adcx %%r13, %%r9;" @@ -607,7 +608,7 @@ static inline void fsqr2(u64 *out, const u64 *f, u64 *tmp) asm volatile( /* Step 1: Compute all partial products */ " movq 0(%1), %%rdx;" /* f[0] */ - " mulxq 8(%1), %%r8, %%r14;" " xor %%r15, %%r15;" /* f[1]*f[0] */ + " mulxq 8(%1), %%r8, %%r14;" " xor %%r15d, %%r15d;" /* f[1]*f[0] */ " mulxq 16(%1), %%r9, %%r10;" " adcx %%r14, %%r9;" /* f[2]*f[0] */ " mulxq 24(%1), %%rax, %%rcx;" " adcx %%rax, %%r10;" /* f[3]*f[0] */ " movq 24(%1), %%rdx;" /* f[3] */ @@ -617,7 +618,7 @@ static inline void fsqr2(u64 *out, const u64 *f, u64 *tmp) " mulxq 16(%1), %%rax, %%rcx;" " mov $0, %%r14;" /* f[2]*f[1] */ /* Step 2: Compute two parallel carry chains */ - " xor %%r15, %%r15;" + " xor %%r15d, %%r15d;" " adox %%rax, %%r10;" " adcx %%r8, %%r8;" " adox %%rcx, %%r11;" @@ -647,7 +648,7 @@ static inline void fsqr2(u64 *out, const u64 *f, u64 *tmp) /* Step 1: Compute all partial products */ " movq 32(%1), %%rdx;" /* f[0] */ - " mulxq 40(%1), %%r8, %%r14;" " xor %%r15, %%r15;" /* f[1]*f[0] */ + " mulxq 40(%1), %%r8, %%r14;" " xor %%r15d, %%r15d;" /* f[1]*f[0] */ " mulxq 48(%1), %%r9, %%r10;" " adcx %%r14, %%r9;" /* f[2]*f[0] */ " mulxq 56(%1), %%rax, %%rcx;" " adcx %%rax, %%r10;" /* f[3]*f[0] */ " movq 56(%1), %%rdx;" /* f[3] */ @@ -657,7 +658,7 @@ static inline void fsqr2(u64 *out, const u64 *f, u64 *tmp) " mulxq 48(%1), %%rax, %%rcx;" " mov $0, %%r14;" /* f[2]*f[1] */ /* Step 2: Compute two parallel carry chains */ - " xor %%r15, %%r15;" + " xor %%r15d, %%r15d;" " adox %%rax, %%r10;" " adcx %%r8, %%r8;" " adox %%rcx, %%r11;" @@ -692,7 +693,7 @@ static inline void fsqr2(u64 *out, const u64 *f, u64 *tmp) /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */ " mov $38, %%rdx;" " mulxq 32(%1), %%r8, %%r13;" - " xor %%rcx, %%rcx;" + " xor %%ecx, %%ecx;" " adoxq 0(%1), %%r8;" " mulxq 40(%1), %%r9, %%rbx;" " adcx %%r13, %%r9;" @@ -725,7 +726,7 @@ static inline void fsqr2(u64 *out, const u64 *f, u64 *tmp) /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */ " mov $38, %%rdx;" " mulxq 96(%1), %%r8, %%r13;" - " xor %%rcx, %%rcx;" + " xor %%ecx, %%ecx;" " adoxq 64(%1), %%r8;" " mulxq 104(%1), %%r9, %%rbx;" " adcx %%r13, %%r9;" diff --git a/arch/x86/crypto/nhpoly1305-avx2-glue.c b/arch/x86/crypto/nhpoly1305-avx2-glue.c index 80fcb85736e1..8ea5ab0f1ca7 100644 --- a/arch/x86/crypto/nhpoly1305-avx2-glue.c +++ b/arch/x86/crypto/nhpoly1305-avx2-glue.c @@ -10,6 +10,7 @@ #include <crypto/internal/simd.h> #include <crypto/nhpoly1305.h> #include <linux/module.h> +#include <linux/sizes.h> #include <asm/simd.h> asmlinkage void nh_avx2(const u32 *key, const u8 *message, size_t message_len, diff --git a/arch/x86/crypto/nhpoly1305-sse2-glue.c b/arch/x86/crypto/nhpoly1305-sse2-glue.c index cc6b7c1a2705..2b353d42ed13 100644 --- a/arch/x86/crypto/nhpoly1305-sse2-glue.c +++ b/arch/x86/crypto/nhpoly1305-sse2-glue.c @@ -10,6 +10,7 @@ #include <crypto/internal/simd.h> #include <crypto/nhpoly1305.h> #include <linux/module.h> +#include <linux/sizes.h> #include <asm/simd.h> asmlinkage void nh_sse2(const u32 *key, const u8 *message, size_t message_len, diff --git a/arch/x86/crypto/poly1305-x86_64-cryptogams.pl b/arch/x86/crypto/poly1305-x86_64-cryptogams.pl index 137edcf038cb..7d568012cc15 100644 --- a/arch/x86/crypto/poly1305-x86_64-cryptogams.pl +++ b/arch/x86/crypto/poly1305-x86_64-cryptogams.pl @@ -246,7 +246,7 @@ $code.=<<___ if (!$kernel); ___ &declare_function("poly1305_init_x86_64", 32, 3); $code.=<<___; - xor %rax,%rax + xor %eax,%eax mov %rax,0($ctx) # initialize hash value mov %rax,8($ctx) mov %rax,16($ctx) @@ -2853,7 +2853,7 @@ $code.=<<___; .type poly1305_init_base2_44,\@function,3 .align 32 poly1305_init_base2_44: - xor %rax,%rax + xor %eax,%eax mov %rax,0($ctx) # initialize hash value mov %rax,8($ctx) mov %rax,16($ctx) @@ -3947,7 +3947,7 @@ xor128_decrypt_n_pad: mov \$16,$len sub %r10,$len xor %eax,%eax - xor %r11,%r11 + xor %r11d,%r11d .Loop_dec_byte: mov ($inp,$otp),%r11b mov ($otp),%al @@ -4085,7 +4085,7 @@ avx_handler: .long 0xa548f3fc # cld; rep movsq mov $disp,%rsi - xor %rcx,%rcx # arg1, UNW_FLAG_NHANDLER + xor %ecx,%ecx # arg1, UNW_FLAG_NHANDLER mov 8(%rsi),%rdx # arg2, disp->ImageBase mov 0(%rsi),%r8 # arg3, disp->ControlPc mov 16(%rsi),%r9 # arg4, disp->FunctionEntry diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c index dfe921efa9b2..e508dbd91813 100644 --- a/arch/x86/crypto/poly1305_glue.c +++ b/arch/x86/crypto/poly1305_glue.c @@ -11,6 +11,7 @@ #include <linux/jump_label.h> #include <linux/kernel.h> #include <linux/module.h> +#include <linux/sizes.h> #include <asm/intel-family.h> #include <asm/simd.h> @@ -157,9 +158,6 @@ static unsigned int crypto_poly1305_setdctxkey(struct poly1305_desc_ctx *dctx, dctx->s[1] = get_unaligned_le32(&inp[4]); dctx->s[2] = get_unaligned_le32(&inp[8]); dctx->s[3] = get_unaligned_le32(&inp[12]); - inp += POLY1305_BLOCK_SIZE; - len -= POLY1305_BLOCK_SIZE; - acc += POLY1305_BLOCK_SIZE; dctx->sset = true; } } diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index ae9b0d4615b3..07a9331d55e7 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -6,7 +6,6 @@ #include <asm/percpu.h> #include <asm/asm-offsets.h> #include <asm/processor-flags.h> -#include <asm/inst.h> /* diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index d977079a7d02..826e73488308 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -46,13 +46,13 @@ .code64 .section .entry.text, "ax" -#ifdef CONFIG_PARAVIRT +#ifdef CONFIG_PARAVIRT_XXL SYM_CODE_START(native_usergs_sysret64) UNWIND_HINT_EMPTY swapgs sysretq SYM_CODE_END(native_usergs_sysret64) -#endif /* CONFIG_PARAVIRT */ +#endif /* CONFIG_PARAVIRT_XXL */ /* * 64-bit SYSCALL instruction entry. Up to 6 arguments in registers. @@ -842,8 +842,9 @@ SYM_CODE_START_LOCAL(paranoid_entry) * retrieve and set the current CPUs kernel GSBASE. The stored value * has to be restored in paranoid_exit unconditionally. * - * The MSR write ensures that no subsequent load is based on a - * mispredicted GSBASE. No extra FENCE required. + * The unconditional write to GS base below ensures that no subsequent + * loads based on a mispredicted GS base can happen, therefore no LFENCE + * is needed here. */ SAVE_AND_SET_GSBASE scratch_reg=%rax save_reg=%rbx ret diff --git a/arch/x86/entry/syscall_x32.c b/arch/x86/entry/syscall_x32.c index 1583831f61a9..f2fe0a33bcfd 100644 --- a/arch/x86/entry/syscall_x32.c +++ b/arch/x86/entry/syscall_x32.c @@ -12,8 +12,13 @@ * Reuse the 64-bit entry points for the x32 versions that occupy different * slots in the syscall table. */ +#define __x32_sys_readv __x64_sys_readv +#define __x32_sys_writev __x64_sys_writev #define __x32_sys_getsockopt __x64_sys_getsockopt #define __x32_sys_setsockopt __x64_sys_setsockopt +#define __x32_sys_vmsplice __x64_sys_vmsplice +#define __x32_sys_process_vm_readv __x64_sys_process_vm_readv +#define __x32_sys_process_vm_writev __x64_sys_process_vm_writev #define __SYSCALL_64(nr, sym) diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 9d1102873666..9b6931f8d555 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -32,7 +32,7 @@ 18 i386 oldstat sys_stat 19 i386 lseek sys_lseek compat_sys_lseek 20 i386 getpid sys_getpid -21 i386 mount sys_mount compat_sys_mount +21 i386 mount sys_mount 22 i386 umount sys_oldumount 23 i386 setuid sys_setuid16 24 i386 getuid sys_getuid16 @@ -142,7 +142,7 @@ 128 i386 init_module sys_init_module 129 i386 delete_module sys_delete_module 130 i386 get_kernel_syms -131 i386 quotactl sys_quotactl compat_sys_quotactl32 +131 i386 quotactl sys_quotactl 132 i386 getpgid sys_getpgid 133 i386 fchdir sys_fchdir 134 i386 bdflush sys_bdflush @@ -156,8 +156,8 @@ 142 i386 _newselect sys_select compat_sys_select 143 i386 flock sys_flock 144 i386 msync sys_msync -145 i386 readv sys_readv compat_sys_readv -146 i386 writev sys_writev compat_sys_writev +145 i386 readv sys_readv +146 i386 writev sys_writev 147 i386 getsid sys_getsid 148 i386 fdatasync sys_fdatasync 149 i386 _sysctl sys_ni_syscall @@ -327,7 +327,7 @@ 313 i386 splice sys_splice 314 i386 sync_file_range sys_ia32_sync_file_range 315 i386 tee sys_tee -316 i386 vmsplice sys_vmsplice compat_sys_vmsplice +316 i386 vmsplice sys_vmsplice 317 i386 move_pages sys_move_pages compat_sys_move_pages 318 i386 getcpu sys_getcpu 319 i386 epoll_pwait sys_epoll_pwait @@ -358,8 +358,8 @@ 344 i386 syncfs sys_syncfs 345 i386 sendmmsg sys_sendmmsg compat_sys_sendmmsg 346 i386 setns sys_setns -347 i386 process_vm_readv sys_process_vm_readv compat_sys_process_vm_readv -348 i386 process_vm_writev sys_process_vm_writev compat_sys_process_vm_writev +347 i386 process_vm_readv sys_process_vm_readv +348 i386 process_vm_writev sys_process_vm_writev 349 i386 kcmp sys_kcmp 350 i386 finit_module sys_finit_module 351 i386 sched_setattr sys_sched_setattr diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index f30d6ae9a688..347809649ba2 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -371,8 +371,8 @@ 512 x32 rt_sigaction compat_sys_rt_sigaction 513 x32 rt_sigreturn compat_sys_x32_rt_sigreturn 514 x32 ioctl compat_sys_ioctl -515 x32 readv compat_sys_readv -516 x32 writev compat_sys_writev +515 x32 readv sys_readv +516 x32 writev sys_writev 517 x32 recvfrom compat_sys_recvfrom 518 x32 sendmsg compat_sys_sendmsg 519 x32 recvmsg compat_sys_recvmsg @@ -388,15 +388,15 @@ 529 x32 waitid compat_sys_waitid 530 x32 set_robust_list compat_sys_set_robust_list 531 x32 get_robust_list compat_sys_get_robust_list -532 x32 vmsplice compat_sys_vmsplice +532 x32 vmsplice sys_vmsplice 533 x32 move_pages compat_sys_move_pages 534 x32 preadv compat_sys_preadv64 535 x32 pwritev compat_sys_pwritev64 536 x32 rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo 537 x32 recvmmsg compat_sys_recvmmsg_time64 538 x32 sendmmsg compat_sys_sendmmsg -539 x32 process_vm_readv compat_sys_process_vm_readv -540 x32 process_vm_writev compat_sys_process_vm_writev +539 x32 process_vm_readv sys_process_vm_readv +540 x32 process_vm_writev sys_process_vm_writev 541 x32 setsockopt sys_setsockopt 542 x32 getsockopt sys_getsockopt 543 x32 io_setup compat_sys_io_setup diff --git a/arch/x86/entry/vdso/vdso32/vclock_gettime.c b/arch/x86/entry/vdso/vdso32/vclock_gettime.c index 84a4a73f77f7..283ed9d00426 100644 --- a/arch/x86/entry/vdso/vdso32/vclock_gettime.c +++ b/arch/x86/entry/vdso/vdso32/vclock_gettime.c @@ -14,6 +14,7 @@ #undef CONFIG_ILLEGAL_POINTER_VALUE #undef CONFIG_SPARSEMEM_VMEMMAP #undef CONFIG_NR_CPUS +#undef CONFIG_PARAVIRT_XXL #define CONFIG_X86_32 1 #define CONFIG_PGTABLE_LEVELS 2 diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c index 26c36357c4c9..40669eac9d6d 100644 --- a/arch/x86/events/amd/ibs.c +++ b/arch/x86/events/amd/ibs.c @@ -89,6 +89,7 @@ struct perf_ibs { u64 max_period; unsigned long offset_mask[1]; int offset_max; + unsigned int fetch_count_reset_broken : 1; struct cpu_perf_ibs __percpu *pcpu; struct attribute **format_attrs; @@ -334,11 +335,18 @@ static u64 get_ibs_op_count(u64 config) { u64 count = 0; - if (config & IBS_OP_VAL) - count += (config & IBS_OP_MAX_CNT) << 4; /* cnt rolled over */ - - if (ibs_caps & IBS_CAPS_RDWROPCNT) - count += (config & IBS_OP_CUR_CNT) >> 32; + /* + * If the internal 27-bit counter rolled over, the count is MaxCnt + * and the lower 7 bits of CurCnt are randomized. + * Otherwise CurCnt has the full 27-bit current counter value. + */ + if (config & IBS_OP_VAL) { + count = (config & IBS_OP_MAX_CNT) << 4; + if (ibs_caps & IBS_CAPS_OPCNTEXT) + count += config & IBS_OP_MAX_CNT_EXT_MASK; + } else if (ibs_caps & IBS_CAPS_RDWROPCNT) { + count = (config & IBS_OP_CUR_CNT) >> 32; + } return count; } @@ -363,7 +371,12 @@ perf_ibs_event_update(struct perf_ibs *perf_ibs, struct perf_event *event, static inline void perf_ibs_enable_event(struct perf_ibs *perf_ibs, struct hw_perf_event *hwc, u64 config) { - wrmsrl(hwc->config_base, hwc->config | config | perf_ibs->enable_mask); + u64 tmp = hwc->config | config; + + if (perf_ibs->fetch_count_reset_broken) + wrmsrl(hwc->config_base, tmp & ~perf_ibs->enable_mask); + + wrmsrl(hwc->config_base, tmp | perf_ibs->enable_mask); } /* @@ -394,7 +407,7 @@ static void perf_ibs_start(struct perf_event *event, int flags) struct hw_perf_event *hwc = &event->hw; struct perf_ibs *perf_ibs = container_of(event->pmu, struct perf_ibs, pmu); struct cpu_perf_ibs *pcpu = this_cpu_ptr(perf_ibs->pcpu); - u64 period; + u64 period, config = 0; if (WARN_ON_ONCE(!(hwc->state & PERF_HES_STOPPED))) return; @@ -403,13 +416,19 @@ static void perf_ibs_start(struct perf_event *event, int flags) hwc->state = 0; perf_ibs_set_period(perf_ibs, hwc, &period); + if (perf_ibs == &perf_ibs_op && (ibs_caps & IBS_CAPS_OPCNTEXT)) { + config |= period & IBS_OP_MAX_CNT_EXT_MASK; + period &= ~IBS_OP_MAX_CNT_EXT_MASK; + } + config |= period >> 4; + /* * Set STARTED before enabling the hardware, such that a subsequent NMI * must observe it. */ set_bit(IBS_STARTED, pcpu->state); clear_bit(IBS_STOPPING, pcpu->state); - perf_ibs_enable_event(perf_ibs, hwc, period >> 4); + perf_ibs_enable_event(perf_ibs, hwc, config); perf_event_update_userpage(event); } @@ -577,7 +596,7 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs) struct perf_ibs_data ibs_data; int offset, size, check_rip, offset_max, throttle = 0; unsigned int msr; - u64 *buf, *config, period; + u64 *buf, *config, period, new_config = 0; if (!test_bit(IBS_STARTED, pcpu->state)) { fail: @@ -626,18 +645,24 @@ fail: perf_ibs->offset_max, offset + 1); } while (offset < offset_max); + /* + * Read IbsBrTarget, IbsOpData4, and IbsExtdCtl separately + * depending on their availability. + * Can't add to offset_max as they are staggered + */ if (event->attr.sample_type & PERF_SAMPLE_RAW) { - /* - * Read IbsBrTarget and IbsOpData4 separately - * depending on their availability. - * Can't add to offset_max as they are staggered - */ - if (ibs_caps & IBS_CAPS_BRNTRGT) { - rdmsrl(MSR_AMD64_IBSBRTARGET, *buf++); - size++; + if (perf_ibs == &perf_ibs_op) { + if (ibs_caps & IBS_CAPS_BRNTRGT) { + rdmsrl(MSR_AMD64_IBSBRTARGET, *buf++); + size++; + } + if (ibs_caps & IBS_CAPS_OPDATA4) { + rdmsrl(MSR_AMD64_IBSOPDATA4, *buf++); + size++; + } } - if (ibs_caps & IBS_CAPS_OPDATA4) { - rdmsrl(MSR_AMD64_IBSOPDATA4, *buf++); + if (perf_ibs == &perf_ibs_fetch && (ibs_caps & IBS_CAPS_FETCHCTLEXTD)) { + rdmsrl(MSR_AMD64_ICIBSEXTDCTL, *buf++); size++; } } @@ -666,13 +691,17 @@ out: if (throttle) { perf_ibs_stop(event, 0); } else { - period >>= 4; - - if ((ibs_caps & IBS_CAPS_RDWROPCNT) && - (*config & IBS_OP_CNT_CTL)) - period |= *config & IBS_OP_CUR_CNT_RAND; + if (perf_ibs == &perf_ibs_op) { + if (ibs_caps & IBS_CAPS_OPCNTEXT) { + new_config = period & IBS_OP_MAX_CNT_EXT_MASK; + period &= ~IBS_OP_MAX_CNT_EXT_MASK; + } + if ((ibs_caps & IBS_CAPS_RDWROPCNT) && (*config & IBS_OP_CNT_CTL)) + new_config |= *config & IBS_OP_CUR_CNT_RAND; + } + new_config |= period >> 4; - perf_ibs_enable_event(perf_ibs, hwc, period); + perf_ibs_enable_event(perf_ibs, hwc, new_config); } perf_event_update_userpage(event); @@ -733,12 +762,26 @@ static __init void perf_event_ibs_init(void) { struct attribute **attr = ibs_op_format_attrs; + /* + * Some chips fail to reset the fetch count when it is written; instead + * they need a 0-1 transition of IbsFetchEn. + */ + if (boot_cpu_data.x86 >= 0x16 && boot_cpu_data.x86 <= 0x18) + perf_ibs_fetch.fetch_count_reset_broken = 1; + perf_ibs_pmu_init(&perf_ibs_fetch, "ibs_fetch"); if (ibs_caps & IBS_CAPS_OPCNT) { perf_ibs_op.config_mask |= IBS_OP_CNT_CTL; *attr++ = &format_attr_cnt_ctl.attr; } + + if (ibs_caps & IBS_CAPS_OPCNTEXT) { + perf_ibs_op.max_period |= IBS_OP_MAX_CNT_EXT_MASK; + perf_ibs_op.config_mask |= IBS_OP_MAX_CNT_EXT_MASK; + perf_ibs_op.cnt_mask |= IBS_OP_MAX_CNT_EXT_MASK; + } + perf_ibs_pmu_init(&perf_ibs_op, "ibs_op"); register_nmi_handler(NMI_LOCAL, perf_ibs_nmi_handler, 0, "perf_ibs"); diff --git a/arch/x86/events/amd/iommu.c b/arch/x86/events/amd/iommu.c index fb616203ce42..be50ef8572cc 100644 --- a/arch/x86/events/amd/iommu.c +++ b/arch/x86/events/amd/iommu.c @@ -379,7 +379,7 @@ static __init int _init_events_attrs(void) while (amd_iommu_v2_event_descs[i].attr.attr.name) i++; - attrs = kcalloc(i + 1, sizeof(struct attribute **), GFP_KERNEL); + attrs = kcalloc(i + 1, sizeof(*attrs), GFP_KERNEL); if (!attrs) return -ENOMEM; diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c index 76400c052b0e..7f014d450bc2 100644 --- a/arch/x86/events/amd/uncore.c +++ b/arch/x86/events/amd/uncore.c @@ -181,28 +181,28 @@ static void amd_uncore_del(struct perf_event *event, int flags) } /* - * Convert logical CPU number to L3 PMC Config ThreadMask format + * Return a full thread and slice mask unless user + * has provided them */ -static u64 l3_thread_slice_mask(int cpu) +static u64 l3_thread_slice_mask(u64 config) { - u64 thread_mask, core = topology_core_id(cpu); - unsigned int shift, thread = 0; + if (boot_cpu_data.x86 <= 0x18) + return ((config & AMD64_L3_SLICE_MASK) ? : AMD64_L3_SLICE_MASK) | + ((config & AMD64_L3_THREAD_MASK) ? : AMD64_L3_THREAD_MASK); - if (topology_smt_supported() && !topology_is_primary_thread(cpu)) - thread = 1; - - if (boot_cpu_data.x86 <= 0x18) { - shift = AMD64_L3_THREAD_SHIFT + 2 * (core % 4) + thread; - thread_mask = BIT_ULL(shift); - - return AMD64_L3_SLICE_MASK | thread_mask; - } - - core = (core << AMD64_L3_COREID_SHIFT) & AMD64_L3_COREID_MASK; - shift = AMD64_L3_THREAD_SHIFT + thread; - thread_mask = BIT_ULL(shift); + /* + * If the user doesn't specify a threadmask, they're not trying to + * count core 0, so we enable all cores & threads. + * We'll also assume that they want to count slice 0 if they specify + * a threadmask and leave sliceid and enallslices unpopulated. + */ + if (!(config & AMD64_L3_F19H_THREAD_MASK)) + return AMD64_L3_F19H_THREAD_MASK | AMD64_L3_EN_ALL_SLICES | + AMD64_L3_EN_ALL_CORES; - return AMD64_L3_EN_ALL_SLICES | core | thread_mask; + return config & (AMD64_L3_F19H_THREAD_MASK | AMD64_L3_SLICEID_MASK | + AMD64_L3_EN_ALL_CORES | AMD64_L3_EN_ALL_SLICES | + AMD64_L3_COREID_MASK); } static int amd_uncore_event_init(struct perf_event *event) @@ -232,7 +232,7 @@ static int amd_uncore_event_init(struct perf_event *event) * For other events, the two fields do not affect the count. */ if (l3_mask && is_llc_event(event)) - hwc->config |= l3_thread_slice_mask(event->cpu); + hwc->config |= l3_thread_slice_mask(event->attr.config); uncore = event_to_amd_uncore(event); if (!uncore) @@ -274,47 +274,72 @@ static struct attribute_group amd_uncore_attr_group = { .attrs = amd_uncore_attrs, }; -/* - * Similar to PMU_FORMAT_ATTR but allowing for format_attr to be assigned based - * on family - */ -#define AMD_FORMAT_ATTR(_dev, _name, _format) \ -static ssize_t \ -_dev##_show##_name(struct device *dev, \ - struct device_attribute *attr, \ - char *page) \ -{ \ - BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \ - return sprintf(page, _format "\n"); \ -} \ -static struct device_attribute format_attr_##_dev##_name = __ATTR_RO(_dev); - -/* Used for each uncore counter type */ -#define AMD_ATTRIBUTE(_name) \ -static struct attribute *amd_uncore_format_attr_##_name[] = { \ - &format_attr_event_##_name.attr, \ - &format_attr_umask.attr, \ - NULL, \ -}; \ -static struct attribute_group amd_uncore_format_group_##_name = { \ - .name = "format", \ - .attrs = amd_uncore_format_attr_##_name, \ -}; \ -static const struct attribute_group *amd_uncore_attr_groups_##_name[] = { \ - &amd_uncore_attr_group, \ - &amd_uncore_format_group_##_name, \ - NULL, \ +#define DEFINE_UNCORE_FORMAT_ATTR(_var, _name, _format) \ +static ssize_t __uncore_##_var##_show(struct kobject *kobj, \ + struct kobj_attribute *attr, \ + char *page) \ +{ \ + BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \ + return sprintf(page, _format "\n"); \ +} \ +static struct kobj_attribute format_attr_##_var = \ + __ATTR(_name, 0444, __uncore_##_var##_show, NULL) + +DEFINE_UNCORE_FORMAT_ATTR(event12, event, "config:0-7,32-35"); +DEFINE_UNCORE_FORMAT_ATTR(event14, event, "config:0-7,32-35,59-60"); /* F17h+ DF */ +DEFINE_UNCORE_FORMAT_ATTR(event8, event, "config:0-7"); /* F17h+ L3 */ +DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15"); +DEFINE_UNCORE_FORMAT_ATTR(coreid, coreid, "config:42-44"); /* F19h L3 */ +DEFINE_UNCORE_FORMAT_ATTR(slicemask, slicemask, "config:48-51"); /* F17h L3 */ +DEFINE_UNCORE_FORMAT_ATTR(threadmask8, threadmask, "config:56-63"); /* F17h L3 */ +DEFINE_UNCORE_FORMAT_ATTR(threadmask2, threadmask, "config:56-57"); /* F19h L3 */ +DEFINE_UNCORE_FORMAT_ATTR(enallslices, enallslices, "config:46"); /* F19h L3 */ +DEFINE_UNCORE_FORMAT_ATTR(enallcores, enallcores, "config:47"); /* F19h L3 */ +DEFINE_UNCORE_FORMAT_ATTR(sliceid, sliceid, "config:48-50"); /* F19h L3 */ + +static struct attribute *amd_uncore_df_format_attr[] = { + &format_attr_event12.attr, /* event14 if F17h+ */ + &format_attr_umask.attr, + NULL, +}; + +static struct attribute *amd_uncore_l3_format_attr[] = { + &format_attr_event12.attr, /* event8 if F17h+ */ + &format_attr_umask.attr, + NULL, /* slicemask if F17h, coreid if F19h */ + NULL, /* threadmask8 if F17h, enallslices if F19h */ + NULL, /* enallcores if F19h */ + NULL, /* sliceid if F19h */ + NULL, /* threadmask2 if F19h */ + NULL, +}; + +static struct attribute_group amd_uncore_df_format_group = { + .name = "format", + .attrs = amd_uncore_df_format_attr, }; -AMD_FORMAT_ATTR(event, , "config:0-7,32-35"); -AMD_FORMAT_ATTR(umask, , "config:8-15"); -AMD_FORMAT_ATTR(event, _df, "config:0-7,32-35,59-60"); -AMD_FORMAT_ATTR(event, _l3, "config:0-7"); -AMD_ATTRIBUTE(df); -AMD_ATTRIBUTE(l3); +static struct attribute_group amd_uncore_l3_format_group = { + .name = "format", + .attrs = amd_uncore_l3_format_attr, +}; + +static const struct attribute_group *amd_uncore_df_attr_groups[] = { + &amd_uncore_attr_group, + &amd_uncore_df_format_group, + NULL, +}; + +static const struct attribute_group *amd_uncore_l3_attr_groups[] = { + &amd_uncore_attr_group, + &amd_uncore_l3_format_group, + NULL, +}; static struct pmu amd_nb_pmu = { .task_ctx_nr = perf_invalid_context, + .attr_groups = amd_uncore_df_attr_groups, + .name = "amd_nb", .event_init = amd_uncore_event_init, .add = amd_uncore_add, .del = amd_uncore_del, @@ -326,6 +351,8 @@ static struct pmu amd_nb_pmu = { static struct pmu amd_llc_pmu = { .task_ctx_nr = perf_invalid_context, + .attr_groups = amd_uncore_l3_attr_groups, + .name = "amd_l2", .event_init = amd_uncore_event_init, .add = amd_uncore_add, .del = amd_uncore_del, @@ -529,6 +556,8 @@ static int amd_uncore_cpu_dead(unsigned int cpu) static int __init amd_uncore_init(void) { + struct attribute **df_attr = amd_uncore_df_format_attr; + struct attribute **l3_attr = amd_uncore_l3_format_attr; int ret = -ENODEV; if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD && @@ -538,6 +567,8 @@ static int __init amd_uncore_init(void) if (!boot_cpu_has(X86_FEATURE_TOPOEXT)) return -ENODEV; + num_counters_nb = NUM_COUNTERS_NB; + num_counters_llc = NUM_COUNTERS_L2; if (boot_cpu_data.x86 >= 0x17) { /* * For F17h and above, the Northbridge counters are @@ -545,27 +576,16 @@ static int __init amd_uncore_init(void) * counters are supported too. The PMUs are exported * based on family as either L2 or L3 and NB or DF. */ - num_counters_nb = NUM_COUNTERS_NB; num_counters_llc = NUM_COUNTERS_L3; amd_nb_pmu.name = "amd_df"; amd_llc_pmu.name = "amd_l3"; - format_attr_event_df.show = &event_show_df; - format_attr_event_l3.show = &event_show_l3; l3_mask = true; - } else { - num_counters_nb = NUM_COUNTERS_NB; - num_counters_llc = NUM_COUNTERS_L2; - amd_nb_pmu.name = "amd_nb"; - amd_llc_pmu.name = "amd_l2"; - format_attr_event_df = format_attr_event; - format_attr_event_l3 = format_attr_event; - l3_mask = false; } - amd_nb_pmu.attr_groups = amd_uncore_attr_groups_df; - amd_llc_pmu.attr_groups = amd_uncore_attr_groups_l3; - if (boot_cpu_has(X86_FEATURE_PERFCTR_NB)) { + if (boot_cpu_data.x86 >= 0x17) + *df_attr = &format_attr_event14.attr; + amd_uncore_nb = alloc_percpu(struct amd_uncore *); if (!amd_uncore_nb) { ret = -ENOMEM; @@ -575,13 +595,29 @@ static int __init amd_uncore_init(void) if (ret) goto fail_nb; - pr_info("%s NB counters detected\n", - boot_cpu_data.x86_vendor == X86_VENDOR_HYGON ? - "HYGON" : "AMD"); + pr_info("%d %s %s counters detected\n", num_counters_nb, + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON ? "HYGON" : "", + amd_nb_pmu.name); + ret = 0; } if (boot_cpu_has(X86_FEATURE_PERFCTR_LLC)) { + if (boot_cpu_data.x86 >= 0x19) { + *l3_attr++ = &format_attr_event8.attr; + *l3_attr++ = &format_attr_umask.attr; + *l3_attr++ = &format_attr_coreid.attr; + *l3_attr++ = &format_attr_enallslices.attr; + *l3_attr++ = &format_attr_enallcores.attr; + *l3_attr++ = &format_attr_sliceid.attr; + *l3_attr++ = &format_attr_threadmask2.attr; + } else if (boot_cpu_data.x86 >= 0x17) { + *l3_attr++ = &format_attr_event8.attr; + *l3_attr++ = &format_attr_umask.attr; + *l3_attr++ = &format_attr_slicemask.attr; + *l3_attr++ = &format_attr_threadmask8.attr; + } + amd_uncore_llc = alloc_percpu(struct amd_uncore *); if (!amd_uncore_llc) { ret = -ENOMEM; @@ -591,9 +627,9 @@ static int __init amd_uncore_init(void) if (ret) goto fail_llc; - pr_info("%s LLC counters detected\n", - boot_cpu_data.x86_vendor == X86_VENDOR_HYGON ? - "HYGON" : "AMD"); + pr_info("%d %s %s counters detected\n", num_counters_llc, + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON ? "HYGON" : "", + amd_llc_pmu.name); ret = 0; } diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 1cbf57dc2ac8..a88c94d65693 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -28,6 +28,7 @@ #include <linux/bitops.h> #include <linux/device.h> #include <linux/nospec.h> +#include <linux/static_call.h> #include <asm/apic.h> #include <asm/stacktrace.h> @@ -52,6 +53,34 @@ DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = { DEFINE_STATIC_KEY_FALSE(rdpmc_never_available_key); DEFINE_STATIC_KEY_FALSE(rdpmc_always_available_key); +/* + * This here uses DEFINE_STATIC_CALL_NULL() to get a static_call defined + * from just a typename, as opposed to an actual function. + */ +DEFINE_STATIC_CALL_NULL(x86_pmu_handle_irq, *x86_pmu.handle_irq); +DEFINE_STATIC_CALL_NULL(x86_pmu_disable_all, *x86_pmu.disable_all); +DEFINE_STATIC_CALL_NULL(x86_pmu_enable_all, *x86_pmu.enable_all); +DEFINE_STATIC_CALL_NULL(x86_pmu_enable, *x86_pmu.enable); +DEFINE_STATIC_CALL_NULL(x86_pmu_disable, *x86_pmu.disable); + +DEFINE_STATIC_CALL_NULL(x86_pmu_add, *x86_pmu.add); +DEFINE_STATIC_CALL_NULL(x86_pmu_del, *x86_pmu.del); +DEFINE_STATIC_CALL_NULL(x86_pmu_read, *x86_pmu.read); + +DEFINE_STATIC_CALL_NULL(x86_pmu_schedule_events, *x86_pmu.schedule_events); +DEFINE_STATIC_CALL_NULL(x86_pmu_get_event_constraints, *x86_pmu.get_event_constraints); +DEFINE_STATIC_CALL_NULL(x86_pmu_put_event_constraints, *x86_pmu.put_event_constraints); + +DEFINE_STATIC_CALL_NULL(x86_pmu_start_scheduling, *x86_pmu.start_scheduling); +DEFINE_STATIC_CALL_NULL(x86_pmu_commit_scheduling, *x86_pmu.commit_scheduling); +DEFINE_STATIC_CALL_NULL(x86_pmu_stop_scheduling, *x86_pmu.stop_scheduling); + +DEFINE_STATIC_CALL_NULL(x86_pmu_sched_task, *x86_pmu.sched_task); +DEFINE_STATIC_CALL_NULL(x86_pmu_swap_task_ctx, *x86_pmu.swap_task_ctx); + +DEFINE_STATIC_CALL_NULL(x86_pmu_drain_pebs, *x86_pmu.drain_pebs); +DEFINE_STATIC_CALL_NULL(x86_pmu_pebs_aliases, *x86_pmu.pebs_aliases); + u64 __read_mostly hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] @@ -76,6 +105,9 @@ u64 x86_perf_event_update(struct perf_event *event) if (unlikely(!hwc->event_base)) return 0; + if (unlikely(is_topdown_count(event)) && x86_pmu.update_topdown_event) + return x86_pmu.update_topdown_event(event); + /* * Careful: an NMI might modify the previous event value. * @@ -660,7 +692,7 @@ static void x86_pmu_disable(struct pmu *pmu) cpuc->enabled = 0; barrier(); - x86_pmu.disable_all(); + static_call(x86_pmu_disable_all)(); } void x86_pmu_enable_all(int added) @@ -907,8 +939,7 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) if (cpuc->txn_flags & PERF_PMU_TXN_ADD) n0 -= cpuc->n_txn; - if (x86_pmu.start_scheduling) - x86_pmu.start_scheduling(cpuc); + static_call_cond(x86_pmu_start_scheduling)(cpuc); for (i = 0, wmin = X86_PMC_IDX_MAX, wmax = 0; i < n; i++) { c = cpuc->event_constraint[i]; @@ -925,7 +956,7 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) * change due to external factors (sibling state, allow_tfa). */ if (!c || (c->flags & PERF_X86_EVENT_DYNAMIC)) { - c = x86_pmu.get_event_constraints(cpuc, i, cpuc->event_list[i]); + c = static_call(x86_pmu_get_event_constraints)(cpuc, i, cpuc->event_list[i]); cpuc->event_constraint[i] = c; } @@ -1008,8 +1039,7 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) if (!unsched && assign) { for (i = 0; i < n; i++) { e = cpuc->event_list[i]; - if (x86_pmu.commit_scheduling) - x86_pmu.commit_scheduling(cpuc, i, assign[i]); + static_call_cond(x86_pmu_commit_scheduling)(cpuc, i, assign[i]); } } else { for (i = n0; i < n; i++) { @@ -1018,19 +1048,56 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) /* * release events that failed scheduling */ - if (x86_pmu.put_event_constraints) - x86_pmu.put_event_constraints(cpuc, e); + static_call_cond(x86_pmu_put_event_constraints)(cpuc, e); cpuc->event_constraint[i] = NULL; } } - if (x86_pmu.stop_scheduling) - x86_pmu.stop_scheduling(cpuc); + static_call_cond(x86_pmu_stop_scheduling)(cpuc); return unsched ? -EINVAL : 0; } +static int add_nr_metric_event(struct cpu_hw_events *cpuc, + struct perf_event *event) +{ + if (is_metric_event(event)) { + if (cpuc->n_metric == INTEL_TD_METRIC_NUM) + return -EINVAL; + cpuc->n_metric++; + cpuc->n_txn_metric++; + } + + return 0; +} + +static void del_nr_metric_event(struct cpu_hw_events *cpuc, + struct perf_event *event) +{ + if (is_metric_event(event)) + cpuc->n_metric--; +} + +static int collect_event(struct cpu_hw_events *cpuc, struct perf_event *event, + int max_count, int n) +{ + + if (x86_pmu.intel_cap.perf_metrics && add_nr_metric_event(cpuc, event)) + return -EINVAL; + + if (n >= max_count + cpuc->n_metric) + return -EINVAL; + + cpuc->event_list[n] = event; + if (is_counter_pair(&event->hw)) { + cpuc->n_pair++; + cpuc->n_txn_pair++; + } + + return 0; +} + /* * dogrp: true if must collect siblings events (group) * returns total number of events and error code @@ -1067,28 +1134,22 @@ static int collect_events(struct cpu_hw_events *cpuc, struct perf_event *leader, } if (is_x86_event(leader)) { - if (n >= max_count) + if (collect_event(cpuc, leader, max_count, n)) return -EINVAL; - cpuc->event_list[n] = leader; n++; - if (is_counter_pair(&leader->hw)) - cpuc->n_pair++; } + if (!dogrp) return n; for_each_sibling_event(event, leader) { - if (!is_x86_event(event) || - event->state <= PERF_EVENT_STATE_OFF) + if (!is_x86_event(event) || event->state <= PERF_EVENT_STATE_OFF) continue; - if (n >= max_count) + if (collect_event(cpuc, event, max_count, n)) return -EINVAL; - cpuc->event_list[n] = event; n++; - if (is_counter_pair(&event->hw)) - cpuc->n_pair++; } return n; } @@ -1110,11 +1171,16 @@ static inline void x86_assign_hw_event(struct perf_event *event, hwc->event_base = 0; break; + case INTEL_PMC_IDX_METRIC_BASE ... INTEL_PMC_IDX_METRIC_END: + /* All the metric events are mapped onto the fixed counter 3. */ + idx = INTEL_PMC_IDX_FIXED_SLOTS; + /* fall through */ case INTEL_PMC_IDX_FIXED ... INTEL_PMC_IDX_FIXED_BTS-1: hwc->config_base = MSR_ARCH_PERFMON_FIXED_CTR_CTRL; hwc->event_base = MSR_ARCH_PERFMON_FIXED_CTR0 + (idx - INTEL_PMC_IDX_FIXED); - hwc->event_base_rdpmc = (idx - INTEL_PMC_IDX_FIXED) | 1<<30; + hwc->event_base_rdpmc = (idx - INTEL_PMC_IDX_FIXED) | + INTEL_PMC_FIXED_RDPMC_BASE; break; default: @@ -1226,7 +1292,7 @@ static void x86_pmu_enable(struct pmu *pmu) cpuc->enabled = 1; barrier(); - x86_pmu.enable_all(added); + static_call(x86_pmu_enable_all)(added); } static DEFINE_PER_CPU(u64 [X86_PMC_IDX_MAX], pmc_prev_left); @@ -1245,6 +1311,10 @@ int x86_perf_event_set_period(struct perf_event *event) if (unlikely(!hwc->event_base)) return 0; + if (unlikely(is_topdown_count(event)) && + x86_pmu.set_topdown_event_period) + return x86_pmu.set_topdown_event_period(event); + /* * If we are way outside a reasonable range then just skip forward: */ @@ -1284,11 +1354,11 @@ int x86_perf_event_set_period(struct perf_event *event) wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask); /* - * Clear the Merge event counter's upper 16 bits since + * Sign extend the Merge event counter's upper 16 bits since * we currently declare a 48-bit counter width */ if (is_counter_pair(hwc)) - wrmsrl(x86_pmu_event_addr(idx + 1), 0); + wrmsrl(x86_pmu_event_addr(idx + 1), 0xffff); /* * Due to erratum on certan cpu we need @@ -1347,7 +1417,7 @@ static int x86_pmu_add(struct perf_event *event, int flags) if (cpuc->txn_flags & PERF_PMU_TXN_ADD) goto done_collect; - ret = x86_pmu.schedule_events(cpuc, n, assign); + ret = static_call(x86_pmu_schedule_events)(cpuc, n, assign); if (ret) goto out; /* @@ -1365,13 +1435,11 @@ done_collect: cpuc->n_added += n - n0; cpuc->n_txn += n - n0; - if (x86_pmu.add) { - /* - * This is before x86_pmu_enable() will call x86_pmu_start(), - * so we enable LBRs before an event needs them etc.. - */ - x86_pmu.add(event); - } + /* + * This is before x86_pmu_enable() will call x86_pmu_start(), + * so we enable LBRs before an event needs them etc.. + */ + static_call_cond(x86_pmu_add)(event); ret = 0; out: @@ -1399,7 +1467,7 @@ static void x86_pmu_start(struct perf_event *event, int flags) cpuc->events[idx] = event; __set_bit(idx, cpuc->active_mask); __set_bit(idx, cpuc->running); - x86_pmu.enable(event); + static_call(x86_pmu_enable)(event); perf_event_update_userpage(event); } @@ -1469,7 +1537,7 @@ void x86_pmu_stop(struct perf_event *event, int flags) struct hw_perf_event *hwc = &event->hw; if (test_bit(hwc->idx, cpuc->active_mask)) { - x86_pmu.disable(event); + static_call(x86_pmu_disable)(event); __clear_bit(hwc->idx, cpuc->active_mask); cpuc->events[hwc->idx] = NULL; WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED); @@ -1519,8 +1587,7 @@ static void x86_pmu_del(struct perf_event *event, int flags) if (i >= cpuc->n_events - cpuc->n_added) --cpuc->n_added; - if (x86_pmu.put_event_constraints) - x86_pmu.put_event_constraints(cpuc, event); + static_call_cond(x86_pmu_put_event_constraints)(cpuc, event); /* Delete the array entry. */ while (++i < cpuc->n_events) { @@ -1529,17 +1596,18 @@ static void x86_pmu_del(struct perf_event *event, int flags) } cpuc->event_constraint[i-1] = NULL; --cpuc->n_events; + if (x86_pmu.intel_cap.perf_metrics) + del_nr_metric_event(cpuc, event); perf_event_update_userpage(event); do_del: - if (x86_pmu.del) { - /* - * This is after x86_pmu_stop(); so we disable LBRs after any - * event can need them etc.. - */ - x86_pmu.del(event); - } + + /* + * This is after x86_pmu_stop(); so we disable LBRs after any + * event can need them etc.. + */ + static_call_cond(x86_pmu_del)(event); } int x86_pmu_handle_irq(struct pt_regs *regs) @@ -1617,7 +1685,7 @@ perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs) return NMI_DONE; start_clock = sched_clock(); - ret = x86_pmu.handle_irq(regs); + ret = static_call(x86_pmu_handle_irq)(regs); finish_clock = sched_clock(); perf_sample_event_took(finish_clock - start_clock); @@ -1830,6 +1898,38 @@ ssize_t x86_event_sysfs_show(char *page, u64 config, u64 event) static struct attribute_group x86_pmu_attr_group; static struct attribute_group x86_pmu_caps_group; +static void x86_pmu_static_call_update(void) +{ + static_call_update(x86_pmu_handle_irq, x86_pmu.handle_irq); + static_call_update(x86_pmu_disable_all, x86_pmu.disable_all); + static_call_update(x86_pmu_enable_all, x86_pmu.enable_all); + static_call_update(x86_pmu_enable, x86_pmu.enable); + static_call_update(x86_pmu_disable, x86_pmu.disable); + + static_call_update(x86_pmu_add, x86_pmu.add); + static_call_update(x86_pmu_del, x86_pmu.del); + static_call_update(x86_pmu_read, x86_pmu.read); + + static_call_update(x86_pmu_schedule_events, x86_pmu.schedule_events); + static_call_update(x86_pmu_get_event_constraints, x86_pmu.get_event_constraints); + static_call_update(x86_pmu_put_event_constraints, x86_pmu.put_event_constraints); + + static_call_update(x86_pmu_start_scheduling, x86_pmu.start_scheduling); + static_call_update(x86_pmu_commit_scheduling, x86_pmu.commit_scheduling); + static_call_update(x86_pmu_stop_scheduling, x86_pmu.stop_scheduling); + + static_call_update(x86_pmu_sched_task, x86_pmu.sched_task); + static_call_update(x86_pmu_swap_task_ctx, x86_pmu.swap_task_ctx); + + static_call_update(x86_pmu_drain_pebs, x86_pmu.drain_pebs); + static_call_update(x86_pmu_pebs_aliases, x86_pmu.pebs_aliases); +} + +static void _x86_pmu_read(struct perf_event *event) +{ + x86_perf_event_update(event); +} + static int __init init_hw_perf_events(void) { struct x86_pmu_quirk *quirk; @@ -1898,6 +1998,11 @@ static int __init init_hw_perf_events(void) pr_info("... fixed-purpose events: %d\n", x86_pmu.num_counters_fixed); pr_info("... event mask: %016Lx\n", x86_pmu.intel_ctrl); + if (!x86_pmu.read) + x86_pmu.read = _x86_pmu_read; + + x86_pmu_static_call_update(); + /* * Install callbacks. Core will call them for each online * cpu. @@ -1934,11 +2039,9 @@ out: } early_initcall(init_hw_perf_events); -static inline void x86_pmu_read(struct perf_event *event) +static void x86_pmu_read(struct perf_event *event) { - if (x86_pmu.read) - return x86_pmu.read(event); - x86_perf_event_update(event); + static_call(x86_pmu_read)(event); } /* @@ -1962,6 +2065,8 @@ static void x86_pmu_start_txn(struct pmu *pmu, unsigned int txn_flags) perf_pmu_disable(pmu); __this_cpu_write(cpu_hw_events.n_txn, 0); + __this_cpu_write(cpu_hw_events.n_txn_pair, 0); + __this_cpu_write(cpu_hw_events.n_txn_metric, 0); } /* @@ -1987,6 +2092,8 @@ static void x86_pmu_cancel_txn(struct pmu *pmu) */ __this_cpu_sub(cpu_hw_events.n_added, __this_cpu_read(cpu_hw_events.n_txn)); __this_cpu_sub(cpu_hw_events.n_events, __this_cpu_read(cpu_hw_events.n_txn)); + __this_cpu_sub(cpu_hw_events.n_pair, __this_cpu_read(cpu_hw_events.n_txn_pair)); + __this_cpu_sub(cpu_hw_events.n_metric, __this_cpu_read(cpu_hw_events.n_txn_metric)); perf_pmu_enable(pmu); } @@ -2015,7 +2122,7 @@ static int x86_pmu_commit_txn(struct pmu *pmu) if (!x86_pmu_initialized()) return -EAGAIN; - ret = x86_pmu.schedule_events(cpuc, n, assign); + ret = static_call(x86_pmu_schedule_events)(cpuc, n, assign); if (ret) return ret; @@ -2208,17 +2315,15 @@ static void x86_pmu_event_unmapped(struct perf_event *event, struct mm_struct *m static int x86_pmu_event_idx(struct perf_event *event) { - int idx = event->hw.idx; + struct hw_perf_event *hwc = &event->hw; - if (!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED)) + if (!(hwc->flags & PERF_X86_EVENT_RDPMC_ALLOWED)) return 0; - if (x86_pmu.num_counters_fixed && idx >= INTEL_PMC_IDX_FIXED) { - idx -= INTEL_PMC_IDX_FIXED; - idx |= 1 << 30; - } - - return idx + 1; + if (is_metric_idx(hwc->idx)) + return INTEL_PMC_FIXED_RDPMC_METRICS + 1; + else + return hwc->event_base_rdpmc + 1; } static ssize_t get_attr_rdpmc(struct device *cdev, @@ -2308,15 +2413,13 @@ static const struct attribute_group *x86_pmu_attr_groups[] = { static void x86_pmu_sched_task(struct perf_event_context *ctx, bool sched_in) { - if (x86_pmu.sched_task) - x86_pmu.sched_task(ctx, sched_in); + static_call_cond(x86_pmu_sched_task)(ctx, sched_in); } static void x86_pmu_swap_task_ctx(struct perf_event_context *prev, struct perf_event_context *next) { - if (x86_pmu.swap_task_ctx) - x86_pmu.swap_task_ctx(prev, next); + static_call_cond(x86_pmu_swap_task_ctx)(prev, next); } void perf_check_microcode(void) diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 31e6887d24f1..f1926e9f2143 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -243,10 +243,14 @@ static struct extra_reg intel_skl_extra_regs[] __read_mostly = { static struct event_constraint intel_icl_event_constraints[] = { FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ - INTEL_UEVENT_CONSTRAINT(0x1c0, 0), /* INST_RETIRED.PREC_DIST */ + FIXED_EVENT_CONSTRAINT(0x01c0, 0), /* INST_RETIRED.PREC_DIST */ FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ FIXED_EVENT_CONSTRAINT(0x0400, 3), /* SLOTS */ + METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_RETIRING, 0), + METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_BAD_SPEC, 1), + METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_FE_BOUND, 2), + METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_BE_BOUND, 3), INTEL_EVENT_CONSTRAINT_RANGE(0x03, 0x0a, 0xf), INTEL_EVENT_CONSTRAINT_RANGE(0x1f, 0x28, 0xf), INTEL_EVENT_CONSTRAINT(0x32, 0xf), /* SW_PREFETCH_ACCESS.* */ @@ -309,6 +313,12 @@ EVENT_ATTR_STR_HT(topdown-recovery-bubbles, td_recovery_bubbles, EVENT_ATTR_STR_HT(topdown-recovery-bubbles.scale, td_recovery_bubbles_scale, "4", "2"); +EVENT_ATTR_STR(slots, slots, "event=0x00,umask=0x4"); +EVENT_ATTR_STR(topdown-retiring, td_retiring, "event=0x00,umask=0x80"); +EVENT_ATTR_STR(topdown-bad-spec, td_bad_spec, "event=0x00,umask=0x81"); +EVENT_ATTR_STR(topdown-fe-bound, td_fe_bound, "event=0x00,umask=0x82"); +EVENT_ATTR_STR(topdown-be-bound, td_be_bound, "event=0x00,umask=0x83"); + static struct attribute *snb_events_attrs[] = { EVENT_PTR(td_slots_issued), EVENT_PTR(td_slots_retired), @@ -2165,11 +2175,24 @@ static inline void intel_clear_masks(struct perf_event *event, int idx) static void intel_pmu_disable_fixed(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; - int idx = hwc->idx - INTEL_PMC_IDX_FIXED; u64 ctrl_val, mask; + int idx = hwc->idx; - mask = 0xfULL << (idx * 4); + if (is_topdown_idx(idx)) { + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + + /* + * When there are other active TopDown events, + * don't disable the fixed counter 3. + */ + if (*(u64 *)cpuc->active_mask & INTEL_PMC_OTHER_TOPDOWN_BITS(idx)) + return; + idx = INTEL_PMC_IDX_FIXED_SLOTS; + } + intel_clear_masks(event, idx); + + mask = 0xfULL << ((idx - INTEL_PMC_IDX_FIXED) * 4); rdmsrl(hwc->config_base, ctrl_val); ctrl_val &= ~mask; wrmsrl(hwc->config_base, ctrl_val); @@ -2180,17 +2203,28 @@ static void intel_pmu_disable_event(struct perf_event *event) struct hw_perf_event *hwc = &event->hw; int idx = hwc->idx; - if (idx < INTEL_PMC_IDX_FIXED) { + switch (idx) { + case 0 ... INTEL_PMC_IDX_FIXED - 1: intel_clear_masks(event, idx); x86_pmu_disable_event(event); - } else if (idx < INTEL_PMC_IDX_FIXED_BTS) { - intel_clear_masks(event, idx); + break; + case INTEL_PMC_IDX_FIXED ... INTEL_PMC_IDX_FIXED_BTS - 1: + case INTEL_PMC_IDX_METRIC_BASE ... INTEL_PMC_IDX_METRIC_END: intel_pmu_disable_fixed(event); - } else if (idx == INTEL_PMC_IDX_FIXED_BTS) { + break; + case INTEL_PMC_IDX_FIXED_BTS: intel_pmu_disable_bts(); intel_pmu_drain_bts_buffer(); - } else if (idx == INTEL_PMC_IDX_FIXED_VLBR) + return; + case INTEL_PMC_IDX_FIXED_VLBR: intel_clear_masks(event, idx); + break; + default: + intel_clear_masks(event, idx); + pr_warn("Failed to disable the event with invalid index %d\n", + idx); + return; + } /* * Needs to be called after x86_pmu_disable_event, @@ -2208,10 +2242,189 @@ static void intel_pmu_del_event(struct perf_event *event) intel_pmu_pebs_del(event); } +static int icl_set_topdown_event_period(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + s64 left = local64_read(&hwc->period_left); + + /* + * The values in PERF_METRICS MSR are derived from fixed counter 3. + * Software should start both registers, PERF_METRICS and fixed + * counter 3, from zero. + * Clear PERF_METRICS and Fixed counter 3 in initialization. + * After that, both MSRs will be cleared for each read. + * Don't need to clear them again. + */ + if (left == x86_pmu.max_period) { + wrmsrl(MSR_CORE_PERF_FIXED_CTR3, 0); + wrmsrl(MSR_PERF_METRICS, 0); + hwc->saved_slots = 0; + hwc->saved_metric = 0; + } + + if ((hwc->saved_slots) && is_slots_event(event)) { + wrmsrl(MSR_CORE_PERF_FIXED_CTR3, hwc->saved_slots); + wrmsrl(MSR_PERF_METRICS, hwc->saved_metric); + } + + perf_event_update_userpage(event); + + return 0; +} + +static inline u64 icl_get_metrics_event_value(u64 metric, u64 slots, int idx) +{ + u32 val; + + /* + * The metric is reported as an 8bit integer fraction + * suming up to 0xff. + * slots-in-metric = (Metric / 0xff) * slots + */ + val = (metric >> ((idx - INTEL_PMC_IDX_METRIC_BASE) * 8)) & 0xff; + return mul_u64_u32_div(slots, val, 0xff); +} + +static u64 icl_get_topdown_value(struct perf_event *event, + u64 slots, u64 metrics) +{ + int idx = event->hw.idx; + u64 delta; + + if (is_metric_idx(idx)) + delta = icl_get_metrics_event_value(metrics, slots, idx); + else + delta = slots; + + return delta; +} + +static void __icl_update_topdown_event(struct perf_event *event, + u64 slots, u64 metrics, + u64 last_slots, u64 last_metrics) +{ + u64 delta, last = 0; + + delta = icl_get_topdown_value(event, slots, metrics); + if (last_slots) + last = icl_get_topdown_value(event, last_slots, last_metrics); + + /* + * The 8bit integer fraction of metric may be not accurate, + * especially when the changes is very small. + * For example, if only a few bad_spec happens, the fraction + * may be reduced from 1 to 0. If so, the bad_spec event value + * will be 0 which is definitely less than the last value. + * Avoid update event->count for this case. + */ + if (delta > last) { + delta -= last; + local64_add(delta, &event->count); + } +} + +static void update_saved_topdown_regs(struct perf_event *event, + u64 slots, u64 metrics) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + struct perf_event *other; + int idx; + + event->hw.saved_slots = slots; + event->hw.saved_metric = metrics; + + for_each_set_bit(idx, cpuc->active_mask, INTEL_PMC_IDX_TD_BE_BOUND + 1) { + if (!is_topdown_idx(idx)) + continue; + other = cpuc->events[idx]; + other->hw.saved_slots = slots; + other->hw.saved_metric = metrics; + } +} + +/* + * Update all active Topdown events. + * + * The PERF_METRICS and Fixed counter 3 are read separately. The values may be + * modify by a NMI. PMU has to be disabled before calling this function. + */ +static u64 icl_update_topdown_event(struct perf_event *event) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + struct perf_event *other; + u64 slots, metrics; + bool reset = true; + int idx; + + /* read Fixed counter 3 */ + rdpmcl((3 | INTEL_PMC_FIXED_RDPMC_BASE), slots); + if (!slots) + return 0; + + /* read PERF_METRICS */ + rdpmcl(INTEL_PMC_FIXED_RDPMC_METRICS, metrics); + + for_each_set_bit(idx, cpuc->active_mask, INTEL_PMC_IDX_TD_BE_BOUND + 1) { + if (!is_topdown_idx(idx)) + continue; + other = cpuc->events[idx]; + __icl_update_topdown_event(other, slots, metrics, + event ? event->hw.saved_slots : 0, + event ? event->hw.saved_metric : 0); + } + + /* + * Check and update this event, which may have been cleared + * in active_mask e.g. x86_pmu_stop() + */ + if (event && !test_bit(event->hw.idx, cpuc->active_mask)) { + __icl_update_topdown_event(event, slots, metrics, + event->hw.saved_slots, + event->hw.saved_metric); + + /* + * In x86_pmu_stop(), the event is cleared in active_mask first, + * then drain the delta, which indicates context switch for + * counting. + * Save metric and slots for context switch. + * Don't need to reset the PERF_METRICS and Fixed counter 3. + * Because the values will be restored in next schedule in. + */ + update_saved_topdown_regs(event, slots, metrics); + reset = false; + } + + if (reset) { + /* The fixed counter 3 has to be written before the PERF_METRICS. */ + wrmsrl(MSR_CORE_PERF_FIXED_CTR3, 0); + wrmsrl(MSR_PERF_METRICS, 0); + if (event) + update_saved_topdown_regs(event, 0, 0); + } + + return slots; +} + +static void intel_pmu_read_topdown_event(struct perf_event *event) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + + /* Only need to call update_topdown_event() once for group read. */ + if ((cpuc->txn_flags & PERF_PMU_TXN_READ) && + !is_slots_event(event)) + return; + + perf_pmu_disable(event->pmu); + x86_pmu.update_topdown_event(event); + perf_pmu_enable(event->pmu); +} + static void intel_pmu_read_event(struct perf_event *event) { if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD) intel_pmu_auto_reload_read(event); + else if (is_topdown_count(event) && x86_pmu.update_topdown_event) + intel_pmu_read_topdown_event(event); else x86_perf_event_update(event); } @@ -2219,8 +2432,22 @@ static void intel_pmu_read_event(struct perf_event *event) static void intel_pmu_enable_fixed(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; - int idx = hwc->idx - INTEL_PMC_IDX_FIXED; u64 ctrl_val, mask, bits = 0; + int idx = hwc->idx; + + if (is_topdown_idx(idx)) { + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + /* + * When there are other active TopDown events, + * don't enable the fixed counter 3 again. + */ + if (*(u64 *)cpuc->active_mask & INTEL_PMC_OTHER_TOPDOWN_BITS(idx)) + return; + + idx = INTEL_PMC_IDX_FIXED_SLOTS; + } + + intel_set_masks(event, idx); /* * Enable IRQ generation (0x8), if not PEBS, @@ -2240,6 +2467,7 @@ static void intel_pmu_enable_fixed(struct perf_event *event) if (x86_pmu.version > 2 && hwc->config & ARCH_PERFMON_EVENTSEL_ANY) bits |= 0x4; + idx -= INTEL_PMC_IDX_FIXED; bits <<= (idx * 4); mask = 0xfULL << (idx * 4); @@ -2262,18 +2490,27 @@ static void intel_pmu_enable_event(struct perf_event *event) if (unlikely(event->attr.precise_ip)) intel_pmu_pebs_enable(event); - if (idx < INTEL_PMC_IDX_FIXED) { + switch (idx) { + case 0 ... INTEL_PMC_IDX_FIXED - 1: intel_set_masks(event, idx); __x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE); - } else if (idx < INTEL_PMC_IDX_FIXED_BTS) { - intel_set_masks(event, idx); + break; + case INTEL_PMC_IDX_FIXED ... INTEL_PMC_IDX_FIXED_BTS - 1: + case INTEL_PMC_IDX_METRIC_BASE ... INTEL_PMC_IDX_METRIC_END: intel_pmu_enable_fixed(event); - } else if (idx == INTEL_PMC_IDX_FIXED_BTS) { + break; + case INTEL_PMC_IDX_FIXED_BTS: if (!__this_cpu_read(cpu_hw_events.enabled)) return; intel_pmu_enable_bts(hwc->config); - } else if (idx == INTEL_PMC_IDX_FIXED_VLBR) + break; + case INTEL_PMC_IDX_FIXED_VLBR: intel_set_masks(event, idx); + break; + default: + pr_warn("Failed to enable the event with invalid index %d\n", + idx); + } } static void intel_pmu_add_event(struct perf_event *event) @@ -2389,7 +2626,7 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status) /* * PEBS overflow sets bit 62 in the global status register */ - if (__test_and_clear_bit(62, (unsigned long *)&status)) { + if (__test_and_clear_bit(GLOBAL_STATUS_BUFFER_OVF_BIT, (unsigned long *)&status)) { u64 pebs_enabled = cpuc->pebs_enabled; handled++; @@ -2410,7 +2647,7 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status) /* * Intel PT */ - if (__test_and_clear_bit(55, (unsigned long *)&status)) { + if (__test_and_clear_bit(GLOBAL_STATUS_TRACE_TOPAPMI_BIT, (unsigned long *)&status)) { handled++; if (unlikely(perf_guest_cbs && perf_guest_cbs->is_in_guest() && perf_guest_cbs->handle_intel_pt_intr)) @@ -2420,6 +2657,15 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status) } /* + * Intel Perf mertrics + */ + if (__test_and_clear_bit(GLOBAL_STATUS_PERF_METRICS_OVF_BIT, (unsigned long *)&status)) { + handled++; + if (x86_pmu.update_topdown_event) + x86_pmu.update_topdown_event(NULL); + } + + /* * Checkpointed counters can lead to 'spurious' PMIs because the * rollback caused by the PMI will have cleared the overflow status * bit. Therefore always force probe these counters. @@ -3355,6 +3601,56 @@ static int intel_pmu_hw_config(struct perf_event *event) if (event->attr.type != PERF_TYPE_RAW) return 0; + /* + * Config Topdown slots and metric events + * + * The slots event on Fixed Counter 3 can support sampling, + * which will be handled normally in x86_perf_event_update(). + * + * Metric events don't support sampling and require being paired + * with a slots event as group leader. When the slots event + * is used in a metrics group, it too cannot support sampling. + */ + if (x86_pmu.intel_cap.perf_metrics && is_topdown_event(event)) { + if (event->attr.config1 || event->attr.config2) + return -EINVAL; + + /* + * The TopDown metrics events and slots event don't + * support any filters. + */ + if (event->attr.config & X86_ALL_EVENT_FLAGS) + return -EINVAL; + + if (is_metric_event(event)) { + struct perf_event *leader = event->group_leader; + + /* The metric events don't support sampling. */ + if (is_sampling_event(event)) + return -EINVAL; + + /* The metric events require a slots group leader. */ + if (!is_slots_event(leader)) + return -EINVAL; + + /* + * The leader/SLOTS must not be a sampling event for + * metric use; hardware requires it starts at 0 when used + * in conjunction with MSR_PERF_METRICS. + */ + if (is_sampling_event(leader)) + return -EINVAL; + + event->event_caps |= PERF_EV_CAP_SIBLING; + /* + * Only once we have a METRICs sibling do we + * need TopDown magic. + */ + leader->hw.flags |= PERF_X86_EVENT_TOPDOWN; + event->hw.flags |= PERF_X86_EVENT_TOPDOWN; + } + } + if (!(event->attr.config & ARCH_PERFMON_EVENTSEL_ANY)) return 0; @@ -3787,6 +4083,17 @@ static void intel_pmu_cpu_starting(int cpu) if (x86_pmu.counter_freezing) enable_counter_freeze(); + /* Disable perf metrics if any added CPU doesn't support it. */ + if (x86_pmu.intel_cap.perf_metrics) { + union perf_capabilities perf_cap; + + rdmsrl(MSR_IA32_PERF_CAPABILITIES, perf_cap.capabilities); + if (!perf_cap.perf_metrics) { + x86_pmu.intel_cap.perf_metrics = 0; + x86_pmu.intel_ctrl &= ~(1ULL << GLOBAL_CTRL_EN_PERF_METRICS); + } + } + if (!cpuc->shared_regs) return; @@ -4355,6 +4662,15 @@ static struct attribute *icl_events_attrs[] = { NULL, }; +static struct attribute *icl_td_events_attrs[] = { + EVENT_PTR(slots), + EVENT_PTR(td_retiring), + EVENT_PTR(td_bad_spec), + EVENT_PTR(td_fe_bound), + EVENT_PTR(td_be_bound), + NULL, +}; + static struct attribute *icl_tsx_events_attrs[] = { EVENT_PTR(tx_start), EVENT_PTR(tx_abort), @@ -4830,6 +5146,7 @@ __init int intel_pmu_init(void) case INTEL_FAM6_ATOM_TREMONT_D: case INTEL_FAM6_ATOM_TREMONT: + case INTEL_FAM6_ATOM_TREMONT_L: x86_pmu.late_ack = true; memcpy(hw_cache_event_ids, glp_hw_cache_event_ids, sizeof(hw_cache_event_ids)); @@ -5139,10 +5456,13 @@ __init int intel_pmu_init(void) hsw_format_attr : nhm_format_attr; extra_skl_attr = skl_format_attr; mem_attr = icl_events_attrs; + td_attr = icl_td_events_attrs; tsx_attr = icl_tsx_events_attrs; x86_pmu.rtm_abort_event = X86_CONFIG(.event=0xca, .umask=0x02); x86_pmu.lbr_pt_coexist = true; intel_pmu_pebs_data_source_skl(pmem); + x86_pmu.update_topdown_event = icl_update_topdown_event; + x86_pmu.set_topdown_event_period = icl_set_topdown_event_period; pr_cont("Icelake events, "); name = "icelake"; break; @@ -5198,6 +5518,15 @@ __init int intel_pmu_init(void) * counter, so do not extend mask to generic counters */ for_each_event_constraint(c, x86_pmu.event_constraints) { + /* + * Don't extend the topdown slots and metrics + * events to the generic counters. + */ + if (c->idxmsk64 & INTEL_PMC_MSK_TOPDOWN) { + c->weight = hweight64(c->idxmsk64); + continue; + } + if (c->cmask == FIXED_EVENT_FLAGS && c->idxmsk64 != INTEL_PMC_MSK_FIXED_REF_CYCLES) { c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1; @@ -5253,6 +5582,9 @@ __init int intel_pmu_init(void) if (x86_pmu.counter_freezing) x86_pmu.handle_irq = intel_pmu_handle_irq_v4; + if (x86_pmu.intel_cap.perf_metrics) + x86_pmu.intel_ctrl |= 1ULL << GLOBAL_CTRL_EN_PERF_METRICS; + return 0; } diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 86848c57b55e..404315df1e16 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -670,9 +670,7 @@ unlock: static inline void intel_pmu_drain_pebs_buffer(void) { - struct pt_regs regs; - - x86_pmu.drain_pebs(®s); + x86_pmu.drain_pebs(NULL); } /* @@ -1737,6 +1735,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event, struct x86_perf_regs perf_regs; struct pt_regs *regs = &perf_regs.regs; void *at = get_next_pebs_record_by_bit(base, top, bit); + struct pt_regs dummy_iregs; if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) { /* @@ -1749,6 +1748,9 @@ static void __intel_pmu_pebs_event(struct perf_event *event, } else if (!intel_pmu_save_and_restart(event)) return; + if (!iregs) + iregs = &dummy_iregs; + while (count > 1) { setup_sample(event, iregs, at, &data, regs); perf_event_output(event, &data, regs); @@ -1758,16 +1760,22 @@ static void __intel_pmu_pebs_event(struct perf_event *event, } setup_sample(event, iregs, at, &data, regs); - - /* - * All but the last records are processed. - * The last one is left to be able to call the overflow handler. - */ - if (perf_event_overflow(event, &data, regs)) { - x86_pmu_stop(event, 0); - return; + if (iregs == &dummy_iregs) { + /* + * The PEBS records may be drained in the non-overflow context, + * e.g., large PEBS + context switch. Perf should treat the + * last record the same as other PEBS records, and doesn't + * invoke the generic overflow handler. + */ + perf_event_output(event, &data, regs); + } else { + /* + * All but the last records are processed. + * The last one is left to be able to call the overflow handler. + */ + if (perf_event_overflow(event, &data, regs)) + x86_pmu_stop(event, 0); } - } static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index d5c6d3b340c5..86d012b3e0b4 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -12,6 +12,8 @@ struct intel_uncore_type **uncore_mmio_uncores = empty_uncore; static bool pcidrv_registered; struct pci_driver *uncore_pci_driver; +/* The PCI driver for the device which the uncore doesn't own. */ +struct pci_driver *uncore_pci_sub_driver; /* pci bus to socket mapping */ DEFINE_RAW_SPINLOCK(pci2phy_map_lock); struct list_head pci2phy_map_head = LIST_HEAD_INIT(pci2phy_map_head); @@ -989,65 +991,71 @@ uncore_types_init(struct intel_uncore_type **types, bool setid) } /* - * add a pci uncore device + * Get the die information of a PCI device. + * @pdev: The PCI device. + * @phys_id: The physical socket id which the device maps to. + * @die: The die id which the device maps to. */ -static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) +static int uncore_pci_get_dev_die_info(struct pci_dev *pdev, + int *phys_id, int *die) { - struct intel_uncore_type *type; - struct intel_uncore_pmu *pmu = NULL; - struct intel_uncore_box *box; - int phys_id, die, ret; - - phys_id = uncore_pcibus_to_physid(pdev->bus); - if (phys_id < 0) + *phys_id = uncore_pcibus_to_physid(pdev->bus); + if (*phys_id < 0) return -ENODEV; - die = (topology_max_die_per_package() > 1) ? phys_id : - topology_phys_to_logical_pkg(phys_id); - if (die < 0) + *die = (topology_max_die_per_package() > 1) ? *phys_id : + topology_phys_to_logical_pkg(*phys_id); + if (*die < 0) return -EINVAL; - if (UNCORE_PCI_DEV_TYPE(id->driver_data) == UNCORE_EXTRA_PCI_DEV) { - int idx = UNCORE_PCI_DEV_IDX(id->driver_data); - - uncore_extra_pci_dev[die].dev[idx] = pdev; - pci_set_drvdata(pdev, NULL); - return 0; - } - - type = uncore_pci_uncores[UNCORE_PCI_DEV_TYPE(id->driver_data)]; + return 0; +} - /* - * Some platforms, e.g. Knights Landing, use a common PCI device ID - * for multiple instances of an uncore PMU device type. We should check - * PCI slot and func to indicate the uncore box. - */ - if (id->driver_data & ~0xffff) { - struct pci_driver *pci_drv = pdev->driver; - const struct pci_device_id *ids = pci_drv->id_table; - unsigned int devfn; - - while (ids && ids->vendor) { - if ((ids->vendor == pdev->vendor) && - (ids->device == pdev->device)) { - devfn = PCI_DEVFN(UNCORE_PCI_DEV_DEV(ids->driver_data), - UNCORE_PCI_DEV_FUNC(ids->driver_data)); - if (devfn == pdev->devfn) { - pmu = &type->pmus[UNCORE_PCI_DEV_IDX(ids->driver_data)]; - break; - } +/* + * Find the PMU of a PCI device. + * @pdev: The PCI device. + * @ids: The ID table of the available PCI devices with a PMU. + */ +static struct intel_uncore_pmu * +uncore_pci_find_dev_pmu(struct pci_dev *pdev, const struct pci_device_id *ids) +{ + struct intel_uncore_pmu *pmu = NULL; + struct intel_uncore_type *type; + kernel_ulong_t data; + unsigned int devfn; + + while (ids && ids->vendor) { + if ((ids->vendor == pdev->vendor) && + (ids->device == pdev->device)) { + data = ids->driver_data; + devfn = PCI_DEVFN(UNCORE_PCI_DEV_DEV(data), + UNCORE_PCI_DEV_FUNC(data)); + if (devfn == pdev->devfn) { + type = uncore_pci_uncores[UNCORE_PCI_DEV_TYPE(data)]; + pmu = &type->pmus[UNCORE_PCI_DEV_IDX(data)]; + break; } - ids++; } - if (pmu == NULL) - return -ENODEV; - } else { - /* - * for performance monitoring unit with multiple boxes, - * each box has a different function id. - */ - pmu = &type->pmus[UNCORE_PCI_DEV_IDX(id->driver_data)]; + ids++; } + return pmu; +} + +/* + * Register the PMU for a PCI device + * @pdev: The PCI device. + * @type: The corresponding PMU type of the device. + * @pmu: The corresponding PMU of the device. + * @phys_id: The physical socket id which the device maps to. + * @die: The die id which the device maps to. + */ +static int uncore_pci_pmu_register(struct pci_dev *pdev, + struct intel_uncore_type *type, + struct intel_uncore_pmu *pmu, + int phys_id, int die) +{ + struct intel_uncore_box *box; + int ret; if (WARN_ON_ONCE(pmu->boxes[die] != NULL)) return -EINVAL; @@ -1067,7 +1075,6 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id box->pci_dev = pdev; box->pmu = pmu; uncore_box_init(box); - pci_set_drvdata(pdev, box); pmu->boxes[die] = box; if (atomic_inc_return(&pmu->activeboxes) > 1) @@ -1076,7 +1083,6 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id /* First active box registers the pmu */ ret = uncore_pmu_register(pmu); if (ret) { - pci_set_drvdata(pdev, NULL); pmu->boxes[die] = NULL; uncore_box_exit(box); kfree(box); @@ -1084,18 +1090,87 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id return ret; } +/* + * add a pci uncore device + */ +static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) +{ + struct intel_uncore_type *type; + struct intel_uncore_pmu *pmu = NULL; + int phys_id, die, ret; + + ret = uncore_pci_get_dev_die_info(pdev, &phys_id, &die); + if (ret) + return ret; + + if (UNCORE_PCI_DEV_TYPE(id->driver_data) == UNCORE_EXTRA_PCI_DEV) { + int idx = UNCORE_PCI_DEV_IDX(id->driver_data); + + uncore_extra_pci_dev[die].dev[idx] = pdev; + pci_set_drvdata(pdev, NULL); + return 0; + } + + type = uncore_pci_uncores[UNCORE_PCI_DEV_TYPE(id->driver_data)]; + + /* + * Some platforms, e.g. Knights Landing, use a common PCI device ID + * for multiple instances of an uncore PMU device type. We should check + * PCI slot and func to indicate the uncore box. + */ + if (id->driver_data & ~0xffff) { + struct pci_driver *pci_drv = pdev->driver; + + pmu = uncore_pci_find_dev_pmu(pdev, pci_drv->id_table); + if (pmu == NULL) + return -ENODEV; + } else { + /* + * for performance monitoring unit with multiple boxes, + * each box has a different function id. + */ + pmu = &type->pmus[UNCORE_PCI_DEV_IDX(id->driver_data)]; + } + + ret = uncore_pci_pmu_register(pdev, type, pmu, phys_id, die); + + pci_set_drvdata(pdev, pmu->boxes[die]); + + return ret; +} + +/* + * Unregister the PMU of a PCI device + * @pmu: The corresponding PMU is unregistered. + * @phys_id: The physical socket id which the device maps to. + * @die: The die id which the device maps to. + */ +static void uncore_pci_pmu_unregister(struct intel_uncore_pmu *pmu, + int phys_id, int die) +{ + struct intel_uncore_box *box = pmu->boxes[die]; + + if (WARN_ON_ONCE(phys_id != box->pci_phys_id)) + return; + + pmu->boxes[die] = NULL; + if (atomic_dec_return(&pmu->activeboxes) == 0) + uncore_pmu_unregister(pmu); + uncore_box_exit(box); + kfree(box); +} + static void uncore_pci_remove(struct pci_dev *pdev) { struct intel_uncore_box *box; struct intel_uncore_pmu *pmu; int i, phys_id, die; - phys_id = uncore_pcibus_to_physid(pdev->bus); + if (uncore_pci_get_dev_die_info(pdev, &phys_id, &die)) + return; box = pci_get_drvdata(pdev); if (!box) { - die = (topology_max_die_per_package() > 1) ? phys_id : - topology_phys_to_logical_pkg(phys_id); for (i = 0; i < UNCORE_EXTRA_PCI_DEV_MAX; i++) { if (uncore_extra_pci_dev[die].dev[i] == pdev) { uncore_extra_pci_dev[die].dev[i] = NULL; @@ -1107,15 +1182,84 @@ static void uncore_pci_remove(struct pci_dev *pdev) } pmu = box->pmu; - if (WARN_ON_ONCE(phys_id != box->pci_phys_id)) - return; pci_set_drvdata(pdev, NULL); - pmu->boxes[box->dieid] = NULL; - if (atomic_dec_return(&pmu->activeboxes) == 0) - uncore_pmu_unregister(pmu); - uncore_box_exit(box); - kfree(box); + + uncore_pci_pmu_unregister(pmu, phys_id, die); +} + +static int uncore_bus_notify(struct notifier_block *nb, + unsigned long action, void *data) +{ + struct device *dev = data; + struct pci_dev *pdev = to_pci_dev(dev); + struct intel_uncore_pmu *pmu; + int phys_id, die; + + /* Unregister the PMU when the device is going to be deleted. */ + if (action != BUS_NOTIFY_DEL_DEVICE) + return NOTIFY_DONE; + + pmu = uncore_pci_find_dev_pmu(pdev, uncore_pci_sub_driver->id_table); + if (!pmu) + return NOTIFY_DONE; + + if (uncore_pci_get_dev_die_info(pdev, &phys_id, &die)) + return NOTIFY_DONE; + + uncore_pci_pmu_unregister(pmu, phys_id, die); + + return NOTIFY_OK; +} + +static struct notifier_block uncore_notifier = { + .notifier_call = uncore_bus_notify, +}; + +static void uncore_pci_sub_driver_init(void) +{ + const struct pci_device_id *ids = uncore_pci_sub_driver->id_table; + struct intel_uncore_type *type; + struct intel_uncore_pmu *pmu; + struct pci_dev *pci_sub_dev; + bool notify = false; + unsigned int devfn; + int phys_id, die; + + while (ids && ids->vendor) { + pci_sub_dev = NULL; + type = uncore_pci_uncores[UNCORE_PCI_DEV_TYPE(ids->driver_data)]; + /* + * Search the available device, and register the + * corresponding PMU. + */ + while ((pci_sub_dev = pci_get_device(PCI_VENDOR_ID_INTEL, + ids->device, pci_sub_dev))) { + devfn = PCI_DEVFN(UNCORE_PCI_DEV_DEV(ids->driver_data), + UNCORE_PCI_DEV_FUNC(ids->driver_data)); + if (devfn != pci_sub_dev->devfn) + continue; + + pmu = &type->pmus[UNCORE_PCI_DEV_IDX(ids->driver_data)]; + if (!pmu) + continue; + + if (uncore_pci_get_dev_die_info(pci_sub_dev, + &phys_id, &die)) + continue; + + if (!uncore_pci_pmu_register(pci_sub_dev, type, pmu, + phys_id, die)) + notify = true; + } + ids++; + } + + if (notify && bus_register_notifier(&pci_bus_type, &uncore_notifier)) + notify = false; + + if (!notify) + uncore_pci_sub_driver = NULL; } static int __init uncore_pci_init(void) @@ -1141,6 +1285,9 @@ static int __init uncore_pci_init(void) if (ret) goto errtype; + if (uncore_pci_sub_driver) + uncore_pci_sub_driver_init(); + pcidrv_registered = true; return 0; @@ -1158,6 +1305,8 @@ static void uncore_pci_exit(void) { if (pcidrv_registered) { pcidrv_registered = false; + if (uncore_pci_sub_driver) + bus_unregister_notifier(&pci_bus_type, &uncore_notifier); pci_unregister_driver(uncore_pci_driver); uncore_types_exit(uncore_pci_uncores); kfree(uncore_extra_pci_dev); @@ -1478,12 +1627,12 @@ static const struct intel_uncore_init_fun icl_uncore_init __initconst = { }; static const struct intel_uncore_init_fun tgl_uncore_init __initconst = { - .cpu_init = icl_uncore_cpu_init, + .cpu_init = tgl_uncore_cpu_init, .mmio_init = tgl_uncore_mmio_init, }; static const struct intel_uncore_init_fun tgl_l_uncore_init __initconst = { - .cpu_init = icl_uncore_cpu_init, + .cpu_init = tgl_uncore_cpu_init, .mmio_init = tgl_l_uncore_mmio_init, }; diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h index 105fdc69825e..83d2a7d490e0 100644 --- a/arch/x86/events/intel/uncore.h +++ b/arch/x86/events/intel/uncore.h @@ -552,6 +552,7 @@ extern struct intel_uncore_type **uncore_msr_uncores; extern struct intel_uncore_type **uncore_pci_uncores; extern struct intel_uncore_type **uncore_mmio_uncores; extern struct pci_driver *uncore_pci_driver; +extern struct pci_driver *uncore_pci_sub_driver; extern raw_spinlock_t pci2phy_map_lock; extern struct list_head pci2phy_map_head; extern struct pci_extra_dev *uncore_extra_pci_dev; @@ -567,6 +568,7 @@ void snb_uncore_cpu_init(void); void nhm_uncore_cpu_init(void); void skl_uncore_cpu_init(void); void icl_uncore_cpu_init(void); +void tgl_uncore_cpu_init(void); void tgl_uncore_mmio_init(void); void tgl_l_uncore_mmio_init(void); int snb_pci2phy_map_init(int devid); diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index 6a4ca27b2c9e..39e632ed6ca9 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -126,6 +126,10 @@ #define ICL_UNC_CBO_0_PER_CTR0 0x702 #define ICL_UNC_CBO_MSR_OFFSET 0x8 +/* ICL ARB register */ +#define ICL_UNC_ARB_PER_CTR 0x3b1 +#define ICL_UNC_ARB_PERFEVTSEL 0x3b3 + DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7"); DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15"); DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18"); @@ -313,15 +317,21 @@ void skl_uncore_cpu_init(void) snb_uncore_arb.ops = &skl_uncore_msr_ops; } +static struct intel_uncore_ops icl_uncore_msr_ops = { + .disable_event = snb_uncore_msr_disable_event, + .enable_event = snb_uncore_msr_enable_event, + .read_counter = uncore_msr_read_counter, +}; + static struct intel_uncore_type icl_uncore_cbox = { .name = "cbox", - .num_counters = 4, + .num_counters = 2, .perf_ctr_bits = 44, .perf_ctr = ICL_UNC_CBO_0_PER_CTR0, .event_ctl = SNB_UNC_CBO_0_PERFEVTSEL0, .event_mask = SNB_UNC_RAW_EVENT_MASK, .msr_offset = ICL_UNC_CBO_MSR_OFFSET, - .ops = &skl_uncore_msr_ops, + .ops = &icl_uncore_msr_ops, .format_group = &snb_uncore_format_group, }; @@ -350,13 +360,25 @@ static struct intel_uncore_type icl_uncore_clockbox = { .single_fixed = 1, .event_mask = SNB_UNC_CTL_EV_SEL_MASK, .format_group = &icl_uncore_clock_format_group, - .ops = &skl_uncore_msr_ops, + .ops = &icl_uncore_msr_ops, .event_descs = icl_uncore_events, }; +static struct intel_uncore_type icl_uncore_arb = { + .name = "arb", + .num_counters = 1, + .num_boxes = 1, + .perf_ctr_bits = 44, + .perf_ctr = ICL_UNC_ARB_PER_CTR, + .event_ctl = ICL_UNC_ARB_PERFEVTSEL, + .event_mask = SNB_UNC_RAW_EVENT_MASK, + .ops = &icl_uncore_msr_ops, + .format_group = &snb_uncore_format_group, +}; + static struct intel_uncore_type *icl_msr_uncores[] = { &icl_uncore_cbox, - &snb_uncore_arb, + &icl_uncore_arb, &icl_uncore_clockbox, NULL, }; @@ -374,6 +396,21 @@ void icl_uncore_cpu_init(void) { uncore_msr_uncores = icl_msr_uncores; icl_uncore_cbox.num_boxes = icl_get_cbox_num(); +} + +static struct intel_uncore_type *tgl_msr_uncores[] = { + &icl_uncore_cbox, + &snb_uncore_arb, + &icl_uncore_clockbox, + NULL, +}; + +void tgl_uncore_cpu_init(void) +{ + uncore_msr_uncores = tgl_msr_uncores; + icl_uncore_cbox.num_boxes = icl_get_cbox_num(); + icl_uncore_cbox.ops = &skl_uncore_msr_ops; + icl_uncore_clockbox.ops = &skl_uncore_msr_ops; snb_uncore_arb.ops = &skl_uncore_msr_ops; } diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 62e88ad919ff..7bdb1821215d 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -393,6 +393,11 @@ #define SNR_M2M_PCI_PMON_BOX_CTL 0x438 #define SNR_M2M_PCI_PMON_UMASK_EXT 0xff +/* SNR PCIE3 */ +#define SNR_PCIE3_PCI_PMON_CTL0 0x508 +#define SNR_PCIE3_PCI_PMON_CTR0 0x4e8 +#define SNR_PCIE3_PCI_PMON_BOX_CTL 0x4e0 + /* SNR IMC */ #define SNR_IMC_MMIO_PMON_FIXED_CTL 0x54 #define SNR_IMC_MMIO_PMON_FIXED_CTR 0x38 @@ -3749,7 +3754,9 @@ static int skx_iio_set_mapping(struct intel_uncore_type *type) ret = skx_iio_get_topology(type); if (ret) - return ret; + goto clear_attr_update; + + ret = -ENOMEM; /* One more for NULL. */ attrs = kcalloc((uncore_max_dies() + 1), sizeof(*attrs), GFP_KERNEL); @@ -3781,8 +3788,9 @@ err: kfree(eas); kfree(attrs); kfree(type->topology); +clear_attr_update: type->attr_update = NULL; - return -ENOMEM; + return ret; } static void skx_iio_cleanup_mapping(struct intel_uncore_type *type) @@ -4551,12 +4559,46 @@ static struct intel_uncore_type snr_uncore_m2m = { .format_group = &snr_m2m_uncore_format_group, }; +static void snr_uncore_pci_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct pci_dev *pdev = box->pci_dev; + struct hw_perf_event *hwc = &event->hw; + + pci_write_config_dword(pdev, hwc->config_base, (u32)(hwc->config | SNBEP_PMON_CTL_EN)); + pci_write_config_dword(pdev, hwc->config_base + 4, (u32)(hwc->config >> 32)); +} + +static struct intel_uncore_ops snr_pcie3_uncore_pci_ops = { + .init_box = snr_m2m_uncore_pci_init_box, + .disable_box = snbep_uncore_pci_disable_box, + .enable_box = snbep_uncore_pci_enable_box, + .disable_event = snbep_uncore_pci_disable_event, + .enable_event = snr_uncore_pci_enable_event, + .read_counter = snbep_uncore_pci_read_counter, +}; + +static struct intel_uncore_type snr_uncore_pcie3 = { + .name = "pcie3", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .perf_ctr = SNR_PCIE3_PCI_PMON_CTR0, + .event_ctl = SNR_PCIE3_PCI_PMON_CTL0, + .event_mask = SKX_IIO_PMON_RAW_EVENT_MASK, + .event_mask_ext = SKX_IIO_PMON_RAW_EVENT_MASK_EXT, + .box_ctl = SNR_PCIE3_PCI_PMON_BOX_CTL, + .ops = &snr_pcie3_uncore_pci_ops, + .format_group = &skx_uncore_iio_format_group, +}; + enum { SNR_PCI_UNCORE_M2M, + SNR_PCI_UNCORE_PCIE3, }; static struct intel_uncore_type *snr_pci_uncores[] = { [SNR_PCI_UNCORE_M2M] = &snr_uncore_m2m, + [SNR_PCI_UNCORE_PCIE3] = &snr_uncore_pcie3, NULL, }; @@ -4573,6 +4615,19 @@ static struct pci_driver snr_uncore_pci_driver = { .id_table = snr_uncore_pci_ids, }; +static const struct pci_device_id snr_uncore_pci_sub_ids[] = { + { /* PCIe3 RP */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x334a), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(4, 0, SNR_PCI_UNCORE_PCIE3, 0), + }, + { /* end: all zeroes */ } +}; + +static struct pci_driver snr_uncore_pci_sub_driver = { + .name = "snr_uncore_sub", + .id_table = snr_uncore_pci_sub_ids, +}; + int snr_uncore_pci_init(void) { /* SNR UBOX DID */ @@ -4584,6 +4639,7 @@ int snr_uncore_pci_init(void) uncore_pci_uncores = snr_pci_uncores; uncore_pci_driver = &snr_uncore_pci_driver; + uncore_pci_sub_driver = &snr_uncore_pci_sub_driver; return 0; } @@ -4751,10 +4807,10 @@ static struct uncore_event_desc snr_uncore_imc_freerunning_events[] = { INTEL_UNCORE_EVENT_DESC(dclk, "event=0xff,umask=0x10"), INTEL_UNCORE_EVENT_DESC(read, "event=0xff,umask=0x20"), - INTEL_UNCORE_EVENT_DESC(read.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(read.scale, "6.103515625e-5"), INTEL_UNCORE_EVENT_DESC(read.unit, "MiB"), INTEL_UNCORE_EVENT_DESC(write, "event=0xff,umask=0x21"), - INTEL_UNCORE_EVENT_DESC(write.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(write.scale, "6.103515625e-5"), INTEL_UNCORE_EVENT_DESC(write.unit, "MiB"), { /* end: all zeroes */ }, }; @@ -5212,17 +5268,17 @@ static struct uncore_event_desc icx_uncore_imc_freerunning_events[] = { INTEL_UNCORE_EVENT_DESC(dclk, "event=0xff,umask=0x10"), INTEL_UNCORE_EVENT_DESC(read, "event=0xff,umask=0x20"), - INTEL_UNCORE_EVENT_DESC(read.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(read.scale, "6.103515625e-5"), INTEL_UNCORE_EVENT_DESC(read.unit, "MiB"), INTEL_UNCORE_EVENT_DESC(write, "event=0xff,umask=0x21"), - INTEL_UNCORE_EVENT_DESC(write.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(write.scale, "6.103515625e-5"), INTEL_UNCORE_EVENT_DESC(write.unit, "MiB"), INTEL_UNCORE_EVENT_DESC(ddrt_read, "event=0xff,umask=0x30"), - INTEL_UNCORE_EVENT_DESC(ddrt_read.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(ddrt_read.scale, "6.103515625e-5"), INTEL_UNCORE_EVENT_DESC(ddrt_read.unit, "MiB"), INTEL_UNCORE_EVENT_DESC(ddrt_write, "event=0xff,umask=0x31"), - INTEL_UNCORE_EVENT_DESC(ddrt_write.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(ddrt_write.scale, "6.103515625e-5"), INTEL_UNCORE_EVENT_DESC(ddrt_write.unit, "MiB"), { /* end: all zeroes */ }, }; diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c index a949f6f55991..4be8f9cabd07 100644 --- a/arch/x86/events/msr.c +++ b/arch/x86/events/msr.c @@ -78,6 +78,7 @@ static bool test_intel(int idx, void *data) case INTEL_FAM6_ATOM_GOLDMONT_PLUS: case INTEL_FAM6_ATOM_TREMONT_D: case INTEL_FAM6_ATOM_TREMONT: + case INTEL_FAM6_ATOM_TREMONT_L: case INTEL_FAM6_XEON_PHI_KNL: case INTEL_FAM6_XEON_PHI_KNM: diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 7b68ab5f19e7..ee2b9b9fc2a5 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -79,6 +79,31 @@ static inline bool constraint_match(struct event_constraint *c, u64 ecode) #define PERF_X86_EVENT_PEBS_VIA_PT 0x0800 /* use PT buffer for PEBS */ #define PERF_X86_EVENT_PAIR 0x1000 /* Large Increment per Cycle */ #define PERF_X86_EVENT_LBR_SELECT 0x2000 /* Save/Restore MSR_LBR_SELECT */ +#define PERF_X86_EVENT_TOPDOWN 0x4000 /* Count Topdown slots/metrics events */ + +static inline bool is_topdown_count(struct perf_event *event) +{ + return event->hw.flags & PERF_X86_EVENT_TOPDOWN; +} + +static inline bool is_metric_event(struct perf_event *event) +{ + u64 config = event->attr.config; + + return ((config & ARCH_PERFMON_EVENTSEL_EVENT) == 0) && + ((config & INTEL_ARCH_EVENT_MASK) >= INTEL_TD_METRIC_RETIRING) && + ((config & INTEL_ARCH_EVENT_MASK) <= INTEL_TD_METRIC_MAX); +} + +static inline bool is_slots_event(struct perf_event *event) +{ + return (event->attr.config & INTEL_ARCH_EVENT_MASK) == INTEL_TD_SLOTS; +} + +static inline bool is_topdown_event(struct perf_event *event) +{ + return is_metric_event(event) || is_slots_event(event); +} struct amd_nb { int nb_id; /* NorthBridge id */ @@ -210,6 +235,8 @@ struct cpu_hw_events { they've never been enabled yet */ int n_txn; /* the # last events in the below arrays; added in the current transaction */ + int n_txn_pair; + int n_txn_metric; int assign[X86_PMC_IDX_MAX]; /* event to counter assignment */ u64 tags[X86_PMC_IDX_MAX]; @@ -285,6 +312,12 @@ struct cpu_hw_events { u64 tfa_shadow; /* + * Perf Metrics + */ + /* number of accepted metrics events */ + int n_metric; + + /* * AMD specific bits */ struct amd_nb *amd_nb; @@ -376,6 +409,19 @@ struct cpu_hw_events { EVENT_CONSTRAINT(c, (1ULL << (32+n)), FIXED_EVENT_FLAGS) /* + * The special metric counters do not actually exist. They are calculated from + * the combination of the FxCtr3 + MSR_PERF_METRICS. + * + * The special metric counters are mapped to a dummy offset for the scheduler. + * The sharing between multiple users of the same metric without multiplexing + * is not allowed, even though the hardware supports that in principle. + */ + +#define METRIC_EVENT_CONSTRAINT(c, n) \ + EVENT_CONSTRAINT(c, (1ULL << (INTEL_PMC_IDX_METRIC_BASE + n)), \ + INTEL_ARCH_EVENT_MASK) + +/* * Constraint on the Event code + UMask */ #define INTEL_UEVENT_CONSTRAINT(c, n) \ @@ -537,7 +583,7 @@ union perf_capabilities { */ u64 full_width_write:1; u64 pebs_baseline:1; - u64 pebs_metrics_available:1; + u64 perf_metrics:1; u64 pebs_output_pt_available:1; }; u64 capabilities; @@ -727,6 +773,12 @@ struct x86_pmu { atomic_t lbr_exclusive[x86_lbr_exclusive_max]; /* + * Intel perf metrics + */ + u64 (*update_topdown_event)(struct perf_event *event); + int (*set_topdown_event_period)(struct perf_event *event); + + /* * perf task context (i.e. struct perf_event_context::task_ctx_data) * switch helper to bridge calls from perf/core to perf/x86. * See struct pmu::swap_task_ctx() usage for examples; diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c index 67b411f7e8c4..7c0120e2e957 100644 --- a/arch/x86/events/rapl.c +++ b/arch/x86/events/rapl.c @@ -815,6 +815,7 @@ static const struct x86_cpu_id rapl_model_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &model_spr), X86_MATCH_VENDOR_FAM(AMD, 0x17, &model_amd_fam17h), X86_MATCH_VENDOR_FAM(HYGON, 0x18, &model_amd_fam17h), + X86_MATCH_VENDOR_FAM(AMD, 0x19, &model_amd_fam17h), {}, }; MODULE_DEVICE_TABLE(x86cpu, rapl_model_match); diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 6035df1b49e1..e04d90af4c27 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -148,9 +148,9 @@ static inline bool hv_reenlightenment_available(void) * Check for required features and priviliges to make TSC frequency * change notifications work. */ - return ms_hyperv.features & HV_X64_ACCESS_FREQUENCY_MSRS && + return ms_hyperv.features & HV_ACCESS_FREQUENCY_MSRS && ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE && - ms_hyperv.features & HV_X64_ACCESS_REENLIGHTENMENT; + ms_hyperv.features & HV_ACCESS_REENLIGHTENMENT; } DEFINE_IDTENTRY_SYSVEC(sysvec_hyperv_reenlightenment) @@ -330,8 +330,8 @@ void __init hyperv_init(void) return; /* Absolutely required MSRs */ - required_msrs = HV_X64_MSR_HYPERCALL_AVAILABLE | - HV_X64_MSR_VP_INDEX_AVAILABLE; + required_msrs = HV_MSR_HYPERCALL_AVAILABLE | + HV_MSR_VP_INDEX_AVAILABLE; if ((ms_hyperv.features & required_msrs) != required_msrs) return; diff --git a/arch/x86/hyperv/hv_spinlock.c b/arch/x86/hyperv/hv_spinlock.c index 07f21a06392f..f3270c1fc48c 100644 --- a/arch/x86/hyperv/hv_spinlock.c +++ b/arch/x86/hyperv/hv_spinlock.c @@ -66,7 +66,7 @@ void __init hv_init_spinlocks(void) { if (!hv_pvspin || !apic || !(ms_hyperv.hints & HV_X64_CLUSTER_IPI_RECOMMENDED) || - !(ms_hyperv.features & HV_X64_MSR_GUEST_IDLE_AVAILABLE)) { + !(ms_hyperv.features & HV_MSR_GUEST_IDLE_AVAILABLE)) { pr_info("PV spinlocks disabled\n"); return; } diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 2cc44e957c31..1c129abb7f09 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -519,6 +519,14 @@ static inline bool apic_id_is_primary_thread(unsigned int id) { return false; } static inline void apic_smt_update(void) { } #endif +struct msi_msg; + +#ifdef CONFIG_PCI_MSI +void x86_vector_msi_compose_msg(struct irq_data *data, struct msi_msg *msg); +#else +# define x86_vector_msi_compose_msg NULL +#endif + extern void ioapic_zap_locks(void); #endif /* _ASM_X86_APIC_H */ diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index 0359cbbd0f50..0603c7423aca 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -141,11 +141,15 @@ # define _ASM_EXTABLE_FAULT(from, to) \ _ASM_EXTABLE_HANDLE(from, to, ex_handler_fault) -# define _ASM_NOKPROBE(entry) \ +# ifdef CONFIG_KPROBES +# define _ASM_NOKPROBE(entry) \ .pushsection "_kprobe_blacklist","aw" ; \ _ASM_ALIGN ; \ _ASM_PTR (entry); \ .popsection +# else +# define _ASM_NOKPROBE(entry) +# endif #else /* ! __ASSEMBLY__ */ # define _EXPAND_EXTABLE_HANDLE(x) #x diff --git a/arch/x86/include/asm/checksum.h b/arch/x86/include/asm/checksum.h index 0ada98d5d09f..bca625a60186 100644 --- a/arch/x86/include/asm/checksum.h +++ b/arch/x86/include/asm/checksum.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ #define _HAVE_ARCH_COPY_AND_CSUM_FROM_USER 1 #define HAVE_CSUM_COPY_USER +#define _HAVE_ARCH_CSUM_AND_COPY #ifdef CONFIG_X86_32 # include <asm/checksum_32.h> #else diff --git a/arch/x86/include/asm/checksum_32.h b/arch/x86/include/asm/checksum_32.h index 11624c8a9d8d..17da95387997 100644 --- a/arch/x86/include/asm/checksum_32.h +++ b/arch/x86/include/asm/checksum_32.h @@ -27,9 +27,7 @@ asmlinkage __wsum csum_partial(const void *buff, int len, __wsum sum); * better 64-bit) boundary */ -asmlinkage __wsum csum_partial_copy_generic(const void *src, void *dst, - int len, __wsum sum, - int *src_err_ptr, int *dst_err_ptr); +asmlinkage __wsum csum_partial_copy_generic(const void *src, void *dst, int len); /* * Note: when you get a NULL pointer exception here this means someone @@ -38,26 +36,20 @@ asmlinkage __wsum csum_partial_copy_generic(const void *src, void *dst, * If you use these functions directly please don't forget the * access_ok(). */ -static inline __wsum csum_partial_copy_nocheck(const void *src, void *dst, - int len, __wsum sum) +static inline __wsum csum_partial_copy_nocheck(const void *src, void *dst, int len) { - return csum_partial_copy_generic(src, dst, len, sum, NULL, NULL); + return csum_partial_copy_generic(src, dst, len); } static inline __wsum csum_and_copy_from_user(const void __user *src, - void *dst, int len, - __wsum sum, int *err_ptr) + void *dst, int len) { __wsum ret; might_sleep(); - if (!user_access_begin(src, len)) { - if (len) - *err_ptr = -EFAULT; - return sum; - } - ret = csum_partial_copy_generic((__force void *)src, dst, - len, sum, err_ptr, NULL); + if (!user_access_begin(src, len)) + return 0; + ret = csum_partial_copy_generic((__force void *)src, dst, len); user_access_end(); return ret; @@ -178,23 +170,17 @@ static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr, */ static inline __wsum csum_and_copy_to_user(const void *src, void __user *dst, - int len, __wsum sum, - int *err_ptr) + int len) { __wsum ret; might_sleep(); - if (user_access_begin(dst, len)) { - ret = csum_partial_copy_generic(src, (__force void *)dst, - len, sum, NULL, err_ptr); - user_access_end(); - return ret; - } + if (!user_access_begin(dst, len)) + return 0; - if (len) - *err_ptr = -EFAULT; - - return (__force __wsum)-1; /* invalid checksum */ + ret = csum_partial_copy_generic(src, (__force void *)dst, len); + user_access_end(); + return ret; } #endif /* _ASM_X86_CHECKSUM_32_H */ diff --git a/arch/x86/include/asm/checksum_64.h b/arch/x86/include/asm/checksum_64.h index 0a289b87e872..407beebadaf4 100644 --- a/arch/x86/include/asm/checksum_64.h +++ b/arch/x86/include/asm/checksum_64.h @@ -130,17 +130,11 @@ static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr, extern __wsum csum_partial(const void *buff, int len, __wsum sum); /* Do not call this directly. Use the wrappers below */ -extern __visible __wsum csum_partial_copy_generic(const void *src, const void *dst, - int len, __wsum sum, - int *src_err_ptr, int *dst_err_ptr); +extern __visible __wsum csum_partial_copy_generic(const void *src, void *dst, int len); - -extern __wsum csum_and_copy_from_user(const void __user *src, void *dst, - int len, __wsum isum, int *errp); -extern __wsum csum_and_copy_to_user(const void *src, void __user *dst, - int len, __wsum isum, int *errp); -extern __wsum csum_partial_copy_nocheck(const void *src, void *dst, - int len, __wsum sum); +extern __wsum csum_and_copy_from_user(const void __user *src, void *dst, int len); +extern __wsum csum_and_copy_to_user(const void *src, void __user *dst, int len); +extern __wsum csum_partial_copy_nocheck(const void *src, void *dst, int len); /** * ip_compute_csum - Compute an 16bit IP checksum. diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h index d4edf281fff4..0e327a01f50f 100644 --- a/arch/x86/include/asm/compat.h +++ b/arch/x86/include/asm/compat.h @@ -27,8 +27,6 @@ typedef u16 compat_nlink_t; typedef u16 compat_ipc_pid_t; typedef u32 compat_caddr_t; typedef __kernel_fsid_t compat_fsid_t; -typedef s64 __attribute__((aligned(4))) compat_s64; -typedef u64 __attribute__((aligned(4))) compat_u64; struct compat_stat { compat_dev_t st_dev; @@ -211,6 +209,7 @@ static inline bool in_compat_syscall(void) return in_32bit_syscall(); } #define in_compat_syscall in_compat_syscall /* override the generic impl */ +#define compat_need_64bit_alignment_fixup in_ia32_syscall #endif struct compat_siginfo; diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 50b2a8d85ef0..7b0afd5e6c57 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -288,6 +288,7 @@ #define X86_FEATURE_FENCE_SWAPGS_USER (11*32+ 4) /* "" LFENCE in user entry SWAPGS path */ #define X86_FEATURE_FENCE_SWAPGS_KERNEL (11*32+ 5) /* "" LFENCE in kernel entry SWAPGS path */ #define X86_FEATURE_SPLIT_LOCK_DETECT (11*32+ 6) /* #AC for split lock */ +#define X86_FEATURE_PER_THREAD_MBA (11*32+ 7) /* "" Per-thread Memory Bandwidth Allocation */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ @@ -353,6 +354,7 @@ #define X86_FEATURE_CLDEMOTE (16*32+25) /* CLDEMOTE instruction */ #define X86_FEATURE_MOVDIRI (16*32+27) /* MOVDIRI instruction */ #define X86_FEATURE_MOVDIR64B (16*32+28) /* MOVDIR64B instruction */ +#define X86_FEATURE_ENQCMD (16*32+29) /* ENQCMD and ENQCMDS instructions */ /* AMD-defined CPU features, CPUID level 0x80000007 (EBX), word 17 */ #define X86_FEATURE_OVERFLOW_RECOV (17*32+ 0) /* MCA overflow recovery support */ diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h index e89558a3fe4a..cfdf307ddc01 100644 --- a/arch/x86/include/asm/debugreg.h +++ b/arch/x86/include/asm/debugreg.h @@ -90,8 +90,6 @@ static __always_inline bool hw_breakpoint_active(void) return __this_cpu_read(cpu_dr7) & DR_GLOBAL_ENABLE_MASK; } -extern void aout_dump_debugregs(struct user *dump); - extern void hw_breakpoint_restore(void); static __always_inline unsigned long local_db_save(void) diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index 4ea8584682f9..5861d34f9771 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -56,6 +56,12 @@ # define DISABLE_PTI (1 << (X86_FEATURE_PTI & 31)) #endif +#ifdef CONFIG_IOMMU_SUPPORT +# define DISABLE_ENQCMD 0 +#else +# define DISABLE_ENQCMD (1 << (X86_FEATURE_ENQCMD & 31)) +#endif + /* * Make sure to add features to the correct mask */ @@ -75,7 +81,8 @@ #define DISABLED_MASK13 0 #define DISABLED_MASK14 0 #define DISABLED_MASK15 0 -#define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP) +#define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP| \ + DISABLE_ENQCMD) #define DISABLED_MASK17 0 #define DISABLED_MASK18 0 #define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19) diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index 0f0dd645b594..77217bd292bd 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -99,7 +99,7 @@ enum fixed_addresses { FIX_PCIE_MCFG, #endif #endif -#ifdef CONFIG_PARAVIRT +#ifdef CONFIG_PARAVIRT_XXL FIX_PARAVIRT_BOOTMAP, #endif #ifdef CONFIG_X86_INTEL_MID diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h index b774c52e5411..dcd9503b1098 100644 --- a/arch/x86/include/asm/fpu/api.h +++ b/arch/x86/include/asm/fpu/api.h @@ -62,4 +62,16 @@ extern void switch_fpu_return(void); */ extern int cpu_has_xfeatures(u64 xfeatures_mask, const char **feature_name); +/* + * Tasks that are not using SVA have mm->pasid set to zero to note that they + * will not have the valid bit set in MSR_IA32_PASID while they are running. + */ +#define PASID_DISABLED 0 + +#ifdef CONFIG_IOMMU_SUPPORT +/* Update current's PASID MSR/state by mm's PASID. */ +void update_pasid(void); +#else +static inline void update_pasid(void) { } +#endif #endif /* _ASM_X86_FPU_API_H */ diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 21a8b5259477..eb1ed3bd8d96 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -583,6 +583,13 @@ static inline void switch_fpu_finish(struct fpu *new_fpu) pkru_val = pk->pkru; } __write_pkru(pkru_val); + + /* + * Expensive PASID MSR write will be avoided in update_pasid() because + * TIF_NEED_FPU_LOAD was set. And the PASID state won't be updated + * unless it's different from mm->pasid to reduce overhead. + */ + update_pasid(); } /* diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h index c87364ea6446..f5a38a5f3ae1 100644 --- a/arch/x86/include/asm/fpu/types.h +++ b/arch/x86/include/asm/fpu/types.h @@ -114,7 +114,7 @@ enum xfeature { XFEATURE_Hi16_ZMM, XFEATURE_PT_UNIMPLEMENTED_SO_FAR, XFEATURE_PKRU, - XFEATURE_RSRVD_COMP_10, + XFEATURE_PASID, XFEATURE_RSRVD_COMP_11, XFEATURE_RSRVD_COMP_12, XFEATURE_RSRVD_COMP_13, @@ -134,6 +134,7 @@ enum xfeature { #define XFEATURE_MASK_Hi16_ZMM (1 << XFEATURE_Hi16_ZMM) #define XFEATURE_MASK_PT (1 << XFEATURE_PT_UNIMPLEMENTED_SO_FAR) #define XFEATURE_MASK_PKRU (1 << XFEATURE_PKRU) +#define XFEATURE_MASK_PASID (1 << XFEATURE_PASID) #define XFEATURE_MASK_LBR (1 << XFEATURE_LBR) #define XFEATURE_MASK_FPSSE (XFEATURE_MASK_FP | XFEATURE_MASK_SSE) @@ -256,6 +257,14 @@ struct arch_lbr_state { struct lbr_entry entries[]; } __packed; +/* + * State component 10 is supervisor state used for context-switching the + * PASID state. + */ +struct ia32_pasid_state { + u64 pasid; +} __packed; + struct xstate_header { u64 xfeatures; u64 xcomp_bv; diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index 14ab815132d4..47a92232d595 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -35,7 +35,7 @@ XFEATURE_MASK_BNDCSR) /* All currently supported supervisor features */ -#define XFEATURE_MASK_SUPERVISOR_SUPPORTED (0) +#define XFEATURE_MASK_SUPERVISOR_SUPPORTED (XFEATURE_MASK_PASID) /* * A supervisor state component may not always contain valuable information, diff --git a/arch/x86/include/asm/fsgsbase.h b/arch/x86/include/asm/fsgsbase.h index d552646411a9..35cff5f2becf 100644 --- a/arch/x86/include/asm/fsgsbase.h +++ b/arch/x86/include/asm/fsgsbase.h @@ -57,7 +57,7 @@ static inline unsigned long x86_fsbase_read_cpu(void) { unsigned long fsbase; - if (static_cpu_has(X86_FEATURE_FSGSBASE)) + if (boot_cpu_has(X86_FEATURE_FSGSBASE)) fsbase = rdfsbase(); else rdmsrl(MSR_FS_BASE, fsbase); @@ -67,7 +67,7 @@ static inline unsigned long x86_fsbase_read_cpu(void) static inline void x86_fsbase_write_cpu(unsigned long fsbase) { - if (static_cpu_has(X86_FEATURE_FSGSBASE)) + if (boot_cpu_has(X86_FEATURE_FSGSBASE)) wrfsbase(fsbase); else wrmsrl(MSR_FS_BASE, fsbase); diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h index 74c12437401e..a4aeeaace040 100644 --- a/arch/x86/include/asm/hw_irq.h +++ b/arch/x86/include/asm/hw_irq.h @@ -36,61 +36,56 @@ struct msi_desc; enum irq_alloc_type { X86_IRQ_ALLOC_TYPE_IOAPIC = 1, X86_IRQ_ALLOC_TYPE_HPET, - X86_IRQ_ALLOC_TYPE_MSI, - X86_IRQ_ALLOC_TYPE_MSIX, + X86_IRQ_ALLOC_TYPE_PCI_MSI, + X86_IRQ_ALLOC_TYPE_PCI_MSIX, X86_IRQ_ALLOC_TYPE_DMAR, X86_IRQ_ALLOC_TYPE_UV, + X86_IRQ_ALLOC_TYPE_IOAPIC_GET_PARENT, + X86_IRQ_ALLOC_TYPE_HPET_GET_PARENT, }; +struct ioapic_alloc_info { + int pin; + int node; + u32 trigger : 1; + u32 polarity : 1; + u32 valid : 1; + struct IO_APIC_route_entry *entry; +}; + +struct uv_alloc_info { + int limit; + int blade; + unsigned long offset; + char *name; + +}; + +/** + * irq_alloc_info - X86 specific interrupt allocation info + * @type: X86 specific allocation type + * @flags: Flags for allocation tweaks + * @devid: Device ID for allocations + * @hwirq: Associated hw interrupt number in the domain + * @mask: CPU mask for vector allocation + * @desc: Pointer to msi descriptor + * @data: Allocation specific data + * + * @ioapic: IOAPIC specific allocation data + * @uv: UV specific allocation data +*/ struct irq_alloc_info { enum irq_alloc_type type; u32 flags; - const struct cpumask *mask; /* CPU mask for vector allocation */ + u32 devid; + irq_hw_number_t hwirq; + const struct cpumask *mask; + struct msi_desc *desc; + void *data; + union { - int unused; -#ifdef CONFIG_HPET_TIMER - struct { - int hpet_id; - int hpet_index; - void *hpet_data; - }; -#endif -#ifdef CONFIG_PCI_MSI - struct { - struct pci_dev *msi_dev; - irq_hw_number_t msi_hwirq; - }; -#endif -#ifdef CONFIG_X86_IO_APIC - struct { - int ioapic_id; - int ioapic_pin; - int ioapic_node; - u32 ioapic_trigger : 1; - u32 ioapic_polarity : 1; - u32 ioapic_valid : 1; - struct IO_APIC_route_entry *ioapic_entry; - }; -#endif -#ifdef CONFIG_DMAR_TABLE - struct { - int dmar_id; - void *dmar_data; - }; -#endif -#ifdef CONFIG_X86_UV - struct { - int uv_limit; - int uv_blade; - unsigned long uv_offset; - char *uv_name; - }; -#endif -#if IS_ENABLED(CONFIG_VMD) - struct { - struct msi_desc *desc; - }; -#endif + struct ioapic_alloc_info ioapic; + struct uv_alloc_info uv; }; }; diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h index 7a4d2062385c..0ed20e8bba9e 100644 --- a/arch/x86/include/asm/hyperv-tlfs.h +++ b/arch/x86/include/asm/hyperv-tlfs.h @@ -28,39 +28,6 @@ #define HYPERV_CPUID_MAX 0x4000ffff /* - * Aliases for Group A features that have X64 in the name. - * On x86/x64 these are HYPERV_CPUID_FEATURES.EAX bits. - */ - -#define HV_X64_MSR_VP_RUNTIME_AVAILABLE \ - HV_MSR_VP_RUNTIME_AVAILABLE -#define HV_X64_MSR_SYNIC_AVAILABLE \ - HV_MSR_SYNIC_AVAILABLE -#define HV_X64_MSR_APIC_ACCESS_AVAILABLE \ - HV_MSR_APIC_ACCESS_AVAILABLE -#define HV_X64_MSR_HYPERCALL_AVAILABLE \ - HV_MSR_HYPERCALL_AVAILABLE -#define HV_X64_MSR_VP_INDEX_AVAILABLE \ - HV_MSR_VP_INDEX_AVAILABLE -#define HV_X64_MSR_RESET_AVAILABLE \ - HV_MSR_RESET_AVAILABLE -#define HV_X64_MSR_GUEST_IDLE_AVAILABLE \ - HV_MSR_GUEST_IDLE_AVAILABLE -#define HV_X64_ACCESS_FREQUENCY_MSRS \ - HV_ACCESS_FREQUENCY_MSRS -#define HV_X64_ACCESS_REENLIGHTENMENT \ - HV_ACCESS_REENLIGHTENMENT -#define HV_X64_ACCESS_TSC_INVARIANT \ - HV_ACCESS_TSC_INVARIANT - -/* - * Aliases for Group B features that have X64 in the name. - * On x86/x64 these are HYPERV_CPUID_FEATURES.EBX bits. - */ -#define HV_X64_POST_MESSAGES HV_POST_MESSAGES -#define HV_X64_SIGNAL_EVENTS HV_SIGNAL_EVENTS - -/* * Group D Features. The bit assignments are custom to each architecture. * On x86/x64 these are HYPERV_CPUID_FEATURES.EDX bits. */ diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h index df4dc975e8fd..cdd41d039cd1 100644 --- a/arch/x86/include/asm/idtentry.h +++ b/arch/x86/include/asm/idtentry.h @@ -547,7 +547,7 @@ DECLARE_IDTENTRY_RAW(X86_TRAP_MC, exc_machine_check); /* NMI */ DECLARE_IDTENTRY_NMI(X86_TRAP_NMI, exc_nmi); -#if defined(CONFIG_XEN_PV) && defined(CONFIG_X86_64) +#ifdef CONFIG_XEN_PV DECLARE_IDTENTRY_RAW(X86_TRAP_NMI, xenpv_exc_nmi); #endif @@ -557,7 +557,7 @@ DECLARE_IDTENTRY_DEBUG(X86_TRAP_DB, exc_debug); #else DECLARE_IDTENTRY_RAW(X86_TRAP_DB, exc_debug); #endif -#if defined(CONFIG_XEN_PV) && defined(CONFIG_X86_64) +#ifdef CONFIG_XEN_PV DECLARE_IDTENTRY_RAW(X86_TRAP_DB, xenpv_exc_debug); #endif diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index e1aa17a468a8..d726459d08e5 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -401,7 +401,7 @@ extern bool phys_mem_access_encrypted(unsigned long phys_addr, /** * iosubmit_cmds512 - copy data to single MMIO location, in 512-bit units - * @__dst: destination, in MMIO space (must be 512-bit aligned) + * @dst: destination, in MMIO space (must be 512-bit aligned) * @src: source * @count: number of 512 bits quantities to submit * @@ -412,25 +412,14 @@ extern bool phys_mem_access_encrypted(unsigned long phys_addr, * Warning: Do not use this helper unless your driver has checked that the CPU * instruction is supported on the platform. */ -static inline void iosubmit_cmds512(void __iomem *__dst, const void *src, +static inline void iosubmit_cmds512(void __iomem *dst, const void *src, size_t count) { - /* - * Note that this isn't an "on-stack copy", just definition of "dst" - * as a pointer to 64-bytes of stuff that is going to be overwritten. - * In the MOVDIR64B case that may be needed as you can use the - * MOVDIR64B instruction to copy arbitrary memory around. This trick - * lets the compiler know how much gets clobbered. - */ - volatile struct { char _[64]; } *dst = __dst; const u8 *from = src; const u8 *end = from + count * 64; while (from < end) { - /* MOVDIR64B [rdx], rax */ - asm volatile(".byte 0x66, 0x0f, 0x38, 0xf8, 0x02" - : "=m" (dst) - : "d" (from), "a" (dst)); + movdir64b(dst, from); from += 64; } } diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h index 4bc985f1e2e4..af4a151d70b3 100644 --- a/arch/x86/include/asm/irq_remapping.h +++ b/arch/x86/include/asm/irq_remapping.h @@ -45,8 +45,6 @@ extern int irq_remap_enable_fault_handling(void); extern void panic_if_irq_remap(const char *msg); extern struct irq_domain * -irq_remapping_get_ir_irq_domain(struct irq_alloc_info *info); -extern struct irq_domain * irq_remapping_get_irq_domain(struct irq_alloc_info *info); /* Create PCI MSI/MSIx irqdomain, use @parent as the parent irqdomain. */ @@ -74,12 +72,6 @@ static inline void panic_if_irq_remap(const char *msg) } static inline struct irq_domain * -irq_remapping_get_ir_irq_domain(struct irq_alloc_info *info) -{ - return NULL; -} - -static inline struct irq_domain * irq_remapping_get_irq_domain(struct irq_alloc_info *info) { return NULL; diff --git a/arch/x86/include/asm/irqdomain.h b/arch/x86/include/asm/irqdomain.h index c066ffae222b..cd684d45cb5f 100644 --- a/arch/x86/include/asm/irqdomain.h +++ b/arch/x86/include/asm/irqdomain.h @@ -51,9 +51,13 @@ extern int mp_irqdomain_ioapic_idx(struct irq_domain *domain); #endif /* CONFIG_X86_IO_APIC */ #ifdef CONFIG_PCI_MSI -extern void arch_init_msi_domain(struct irq_domain *domain); +void x86_create_pci_msi_domain(void); +struct irq_domain *native_create_pci_msi_domain(void); +extern struct irq_domain *x86_pci_msi_default_domain; #else -static inline void arch_init_msi_domain(struct irq_domain *domain) { } +static inline void x86_create_pci_msi_domain(void) { } +#define native_create_pci_msi_domain NULL +#define x86_pci_msi_default_domain NULL #endif #endif diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h index 143bc9abe99c..991a7ad540c7 100644 --- a/arch/x86/include/asm/kprobes.h +++ b/arch/x86/include/asm/kprobes.h @@ -106,5 +106,9 @@ extern int kprobe_exceptions_notify(struct notifier_block *self, extern int kprobe_int3_handler(struct pt_regs *regs); extern int kprobe_debug_handler(struct pt_regs *regs); +#else + +static inline int kprobe_debug_handler(struct pt_regs *regs) { return 0; } + #endif /* CONFIG_KPROBES */ #endif /* _ASM_X86_KPROBES_H */ diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h index 606cbaebd336..e90ac7e9ae2c 100644 --- a/arch/x86/include/asm/mpspec.h +++ b/arch/x86/include/asm/mpspec.h @@ -67,21 +67,11 @@ static inline void find_smp_config(void) #ifdef CONFIG_X86_MPPARSE extern void e820__memblock_alloc_reserved_mpc_new(void); extern int enable_update_mptable; -extern int default_mpc_apic_id(struct mpc_cpu *m); -extern void default_smp_read_mpc_oem(struct mpc_table *mpc); -# ifdef CONFIG_X86_IO_APIC -extern void default_mpc_oem_bus_info(struct mpc_bus *m, char *str); -# else -# define default_mpc_oem_bus_info NULL -# endif extern void default_find_smp_config(void); extern void default_get_smp_config(unsigned int early); #else static inline void e820__memblock_alloc_reserved_mpc_new(void) { } #define enable_update_mptable 0 -#define default_mpc_apic_id NULL -#define default_smp_read_mpc_oem NULL -#define default_mpc_oem_bus_info NULL #define default_find_smp_config x86_init_noop #define default_get_smp_config x86_init_uint_noop #endif diff --git a/arch/x86/include/asm/msi.h b/arch/x86/include/asm/msi.h index 25ddd0916bb2..cd30013d15d3 100644 --- a/arch/x86/include/asm/msi.h +++ b/arch/x86/include/asm/msi.h @@ -9,6 +9,4 @@ typedef struct irq_alloc_info msi_alloc_info_t; int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec, msi_alloc_info_t *arg); -void pci_msi_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc); - #endif /* _ASM_X86_MSI_H */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 2859ee4f39a8..c07a70ce7ffd 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -257,6 +257,9 @@ #define MSR_IA32_LASTINTFROMIP 0x000001dd #define MSR_IA32_LASTINTTOIP 0x000001de +#define MSR_IA32_PASID 0x00000d93 +#define MSR_IA32_PASID_VALID BIT_ULL(31) + /* DEBUGCTLMSR bits (others vary by model): */ #define DEBUGCTLMSR_LBR (1UL << 0) /* last branch recording */ #define DEBUGCTLMSR_BTF_SHIFT 1 @@ -464,6 +467,7 @@ #define MSR_AMD64_IBSOP_REG_MASK ((1UL<<MSR_AMD64_IBSOP_REG_COUNT)-1) #define MSR_AMD64_IBSCTL 0xc001103a #define MSR_AMD64_IBSBRTARGET 0xc001103b +#define MSR_AMD64_ICIBSEXTDCTL 0xc001103c #define MSR_AMD64_IBSOPDATA4 0xc001103d #define MSR_AMD64_IBS_REG_COUNT_MAX 8 /* includes MSR_AMD64_IBSBRTARGET */ #define MSR_AMD64_SEV 0xc0010131 @@ -857,11 +861,14 @@ #define MSR_CORE_PERF_FIXED_CTR0 0x00000309 #define MSR_CORE_PERF_FIXED_CTR1 0x0000030a #define MSR_CORE_PERF_FIXED_CTR2 0x0000030b +#define MSR_CORE_PERF_FIXED_CTR3 0x0000030c #define MSR_CORE_PERF_FIXED_CTR_CTRL 0x0000038d #define MSR_CORE_PERF_GLOBAL_STATUS 0x0000038e #define MSR_CORE_PERF_GLOBAL_CTRL 0x0000038f #define MSR_CORE_PERF_GLOBAL_OVF_CTRL 0x00000390 +#define MSR_PERF_METRICS 0x00000329 + /* PERF_GLOBAL_OVF_CTL bits */ #define MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI_BIT 55 #define MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI (1ULL << MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI_BIT) diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 3d2afecde50c..d25cc6830e89 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -160,8 +160,6 @@ static inline void wbinvd(void) PVOP_VCALL0(cpu.wbinvd); } -#define get_kernel_rpl() (pv_info.kernel_rpl) - static inline u64 paravirt_read_msr(unsigned msr) { return PVOP_CALL1(u64, cpu.read_msr, msr); @@ -277,12 +275,10 @@ static inline void load_TLS(struct thread_struct *t, unsigned cpu) PVOP_VCALL2(cpu.load_tls, t, cpu); } -#ifdef CONFIG_X86_64 static inline void load_gs_index(unsigned int gs) { PVOP_VCALL1(cpu.load_gs_index, gs); } -#endif static inline void write_ldt_entry(struct desc_struct *dt, int entry, const void *desc) @@ -375,52 +371,22 @@ static inline void paravirt_release_p4d(unsigned long pfn) static inline pte_t __pte(pteval_t val) { - pteval_t ret; - - if (sizeof(pteval_t) > sizeof(long)) - ret = PVOP_CALLEE2(pteval_t, mmu.make_pte, val, (u64)val >> 32); - else - ret = PVOP_CALLEE1(pteval_t, mmu.make_pte, val); - - return (pte_t) { .pte = ret }; + return (pte_t) { PVOP_CALLEE1(pteval_t, mmu.make_pte, val) }; } static inline pteval_t pte_val(pte_t pte) { - pteval_t ret; - - if (sizeof(pteval_t) > sizeof(long)) - ret = PVOP_CALLEE2(pteval_t, mmu.pte_val, - pte.pte, (u64)pte.pte >> 32); - else - ret = PVOP_CALLEE1(pteval_t, mmu.pte_val, pte.pte); - - return ret; + return PVOP_CALLEE1(pteval_t, mmu.pte_val, pte.pte); } static inline pgd_t __pgd(pgdval_t val) { - pgdval_t ret; - - if (sizeof(pgdval_t) > sizeof(long)) - ret = PVOP_CALLEE2(pgdval_t, mmu.make_pgd, val, (u64)val >> 32); - else - ret = PVOP_CALLEE1(pgdval_t, mmu.make_pgd, val); - - return (pgd_t) { ret }; + return (pgd_t) { PVOP_CALLEE1(pgdval_t, mmu.make_pgd, val) }; } static inline pgdval_t pgd_val(pgd_t pgd) { - pgdval_t ret; - - if (sizeof(pgdval_t) > sizeof(long)) - ret = PVOP_CALLEE2(pgdval_t, mmu.pgd_val, - pgd.pgd, (u64)pgd.pgd >> 32); - else - ret = PVOP_CALLEE1(pgdval_t, mmu.pgd_val, pgd.pgd); - - return ret; + return PVOP_CALLEE1(pgdval_t, mmu.pgd_val, pgd.pgd); } #define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION @@ -438,78 +404,34 @@ static inline void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned pte_t *ptep, pte_t old_pte, pte_t pte) { - if (sizeof(pteval_t) > sizeof(long)) - /* 5 arg words */ - pv_ops.mmu.ptep_modify_prot_commit(vma, addr, ptep, pte); - else - PVOP_VCALL4(mmu.ptep_modify_prot_commit, - vma, addr, ptep, pte.pte); + PVOP_VCALL4(mmu.ptep_modify_prot_commit, vma, addr, ptep, pte.pte); } static inline void set_pte(pte_t *ptep, pte_t pte) { - if (sizeof(pteval_t) > sizeof(long)) - PVOP_VCALL3(mmu.set_pte, ptep, pte.pte, (u64)pte.pte >> 32); - else - PVOP_VCALL2(mmu.set_pte, ptep, pte.pte); -} - -static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte) -{ - if (sizeof(pteval_t) > sizeof(long)) - /* 5 arg words */ - pv_ops.mmu.set_pte_at(mm, addr, ptep, pte); - else - PVOP_VCALL4(mmu.set_pte_at, mm, addr, ptep, pte.pte); + PVOP_VCALL2(mmu.set_pte, ptep, pte.pte); } static inline void set_pmd(pmd_t *pmdp, pmd_t pmd) { - pmdval_t val = native_pmd_val(pmd); - - if (sizeof(pmdval_t) > sizeof(long)) - PVOP_VCALL3(mmu.set_pmd, pmdp, val, (u64)val >> 32); - else - PVOP_VCALL2(mmu.set_pmd, pmdp, val); + PVOP_VCALL2(mmu.set_pmd, pmdp, native_pmd_val(pmd)); } -#if CONFIG_PGTABLE_LEVELS >= 3 static inline pmd_t __pmd(pmdval_t val) { - pmdval_t ret; - - if (sizeof(pmdval_t) > sizeof(long)) - ret = PVOP_CALLEE2(pmdval_t, mmu.make_pmd, val, (u64)val >> 32); - else - ret = PVOP_CALLEE1(pmdval_t, mmu.make_pmd, val); - - return (pmd_t) { ret }; + return (pmd_t) { PVOP_CALLEE1(pmdval_t, mmu.make_pmd, val) }; } static inline pmdval_t pmd_val(pmd_t pmd) { - pmdval_t ret; - - if (sizeof(pmdval_t) > sizeof(long)) - ret = PVOP_CALLEE2(pmdval_t, mmu.pmd_val, - pmd.pmd, (u64)pmd.pmd >> 32); - else - ret = PVOP_CALLEE1(pmdval_t, mmu.pmd_val, pmd.pmd); - - return ret; + return PVOP_CALLEE1(pmdval_t, mmu.pmd_val, pmd.pmd); } static inline void set_pud(pud_t *pudp, pud_t pud) { - pudval_t val = native_pud_val(pud); - - if (sizeof(pudval_t) > sizeof(long)) - PVOP_VCALL3(mmu.set_pud, pudp, val, (u64)val >> 32); - else - PVOP_VCALL2(mmu.set_pud, pudp, val); + PVOP_VCALL2(mmu.set_pud, pudp, native_pud_val(pud)); } -#if CONFIG_PGTABLE_LEVELS >= 4 + static inline pud_t __pud(pudval_t val) { pudval_t ret; @@ -526,7 +448,7 @@ static inline pudval_t pud_val(pud_t pud) static inline void pud_clear(pud_t *pudp) { - set_pud(pudp, __pud(0)); + set_pud(pudp, native_make_pud(0)); } static inline void set_p4d(p4d_t *p4dp, p4d_t p4d) @@ -563,40 +485,17 @@ static inline void __set_pgd(pgd_t *pgdp, pgd_t pgd) } while (0) #define pgd_clear(pgdp) do { \ - if (pgtable_l5_enabled()) \ - set_pgd(pgdp, __pgd(0)); \ + if (pgtable_l5_enabled()) \ + set_pgd(pgdp, native_make_pgd(0)); \ } while (0) #endif /* CONFIG_PGTABLE_LEVELS == 5 */ static inline void p4d_clear(p4d_t *p4dp) { - set_p4d(p4dp, __p4d(0)); + set_p4d(p4dp, native_make_p4d(0)); } -#endif /* CONFIG_PGTABLE_LEVELS == 4 */ - -#endif /* CONFIG_PGTABLE_LEVELS >= 3 */ - -#ifdef CONFIG_X86_PAE -/* Special-case pte-setting operations for PAE, which can't update a - 64-bit pte atomically */ -static inline void set_pte_atomic(pte_t *ptep, pte_t pte) -{ - PVOP_VCALL3(mmu.set_pte_atomic, ptep, pte.pte, pte.pte >> 32); -} - -static inline void pte_clear(struct mm_struct *mm, unsigned long addr, - pte_t *ptep) -{ - PVOP_VCALL3(mmu.pte_clear, mm, addr, ptep); -} - -static inline void pmd_clear(pmd_t *pmdp) -{ - PVOP_VCALL1(mmu.pmd_clear, pmdp); -} -#else /* !CONFIG_X86_PAE */ static inline void set_pte_atomic(pte_t *ptep, pte_t pte) { set_pte(ptep, pte); @@ -605,14 +504,13 @@ static inline void set_pte_atomic(pte_t *ptep, pte_t pte) static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - set_pte_at(mm, addr, ptep, __pte(0)); + set_pte(ptep, native_make_pte(0)); } static inline void pmd_clear(pmd_t *pmdp) { - set_pmd(pmdp, __pmd(0)); + set_pmd(pmdp, native_make_pmd(0)); } -#endif /* CONFIG_X86_PAE */ #define __HAVE_ARCH_START_CONTEXT_SWITCH static inline void arch_start_context_switch(struct task_struct *prev) @@ -682,16 +580,9 @@ bool __raw_callee_save___native_vcpu_is_preempted(long cpu); #endif /* SMP && PARAVIRT_SPINLOCKS */ #ifdef CONFIG_X86_32 -#define PV_SAVE_REGS "pushl %ecx; pushl %edx;" -#define PV_RESTORE_REGS "popl %edx; popl %ecx;" - /* save and restore all caller-save registers, except return value */ #define PV_SAVE_ALL_CALLER_REGS "pushl %ecx;" #define PV_RESTORE_ALL_CALLER_REGS "popl %ecx;" - -#define PV_FLAGS_ARG "0" -#define PV_EXTRA_CLOBBERS -#define PV_VEXTRA_CLOBBERS #else /* save and restore all caller-save registers, except return value */ #define PV_SAVE_ALL_CALLER_REGS \ @@ -712,14 +603,6 @@ bool __raw_callee_save___native_vcpu_is_preempted(long cpu); "pop %rsi;" \ "pop %rdx;" \ "pop %rcx;" - -/* We save some registers, but all of them, that's too much. We clobber all - * caller saved registers but the argument parameter */ -#define PV_SAVE_REGS "pushq %%rdi;" -#define PV_RESTORE_REGS "popq %%rdi;" -#define PV_EXTRA_CLOBBERS EXTRA_CLOBBERS, "rcx" , "rdx", "rsi" -#define PV_VEXTRA_CLOBBERS EXTRA_CLOBBERS, "rdi", "rcx" , "rdx", "rsi" -#define PV_FLAGS_ARG "D" #endif /* diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 8dfcb2508e6d..0fad9f61c76a 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -68,13 +68,8 @@ struct paravirt_callee_save { /* general info */ struct pv_info { #ifdef CONFIG_PARAVIRT_XXL - unsigned int kernel_rpl; - int shared_kernel_pmd; - -#ifdef CONFIG_X86_64 u16 extra_user_64bit_cs; /* __USER_CS if none */ #endif -#endif const char *name; }; @@ -126,9 +121,7 @@ struct pv_cpu_ops { void (*set_ldt)(const void *desc, unsigned entries); unsigned long (*store_tr)(void); void (*load_tls)(struct thread_struct *t, unsigned int cpu); -#ifdef CONFIG_X86_64 void (*load_gs_index)(unsigned int idx); -#endif void (*write_ldt_entry)(struct desc_struct *ldt, int entrynum, const void *desc); void (*write_gdt_entry)(struct desc_struct *, @@ -249,8 +242,6 @@ struct pv_mmu_ops { /* Pagetable manipulation functions */ void (*set_pte)(pte_t *ptep, pte_t pteval); - void (*set_pte_at)(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pteval); void (*set_pmd)(pmd_t *pmdp, pmd_t pmdval); pte_t (*ptep_modify_prot_start)(struct vm_area_struct *vma, unsigned long addr, @@ -264,21 +255,11 @@ struct pv_mmu_ops { struct paravirt_callee_save pgd_val; struct paravirt_callee_save make_pgd; -#if CONFIG_PGTABLE_LEVELS >= 3 -#ifdef CONFIG_X86_PAE - void (*set_pte_atomic)(pte_t *ptep, pte_t pteval); - void (*pte_clear)(struct mm_struct *mm, unsigned long addr, - pte_t *ptep); - void (*pmd_clear)(pmd_t *pmdp); - -#endif /* CONFIG_X86_PAE */ - void (*set_pud)(pud_t *pudp, pud_t pudval); struct paravirt_callee_save pmd_val; struct paravirt_callee_save make_pmd; -#if CONFIG_PGTABLE_LEVELS >= 4 struct paravirt_callee_save pud_val; struct paravirt_callee_save make_pud; @@ -291,10 +272,6 @@ struct pv_mmu_ops { void (*set_pgd)(pgd_t *pgdp, pgd_t pgdval); #endif /* CONFIG_PGTABLE_LEVELS >= 5 */ -#endif /* CONFIG_PGTABLE_LEVELS >= 4 */ - -#endif /* CONFIG_PGTABLE_LEVELS >= 3 */ - struct pv_lazy_ops lazy_mode; /* dom0 ops */ diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h index 7ccb338507e3..d2c76c8d8cfd 100644 --- a/arch/x86/include/asm/pci.h +++ b/arch/x86/include/asm/pci.h @@ -105,17 +105,6 @@ static inline void early_quirks(void) { } extern void pci_iommu_alloc(void); -#ifdef CONFIG_PCI_MSI -/* implemented in arch/x86/kernel/apic/io_apic. */ -struct msi_desc; -int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type); -void native_teardown_msi_irq(unsigned int irq); -void native_restore_msi_irqs(struct pci_dev *dev); -#else -#define native_setup_msi_irqs NULL -#define native_teardown_msi_irq NULL -#endif - /* generic pci stuff */ #include <asm-generic/pci.h> diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h index 73bb404f4d2a..490411dba438 100644 --- a/arch/x86/include/asm/pci_x86.h +++ b/arch/x86/include/asm/pci_x86.h @@ -114,9 +114,20 @@ extern const struct pci_raw_ops pci_direct_conf1; extern bool port_cf9_safe; /* arch_initcall level */ +#ifdef CONFIG_PCI_DIRECT extern int pci_direct_probe(void); extern void pci_direct_init(int type); +#else +static inline int pci_direct_probe(void) { return -1; } +static inline void pci_direct_init(int type) { } +#endif + +#ifdef CONFIG_PCI_BIOS extern void pci_pcbios_init(void); +#else +static inline void pci_pcbios_init(void) { } +#endif + extern void __init dmi_check_pciprobe(void); extern void __init dmi_check_skip_isa_align(void); diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 0c1b13720525..6960cd6d1f23 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -196,13 +196,29 @@ struct x86_pmu_capability { * Fixed-purpose performance events: */ +/* RDPMC offset for Fixed PMCs */ +#define INTEL_PMC_FIXED_RDPMC_BASE (1 << 30) +#define INTEL_PMC_FIXED_RDPMC_METRICS (1 << 29) + /* - * All 3 fixed-mode PMCs are configured via this single MSR: + * All the fixed-mode PMCs are configured via this single MSR: */ #define MSR_ARCH_PERFMON_FIXED_CTR_CTRL 0x38d /* - * The counts are available in three separate MSRs: + * There is no event-code assigned to the fixed-mode PMCs. + * + * For a fixed-mode PMC, which has an equivalent event on a general-purpose + * PMC, the event-code of the equivalent event is used for the fixed-mode PMC, + * e.g., Instr_Retired.Any and CPU_CLK_Unhalted.Core. + * + * For a fixed-mode PMC, which doesn't have an equivalent event, a + * pseudo-encoding is used, e.g., CPU_CLK_Unhalted.Ref and TOPDOWN.SLOTS. + * The pseudo event-code for a fixed-mode PMC must be 0x00. + * The pseudo umask-code is 0xX. The X equals the index of the fixed + * counter + 1, e.g., the fixed counter 2 has the pseudo-encoding 0x0300. + * + * The counts are available in separate MSRs: */ /* Instr_Retired.Any: */ @@ -213,29 +229,84 @@ struct x86_pmu_capability { #define MSR_ARCH_PERFMON_FIXED_CTR1 0x30a #define INTEL_PMC_IDX_FIXED_CPU_CYCLES (INTEL_PMC_IDX_FIXED + 1) -/* CPU_CLK_Unhalted.Ref: */ +/* CPU_CLK_Unhalted.Ref: event=0x00,umask=0x3 (pseudo-encoding) */ #define MSR_ARCH_PERFMON_FIXED_CTR2 0x30b #define INTEL_PMC_IDX_FIXED_REF_CYCLES (INTEL_PMC_IDX_FIXED + 2) #define INTEL_PMC_MSK_FIXED_REF_CYCLES (1ULL << INTEL_PMC_IDX_FIXED_REF_CYCLES) +/* TOPDOWN.SLOTS: event=0x00,umask=0x4 (pseudo-encoding) */ +#define MSR_ARCH_PERFMON_FIXED_CTR3 0x30c +#define INTEL_PMC_IDX_FIXED_SLOTS (INTEL_PMC_IDX_FIXED + 3) +#define INTEL_PMC_MSK_FIXED_SLOTS (1ULL << INTEL_PMC_IDX_FIXED_SLOTS) + /* * We model BTS tracing as another fixed-mode PMC. * - * We choose a value in the middle of the fixed event range, since lower + * We choose the value 47 for the fixed index of BTS, since lower * values are used by actual fixed events and higher values are used * to indicate other overflow conditions in the PERF_GLOBAL_STATUS msr. */ -#define INTEL_PMC_IDX_FIXED_BTS (INTEL_PMC_IDX_FIXED + 16) +#define INTEL_PMC_IDX_FIXED_BTS (INTEL_PMC_IDX_FIXED + 15) + +/* + * The PERF_METRICS MSR is modeled as several magic fixed-mode PMCs, one for + * each TopDown metric event. + * + * Internally the TopDown metric events are mapped to the FxCtr 3 (SLOTS). + */ +#define INTEL_PMC_IDX_METRIC_BASE (INTEL_PMC_IDX_FIXED + 16) +#define INTEL_PMC_IDX_TD_RETIRING (INTEL_PMC_IDX_METRIC_BASE + 0) +#define INTEL_PMC_IDX_TD_BAD_SPEC (INTEL_PMC_IDX_METRIC_BASE + 1) +#define INTEL_PMC_IDX_TD_FE_BOUND (INTEL_PMC_IDX_METRIC_BASE + 2) +#define INTEL_PMC_IDX_TD_BE_BOUND (INTEL_PMC_IDX_METRIC_BASE + 3) +#define INTEL_PMC_IDX_METRIC_END INTEL_PMC_IDX_TD_BE_BOUND +#define INTEL_PMC_MSK_TOPDOWN ((0xfull << INTEL_PMC_IDX_METRIC_BASE) | \ + INTEL_PMC_MSK_FIXED_SLOTS) -#define GLOBAL_STATUS_COND_CHG BIT_ULL(63) -#define GLOBAL_STATUS_BUFFER_OVF BIT_ULL(62) -#define GLOBAL_STATUS_UNC_OVF BIT_ULL(61) -#define GLOBAL_STATUS_ASIF BIT_ULL(60) -#define GLOBAL_STATUS_COUNTERS_FROZEN BIT_ULL(59) -#define GLOBAL_STATUS_LBRS_FROZEN_BIT 58 -#define GLOBAL_STATUS_LBRS_FROZEN BIT_ULL(GLOBAL_STATUS_LBRS_FROZEN_BIT) -#define GLOBAL_STATUS_TRACE_TOPAPMI BIT_ULL(55) +/* + * There is no event-code assigned to the TopDown events. + * + * For the slots event, use the pseudo code of the fixed counter 3. + * + * For the metric events, the pseudo event-code is 0x00. + * The pseudo umask-code starts from the middle of the pseudo event + * space, 0x80. + */ +#define INTEL_TD_SLOTS 0x0400 /* TOPDOWN.SLOTS */ +/* Level 1 metrics */ +#define INTEL_TD_METRIC_RETIRING 0x8000 /* Retiring metric */ +#define INTEL_TD_METRIC_BAD_SPEC 0x8100 /* Bad speculation metric */ +#define INTEL_TD_METRIC_FE_BOUND 0x8200 /* FE bound metric */ +#define INTEL_TD_METRIC_BE_BOUND 0x8300 /* BE bound metric */ +#define INTEL_TD_METRIC_MAX INTEL_TD_METRIC_BE_BOUND +#define INTEL_TD_METRIC_NUM 4 + +static inline bool is_metric_idx(int idx) +{ + return (unsigned)(idx - INTEL_PMC_IDX_METRIC_BASE) < INTEL_TD_METRIC_NUM; +} + +static inline bool is_topdown_idx(int idx) +{ + return is_metric_idx(idx) || idx == INTEL_PMC_IDX_FIXED_SLOTS; +} +#define INTEL_PMC_OTHER_TOPDOWN_BITS(bit) \ + (~(0x1ull << bit) & INTEL_PMC_MSK_TOPDOWN) + +#define GLOBAL_STATUS_COND_CHG BIT_ULL(63) +#define GLOBAL_STATUS_BUFFER_OVF_BIT 62 +#define GLOBAL_STATUS_BUFFER_OVF BIT_ULL(GLOBAL_STATUS_BUFFER_OVF_BIT) +#define GLOBAL_STATUS_UNC_OVF BIT_ULL(61) +#define GLOBAL_STATUS_ASIF BIT_ULL(60) +#define GLOBAL_STATUS_COUNTERS_FROZEN BIT_ULL(59) +#define GLOBAL_STATUS_LBRS_FROZEN_BIT 58 +#define GLOBAL_STATUS_LBRS_FROZEN BIT_ULL(GLOBAL_STATUS_LBRS_FROZEN_BIT) +#define GLOBAL_STATUS_TRACE_TOPAPMI_BIT 55 +#define GLOBAL_STATUS_TRACE_TOPAPMI BIT_ULL(GLOBAL_STATUS_TRACE_TOPAPMI_BIT) +#define GLOBAL_STATUS_PERF_METRICS_OVF_BIT 48 + +#define GLOBAL_CTRL_EN_PERF_METRICS 48 /* * We model guest LBR event tracing as another fixed-mode PMC like BTS. * @@ -334,6 +405,7 @@ struct pebs_xmm { #define IBS_OP_ENABLE (1ULL<<17) #define IBS_OP_MAX_CNT 0x0000FFFFULL #define IBS_OP_MAX_CNT_EXT 0x007FFFFFULL /* not a register bit mask */ +#define IBS_OP_MAX_CNT_EXT_MASK (0x7FULL<<20) /* separate upper 7 bits */ #define IBS_RIP_INVALID (1ULL<<38) #ifdef CONFIG_X86_LOCAL_APIC diff --git a/arch/x86/include/asm/pgtable-3level_types.h b/arch/x86/include/asm/pgtable-3level_types.h index 80fbb4a9ed87..56baf43befb4 100644 --- a/arch/x86/include/asm/pgtable-3level_types.h +++ b/arch/x86/include/asm/pgtable-3level_types.h @@ -20,12 +20,7 @@ typedef union { } pte_t; #endif /* !__ASSEMBLY__ */ -#ifdef CONFIG_PARAVIRT_XXL -#define SHARED_KERNEL_PMD ((!static_cpu_has(X86_FEATURE_PTI) && \ - (pv_info.shared_kernel_pmd))) -#else #define SHARED_KERNEL_PMD (!static_cpu_has(X86_FEATURE_PTI)) -#endif #define ARCH_PAGE_TABLE_SYNC_MASK (SHARED_KERNEL_PMD ? 0 : PGTBL_PMD_MODIFIED) diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index b836138ce852..5e0dcc20614d 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -63,7 +63,6 @@ extern pmdval_t early_pmd_flags; #include <asm/paravirt.h> #else /* !CONFIG_PARAVIRT_XXL */ #define set_pte(ptep, pte) native_set_pte(ptep, pte) -#define set_pte_at(mm, addr, ptep, pte) native_set_pte_at(mm, addr, ptep, pte) #define set_pte_atomic(ptep, pte) \ native_set_pte_atomic(ptep, pte) @@ -1033,10 +1032,10 @@ static inline pud_t native_local_pudp_get_and_clear(pud_t *pudp) return res; } -static inline void native_set_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep , pte_t pte) +static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte) { - native_set_pte(ptep, pte); + set_pte(ptep, pte); } static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h index 8f63efb2a2cc..52e5f5f2240d 100644 --- a/arch/x86/include/asm/pgtable_64_types.h +++ b/arch/x86/include/asm/pgtable_64_types.h @@ -159,6 +159,4 @@ extern unsigned int ptrs_per_p4d; #define PGD_KERNEL_START ((PAGE_SIZE / 2) / sizeof(pgd_t)) -#define ARCH_PAGE_TABLE_SYNC_MASK (pgtable_l5_enabled() ? PGTBL_PGD_MODIFIED : PGTBL_P4D_MODIFIED) - #endif /* _ASM_X86_PGTABLE_64_DEFS_H */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 97143d87994c..d8a82e650810 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -517,7 +517,7 @@ struct thread_struct { /* Save middle states of ptrace breakpoints */ struct perf_event *ptrace_bps[HBP_NUM]; /* Debug status used for traps, single steps, etc... */ - unsigned long debugreg6; + unsigned long virtual_dr6; /* Keep track of the exact dr7 value set by the user */ unsigned long ptrace_dr7; /* Fault info: */ diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h index 6847d85400a8..3ff0d48469f2 100644 --- a/arch/x86/include/asm/required-features.h +++ b/arch/x86/include/asm/required-features.h @@ -54,7 +54,7 @@ #endif #ifdef CONFIG_X86_64 -#ifdef CONFIG_PARAVIRT +#ifdef CONFIG_PARAVIRT_XXL /* Paravirtualized systems may not have PSE or PGE available */ #define NEED_PSE 0 #define NEED_PGE 0 diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h index 9646c300f128..517920928989 100644 --- a/arch/x86/include/asm/segment.h +++ b/arch/x86/include/asm/segment.h @@ -222,10 +222,6 @@ #endif -#ifndef CONFIG_PARAVIRT_XXL -# define get_kernel_rpl() 0 -#endif - #define IDT_ENTRIES 256 #define NUM_EXCEPTION_VECTORS 32 diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h index 5999b0b3dd4a..94624fb06fac 100644 --- a/arch/x86/include/asm/special_insns.h +++ b/arch/x86/include/asm/special_insns.h @@ -240,6 +240,70 @@ static inline void serialize(void) asm volatile(".byte 0xf, 0x1, 0xe8" ::: "memory"); } +/* The dst parameter must be 64-bytes aligned */ +static inline void movdir64b(void *dst, const void *src) +{ + const struct { char _[64]; } *__src = src; + struct { char _[64]; } *__dst = dst; + + /* + * MOVDIR64B %(rdx), rax. + * + * Both __src and __dst must be memory constraints in order to tell the + * compiler that no other memory accesses should be reordered around + * this one. + * + * Also, both must be supplied as lvalues because this tells + * the compiler what the object is (its size) the instruction accesses. + * I.e., not the pointers but what they point to, thus the deref'ing '*'. + */ + asm volatile(".byte 0x66, 0x0f, 0x38, 0xf8, 0x02" + : "+m" (*__dst) + : "m" (*__src), "a" (__dst), "d" (__src)); +} + +/** + * enqcmds - Enqueue a command in supervisor (CPL0) mode + * @dst: destination, in MMIO space (must be 512-bit aligned) + * @src: 512 bits memory operand + * + * The ENQCMDS instruction allows software to write a 512-bit command to + * a 512-bit-aligned special MMIO region that supports the instruction. + * A return status is loaded into the ZF flag in the RFLAGS register. + * ZF = 0 equates to success, and ZF = 1 indicates retry or error. + * + * This function issues the ENQCMDS instruction to submit data from + * kernel space to MMIO space, in a unit of 512 bits. Order of data access + * is not guaranteed, nor is a memory barrier performed afterwards. It + * returns 0 on success and -EAGAIN on failure. + * + * Warning: Do not use this helper unless your driver has checked that the + * ENQCMDS instruction is supported on the platform and the device accepts + * ENQCMDS. + */ +static inline int enqcmds(void __iomem *dst, const void *src) +{ + const struct { char _[64]; } *__src = src; + struct { char _[64]; } *__dst = dst; + int zf; + + /* + * ENQCMDS %(rdx), rax + * + * See movdir64b()'s comment on operand specification. + */ + asm volatile(".byte 0xf3, 0x0f, 0x38, 0xf8, 0x02, 0x66, 0x90" + CC_SET(z) + : CC_OUT(z) (zf), "+m" (*__dst) + : "m" (*__src), "a" (__dst), "d" (__src)); + + /* Submission failure is indicated via EFLAGS.ZF=1 */ + if (zf) + return -EAGAIN; + + return 0; +} + #endif /* __KERNEL__ */ #endif /* _ASM_X86_SPECIAL_INSNS_H */ diff --git a/arch/x86/include/asm/static_call.h b/arch/x86/include/asm/static_call.h new file mode 100644 index 000000000000..c37f11999d0c --- /dev/null +++ b/arch/x86/include/asm/static_call.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_STATIC_CALL_H +#define _ASM_STATIC_CALL_H + +#include <asm/text-patching.h> + +/* + * For CONFIG_HAVE_STATIC_CALL_INLINE, this is a temporary trampoline which + * uses the current value of the key->func pointer to do an indirect jump to + * the function. This trampoline is only used during boot, before the call + * sites get patched by static_call_update(). The name of this trampoline has + * a magical aspect: objtool uses it to find static call sites so it can create + * the .static_call_sites section. + * + * For CONFIG_HAVE_STATIC_CALL, this is a permanent trampoline which + * does a direct jump to the function. The direct jump gets patched by + * static_call_update(). + * + * Having the trampoline in a special section forces GCC to emit a JMP.d32 when + * it does tail-call optimization on the call; since you cannot compute the + * relative displacement across sections. + */ + +#define __ARCH_DEFINE_STATIC_CALL_TRAMP(name, insns) \ + asm(".pushsection .static_call.text, \"ax\" \n" \ + ".align 4 \n" \ + ".globl " STATIC_CALL_TRAMP_STR(name) " \n" \ + STATIC_CALL_TRAMP_STR(name) ": \n" \ + insns " \n" \ + ".type " STATIC_CALL_TRAMP_STR(name) ", @function \n" \ + ".size " STATIC_CALL_TRAMP_STR(name) ", . - " STATIC_CALL_TRAMP_STR(name) " \n" \ + ".popsection \n") + +#define ARCH_DEFINE_STATIC_CALL_TRAMP(name, func) \ + __ARCH_DEFINE_STATIC_CALL_TRAMP(name, ".byte 0xe9; .long " #func " - (. + 4)") + +#define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) \ + __ARCH_DEFINE_STATIC_CALL_TRAMP(name, "ret; nop; nop; nop; nop") + +#endif /* _ASM_STATIC_CALL_H */ diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h index 6593b42cb379..b7421780e4e9 100644 --- a/arch/x86/include/asm/text-patching.h +++ b/arch/x86/include/asm/text-patching.h @@ -53,6 +53,9 @@ extern void text_poke_finish(void); #define INT3_INSN_SIZE 1 #define INT3_INSN_OPCODE 0xCC +#define RET_INSN_SIZE 1 +#define RET_INSN_OPCODE 0xC3 + #define CALL_INSN_SIZE 5 #define CALL_INSN_OPCODE 0xE8 @@ -73,6 +76,7 @@ static __always_inline int text_opcode_size(u8 opcode) switch(opcode) { __CASE(INT3); + __CASE(RET); __CASE(CALL); __CASE(JMP32); __CASE(JMP8); @@ -141,11 +145,26 @@ void int3_emulate_push(struct pt_regs *regs, unsigned long val) } static __always_inline +unsigned long int3_emulate_pop(struct pt_regs *regs) +{ + unsigned long val = *(unsigned long *)regs->sp; + regs->sp += sizeof(unsigned long); + return val; +} + +static __always_inline void int3_emulate_call(struct pt_regs *regs, unsigned long func) { int3_emulate_push(regs, regs->ip - INT3_INSN_SIZE + CALL_INSN_SIZE); int3_emulate_jmp(regs, func); } + +static __always_inline +void int3_emulate_ret(struct pt_regs *regs) +{ + unsigned long ip = int3_emulate_pop(regs); + int3_emulate_jmp(regs, ip); +} #endif /* !CONFIG_UML_X86 */ #endif /* _ASM_X86_TEXT_PATCHING_H */ diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index eff7fb847149..aa60c239931b 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -96,25 +96,14 @@ static inline bool pagefault_disabled(void); likely(!__range_not_ok(addr, size, user_addr_max())); \ }) -/* - * These are the main single-value transfer routines. They automatically - * use the right size if we just have the right pointer type. - * - * This gets kind of ugly. We want to return _two_ values in "get_user()" - * and yet we don't want to do any pointers, because that is too much - * of a performance impact. Thus we have a few rather ugly macros here, - * and hide all the ugliness from the user. - * - * The "__xxx" versions of the user access functions are versions that - * do not verify the address space, that must have been done previously - * with a separate "access_ok()" call (this is used when we do multiple - * accesses to the same area of user memory). - */ - extern int __get_user_1(void); extern int __get_user_2(void); extern int __get_user_4(void); extern int __get_user_8(void); +extern int __get_user_nocheck_1(void); +extern int __get_user_nocheck_2(void); +extern int __get_user_nocheck_4(void); +extern int __get_user_nocheck_8(void); extern int __get_user_bad(void); #define __uaccess_begin() stac() @@ -138,25 +127,12 @@ extern int __get_user_bad(void); #define __typefits(x,type,not) \ __builtin_choose_expr(sizeof(x)<=sizeof(type),(unsigned type)0,not) -/** - * get_user - Get a simple variable from user space. - * @x: Variable to store result. - * @ptr: Source address, in user space. - * - * Context: User context only. This function may sleep if pagefaults are - * enabled. - * - * This macro copies a single simple variable from user space to kernel - * space. It supports simple types like char and int, but not larger - * data types like structures or arrays. - * - * @ptr must have pointer-to-simple-variable type, and the result of - * dereferencing @ptr must be assignable to @x without a cast. - * - * Return: zero on success, or -EFAULT on error. - * On error, the variable @x is set to zero. - */ /* + * This is used for both get_user() and __get_user() to expand to + * the proper special function call that has odd calling conventions + * due to returning both a value and an error, and that depends on + * the size of the pointer passed in. + * * Careful: we have to cast the result to the type of the pointer * for sign reasons. * @@ -169,13 +145,12 @@ extern int __get_user_bad(void); * Clang/LLVM cares about the size of the register, but still wants * the base register for something that ends up being a pair. */ -#define get_user(x, ptr) \ +#define do_get_user_call(fn,x,ptr) \ ({ \ int __ret_gu; \ register __inttype(*(ptr)) __val_gu asm("%"_ASM_DX); \ __chk_user_ptr(ptr); \ - might_fault(); \ - asm volatile("call __get_user_%P4" \ + asm volatile("call __" #fn "_%P4" \ : "=a" (__ret_gu), "=r" (__val_gu), \ ASM_CALL_CONSTRAINT \ : "0" (ptr), "i" (sizeof(*(ptr)))); \ @@ -183,10 +158,48 @@ extern int __get_user_bad(void); __builtin_expect(__ret_gu, 0); \ }) -#define __put_user_x(size, x, ptr, __ret_pu) \ - asm volatile("call __put_user_" #size : "=a" (__ret_pu) \ - : "0" ((typeof(*(ptr)))(x)), "c" (ptr) : "ebx") +/** + * get_user - Get a simple variable from user space. + * @x: Variable to store result. + * @ptr: Source address, in user space. + * + * Context: User context only. This function may sleep if pagefaults are + * enabled. + * + * This macro copies a single simple variable from user space to kernel + * space. It supports simple types like char and int, but not larger + * data types like structures or arrays. + * + * @ptr must have pointer-to-simple-variable type, and the result of + * dereferencing @ptr must be assignable to @x without a cast. + * + * Return: zero on success, or -EFAULT on error. + * On error, the variable @x is set to zero. + */ +#define get_user(x,ptr) ({ might_fault(); do_get_user_call(get_user,x,ptr); }) +/** + * __get_user - Get a simple variable from user space, with less checking. + * @x: Variable to store result. + * @ptr: Source address, in user space. + * + * Context: User context only. This function may sleep if pagefaults are + * enabled. + * + * This macro copies a single simple variable from user space to kernel + * space. It supports simple types like char and int, but not larger + * data types like structures or arrays. + * + * @ptr must have pointer-to-simple-variable type, and the result of + * dereferencing @ptr must be assignable to @x without a cast. + * + * Caller must check the pointer with access_ok() before calling this + * function. + * + * Return: zero on success, or -EFAULT on error. + * On error, the variable @x is set to zero. + */ +#define __get_user(x,ptr) do_get_user_call(get_user_nocheck,x,ptr) #ifdef CONFIG_X86_32 @@ -199,25 +212,41 @@ extern int __get_user_bad(void); : : "A" (x), "r" (addr) \ : : label) -#define __put_user_x8(x, ptr, __ret_pu) \ - asm volatile("call __put_user_8" : "=a" (__ret_pu) \ - : "A" ((typeof(*(ptr)))(x)), "c" (ptr) : "ebx") #else #define __put_user_goto_u64(x, ptr, label) \ __put_user_goto(x, ptr, "q", "er", label) -#define __put_user_x8(x, ptr, __ret_pu) __put_user_x(8, x, ptr, __ret_pu) #endif extern void __put_user_bad(void); /* * Strange magic calling convention: pointer in %ecx, - * value in %eax(:%edx), return value in %eax. clobbers %rbx + * value in %eax(:%edx), return value in %ecx. clobbers %rbx */ extern void __put_user_1(void); extern void __put_user_2(void); extern void __put_user_4(void); extern void __put_user_8(void); +extern void __put_user_nocheck_1(void); +extern void __put_user_nocheck_2(void); +extern void __put_user_nocheck_4(void); +extern void __put_user_nocheck_8(void); + +#define do_put_user_call(fn,x,ptr) \ +({ \ + int __ret_pu; \ + register __typeof__(*(ptr)) __val_pu asm("%"_ASM_AX); \ + __chk_user_ptr(ptr); \ + __val_pu = (x); \ + asm volatile("call __" #fn "_%P[size]" \ + : "=c" (__ret_pu), \ + ASM_CALL_CONSTRAINT \ + : "0" (ptr), \ + "r" (__val_pu), \ + [size] "i" (sizeof(*(ptr))) \ + :"ebx"); \ + __builtin_expect(__ret_pu, 0); \ +}) /** * put_user - Write a simple value into user space. @@ -236,32 +265,29 @@ extern void __put_user_8(void); * * Return: zero on success, or -EFAULT on error. */ -#define put_user(x, ptr) \ -({ \ - int __ret_pu; \ - __typeof__(*(ptr)) __pu_val; \ - __chk_user_ptr(ptr); \ - might_fault(); \ - __pu_val = x; \ - switch (sizeof(*(ptr))) { \ - case 1: \ - __put_user_x(1, __pu_val, ptr, __ret_pu); \ - break; \ - case 2: \ - __put_user_x(2, __pu_val, ptr, __ret_pu); \ - break; \ - case 4: \ - __put_user_x(4, __pu_val, ptr, __ret_pu); \ - break; \ - case 8: \ - __put_user_x8(__pu_val, ptr, __ret_pu); \ - break; \ - default: \ - __put_user_x(X, __pu_val, ptr, __ret_pu); \ - break; \ - } \ - __builtin_expect(__ret_pu, 0); \ -}) +#define put_user(x, ptr) ({ might_fault(); do_put_user_call(put_user,x,ptr); }) + +/** + * __put_user - Write a simple value into user space, with less checking. + * @x: Value to copy to user space. + * @ptr: Destination address, in user space. + * + * Context: User context only. This function may sleep if pagefaults are + * enabled. + * + * This macro copies a single simple value from kernel space to user + * space. It supports simple types like char and int, but not larger + * data types like structures or arrays. + * + * @ptr must have pointer-to-simple-variable type, and @x must be assignable + * to the result of dereferencing @ptr. + * + * Caller must check the pointer with access_ok() before calling this + * function. + * + * Return: zero on success, or -EFAULT on error. + */ +#define __put_user(x, ptr) do_put_user_call(put_user_nocheck,x,ptr) #define __put_user_size(x, ptr, size, label) \ do { \ @@ -284,6 +310,55 @@ do { \ } \ } while (0) +#ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT + +#ifdef CONFIG_X86_32 +#define __get_user_asm_u64(x, ptr, label) do { \ + unsigned int __gu_low, __gu_high; \ + const unsigned int __user *__gu_ptr; \ + __gu_ptr = (const void __user *)(ptr); \ + __get_user_asm(__gu_low, ptr, "l", "=r", label); \ + __get_user_asm(__gu_high, ptr+1, "l", "=r", label); \ + (x) = ((unsigned long long)__gu_high << 32) | __gu_low; \ +} while (0) +#else +#define __get_user_asm_u64(x, ptr, label) \ + __get_user_asm(x, ptr, "q", "=r", label) +#endif + +#define __get_user_size(x, ptr, size, label) \ +do { \ + __chk_user_ptr(ptr); \ + switch (size) { \ + unsigned char x_u8__; \ + case 1: \ + __get_user_asm(x_u8__, ptr, "b", "=q", label); \ + (x) = x_u8__; \ + break; \ + case 2: \ + __get_user_asm(x, ptr, "w", "=r", label); \ + break; \ + case 4: \ + __get_user_asm(x, ptr, "l", "=r", label); \ + break; \ + case 8: \ + __get_user_asm_u64(x, ptr, label); \ + break; \ + default: \ + (x) = __get_user_bad(); \ + } \ +} while (0) + +#define __get_user_asm(x, addr, itype, ltype, label) \ + asm_volatile_goto("\n" \ + "1: mov"itype" %[umem],%[output]\n" \ + _ASM_EXTABLE_UA(1b, %l2) \ + : [output] ltype(x) \ + : [umem] "m" (__m(addr)) \ + : : label) + +#else // !CONFIG_CC_HAS_ASM_GOTO_OUTPUT + #ifdef CONFIG_X86_32 #define __get_user_asm_u64(x, ptr, retval) \ ({ \ @@ -352,33 +427,7 @@ do { \ : [umem] "m" (__m(addr)), \ [efault] "i" (-EFAULT), "0" (err)) -#define __put_user_nocheck(x, ptr, size) \ -({ \ - __label__ __pu_label; \ - int __pu_err = -EFAULT; \ - __typeof__(*(ptr)) __pu_val = (x); \ - __typeof__(ptr) __pu_ptr = (ptr); \ - __typeof__(size) __pu_size = (size); \ - __uaccess_begin(); \ - __put_user_size(__pu_val, __pu_ptr, __pu_size, __pu_label); \ - __pu_err = 0; \ -__pu_label: \ - __uaccess_end(); \ - __builtin_expect(__pu_err, 0); \ -}) - -#define __get_user_nocheck(x, ptr, size) \ -({ \ - int __gu_err; \ - __inttype(*(ptr)) __gu_val; \ - __typeof__(ptr) __gu_ptr = (ptr); \ - __typeof__(size) __gu_size = (size); \ - __uaccess_begin_nospec(); \ - __get_user_size(__gu_val, __gu_ptr, __gu_size, __gu_err); \ - __uaccess_end(); \ - (x) = (__force __typeof__(*(ptr)))__gu_val; \ - __builtin_expect(__gu_err, 0); \ -}) +#endif // CONFIG_CC_ASM_GOTO_OUTPUT /* FIXME: this hack is definitely wrong -AK */ struct __large_struct { unsigned long buf[100]; }; @@ -396,55 +445,6 @@ struct __large_struct { unsigned long buf[100]; }; : : ltype(x), "m" (__m(addr)) \ : : label) -/** - * __get_user - Get a simple variable from user space, with less checking. - * @x: Variable to store result. - * @ptr: Source address, in user space. - * - * Context: User context only. This function may sleep if pagefaults are - * enabled. - * - * This macro copies a single simple variable from user space to kernel - * space. It supports simple types like char and int, but not larger - * data types like structures or arrays. - * - * @ptr must have pointer-to-simple-variable type, and the result of - * dereferencing @ptr must be assignable to @x without a cast. - * - * Caller must check the pointer with access_ok() before calling this - * function. - * - * Return: zero on success, or -EFAULT on error. - * On error, the variable @x is set to zero. - */ - -#define __get_user(x, ptr) \ - __get_user_nocheck((x), (ptr), sizeof(*(ptr))) - -/** - * __put_user - Write a simple value into user space, with less checking. - * @x: Value to copy to user space. - * @ptr: Destination address, in user space. - * - * Context: User context only. This function may sleep if pagefaults are - * enabled. - * - * This macro copies a single simple value from kernel space to user - * space. It supports simple types like char and int, but not larger - * data types like structures or arrays. - * - * @ptr must have pointer-to-simple-variable type, and @x must be assignable - * to the result of dereferencing @ptr. - * - * Caller must check the pointer with access_ok() before calling this - * function. - * - * Return: zero on success, or -EFAULT on error. - */ - -#define __put_user(x, ptr) \ - __put_user_nocheck((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr))) - extern unsigned long copy_from_user_nmi(void *to, const void __user *from, unsigned long n); extern __must_check long @@ -503,6 +503,14 @@ static __must_check __always_inline bool user_access_begin(const void __user *pt #define unsafe_put_user(x, ptr, label) \ __put_user_size((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)), label) +#ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT +#define unsafe_get_user(x, ptr, err_label) \ +do { \ + __inttype(*(ptr)) __gu_val; \ + __get_user_size(__gu_val, (ptr), sizeof(*(ptr)), err_label); \ + (x) = (__force __typeof__(*(ptr)))__gu_val; \ +} while (0) +#else // !CONFIG_CC_HAS_ASM_GOTO_OUTPUT #define unsafe_get_user(x, ptr, err_label) \ do { \ int __gu_err; \ @@ -511,6 +519,7 @@ do { \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ if (unlikely(__gu_err)) goto err_label; \ } while (0) +#endif // CONFIG_CC_HAS_ASM_GOTO_OUTPUT /* * We want the unsafe accessors to always be inlined and use @@ -537,6 +546,11 @@ do { \ #define HAVE_GET_KERNEL_NOFAULT +#ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT +#define __get_kernel_nofault(dst, src, type, err_label) \ + __get_user_size(*((type *)(dst)), (__force type __user *)(src), \ + sizeof(type), err_label) +#else // !CONFIG_CC_HAS_ASM_GOTO_OUTPUT #define __get_kernel_nofault(dst, src, type, err_label) \ do { \ int __kr_err; \ @@ -546,6 +560,7 @@ do { \ if (unlikely(__kr_err)) \ goto err_label; \ } while (0) +#endif // CONFIG_CC_HAS_ASM_GOTO_OUTPUT #define __put_kernel_nofault(dst, src, type, err_label) \ __put_user_size(*((type *)(src)), (__force type __user *)(dst), \ diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 6807153c0410..397196fae24d 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -8,25 +8,16 @@ struct mpc_bus; struct mpc_cpu; struct mpc_table; struct cpuinfo_x86; +struct irq_domain; /** * struct x86_init_mpparse - platform specific mpparse ops - * @mpc_record: platform specific mpc record accounting * @setup_ioapic_ids: platform specific ioapic id override - * @mpc_apic_id: platform specific mpc apic id assignment - * @smp_read_mpc_oem: platform specific oem mpc table setup - * @mpc_oem_pci_bus: platform specific pci bus setup (default NULL) - * @mpc_oem_bus_info: platform specific mpc bus info * @find_smp_config: find the smp configuration * @get_smp_config: get the smp configuration */ struct x86_init_mpparse { - void (*mpc_record)(unsigned int mode); void (*setup_ioapic_ids)(void); - int (*mpc_apic_id)(struct mpc_cpu *m); - void (*smp_read_mpc_oem)(struct mpc_table *mpc); - void (*mpc_oem_pci_bus)(struct mpc_bus *m); - void (*mpc_oem_bus_info)(struct mpc_bus *m, char *name); void (*find_smp_config)(void); void (*get_smp_config)(unsigned int early); }; @@ -52,12 +43,14 @@ struct x86_init_resources { * @intr_init: interrupt init code * @intr_mode_select: interrupt delivery mode selection * @intr_mode_init: interrupt delivery mode setup + * @create_pci_msi_domain: Create the PCI/MSI interrupt domain */ struct x86_init_irqs { void (*pre_vector_init)(void); void (*intr_init)(void); void (*intr_mode_select)(void); void (*intr_mode_init)(void); + struct irq_domain *(*create_pci_msi_domain)(void); }; /** @@ -283,9 +276,6 @@ struct x86_platform_ops { struct pci_dev; struct x86_msi_ops { - int (*setup_msi_irqs)(struct pci_dev *dev, int nvec, int type); - void (*teardown_msi_irq)(unsigned int irq); - void (*teardown_msi_irqs)(struct pci_dev *dev); void (*restore_msi_irqs)(struct pci_dev *dev); }; diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index e77261db2391..de09af019e23 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -68,6 +68,7 @@ obj-y += tsc.o tsc_msr.o io_delay.o rtc.o obj-y += pci-iommu_table.o obj-y += resource.o obj-y += irqflags.o +obj-y += static_call.o obj-y += process.o obj-y += fpu/ diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index cdaab30880b9..4adbe65afe23 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -1103,6 +1103,10 @@ noinstr int poke_int3_handler(struct pt_regs *regs) */ goto out_put; + case RET_INSN_OPCODE: + int3_emulate_ret(regs); + break; + case CALL_INSN_OPCODE: int3_emulate_call(regs, (long)ip + tp->rel32); break; @@ -1277,6 +1281,7 @@ static void text_poke_loc_init(struct text_poke_loc *tp, void *addr, switch (tp->opcode) { case INT3_INSN_OPCODE: + case RET_INSN_OPCODE: break; case CALL_INSN_OPCODE: diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 5f943b938167..b3eef1d5c903 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1429,6 +1429,9 @@ void __init apic_intr_mode_init(void) break; } + if (x86_platform.apic_post_init) + x86_platform.apic_post_init(); + apic_bsp_setup(upmode); } diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 21f9c7f11779..7b3c7e0d4a09 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -860,10 +860,10 @@ void ioapic_set_alloc_attr(struct irq_alloc_info *info, int node, { init_irq_alloc_info(info, NULL); info->type = X86_IRQ_ALLOC_TYPE_IOAPIC; - info->ioapic_node = node; - info->ioapic_trigger = trigger; - info->ioapic_polarity = polarity; - info->ioapic_valid = 1; + info->ioapic.node = node; + info->ioapic.trigger = trigger; + info->ioapic.polarity = polarity; + info->ioapic.valid = 1; } #ifndef CONFIG_ACPI @@ -878,32 +878,32 @@ static void ioapic_copy_alloc_attr(struct irq_alloc_info *dst, copy_irq_alloc_info(dst, src); dst->type = X86_IRQ_ALLOC_TYPE_IOAPIC; - dst->ioapic_id = mpc_ioapic_id(ioapic_idx); - dst->ioapic_pin = pin; - dst->ioapic_valid = 1; - if (src && src->ioapic_valid) { - dst->ioapic_node = src->ioapic_node; - dst->ioapic_trigger = src->ioapic_trigger; - dst->ioapic_polarity = src->ioapic_polarity; + dst->devid = mpc_ioapic_id(ioapic_idx); + dst->ioapic.pin = pin; + dst->ioapic.valid = 1; + if (src && src->ioapic.valid) { + dst->ioapic.node = src->ioapic.node; + dst->ioapic.trigger = src->ioapic.trigger; + dst->ioapic.polarity = src->ioapic.polarity; } else { - dst->ioapic_node = NUMA_NO_NODE; + dst->ioapic.node = NUMA_NO_NODE; if (acpi_get_override_irq(gsi, &trigger, &polarity) >= 0) { - dst->ioapic_trigger = trigger; - dst->ioapic_polarity = polarity; + dst->ioapic.trigger = trigger; + dst->ioapic.polarity = polarity; } else { /* * PCI interrupts are always active low level * triggered. */ - dst->ioapic_trigger = IOAPIC_LEVEL; - dst->ioapic_polarity = IOAPIC_POL_LOW; + dst->ioapic.trigger = IOAPIC_LEVEL; + dst->ioapic.polarity = IOAPIC_POL_LOW; } } } static int ioapic_alloc_attr_node(struct irq_alloc_info *info) { - return (info && info->ioapic_valid) ? info->ioapic_node : NUMA_NO_NODE; + return (info && info->ioapic.valid) ? info->ioapic.node : NUMA_NO_NODE; } static void mp_register_handler(unsigned int irq, unsigned long trigger) @@ -933,14 +933,14 @@ static bool mp_check_pin_attr(int irq, struct irq_alloc_info *info) * pin with real trigger and polarity attributes. */ if (irq < nr_legacy_irqs() && data->count == 1) { - if (info->ioapic_trigger != data->trigger) - mp_register_handler(irq, info->ioapic_trigger); - data->entry.trigger = data->trigger = info->ioapic_trigger; - data->entry.polarity = data->polarity = info->ioapic_polarity; + if (info->ioapic.trigger != data->trigger) + mp_register_handler(irq, info->ioapic.trigger); + data->entry.trigger = data->trigger = info->ioapic.trigger; + data->entry.polarity = data->polarity = info->ioapic.polarity; } - return data->trigger == info->ioapic_trigger && - data->polarity == info->ioapic_polarity; + return data->trigger == info->ioapic.trigger && + data->polarity == info->ioapic.polarity; } static int alloc_irq_from_domain(struct irq_domain *domain, int ioapic, u32 gsi, @@ -1002,7 +1002,7 @@ static int alloc_isa_irq_from_domain(struct irq_domain *domain, if (!mp_check_pin_attr(irq, info)) return -EBUSY; if (__add_pin_to_irq_node(irq_data->chip_data, node, ioapic, - info->ioapic_pin)) + info->ioapic.pin)) return -ENOMEM; } else { info->flags |= X86_IRQ_ALLOC_LEGACY; @@ -2092,8 +2092,8 @@ static int mp_alloc_timer_irq(int ioapic, int pin) struct irq_alloc_info info; ioapic_set_alloc_attr(&info, NUMA_NO_NODE, 0, 0); - info.ioapic_id = mpc_ioapic_id(ioapic); - info.ioapic_pin = pin; + info.devid = mpc_ioapic_id(ioapic); + info.ioapic.pin = pin; mutex_lock(&ioapic_mutex); irq = alloc_isa_irq_from_domain(domain, 0, ioapic, pin, &info); mutex_unlock(&ioapic_mutex); @@ -2297,9 +2297,9 @@ static int mp_irqdomain_create(int ioapic) return 0; init_irq_alloc_info(&info, NULL); - info.type = X86_IRQ_ALLOC_TYPE_IOAPIC; - info.ioapic_id = mpc_ioapic_id(ioapic); - parent = irq_remapping_get_ir_irq_domain(&info); + info.type = X86_IRQ_ALLOC_TYPE_IOAPIC_GET_PARENT; + info.devid = mpc_ioapic_id(ioapic); + parent = irq_remapping_get_irq_domain(&info); if (!parent) parent = x86_vector_domain; else @@ -2933,9 +2933,9 @@ int mp_ioapic_registered(u32 gsi_base) static void mp_irqdomain_get_attr(u32 gsi, struct mp_chip_data *data, struct irq_alloc_info *info) { - if (info && info->ioapic_valid) { - data->trigger = info->ioapic_trigger; - data->polarity = info->ioapic_polarity; + if (info && info->ioapic.valid) { + data->trigger = info->ioapic.trigger; + data->polarity = info->ioapic.polarity; } else if (acpi_get_override_irq(gsi, &data->trigger, &data->polarity) < 0) { /* PCI interrupts are always active low level triggered. */ @@ -2981,7 +2981,7 @@ int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, return -EINVAL; ioapic = mp_irqdomain_ioapic_idx(domain); - pin = info->ioapic_pin; + pin = info->ioapic.pin; if (irq_find_mapping(domain, (irq_hw_number_t)pin) > 0) return -EEXIST; @@ -2989,7 +2989,7 @@ int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, if (!data) return -ENOMEM; - info->ioapic_entry = &data->entry; + info->ioapic.entry = &data->entry; ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, info); if (ret < 0) { kfree(data); @@ -2997,7 +2997,7 @@ int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, } INIT_LIST_HEAD(&data->irq_2_pin); - irq_data->hwirq = info->ioapic_pin; + irq_data->hwirq = info->ioapic.pin; irq_data->chip = (domain->parent == x86_vector_domain) ? &ioapic_chip : &ioapic_ir_chip; irq_data->chip_data = data; @@ -3007,8 +3007,8 @@ int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, add_pin_to_irq_node(data, ioapic_alloc_attr_node(info), ioapic, pin); local_irq_save(flags); - if (info->ioapic_entry) - mp_setup_entry(cfg, data, info->ioapic_entry); + if (info->ioapic.entry) + mp_setup_entry(cfg, data, info->ioapic.entry); mp_register_handler(virq, data->trigger); if (virq < nr_legacy_irqs()) legacy_pic->mask(virq); diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c index c2b2911feeef..6313f0a05db7 100644 --- a/arch/x86/kernel/apic/msi.c +++ b/arch/x86/kernel/apic/msi.c @@ -21,7 +21,7 @@ #include <asm/apic.h> #include <asm/irq_remapping.h> -static struct irq_domain *msi_default_domain; +struct irq_domain *x86_pci_msi_default_domain __ro_after_init; static void __irq_msi_compose_msg(struct irq_cfg *cfg, struct msi_msg *msg) { @@ -45,7 +45,7 @@ static void __irq_msi_compose_msg(struct irq_cfg *cfg, struct msi_msg *msg) MSI_DATA_VECTOR(cfg->vector); } -static void irq_msi_compose_msg(struct irq_data *data, struct msi_msg *msg) +void x86_vector_msi_compose_msg(struct irq_data *data, struct msi_msg *msg) { __irq_msi_compose_msg(irqd_cfg(data), msg); } @@ -177,40 +177,10 @@ static struct irq_chip pci_msi_controller = { .irq_mask = pci_msi_mask_irq, .irq_ack = irq_chip_ack_parent, .irq_retrigger = irq_chip_retrigger_hierarchy, - .irq_compose_msi_msg = irq_msi_compose_msg, .irq_set_affinity = msi_set_affinity, .flags = IRQCHIP_SKIP_SET_WAKE, }; -int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) -{ - struct irq_domain *domain; - struct irq_alloc_info info; - - init_irq_alloc_info(&info, NULL); - info.type = X86_IRQ_ALLOC_TYPE_MSI; - info.msi_dev = dev; - - domain = irq_remapping_get_irq_domain(&info); - if (domain == NULL) - domain = msi_default_domain; - if (domain == NULL) - return -ENOSYS; - - return msi_domain_alloc_irqs(domain, &dev->dev, nvec); -} - -void native_teardown_msi_irq(unsigned int irq) -{ - irq_domain_free_irqs(irq, 1); -} - -static irq_hw_number_t pci_msi_get_hwirq(struct msi_domain_info *info, - msi_alloc_info_t *arg) -{ - return arg->msi_hwirq; -} - int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec, msi_alloc_info_t *arg) { @@ -218,11 +188,10 @@ int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec, struct msi_desc *desc = first_pci_msi_entry(pdev); init_irq_alloc_info(arg, NULL); - arg->msi_dev = pdev; if (desc->msi_attrib.is_msix) { - arg->type = X86_IRQ_ALLOC_TYPE_MSIX; + arg->type = X86_IRQ_ALLOC_TYPE_PCI_MSIX; } else { - arg->type = X86_IRQ_ALLOC_TYPE_MSI; + arg->type = X86_IRQ_ALLOC_TYPE_PCI_MSI; arg->flags |= X86_IRQ_ALLOC_CONTIGUOUS_VECTORS; } @@ -230,16 +199,8 @@ int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec, } EXPORT_SYMBOL_GPL(pci_msi_prepare); -void pci_msi_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc) -{ - arg->msi_hwirq = pci_msi_domain_calc_hwirq(arg->msi_dev, desc); -} -EXPORT_SYMBOL_GPL(pci_msi_set_desc); - static struct msi_domain_ops pci_msi_domain_ops = { - .get_hwirq = pci_msi_get_hwirq, .msi_prepare = pci_msi_prepare, - .set_desc = pci_msi_set_desc, }; static struct msi_domain_info pci_msi_domain_info = { @@ -251,25 +212,32 @@ static struct msi_domain_info pci_msi_domain_info = { .handler_name = "edge", }; -void __init arch_init_msi_domain(struct irq_domain *parent) +struct irq_domain * __init native_create_pci_msi_domain(void) { struct fwnode_handle *fn; + struct irq_domain *d; if (disable_apic) - return; + return NULL; fn = irq_domain_alloc_named_fwnode("PCI-MSI"); - if (fn) { - msi_default_domain = - pci_msi_create_irq_domain(fn, &pci_msi_domain_info, - parent); - } - if (!msi_default_domain) { + if (!fn) + return NULL; + + d = pci_msi_create_irq_domain(fn, &pci_msi_domain_info, + x86_vector_domain); + if (!d) { irq_domain_free_fwnode(fn); - pr_warn("failed to initialize irqdomain for MSI/MSI-x.\n"); + pr_warn("Failed to initialize PCI-MSI irqdomain.\n"); } else { - msi_default_domain->flags |= IRQ_DOMAIN_MSI_NOMASK_QUIRK; + d->flags |= IRQ_DOMAIN_MSI_NOMASK_QUIRK; } + return d; +} + +void __init x86_create_pci_msi_domain(void) +{ + x86_pci_msi_default_domain = x86_init.irqs.create_pci_msi_domain(); } #ifdef CONFIG_IRQ_REMAP @@ -279,7 +247,6 @@ static struct irq_chip pci_msi_ir_controller = { .irq_mask = pci_msi_mask_irq, .irq_ack = irq_chip_ack_parent, .irq_retrigger = irq_chip_retrigger_hierarchy, - .irq_set_vcpu_affinity = irq_chip_set_vcpu_affinity_parent, .flags = IRQCHIP_SKIP_SET_WAKE, }; @@ -321,35 +288,28 @@ static struct irq_chip dmar_msi_controller = { .irq_ack = irq_chip_ack_parent, .irq_set_affinity = msi_domain_set_affinity, .irq_retrigger = irq_chip_retrigger_hierarchy, - .irq_compose_msi_msg = irq_msi_compose_msg, .irq_write_msi_msg = dmar_msi_write_msg, .flags = IRQCHIP_SKIP_SET_WAKE, }; -static irq_hw_number_t dmar_msi_get_hwirq(struct msi_domain_info *info, - msi_alloc_info_t *arg) -{ - return arg->dmar_id; -} - static int dmar_msi_init(struct irq_domain *domain, struct msi_domain_info *info, unsigned int virq, irq_hw_number_t hwirq, msi_alloc_info_t *arg) { - irq_domain_set_info(domain, virq, arg->dmar_id, info->chip, NULL, - handle_edge_irq, arg->dmar_data, "edge"); + irq_domain_set_info(domain, virq, arg->devid, info->chip, NULL, + handle_edge_irq, arg->data, "edge"); return 0; } static struct msi_domain_ops dmar_msi_domain_ops = { - .get_hwirq = dmar_msi_get_hwirq, .msi_init = dmar_msi_init, }; static struct msi_domain_info dmar_msi_domain_info = { .ops = &dmar_msi_domain_ops, .chip = &dmar_msi_controller, + .flags = MSI_FLAG_USE_DEF_DOM_OPS, }; static struct irq_domain *dmar_get_irq_domain(void) @@ -384,8 +344,9 @@ int dmar_alloc_hwirq(int id, int node, void *arg) init_irq_alloc_info(&info, NULL); info.type = X86_IRQ_ALLOC_TYPE_DMAR; - info.dmar_id = id; - info.dmar_data = arg; + info.devid = id; + info.hwirq = id; + info.data = arg; return irq_domain_alloc_irqs(domain, 1, node, &info); } @@ -419,24 +380,17 @@ static struct irq_chip hpet_msi_controller __ro_after_init = { .irq_ack = irq_chip_ack_parent, .irq_set_affinity = msi_domain_set_affinity, .irq_retrigger = irq_chip_retrigger_hierarchy, - .irq_compose_msi_msg = irq_msi_compose_msg, .irq_write_msi_msg = hpet_msi_write_msg, .flags = IRQCHIP_SKIP_SET_WAKE, }; -static irq_hw_number_t hpet_msi_get_hwirq(struct msi_domain_info *info, - msi_alloc_info_t *arg) -{ - return arg->hpet_index; -} - static int hpet_msi_init(struct irq_domain *domain, struct msi_domain_info *info, unsigned int virq, irq_hw_number_t hwirq, msi_alloc_info_t *arg) { irq_set_status_flags(virq, IRQ_MOVE_PCNTXT); - irq_domain_set_info(domain, virq, arg->hpet_index, info->chip, NULL, - handle_edge_irq, arg->hpet_data, "edge"); + irq_domain_set_info(domain, virq, arg->hwirq, info->chip, NULL, + handle_edge_irq, arg->data, "edge"); return 0; } @@ -448,7 +402,6 @@ static void hpet_msi_free(struct irq_domain *domain, } static struct msi_domain_ops hpet_msi_domain_ops = { - .get_hwirq = hpet_msi_get_hwirq, .msi_init = hpet_msi_init, .msi_free = hpet_msi_free, }; @@ -456,6 +409,7 @@ static struct msi_domain_ops hpet_msi_domain_ops = { static struct msi_domain_info hpet_msi_domain_info = { .ops = &hpet_msi_domain_ops, .chip = &hpet_msi_controller, + .flags = MSI_FLAG_USE_DEF_DOM_OPS, }; struct irq_domain *hpet_create_irq_domain(int hpet_id) @@ -476,9 +430,9 @@ struct irq_domain *hpet_create_irq_domain(int hpet_id) domain_info->data = (void *)(long)hpet_id; init_irq_alloc_info(&info, NULL); - info.type = X86_IRQ_ALLOC_TYPE_HPET; - info.hpet_id = hpet_id; - parent = irq_remapping_get_ir_irq_domain(&info); + info.type = X86_IRQ_ALLOC_TYPE_HPET_GET_PARENT; + info.devid = hpet_id; + parent = irq_remapping_get_irq_domain(&info); if (parent == NULL) parent = x86_vector_domain; else @@ -506,9 +460,9 @@ int hpet_assign_irq(struct irq_domain *domain, struct hpet_channel *hc, init_irq_alloc_info(&info, NULL); info.type = X86_IRQ_ALLOC_TYPE_HPET; - info.hpet_data = hc; - info.hpet_id = hpet_dev_id(domain); - info.hpet_index = dev_num; + info.data = hc; + info.devid = hpet_dev_id(domain); + info.hwirq = dev_num; return irq_domain_alloc_irqs(domain, 1, NUMA_NO_NODE, &info); } diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index 99ee61c9ba54..67b6f7c049ec 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -170,9 +170,6 @@ void __init default_setup_apic_routing(void) if (apic->setup_apic_routing) apic->setup_apic_routing(); - - if (x86_platform.apic_post_init) - x86_platform.apic_post_init(); } void __init generic_apic_probe(void) diff --git a/arch/x86/kernel/apic/probe_64.c b/arch/x86/kernel/apic/probe_64.c index bd3835d6b535..c46720f185c0 100644 --- a/arch/x86/kernel/apic/probe_64.c +++ b/arch/x86/kernel/apic/probe_64.c @@ -32,9 +32,6 @@ void __init default_setup_apic_routing(void) break; } } - - if (x86_platform.apic_post_init) - x86_platform.apic_post_init(); } int __init default_acpi_madt_oem_check(char *oem_id, char *oem_table_id) diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index f8a56b5dc29f..1eac53632786 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -714,8 +714,6 @@ int __init arch_early_irq_init(void) BUG_ON(x86_vector_domain == NULL); irq_set_default_host(x86_vector_domain); - arch_init_msi_domain(x86_vector_domain); - BUG_ON(!alloc_cpumask_var(&vector_searchmask, GFP_KERNEL)); /* @@ -824,6 +822,7 @@ static struct irq_chip lapic_controller = { .name = "APIC", .irq_ack = apic_ack_edge, .irq_set_affinity = apic_set_affinity, + .irq_compose_msi_msg = x86_vector_msi_compose_msg, .irq_retrigger = apic_retrigger_irq, }; diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index c5d6f17d9b9d..7824fc62c7cd 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -23,6 +23,7 @@ #include <linux/syscore_ops.h> #include <linux/pgtable.h> +#include <asm/cmdline.h> #include <asm/stackprotector.h> #include <asm/perf_event.h> #include <asm/mmu_context.h> @@ -1221,6 +1222,59 @@ static void detect_nopl(void) } /* + * We parse cpu parameters early because fpu__init_system() is executed + * before parse_early_param(). + */ +static void __init cpu_parse_early_param(void) +{ + char arg[128]; + char *argptr = arg; + int arglen, res, bit; + +#ifdef CONFIG_X86_32 + if (cmdline_find_option_bool(boot_command_line, "no387")) +#ifdef CONFIG_MATH_EMULATION + setup_clear_cpu_cap(X86_FEATURE_FPU); +#else + pr_err("Option 'no387' required CONFIG_MATH_EMULATION enabled.\n"); +#endif + + if (cmdline_find_option_bool(boot_command_line, "nofxsr")) + setup_clear_cpu_cap(X86_FEATURE_FXSR); +#endif + + if (cmdline_find_option_bool(boot_command_line, "noxsave")) + setup_clear_cpu_cap(X86_FEATURE_XSAVE); + + if (cmdline_find_option_bool(boot_command_line, "noxsaveopt")) + setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); + + if (cmdline_find_option_bool(boot_command_line, "noxsaves")) + setup_clear_cpu_cap(X86_FEATURE_XSAVES); + + arglen = cmdline_find_option(boot_command_line, "clearcpuid", arg, sizeof(arg)); + if (arglen <= 0) + return; + + pr_info("Clearing CPUID bits:"); + do { + res = get_option(&argptr, &bit); + if (res == 0 || res == 3) + break; + + /* If the argument was too long, the last bit may be cut off */ + if (res == 1 && arglen >= sizeof(arg)) + break; + + if (bit >= 0 && bit < NCAPINTS * 32) { + pr_cont(" " X86_CAP_FMT, x86_cap_flag(bit)); + setup_clear_cpu_cap(bit); + } + } while (res == 2); + pr_cont("\n"); +} + +/* * Do minimum CPU detection early. * Fields really needed: vendor, cpuid_level, family, model, mask, * cache alignment. @@ -1255,6 +1309,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) get_cpu_cap(c); get_cpu_address_sizes(c); setup_force_cpu_cap(X86_FEATURE_CPUID); + cpu_parse_early_param(); if (this_cpu->c_early_init) this_cpu->c_early_init(c); @@ -1413,15 +1468,7 @@ static void generic_identify(struct cpuinfo_x86 *c) * ESPFIX issue, we can change this. */ #ifdef CONFIG_X86_32 -# ifdef CONFIG_PARAVIRT_XXL - do { - extern void native_iret(void); - if (pv_ops.cpu.iret == native_iret) - set_cpu_bug(c, X86_BUG_ESPFIX); - } while (0); -# else set_cpu_bug(c, X86_BUG_ESPFIX); -# endif #endif } diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c index 3cbe24ca80ab..d502241995a3 100644 --- a/arch/x86/kernel/cpu/cpuid-deps.c +++ b/arch/x86/kernel/cpu/cpuid-deps.c @@ -69,6 +69,8 @@ static const struct cpuid_dep cpuid_deps[] = { { X86_FEATURE_CQM_MBM_TOTAL, X86_FEATURE_CQM_LLC }, { X86_FEATURE_CQM_MBM_LOCAL, X86_FEATURE_CQM_LLC }, { X86_FEATURE_AVX512_BF16, X86_FEATURE_AVX512VL }, + { X86_FEATURE_ENQCMD, X86_FEATURE_XSAVES }, + { X86_FEATURE_PER_THREAD_MBA, X86_FEATURE_MBA }, {} }; diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 31125448b174..9834a43cd0fa 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -248,7 +248,7 @@ static void __init ms_hyperv_init_platform(void) hv_host_info_edx >> 24, hv_host_info_edx & 0xFFFFFF); } - if (ms_hyperv.features & HV_X64_ACCESS_FREQUENCY_MSRS && + if (ms_hyperv.features & HV_ACCESS_FREQUENCY_MSRS && ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE) { x86_platform.calibrate_tsc = hv_get_tsc_khz; x86_platform.calibrate_cpu = hv_get_tsc_khz; @@ -270,7 +270,7 @@ static void __init ms_hyperv_init_platform(void) crash_kexec_post_notifiers = true; #ifdef CONFIG_X86_LOCAL_APIC - if (ms_hyperv.features & HV_X64_ACCESS_FREQUENCY_MSRS && + if (ms_hyperv.features & HV_ACCESS_FREQUENCY_MSRS && ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE) { /* * Get the APIC frequency. @@ -296,7 +296,7 @@ static void __init ms_hyperv_init_platform(void) machine_ops.shutdown = hv_machine_shutdown; machine_ops.crash_shutdown = hv_machine_crash_shutdown; #endif - if (ms_hyperv.features & HV_X64_ACCESS_TSC_INVARIANT) { + if (ms_hyperv.features & HV_ACCESS_TSC_INVARIANT) { wrmsrl(HV_X64_MSR_TSC_INVARIANT_CONTROL, 0x1); setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE); } else { @@ -330,7 +330,7 @@ static void __init ms_hyperv_init_platform(void) alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, asm_sysvec_hyperv_callback); /* Setup the IDT for reenlightenment notifications */ - if (ms_hyperv.features & HV_X64_ACCESS_REENLIGHTENMENT) { + if (ms_hyperv.features & HV_ACCESS_REENLIGHTENMENT) { alloc_intr_gate(HYPERV_REENLIGHTENMENT_VECTOR, asm_sysvec_hyperv_reenlightenment); } diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 6a9df71c1b9e..e5f4ee8f4c3b 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -168,6 +168,7 @@ struct rdt_resource rdt_resources_all[] = { .name = "MB", .domains = domain_init(RDT_RESOURCE_MBA), .cache_level = 3, + .parse_ctrlval = parse_bw, .format_str = "%d=%*u", .fflags = RFTYPE_RES_MB, }, @@ -254,22 +255,30 @@ static bool __get_mem_config_intel(struct rdt_resource *r) { union cpuid_0x10_3_eax eax; union cpuid_0x10_x_edx edx; - u32 ebx, ecx; + u32 ebx, ecx, max_delay; cpuid_count(0x00000010, 3, &eax.full, &ebx, &ecx, &edx.full); r->num_closid = edx.split.cos_max + 1; - r->membw.max_delay = eax.split.max_delay + 1; + max_delay = eax.split.max_delay + 1; r->default_ctrl = MAX_MBA_BW; + r->membw.arch_needs_linear = true; if (ecx & MBA_IS_LINEAR) { r->membw.delay_linear = true; - r->membw.min_bw = MAX_MBA_BW - r->membw.max_delay; - r->membw.bw_gran = MAX_MBA_BW - r->membw.max_delay; + r->membw.min_bw = MAX_MBA_BW - max_delay; + r->membw.bw_gran = MAX_MBA_BW - max_delay; } else { if (!rdt_get_mb_table(r)) return false; + r->membw.arch_needs_linear = false; } r->data_width = 3; + if (boot_cpu_has(X86_FEATURE_PER_THREAD_MBA)) + r->membw.throttle_mode = THREAD_THROTTLE_PER_THREAD; + else + r->membw.throttle_mode = THREAD_THROTTLE_MAX; + thread_throttle_mode_init(); + r->alloc_capable = true; r->alloc_enabled = true; @@ -288,7 +297,13 @@ static bool __rdt_get_mem_config_amd(struct rdt_resource *r) /* AMD does not use delay */ r->membw.delay_linear = false; + r->membw.arch_needs_linear = false; + /* + * AMD does not use memory delay throttle model to control + * the allocation like Intel does. + */ + r->membw.throttle_mode = THREAD_THROTTLE_UNDEFINED; r->membw.min_bw = 0; r->membw.bw_gran = 1; /* Max value is 2048, Data width should be 4 in decimal */ @@ -346,19 +361,6 @@ static void rdt_get_cdp_l2_config(void) rdt_get_cdp_config(RDT_RESOURCE_L2, RDT_RESOURCE_L2CODE); } -static int get_cache_id(int cpu, int level) -{ - struct cpu_cacheinfo *ci = get_cpu_cacheinfo(cpu); - int i; - - for (i = 0; i < ci->num_leaves; i++) { - if (ci->info_list[i].level == level) - return ci->info_list[i].id; - } - - return -1; -} - static void mba_wrmsr_amd(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r) { @@ -556,13 +558,13 @@ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d) */ static void domain_add_cpu(int cpu, struct rdt_resource *r) { - int id = get_cache_id(cpu, r->cache_level); + int id = get_cpu_cacheinfo_id(cpu, r->cache_level); struct list_head *add_pos = NULL; struct rdt_domain *d; d = rdt_find_domain(r, id, &add_pos); if (IS_ERR(d)) { - pr_warn("Could't find cache id for cpu %d\n", cpu); + pr_warn("Couldn't find cache id for CPU %d\n", cpu); return; } @@ -602,12 +604,12 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r) static void domain_remove_cpu(int cpu, struct rdt_resource *r) { - int id = get_cache_id(cpu, r->cache_level); + int id = get_cpu_cacheinfo_id(cpu, r->cache_level); struct rdt_domain *d; d = rdt_find_domain(r, id, NULL); if (IS_ERR_OR_NULL(d)) { - pr_warn("Could't find cache id for cpu %d\n", cpu); + pr_warn("Couldn't find cache id for CPU %d\n", cpu); return; } @@ -918,12 +920,12 @@ static __init void rdt_init_res_defs_intel(void) r->rid == RDT_RESOURCE_L3CODE || r->rid == RDT_RESOURCE_L2 || r->rid == RDT_RESOURCE_L2DATA || - r->rid == RDT_RESOURCE_L2CODE) - r->cbm_validate = cbm_validate_intel; - else if (r->rid == RDT_RESOURCE_MBA) { + r->rid == RDT_RESOURCE_L2CODE) { + r->cache.arch_has_sparse_bitmaps = false; + r->cache.arch_has_empty_bitmaps = false; + } else if (r->rid == RDT_RESOURCE_MBA) { r->msr_base = MSR_IA32_MBA_THRTL_BASE; r->msr_update = mba_wrmsr_intel; - r->parse_ctrlval = parse_bw_intel; } } } @@ -938,12 +940,12 @@ static __init void rdt_init_res_defs_amd(void) r->rid == RDT_RESOURCE_L3CODE || r->rid == RDT_RESOURCE_L2 || r->rid == RDT_RESOURCE_L2DATA || - r->rid == RDT_RESOURCE_L2CODE) - r->cbm_validate = cbm_validate_amd; - else if (r->rid == RDT_RESOURCE_MBA) { + r->rid == RDT_RESOURCE_L2CODE) { + r->cache.arch_has_sparse_bitmaps = true; + r->cache.arch_has_empty_bitmaps = true; + } else if (r->rid == RDT_RESOURCE_MBA) { r->msr_base = MSR_IA32_MBA_BW_BASE; r->msr_update = mba_wrmsr_amd; - r->parse_ctrlval = parse_bw_amd; } } } diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c index 934c8fb8a64a..c877642e8a14 100644 --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -23,53 +23,6 @@ /* * Check whether MBA bandwidth percentage value is correct. The value is - * checked against the minimum and maximum bandwidth values specified by - * the hardware. The allocated bandwidth percentage is rounded to the next - * control step available on the hardware. - */ -static bool bw_validate_amd(char *buf, unsigned long *data, - struct rdt_resource *r) -{ - unsigned long bw; - int ret; - - ret = kstrtoul(buf, 10, &bw); - if (ret) { - rdt_last_cmd_printf("Non-decimal digit in MB value %s\n", buf); - return false; - } - - if (bw < r->membw.min_bw || bw > r->default_ctrl) { - rdt_last_cmd_printf("MB value %ld out of range [%d,%d]\n", bw, - r->membw.min_bw, r->default_ctrl); - return false; - } - - *data = roundup(bw, (unsigned long)r->membw.bw_gran); - return true; -} - -int parse_bw_amd(struct rdt_parse_data *data, struct rdt_resource *r, - struct rdt_domain *d) -{ - unsigned long bw_val; - - if (d->have_new_ctrl) { - rdt_last_cmd_printf("Duplicate domain %d\n", d->id); - return -EINVAL; - } - - if (!bw_validate_amd(data->buf, &bw_val, r)) - return -EINVAL; - - d->new_ctrl = bw_val; - d->have_new_ctrl = true; - - return 0; -} - -/* - * Check whether MBA bandwidth percentage value is correct. The value is * checked against the minimum and max bandwidth values specified by the * hardware. The allocated bandwidth percentage is rounded to the next * control step available on the hardware. @@ -82,7 +35,7 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r) /* * Only linear delay values is supported for current Intel SKUs. */ - if (!r->membw.delay_linear) { + if (!r->membw.delay_linear && r->membw.arch_needs_linear) { rdt_last_cmd_puts("No support for non-linear MB domains\n"); return false; } @@ -104,8 +57,8 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r) return true; } -int parse_bw_intel(struct rdt_parse_data *data, struct rdt_resource *r, - struct rdt_domain *d) +int parse_bw(struct rdt_parse_data *data, struct rdt_resource *r, + struct rdt_domain *d) { unsigned long bw_val; @@ -123,12 +76,14 @@ int parse_bw_intel(struct rdt_parse_data *data, struct rdt_resource *r, } /* - * Check whether a cache bit mask is valid. The SDM says: + * Check whether a cache bit mask is valid. + * For Intel the SDM says: * Please note that all (and only) contiguous '1' combinations * are allowed (e.g. FFFFH, 0FF0H, 003CH, etc.). * Additionally Haswell requires at least two bits set. + * AMD allows non-contiguous bitmasks. */ -bool cbm_validate_intel(char *buf, u32 *data, struct rdt_resource *r) +static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r) { unsigned long first_bit, zero_bit, val; unsigned int cbm_len = r->cache.cbm_len; @@ -140,7 +95,8 @@ bool cbm_validate_intel(char *buf, u32 *data, struct rdt_resource *r) return false; } - if (val == 0 || val > r->default_ctrl) { + if ((!r->cache.arch_has_empty_bitmaps && val == 0) || + val > r->default_ctrl) { rdt_last_cmd_puts("Mask out of range\n"); return false; } @@ -148,7 +104,9 @@ bool cbm_validate_intel(char *buf, u32 *data, struct rdt_resource *r) first_bit = find_first_bit(&val, cbm_len); zero_bit = find_next_zero_bit(&val, cbm_len, first_bit); - if (find_next_bit(&val, cbm_len, zero_bit) < cbm_len) { + /* Are non-contiguous bitmaps allowed? */ + if (!r->cache.arch_has_sparse_bitmaps && + (find_next_bit(&val, cbm_len, zero_bit) < cbm_len)) { rdt_last_cmd_printf("The mask %lx has non-consecutive 1-bits\n", val); return false; } @@ -164,30 +122,6 @@ bool cbm_validate_intel(char *buf, u32 *data, struct rdt_resource *r) } /* - * Check whether a cache bit mask is valid. AMD allows non-contiguous - * bitmasks - */ -bool cbm_validate_amd(char *buf, u32 *data, struct rdt_resource *r) -{ - unsigned long val; - int ret; - - ret = kstrtoul(buf, 16, &val); - if (ret) { - rdt_last_cmd_printf("Non-hex character in the mask %s\n", buf); - return false; - } - - if (val > r->default_ctrl) { - rdt_last_cmd_puts("Mask out of range\n"); - return false; - } - - *data = val; - return true; -} - -/* * Read one cache bit mask (hex). Check that it is valid for the current * resource type. */ @@ -212,7 +146,7 @@ int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r, return -EINVAL; } - if (!r->cbm_validate(data->buf, &cbm_val, r)) + if (!cbm_validate(data->buf, &cbm_val, r)) return -EINVAL; if ((rdtgrp->mode == RDT_MODE_EXCLUSIVE || diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index 5ffa32256b3b..80fa997fae60 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -283,7 +283,6 @@ struct rftype { * struct mbm_state - status for each MBM counter in each domain * @chunks: Total data moved (multiply by rdt_group.mon_scale to get bytes) * @prev_msr Value of IA32_QM_CTR for this RMID last time we read it - * @chunks_bw Total local data moved. Used for bandwidth calculation * @prev_bw_msr:Value of previous IA32_QM_CTR for bandwidth counting * @prev_bw The most recent bandwidth in MBps * @delta_bw Difference between the current and previous bandwidth @@ -292,7 +291,6 @@ struct rftype { struct mbm_state { u64 chunks; u64 prev_msr; - u64 chunks_bw; u64 prev_bw_msr; u32 prev_bw; u32 delta_bw; @@ -360,6 +358,8 @@ struct msr_param { * in a cache bit mask * @shareable_bits: Bitmask of shareable resource with other * executing entities + * @arch_has_sparse_bitmaps: True if a bitmap like f00f is valid. + * @arch_has_empty_bitmaps: True if the '0' bitmap is valid. */ struct rdt_cache { unsigned int cbm_len; @@ -367,25 +367,43 @@ struct rdt_cache { unsigned int cbm_idx_mult; unsigned int cbm_idx_offset; unsigned int shareable_bits; + bool arch_has_sparse_bitmaps; + bool arch_has_empty_bitmaps; +}; + +/** + * enum membw_throttle_mode - System's memory bandwidth throttling mode + * @THREAD_THROTTLE_UNDEFINED: Not relevant to the system + * @THREAD_THROTTLE_MAX: Memory bandwidth is throttled at the core + * always using smallest bandwidth percentage + * assigned to threads, aka "max throttling" + * @THREAD_THROTTLE_PER_THREAD: Memory bandwidth is throttled at the thread + */ +enum membw_throttle_mode { + THREAD_THROTTLE_UNDEFINED = 0, + THREAD_THROTTLE_MAX, + THREAD_THROTTLE_PER_THREAD, }; /** * struct rdt_membw - Memory bandwidth allocation related data - * @max_delay: Max throttle delay. Delay is the hardware - * representation for memory bandwidth. * @min_bw: Minimum memory bandwidth percentage user can request * @bw_gran: Granularity at which the memory bandwidth is allocated * @delay_linear: True if memory B/W delay is in linear scale + * @arch_needs_linear: True if we can't configure non-linear resources + * @throttle_mode: Bandwidth throttling mode when threads request + * different memory bandwidths * @mba_sc: True if MBA software controller(mba_sc) is enabled * @mb_map: Mapping of memory B/W percentage to memory B/W delay */ struct rdt_membw { - u32 max_delay; - u32 min_bw; - u32 bw_gran; - u32 delay_linear; - bool mba_sc; - u32 *mb_map; + u32 min_bw; + u32 bw_gran; + u32 delay_linear; + bool arch_needs_linear; + enum membw_throttle_mode throttle_mode; + bool mba_sc; + u32 *mb_map; }; static inline bool is_llc_occupancy_enabled(void) @@ -437,7 +455,6 @@ struct rdt_parse_data { * @cache: Cache allocation related data * @format_str: Per resource format string to show domain value * @parse_ctrlval: Per resource function pointer to parse control values - * @cbm_validate Cache bitmask validate function * @evt_list: List of monitoring events * @num_rmid: Number of RMIDs available * @mon_scale: cqm counter * mon_scale = occupancy in bytes @@ -464,7 +481,6 @@ struct rdt_resource { int (*parse_ctrlval)(struct rdt_parse_data *data, struct rdt_resource *r, struct rdt_domain *d); - bool (*cbm_validate)(char *buf, u32 *data, struct rdt_resource *r); struct list_head evt_list; int num_rmid; unsigned int mon_scale; @@ -474,10 +490,8 @@ struct rdt_resource { int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r, struct rdt_domain *d); -int parse_bw_intel(struct rdt_parse_data *data, struct rdt_resource *r, - struct rdt_domain *d); -int parse_bw_amd(struct rdt_parse_data *data, struct rdt_resource *r, - struct rdt_domain *d); +int parse_bw(struct rdt_parse_data *data, struct rdt_resource *r, + struct rdt_domain *d); extern struct mutex rdtgroup_mutex; @@ -609,8 +623,7 @@ void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms); void cqm_handle_limbo(struct work_struct *work); bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d); void __check_limbo(struct rdt_domain *d, bool force_free); -bool cbm_validate_intel(char *buf, u32 *data, struct rdt_resource *r); -bool cbm_validate_amd(char *buf, u32 *data, struct rdt_resource *r); void rdt_domain_reconfigure_cdp(struct rdt_resource *r); +void __init thread_throttle_mode_init(void); #endif /* _ASM_X86_RESCTRL_INTERNAL_H */ diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index 837d7d012b7b..54dffe574e67 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -279,8 +279,7 @@ static void mbm_bw_count(u32 rmid, struct rmid_read *rr) return; chunks = mbm_overflow_count(m->prev_bw_msr, tval, rr->r->mbm_width); - m->chunks_bw += chunks; - m->chunks = m->chunks_bw; + m->chunks += chunks; cur_bw = (chunks * r->mon_scale) >> 20; if (m->delta_comp) @@ -478,19 +477,13 @@ void cqm_handle_limbo(struct work_struct *work) mutex_lock(&rdtgroup_mutex); r = &rdt_resources_all[RDT_RESOURCE_L3]; - d = get_domain_from_cpu(cpu, r); - - if (!d) { - pr_warn_once("Failure to get domain for limbo worker\n"); - goto out_unlock; - } + d = container_of(work, struct rdt_domain, cqm_limbo.work); __check_limbo(d, false); if (has_busy_rmid(r, d)) schedule_delayed_work_on(cpu, &d->cqm_limbo, delay); -out_unlock: mutex_unlock(&rdtgroup_mutex); } @@ -520,10 +513,7 @@ void mbm_handle_overflow(struct work_struct *work) goto out_unlock; r = &rdt_resources_all[RDT_RESOURCE_L3]; - - d = get_domain_from_cpu(cpu, r); - if (!d) - goto out_unlock; + d = container_of(work, struct rdt_domain, mbm_over.work); list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) { mbm_update(r, d, prgrp->mon.rmid); diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 3f844f14fc0a..b494187632b2 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -592,6 +592,18 @@ static int __rdtgroup_move_task(struct task_struct *tsk, return ret; } +static bool is_closid_match(struct task_struct *t, struct rdtgroup *r) +{ + return (rdt_alloc_capable && + (r->type == RDTCTRL_GROUP) && (t->closid == r->closid)); +} + +static bool is_rmid_match(struct task_struct *t, struct rdtgroup *r) +{ + return (rdt_mon_capable && + (r->type == RDTMON_GROUP) && (t->rmid == r->mon.rmid)); +} + /** * rdtgroup_tasks_assigned - Test if tasks have been assigned to resource group * @r: Resource group @@ -607,8 +619,7 @@ int rdtgroup_tasks_assigned(struct rdtgroup *r) rcu_read_lock(); for_each_process_thread(p, t) { - if ((r->type == RDTCTRL_GROUP && t->closid == r->closid) || - (r->type == RDTMON_GROUP && t->rmid == r->mon.rmid)) { + if (is_closid_match(t, r) || is_rmid_match(t, r)) { ret = 1; break; } @@ -706,8 +717,7 @@ static void show_rdt_tasks(struct rdtgroup *r, struct seq_file *s) rcu_read_lock(); for_each_process_thread(p, t) { - if ((r->type == RDTCTRL_GROUP && t->closid == r->closid) || - (r->type == RDTMON_GROUP && t->rmid == r->mon.rmid)) + if (is_closid_match(t, r) || is_rmid_match(t, r)) seq_printf(s, "%d\n", t->pid); } rcu_read_unlock(); @@ -1017,6 +1027,19 @@ static int max_threshold_occ_show(struct kernfs_open_file *of, return 0; } +static int rdt_thread_throttle_mode_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct rdt_resource *r = of->kn->parent->priv; + + if (r->membw.throttle_mode == THREAD_THROTTLE_PER_THREAD) + seq_puts(seq, "per-thread\n"); + else + seq_puts(seq, "max\n"); + + return 0; +} + static ssize_t max_threshold_occ_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { @@ -1513,6 +1536,17 @@ static struct rftype res_common_files[] = { .seq_show = rdt_delay_linear_show, .fflags = RF_CTRL_INFO | RFTYPE_RES_MB, }, + /* + * Platform specific which (if any) capabilities are provided by + * thread_throttle_mode. Defer "fflags" initialization to platform + * discovery. + */ + { + .name = "thread_throttle_mode", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_thread_throttle_mode_show, + }, { .name = "max_threshold_occupancy", .mode = 0644, @@ -1583,7 +1617,7 @@ static int rdtgroup_add_files(struct kernfs_node *kn, unsigned long fflags) lockdep_assert_held(&rdtgroup_mutex); for (rft = rfts; rft < rfts + len; rft++) { - if ((fflags & rft->fflags) == rft->fflags) { + if (rft->fflags && ((fflags & rft->fflags) == rft->fflags)) { ret = rdtgroup_add_file(kn, rft); if (ret) goto error; @@ -1600,6 +1634,33 @@ error: return ret; } +static struct rftype *rdtgroup_get_rftype_by_name(const char *name) +{ + struct rftype *rfts, *rft; + int len; + + rfts = res_common_files; + len = ARRAY_SIZE(res_common_files); + + for (rft = rfts; rft < rfts + len; rft++) { + if (!strcmp(rft->name, name)) + return rft; + } + + return NULL; +} + +void __init thread_throttle_mode_init(void) +{ + struct rftype *rft; + + rft = rdtgroup_get_rftype_by_name("thread_throttle_mode"); + if (!rft) + return; + + rft->fflags = RF_CTRL_INFO | RFTYPE_RES_MB; +} + /** * rdtgroup_kn_mode_restrict - Restrict user access to named resctrl file * @r: The resource group with which the file is associated. @@ -2245,18 +2306,6 @@ static int reset_all_ctrls(struct rdt_resource *r) return 0; } -static bool is_closid_match(struct task_struct *t, struct rdtgroup *r) -{ - return (rdt_alloc_capable && - (r->type == RDTCTRL_GROUP) && (t->closid == r->closid)); -} - -static bool is_rmid_match(struct task_struct *t, struct rdtgroup *r) -{ - return (rdt_mon_capable && - (r->type == RDTMON_GROUP) && (t->rmid == r->mon.rmid)); -} - /* * Move tasks from one to the other group. If @from is NULL, then all tasks * in the systems are moved unconditionally (used for teardown). @@ -3196,7 +3245,7 @@ int __init rdtgroup_init(void) * It may also be ok since that would enable debugging of RDT before * resctrl is mounted. * The reason why the debugfs directory is created here and not in - * rdt_mount() is because rdt_mount() takes rdtgroup_mutex and + * rdt_get_tree() is because rdt_get_tree() takes rdtgroup_mutex and * during the debugfs directory creation also &sb->s_type->i_mutex_key * (the lockdep class of inode->i_rwsem). Other filesystem * interactions (eg. SyS_getdents) have the lock ordering: diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index 3221b71a0df8..2eb0a8c44b35 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -35,6 +35,7 @@ static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_CDP_L3, CPUID_ECX, 2, 0x00000010, 1 }, { X86_FEATURE_CDP_L2, CPUID_ECX, 2, 0x00000010, 2 }, { X86_FEATURE_MBA, CPUID_EBX, 3, 0x00000010, 0 }, + { X86_FEATURE_PER_THREAD_MBA, CPUID_ECX, 0, 0x00000010, 3 }, { X86_FEATURE_HW_PSTATE, CPUID_EDX, 7, 0x80000007, 0 }, { X86_FEATURE_CPB, CPUID_EDX, 9, 0x80000007, 0 }, { X86_FEATURE_PROC_FEEDBACK, CPUID_EDX, 11, 0x80000007, 0 }, diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index a0e8fc7d85f1..ddffd80f5c52 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -229,8 +229,8 @@ static int dt_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, it = &of_ioapic_type[type_index]; ioapic_set_alloc_attr(&tmp, NUMA_NO_NODE, it->trigger, it->polarity); - tmp.ioapic_id = mpc_ioapic_id(mp_irqdomain_ioapic_idx(domain)); - tmp.ioapic_pin = fwspec->param[0]; + tmp.devid = mpc_ioapic_id(mp_irqdomain_ioapic_idx(domain)); + tmp.ioapic.pin = fwspec->param[0]; return mp_irqdomain_alloc(domain, virq, nr_irqs, &tmp); } diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 48ce44576947..ea8d51ec251b 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -115,7 +115,8 @@ void show_opcodes(struct pt_regs *regs, const char *loglvl) unsigned long prologue = regs->ip - PROLOGUE_SIZE; if (copy_code(regs, opcodes, prologue, sizeof(opcodes))) { - printk("%sCode: Bad RIP value.\n", loglvl); + printk("%sCode: Unable to access opcode bytes at RIP 0x%lx.\n", + loglvl, prologue); } else { printk("%sCode: %" __stringify(PROLOGUE_SIZE) "ph <%02x> %" __stringify(EPILOGUE_SIZE) "ph\n", loglvl, opcodes, diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index 61ddc3a5e5c2..701f196d7c68 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -5,7 +5,6 @@ #include <asm/fpu/internal.h> #include <asm/tlbflush.h> #include <asm/setup.h> -#include <asm/cmdline.h> #include <linux/sched.h> #include <linux/sched/task.h> @@ -238,51 +237,11 @@ static void __init fpu__init_system_ctx_switch(void) } /* - * We parse fpu parameters early because fpu__init_system() is executed - * before parse_early_param(). - */ -static void __init fpu__init_parse_early_param(void) -{ - char arg[32]; - char *argptr = arg; - int bit; - -#ifdef CONFIG_X86_32 - if (cmdline_find_option_bool(boot_command_line, "no387")) -#ifdef CONFIG_MATH_EMULATION - setup_clear_cpu_cap(X86_FEATURE_FPU); -#else - pr_err("Option 'no387' required CONFIG_MATH_EMULATION enabled.\n"); -#endif - - if (cmdline_find_option_bool(boot_command_line, "nofxsr")) - setup_clear_cpu_cap(X86_FEATURE_FXSR); -#endif - - if (cmdline_find_option_bool(boot_command_line, "noxsave")) - setup_clear_cpu_cap(X86_FEATURE_XSAVE); - - if (cmdline_find_option_bool(boot_command_line, "noxsaveopt")) - setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); - - if (cmdline_find_option_bool(boot_command_line, "noxsaves")) - setup_clear_cpu_cap(X86_FEATURE_XSAVES); - - if (cmdline_find_option(boot_command_line, "clearcpuid", arg, - sizeof(arg)) && - get_option(&argptr, &bit) && - bit >= 0 && - bit < NCAPINTS * 32) - setup_clear_cpu_cap(bit); -} - -/* * Called on the boot CPU once per system bootup, to set up the initial * FPU state that is later cloned into all processes: */ void __init fpu__init_system(struct cpuinfo_x86 *c) { - fpu__init_parse_early_param(); fpu__init_system_early_generic(c); /* diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 038e19c0019e..5d8047441a0a 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -37,6 +37,7 @@ static const char *xfeature_names[] = "AVX-512 ZMM_Hi256" , "Processor Trace (unused)" , "Protection Keys User registers", + "PASID state", "unknown xstate feature" , }; @@ -51,6 +52,7 @@ static short xsave_cpuid_features[] __initdata = { X86_FEATURE_AVX512F, X86_FEATURE_INTEL_PT, X86_FEATURE_PKU, + X86_FEATURE_ENQCMD, }; /* @@ -318,6 +320,7 @@ static void __init print_xstate_features(void) print_xstate_feature(XFEATURE_MASK_ZMM_Hi256); print_xstate_feature(XFEATURE_MASK_Hi16_ZMM); print_xstate_feature(XFEATURE_MASK_PKRU); + print_xstate_feature(XFEATURE_MASK_PASID); } /* @@ -592,6 +595,7 @@ static void check_xstate_against_struct(int nr) XCHECK_SZ(sz, nr, XFEATURE_ZMM_Hi256, struct avx_512_zmm_uppers_state); XCHECK_SZ(sz, nr, XFEATURE_Hi16_ZMM, struct avx_512_hi16_state); XCHECK_SZ(sz, nr, XFEATURE_PKRU, struct pkru_state); + XCHECK_SZ(sz, nr, XFEATURE_PASID, struct ia32_pasid_state); /* * Make *SURE* to add any feature numbers in below if @@ -601,7 +605,7 @@ static void check_xstate_against_struct(int nr) if ((nr < XFEATURE_YMM) || (nr >= XFEATURE_MAX) || (nr == XFEATURE_PT_UNIMPLEMENTED_SO_FAR) || - ((nr >= XFEATURE_RSRVD_COMP_10) && (nr <= XFEATURE_LBR))) { + ((nr >= XFEATURE_RSRVD_COMP_11) && (nr <= XFEATURE_LBR))) { WARN_ONCE(1, "no structure for xstate: %d\n", nr); XSTATE_WARN_ON(1); } @@ -1398,3 +1402,60 @@ int proc_pid_arch_status(struct seq_file *m, struct pid_namespace *ns, return 0; } #endif /* CONFIG_PROC_PID_ARCH_STATUS */ + +#ifdef CONFIG_IOMMU_SUPPORT +void update_pasid(void) +{ + u64 pasid_state; + u32 pasid; + + if (!cpu_feature_enabled(X86_FEATURE_ENQCMD)) + return; + + if (!current->mm) + return; + + pasid = READ_ONCE(current->mm->pasid); + /* Set the valid bit in the PASID MSR/state only for valid pasid. */ + pasid_state = pasid == PASID_DISABLED ? + pasid : pasid | MSR_IA32_PASID_VALID; + + /* + * No need to hold fregs_lock() since the task's fpstate won't + * be changed by others (e.g. ptrace) while the task is being + * switched to or is in IPI. + */ + if (!test_thread_flag(TIF_NEED_FPU_LOAD)) { + /* The MSR is active and can be directly updated. */ + wrmsrl(MSR_IA32_PASID, pasid_state); + } else { + struct fpu *fpu = ¤t->thread.fpu; + struct ia32_pasid_state *ppasid_state; + struct xregs_state *xsave; + + /* + * The CPU's xstate registers are not currently active. Just + * update the PASID state in the memory buffer here. The + * PASID MSR will be loaded when returning to user mode. + */ + xsave = &fpu->state.xsave; + xsave->header.xfeatures |= XFEATURE_MASK_PASID; + ppasid_state = get_xsave_addr(xsave, XFEATURE_PASID); + /* + * Since XFEATURE_MASK_PASID is set in xfeatures, ppasid_state + * won't be NULL and no need to check its value. + * + * Only update the task's PASID state when it's different + * from the mm's pasid. + */ + if (ppasid_state->pasid != pasid_state) { + /* + * Invalid fpregs so that state restoring will pick up + * the PASID state. + */ + __fpu_invalidate_fpregs_state(fpu); + ppasid_state->pasid = pasid_state; + } + } +} +#endif /* CONFIG_IOMMU_SUPPORT */ diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index b98ff620ba77..03aa33b58165 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -442,42 +442,6 @@ int hw_breakpoint_arch_parse(struct perf_event *bp, } /* - * Dump the debug register contents to the user. - * We can't dump our per cpu values because it - * may contain cpu wide breakpoint, something that - * doesn't belong to the current task. - * - * TODO: include non-ptrace user breakpoints (perf) - */ -void aout_dump_debugregs(struct user *dump) -{ - int i; - int dr7 = 0; - struct perf_event *bp; - struct arch_hw_breakpoint *info; - struct thread_struct *thread = ¤t->thread; - - for (i = 0; i < HBP_NUM; i++) { - bp = thread->ptrace_bps[i]; - - if (bp && !bp->attr.disabled) { - dump->u_debugreg[i] = bp->attr.bp_addr; - info = counter_arch_bp(bp); - dr7 |= encode_dr7(i, info->len, info->type); - } else { - dump->u_debugreg[i] = 0; - } - } - - dump->u_debugreg[4] = 0; - dump->u_debugreg[5] = 0; - dump->u_debugreg[6] = current->thread.debugreg6; - - dump->u_debugreg[7] = dr7; -} -EXPORT_SYMBOL_GPL(aout_dump_debugregs); - -/* * Release the user breakpoints used by ptrace */ void flush_ptrace_hw_breakpoint(struct task_struct *tsk) @@ -490,7 +454,7 @@ void flush_ptrace_hw_breakpoint(struct task_struct *tsk) t->ptrace_bps[i] = NULL; } - t->debugreg6 = 0; + t->virtual_dr6 = 0; t->ptrace_dr7 = 0; } @@ -500,7 +464,7 @@ void hw_breakpoint_restore(void) set_debugreg(__this_cpu_read(cpu_debugreg[1]), 1); set_debugreg(__this_cpu_read(cpu_debugreg[2]), 2); set_debugreg(__this_cpu_read(cpu_debugreg[3]), 3); - set_debugreg(current->thread.debugreg6, 6); + set_debugreg(DR6_RESERVED, 6); set_debugreg(__this_cpu_read(cpu_dr7), 7); } EXPORT_SYMBOL_GPL(hw_breakpoint_restore); @@ -523,10 +487,10 @@ EXPORT_SYMBOL_GPL(hw_breakpoint_restore); */ static int hw_breakpoint_handler(struct die_args *args) { - int i, cpu, rc = NOTIFY_STOP; + int i, rc = NOTIFY_STOP; struct perf_event *bp; - unsigned long dr6; unsigned long *dr6_p; + unsigned long dr6; /* The DR6 value is pointed by args->err */ dr6_p = (unsigned long *)ERR_PTR(args->err); @@ -540,14 +504,6 @@ static int hw_breakpoint_handler(struct die_args *args) if ((dr6 & DR_TRAP_BITS) == 0) return NOTIFY_DONE; - /* - * Assert that local interrupts are disabled - * Reset the DRn bits in the virtualized register value. - * The ptrace trigger routine will add in whatever is needed. - */ - current->thread.debugreg6 &= ~DR_TRAP_BITS; - cpu = get_cpu(); - /* Handle all the breakpoints that were triggered */ for (i = 0; i < HBP_NUM; ++i) { if (likely(!(dr6 & (DR_TRAP0 << i)))) @@ -561,7 +517,7 @@ static int hw_breakpoint_handler(struct die_args *args) */ rcu_read_lock(); - bp = per_cpu(bp_per_reg[i], cpu); + bp = this_cpu_read(bp_per_reg[i]); /* * Reset the 'i'th TRAP bit in dr6 to denote completion of * exception handling @@ -592,12 +548,10 @@ static int hw_breakpoint_handler(struct die_args *args) * breakpoints (to generate signals) and b) when the system has * taken exception due to multiple causes */ - if ((current->thread.debugreg6 & DR_TRAP_BITS) || + if ((current->thread.virtual_dr6 & DR_TRAP_BITS) || (dr6 & (~DR_TRAP_BITS))) rc = NOTIFY_DONE; - put_cpu(); - return rc; } diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index c2f02f308ecf..ff7878df96b4 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -629,9 +629,10 @@ static void kgdb_hw_overflow_handler(struct perf_event *event, struct task_struct *tsk = current; int i; - for (i = 0; i < 4; i++) + for (i = 0; i < 4; i++) { if (breakinfo[i].enabled) - tsk->thread.debugreg6 |= (DR_TRAP0 << i); + tsk->thread.virtual_dr6 |= (DR_TRAP0 << i); + } } void kgdb_arch_late(void) diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index fdadc37d72af..db8f8693ab8d 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -767,124 +767,21 @@ asm( NOKPROBE_SYMBOL(kretprobe_trampoline); STACK_FRAME_NON_STANDARD(kretprobe_trampoline); + /* * Called from kretprobe_trampoline */ __used __visible void *trampoline_handler(struct pt_regs *regs) { - struct kretprobe_instance *ri = NULL; - struct hlist_head *head, empty_rp; - struct hlist_node *tmp; - unsigned long flags, orig_ret_address = 0; - unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline; - kprobe_opcode_t *correct_ret_addr = NULL; - void *frame_pointer; - bool skipped = false; - - /* - * Set a dummy kprobe for avoiding kretprobe recursion. - * Since kretprobe never run in kprobe handler, kprobe must not - * be running at this point. - */ - kprobe_busy_begin(); - - INIT_HLIST_HEAD(&empty_rp); - kretprobe_hash_lock(current, &head, &flags); /* fixup registers */ regs->cs = __KERNEL_CS; #ifdef CONFIG_X86_32 - regs->cs |= get_kernel_rpl(); regs->gs = 0; #endif - /* We use pt_regs->sp for return address holder. */ - frame_pointer = ®s->sp; - regs->ip = trampoline_address; + regs->ip = (unsigned long)&kretprobe_trampoline; regs->orig_ax = ~0UL; - /* - * It is possible to have multiple instances associated with a given - * task either because multiple functions in the call path have - * return probes installed on them, and/or more than one - * return probe was registered for a target function. - * - * We can handle this because: - * - instances are always pushed into the head of the list - * - when multiple return probes are registered for the same - * function, the (chronologically) first instance's ret_addr - * will be the real return address, and all the rest will - * point to kretprobe_trampoline. - */ - hlist_for_each_entry(ri, head, hlist) { - if (ri->task != current) - /* another task is sharing our hash bucket */ - continue; - /* - * Return probes must be pushed on this hash list correct - * order (same as return order) so that it can be popped - * correctly. However, if we find it is pushed it incorrect - * order, this means we find a function which should not be - * probed, because the wrong order entry is pushed on the - * path of processing other kretprobe itself. - */ - if (ri->fp != frame_pointer) { - if (!skipped) - pr_warn("kretprobe is stacked incorrectly. Trying to fixup.\n"); - skipped = true; - continue; - } - - orig_ret_address = (unsigned long)ri->ret_addr; - if (skipped) - pr_warn("%ps must be blacklisted because of incorrect kretprobe order\n", - ri->rp->kp.addr); - - if (orig_ret_address != trampoline_address) - /* - * This is the real return address. Any other - * instances associated with this task are for - * other calls deeper on the call stack - */ - break; - } - - kretprobe_assert(ri, orig_ret_address, trampoline_address); - - correct_ret_addr = ri->ret_addr; - hlist_for_each_entry_safe(ri, tmp, head, hlist) { - if (ri->task != current) - /* another task is sharing our hash bucket */ - continue; - if (ri->fp != frame_pointer) - continue; - - orig_ret_address = (unsigned long)ri->ret_addr; - if (ri->rp && ri->rp->handler) { - __this_cpu_write(current_kprobe, &ri->rp->kp); - ri->ret_addr = correct_ret_addr; - ri->rp->handler(ri, regs); - __this_cpu_write(current_kprobe, &kprobe_busy); - } - - recycle_rp_inst(ri, &empty_rp); - - if (orig_ret_address != trampoline_address) - /* - * This is the real return address. Any other - * instances associated with this task are for - * other calls deeper on the call stack - */ - break; - } - - kretprobe_hash_unlock(current, &flags); - - kprobe_busy_end(); - - hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { - hlist_del(&ri->hlist); - kfree(ri); - } - return (void *)orig_ret_address; + return (void *)kretprobe_trampoline_handler(regs, &kretprobe_trampoline, ®s->sp); } NOKPROBE_SYMBOL(trampoline_handler); diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 40f380461e6d..15e06408f6ba 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -18,6 +18,7 @@ #include <linux/ftrace.h> #include <linux/frame.h> #include <linux/pgtable.h> +#include <linux/static_call.h> #include <asm/text-patching.h> #include <asm/cacheflush.h> @@ -181,7 +182,6 @@ optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs) /* Save skipped registers */ regs->cs = __KERNEL_CS; #ifdef CONFIG_X86_32 - regs->cs |= get_kernel_rpl(); regs->gs = 0; #endif regs->ip = (unsigned long)op->kp.addr + INT3_INSN_SIZE; @@ -210,7 +210,8 @@ static int copy_optimized_instructions(u8 *dest, u8 *src, u8 *real) /* Check whether the address range is reserved */ if (ftrace_text_reserved(src, src + len - 1) || alternatives_text_reserved(src, src + len - 1) || - jump_label_text_reserved(src, src + len - 1)) + jump_label_text_reserved(src, src + len - 1) || + static_call_text_reserved(src, src + len - 1)) return -EBUSY; return len; diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index baa21090c9be..8f06449aab27 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -24,7 +24,6 @@ #include <asm/irqdomain.h> #include <asm/mtrr.h> #include <asm/mpspec.h> -#include <asm/io_apic.h> #include <asm/proto.h> #include <asm/bios_ebda.h> #include <asm/e820/api.h> @@ -46,11 +45,6 @@ static int __init mpf_checksum(unsigned char *mp, int len) return sum & 0xFF; } -int __init default_mpc_apic_id(struct mpc_cpu *m) -{ - return m->apicid; -} - static void __init MP_processor_info(struct mpc_cpu *m) { int apicid; @@ -61,7 +55,7 @@ static void __init MP_processor_info(struct mpc_cpu *m) return; } - apicid = x86_init.mpparse.mpc_apic_id(m); + apicid = m->apicid; if (m->cpuflag & CPU_BOOTPROCESSOR) { bootup_cpu = " (Bootup-CPU)"; @@ -73,7 +67,7 @@ static void __init MP_processor_info(struct mpc_cpu *m) } #ifdef CONFIG_X86_IO_APIC -void __init default_mpc_oem_bus_info(struct mpc_bus *m, char *str) +static void __init mpc_oem_bus_info(struct mpc_bus *m, char *str) { memcpy(str, m->bustype, 6); str[6] = 0; @@ -84,7 +78,7 @@ static void __init MP_bus_info(struct mpc_bus *m) { char str[7]; - x86_init.mpparse.mpc_oem_bus_info(m, str); + mpc_oem_bus_info(m, str); #if MAX_MP_BUSSES < 256 if (m->busid >= MAX_MP_BUSSES) { @@ -100,9 +94,6 @@ static void __init MP_bus_info(struct mpc_bus *m) mp_bus_id_to_type[m->busid] = MP_BUS_ISA; #endif } else if (strncmp(str, BUSTYPE_PCI, sizeof(BUSTYPE_PCI) - 1) == 0) { - if (x86_init.mpparse.mpc_oem_pci_bus) - x86_init.mpparse.mpc_oem_pci_bus(m); - clear_bit(m->busid, mp_bus_not_pci); #ifdef CONFIG_EISA mp_bus_id_to_type[m->busid] = MP_BUS_PCI; @@ -198,8 +189,6 @@ static void __init smp_dump_mptable(struct mpc_table *mpc, unsigned char *mpt) 1, mpc, mpc->length, 1); } -void __init default_smp_read_mpc_oem(struct mpc_table *mpc) { } - static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early) { char str[16]; @@ -218,14 +207,7 @@ static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early) if (early) return 1; - if (mpc->oemptr) - x86_init.mpparse.smp_read_mpc_oem(mpc); - - /* - * Now process the configuration blocks. - */ - x86_init.mpparse.mpc_record(0); - + /* Now process the configuration blocks. */ while (count < mpc->length) { switch (*mpt) { case MP_PROCESSOR: @@ -256,7 +238,6 @@ static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early) count = mpc->length; break; } - x86_init.mpparse.mpc_record(1); } if (!num_processors) diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c index 49dcfb85e773..c0d409810658 100644 --- a/arch/x86/kernel/msr.c +++ b/arch/x86/kernel/msr.c @@ -80,18 +80,30 @@ static ssize_t msr_read(struct file *file, char __user *buf, static int filter_write(u32 reg) { + /* + * MSRs writes usually happen all at once, and can easily saturate kmsg. + * Only allow one message every 30 seconds. + * + * It's possible to be smarter here and do it (for example) per-MSR, but + * it would certainly be more complex, and this is enough at least to + * avoid saturating the ring buffer. + */ + static DEFINE_RATELIMIT_STATE(fw_rs, 30 * HZ, 1); + switch (allow_writes) { case MSR_WRITES_ON: return 0; case MSR_WRITES_OFF: return -EPERM; default: break; } + if (!__ratelimit(&fw_rs)) + return 0; + if (reg == MSR_IA32_ENERGY_PERF_BIAS) return 0; - pr_err_ratelimited("Write to unrecognized MSR 0x%x by %s\n" - "Please report to x86@kernel.org\n", - reg, current->comm); + pr_err("Write to unrecognized MSR 0x%x by %s (pid: %d). Please report to x86@kernel.org.\n", + reg, current->comm, current->pid); return 0; } diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 4fc9954a9560..47381666d6a5 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -102,7 +102,6 @@ fs_initcall(nmi_warning_debugfs); static void nmi_check_duration(struct nmiaction *action, u64 duration) { - u64 whole_msecs = READ_ONCE(action->max_duration); int remainder_ns, decimal_msecs; if (duration < nmi_longest_ns || duration < action->max_duration) @@ -110,12 +109,12 @@ static void nmi_check_duration(struct nmiaction *action, u64 duration) action->max_duration = duration; - remainder_ns = do_div(whole_msecs, (1000 * 1000)); + remainder_ns = do_div(duration, (1000 * 1000)); decimal_msecs = remainder_ns / 1000; printk_ratelimited(KERN_INFO "INFO: NMI handler (%ps) took too long to run: %lld.%03d msecs\n", - action->handler, whole_msecs, decimal_msecs); + action->handler, duration, decimal_msecs); } static int nmi_handle(unsigned int type, struct pt_regs *regs) diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index de2138ba38e5..6c3407ba6ee9 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -263,13 +263,8 @@ enum paravirt_lazy_mode paravirt_get_lazy_mode(void) struct pv_info pv_info = { .name = "bare hardware", #ifdef CONFIG_PARAVIRT_XXL - .kernel_rpl = 0, - .shared_kernel_pmd = 1, /* Only used when CONFIG_X86_PAE is set */ - -#ifdef CONFIG_X86_64 .extra_user_64bit_cs = __USER_CS, #endif -#endif }; /* 64-bit pagetable entries */ @@ -305,9 +300,7 @@ struct paravirt_patch_template pv_ops = { .cpu.load_idt = native_load_idt, .cpu.store_tr = native_store_tr, .cpu.load_tls = native_load_tls, -#ifdef CONFIG_X86_64 .cpu.load_gs_index = native_load_gs_index, -#endif .cpu.write_ldt_entry = native_write_ldt_entry, .cpu.write_gdt_entry = native_write_gdt_entry, .cpu.write_idt_entry = native_write_idt_entry, @@ -317,9 +310,7 @@ struct paravirt_patch_template pv_ops = { .cpu.load_sp0 = native_load_sp0, -#ifdef CONFIG_X86_64 .cpu.usergs_sysret64 = native_usergs_sysret64, -#endif .cpu.iret = native_iret, .cpu.swapgs = native_swapgs, @@ -369,24 +360,16 @@ struct paravirt_patch_template pv_ops = { .mmu.release_p4d = paravirt_nop, .mmu.set_pte = native_set_pte, - .mmu.set_pte_at = native_set_pte_at, .mmu.set_pmd = native_set_pmd, .mmu.ptep_modify_prot_start = __ptep_modify_prot_start, .mmu.ptep_modify_prot_commit = __ptep_modify_prot_commit, -#if CONFIG_PGTABLE_LEVELS >= 3 -#ifdef CONFIG_X86_PAE - .mmu.set_pte_atomic = native_set_pte_atomic, - .mmu.pte_clear = native_pte_clear, - .mmu.pmd_clear = native_pmd_clear, -#endif .mmu.set_pud = native_set_pud, .mmu.pmd_val = PTE_IDENT, .mmu.make_pmd = PTE_IDENT, -#if CONFIG_PGTABLE_LEVELS >= 4 .mmu.pud_val = PTE_IDENT, .mmu.make_pud = PTE_IDENT, @@ -398,8 +381,6 @@ struct paravirt_patch_template pv_ops = { .mmu.set_pgd = native_set_pgd, #endif /* CONFIG_PGTABLE_LEVELS >= 5 */ -#endif /* CONFIG_PGTABLE_LEVELS >= 4 */ -#endif /* CONFIG_PGTABLE_LEVELS >= 3 */ .mmu.pte_val = PTE_IDENT, .mmu.pgd_val = PTE_IDENT, diff --git a/arch/x86/kernel/paravirt_patch.c b/arch/x86/kernel/paravirt_patch.c index 3eff63c090d2..ace6e334cb39 100644 --- a/arch/x86/kernel/paravirt_patch.c +++ b/arch/x86/kernel/paravirt_patch.c @@ -26,14 +26,10 @@ struct patch_xxl { const unsigned char mmu_read_cr3[3]; const unsigned char mmu_write_cr3[3]; const unsigned char irq_restore_fl[2]; -# ifdef CONFIG_X86_64 const unsigned char cpu_wbinvd[2]; const unsigned char cpu_usergs_sysret64[6]; const unsigned char cpu_swapgs[3]; const unsigned char mov64[3]; -# else - const unsigned char cpu_iret[1]; -# endif }; static const struct patch_xxl patch_data_xxl = { @@ -42,7 +38,6 @@ static const struct patch_xxl patch_data_xxl = { .irq_save_fl = { 0x9c, 0x58 }, // pushf; pop %[re]ax .mmu_read_cr2 = { 0x0f, 0x20, 0xd0 }, // mov %cr2, %[re]ax .mmu_read_cr3 = { 0x0f, 0x20, 0xd8 }, // mov %cr3, %[re]ax -# ifdef CONFIG_X86_64 .mmu_write_cr3 = { 0x0f, 0x22, 0xdf }, // mov %rdi, %cr3 .irq_restore_fl = { 0x57, 0x9d }, // push %rdi; popfq .cpu_wbinvd = { 0x0f, 0x09 }, // wbinvd @@ -50,19 +45,11 @@ static const struct patch_xxl patch_data_xxl = { 0x48, 0x0f, 0x07 }, // swapgs; sysretq .cpu_swapgs = { 0x0f, 0x01, 0xf8 }, // swapgs .mov64 = { 0x48, 0x89, 0xf8 }, // mov %rdi, %rax -# else - .mmu_write_cr3 = { 0x0f, 0x22, 0xd8 }, // mov %eax, %cr3 - .irq_restore_fl = { 0x50, 0x9d }, // push %eax; popf - .cpu_iret = { 0xcf }, // iret -# endif }; unsigned int paravirt_patch_ident_64(void *insn_buff, unsigned int len) { -#ifdef CONFIG_X86_64 return PATCH(xxl, mov64, insn_buff, len); -#endif - return 0; } # endif /* CONFIG_PARAVIRT_XXL */ @@ -98,13 +85,9 @@ unsigned int native_patch(u8 type, void *insn_buff, unsigned long addr, PATCH_CASE(mmu, read_cr3, xxl, insn_buff, len); PATCH_CASE(mmu, write_cr3, xxl, insn_buff, len); -# ifdef CONFIG_X86_64 PATCH_CASE(cpu, usergs_sysret64, xxl, insn_buff, len); PATCH_CASE(cpu, swapgs, xxl, insn_buff, len); PATCH_CASE(cpu, wbinvd, xxl, insn_buff, len); -# else - PATCH_CASE(cpu, iret, xxl, insn_buff, len); -# endif #endif #ifdef CONFIG_PARAVIRT_SPINLOCKS diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 9afefe325acb..df342bedea88 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -407,7 +407,7 @@ unsigned long x86_gsbase_read_cpu_inactive(void) { unsigned long gsbase; - if (static_cpu_has(X86_FEATURE_FSGSBASE)) { + if (boot_cpu_has(X86_FEATURE_FSGSBASE)) { unsigned long flags; local_irq_save(flags); @@ -422,7 +422,7 @@ unsigned long x86_gsbase_read_cpu_inactive(void) void x86_gsbase_write_cpu_inactive(unsigned long gsbase) { - if (static_cpu_has(X86_FEATURE_FSGSBASE)) { + if (boot_cpu_has(X86_FEATURE_FSGSBASE)) { unsigned long flags; local_irq_save(flags); @@ -439,7 +439,7 @@ unsigned long x86_fsbase_read_task(struct task_struct *task) if (task == current) fsbase = x86_fsbase_read_cpu(); - else if (static_cpu_has(X86_FEATURE_FSGSBASE) || + else if (boot_cpu_has(X86_FEATURE_FSGSBASE) || (task->thread.fsindex == 0)) fsbase = task->thread.fsbase; else @@ -454,7 +454,7 @@ unsigned long x86_gsbase_read_task(struct task_struct *task) if (task == current) gsbase = x86_gsbase_read_cpu_inactive(); - else if (static_cpu_has(X86_FEATURE_FSGSBASE) || + else if (boot_cpu_has(X86_FEATURE_FSGSBASE) || (task->thread.gsindex == 0)) gsbase = task->thread.gsbase; else diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index e7537c5440bb..bedca011459c 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -465,7 +465,7 @@ static void ptrace_triggered(struct perf_event *bp, break; } - thread->debugreg6 |= (DR_TRAP0 << i); + thread->virtual_dr6 |= (DR_TRAP0 << i); } /* @@ -601,7 +601,7 @@ static unsigned long ptrace_get_debugreg(struct task_struct *tsk, int n) if (bp) val = bp->hw.info.address; } else if (n == 6) { - val = thread->debugreg6; + val = thread->virtual_dr6 ^ DR6_RESERVED; /* Flip back to arch polarity */ } else if (n == 7) { val = thread->ptrace_dr7; } @@ -657,7 +657,7 @@ static int ptrace_set_debugreg(struct task_struct *tsk, int n, if (n < HBP_NUM) { rc = ptrace_set_breakpoint_addr(tsk, n, val); } else if (n == 6) { - thread->debugreg6 = val; + thread->virtual_dr6 = val ^ DR6_RESERVED; /* Flip to positive polarity */ rc = 0; } else if (n == 7) { rc = ptrace_write_dr7(tsk, val); diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 3511736fbc74..fa16b906ea3f 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -19,6 +19,7 @@ #include <linux/hugetlb.h> #include <linux/tboot.h> #include <linux/usb/xhci-dbgp.h> +#include <linux/static_call.h> #include <uapi/linux/mount.h> @@ -849,6 +850,7 @@ void __init setup_arch(char **cmdline_p) early_cpu_init(); arch_init_ideal_nops(); jump_label_init(); + static_call_init(); early_ioremap_init(); setup_olpc_ofw_pgd(); @@ -1077,6 +1079,7 @@ void __init setup_arch(char **cmdline_p) efi_fake_memmap(); efi_find_mirror(); efi_esrt_init(); + efi_mokvar_table_init(); /* * The EFI specification says that boot service code won't be diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c new file mode 100644 index 000000000000..ca9a380d9c0b --- /dev/null +++ b/arch/x86/kernel/static_call.c @@ -0,0 +1,98 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/static_call.h> +#include <linux/memory.h> +#include <linux/bug.h> +#include <asm/text-patching.h> + +enum insn_type { + CALL = 0, /* site call */ + NOP = 1, /* site cond-call */ + JMP = 2, /* tramp / site tail-call */ + RET = 3, /* tramp / site cond-tail-call */ +}; + +static void __ref __static_call_transform(void *insn, enum insn_type type, void *func) +{ + int size = CALL_INSN_SIZE; + const void *code; + + switch (type) { + case CALL: + code = text_gen_insn(CALL_INSN_OPCODE, insn, func); + break; + + case NOP: + code = ideal_nops[NOP_ATOMIC5]; + break; + + case JMP: + code = text_gen_insn(JMP32_INSN_OPCODE, insn, func); + break; + + case RET: + code = text_gen_insn(RET_INSN_OPCODE, insn, func); + size = RET_INSN_SIZE; + break; + } + + if (memcmp(insn, code, size) == 0) + return; + + if (unlikely(system_state == SYSTEM_BOOTING)) + return text_poke_early(insn, code, size); + + text_poke_bp(insn, code, size, NULL); +} + +static void __static_call_validate(void *insn, bool tail) +{ + u8 opcode = *(u8 *)insn; + + if (tail) { + if (opcode == JMP32_INSN_OPCODE || + opcode == RET_INSN_OPCODE) + return; + } else { + if (opcode == CALL_INSN_OPCODE || + !memcmp(insn, ideal_nops[NOP_ATOMIC5], 5)) + return; + } + + /* + * If we ever trigger this, our text is corrupt, we'll probably not live long. + */ + WARN_ONCE(1, "unexpected static_call insn opcode 0x%x at %pS\n", opcode, insn); +} + +static inline enum insn_type __sc_insn(bool null, bool tail) +{ + /* + * Encode the following table without branches: + * + * tail null insn + * -----+-------+------ + * 0 | 0 | CALL + * 0 | 1 | NOP + * 1 | 0 | JMP + * 1 | 1 | RET + */ + return 2*tail + null; +} + +void arch_static_call_transform(void *site, void *tramp, void *func, bool tail) +{ + mutex_lock(&text_mutex); + + if (tramp) { + __static_call_validate(tramp, true); + __static_call_transform(tramp, __sc_insn(!func, true), func); + } + + if (IS_ENABLED(CONFIG_HAVE_STATIC_CALL_INLINE) && site) { + __static_call_validate(site, tail); + __static_call_transform(site, __sc_insn(!func, tail), func); + } + + mutex_unlock(&text_mutex); +} +EXPORT_SYMBOL_GPL(arch_static_call_transform); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 316ce1c09e84..ec3a2572843f 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -745,9 +745,21 @@ static __always_inline unsigned long debug_read_clear_dr6(void) * Keep it simple: clear DR6 immediately. */ get_debugreg(dr6, 6); - set_debugreg(0, 6); - /* Filter out all the reserved bits which are preset to 1 */ - dr6 &= ~DR6_RESERVED; + set_debugreg(DR6_RESERVED, 6); + dr6 ^= DR6_RESERVED; /* Flip to positive polarity */ + + /* + * Clear the virtual DR6 value, ptrace routines will set bits here for + * things we want signals for. + */ + current->thread.virtual_dr6 = 0; + + /* + * The SDM says "The processor clears the BTF flag when it + * generates a debug exception." Clear TIF_BLOCKSTEP to keep + * TIF_BLOCKSTEP in sync with the hardware BTF flag. + */ + clear_thread_flag(TIF_BLOCKSTEP); return dr6; } @@ -776,74 +788,20 @@ static __always_inline unsigned long debug_read_clear_dr6(void) * * May run on IST stack. */ -static void handle_debug(struct pt_regs *regs, unsigned long dr6, bool user) -{ - struct task_struct *tsk = current; - bool user_icebp; - int si_code; - - /* - * The SDM says "The processor clears the BTF flag when it - * generates a debug exception." Clear TIF_BLOCKSTEP to keep - * TIF_BLOCKSTEP in sync with the hardware BTF flag. - */ - clear_thread_flag(TIF_BLOCKSTEP); - - /* - * If DR6 is zero, no point in trying to handle it. The kernel is - * not using INT1. - */ - if (!user && !dr6) - return; +static bool notify_debug(struct pt_regs *regs, unsigned long *dr6) +{ /* - * If dr6 has no reason to give us about the origin of this trap, - * then it's very likely the result of an icebp/int01 trap. - * User wants a sigtrap for that. + * Notifiers will clear bits in @dr6 to indicate the event has been + * consumed - hw_breakpoint_handler(), single_stop_cont(). + * + * Notifiers will set bits in @virtual_dr6 to indicate the desire + * for signals - ptrace_triggered(), kgdb_hw_overflow_handler(). */ - user_icebp = user && !dr6; - - /* Store the virtualized DR6 value */ - tsk->thread.debugreg6 = dr6; - -#ifdef CONFIG_KPROBES - if (kprobe_debug_handler(regs)) { - return; - } -#endif - - if (notify_die(DIE_DEBUG, "debug", regs, (long)&dr6, 0, - SIGTRAP) == NOTIFY_STOP) { - return; - } - - /* It's safe to allow irq's after DR6 has been saved */ - cond_local_irq_enable(regs); - - if (v8086_mode(regs)) { - handle_vm86_trap((struct kernel_vm86_regs *) regs, 0, - X86_TRAP_DB); - goto out; - } - - if (WARN_ON_ONCE((dr6 & DR_STEP) && !user_mode(regs))) { - /* - * Historical junk that used to handle SYSENTER single-stepping. - * This should be unreachable now. If we survive for a while - * without anyone hitting this warning, we'll turn this into - * an oops. - */ - tsk->thread.debugreg6 &= ~DR_STEP; - set_tsk_thread_flag(tsk, TIF_SINGLESTEP); - regs->flags &= ~X86_EFLAGS_TF; - } - - si_code = get_si_code(tsk->thread.debugreg6); - if (tsk->thread.debugreg6 & (DR_STEP | DR_TRAP_BITS) || user_icebp) - send_sigtrap(regs, 0, si_code); + if (notify_die(DIE_DEBUG, "debug", regs, (long)dr6, 0, SIGTRAP) == NOTIFY_STOP) + return true; -out: - cond_local_irq_disable(regs); + return false; } static __always_inline void exc_debug_kernel(struct pt_regs *regs, @@ -877,8 +835,32 @@ static __always_inline void exc_debug_kernel(struct pt_regs *regs, if ((dr6 & DR_STEP) && is_sysenter_singlestep(regs)) dr6 &= ~DR_STEP; - handle_debug(regs, dr6, false); + if (kprobe_debug_handler(regs)) + goto out; + + /* + * The kernel doesn't use INT1 + */ + if (!dr6) + goto out; + if (notify_debug(regs, &dr6)) + goto out; + + /* + * The kernel doesn't use TF single-step outside of: + * + * - Kprobes, consumed through kprobe_debug_handler() + * - KGDB, consumed through notify_debug() + * + * So if we get here with DR_STEP set, something is wonky. + * + * A known way to trigger this is through QEMU's GDB stub, + * which leaks #DB into the guest and causes IST recursion. + */ + if (WARN_ON_ONCE(dr6 & DR_STEP)) + regs->flags &= ~X86_EFLAGS_TF; +out: instrumentation_end(); idtentry_exit_nmi(regs, irq_state); @@ -888,6 +870,8 @@ static __always_inline void exc_debug_kernel(struct pt_regs *regs, static __always_inline void exc_debug_user(struct pt_regs *regs, unsigned long dr6) { + bool icebp; + /* * If something gets miswired and we end up here for a kernel mode * #DB, we will malfunction. @@ -906,8 +890,32 @@ static __always_inline void exc_debug_user(struct pt_regs *regs, irqentry_enter_from_user_mode(regs); instrumentation_begin(); - handle_debug(regs, dr6, true); + /* + * If dr6 has no reason to give us about the origin of this trap, + * then it's very likely the result of an icebp/int01 trap. + * User wants a sigtrap for that. + */ + icebp = !dr6; + if (notify_debug(regs, &dr6)) + goto out; + + /* It's safe to allow irq's after DR6 has been saved */ + local_irq_enable(); + + if (v8086_mode(regs)) { + handle_vm86_trap((struct kernel_vm86_regs *)regs, 0, X86_TRAP_DB); + goto out_irq; + } + + /* Add the virtual_dr6 bits for signals. */ + dr6 |= current->thread.virtual_dr6; + if (dr6 & (DR_STEP | DR_TRAP_BITS) || icebp) + send_sigtrap(regs, 0, get_si_code(dr6)); + +out_irq: + local_irq_disable(); +out: instrumentation_end(); irqentry_exit_to_user_mode(regs); } diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 49d925043171..f70dffc2771f 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -54,7 +54,7 @@ struct clocksource *art_related_clocksource; struct cyc2ns { struct cyc2ns_data data[2]; /* 0 + 2*16 = 32 */ - seqcount_t seq; /* 32 + 4 = 36 */ + seqcount_latch_t seq; /* 32 + 4 = 36 */ }; /* fits one cacheline */ @@ -73,14 +73,14 @@ __always_inline void cyc2ns_read_begin(struct cyc2ns_data *data) preempt_disable_notrace(); do { - seq = this_cpu_read(cyc2ns.seq.sequence); + seq = this_cpu_read(cyc2ns.seq.seqcount.sequence); idx = seq & 1; data->cyc2ns_offset = this_cpu_read(cyc2ns.data[idx].cyc2ns_offset); data->cyc2ns_mul = this_cpu_read(cyc2ns.data[idx].cyc2ns_mul); data->cyc2ns_shift = this_cpu_read(cyc2ns.data[idx].cyc2ns_shift); - } while (unlikely(seq != this_cpu_read(cyc2ns.seq.sequence))); + } while (unlikely(seq != this_cpu_read(cyc2ns.seq.seqcount.sequence))); } __always_inline void cyc2ns_read_end(void) @@ -186,7 +186,7 @@ static void __init cyc2ns_init_boot_cpu(void) { struct cyc2ns *c2n = this_cpu_ptr(&cyc2ns); - seqcount_init(&c2n->seq); + seqcount_latch_init(&c2n->seq); __set_cyc2ns_scale(tsc_khz, smp_processor_id(), rdtsc()); } @@ -203,7 +203,7 @@ static void __init cyc2ns_init_secondary_cpus(void) for_each_possible_cpu(cpu) { if (cpu != this_cpu) { - seqcount_init(&c2n->seq); + seqcount_latch_init(&c2n->seq); c2n = per_cpu_ptr(&cyc2ns, cpu); c2n->data[0] = data[0]; c2n->data[1] = data[1]; diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 9a03e5b23135..bf9e0adb5b7e 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -136,6 +136,7 @@ SECTIONS ENTRY_TEXT ALIGN_ENTRY_TEXT_END SOFTIRQENTRY_TEXT + STATIC_CALL_TEXT *(.fixup) *(.gnu.warning) @@ -411,10 +412,47 @@ SECTIONS STABS_DEBUG DWARF_DEBUG + ELF_DETAILS DISCARDS -} + /* + * Make sure that the .got.plt is either completely empty or it + * contains only the lazy dispatch entries. + */ + .got.plt (INFO) : { *(.got.plt) } + ASSERT(SIZEOF(.got.plt) == 0 || +#ifdef CONFIG_X86_64 + SIZEOF(.got.plt) == 0x18, +#else + SIZEOF(.got.plt) == 0xc, +#endif + "Unexpected GOT/PLT entries detected!") + + /* + * Sections that should stay zero sized, which is safer to + * explicitly check instead of blindly discarding. + */ + .got : { + *(.got) *(.igot.*) + } + ASSERT(SIZEOF(.got) == 0, "Unexpected GOT entries detected!") + + .plt : { + *(.plt) *(.plt.*) *(.iplt) + } + ASSERT(SIZEOF(.plt) == 0, "Unexpected run-time procedure linkages detected!") + + .rel.dyn : { + *(.rel.*) *(.rel_*) + } + ASSERT(SIZEOF(.rel.dyn) == 0, "Unexpected run-time relocations (.rel) detected!") + + .rela.dyn : { + *(.rela.*) *(.rela_*) + } + ASSERT(SIZEOF(.rela.dyn) == 0, "Unexpected run-time relocations (.rela) detected!") +} #ifdef CONFIG_X86_32 /* diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 123f1c1f1788..a3038d8deb6a 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -24,6 +24,7 @@ #include <asm/tsc.h> #include <asm/iommu.h> #include <asm/mach_traps.h> +#include <asm/irqdomain.h> void x86_init_noop(void) { } void __init x86_init_uint_noop(unsigned int unused) { } @@ -67,11 +68,7 @@ struct x86_init_ops x86_init __initdata = { }, .mpparse = { - .mpc_record = x86_init_uint_noop, .setup_ioapic_ids = x86_init_noop, - .mpc_apic_id = default_mpc_apic_id, - .smp_read_mpc_oem = default_smp_read_mpc_oem, - .mpc_oem_bus_info = default_mpc_oem_bus_info, .find_smp_config = default_find_smp_config, .get_smp_config = default_get_smp_config, }, @@ -80,7 +77,8 @@ struct x86_init_ops x86_init __initdata = { .pre_vector_init = init_ISA_irqs, .intr_init = native_init_IRQ, .intr_mode_select = apic_intr_mode_select, - .intr_mode_init = apic_intr_mode_init + .intr_mode_init = apic_intr_mode_init, + .create_pci_msi_domain = native_create_pci_msi_domain, }, .oem = { @@ -148,28 +146,10 @@ EXPORT_SYMBOL_GPL(x86_platform); #if defined(CONFIG_PCI_MSI) struct x86_msi_ops x86_msi __ro_after_init = { - .setup_msi_irqs = native_setup_msi_irqs, - .teardown_msi_irq = native_teardown_msi_irq, - .teardown_msi_irqs = default_teardown_msi_irqs, .restore_msi_irqs = default_restore_msi_irqs, }; /* MSI arch specific hooks */ -int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) -{ - return x86_msi.setup_msi_irqs(dev, nvec, type); -} - -void arch_teardown_msi_irqs(struct pci_dev *dev) -{ - x86_msi.teardown_msi_irqs(dev); -} - -void arch_teardown_msi_irq(unsigned int irq) -{ - x86_msi.teardown_msi_irq(irq); -} - void arch_restore_msi_irqs(struct pci_dev *dev) { x86_msi.restore_msi_irqs(dev); diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 1d330564eed8..8c1e8334eff0 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -2000,20 +2000,20 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, break; case HYPERV_CPUID_FEATURES: - ent->eax |= HV_X64_MSR_VP_RUNTIME_AVAILABLE; + ent->eax |= HV_MSR_VP_RUNTIME_AVAILABLE; ent->eax |= HV_MSR_TIME_REF_COUNT_AVAILABLE; - ent->eax |= HV_X64_MSR_SYNIC_AVAILABLE; + ent->eax |= HV_MSR_SYNIC_AVAILABLE; ent->eax |= HV_MSR_SYNTIMER_AVAILABLE; - ent->eax |= HV_X64_MSR_APIC_ACCESS_AVAILABLE; - ent->eax |= HV_X64_MSR_HYPERCALL_AVAILABLE; - ent->eax |= HV_X64_MSR_VP_INDEX_AVAILABLE; - ent->eax |= HV_X64_MSR_RESET_AVAILABLE; + ent->eax |= HV_MSR_APIC_ACCESS_AVAILABLE; + ent->eax |= HV_MSR_HYPERCALL_AVAILABLE; + ent->eax |= HV_MSR_VP_INDEX_AVAILABLE; + ent->eax |= HV_MSR_RESET_AVAILABLE; ent->eax |= HV_MSR_REFERENCE_TSC_AVAILABLE; - ent->eax |= HV_X64_ACCESS_FREQUENCY_MSRS; - ent->eax |= HV_X64_ACCESS_REENLIGHTENMENT; + ent->eax |= HV_ACCESS_FREQUENCY_MSRS; + ent->eax |= HV_ACCESS_REENLIGHTENMENT; - ent->ebx |= HV_X64_POST_MESSAGES; - ent->ebx |= HV_X64_SIGNAL_EVENTS; + ent->ebx |= HV_POST_MESSAGES; + ent->ebx |= HV_SIGNAL_EVENTS; ent->edx |= HV_FEATURE_FREQUENCY_MSRS_AVAILABLE; ent->edx |= HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE; diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S index d1d768912368..4304320e51f4 100644 --- a/arch/x86/lib/checksum_32.S +++ b/arch/x86/lib/checksum_32.S @@ -253,28 +253,17 @@ EXPORT_SYMBOL(csum_partial) /* unsigned int csum_partial_copy_generic (const char *src, char *dst, - int len, int sum, int *src_err_ptr, int *dst_err_ptr) + int len) */ /* * Copy from ds while checksumming, otherwise like csum_partial - * - * The macros SRC and DST specify the type of access for the instruction. - * thus we can call a custom exception handler for all access types. - * - * FIXME: could someone double-check whether I haven't mixed up some SRC and - * DST definitions? It's damn hard to trigger all cases. I hope I got - * them all but there's no guarantee. */ -#define SRC(y...) \ +#define EXC(y...) \ 9999: y; \ _ASM_EXTABLE_UA(9999b, 6001f) -#define DST(y...) \ - 9999: y; \ - _ASM_EXTABLE_UA(9999b, 6002f) - #ifndef CONFIG_X86_USE_PPRO_CHECKSUM #define ARGBASE 16 @@ -285,20 +274,20 @@ SYM_FUNC_START(csum_partial_copy_generic) pushl %edi pushl %esi pushl %ebx - movl ARGBASE+16(%esp),%eax # sum movl ARGBASE+12(%esp),%ecx # len movl ARGBASE+4(%esp),%esi # src movl ARGBASE+8(%esp),%edi # dst + movl $-1, %eax # sum testl $2, %edi # Check alignment. jz 2f # Jump if alignment is ok. subl $2, %ecx # Alignment uses up two bytes. jae 1f # Jump if we had at least two bytes. addl $2, %ecx # ecx was < 2. Deal with it. jmp 4f -SRC(1: movw (%esi), %bx ) +EXC(1: movw (%esi), %bx ) addl $2, %esi -DST( movw %bx, (%edi) ) +EXC( movw %bx, (%edi) ) addl $2, %edi addw %bx, %ax adcl $0, %eax @@ -306,34 +295,34 @@ DST( movw %bx, (%edi) ) movl %ecx, FP(%esp) shrl $5, %ecx jz 2f - testl %esi, %esi -SRC(1: movl (%esi), %ebx ) -SRC( movl 4(%esi), %edx ) + testl %esi, %esi # what's wrong with clc? +EXC(1: movl (%esi), %ebx ) +EXC( movl 4(%esi), %edx ) adcl %ebx, %eax -DST( movl %ebx, (%edi) ) +EXC( movl %ebx, (%edi) ) adcl %edx, %eax -DST( movl %edx, 4(%edi) ) +EXC( movl %edx, 4(%edi) ) -SRC( movl 8(%esi), %ebx ) -SRC( movl 12(%esi), %edx ) +EXC( movl 8(%esi), %ebx ) +EXC( movl 12(%esi), %edx ) adcl %ebx, %eax -DST( movl %ebx, 8(%edi) ) +EXC( movl %ebx, 8(%edi) ) adcl %edx, %eax -DST( movl %edx, 12(%edi) ) +EXC( movl %edx, 12(%edi) ) -SRC( movl 16(%esi), %ebx ) -SRC( movl 20(%esi), %edx ) +EXC( movl 16(%esi), %ebx ) +EXC( movl 20(%esi), %edx ) adcl %ebx, %eax -DST( movl %ebx, 16(%edi) ) +EXC( movl %ebx, 16(%edi) ) adcl %edx, %eax -DST( movl %edx, 20(%edi) ) +EXC( movl %edx, 20(%edi) ) -SRC( movl 24(%esi), %ebx ) -SRC( movl 28(%esi), %edx ) +EXC( movl 24(%esi), %ebx ) +EXC( movl 28(%esi), %edx ) adcl %ebx, %eax -DST( movl %ebx, 24(%edi) ) +EXC( movl %ebx, 24(%edi) ) adcl %edx, %eax -DST( movl %edx, 28(%edi) ) +EXC( movl %edx, 28(%edi) ) lea 32(%esi), %esi lea 32(%edi), %edi @@ -345,9 +334,9 @@ DST( movl %edx, 28(%edi) ) andl $0x1c, %edx je 4f shrl $2, %edx # This clears CF -SRC(3: movl (%esi), %ebx ) +EXC(3: movl (%esi), %ebx ) adcl %ebx, %eax -DST( movl %ebx, (%edi) ) +EXC( movl %ebx, (%edi) ) lea 4(%esi), %esi lea 4(%edi), %edi dec %edx @@ -357,39 +346,24 @@ DST( movl %ebx, (%edi) ) jz 7f cmpl $2, %ecx jb 5f -SRC( movw (%esi), %cx ) +EXC( movw (%esi), %cx ) leal 2(%esi), %esi -DST( movw %cx, (%edi) ) +EXC( movw %cx, (%edi) ) leal 2(%edi), %edi je 6f shll $16,%ecx -SRC(5: movb (%esi), %cl ) -DST( movb %cl, (%edi) ) +EXC(5: movb (%esi), %cl ) +EXC( movb %cl, (%edi) ) 6: addl %ecx, %eax adcl $0, %eax 7: -5000: # Exception handler: .section .fixup, "ax" 6001: - movl ARGBASE+20(%esp), %ebx # src_err_ptr - movl $-EFAULT, (%ebx) - - # zero the complete destination - computing the rest - # is too much work - movl ARGBASE+8(%esp), %edi # dst - movl ARGBASE+12(%esp), %ecx # len - xorl %eax,%eax - rep ; stosb - - jmp 5000b - -6002: - movl ARGBASE+24(%esp), %ebx # dst_err_ptr - movl $-EFAULT,(%ebx) - jmp 5000b + xorl %eax, %eax + jmp 7b .previous @@ -405,14 +379,14 @@ SYM_FUNC_END(csum_partial_copy_generic) /* Version for PentiumII/PPro */ #define ROUND1(x) \ - SRC(movl x(%esi), %ebx ) ; \ + EXC(movl x(%esi), %ebx ) ; \ addl %ebx, %eax ; \ - DST(movl %ebx, x(%edi) ) ; + EXC(movl %ebx, x(%edi) ) ; #define ROUND(x) \ - SRC(movl x(%esi), %ebx ) ; \ + EXC(movl x(%esi), %ebx ) ; \ adcl %ebx, %eax ; \ - DST(movl %ebx, x(%edi) ) ; + EXC(movl %ebx, x(%edi) ) ; #define ARGBASE 12 @@ -423,7 +397,7 @@ SYM_FUNC_START(csum_partial_copy_generic) movl ARGBASE+4(%esp),%esi #src movl ARGBASE+8(%esp),%edi #dst movl ARGBASE+12(%esp),%ecx #len - movl ARGBASE+16(%esp),%eax #sum + movl $-1, %eax #sum # movl %ecx, %edx movl %ecx, %ebx movl %esi, %edx @@ -439,7 +413,7 @@ SYM_FUNC_START(csum_partial_copy_generic) JMP_NOSPEC ebx 1: addl $64,%esi addl $64,%edi - SRC(movb -32(%edx),%bl) ; SRC(movb (%edx),%bl) + EXC(movb -32(%edx),%bl) ; EXC(movb (%edx),%bl) ROUND1(-64) ROUND(-60) ROUND(-56) ROUND(-52) ROUND (-48) ROUND(-44) ROUND(-40) ROUND(-36) ROUND (-32) ROUND(-28) ROUND(-24) ROUND(-20) @@ -453,29 +427,20 @@ SYM_FUNC_START(csum_partial_copy_generic) jz 7f cmpl $2, %edx jb 5f -SRC( movw (%esi), %dx ) +EXC( movw (%esi), %dx ) leal 2(%esi), %esi -DST( movw %dx, (%edi) ) +EXC( movw %dx, (%edi) ) leal 2(%edi), %edi je 6f shll $16,%edx 5: -SRC( movb (%esi), %dl ) -DST( movb %dl, (%edi) ) +EXC( movb (%esi), %dl ) +EXC( movb %dl, (%edi) ) 6: addl %edx, %eax adcl $0, %eax 7: .section .fixup, "ax" -6001: movl ARGBASE+20(%esp), %ebx # src_err_ptr - movl $-EFAULT, (%ebx) - # zero the complete destination (computing the rest is too much work) - movl ARGBASE+8(%esp),%edi # dst - movl ARGBASE+12(%esp),%ecx # len - xorl %eax,%eax - rep; stosb - jmp 7b -6002: movl ARGBASE+24(%esp), %ebx # dst_err_ptr - movl $-EFAULT, (%ebx) +6001: xorl %eax, %eax jmp 7b .previous diff --git a/arch/x86/lib/csum-copy_64.S b/arch/x86/lib/csum-copy_64.S index 3394a8ff7fd0..1fbd8ee9642d 100644 --- a/arch/x86/lib/csum-copy_64.S +++ b/arch/x86/lib/csum-copy_64.S @@ -18,9 +18,6 @@ * rdi source * rsi destination * edx len (32bit) - * ecx sum (32bit) - * r8 src_err_ptr (int) - * r9 dst_err_ptr (int) * * Output * eax 64bit sum. undefined in case of exception. @@ -31,44 +28,32 @@ .macro source 10: - _ASM_EXTABLE_UA(10b, .Lbad_source) + _ASM_EXTABLE_UA(10b, .Lfault) .endm .macro dest 20: - _ASM_EXTABLE_UA(20b, .Lbad_dest) + _ASM_EXTABLE_UA(20b, .Lfault) .endm - /* - * No _ASM_EXTABLE_UA; this is used for intentional prefetch on a - * potentially unmapped kernel address. - */ - .macro ignore L=.Lignore -30: - _ASM_EXTABLE(30b, \L) - .endm - - SYM_FUNC_START(csum_partial_copy_generic) - cmpl $3*64, %edx - jle .Lignore - -.Lignore: - subq $7*8, %rsp - movq %rbx, 2*8(%rsp) - movq %r12, 3*8(%rsp) - movq %r14, 4*8(%rsp) - movq %r13, 5*8(%rsp) - movq %r15, 6*8(%rsp) + subq $5*8, %rsp + movq %rbx, 0*8(%rsp) + movq %r12, 1*8(%rsp) + movq %r14, 2*8(%rsp) + movq %r13, 3*8(%rsp) + movq %r15, 4*8(%rsp) - movq %r8, (%rsp) - movq %r9, 1*8(%rsp) - - movl %ecx, %eax + movl $-1, %eax + xorl %r9d, %r9d movl %edx, %ecx + cmpl $8, %ecx + jb .Lshort - xorl %r9d, %r9d - movq %rcx, %r12 + testb $7, %sil + jne .Lunaligned +.Laligned: + movl %ecx, %r12d shrq $6, %r12 jz .Lhandle_tail /* < 64 */ @@ -99,7 +84,12 @@ SYM_FUNC_START(csum_partial_copy_generic) source movq 56(%rdi), %r13 - ignore 2f +30: + /* + * No _ASM_EXTABLE_UA; this is used for intentional prefetch on a + * potentially unmapped kernel address. + */ + _ASM_EXTABLE(30b, 2f) prefetcht0 5*64(%rdi) 2: adcq %rbx, %rax @@ -131,8 +121,6 @@ SYM_FUNC_START(csum_partial_copy_generic) dest movq %r13, 56(%rsi) -3: - leaq 64(%rdi), %rdi leaq 64(%rsi), %rsi @@ -142,8 +130,8 @@ SYM_FUNC_START(csum_partial_copy_generic) /* do last up to 56 bytes */ .Lhandle_tail: - /* ecx: count */ - movl %ecx, %r10d + /* ecx: count, rcx.63: the end result needs to be rol8 */ + movq %rcx, %r10 andl $63, %ecx shrl $3, %ecx jz .Lfold @@ -172,6 +160,7 @@ SYM_FUNC_START(csum_partial_copy_generic) .Lhandle_7: movl %r10d, %ecx andl $7, %ecx +.L1: /* .Lshort rejoins the common path here */ shrl $1, %ecx jz .Lhandle_1 movl $2, %edx @@ -203,26 +192,65 @@ SYM_FUNC_START(csum_partial_copy_generic) adcl %r9d, %eax /* carry */ .Lende: - movq 2*8(%rsp), %rbx - movq 3*8(%rsp), %r12 - movq 4*8(%rsp), %r14 - movq 5*8(%rsp), %r13 - movq 6*8(%rsp), %r15 - addq $7*8, %rsp + testq %r10, %r10 + js .Lwas_odd +.Lout: + movq 0*8(%rsp), %rbx + movq 1*8(%rsp), %r12 + movq 2*8(%rsp), %r14 + movq 3*8(%rsp), %r13 + movq 4*8(%rsp), %r15 + addq $5*8, %rsp ret +.Lshort: + movl %ecx, %r10d + jmp .L1 +.Lunaligned: + xorl %ebx, %ebx + testb $1, %sil + jne .Lodd +1: testb $2, %sil + je 2f + source + movw (%rdi), %bx + dest + movw %bx, (%rsi) + leaq 2(%rdi), %rdi + subq $2, %rcx + leaq 2(%rsi), %rsi + addq %rbx, %rax +2: testb $4, %sil + je .Laligned + source + movl (%rdi), %ebx + dest + movl %ebx, (%rsi) + leaq 4(%rdi), %rdi + subq $4, %rcx + leaq 4(%rsi), %rsi + addq %rbx, %rax + jmp .Laligned + +.Lodd: + source + movb (%rdi), %bl + dest + movb %bl, (%rsi) + leaq 1(%rdi), %rdi + leaq 1(%rsi), %rsi + /* decrement, set MSB */ + leaq -1(%rcx, %rcx), %rcx + rorq $1, %rcx + shll $8, %ebx + addq %rbx, %rax + jmp 1b + +.Lwas_odd: + roll $8, %eax + jmp .Lout - /* Exception handlers. Very simple, zeroing is done in the wrappers */ -.Lbad_source: - movq (%rsp), %rax - testq %rax, %rax - jz .Lende - movl $-EFAULT, (%rax) - jmp .Lende - -.Lbad_dest: - movq 8(%rsp), %rax - testq %rax, %rax - jz .Lende - movl $-EFAULT, (%rax) - jmp .Lende + /* Exception: just return 0 */ +.Lfault: + xorl %eax, %eax + jmp .Lout SYM_FUNC_END(csum_partial_copy_generic) diff --git a/arch/x86/lib/csum-wrappers_64.c b/arch/x86/lib/csum-wrappers_64.c index ee63d7576fd2..189344924a2b 100644 --- a/arch/x86/lib/csum-wrappers_64.c +++ b/arch/x86/lib/csum-wrappers_64.c @@ -21,52 +21,16 @@ * src and dst are best aligned to 64bits. */ __wsum -csum_and_copy_from_user(const void __user *src, void *dst, - int len, __wsum isum, int *errp) +csum_and_copy_from_user(const void __user *src, void *dst, int len) { - might_sleep(); - *errp = 0; + __wsum sum; + might_sleep(); if (!user_access_begin(src, len)) - goto out_err; - - /* - * Why 6, not 7? To handle odd addresses aligned we - * would need to do considerable complications to fix the - * checksum which is defined as an 16bit accumulator. The - * fix alignment code is primarily for performance - * compatibility with 32bit and that will handle odd - * addresses slowly too. - */ - if (unlikely((unsigned long)src & 6)) { - while (((unsigned long)src & 6) && len >= 2) { - __u16 val16; - - unsafe_get_user(val16, (const __u16 __user *)src, out); - - *(__u16 *)dst = val16; - isum = (__force __wsum)add32_with_carry( - (__force unsigned)isum, val16); - src += 2; - dst += 2; - len -= 2; - } - } - isum = csum_partial_copy_generic((__force const void *)src, - dst, len, isum, errp, NULL); - user_access_end(); - if (unlikely(*errp)) - goto out_err; - - return isum; - -out: + return 0; + sum = csum_partial_copy_generic((__force const void *)src, dst, len); user_access_end(); -out_err: - *errp = -EFAULT; - memset(dst, 0, len); - - return isum; + return sum; } EXPORT_SYMBOL(csum_and_copy_from_user); @@ -82,40 +46,16 @@ EXPORT_SYMBOL(csum_and_copy_from_user); * src and dst are best aligned to 64bits. */ __wsum -csum_and_copy_to_user(const void *src, void __user *dst, - int len, __wsum isum, int *errp) +csum_and_copy_to_user(const void *src, void __user *dst, int len) { - __wsum ret; + __wsum sum; might_sleep(); - - if (!user_access_begin(dst, len)) { - *errp = -EFAULT; + if (!user_access_begin(dst, len)) return 0; - } - - if (unlikely((unsigned long)dst & 6)) { - while (((unsigned long)dst & 6) && len >= 2) { - __u16 val16 = *(__u16 *)src; - - isum = (__force __wsum)add32_with_carry( - (__force unsigned)isum, val16); - unsafe_put_user(val16, (__u16 __user *)dst, out); - src += 2; - dst += 2; - len -= 2; - } - } - - *errp = 0; - ret = csum_partial_copy_generic(src, (void __force *)dst, - len, isum, NULL, errp); - user_access_end(); - return ret; -out: + sum = csum_partial_copy_generic(src, (void __force *)dst, len); user_access_end(); - *errp = -EFAULT; - return isum; + return sum; } EXPORT_SYMBOL(csum_and_copy_to_user); @@ -129,9 +69,9 @@ EXPORT_SYMBOL(csum_and_copy_to_user); * Returns an 32bit unfolded checksum of the buffer. */ __wsum -csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum) +csum_partial_copy_nocheck(const void *src, void *dst, int len) { - return csum_partial_copy_generic(src, dst, len, sum, NULL, NULL); + return csum_partial_copy_generic(src, dst, len); } EXPORT_SYMBOL(csum_partial_copy_nocheck); diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S index c8a85b512796..2cd902e06062 100644 --- a/arch/x86/lib/getuser.S +++ b/arch/x86/lib/getuser.S @@ -35,6 +35,8 @@ #include <asm/smap.h> #include <asm/export.h> +#define ASM_BARRIER_NOSPEC ALTERNATIVE "", "lfence", X86_FEATURE_LFENCE_RDTSC + .text SYM_FUNC_START(__get_user_1) mov PER_CPU_VAR(current_task), %_ASM_DX @@ -114,6 +116,52 @@ SYM_FUNC_START(__get_user_8) SYM_FUNC_END(__get_user_8) EXPORT_SYMBOL(__get_user_8) +/* .. and the same for __get_user, just without the range checks */ +SYM_FUNC_START(__get_user_nocheck_1) + ASM_STAC + ASM_BARRIER_NOSPEC +6: movzbl (%_ASM_AX),%edx + xor %eax,%eax + ASM_CLAC + ret +SYM_FUNC_END(__get_user_nocheck_1) +EXPORT_SYMBOL(__get_user_nocheck_1) + +SYM_FUNC_START(__get_user_nocheck_2) + ASM_STAC + ASM_BARRIER_NOSPEC +7: movzwl (%_ASM_AX),%edx + xor %eax,%eax + ASM_CLAC + ret +SYM_FUNC_END(__get_user_nocheck_2) +EXPORT_SYMBOL(__get_user_nocheck_2) + +SYM_FUNC_START(__get_user_nocheck_4) + ASM_STAC + ASM_BARRIER_NOSPEC +8: movl (%_ASM_AX),%edx + xor %eax,%eax + ASM_CLAC + ret +SYM_FUNC_END(__get_user_nocheck_4) +EXPORT_SYMBOL(__get_user_nocheck_4) + +SYM_FUNC_START(__get_user_nocheck_8) + ASM_STAC + ASM_BARRIER_NOSPEC +#ifdef CONFIG_X86_64 +9: movq (%_ASM_AX),%rdx +#else +9: movl (%_ASM_AX),%edx +10: movl 4(%_ASM_AX),%ecx +#endif + xor %eax,%eax + ASM_CLAC + ret +SYM_FUNC_END(__get_user_nocheck_8) +EXPORT_SYMBOL(__get_user_nocheck_8) + SYM_CODE_START_LOCAL(.Lbad_get_user_clac) ASM_CLAC @@ -134,6 +182,7 @@ bad_get_user_8: SYM_CODE_END(.Lbad_get_user_8_clac) #endif +/* get_user */ _ASM_EXTABLE_UA(1b, .Lbad_get_user_clac) _ASM_EXTABLE_UA(2b, .Lbad_get_user_clac) _ASM_EXTABLE_UA(3b, .Lbad_get_user_clac) @@ -143,3 +192,14 @@ SYM_CODE_END(.Lbad_get_user_8_clac) _ASM_EXTABLE_UA(4b, .Lbad_get_user_8_clac) _ASM_EXTABLE_UA(5b, .Lbad_get_user_8_clac) #endif + +/* __get_user */ + _ASM_EXTABLE_UA(6b, .Lbad_get_user_clac) + _ASM_EXTABLE_UA(7b, .Lbad_get_user_clac) + _ASM_EXTABLE_UA(8b, .Lbad_get_user_clac) +#ifdef CONFIG_X86_64 + _ASM_EXTABLE_UA(9b, .Lbad_get_user_clac) +#else + _ASM_EXTABLE_UA(9b, .Lbad_get_user_8_clac) + _ASM_EXTABLE_UA(10b, .Lbad_get_user_8_clac) +#endif diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S index 7c7c92db8497..b34a17763f28 100644 --- a/arch/x86/lib/putuser.S +++ b/arch/x86/lib/putuser.S @@ -25,7 +25,9 @@ * Inputs: %eax[:%edx] contains the data * %ecx contains the address * - * Outputs: %eax is error code (0 or -EFAULT) + * Outputs: %ecx is error code (0 or -EFAULT) + * + * Clobbers: %ebx needed for task pointer * * These functions should not modify any other registers, * as they get called from within inline assembly. @@ -38,13 +40,15 @@ SYM_FUNC_START(__put_user_1) ENTER cmp TASK_addr_limit(%_ASM_BX),%_ASM_CX jae .Lbad_put_user +SYM_INNER_LABEL(__put_user_nocheck_1, SYM_L_GLOBAL) ASM_STAC 1: movb %al,(%_ASM_CX) - xor %eax,%eax + xor %ecx,%ecx ASM_CLAC ret SYM_FUNC_END(__put_user_1) EXPORT_SYMBOL(__put_user_1) +EXPORT_SYMBOL(__put_user_nocheck_1) SYM_FUNC_START(__put_user_2) ENTER @@ -52,13 +56,15 @@ SYM_FUNC_START(__put_user_2) sub $1,%_ASM_BX cmp %_ASM_BX,%_ASM_CX jae .Lbad_put_user +SYM_INNER_LABEL(__put_user_nocheck_2, SYM_L_GLOBAL) ASM_STAC 2: movw %ax,(%_ASM_CX) - xor %eax,%eax + xor %ecx,%ecx ASM_CLAC ret SYM_FUNC_END(__put_user_2) EXPORT_SYMBOL(__put_user_2) +EXPORT_SYMBOL(__put_user_nocheck_2) SYM_FUNC_START(__put_user_4) ENTER @@ -66,13 +72,15 @@ SYM_FUNC_START(__put_user_4) sub $3,%_ASM_BX cmp %_ASM_BX,%_ASM_CX jae .Lbad_put_user +SYM_INNER_LABEL(__put_user_nocheck_4, SYM_L_GLOBAL) ASM_STAC 3: movl %eax,(%_ASM_CX) - xor %eax,%eax + xor %ecx,%ecx ASM_CLAC ret SYM_FUNC_END(__put_user_4) EXPORT_SYMBOL(__put_user_4) +EXPORT_SYMBOL(__put_user_nocheck_4) SYM_FUNC_START(__put_user_8) ENTER @@ -80,21 +88,23 @@ SYM_FUNC_START(__put_user_8) sub $7,%_ASM_BX cmp %_ASM_BX,%_ASM_CX jae .Lbad_put_user +SYM_INNER_LABEL(__put_user_nocheck_8, SYM_L_GLOBAL) ASM_STAC 4: mov %_ASM_AX,(%_ASM_CX) #ifdef CONFIG_X86_32 5: movl %edx,4(%_ASM_CX) #endif - xor %eax,%eax + xor %ecx,%ecx ASM_CLAC RET SYM_FUNC_END(__put_user_8) EXPORT_SYMBOL(__put_user_8) +EXPORT_SYMBOL(__put_user_nocheck_8) SYM_CODE_START_LOCAL(.Lbad_put_user_clac) ASM_CLAC .Lbad_put_user: - movl $-EFAULT,%eax + movl $-EFAULT,%ecx RET SYM_CODE_END(.Lbad_put_user_clac) diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index a4ac13cc3fdc..b5a3fa4033d3 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -217,11 +217,6 @@ static void sync_global_pgds(unsigned long start, unsigned long end) sync_global_pgds_l4(start, end); } -void arch_sync_kernel_mappings(unsigned long start, unsigned long end) -{ - sync_global_pgds(start, end); -} - /* * NOTE: This function is marked __ref because it calls __init function * (alloc_bootmem_pages). It's safe to do it ONLY when after_bootmem == 0. @@ -1257,14 +1252,19 @@ static void __init preallocate_vmalloc_pages(void) if (!p4d) goto failed; - /* - * With 5-level paging the P4D level is not folded. So the PGDs - * are now populated and there is no need to walk down to the - * PUD level. - */ if (pgtable_l5_enabled()) continue; + /* + * The goal here is to allocate all possibly required + * hardware page tables pointed to by the top hardware + * level. + * + * On 4-level systems, the P4D layer is folded away and + * the above code does no preallocation. Below, go down + * to the pud _software_ level to ensure the second + * hardware level is allocated on 4-level systems too. + */ lvl = "pud"; pud = pud_alloc(&init_mm, p4d, addr); if (!pud) diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index df1d95913d4e..3507f456fcd0 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -19,6 +19,7 @@ #include <asm/smp.h> #include <asm/pci_x86.h> #include <asm/setup.h> +#include <asm/irqdomain.h> unsigned int pci_probe = PCI_PROBE_BIOS | PCI_PROBE_CONF1 | PCI_PROBE_CONF2 | PCI_PROBE_MMCONF; @@ -633,8 +634,9 @@ static void set_dev_domain_options(struct pci_dev *pdev) int pcibios_add_device(struct pci_dev *dev) { - struct setup_data *data; struct pci_setup_rom *rom; + struct irq_domain *msidom; + struct setup_data *data; u64 pa_data; pa_data = boot_params.hdr.setup_data; @@ -661,6 +663,20 @@ int pcibios_add_device(struct pci_dev *dev) memunmap(data); } set_dev_domain_options(dev); + + /* + * Setup the initial MSI domain of the device. If the underlying + * bus has a PCI/MSI irqdomain associated use the bus domain, + * otherwise set the default domain. This ensures that special irq + * domains e.g. VMD are preserved. The default ensures initial + * operation if irq remapping is not active. If irq remapping is + * active it will overwrite the domain pointer when the device is + * associated to a remapping domain. + */ + msidom = dev_get_msi_domain(&dev->bus->dev); + if (!msidom) + msidom = x86_pci_msi_default_domain; + dev_set_msi_domain(&dev->dev, msidom); return 0; } diff --git a/arch/x86/pci/init.c b/arch/x86/pci/init.c index 5fc617edf108..00bfa1ebad6c 100644 --- a/arch/x86/pci/init.c +++ b/arch/x86/pci/init.c @@ -3,16 +3,17 @@ #include <linux/init.h> #include <asm/pci_x86.h> #include <asm/x86_init.h> +#include <asm/irqdomain.h> /* arch_initcall has too random ordering, so call the initializers in the right sequence from here. */ static __init int pci_arch_init(void) { -#ifdef CONFIG_PCI_DIRECT - int type = 0; + int type; + + x86_create_pci_msi_domain(); type = pci_direct_probe(); -#endif if (!(pci_probe & PCI_PROBE_NOEARLY)) pci_mmcfg_early_init(); @@ -20,18 +21,16 @@ static __init int pci_arch_init(void) if (x86_init.pci.arch_init && !x86_init.pci.arch_init()) return 0; -#ifdef CONFIG_PCI_BIOS pci_pcbios_init(); -#endif + /* * don't check for raw_pci_ops here because we want pcbios as last * fallback, yet it's needed to run first to set pcibios_last_bus * in case legacy PCI probing is used. otherwise detecting peer busses * fails. */ -#ifdef CONFIG_PCI_DIRECT pci_direct_init(type); -#endif + if (!raw_pci_ops && !raw_pci_ext_ops) printk(KERN_ERR "PCI: Fatal: No config space access function found\n"); diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 89395a5049bb..c552cd2d0632 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -157,6 +157,13 @@ static int acpi_register_gsi_xen(struct device *dev, u32 gsi, struct xen_pci_frontend_ops *xen_pci_frontend; EXPORT_SYMBOL_GPL(xen_pci_frontend); +struct xen_msi_ops { + int (*setup_msi_irqs)(struct pci_dev *dev, int nvec, int type); + void (*teardown_msi_irqs)(struct pci_dev *dev); +}; + +static struct xen_msi_ops xen_msi_ops __ro_after_init; + static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) { int irq, ret, i; @@ -372,28 +379,122 @@ static void xen_initdom_restore_msi_irqs(struct pci_dev *dev) WARN(ret && ret != -ENOSYS, "restore_msi -> %d\n", ret); } } -#endif +#else /* CONFIG_XEN_DOM0 */ +#define xen_initdom_setup_msi_irqs NULL +#define xen_initdom_restore_msi_irqs NULL +#endif /* !CONFIG_XEN_DOM0 */ static void xen_teardown_msi_irqs(struct pci_dev *dev) { struct msi_desc *msidesc; + int i; + + for_each_pci_msi_entry(msidesc, dev) { + if (msidesc->irq) { + for (i = 0; i < msidesc->nvec_used; i++) + xen_destroy_irq(msidesc->irq + i); + } + } +} + +static void xen_pv_teardown_msi_irqs(struct pci_dev *dev) +{ + struct msi_desc *msidesc = first_pci_msi_entry(dev); - msidesc = first_pci_msi_entry(dev); if (msidesc->msi_attrib.is_msix) xen_pci_frontend_disable_msix(dev); else xen_pci_frontend_disable_msi(dev); - /* Free the IRQ's and the msidesc using the generic code. */ - default_teardown_msi_irqs(dev); + xen_teardown_msi_irqs(dev); } -static void xen_teardown_msi_irq(unsigned int irq) +static int xen_msi_domain_alloc_irqs(struct irq_domain *domain, + struct device *dev, int nvec) { - xen_destroy_irq(irq); + int type; + + if (WARN_ON_ONCE(!dev_is_pci(dev))) + return -EINVAL; + + if (first_msi_entry(dev)->msi_attrib.is_msix) + type = PCI_CAP_ID_MSIX; + else + type = PCI_CAP_ID_MSI; + + return xen_msi_ops.setup_msi_irqs(to_pci_dev(dev), nvec, type); } -#endif +static void xen_msi_domain_free_irqs(struct irq_domain *domain, + struct device *dev) +{ + if (WARN_ON_ONCE(!dev_is_pci(dev))) + return; + + xen_msi_ops.teardown_msi_irqs(to_pci_dev(dev)); +} + +static struct msi_domain_ops xen_pci_msi_domain_ops = { + .domain_alloc_irqs = xen_msi_domain_alloc_irqs, + .domain_free_irqs = xen_msi_domain_free_irqs, +}; + +static struct msi_domain_info xen_pci_msi_domain_info = { + .ops = &xen_pci_msi_domain_ops, +}; + +/* + * This irq domain is a blatant violation of the irq domain design, but + * distangling XEN into real irq domains is not a job for mere mortals with + * limited XENology. But it's the least dangerous way for a mere mortal to + * get rid of the arch_*_msi_irqs() hackery in order to store the irq + * domain pointer in struct device. This irq domain wrappery allows to do + * that without breaking XEN terminally. + */ +static __init struct irq_domain *xen_create_pci_msi_domain(void) +{ + struct irq_domain *d = NULL; + struct fwnode_handle *fn; + + fn = irq_domain_alloc_named_fwnode("XEN-MSI"); + if (fn) + d = msi_create_irq_domain(fn, &xen_pci_msi_domain_info, NULL); + + /* FIXME: No idea how to survive if this fails */ + BUG_ON(!d); + + return d; +} + +static __init void xen_setup_pci_msi(void) +{ + if (xen_pv_domain()) { + if (xen_initial_domain()) { + xen_msi_ops.setup_msi_irqs = xen_initdom_setup_msi_irqs; + x86_msi.restore_msi_irqs = xen_initdom_restore_msi_irqs; + } else { + xen_msi_ops.setup_msi_irqs = xen_setup_msi_irqs; + } + xen_msi_ops.teardown_msi_irqs = xen_pv_teardown_msi_irqs; + pci_msi_ignore_mask = 1; + } else if (xen_hvm_domain()) { + xen_msi_ops.setup_msi_irqs = xen_hvm_setup_msi_irqs; + xen_msi_ops.teardown_msi_irqs = xen_teardown_msi_irqs; + } else { + WARN_ON_ONCE(1); + return; + } + + /* + * Override the PCI/MSI irq domain init function. No point + * in allocating the native domain and never use it. + */ + x86_init.irqs.create_pci_msi_domain = xen_create_pci_msi_domain; +} + +#else /* CONFIG_PCI_MSI */ +static inline void xen_setup_pci_msi(void) { } +#endif /* CONFIG_PCI_MSI */ int __init pci_xen_init(void) { @@ -410,17 +511,12 @@ int __init pci_xen_init(void) /* Keep ACPI out of the picture */ acpi_noirq_set(); -#ifdef CONFIG_PCI_MSI - x86_msi.setup_msi_irqs = xen_setup_msi_irqs; - x86_msi.teardown_msi_irq = xen_teardown_msi_irq; - x86_msi.teardown_msi_irqs = xen_teardown_msi_irqs; - pci_msi_ignore_mask = 1; -#endif + xen_setup_pci_msi(); return 0; } #ifdef CONFIG_PCI_MSI -void __init xen_msi_init(void) +static void __init xen_hvm_msi_init(void) { if (!disable_apic) { /* @@ -435,9 +531,7 @@ void __init xen_msi_init(void) ((eax & XEN_HVM_CPUID_APIC_ACCESS_VIRT) && boot_cpu_has(X86_FEATURE_APIC))) return; } - - x86_msi.setup_msi_irqs = xen_hvm_setup_msi_irqs; - x86_msi.teardown_msi_irq = xen_teardown_msi_irq; + xen_setup_pci_msi(); } #endif @@ -460,7 +554,7 @@ int __init pci_xen_hvm_init(void) * We need to wait until after x2apic is initialized * before we can set MSI IRQ ops. */ - x86_platform.apic_post_init = xen_msi_init; + x86_platform.apic_post_init = xen_hvm_msi_init; #endif return 0; } @@ -470,12 +564,7 @@ int __init pci_xen_initial_domain(void) { int irq; -#ifdef CONFIG_PCI_MSI - x86_msi.setup_msi_irqs = xen_initdom_setup_msi_irqs; - x86_msi.teardown_msi_irq = xen_teardown_msi_irq; - x86_msi.restore_msi_irqs = xen_initdom_restore_msi_irqs; - pci_msi_ignore_mask = 1; -#endif + xen_setup_pci_msi(); __acpi_register_gsi = acpi_register_gsi_xen; __acpi_unregister_gsi = NULL; /* diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index d37ebe6e70d7..8a26e705cb06 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -90,6 +90,9 @@ static const unsigned long * const efi_tables[] = { &efi.tpm_log, &efi.tpm_final_log, &efi_rng_seed, +#ifdef CONFIG_LOAD_UEFI_KEYS + &efi.mokvar_table, +#endif }; u64 efi_setup; /* efi setup_data physical address */ diff --git a/arch/x86/platform/uv/uv_irq.c b/arch/x86/platform/uv/uv_irq.c index abb6075397f0..18ca2261cc9a 100644 --- a/arch/x86/platform/uv/uv_irq.c +++ b/arch/x86/platform/uv/uv_irq.c @@ -90,15 +90,15 @@ static int uv_domain_alloc(struct irq_domain *domain, unsigned int virq, ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg); if (ret >= 0) { - if (info->uv_limit == UV_AFFINITY_CPU) + if (info->uv.limit == UV_AFFINITY_CPU) irq_set_status_flags(virq, IRQ_NO_BALANCING); else irq_set_status_flags(virq, IRQ_MOVE_PCNTXT); - chip_data->pnode = uv_blade_to_pnode(info->uv_blade); - chip_data->offset = info->uv_offset; + chip_data->pnode = uv_blade_to_pnode(info->uv.blade); + chip_data->offset = info->uv.offset; irq_domain_set_info(domain, virq, virq, &uv_irq_chip, chip_data, - handle_percpu_irq, NULL, info->uv_name); + handle_percpu_irq, NULL, info->uv.name); } else { kfree(chip_data); } @@ -193,10 +193,10 @@ int uv_setup_irq(char *irq_name, int cpu, int mmr_blade, init_irq_alloc_info(&info, cpumask_of(cpu)); info.type = X86_IRQ_ALLOC_TYPE_UV; - info.uv_limit = limit; - info.uv_blade = mmr_blade; - info.uv_offset = mmr_offset; - info.uv_name = irq_name; + info.uv.limit = limit; + info.uv.blade = mmr_blade; + info.uv.offset = mmr_offset; + info.uv.name = irq_name; return irq_domain_alloc_irqs(domain, 1, uv_blade_to_memory_nid(mmr_blade), &info); diff --git a/arch/x86/um/asm/checksum.h b/arch/x86/um/asm/checksum.h index ff6bba2c8ab6..b07824500363 100644 --- a/arch/x86/um/asm/checksum.h +++ b/arch/x86/um/asm/checksum.h @@ -20,22 +20,6 @@ */ extern __wsum csum_partial(const void *buff, int len, __wsum sum); -/* - * Note: when you get a NULL pointer exception here this means someone - * passed in an incorrect kernel address to one of these functions. - * - * If you use these functions directly please don't forget the - * access_ok(). - */ - -static __inline__ -__wsum csum_partial_copy_nocheck(const void *src, void *dst, - int len, __wsum sum) -{ - memcpy(dst, src, len); - return csum_partial(dst, len, sum); -} - /** * csum_fold - Fold and invert a 32bit checksum. * sum: 32bit unfolded sum diff --git a/arch/x86/um/asm/checksum_32.h b/arch/x86/um/asm/checksum_32.h index b9ac7c9eb72c..0b13c2947ad1 100644 --- a/arch/x86/um/asm/checksum_32.h +++ b/arch/x86/um/asm/checksum_32.h @@ -35,27 +35,4 @@ static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr, return csum_fold(sum); } -/* - * Copy and checksum to user - */ -#define HAVE_CSUM_COPY_USER -static __inline__ __wsum csum_and_copy_to_user(const void *src, - void __user *dst, - int len, __wsum sum, int *err_ptr) -{ - if (access_ok(dst, len)) { - if (copy_to_user(dst, src, len)) { - *err_ptr = -EFAULT; - return (__force __wsum)-1; - } - - return csum_partial(src, len, sum); - } - - if (len) - *err_ptr = -EFAULT; - - return (__force __wsum)-1; /* invalid checksum */ -} - #endif diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 22e741e0b10c..41485a8a6dcf 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -1014,8 +1014,6 @@ void __init xen_setup_vcpu_info_placement(void) } static const struct pv_info xen_info __initconst = { - .shared_kernel_pmd = 0, - .extra_user_64bit_cs = FLAT_USER_CS64, .name = "Xen", }; @@ -1314,10 +1312,6 @@ asmlinkage __visible void __init xen_start_kernel(void) xen_start_info->nr_pages); xen_reserve_special_pages(); - /* keep using Xen gdt for now; no urgent need to change it */ - - pv_info.kernel_rpl = 0; - /* * We used to do this in xen_arch_setup, but that is too late * on AMD were early_cpu_init (run before ->arch_setup()) calls diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 3273c985d3dd..eda78144c000 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -285,13 +285,6 @@ static void xen_set_pte(pte_t *ptep, pte_t pteval) __xen_set_pte(ptep, pteval); } -static void xen_set_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pteval) -{ - trace_xen_mmu_set_pte_at(mm, addr, ptep, pteval); - __xen_set_pte(ptep, pteval); -} - pte_t xen_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { @@ -2105,7 +2098,6 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = { .release_pmd = xen_release_pmd_init, .set_pte = xen_set_pte_init, - .set_pte_at = xen_set_pte_at, .set_pmd = xen_set_pmd_hyper, .ptep_modify_prot_start = __ptep_modify_prot_start, |