diff options
Diffstat (limited to 'arch/x86')
258 files changed, 8897 insertions, 7016 deletions
diff --git a/arch/x86/Kbuild b/arch/x86/Kbuild index 586b786b3edf..f65a804b86f0 100644 --- a/arch/x86/Kbuild +++ b/arch/x86/Kbuild @@ -10,9 +10,6 @@ obj-$(CONFIG_XEN) += xen/ # Hyper-V paravirtualization support obj-$(CONFIG_HYPERVISOR_GUEST) += hyperv/ -# lguest paravirtualization support -obj-$(CONFIG_LGUEST_GUEST) += lguest/ - obj-y += realmode/ obj-y += kernel/ obj-y += mm/ diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 781521b7cf9e..acb366bf6bc1 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -55,6 +55,8 @@ config X86 select ARCH_HAS_KCOV if X86_64 select ARCH_HAS_MMIO_FLUSH select ARCH_HAS_PMEM_API if X86_64 + # Causing hangs/crashes, see the commit that added this change for details. + select ARCH_HAS_REFCOUNT if BROKEN select ARCH_HAS_UACCESS_FLUSHCACHE if X86_64 select ARCH_HAS_SET_MEMORY select ARCH_HAS_SG_CHAIN @@ -73,7 +75,6 @@ config X86 select ARCH_USE_QUEUED_RWLOCKS select ARCH_USE_QUEUED_SPINLOCKS select ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH - select ARCH_WANT_FRAME_POINTERS select ARCH_WANTS_DYNAMIC_TASK_STRUCT select ARCH_WANTS_THP_SWAP if X86_64 select BUILDTIME_EXTABLE_SORT @@ -100,6 +101,7 @@ config X86 select GENERIC_STRNCPY_FROM_USER select GENERIC_STRNLEN_USER select GENERIC_TIME_VSYSCALL + select HARDLOCKUP_CHECK_TIMESTAMP if X86_64 select HAVE_ACPI_APEI if ACPI select HAVE_ACPI_APEI_NMI if ACPI select HAVE_ALIGNED_STRUCT_PAGE if SLUB @@ -157,17 +159,19 @@ config X86 select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP select HAVE_MIXED_BREAKPOINTS_REGS + select HAVE_MOD_ARCH_SPECIFIC select HAVE_NMI select HAVE_OPROFILE select HAVE_OPTPROBES select HAVE_PCSPKR_PLATFORM select HAVE_PERF_EVENTS select HAVE_PERF_EVENTS_NMI - select HAVE_HARDLOCKUP_DETECTOR_PERF if HAVE_PERF_EVENTS_NMI + select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && HAVE_PERF_EVENTS_NMI select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP + select HAVE_RCU_TABLE_FREE select HAVE_REGS_AND_STACK_ACCESS_API - select HAVE_RELIABLE_STACKTRACE if X86_64 && FRAME_POINTER && STACK_VALIDATION + select HAVE_RELIABLE_STACKTRACE if X86_64 && FRAME_POINTER_UNWINDER && STACK_VALIDATION select HAVE_STACK_VALIDATION if X86_64 select HAVE_SYSCALL_TRACEPOINTS select HAVE_UNSTABLE_SCHED_CLOCK @@ -326,6 +330,7 @@ config FIX_EARLYCON_MEM config PGTABLE_LEVELS int + default 5 if X86_5LEVEL default 4 if X86_64 default 3 if X86_PAE default 2 @@ -424,16 +429,16 @@ config GOLDFISH def_bool y depends on X86_GOLDFISH -config INTEL_RDT_A - bool "Intel Resource Director Technology Allocation support" +config INTEL_RDT + bool "Intel Resource Director Technology support" default n depends on X86 && CPU_SUP_INTEL select KERNFS help - Select to enable resource allocation which is a sub-feature of - Intel Resource Director Technology(RDT). More information about - RDT can be found in the Intel x86 Architecture Software - Developer Manual. + Select to enable resource allocation and monitoring which are + sub-features of Intel Resource Director Technology(RDT). More + information about RDT can be found in the Intel x86 + Architecture Software Developer Manual. Say N if unsure. @@ -777,8 +782,6 @@ config KVM_DEBUG_FS Statistics are displayed in debugfs filesystem. Enabling this option may incur significant overhead. -source "arch/x86/lguest/Kconfig" - config PARAVIRT_TIME_ACCOUNTING bool "Paravirtual steal time accounting" depends on PARAVIRT @@ -1398,6 +1401,24 @@ config X86_PAE has the cost of more pagetable lookup overhead, and also consumes more pagetable space per process. +config X86_5LEVEL + bool "Enable 5-level page tables support" + depends on X86_64 + ---help--- + 5-level paging enables access to larger address space: + upto 128 PiB of virtual address space and 4 PiB of + physical address space. + + It will be supported by future Intel CPUs. + + Note: a kernel with this option enabled can only be booted + on machines that support the feature. + + See Documentation/x86/x86_64/5level-paging.txt for more + information. + + Say N if unsure. + config ARCH_PHYS_ADDR_T_64BIT def_bool y depends on X86_64 || X86_PAE @@ -1415,6 +1436,35 @@ config X86_DIRECT_GBPAGES supports them), so don't confuse the user by printing that we have them enabled. +config ARCH_HAS_MEM_ENCRYPT + def_bool y + +config AMD_MEM_ENCRYPT + bool "AMD Secure Memory Encryption (SME) support" + depends on X86_64 && CPU_SUP_AMD + ---help--- + Say yes to enable support for the encryption of system memory. + This requires an AMD processor that supports Secure Memory + Encryption (SME). + +config AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT + bool "Activate AMD Secure Memory Encryption (SME) by default" + default y + depends on AMD_MEM_ENCRYPT + ---help--- + Say yes to have system memory encrypted by default if running on + an AMD processor that supports Secure Memory Encryption (SME). + + If set to Y, then the encryption of system memory can be + deactivated with the mem_encrypt=off command line option. + + If set to N, then the encryption of system memory can be + activated with the mem_encrypt=on command line option. + +config ARCH_USE_MEMREMAP_PROT + def_bool y + depends on AMD_MEM_ENCRYPT + # Common NUMA Features config NUMA bool "Numa Memory Allocation and Scheduler Support" diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index cd20ca0b4043..71a48a30fc84 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -305,8 +305,6 @@ config DEBUG_ENTRY Some of these sanity checks may slow down kernel entries and exits or otherwise impact performance. - This is currently used to help test NMI code. - If unsure, say N. config DEBUG_NMI_SELFTEST @@ -358,4 +356,61 @@ config PUNIT_ATOM_DEBUG The current power state can be read from /sys/kernel/debug/punit_atom/dev_power_state +choice + prompt "Choose kernel unwinder" + default FRAME_POINTER_UNWINDER + ---help--- + This determines which method will be used for unwinding kernel stack + traces for panics, oopses, bugs, warnings, perf, /proc/<pid>/stack, + livepatch, lockdep, and more. + +config FRAME_POINTER_UNWINDER + bool "Frame pointer unwinder" + select FRAME_POINTER + ---help--- + This option enables the frame pointer unwinder for unwinding kernel + stack traces. + + The unwinder itself is fast and it uses less RAM than the ORC + unwinder, but the kernel text size will grow by ~3% and the kernel's + overall performance will degrade by roughly 5-10%. + + This option is recommended if you want to use the livepatch + consistency model, as this is currently the only way to get a + reliable stack trace (CONFIG_HAVE_RELIABLE_STACKTRACE). + +config ORC_UNWINDER + bool "ORC unwinder" + depends on X86_64 + select STACK_VALIDATION + ---help--- + This option enables the ORC (Oops Rewind Capability) unwinder for + unwinding kernel stack traces. It uses a custom data format which is + a simplified version of the DWARF Call Frame Information standard. + + This unwinder is more accurate across interrupt entry frames than the + frame pointer unwinder. It also enables a 5-10% performance + improvement across the entire kernel compared to frame pointers. + + Enabling this option will increase the kernel's runtime memory usage + by roughly 2-4MB, depending on your kernel config. + +config GUESS_UNWINDER + bool "Guess unwinder" + depends on EXPERT + ---help--- + This option enables the "guess" unwinder for unwinding kernel stack + traces. It scans the stack and reports every kernel text address it + finds. Some of the addresses it reports may be incorrect. + + While this option often produces false positives, it can still be + useful in many cases. Unlike the other unwinders, it has no runtime + overhead. + +endchoice + +config FRAME_POINTER + depends on !ORC_UNWINDER && !GUESS_UNWINDER + bool + endmenu diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 1e902f926be3..6276572259c8 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -14,9 +14,11 @@ endif # For gcc stack alignment is specified with -mpreferred-stack-boundary, # clang has the option -mstack-alignment for that purpose. ifneq ($(call cc-option, -mpreferred-stack-boundary=4),) - cc_stack_align_opt := -mpreferred-stack-boundary -else ifneq ($(call cc-option, -mstack-alignment=4),) - cc_stack_align_opt := -mstack-alignment + cc_stack_align4 := -mpreferred-stack-boundary=2 + cc_stack_align8 := -mpreferred-stack-boundary=3 +else ifneq ($(call cc-option, -mstack-alignment=16),) + cc_stack_align4 := -mstack-alignment=4 + cc_stack_align8 := -mstack-alignment=8 endif # How to compile the 16-bit code. Note we always compile for -march=i386; @@ -36,7 +38,7 @@ REALMODE_CFLAGS := $(M16_CFLAGS) -g -Os -D__KERNEL__ \ REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), -ffreestanding) REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), -fno-stack-protector) -REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), $(cc_stack_align_opt)=2) +REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), $(cc_stack_align4)) export REALMODE_CFLAGS # BITS is used as extension for files which are available in a 32 bit @@ -76,7 +78,7 @@ ifeq ($(CONFIG_X86_32),y) # Align the stack to the register width instead of using the default # alignment of 16 bytes. This reduces stack usage and the number of # alignment instructions. - KBUILD_CFLAGS += $(call cc-option,$(cc_stack_align_opt)=2) + KBUILD_CFLAGS += $(call cc-option,$(cc_stack_align4)) # Disable unit-at-a-time mode on pre-gcc-4.0 compilers, it makes gcc use # a lot more stack due to the lack of sharing of stacklots: @@ -115,7 +117,7 @@ else # default alignment which keep the stack *mis*aligned. # Furthermore an alignment to the register width reduces stack usage # and the number of alignment instructions. - KBUILD_CFLAGS += $(call cc-option,$(cc_stack_align_opt)=3) + KBUILD_CFLAGS += $(call cc-option,$(cc_stack_align8)) # Use -mskip-rax-setup if supported. KBUILD_CFLAGS += $(call cc-option,-mskip-rax-setup) @@ -232,9 +234,6 @@ KBUILD_CFLAGS += -Wno-sign-compare # KBUILD_CFLAGS += -fno-asynchronous-unwind-tables -KBUILD_CFLAGS += $(mflags-y) -KBUILD_AFLAGS += $(mflags-y) - 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 2c860ad4fe06..8a958274b54c 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -34,6 +34,7 @@ KBUILD_CFLAGS += $(cflags-y) KBUILD_CFLAGS += -mno-mmx -mno-sse KBUILD_CFLAGS += $(call cc-option,-ffreestanding) KBUILD_CFLAGS += $(call cc-option,-fno-stack-protector) +KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member) KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__ GCOV_PROFILE := n diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index c3e869eaef0c..926c2cc4facc 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -767,7 +767,7 @@ static efi_status_t setup_e820(struct boot_params *params, m |= (u64)efi->efi_memmap_hi << 32; #endif - d = (efi_memory_desc_t *)(m + (i * efi->efi_memdesc_size)); + d = efi_early_memdesc_ptr(m, efi->efi_memdesc_size, i); switch (d->type) { case EFI_RESERVED_TYPE: case EFI_RUNTIME_SERVICES_CODE: @@ -1058,7 +1058,7 @@ struct boot_params *efi_main(struct efi_config *c, desc->s = DESC_TYPE_CODE_DATA; desc->dpl = 0; desc->p = 1; - desc->limit = 0xf; + desc->limit1 = 0xf; desc->avl = 0; desc->l = 0; desc->d = SEG_OP_SIZE_32BIT; @@ -1078,7 +1078,7 @@ struct boot_params *efi_main(struct efi_config *c, desc->s = DESC_TYPE_CODE_DATA; desc->dpl = 0; desc->p = 1; - desc->limit = 0xf; + desc->limit1 = 0xf; desc->avl = 0; if (IS_ENABLED(CONFIG_X86_64)) { desc->l = 1; @@ -1099,7 +1099,7 @@ struct boot_params *efi_main(struct efi_config *c, desc->s = DESC_TYPE_CODE_DATA; desc->dpl = 0; desc->p = 1; - desc->limit = 0xf; + desc->limit1 = 0xf; desc->avl = 0; desc->l = 0; desc->d = SEG_OP_SIZE_32BIT; @@ -1116,7 +1116,7 @@ struct boot_params *efi_main(struct efi_config *c, desc->s = 0; desc->dpl = 0; desc->p = 1; - desc->limit = 0x0; + desc->limit1 = 0x0; desc->avl = 0; desc->l = 0; desc->d = 0; diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S index d85b9625e836..11c68cf53d4e 100644 --- a/arch/x86/boot/compressed/head_32.S +++ b/arch/x86/boot/compressed/head_32.S @@ -61,71 +61,6 @@ __HEAD ENTRY(startup_32) -#ifdef CONFIG_EFI_STUB - jmp preferred_addr - - /* - * We don't need the return address, so set up the stack so - * efi_main() can find its arguments. - */ -ENTRY(efi_pe_entry) - add $0x4, %esp - - call 1f -1: popl %esi - subl $1b, %esi - - popl %ecx - movl %ecx, efi32_config(%esi) /* Handle */ - popl %ecx - movl %ecx, efi32_config+8(%esi) /* EFI System table pointer */ - - /* Relocate efi_config->call() */ - leal efi32_config(%esi), %eax - add %esi, 40(%eax) - pushl %eax - - call make_boot_params - cmpl $0, %eax - je fail - movl %esi, BP_code32_start(%eax) - popl %ecx - pushl %eax - pushl %ecx - jmp 2f /* Skip efi_config initialization */ - -ENTRY(efi32_stub_entry) - add $0x4, %esp - popl %ecx - popl %edx - - call 1f -1: popl %esi - subl $1b, %esi - - movl %ecx, efi32_config(%esi) /* Handle */ - movl %edx, efi32_config+8(%esi) /* EFI System table pointer */ - - /* Relocate efi_config->call() */ - leal efi32_config(%esi), %eax - add %esi, 40(%eax) - pushl %eax -2: - call efi_main - cmpl $0, %eax - movl %eax, %esi - jne 2f -fail: - /* EFI init failed, so hang. */ - hlt - jmp fail -2: - movl BP_code32_start(%esi), %eax - leal preferred_addr(%eax), %eax - jmp *%eax - -preferred_addr: -#endif cld /* * Test KEEP_SEGMENTS flag to see if the bootloader is asking @@ -208,6 +143,70 @@ preferred_addr: jmp *%eax ENDPROC(startup_32) +#ifdef CONFIG_EFI_STUB +/* + * We don't need the return address, so set up the stack so efi_main() can find + * its arguments. + */ +ENTRY(efi_pe_entry) + add $0x4, %esp + + call 1f +1: popl %esi + subl $1b, %esi + + popl %ecx + movl %ecx, efi32_config(%esi) /* Handle */ + popl %ecx + movl %ecx, efi32_config+8(%esi) /* EFI System table pointer */ + + /* Relocate efi_config->call() */ + leal efi32_config(%esi), %eax + add %esi, 40(%eax) + pushl %eax + + call make_boot_params + cmpl $0, %eax + je fail + movl %esi, BP_code32_start(%eax) + popl %ecx + pushl %eax + pushl %ecx + jmp 2f /* Skip efi_config initialization */ +ENDPROC(efi_pe_entry) + +ENTRY(efi32_stub_entry) + add $0x4, %esp + popl %ecx + popl %edx + + call 1f +1: popl %esi + subl $1b, %esi + + movl %ecx, efi32_config(%esi) /* Handle */ + movl %edx, efi32_config+8(%esi) /* EFI System table pointer */ + + /* Relocate efi_config->call() */ + leal efi32_config(%esi), %eax + add %esi, 40(%eax) + pushl %eax +2: + call efi_main + cmpl $0, %eax + movl %eax, %esi + jne 2f +fail: + /* EFI init failed, so hang. */ + hlt + jmp fail +2: + movl BP_code32_start(%esi), %eax + leal startup_32(%eax), %eax + jmp *%eax +ENDPROC(efi32_stub_entry) +#endif + .text relocated: diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index fbf4c32d0b62..b4a5d284391c 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -243,65 +243,6 @@ ENTRY(startup_64) * that maps our entire kernel(text+data+bss+brk), zero page * and command line. */ -#ifdef CONFIG_EFI_STUB - /* - * The entry point for the PE/COFF executable is efi_pe_entry, so - * only legacy boot loaders will execute this jmp. - */ - jmp preferred_addr - -ENTRY(efi_pe_entry) - movq %rcx, efi64_config(%rip) /* Handle */ - movq %rdx, efi64_config+8(%rip) /* EFI System table pointer */ - - leaq efi64_config(%rip), %rax - movq %rax, efi_config(%rip) - - call 1f -1: popq %rbp - subq $1b, %rbp - - /* - * Relocate efi_config->call(). - */ - addq %rbp, efi64_config+40(%rip) - - movq %rax, %rdi - call make_boot_params - cmpq $0,%rax - je fail - mov %rax, %rsi - leaq startup_32(%rip), %rax - movl %eax, BP_code32_start(%rsi) - jmp 2f /* Skip the relocation */ - -handover_entry: - call 1f -1: popq %rbp - subq $1b, %rbp - - /* - * Relocate efi_config->call(). - */ - movq efi_config(%rip), %rax - addq %rbp, 40(%rax) -2: - movq efi_config(%rip), %rdi - call efi_main - movq %rax,%rsi - cmpq $0,%rax - jne 2f -fail: - /* EFI init failed, so hang. */ - hlt - jmp fail -2: - movl BP_code32_start(%esi), %eax - leaq preferred_addr(%rax), %rax - jmp *%rax - -preferred_addr: -#endif /* Setup data segments. */ xorl %eax, %eax @@ -413,6 +354,59 @@ lvl5: jmp *%rax #ifdef CONFIG_EFI_STUB + +/* The entry point for the PE/COFF executable is efi_pe_entry. */ +ENTRY(efi_pe_entry) + movq %rcx, efi64_config(%rip) /* Handle */ + movq %rdx, efi64_config+8(%rip) /* EFI System table pointer */ + + leaq efi64_config(%rip), %rax + movq %rax, efi_config(%rip) + + call 1f +1: popq %rbp + subq $1b, %rbp + + /* + * Relocate efi_config->call(). + */ + addq %rbp, efi64_config+40(%rip) + + movq %rax, %rdi + call make_boot_params + cmpq $0,%rax + je fail + mov %rax, %rsi + leaq startup_32(%rip), %rax + movl %eax, BP_code32_start(%rsi) + jmp 2f /* Skip the relocation */ + +handover_entry: + call 1f +1: popq %rbp + subq $1b, %rbp + + /* + * Relocate efi_config->call(). + */ + movq efi_config(%rip), %rax + addq %rbp, 40(%rax) +2: + movq efi_config(%rip), %rdi + call efi_main + movq %rax,%rsi + cmpq $0,%rax + jne 2f +fail: + /* EFI init failed, so hang. */ + hlt + jmp fail +2: + movl BP_code32_start(%esi), %eax + leaq startup_64(%rax), %rax + jmp *%rax +ENDPROC(efi_pe_entry) + .org 0x390 ENTRY(efi64_stub_entry) movq %rdi, efi64_config(%rip) /* Handle */ diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index 91f27ab970ef..17818ba6906f 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -37,7 +37,9 @@ #include <linux/uts.h> #include <linux/utsname.h> #include <linux/ctype.h> +#include <linux/efi.h> #include <generated/utsrelease.h> +#include <asm/efi.h> /* Macros used by the included decompressor code below. */ #define STATIC @@ -479,35 +481,31 @@ static unsigned long slots_fetch_random(void) return 0; } -static void process_e820_entry(struct boot_e820_entry *entry, +static void process_mem_region(struct mem_vector *entry, unsigned long minimum, unsigned long image_size) { struct mem_vector region, overlap; struct slot_area slot_area; unsigned long start_orig, end; - struct boot_e820_entry cur_entry; - - /* Skip non-RAM entries. */ - if (entry->type != E820_TYPE_RAM) - return; + struct mem_vector cur_entry; /* On 32-bit, ignore entries entirely above our maximum. */ - if (IS_ENABLED(CONFIG_X86_32) && entry->addr >= KERNEL_IMAGE_SIZE) + if (IS_ENABLED(CONFIG_X86_32) && entry->start >= KERNEL_IMAGE_SIZE) return; /* Ignore entries entirely below our minimum. */ - if (entry->addr + entry->size < minimum) + if (entry->start + entry->size < minimum) return; /* Ignore entries above memory limit */ - end = min(entry->size + entry->addr, mem_limit); - if (entry->addr >= end) + end = min(entry->size + entry->start, mem_limit); + if (entry->start >= end) return; - cur_entry.addr = entry->addr; - cur_entry.size = end - entry->addr; + cur_entry.start = entry->start; + cur_entry.size = end - entry->start; - region.start = cur_entry.addr; + region.start = cur_entry.start; region.size = cur_entry.size; /* Give up if slot area array is full. */ @@ -521,8 +519,8 @@ static void process_e820_entry(struct boot_e820_entry *entry, /* Potentially raise address to meet alignment needs. */ region.start = ALIGN(region.start, CONFIG_PHYSICAL_ALIGN); - /* Did we raise the address above this e820 region? */ - if (region.start > cur_entry.addr + cur_entry.size) + /* Did we raise the address above the passed in memory entry? */ + if (region.start > cur_entry.start + cur_entry.size) return; /* Reduce size by any delta from the original address. */ @@ -562,31 +560,126 @@ static void process_e820_entry(struct boot_e820_entry *entry, } } -static unsigned long find_random_phys_addr(unsigned long minimum, - unsigned long image_size) +#ifdef CONFIG_EFI +/* + * Returns true if mirror region found (and must have been processed + * for slots adding) + */ +static bool +process_efi_entries(unsigned long minimum, unsigned long image_size) { + struct efi_info *e = &boot_params->efi_info; + bool efi_mirror_found = false; + struct mem_vector region; + efi_memory_desc_t *md; + unsigned long pmap; + char *signature; + u32 nr_desc; int i; - unsigned long addr; - /* Check if we had too many memmaps. */ - if (memmap_too_large) { - debug_putstr("Aborted e820 scan (more than 4 memmap= args)!\n"); - return 0; + signature = (char *)&e->efi_loader_signature; + if (strncmp(signature, EFI32_LOADER_SIGNATURE, 4) && + strncmp(signature, EFI64_LOADER_SIGNATURE, 4)) + return false; + +#ifdef CONFIG_X86_32 + /* Can't handle data above 4GB at this time */ + if (e->efi_memmap_hi) { + warn("EFI memmap is above 4GB, can't be handled now on x86_32. EFI should be disabled.\n"); + return false; } + pmap = e->efi_memmap; +#else + pmap = (e->efi_memmap | ((__u64)e->efi_memmap_hi << 32)); +#endif - /* Make sure minimum is aligned. */ - minimum = ALIGN(minimum, CONFIG_PHYSICAL_ALIGN); + nr_desc = e->efi_memmap_size / e->efi_memdesc_size; + for (i = 0; i < nr_desc; i++) { + md = efi_early_memdesc_ptr(pmap, e->efi_memdesc_size, i); + if (md->attribute & EFI_MEMORY_MORE_RELIABLE) { + efi_mirror_found = true; + break; + } + } + + for (i = 0; i < nr_desc; i++) { + md = efi_early_memdesc_ptr(pmap, e->efi_memdesc_size, i); + + /* + * Here we are more conservative in picking free memory than + * the EFI spec allows: + * + * According to the spec, EFI_BOOT_SERVICES_{CODE|DATA} are also + * free memory and thus available to place the kernel image into, + * but in practice there's firmware where using that memory leads + * to crashes. + * + * Only EFI_CONVENTIONAL_MEMORY is guaranteed to be free. + */ + if (md->type != EFI_CONVENTIONAL_MEMORY) + continue; + + if (efi_mirror_found && + !(md->attribute & EFI_MEMORY_MORE_RELIABLE)) + continue; + + region.start = md->phys_addr; + region.size = md->num_pages << EFI_PAGE_SHIFT; + process_mem_region(®ion, minimum, image_size); + if (slot_area_index == MAX_SLOT_AREA) { + debug_putstr("Aborted EFI scan (slot_areas full)!\n"); + break; + } + } + return true; +} +#else +static inline bool +process_efi_entries(unsigned long minimum, unsigned long image_size) +{ + return false; +} +#endif + +static void process_e820_entries(unsigned long minimum, + unsigned long image_size) +{ + int i; + struct mem_vector region; + struct boot_e820_entry *entry; /* Verify potential e820 positions, appending to slots list. */ for (i = 0; i < boot_params->e820_entries; i++) { - process_e820_entry(&boot_params->e820_table[i], minimum, - image_size); + entry = &boot_params->e820_table[i]; + /* Skip non-RAM entries. */ + if (entry->type != E820_TYPE_RAM) + continue; + region.start = entry->addr; + region.size = entry->size; + process_mem_region(®ion, minimum, image_size); if (slot_area_index == MAX_SLOT_AREA) { debug_putstr("Aborted e820 scan (slot_areas full)!\n"); break; } } +} + +static unsigned long find_random_phys_addr(unsigned long minimum, + unsigned long image_size) +{ + /* 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)) + return slots_fetch_random(); + process_e820_entries(minimum, image_size); return slots_fetch_random(); } @@ -645,7 +738,7 @@ void choose_random_location(unsigned long input, */ min_addr = min(*output, 512UL << 20); - /* Walk e820 and find a random address. */ + /* Walk available memory entries to find a random address. */ random_addr = find_random_phys_addr(min_addr, output_size); if (!random_addr) { warn("Physical KASLR disabled: no suitable memory region!"); diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index a0838ab929f2..c14217cd0155 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -116,8 +116,7 @@ void __putstr(const char *s) } } - if (boot_params->screen_info.orig_video_mode == 0 && - lines == 0 && cols == 0) + if (lines == 0 || cols == 0) return; x = boot_params->screen_info.orig_x; diff --git a/arch/x86/boot/compressed/pagetable.c b/arch/x86/boot/compressed/pagetable.c index 28029be47fbb..f1aa43854bed 100644 --- a/arch/x86/boot/compressed/pagetable.c +++ b/arch/x86/boot/compressed/pagetable.c @@ -15,6 +15,13 @@ #define __pa(x) ((unsigned long)(x)) #define __va(x) ((void *)((unsigned long)(x))) +/* + * The pgtable.h and mm/ident_map.c includes make use of the SME related + * information which is not used in the compressed image support. Un-define + * the SME support to avoid any compile and link errors. + */ +#undef CONFIG_AMD_MEM_ENCRYPT + #include "misc.h" /* These actually do the work of building the kernel identity maps. */ diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index 2ed8f0c25def..1bb08ecffd24 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -520,8 +520,14 @@ pref_address: .quad LOAD_PHYSICAL_ADDR # preferred load addr # the description in lib/decompressor_xxx.c for specific information. # # extra_bytes = (uncompressed_size >> 12) + 65536 + 128 +# +# LZ4 is even worse: data that cannot be further compressed grows by 0.4%, +# or one byte per 256 bytes. OTOH, we can safely get rid of the +128 as +# the size-dependent part now grows so fast. +# +# extra_bytes = (uncompressed_size >> 8) + 65536 -#define ZO_z_extra_bytes ((ZO_z_output_len >> 12) + 65536 + 128) +#define ZO_z_extra_bytes ((ZO_z_output_len >> 8) + 65536) #if ZO_z_output_len > ZO_z_input_len # define ZO_z_extract_offset (ZO_z_output_len + ZO_z_extra_bytes - \ ZO_z_input_len) diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c index 630e3664906b..16f49123d747 100644 --- a/arch/x86/boot/string.c +++ b/arch/x86/boot/string.c @@ -16,6 +16,15 @@ #include "ctype.h" #include "string.h" +/* + * Undef these macros so that the functions that we provide + * here will have the correct names regardless of how string.h + * may have chosen to #define them. + */ +#undef memcpy +#undef memset +#undef memcmp + int memcmp(const void *s1, const void *s2, size_t len) { bool diff; diff --git a/arch/x86/configs/tiny.config b/arch/x86/configs/tiny.config index 4b429df40d7a..550cd5012b73 100644 --- a/arch/x86/configs/tiny.config +++ b/arch/x86/configs/tiny.config @@ -1,3 +1,5 @@ CONFIG_NOHIGHMEM=y # CONFIG_HIGHMEM4G is not set # CONFIG_HIGHMEM64G is not set +CONFIG_GUESS_UNWINDER=y +# CONFIG_FRAME_POINTER_UNWINDER is not set diff --git a/arch/x86/crypto/sha1_avx2_x86_64_asm.S b/arch/x86/crypto/sha1_avx2_x86_64_asm.S index 1cd792db15ef..1eab79c9ac48 100644 --- a/arch/x86/crypto/sha1_avx2_x86_64_asm.S +++ b/arch/x86/crypto/sha1_avx2_x86_64_asm.S @@ -117,11 +117,10 @@ .set T1, REG_T1 .endm -#define K_BASE %r8 #define HASH_PTR %r9 +#define BLOCKS_CTR %r8 #define BUFFER_PTR %r10 #define BUFFER_PTR2 %r13 -#define BUFFER_END %r11 #define PRECALC_BUF %r14 #define WK_BUF %r15 @@ -205,14 +204,14 @@ * blended AVX2 and ALU instruction scheduling * 1 vector iteration per 8 rounds */ - vmovdqu ((i * 2) + PRECALC_OFFSET)(BUFFER_PTR), W_TMP + vmovdqu (i * 2)(BUFFER_PTR), W_TMP .elseif ((i & 7) == 1) - vinsertf128 $1, (((i-1) * 2)+PRECALC_OFFSET)(BUFFER_PTR2),\ + vinsertf128 $1, ((i-1) * 2)(BUFFER_PTR2),\ WY_TMP, WY_TMP .elseif ((i & 7) == 2) vpshufb YMM_SHUFB_BSWAP, WY_TMP, WY .elseif ((i & 7) == 4) - vpaddd K_XMM(K_BASE), WY, WY_TMP + vpaddd K_XMM + K_XMM_AR(%rip), WY, WY_TMP .elseif ((i & 7) == 7) vmovdqu WY_TMP, PRECALC_WK(i&~7) @@ -255,7 +254,7 @@ vpxor WY, WY_TMP, WY_TMP .elseif ((i & 7) == 7) vpxor WY_TMP2, WY_TMP, WY - vpaddd K_XMM(K_BASE), WY, WY_TMP + vpaddd K_XMM + K_XMM_AR(%rip), WY, WY_TMP vmovdqu WY_TMP, PRECALC_WK(i&~7) PRECALC_ROTATE_WY @@ -291,7 +290,7 @@ vpsrld $30, WY, WY vpor WY, WY_TMP, WY .elseif ((i & 7) == 7) - vpaddd K_XMM(K_BASE), WY, WY_TMP + vpaddd K_XMM + K_XMM_AR(%rip), WY, WY_TMP vmovdqu WY_TMP, PRECALC_WK(i&~7) PRECALC_ROTATE_WY @@ -446,6 +445,16 @@ .endm +/* Add constant only if (%2 > %3) condition met (uses RTA as temp) + * %1 + %2 >= %3 ? %4 : 0 + */ +.macro ADD_IF_GE a, b, c, d + mov \a, RTA + add $\d, RTA + cmp $\c, \b + cmovge RTA, \a +.endm + /* * macro implements 80 rounds of SHA-1, for multiple blocks with s/w pipelining */ @@ -463,13 +472,16 @@ lea (2*4*80+32)(%rsp), WK_BUF # Precalc WK for first 2 blocks - PRECALC_OFFSET = 0 + ADD_IF_GE BUFFER_PTR2, BLOCKS_CTR, 2, 64 .set i, 0 .rept 160 PRECALC i .set i, i + 1 .endr - PRECALC_OFFSET = 128 + + /* Go to next block if needed */ + ADD_IF_GE BUFFER_PTR, BLOCKS_CTR, 3, 128 + ADD_IF_GE BUFFER_PTR2, BLOCKS_CTR, 4, 128 xchg WK_BUF, PRECALC_BUF .align 32 @@ -479,8 +491,8 @@ _loop: * we use K_BASE value as a signal of a last block, * it is set below by: cmovae BUFFER_PTR, K_BASE */ - cmp K_BASE, BUFFER_PTR - jne _begin + test BLOCKS_CTR, BLOCKS_CTR + jnz _begin .align 32 jmp _end .align 32 @@ -512,10 +524,10 @@ _loop0: .set j, j+2 .endr - add $(2*64), BUFFER_PTR /* move to next odd-64-byte block */ - cmp BUFFER_END, BUFFER_PTR /* is current block the last one? */ - cmovae K_BASE, BUFFER_PTR /* signal the last iteration smartly */ - + /* Update Counter */ + sub $1, BLOCKS_CTR + /* Move to the next block only if needed*/ + ADD_IF_GE BUFFER_PTR, BLOCKS_CTR, 4, 128 /* * rounds * 60,62,64,66,68 @@ -532,8 +544,8 @@ _loop0: UPDATE_HASH 12(HASH_PTR), D UPDATE_HASH 16(HASH_PTR), E - cmp K_BASE, BUFFER_PTR /* is current block the last one? */ - je _loop + test BLOCKS_CTR, BLOCKS_CTR + jz _loop mov TB, B @@ -575,10 +587,10 @@ _loop2: .set j, j+2 .endr - add $(2*64), BUFFER_PTR2 /* move to next even-64-byte block */ - - cmp BUFFER_END, BUFFER_PTR2 /* is current block the last one */ - cmovae K_BASE, BUFFER_PTR /* signal the last iteration smartly */ + /* update counter */ + sub $1, BLOCKS_CTR + /* Move to the next block only if needed*/ + ADD_IF_GE BUFFER_PTR2, BLOCKS_CTR, 4, 128 jmp _loop3 _loop3: @@ -641,19 +653,12 @@ _loop3: avx2_zeroupper - lea K_XMM_AR(%rip), K_BASE - + /* Setup initial values */ mov CTX, HASH_PTR mov BUF, BUFFER_PTR - lea 64(BUF), BUFFER_PTR2 - - shl $6, CNT /* mul by 64 */ - add BUF, CNT - add $64, CNT - mov CNT, BUFFER_END - cmp BUFFER_END, BUFFER_PTR2 - cmovae K_BASE, BUFFER_PTR2 + mov BUF, BUFFER_PTR2 + mov CNT, BLOCKS_CTR xmm_mov BSWAP_SHUFB_CTL(%rip), YMM_SHUFB_BSWAP diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c index f960a043cdeb..fc61739150e7 100644 --- a/arch/x86/crypto/sha1_ssse3_glue.c +++ b/arch/x86/crypto/sha1_ssse3_glue.c @@ -201,7 +201,7 @@ asmlinkage void sha1_transform_avx2(u32 *digest, const char *data, static bool avx2_usable(void) { - if (false && avx_usable() && boot_cpu_has(X86_FEATURE_AVX2) + if (avx_usable() && boot_cpu_has(X86_FEATURE_AVX2) && boot_cpu_has(X86_FEATURE_BMI1) && boot_cpu_has(X86_FEATURE_BMI2)) return true; diff --git a/arch/x86/entry/Makefile b/arch/x86/entry/Makefile index 9976fcecd17e..af28a8a24366 100644 --- a/arch/x86/entry/Makefile +++ b/arch/x86/entry/Makefile @@ -2,7 +2,6 @@ # Makefile for the x86 low level entry code # -OBJECT_FILES_NON_STANDARD_entry_$(BITS).o := y OBJECT_FILES_NON_STANDARD_entry_64_compat.o := y CFLAGS_syscall_64.o += $(call cc-option,-Wno-override-init,) diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 05ed3d393da7..640aafebdc00 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -1,4 +1,5 @@ #include <linux/jump_label.h> +#include <asm/unwind_hints.h> /* @@ -112,6 +113,7 @@ For 32-bit we have the following conventions - kernel is built with movq %rdx, 12*8+\offset(%rsp) movq %rsi, 13*8+\offset(%rsp) movq %rdi, 14*8+\offset(%rsp) + UNWIND_HINT_REGS offset=\offset extra=0 .endm .macro SAVE_C_REGS offset=0 SAVE_C_REGS_HELPER \offset, 1, 1, 1, 1 @@ -136,6 +138,7 @@ For 32-bit we have the following conventions - kernel is built with movq %r12, 3*8+\offset(%rsp) movq %rbp, 4*8+\offset(%rsp) movq %rbx, 5*8+\offset(%rsp) + UNWIND_HINT_REGS offset=\offset .endm .macro RESTORE_EXTRA_REGS offset=0 @@ -145,6 +148,7 @@ For 32-bit we have the following conventions - kernel is built with movq 3*8+\offset(%rsp), %r12 movq 4*8+\offset(%rsp), %rbp movq 5*8+\offset(%rsp), %rbx + UNWIND_HINT_REGS offset=\offset extra=0 .endm .macro RESTORE_C_REGS_HELPER rstor_rax=1, rstor_rcx=1, rstor_r11=1, rstor_r8910=1, rstor_rdx=1 @@ -167,6 +171,7 @@ For 32-bit we have the following conventions - kernel is built with .endif movq 13*8(%rsp), %rsi movq 14*8(%rsp), %rdi + UNWIND_HINT_IRET_REGS offset=16*8 .endm .macro RESTORE_C_REGS RESTORE_C_REGS_HELPER 1,1,1,1,1 diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index cdefcfdd9e63..03505ffbe1b6 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -23,6 +23,7 @@ #include <linux/user-return-notifier.h> #include <linux/uprobes.h> #include <linux/livepatch.h> +#include <linux/syscalls.h> #include <asm/desc.h> #include <asm/traps.h> @@ -183,6 +184,8 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs) struct thread_info *ti = current_thread_info(); u32 cached_flags; + addr_limit_user_check(); + if (IS_ENABLED(CONFIG_PROVE_LOCKING) && WARN_ON(!irqs_disabled())) local_irq_disable(); diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 48ef7bb32c42..8a13d468635a 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -673,16 +673,8 @@ ENTRY(name) \ jmp ret_from_intr; \ ENDPROC(name) - -#ifdef CONFIG_TRACING -# define TRACE_BUILD_INTERRUPT(name, nr) BUILD_INTERRUPT3(trace_##name, nr, smp_trace_##name) -#else -# define TRACE_BUILD_INTERRUPT(name, nr) -#endif - #define BUILD_INTERRUPT(name, nr) \ BUILD_INTERRUPT3(name, nr, smp_##name); \ - TRACE_BUILD_INTERRUPT(name, nr) /* The include is where all of the SMP etc. interrupts come from */ #include <asm/entry_arch.h> @@ -880,25 +872,17 @@ ENTRY(xen_failsafe_callback) ENDPROC(xen_failsafe_callback) BUILD_INTERRUPT3(xen_hvm_callback_vector, HYPERVISOR_CALLBACK_VECTOR, - xen_evtchn_do_upcall) + xen_evtchn_do_upcall) #endif /* CONFIG_XEN */ #if IS_ENABLED(CONFIG_HYPERV) BUILD_INTERRUPT3(hyperv_callback_vector, HYPERVISOR_CALLBACK_VECTOR, - hyperv_vector_handler) + hyperv_vector_handler) #endif /* CONFIG_HYPERV */ -#ifdef CONFIG_TRACING -ENTRY(trace_page_fault) - ASM_CLAC - pushl $trace_do_page_fault - jmp common_exception -END(trace_page_fault) -#endif - ENTRY(page_fault) ASM_CLAC pushl $do_page_fault diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index a9a8027a6c0e..49167258d587 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -36,6 +36,7 @@ #include <asm/smap.h> #include <asm/pgtable_types.h> #include <asm/export.h> +#include <asm/frame.h> #include <linux/err.h> .code64 @@ -43,9 +44,10 @@ #ifdef CONFIG_PARAVIRT ENTRY(native_usergs_sysret64) + UNWIND_HINT_EMPTY swapgs sysretq -ENDPROC(native_usergs_sysret64) +END(native_usergs_sysret64) #endif /* CONFIG_PARAVIRT */ .macro TRACE_IRQS_IRETQ @@ -134,19 +136,14 @@ ENDPROC(native_usergs_sysret64) */ ENTRY(entry_SYSCALL_64) + UNWIND_HINT_EMPTY /* * Interrupts are off on entry. * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON, * it is too small to ever cause noticeable irq latency. */ - SWAPGS_UNSAFE_STACK - /* - * A hypervisor implementation might want to use a label - * after the swapgs, so that it can do the swapgs - * for the guest and jump here on syscall. - */ -GLOBAL(entry_SYSCALL_64_after_swapgs) + swapgs movq %rsp, PER_CPU_VAR(rsp_scratch) movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp @@ -158,6 +155,7 @@ GLOBAL(entry_SYSCALL_64_after_swapgs) pushq %r11 /* pt_regs->flags */ pushq $__USER_CS /* pt_regs->cs */ pushq %rcx /* pt_regs->ip */ +GLOBAL(entry_SYSCALL_64_after_hwframe) pushq %rax /* pt_regs->orig_ax */ pushq %rdi /* pt_regs->di */ pushq %rsi /* pt_regs->si */ @@ -169,6 +167,7 @@ GLOBAL(entry_SYSCALL_64_after_swapgs) pushq %r10 /* pt_regs->r10 */ pushq %r11 /* pt_regs->r11 */ sub $(6*8), %rsp /* pt_regs->bp, bx, r12-15 not saved */ + UNWIND_HINT_REGS extra=0 /* * If we need to do entry work or if we guess we'll need to do @@ -223,6 +222,7 @@ entry_SYSCALL_64_fastpath: movq EFLAGS(%rsp), %r11 RESTORE_C_REGS_EXCEPT_RCX_R11 movq RSP(%rsp), %rsp + UNWIND_HINT_EMPTY USERGS_SYSRET64 1: @@ -316,6 +316,7 @@ syscall_return_via_sysret: /* rcx and r11 are already restored (see code above) */ RESTORE_C_REGS_EXCEPT_RCX_R11 movq RSP(%rsp), %rsp + UNWIND_HINT_EMPTY USERGS_SYSRET64 opportunistic_sysret_failed: @@ -343,6 +344,7 @@ ENTRY(stub_ptregs_64) DISABLE_INTERRUPTS(CLBR_ANY) TRACE_IRQS_OFF popq %rax + UNWIND_HINT_REGS extra=0 jmp entry_SYSCALL64_slow_path 1: @@ -351,6 +353,7 @@ END(stub_ptregs_64) .macro ptregs_stub func ENTRY(ptregs_\func) + UNWIND_HINT_FUNC leaq \func(%rip), %rax jmp stub_ptregs_64 END(ptregs_\func) @@ -367,6 +370,7 @@ END(ptregs_\func) * %rsi: next task */ ENTRY(__switch_to_asm) + UNWIND_HINT_FUNC /* * Save callee-saved registers * This must match the order in inactive_task_frame @@ -406,6 +410,7 @@ END(__switch_to_asm) * r12: kernel thread arg */ ENTRY(ret_from_fork) + UNWIND_HINT_EMPTY movq %rax, %rdi call schedule_tail /* rdi: 'prev' task parameter */ @@ -413,6 +418,7 @@ ENTRY(ret_from_fork) jnz 1f /* kernel threads are uncommon */ 2: + UNWIND_HINT_REGS movq %rsp, %rdi call syscall_return_slowpath /* returns with IRQs disabled */ TRACE_IRQS_ON /* user mode is traced as IRQS on */ @@ -440,13 +446,102 @@ END(ret_from_fork) ENTRY(irq_entries_start) vector=FIRST_EXTERNAL_VECTOR .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR) + UNWIND_HINT_IRET_REGS pushq $(~vector+0x80) /* Note: always in signed byte range */ - vector=vector+1 jmp common_interrupt .align 8 + vector=vector+1 .endr END(irq_entries_start) +.macro DEBUG_ENTRY_ASSERT_IRQS_OFF +#ifdef CONFIG_DEBUG_ENTRY + pushfq + testl $X86_EFLAGS_IF, (%rsp) + jz .Lokay_\@ + ud2 +.Lokay_\@: + addq $8, %rsp +#endif +.endm + +/* + * Enters the IRQ stack if we're not already using it. NMI-safe. Clobbers + * flags and puts old RSP into old_rsp, and leaves all other GPRs alone. + * Requires kernel GSBASE. + * + * The invariant is that, if irq_count != -1, then the IRQ stack is in use. + */ +.macro ENTER_IRQ_STACK regs=1 old_rsp + DEBUG_ENTRY_ASSERT_IRQS_OFF + movq %rsp, \old_rsp + + .if \regs + UNWIND_HINT_REGS base=\old_rsp + .endif + + incl PER_CPU_VAR(irq_count) + jnz .Lirq_stack_push_old_rsp_\@ + + /* + * Right now, if we just incremented irq_count to zero, we've + * claimed the IRQ stack but we haven't switched to it yet. + * + * If anything is added that can interrupt us here without using IST, + * it must be *extremely* careful to limit its stack usage. This + * could include kprobes and a hypothetical future IST-less #DB + * handler. + * + * The OOPS unwinder relies on the word at the top of the IRQ + * stack linking back to the previous RSP for the entire time we're + * on the IRQ stack. For this to work reliably, we need to write + * it before we actually move ourselves to the IRQ stack. + */ + + movq \old_rsp, PER_CPU_VAR(irq_stack_union + IRQ_STACK_SIZE - 8) + movq PER_CPU_VAR(irq_stack_ptr), %rsp + +#ifdef CONFIG_DEBUG_ENTRY + /* + * If the first movq above becomes wrong due to IRQ stack layout + * changes, the only way we'll notice is if we try to unwind right + * here. Assert that we set up the stack right to catch this type + * of bug quickly. + */ + cmpq -8(%rsp), \old_rsp + je .Lirq_stack_okay\@ + ud2 + .Lirq_stack_okay\@: +#endif + +.Lirq_stack_push_old_rsp_\@: + pushq \old_rsp + + .if \regs + UNWIND_HINT_REGS indirect=1 + .endif +.endm + +/* + * Undoes ENTER_IRQ_STACK. + */ +.macro LEAVE_IRQ_STACK regs=1 + DEBUG_ENTRY_ASSERT_IRQS_OFF + /* We need to be off the IRQ stack before decrementing irq_count. */ + popq %rsp + + .if \regs + UNWIND_HINT_REGS + .endif + + /* + * As in ENTER_IRQ_STACK, irq_count == 0, we are still claiming + * the irq stack but we're not on it. + */ + + decl PER_CPU_VAR(irq_count) +.endm + /* * Interrupt entry/exit. * @@ -485,17 +580,7 @@ END(irq_entries_start) CALL_enter_from_user_mode 1: - /* - * Save previous stack pointer, optionally switch to interrupt stack. - * irq_count is used to check if a CPU is already on an interrupt stack - * or not. While this is essentially redundant with preempt_count it is - * a little cheaper to use a separate counter in the PDA (short of - * moving irq_enter into assembly, which would be too much work) - */ - movq %rsp, %rdi - incl PER_CPU_VAR(irq_count) - cmovzq PER_CPU_VAR(irq_stack_ptr), %rsp - pushq %rdi + ENTER_IRQ_STACK old_rsp=%rdi /* We entered an interrupt context - irqs are off: */ TRACE_IRQS_OFF @@ -515,10 +600,8 @@ common_interrupt: ret_from_intr: DISABLE_INTERRUPTS(CLBR_ANY) TRACE_IRQS_OFF - decl PER_CPU_VAR(irq_count) - /* Restore saved previous stack */ - popq %rsp + LEAVE_IRQ_STACK testb $3, CS(%rsp) jz retint_kernel @@ -561,6 +644,7 @@ restore_c_regs_and_iret: INTERRUPT_RETURN ENTRY(native_iret) + UNWIND_HINT_IRET_REGS /* * Are we returning to a stack segment from the LDT? Note: in * 64-bit mode SS:RSP on the exception stack is always valid. @@ -633,6 +717,7 @@ native_irq_return_ldt: orq PER_CPU_VAR(espfix_stack), %rax SWAPGS movq %rax, %rsp + UNWIND_HINT_IRET_REGS offset=8 /* * At this point, we cannot write to the stack any more, but we can @@ -654,6 +739,7 @@ END(common_interrupt) */ .macro apicinterrupt3 num sym do_sym ENTRY(\sym) + UNWIND_HINT_IRET_REGS ASM_CLAC pushq $~(\num) .Lcommon_\sym: @@ -662,31 +748,13 @@ ENTRY(\sym) END(\sym) .endm -#ifdef CONFIG_TRACING -#define trace(sym) trace_##sym -#define smp_trace(sym) smp_trace_##sym - -.macro trace_apicinterrupt num sym -apicinterrupt3 \num trace(\sym) smp_trace(\sym) -.endm -#else -.macro trace_apicinterrupt num sym do_sym -.endm -#endif - /* Make sure APIC interrupt handlers end up in the irqentry section: */ -#if defined(CONFIG_FUNCTION_GRAPH_TRACER) || defined(CONFIG_KASAN) -# define PUSH_SECTION_IRQENTRY .pushsection .irqentry.text, "ax" -# define POP_SECTION_IRQENTRY .popsection -#else -# define PUSH_SECTION_IRQENTRY -# define POP_SECTION_IRQENTRY -#endif +#define PUSH_SECTION_IRQENTRY .pushsection .irqentry.text, "ax" +#define POP_SECTION_IRQENTRY .popsection .macro apicinterrupt num sym do_sym PUSH_SECTION_IRQENTRY apicinterrupt3 \num \sym \do_sym -trace_apicinterrupt \num \sym POP_SECTION_IRQENTRY .endm @@ -705,6 +773,7 @@ apicinterrupt X86_PLATFORM_IPI_VECTOR x86_platform_ipi smp_x86_platform_ipi #ifdef CONFIG_HAVE_KVM apicinterrupt3 POSTED_INTR_VECTOR kvm_posted_intr_ipi smp_kvm_posted_intr_ipi apicinterrupt3 POSTED_INTR_WAKEUP_VECTOR kvm_posted_intr_wakeup_ipi smp_kvm_posted_intr_wakeup_ipi +apicinterrupt3 POSTED_INTR_NESTED_VECTOR kvm_posted_intr_nested_ipi smp_kvm_posted_intr_nested_ipi #endif #ifdef CONFIG_X86_MCE_THRESHOLD @@ -739,13 +808,14 @@ apicinterrupt IRQ_WORK_VECTOR irq_work_interrupt smp_irq_work_interrupt .macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1 ENTRY(\sym) + UNWIND_HINT_IRET_REGS offset=8 + /* Sanity check */ .if \shift_ist != -1 && \paranoid == 0 .error "using shift_ist requires paranoid=1" .endif ASM_CLAC - PARAVIRT_ADJUST_EXCEPTION_FRAME .ifeq \has_error_code pushq $-1 /* ORIG_RAX: no syscall to restart */ @@ -762,6 +832,7 @@ ENTRY(\sym) .else call error_entry .endif + UNWIND_HINT_REGS /* returned flag: ebx=0: need swapgs on exit, ebx=1: don't need it */ .if \paranoid @@ -828,17 +899,6 @@ ENTRY(\sym) END(\sym) .endm -#ifdef CONFIG_TRACING -.macro trace_idtentry sym do_sym has_error_code:req -idtentry trace(\sym) trace(\do_sym) has_error_code=\has_error_code -idtentry \sym \do_sym has_error_code=\has_error_code -.endm -#else -.macro trace_idtentry sym do_sym has_error_code:req -idtentry \sym \do_sym has_error_code=\has_error_code -.endm -#endif - idtentry divide_error do_divide_error has_error_code=0 idtentry overflow do_overflow has_error_code=0 idtentry bounds do_bounds has_error_code=0 @@ -859,6 +919,7 @@ idtentry simd_coprocessor_error do_simd_coprocessor_error has_error_code=0 * edi: new selector */ ENTRY(native_load_gs_index) + FRAME_BEGIN pushfq DISABLE_INTERRUPTS(CLBR_ANY & ~CLBR_RDI) SWAPGS @@ -867,8 +928,9 @@ ENTRY(native_load_gs_index) 2: ALTERNATIVE "", "mfence", X86_BUG_SWAPGS_FENCE SWAPGS popfq + FRAME_END ret -END(native_load_gs_index) +ENDPROC(native_load_gs_index) EXPORT_SYMBOL(native_load_gs_index) _ASM_EXTABLE(.Lgs_change, bad_gs) @@ -891,17 +953,15 @@ bad_gs: ENTRY(do_softirq_own_stack) pushq %rbp mov %rsp, %rbp - incl PER_CPU_VAR(irq_count) - cmove PER_CPU_VAR(irq_stack_ptr), %rsp - push %rbp /* frame pointer backlink */ + ENTER_IRQ_STACK regs=0 old_rsp=%r11 call __do_softirq + LEAVE_IRQ_STACK regs=0 leaveq - decl PER_CPU_VAR(irq_count) ret -END(do_softirq_own_stack) +ENDPROC(do_softirq_own_stack) #ifdef CONFIG_XEN -idtentry xen_hypervisor_callback xen_do_hypervisor_callback has_error_code=0 +idtentry hypervisor_callback xen_do_hypervisor_callback has_error_code=0 /* * A note on the "critical region" in our callback handler. @@ -922,14 +982,14 @@ ENTRY(xen_do_hypervisor_callback) /* do_hypervisor_callback(struct *pt_regs) */ * Since we don't modify %rdi, evtchn_do_upall(struct *pt_regs) will * see the correct pointer to the pt_regs */ + UNWIND_HINT_FUNC movq %rdi, %rsp /* we don't return, adjust the stack frame */ -11: incl PER_CPU_VAR(irq_count) - movq %rsp, %rbp - cmovzq PER_CPU_VAR(irq_stack_ptr), %rsp - pushq %rbp /* frame pointer backlink */ + UNWIND_HINT_REGS + + ENTER_IRQ_STACK old_rsp=%r10 call xen_evtchn_do_upcall - popq %rsp - decl PER_CPU_VAR(irq_count) + LEAVE_IRQ_STACK + #ifndef CONFIG_PREEMPT call xen_maybe_preempt_hcall #endif @@ -950,6 +1010,7 @@ END(xen_do_hypervisor_callback) * with its current contents: any discrepancy means we in category 1. */ ENTRY(xen_failsafe_callback) + UNWIND_HINT_EMPTY movl %ds, %ecx cmpw %cx, 0x10(%rsp) jne 1f @@ -967,13 +1028,13 @@ ENTRY(xen_failsafe_callback) movq 8(%rsp), %r11 addq $0x30, %rsp pushq $0 /* RIP */ - pushq %r11 - pushq %rcx + UNWIND_HINT_IRET_REGS offset=8 jmp general_protection 1: /* Segment mismatch => Category 1 (Bad segment). Retry the IRET. */ movq (%rsp), %rcx movq 8(%rsp), %r11 addq $0x30, %rsp + UNWIND_HINT_IRET_REGS pushq $-1 /* orig_ax = -1 => not a system call */ ALLOC_PT_GPREGS_ON_STACK SAVE_C_REGS @@ -997,13 +1058,12 @@ idtentry int3 do_int3 has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK idtentry stack_segment do_stack_segment has_error_code=1 #ifdef CONFIG_XEN -idtentry xen_debug do_debug has_error_code=0 -idtentry xen_int3 do_int3 has_error_code=0 -idtentry xen_stack_segment do_stack_segment has_error_code=1 +idtentry xendebug do_debug has_error_code=0 +idtentry xenint3 do_int3 has_error_code=0 #endif idtentry general_protection do_general_protection has_error_code=1 -trace_idtentry page_fault do_page_fault has_error_code=1 +idtentry page_fault do_page_fault has_error_code=1 #ifdef CONFIG_KVM_GUEST idtentry async_page_fault do_async_page_fault has_error_code=1 @@ -1019,6 +1079,7 @@ idtentry machine_check has_error_code=0 paranoid=1 do_sym=*machine_check_vec * Return: ebx=0: need swapgs on exit, ebx=1: otherwise */ ENTRY(paranoid_entry) + UNWIND_HINT_FUNC cld SAVE_C_REGS 8 SAVE_EXTRA_REGS 8 @@ -1046,6 +1107,7 @@ END(paranoid_entry) * On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it) */ ENTRY(paranoid_exit) + UNWIND_HINT_REGS DISABLE_INTERRUPTS(CLBR_ANY) TRACE_IRQS_OFF_DEBUG testl %ebx, %ebx /* swapgs needed? */ @@ -1067,6 +1129,7 @@ END(paranoid_exit) * Return: EBX=0: came from user mode; EBX=1: otherwise */ ENTRY(error_entry) + UNWIND_HINT_FUNC cld SAVE_C_REGS 8 SAVE_EXTRA_REGS 8 @@ -1151,6 +1214,7 @@ END(error_entry) * 0: user gsbase is loaded, we need SWAPGS and standard preparation for return to usermode */ ENTRY(error_exit) + UNWIND_HINT_REGS DISABLE_INTERRUPTS(CLBR_ANY) TRACE_IRQS_OFF testl %ebx, %ebx @@ -1159,19 +1223,9 @@ ENTRY(error_exit) END(error_exit) /* Runs on exception stack */ +/* XXX: broken on Xen PV */ ENTRY(nmi) - /* - * Fix up the exception frame if we're on Xen. - * PARAVIRT_ADJUST_EXCEPTION_FRAME is guaranteed to push at most - * one value to the stack on native, so it may clobber the rdx - * scratch slot, but it won't clobber any of the important - * slots past it. - * - * Xen is a different story, because the Xen frame itself overlaps - * the "NMI executing" variable. - */ - PARAVIRT_ADJUST_EXCEPTION_FRAME - + UNWIND_HINT_IRET_REGS /* * We allow breakpoints in NMIs. If a breakpoint occurs, then * the iretq it performs will take us out of NMI context. @@ -1210,6 +1264,8 @@ ENTRY(nmi) * other IST entries. */ + ASM_CLAC + /* Use %rdx as our temp variable throughout */ pushq %rdx @@ -1231,11 +1287,13 @@ ENTRY(nmi) cld movq %rsp, %rdx movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp + UNWIND_HINT_IRET_REGS base=%rdx offset=8 pushq 5*8(%rdx) /* pt_regs->ss */ pushq 4*8(%rdx) /* pt_regs->rsp */ pushq 3*8(%rdx) /* pt_regs->flags */ pushq 2*8(%rdx) /* pt_regs->cs */ pushq 1*8(%rdx) /* pt_regs->rip */ + UNWIND_HINT_IRET_REGS pushq $-1 /* pt_regs->orig_ax */ pushq %rdi /* pt_regs->di */ pushq %rsi /* pt_regs->si */ @@ -1252,6 +1310,7 @@ ENTRY(nmi) pushq %r13 /* pt_regs->r13 */ pushq %r14 /* pt_regs->r14 */ pushq %r15 /* pt_regs->r15 */ + UNWIND_HINT_REGS ENCODE_FRAME_POINTER /* @@ -1406,6 +1465,7 @@ first_nmi: .rept 5 pushq 11*8(%rsp) .endr + UNWIND_HINT_IRET_REGS /* Everything up to here is safe from nested NMIs */ @@ -1421,6 +1481,7 @@ first_nmi: pushq $__KERNEL_CS /* CS */ pushq $1f /* RIP */ INTERRUPT_RETURN /* continues at repeat_nmi below */ + UNWIND_HINT_IRET_REGS 1: #endif @@ -1470,6 +1531,7 @@ end_repeat_nmi: * exceptions might do. */ call paranoid_entry + UNWIND_HINT_REGS /* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */ movq %rsp, %rdi @@ -1507,17 +1569,19 @@ nmi_restore: END(nmi) ENTRY(ignore_sysret) + UNWIND_HINT_EMPTY mov $-ENOSYS, %eax sysret END(ignore_sysret) ENTRY(rewind_stack_do_exit) + UNWIND_HINT_FUNC /* Prevent any naive code from trying to unwind to our caller. */ xorl %ebp, %ebp movq PER_CPU_VAR(cpu_current_top_of_stack), %rax - leaq -TOP_OF_KERNEL_STACK_PADDING-PTREGS_SIZE(%rax), %rsp + leaq -PTREGS_SIZE(%rax), %rsp + UNWIND_HINT_FUNC sp_offset=PTREGS_SIZE call do_exit -1: jmp 1b END(rewind_stack_do_exit) diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index e1721dafbcb1..e26c25ca7756 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -183,21 +183,20 @@ ENDPROC(entry_SYSENTER_compat) */ ENTRY(entry_SYSCALL_compat) /* Interrupts are off on entry. */ - SWAPGS_UNSAFE_STACK + swapgs /* Stash user ESP and switch to the kernel stack. */ movl %esp, %r8d movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp - /* Zero-extending 32-bit regs, do not remove */ - movl %eax, %eax - /* Construct struct pt_regs on stack */ pushq $__USER32_DS /* pt_regs->ss */ pushq %r8 /* pt_regs->sp */ pushq %r11 /* pt_regs->flags */ pushq $__USER32_CS /* pt_regs->cs */ pushq %rcx /* pt_regs->ip */ +GLOBAL(entry_SYSCALL_compat_after_hwframe) + movl %eax, %eax /* discard orig_ax high bits */ pushq %rax /* pt_regs->orig_ax */ pushq %rdi /* pt_regs->di */ pushq %rsi /* pt_regs->si */ @@ -294,7 +293,6 @@ ENTRY(entry_INT80_compat) /* * Interrupts are off on entry. */ - PARAVIRT_ADJUST_EXCEPTION_FRAME ASM_CLAC /* Do this early to minimize exposure */ SWAPGS @@ -342,8 +340,7 @@ ENTRY(entry_INT80_compat) jmp restore_regs_and_iret END(entry_INT80_compat) - ALIGN -GLOBAL(stub32_clone) +ENTRY(stub32_clone) /* * The 32-bit clone ABI is: clone(..., int tls_val, int *child_tidptr). * The 64-bit clone ABI is: clone(..., int *child_tidptr, int tls_val). @@ -353,3 +350,4 @@ GLOBAL(stub32_clone) */ xchg %r8, %rcx jmp sys_clone +ENDPROC(stub32_clone) diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index 726355ce8497..1911310959f8 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -351,7 +351,7 @@ static void vgetcpu_cpu_init(void *arg) * and 8 bits for the node) */ d.limit0 = cpu | ((node & 0xf) << 12); - d.limit = node >> 4; + d.limit1 = node >> 4; d.type = 5; /* RO data, expand down, accessed */ d.dpl = 3; /* Visible to user code */ d.s = 1; /* Not a system segment */ diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c index ad44af0dd667..f5cbbba99283 100644 --- a/arch/x86/events/amd/uncore.c +++ b/arch/x86/events/amd/uncore.c @@ -400,11 +400,24 @@ static int amd_uncore_cpu_starting(unsigned int cpu) if (amd_uncore_llc) { unsigned int apicid = cpu_data(cpu).apicid; - unsigned int nshared; + unsigned int nshared, subleaf, prev_eax = 0; uncore = *per_cpu_ptr(amd_uncore_llc, cpu); - cpuid_count(0x8000001d, 2, &eax, &ebx, &ecx, &edx); - nshared = ((eax >> 14) & 0xfff) + 1; + /* + * Iterate over Cache Topology Definition leaves until no + * more cache descriptions are available. + */ + for (subleaf = 0; subleaf < 5; subleaf++) { + cpuid_count(0x8000001d, subleaf, &eax, &ebx, &ecx, &edx); + + /* EAX[0:4] gives type of cache */ + if (!(eax & 0x1f)) + break; + + prev_eax = eax; + } + nshared = ((prev_eax >> 14) & 0xfff) + 1; + uncore->id = apicid - (apicid % nshared); uncore = amd_uncore_find_online_sibling(uncore, amd_uncore_llc); @@ -555,7 +568,7 @@ static int __init amd_uncore_init(void) ret = 0; } - if (boot_cpu_has(X86_FEATURE_PERFCTR_L2)) { + if (boot_cpu_has(X86_FEATURE_PERFCTR_LLC)) { amd_uncore_llc = alloc_percpu(struct amd_uncore *); if (!amd_uncore_llc) { ret = -ENOMEM; diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 8e3db8f642a7..80534d3c2480 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -487,22 +487,28 @@ static inline int precise_br_compat(struct perf_event *event) return m == b; } -int x86_pmu_hw_config(struct perf_event *event) +int x86_pmu_max_precise(void) { - if (event->attr.precise_ip) { - int precise = 0; + int precise = 0; - /* Support for constant skid */ - if (x86_pmu.pebs_active && !x86_pmu.pebs_broken) { + /* Support for constant skid */ + if (x86_pmu.pebs_active && !x86_pmu.pebs_broken) { + precise++; + + /* Support for IP fixup */ + if (x86_pmu.lbr_nr || x86_pmu.intel_cap.pebs_format >= 2) precise++; - /* Support for IP fixup */ - if (x86_pmu.lbr_nr || x86_pmu.intel_cap.pebs_format >= 2) - precise++; + if (x86_pmu.pebs_prec_dist) + precise++; + } + return precise; +} - if (x86_pmu.pebs_prec_dist) - precise++; - } +int x86_pmu_hw_config(struct perf_event *event) +{ + if (event->attr.precise_ip) { + int precise = x86_pmu_max_precise(); if (event->attr.precise_ip > precise) return -EOPNOTSUPP; @@ -1751,6 +1757,7 @@ 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 int __init init_hw_perf_events(void) { @@ -1799,6 +1806,14 @@ static int __init init_hw_perf_events(void) x86_pmu_format_group.attrs = x86_pmu.format_attrs; + if (x86_pmu.caps_attrs) { + struct attribute **tmp; + + tmp = merge_attr(x86_pmu_caps_group.attrs, x86_pmu.caps_attrs); + if (!WARN_ON(!tmp)) + x86_pmu_caps_group.attrs = tmp; + } + if (x86_pmu.event_attrs) x86_pmu_events_group.attrs = x86_pmu.event_attrs; @@ -2114,7 +2129,7 @@ static void refresh_pce(void *ignored) load_mm_cr4(this_cpu_read(cpu_tlbstate.loaded_mm)); } -static void x86_pmu_event_mapped(struct perf_event *event) +static void x86_pmu_event_mapped(struct perf_event *event, struct mm_struct *mm) { if (!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED)) return; @@ -2129,22 +2144,20 @@ static void x86_pmu_event_mapped(struct perf_event *event) * For now, this can't happen because all callers hold mmap_sem * for write. If this changes, we'll need a different solution. */ - lockdep_assert_held_exclusive(¤t->mm->mmap_sem); + lockdep_assert_held_exclusive(&mm->mmap_sem); - if (atomic_inc_return(¤t->mm->context.perf_rdpmc_allowed) == 1) - on_each_cpu_mask(mm_cpumask(current->mm), refresh_pce, NULL, 1); + if (atomic_inc_return(&mm->context.perf_rdpmc_allowed) == 1) + on_each_cpu_mask(mm_cpumask(mm), refresh_pce, NULL, 1); } -static void x86_pmu_event_unmapped(struct perf_event *event) +static void x86_pmu_event_unmapped(struct perf_event *event, struct mm_struct *mm) { - if (!current->mm) - return; if (!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED)) return; - if (atomic_dec_and_test(¤t->mm->context.perf_rdpmc_allowed)) - on_each_cpu_mask(mm_cpumask(current->mm), refresh_pce, NULL, 1); + if (atomic_dec_and_test(&mm->context.perf_rdpmc_allowed)) + on_each_cpu_mask(mm_cpumask(mm), refresh_pce, NULL, 1); } static int x86_pmu_event_idx(struct perf_event *event) @@ -2215,10 +2228,30 @@ static struct attribute_group x86_pmu_attr_group = { .attrs = x86_pmu_attrs, }; +static ssize_t max_precise_show(struct device *cdev, + struct device_attribute *attr, + char *buf) +{ + return snprintf(buf, PAGE_SIZE, "%d\n", x86_pmu_max_precise()); +} + +static DEVICE_ATTR_RO(max_precise); + +static struct attribute *x86_pmu_caps_attrs[] = { + &dev_attr_max_precise.attr, + NULL +}; + +static struct attribute_group x86_pmu_caps_group = { + .name = "caps", + .attrs = x86_pmu_caps_attrs, +}; + static const struct attribute_group *x86_pmu_attr_groups[] = { &x86_pmu_attr_group, &x86_pmu_format_group, &x86_pmu_events_group, + &x86_pmu_caps_group, NULL, }; @@ -2337,12 +2370,9 @@ static unsigned long get_segment_base(unsigned int segment) #ifdef CONFIG_MODIFY_LDT_SYSCALL struct ldt_struct *ldt; - if (idx > LDT_ENTRIES) - return 0; - /* IRQs are off, so this synchronizes with smp_store_release */ ldt = lockless_dereference(current->active_mm->context.ldt); - if (!ldt || idx > ldt->nr_entries) + if (!ldt || idx >= ldt->nr_entries) return 0; desc = &ldt->entries[idx]; @@ -2350,7 +2380,7 @@ static unsigned long get_segment_base(unsigned int segment) return 0; #endif } else { - if (idx > GDT_ENTRIES) + if (idx >= GDT_ENTRIES) return 0; desc = raw_cpu_ptr(gdt_page.gdt) + idx; diff --git a/arch/x86/events/intel/Makefile b/arch/x86/events/intel/Makefile index 06c2baa51814..e9d8520a801a 100644 --- a/arch/x86/events/intel/Makefile +++ b/arch/x86/events/intel/Makefile @@ -1,4 +1,4 @@ -obj-$(CONFIG_CPU_SUP_INTEL) += core.o bts.o cqm.o +obj-$(CONFIG_CPU_SUP_INTEL) += core.o bts.o obj-$(CONFIG_CPU_SUP_INTEL) += ds.o knc.o obj-$(CONFIG_CPU_SUP_INTEL) += lbr.o p4.o p6.o pt.o obj-$(CONFIG_PERF_EVENTS_INTEL_RAPL) += intel-rapl-perf.o diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c index 8ae8c5ce3a1f..16076eb34699 100644 --- a/arch/x86/events/intel/bts.c +++ b/arch/x86/events/intel/bts.c @@ -69,7 +69,7 @@ struct bts_buffer { struct bts_phys buf[0]; }; -struct pmu bts_pmu; +static struct pmu bts_pmu; static size_t buf_size(struct page *page) { @@ -268,7 +268,7 @@ static void bts_event_start(struct perf_event *event, int flags) bts->ds_back.bts_absolute_maximum = cpuc->ds->bts_absolute_maximum; bts->ds_back.bts_interrupt_threshold = cpuc->ds->bts_interrupt_threshold; - event->hw.itrace_started = 1; + perf_event_itrace_started(event); event->hw.state = 0; __bts_event_start(event); diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 98b0f0729527..829e89cfcee2 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3415,12 +3415,26 @@ static struct attribute *intel_arch3_formats_attr[] = { &format_attr_any.attr, &format_attr_inv.attr, &format_attr_cmask.attr, + NULL, +}; + +static struct attribute *hsw_format_attr[] = { &format_attr_in_tx.attr, &format_attr_in_tx_cp.attr, + &format_attr_offcore_rsp.attr, + &format_attr_ldlat.attr, + NULL +}; - &format_attr_offcore_rsp.attr, /* XXX do NHM/WSM + SNB breakout */ - &format_attr_ldlat.attr, /* PEBS load latency */ - NULL, +static struct attribute *nhm_format_attr[] = { + &format_attr_offcore_rsp.attr, + &format_attr_ldlat.attr, + NULL +}; + +static struct attribute *slm_format_attr[] = { + &format_attr_offcore_rsp.attr, + NULL }; static struct attribute *skl_format_attr[] = { @@ -3781,6 +3795,36 @@ done: static DEVICE_ATTR_RW(freeze_on_smi); +static ssize_t branches_show(struct device *cdev, + struct device_attribute *attr, + char *buf) +{ + return snprintf(buf, PAGE_SIZE, "%d\n", x86_pmu.lbr_nr); +} + +static DEVICE_ATTR_RO(branches); + +static struct attribute *lbr_attrs[] = { + &dev_attr_branches.attr, + NULL +}; + +static char pmu_name_str[30]; + +static ssize_t pmu_name_show(struct device *cdev, + struct device_attribute *attr, + char *buf) +{ + return snprintf(buf, PAGE_SIZE, "%s\n", pmu_name_str); +} + +static DEVICE_ATTR_RO(pmu_name); + +static struct attribute *intel_pmu_caps_attrs[] = { + &dev_attr_pmu_name.attr, + NULL +}; + static struct attribute *intel_pmu_attrs[] = { &dev_attr_freeze_on_smi.attr, NULL, @@ -3795,6 +3839,8 @@ __init int intel_pmu_init(void) unsigned int unused; struct extra_reg *er; int version, i; + struct attribute **extra_attr = NULL; + char *name; if (!cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) { switch (boot_cpu_data.x86) { @@ -3862,6 +3908,7 @@ __init int intel_pmu_init(void) switch (boot_cpu_data.x86_model) { case INTEL_FAM6_CORE_YONAH: pr_cont("Core events, "); + name = "core"; break; case INTEL_FAM6_CORE2_MEROM: @@ -3877,6 +3924,7 @@ __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_core2_event_constraints; x86_pmu.pebs_constraints = intel_core2_pebs_event_constraints; pr_cont("Core2 events, "); + name = "core2"; break; case INTEL_FAM6_NEHALEM: @@ -3905,8 +3953,11 @@ __init int intel_pmu_init(void) intel_pmu_pebs_data_source_nhm(); x86_add_quirk(intel_nehalem_quirk); + x86_pmu.pebs_no_tlb = 1; + extra_attr = nhm_format_attr; pr_cont("Nehalem events, "); + name = "nehalem"; break; case INTEL_FAM6_ATOM_PINEVIEW: @@ -3923,6 +3974,7 @@ __init int intel_pmu_init(void) x86_pmu.pebs_constraints = intel_atom_pebs_event_constraints; x86_pmu.pebs_aliases = intel_pebs_aliases_core2; pr_cont("Atom events, "); + name = "bonnell"; break; case INTEL_FAM6_ATOM_SILVERMONT1: @@ -3940,7 +3992,9 @@ __init int intel_pmu_init(void) x86_pmu.extra_regs = intel_slm_extra_regs; x86_pmu.flags |= PMU_FL_HAS_RSP_1; x86_pmu.cpu_events = slm_events_attrs; + extra_attr = slm_format_attr; pr_cont("Silvermont events, "); + name = "silvermont"; break; case INTEL_FAM6_ATOM_GOLDMONT: @@ -3965,7 +4019,9 @@ __init int intel_pmu_init(void) x86_pmu.lbr_pt_coexist = true; x86_pmu.flags |= PMU_FL_HAS_RSP_1; x86_pmu.cpu_events = glm_events_attrs; + extra_attr = slm_format_attr; pr_cont("Goldmont events, "); + name = "goldmont"; break; case INTEL_FAM6_ATOM_GEMINI_LAKE: @@ -3991,7 +4047,9 @@ __init int intel_pmu_init(void) x86_pmu.cpu_events = glm_events_attrs; /* Goldmont Plus has 4-wide pipeline */ event_attr_td_total_slots_scale_glm.event_str = "4"; + extra_attr = slm_format_attr; pr_cont("Goldmont plus events, "); + name = "goldmont_plus"; break; case INTEL_FAM6_WESTMERE: @@ -4020,7 +4078,9 @@ __init int intel_pmu_init(void) X86_CONFIG(.event=0xb1, .umask=0x3f, .inv=1, .cmask=1); intel_pmu_pebs_data_source_nhm(); + extra_attr = nhm_format_attr; pr_cont("Westmere events, "); + name = "westmere"; break; case INTEL_FAM6_SANDYBRIDGE: @@ -4056,7 +4116,10 @@ __init int intel_pmu_init(void) intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = X86_CONFIG(.event=0xb1, .umask=0x01, .inv=1, .cmask=1); + extra_attr = nhm_format_attr; + pr_cont("SandyBridge events, "); + name = "sandybridge"; break; case INTEL_FAM6_IVYBRIDGE: @@ -4090,7 +4153,10 @@ __init int intel_pmu_init(void) intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1); + extra_attr = nhm_format_attr; + pr_cont("IvyBridge events, "); + name = "ivybridge"; break; @@ -4118,7 +4184,10 @@ __init int intel_pmu_init(void) x86_pmu.get_event_constraints = hsw_get_event_constraints; x86_pmu.cpu_events = hsw_events_attrs; x86_pmu.lbr_double_abort = true; + extra_attr = boot_cpu_has(X86_FEATURE_RTM) ? + hsw_format_attr : nhm_format_attr; pr_cont("Haswell events, "); + name = "haswell"; break; case INTEL_FAM6_BROADWELL_CORE: @@ -4154,7 +4223,10 @@ __init int intel_pmu_init(void) x86_pmu.get_event_constraints = hsw_get_event_constraints; x86_pmu.cpu_events = hsw_events_attrs; x86_pmu.limit_period = bdw_limit_period; + extra_attr = boot_cpu_has(X86_FEATURE_RTM) ? + hsw_format_attr : nhm_format_attr; pr_cont("Broadwell events, "); + name = "broadwell"; break; case INTEL_FAM6_XEON_PHI_KNL: @@ -4172,8 +4244,9 @@ __init int intel_pmu_init(void) /* all extra regs are per-cpu when HT is on */ x86_pmu.flags |= PMU_FL_HAS_RSP_1; x86_pmu.flags |= PMU_FL_NO_HT_SHARING; - + extra_attr = slm_format_attr; pr_cont("Knights Landing/Mill events, "); + name = "knights-landing"; break; case INTEL_FAM6_SKYLAKE_MOBILE: @@ -4203,11 +4276,14 @@ __init int intel_pmu_init(void) x86_pmu.hw_config = hsw_hw_config; x86_pmu.get_event_constraints = hsw_get_event_constraints; - x86_pmu.format_attrs = merge_attr(intel_arch3_formats_attr, - skl_format_attr); - WARN_ON(!x86_pmu.format_attrs); + extra_attr = boot_cpu_has(X86_FEATURE_RTM) ? + hsw_format_attr : nhm_format_attr; + extra_attr = merge_attr(extra_attr, skl_format_attr); x86_pmu.cpu_events = hsw_events_attrs; + intel_pmu_pebs_data_source_skl( + boot_cpu_data.x86_model == INTEL_FAM6_SKYLAKE_X); pr_cont("Skylake events, "); + name = "skylake"; break; default: @@ -4215,6 +4291,7 @@ __init int intel_pmu_init(void) case 1: x86_pmu.event_constraints = intel_v1_event_constraints; pr_cont("generic architected perfmon v1, "); + name = "generic_arch_v1"; break; default: /* @@ -4222,10 +4299,19 @@ __init int intel_pmu_init(void) */ x86_pmu.event_constraints = intel_gen_event_constraints; pr_cont("generic architected perfmon, "); + name = "generic_arch_v2+"; break; } } + snprintf(pmu_name_str, sizeof pmu_name_str, "%s", name); + + if (version >= 2 && extra_attr) { + x86_pmu.format_attrs = merge_attr(intel_arch3_formats_attr, + extra_attr); + WARN_ON(!x86_pmu.format_attrs); + } + if (x86_pmu.num_counters > INTEL_PMC_MAX_GENERIC) { WARN(1, KERN_ERR "hw perf events %d > max(%d), clipping!", x86_pmu.num_counters, INTEL_PMC_MAX_GENERIC); @@ -4272,8 +4358,13 @@ __init int intel_pmu_init(void) x86_pmu.lbr_nr = 0; } - if (x86_pmu.lbr_nr) + x86_pmu.caps_attrs = intel_pmu_caps_attrs; + + if (x86_pmu.lbr_nr) { + x86_pmu.caps_attrs = merge_attr(x86_pmu.caps_attrs, lbr_attrs); pr_cont("%d-deep LBR, ", x86_pmu.lbr_nr); + } + /* * Access extra MSR may cause #GP under certain circumstances. * E.g. KVM doesn't support offcore event diff --git a/arch/x86/events/intel/cqm.c b/arch/x86/events/intel/cqm.c deleted file mode 100644 index 2521f771f2f5..000000000000 --- a/arch/x86/events/intel/cqm.c +++ /dev/null @@ -1,1766 +0,0 @@ -/* - * Intel Cache Quality-of-Service Monitoring (CQM) support. - * - * Based very, very heavily on work by Peter Zijlstra. - */ - -#include <linux/perf_event.h> -#include <linux/slab.h> -#include <asm/cpu_device_id.h> -#include <asm/intel_rdt_common.h> -#include "../perf_event.h" - -#define MSR_IA32_QM_CTR 0x0c8e -#define MSR_IA32_QM_EVTSEL 0x0c8d - -#define MBM_CNTR_WIDTH 24 -/* - * Guaranteed time in ms as per SDM where MBM counters will not overflow. - */ -#define MBM_CTR_OVERFLOW_TIME 1000 - -static u32 cqm_max_rmid = -1; -static unsigned int cqm_l3_scale; /* supposedly cacheline size */ -static bool cqm_enabled, mbm_enabled; -unsigned int mbm_socket_max; - -/* - * The cached intel_pqr_state is strictly per CPU and can never be - * updated from a remote CPU. Both functions which modify the state - * (intel_cqm_event_start and intel_cqm_event_stop) are called with - * interrupts disabled, which is sufficient for the protection. - */ -DEFINE_PER_CPU(struct intel_pqr_state, pqr_state); -static struct hrtimer *mbm_timers; -/** - * struct sample - mbm event's (local or total) data - * @total_bytes #bytes since we began monitoring - * @prev_msr previous value of MSR - */ -struct sample { - u64 total_bytes; - u64 prev_msr; -}; - -/* - * samples profiled for total memory bandwidth type events - */ -static struct sample *mbm_total; -/* - * samples profiled for local memory bandwidth type events - */ -static struct sample *mbm_local; - -#define pkg_id topology_physical_package_id(smp_processor_id()) -/* - * rmid_2_index returns the index for the rmid in mbm_local/mbm_total array. - * mbm_total[] and mbm_local[] are linearly indexed by socket# * max number of - * rmids per socket, an example is given below - * RMID1 of Socket0: vrmid = 1 - * RMID1 of Socket1: vrmid = 1 * (cqm_max_rmid + 1) + 1 - * RMID1 of Socket2: vrmid = 2 * (cqm_max_rmid + 1) + 1 - */ -#define rmid_2_index(rmid) ((pkg_id * (cqm_max_rmid + 1)) + rmid) -/* - * Protects cache_cgroups and cqm_rmid_free_lru and cqm_rmid_limbo_lru. - * Also protects event->hw.cqm_rmid - * - * Hold either for stability, both for modification of ->hw.cqm_rmid. - */ -static DEFINE_MUTEX(cache_mutex); -static DEFINE_RAW_SPINLOCK(cache_lock); - -/* - * Groups of events that have the same target(s), one RMID per group. - */ -static LIST_HEAD(cache_groups); - -/* - * Mask of CPUs for reading CQM values. We only need one per-socket. - */ -static cpumask_t cqm_cpumask; - -#define RMID_VAL_ERROR (1ULL << 63) -#define RMID_VAL_UNAVAIL (1ULL << 62) - -/* - * Event IDs are used to program IA32_QM_EVTSEL before reading event - * counter from IA32_QM_CTR - */ -#define QOS_L3_OCCUP_EVENT_ID 0x01 -#define QOS_MBM_TOTAL_EVENT_ID 0x02 -#define QOS_MBM_LOCAL_EVENT_ID 0x03 - -/* - * This is central to the rotation algorithm in __intel_cqm_rmid_rotate(). - * - * This rmid is always free and is guaranteed to have an associated - * near-zero occupancy value, i.e. no cachelines are tagged with this - * RMID, once __intel_cqm_rmid_rotate() returns. - */ -static u32 intel_cqm_rotation_rmid; - -#define INVALID_RMID (-1) - -/* - * Is @rmid valid for programming the hardware? - * - * rmid 0 is reserved by the hardware for all non-monitored tasks, which - * means that we should never come across an rmid with that value. - * Likewise, an rmid value of -1 is used to indicate "no rmid currently - * assigned" and is used as part of the rotation code. - */ -static inline bool __rmid_valid(u32 rmid) -{ - if (!rmid || rmid == INVALID_RMID) - return false; - - return true; -} - -static u64 __rmid_read(u32 rmid) -{ - u64 val; - - /* - * Ignore the SDM, this thing is _NOTHING_ like a regular perfcnt, - * it just says that to increase confusion. - */ - wrmsr(MSR_IA32_QM_EVTSEL, QOS_L3_OCCUP_EVENT_ID, rmid); - rdmsrl(MSR_IA32_QM_CTR, val); - - /* - * Aside from the ERROR and UNAVAIL bits, assume this thing returns - * the number of cachelines tagged with @rmid. - */ - return val; -} - -enum rmid_recycle_state { - RMID_YOUNG = 0, - RMID_AVAILABLE, - RMID_DIRTY, -}; - -struct cqm_rmid_entry { - u32 rmid; - enum rmid_recycle_state state; - struct list_head list; - unsigned long queue_time; -}; - -/* - * cqm_rmid_free_lru - A least recently used list of RMIDs. - * - * Oldest entry at the head, newest (most recently used) entry at the - * tail. This list is never traversed, it's only used to keep track of - * the lru order. That is, we only pick entries of the head or insert - * them on the tail. - * - * All entries on the list are 'free', and their RMIDs are not currently - * in use. To mark an RMID as in use, remove its entry from the lru - * list. - * - * - * cqm_rmid_limbo_lru - list of currently unused but (potentially) dirty RMIDs. - * - * This list is contains RMIDs that no one is currently using but that - * may have a non-zero occupancy value associated with them. The - * rotation worker moves RMIDs from the limbo list to the free list once - * the occupancy value drops below __intel_cqm_threshold. - * - * Both lists are protected by cache_mutex. - */ -static LIST_HEAD(cqm_rmid_free_lru); -static LIST_HEAD(cqm_rmid_limbo_lru); - -/* - * We use a simple array of pointers so that we can lookup a struct - * cqm_rmid_entry in O(1). This alleviates the callers of __get_rmid() - * and __put_rmid() from having to worry about dealing with struct - * cqm_rmid_entry - they just deal with rmids, i.e. integers. - * - * Once this array is initialized it is read-only. No locks are required - * to access it. - * - * All entries for all RMIDs can be looked up in the this array at all - * times. - */ -static struct cqm_rmid_entry **cqm_rmid_ptrs; - -static inline struct cqm_rmid_entry *__rmid_entry(u32 rmid) -{ - struct cqm_rmid_entry *entry; - - entry = cqm_rmid_ptrs[rmid]; - WARN_ON(entry->rmid != rmid); - - return entry; -} - -/* - * Returns < 0 on fail. - * - * We expect to be called with cache_mutex held. - */ -static u32 __get_rmid(void) -{ - struct cqm_rmid_entry *entry; - - lockdep_assert_held(&cache_mutex); - - if (list_empty(&cqm_rmid_free_lru)) - return INVALID_RMID; - - entry = list_first_entry(&cqm_rmid_free_lru, struct cqm_rmid_entry, list); - list_del(&entry->list); - - return entry->rmid; -} - -static void __put_rmid(u32 rmid) -{ - struct cqm_rmid_entry *entry; - - lockdep_assert_held(&cache_mutex); - - WARN_ON(!__rmid_valid(rmid)); - entry = __rmid_entry(rmid); - - entry->queue_time = jiffies; - entry->state = RMID_YOUNG; - - list_add_tail(&entry->list, &cqm_rmid_limbo_lru); -} - -static void cqm_cleanup(void) -{ - int i; - - if (!cqm_rmid_ptrs) - return; - - for (i = 0; i < cqm_max_rmid; i++) - kfree(cqm_rmid_ptrs[i]); - - kfree(cqm_rmid_ptrs); - cqm_rmid_ptrs = NULL; - cqm_enabled = false; -} - -static int intel_cqm_setup_rmid_cache(void) -{ - struct cqm_rmid_entry *entry; - unsigned int nr_rmids; - int r = 0; - - nr_rmids = cqm_max_rmid + 1; - cqm_rmid_ptrs = kzalloc(sizeof(struct cqm_rmid_entry *) * - nr_rmids, GFP_KERNEL); - if (!cqm_rmid_ptrs) - return -ENOMEM; - - for (; r <= cqm_max_rmid; r++) { - struct cqm_rmid_entry *entry; - - entry = kmalloc(sizeof(*entry), GFP_KERNEL); - if (!entry) - goto fail; - - INIT_LIST_HEAD(&entry->list); - entry->rmid = r; - cqm_rmid_ptrs[r] = entry; - - list_add_tail(&entry->list, &cqm_rmid_free_lru); - } - - /* - * RMID 0 is special and is always allocated. It's used for all - * tasks that are not monitored. - */ - entry = __rmid_entry(0); - list_del(&entry->list); - - mutex_lock(&cache_mutex); - intel_cqm_rotation_rmid = __get_rmid(); - mutex_unlock(&cache_mutex); - - return 0; - -fail: - cqm_cleanup(); - return -ENOMEM; -} - -/* - * Determine if @a and @b measure the same set of tasks. - * - * If @a and @b measure the same set of tasks then we want to share a - * single RMID. - */ -static bool __match_event(struct perf_event *a, struct perf_event *b) -{ - /* Per-cpu and task events don't mix */ - if ((a->attach_state & PERF_ATTACH_TASK) != - (b->attach_state & PERF_ATTACH_TASK)) - return false; - -#ifdef CONFIG_CGROUP_PERF - if (a->cgrp != b->cgrp) - return false; -#endif - - /* If not task event, we're machine wide */ - if (!(b->attach_state & PERF_ATTACH_TASK)) - return true; - - /* - * Events that target same task are placed into the same cache group. - * Mark it as a multi event group, so that we update ->count - * for every event rather than just the group leader later. - */ - if (a->hw.target == b->hw.target) { - b->hw.is_group_event = true; - return true; - } - - /* - * Are we an inherited event? - */ - if (b->parent == a) - return true; - - return false; -} - -#ifdef CONFIG_CGROUP_PERF -static inline struct perf_cgroup *event_to_cgroup(struct perf_event *event) -{ - if (event->attach_state & PERF_ATTACH_TASK) - return perf_cgroup_from_task(event->hw.target, event->ctx); - - return event->cgrp; -} -#endif - -/* - * Determine if @a's tasks intersect with @b's tasks - * - * There are combinations of events that we explicitly prohibit, - * - * PROHIBITS - * system-wide -> cgroup and task - * cgroup -> system-wide - * -> task in cgroup - * task -> system-wide - * -> task in cgroup - * - * Call this function before allocating an RMID. - */ -static bool __conflict_event(struct perf_event *a, struct perf_event *b) -{ -#ifdef CONFIG_CGROUP_PERF - /* - * We can have any number of cgroups but only one system-wide - * event at a time. - */ - if (a->cgrp && b->cgrp) { - struct perf_cgroup *ac = a->cgrp; - struct perf_cgroup *bc = b->cgrp; - - /* - * This condition should have been caught in - * __match_event() and we should be sharing an RMID. - */ - WARN_ON_ONCE(ac == bc); - - if (cgroup_is_descendant(ac->css.cgroup, bc->css.cgroup) || - cgroup_is_descendant(bc->css.cgroup, ac->css.cgroup)) - return true; - - return false; - } - - if (a->cgrp || b->cgrp) { - struct perf_cgroup *ac, *bc; - - /* - * cgroup and system-wide events are mutually exclusive - */ - if ((a->cgrp && !(b->attach_state & PERF_ATTACH_TASK)) || - (b->cgrp && !(a->attach_state & PERF_ATTACH_TASK))) - return true; - - /* - * Ensure neither event is part of the other's cgroup - */ - ac = event_to_cgroup(a); - bc = event_to_cgroup(b); - if (ac == bc) - return true; - - /* - * Must have cgroup and non-intersecting task events. - */ - if (!ac || !bc) - return false; - - /* - * We have cgroup and task events, and the task belongs - * to a cgroup. Check for for overlap. - */ - if (cgroup_is_descendant(ac->css.cgroup, bc->css.cgroup) || - cgroup_is_descendant(bc->css.cgroup, ac->css.cgroup)) - return true; - - return false; - } -#endif - /* - * If one of them is not a task, same story as above with cgroups. - */ - if (!(a->attach_state & PERF_ATTACH_TASK) || - !(b->attach_state & PERF_ATTACH_TASK)) - return true; - - /* - * Must be non-overlapping. - */ - return false; -} - -struct rmid_read { - u32 rmid; - u32 evt_type; - atomic64_t value; -}; - -static void __intel_cqm_event_count(void *info); -static void init_mbm_sample(u32 rmid, u32 evt_type); -static void __intel_mbm_event_count(void *info); - -static bool is_cqm_event(int e) -{ - return (e == QOS_L3_OCCUP_EVENT_ID); -} - -static bool is_mbm_event(int e) -{ - return (e >= QOS_MBM_TOTAL_EVENT_ID && e <= QOS_MBM_LOCAL_EVENT_ID); -} - -static void cqm_mask_call(struct rmid_read *rr) -{ - if (is_mbm_event(rr->evt_type)) - on_each_cpu_mask(&cqm_cpumask, __intel_mbm_event_count, rr, 1); - else - on_each_cpu_mask(&cqm_cpumask, __intel_cqm_event_count, rr, 1); -} - -/* - * Exchange the RMID of a group of events. - */ -static u32 intel_cqm_xchg_rmid(struct perf_event *group, u32 rmid) -{ - struct perf_event *event; - struct list_head *head = &group->hw.cqm_group_entry; - u32 old_rmid = group->hw.cqm_rmid; - - lockdep_assert_held(&cache_mutex); - - /* - * If our RMID is being deallocated, perform a read now. - */ - if (__rmid_valid(old_rmid) && !__rmid_valid(rmid)) { - struct rmid_read rr = { - .rmid = old_rmid, - .evt_type = group->attr.config, - .value = ATOMIC64_INIT(0), - }; - - cqm_mask_call(&rr); - local64_set(&group->count, atomic64_read(&rr.value)); - } - - raw_spin_lock_irq(&cache_lock); - - group->hw.cqm_rmid = rmid; - list_for_each_entry(event, head, hw.cqm_group_entry) - event->hw.cqm_rmid = rmid; - - raw_spin_unlock_irq(&cache_lock); - - /* - * If the allocation is for mbm, init the mbm stats. - * Need to check if each event in the group is mbm event - * because there could be multiple type of events in the same group. - */ - if (__rmid_valid(rmid)) { - event = group; - if (is_mbm_event(event->attr.config)) - init_mbm_sample(rmid, event->attr.config); - - list_for_each_entry(event, head, hw.cqm_group_entry) { - if (is_mbm_event(event->attr.config)) - init_mbm_sample(rmid, event->attr.config); - } - } - - return old_rmid; -} - -/* - * If we fail to assign a new RMID for intel_cqm_rotation_rmid because - * cachelines are still tagged with RMIDs in limbo, we progressively - * increment the threshold until we find an RMID in limbo with <= - * __intel_cqm_threshold lines tagged. This is designed to mitigate the - * problem where cachelines tagged with an RMID are not steadily being - * evicted. - * - * On successful rotations we decrease the threshold back towards zero. - * - * __intel_cqm_max_threshold provides an upper bound on the threshold, - * and is measured in bytes because it's exposed to userland. - */ -static unsigned int __intel_cqm_threshold; -static unsigned int __intel_cqm_max_threshold; - -/* - * Test whether an RMID has a zero occupancy value on this cpu. - */ -static void intel_cqm_stable(void *arg) -{ - struct cqm_rmid_entry *entry; - - list_for_each_entry(entry, &cqm_rmid_limbo_lru, list) { - if (entry->state != RMID_AVAILABLE) - break; - - if (__rmid_read(entry->rmid) > __intel_cqm_threshold) - entry->state = RMID_DIRTY; - } -} - -/* - * If we have group events waiting for an RMID that don't conflict with - * events already running, assign @rmid. - */ -static bool intel_cqm_sched_in_event(u32 rmid) -{ - struct perf_event *leader, *event; - - lockdep_assert_held(&cache_mutex); - - leader = list_first_entry(&cache_groups, struct perf_event, - hw.cqm_groups_entry); - event = leader; - - list_for_each_entry_continue(event, &cache_groups, - hw.cqm_groups_entry) { - if (__rmid_valid(event->hw.cqm_rmid)) - continue; - - if (__conflict_event(event, leader)) - continue; - - intel_cqm_xchg_rmid(event, rmid); - return true; - } - - return false; -} - -/* - * Initially use this constant for both the limbo queue time and the - * rotation timer interval, pmu::hrtimer_interval_ms. - * - * They don't need to be the same, but the two are related since if you - * rotate faster than you recycle RMIDs, you may run out of available - * RMIDs. - */ -#define RMID_DEFAULT_QUEUE_TIME 250 /* ms */ - -static unsigned int __rmid_queue_time_ms = RMID_DEFAULT_QUEUE_TIME; - -/* - * intel_cqm_rmid_stabilize - move RMIDs from limbo to free list - * @nr_available: number of freeable RMIDs on the limbo list - * - * Quiescent state; wait for all 'freed' RMIDs to become unused, i.e. no - * cachelines are tagged with those RMIDs. After this we can reuse them - * and know that the current set of active RMIDs is stable. - * - * Return %true or %false depending on whether stabilization needs to be - * reattempted. - * - * If we return %true then @nr_available is updated to indicate the - * number of RMIDs on the limbo list that have been queued for the - * minimum queue time (RMID_AVAILABLE), but whose data occupancy values - * are above __intel_cqm_threshold. - */ -static bool intel_cqm_rmid_stabilize(unsigned int *available) -{ - struct cqm_rmid_entry *entry, *tmp; - - lockdep_assert_held(&cache_mutex); - - *available = 0; - list_for_each_entry(entry, &cqm_rmid_limbo_lru, list) { - unsigned long min_queue_time; - unsigned long now = jiffies; - - /* - * We hold RMIDs placed into limbo for a minimum queue - * time. Before the minimum queue time has elapsed we do - * not recycle RMIDs. - * - * The reasoning is that until a sufficient time has - * passed since we stopped using an RMID, any RMID - * placed onto the limbo list will likely still have - * data tagged in the cache, which means we'll probably - * fail to recycle it anyway. - * - * We can save ourselves an expensive IPI by skipping - * any RMIDs that have not been queued for the minimum - * time. - */ - min_queue_time = entry->queue_time + - msecs_to_jiffies(__rmid_queue_time_ms); - - if (time_after(min_queue_time, now)) - break; - - entry->state = RMID_AVAILABLE; - (*available)++; - } - - /* - * Fast return if none of the RMIDs on the limbo list have been - * sitting on the queue for the minimum queue time. - */ - if (!*available) - return false; - - /* - * Test whether an RMID is free for each package. - */ - on_each_cpu_mask(&cqm_cpumask, intel_cqm_stable, NULL, true); - - list_for_each_entry_safe(entry, tmp, &cqm_rmid_limbo_lru, list) { - /* - * Exhausted all RMIDs that have waited min queue time. - */ - if (entry->state == RMID_YOUNG) - break; - - if (entry->state == RMID_DIRTY) - continue; - - list_del(&entry->list); /* remove from limbo */ - - /* - * The rotation RMID gets priority if it's - * currently invalid. In which case, skip adding - * the RMID to the the free lru. - */ - if (!__rmid_valid(intel_cqm_rotation_rmid)) { - intel_cqm_rotation_rmid = entry->rmid; - continue; - } - - /* - * If we have groups waiting for RMIDs, hand - * them one now provided they don't conflict. - */ - if (intel_cqm_sched_in_event(entry->rmid)) - continue; - - /* - * Otherwise place it onto the free list. - */ - list_add_tail(&entry->list, &cqm_rmid_free_lru); - } - - - return __rmid_valid(intel_cqm_rotation_rmid); -} - -/* - * Pick a victim group and move it to the tail of the group list. - * @next: The first group without an RMID - */ -static void __intel_cqm_pick_and_rotate(struct perf_event *next) -{ - struct perf_event *rotor; - u32 rmid; - - lockdep_assert_held(&cache_mutex); - - rotor = list_first_entry(&cache_groups, struct perf_event, - hw.cqm_groups_entry); - - /* - * The group at the front of the list should always have a valid - * RMID. If it doesn't then no groups have RMIDs assigned and we - * don't need to rotate the list. - */ - if (next == rotor) - return; - - rmid = intel_cqm_xchg_rmid(rotor, INVALID_RMID); - __put_rmid(rmid); - - list_rotate_left(&cache_groups); -} - -/* - * Deallocate the RMIDs from any events that conflict with @event, and - * place them on the back of the group list. - */ -static void intel_cqm_sched_out_conflicting_events(struct perf_event *event) -{ - struct perf_event *group, *g; - u32 rmid; - - lockdep_assert_held(&cache_mutex); - - list_for_each_entry_safe(group, g, &cache_groups, hw.cqm_groups_entry) { - if (group == event) - continue; - - rmid = group->hw.cqm_rmid; - - /* - * Skip events that don't have a valid RMID. - */ - if (!__rmid_valid(rmid)) - continue; - - /* - * No conflict? No problem! Leave the event alone. - */ - if (!__conflict_event(group, event)) - continue; - - intel_cqm_xchg_rmid(group, INVALID_RMID); - __put_rmid(rmid); - } -} - -/* - * Attempt to rotate the groups and assign new RMIDs. - * - * We rotate for two reasons, - * 1. To handle the scheduling of conflicting events - * 2. To recycle RMIDs - * - * Rotating RMIDs is complicated because the hardware doesn't give us - * any clues. - * - * There's problems with the hardware interface; when you change the - * task:RMID map cachelines retain their 'old' tags, giving a skewed - * picture. In order to work around this, we must always keep one free - * RMID - intel_cqm_rotation_rmid. - * - * Rotation works by taking away an RMID from a group (the old RMID), - * and assigning the free RMID to another group (the new RMID). We must - * then wait for the old RMID to not be used (no cachelines tagged). - * This ensure that all cachelines are tagged with 'active' RMIDs. At - * this point we can start reading values for the new RMID and treat the - * old RMID as the free RMID for the next rotation. - * - * Return %true or %false depending on whether we did any rotating. - */ -static bool __intel_cqm_rmid_rotate(void) -{ - struct perf_event *group, *start = NULL; - unsigned int threshold_limit; - unsigned int nr_needed = 0; - unsigned int nr_available; - bool rotated = false; - - mutex_lock(&cache_mutex); - -again: - /* - * Fast path through this function if there are no groups and no - * RMIDs that need cleaning. - */ - if (list_empty(&cache_groups) && list_empty(&cqm_rmid_limbo_lru)) - goto out; - - list_for_each_entry(group, &cache_groups, hw.cqm_groups_entry) { - if (!__rmid_valid(group->hw.cqm_rmid)) { - if (!start) - start = group; - nr_needed++; - } - } - - /* - * We have some event groups, but they all have RMIDs assigned - * and no RMIDs need cleaning. - */ - if (!nr_needed && list_empty(&cqm_rmid_limbo_lru)) - goto out; - - if (!nr_needed) - goto stabilize; - - /* - * We have more event groups without RMIDs than available RMIDs, - * or we have event groups that conflict with the ones currently - * scheduled. - * - * We force deallocate the rmid of the group at the head of - * cache_groups. The first event group without an RMID then gets - * assigned intel_cqm_rotation_rmid. This ensures we always make - * forward progress. - * - * Rotate the cache_groups list so the previous head is now the - * tail. - */ - __intel_cqm_pick_and_rotate(start); - - /* - * If the rotation is going to succeed, reduce the threshold so - * that we don't needlessly reuse dirty RMIDs. - */ - if (__rmid_valid(intel_cqm_rotation_rmid)) { - intel_cqm_xchg_rmid(start, intel_cqm_rotation_rmid); - intel_cqm_rotation_rmid = __get_rmid(); - - intel_cqm_sched_out_conflicting_events(start); - - if (__intel_cqm_threshold) - __intel_cqm_threshold--; - } - - rotated = true; - -stabilize: - /* - * We now need to stablize the RMID we freed above (if any) to - * ensure that the next time we rotate we have an RMID with zero - * occupancy value. - * - * Alternatively, if we didn't need to perform any rotation, - * we'll have a bunch of RMIDs in limbo that need stabilizing. - */ - threshold_limit = __intel_cqm_max_threshold / cqm_l3_scale; - - while (intel_cqm_rmid_stabilize(&nr_available) && - __intel_cqm_threshold < threshold_limit) { - unsigned int steal_limit; - - /* - * Don't spin if nobody is actively waiting for an RMID, - * the rotation worker will be kicked as soon as an - * event needs an RMID anyway. - */ - if (!nr_needed) - break; - - /* Allow max 25% of RMIDs to be in limbo. */ - steal_limit = (cqm_max_rmid + 1) / 4; - - /* - * We failed to stabilize any RMIDs so our rotation - * logic is now stuck. In order to make forward progress - * we have a few options: - * - * 1. rotate ("steal") another RMID - * 2. increase the threshold - * 3. do nothing - * - * We do both of 1. and 2. until we hit the steal limit. - * - * The steal limit prevents all RMIDs ending up on the - * limbo list. This can happen if every RMID has a - * non-zero occupancy above threshold_limit, and the - * occupancy values aren't dropping fast enough. - * - * Note that there is prioritisation at work here - we'd - * rather increase the number of RMIDs on the limbo list - * than increase the threshold, because increasing the - * threshold skews the event data (because we reuse - * dirty RMIDs) - threshold bumps are a last resort. - */ - if (nr_available < steal_limit) - goto again; - - __intel_cqm_threshold++; - } - -out: - mutex_unlock(&cache_mutex); - return rotated; -} - -static void intel_cqm_rmid_rotate(struct work_struct *work); - -static DECLARE_DELAYED_WORK(intel_cqm_rmid_work, intel_cqm_rmid_rotate); - -static struct pmu intel_cqm_pmu; - -static void intel_cqm_rmid_rotate(struct work_struct *work) -{ - unsigned long delay; - - __intel_cqm_rmid_rotate(); - - delay = msecs_to_jiffies(intel_cqm_pmu.hrtimer_interval_ms); - schedule_delayed_work(&intel_cqm_rmid_work, delay); -} - -static u64 update_sample(unsigned int rmid, u32 evt_type, int first) -{ - struct sample *mbm_current; - u32 vrmid = rmid_2_index(rmid); - u64 val, bytes, shift; - u32 eventid; - - if (evt_type == QOS_MBM_LOCAL_EVENT_ID) { - mbm_current = &mbm_local[vrmid]; - eventid = QOS_MBM_LOCAL_EVENT_ID; - } else { - mbm_current = &mbm_total[vrmid]; - eventid = QOS_MBM_TOTAL_EVENT_ID; - } - - wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid); - rdmsrl(MSR_IA32_QM_CTR, val); - if (val & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL)) - return mbm_current->total_bytes; - - if (first) { - mbm_current->prev_msr = val; - mbm_current->total_bytes = 0; - return mbm_current->total_bytes; - } - - /* - * The h/w guarantees that counters will not overflow - * so long as we poll them at least once per second. - */ - shift = 64 - MBM_CNTR_WIDTH; - bytes = (val << shift) - (mbm_current->prev_msr << shift); - bytes >>= shift; - - bytes *= cqm_l3_scale; - - mbm_current->total_bytes += bytes; - mbm_current->prev_msr = val; - - return mbm_current->total_bytes; -} - -static u64 rmid_read_mbm(unsigned int rmid, u32 evt_type) -{ - return update_sample(rmid, evt_type, 0); -} - -static void __intel_mbm_event_init(void *info) -{ - struct rmid_read *rr = info; - - update_sample(rr->rmid, rr->evt_type, 1); -} - -static void init_mbm_sample(u32 rmid, u32 evt_type) -{ - struct rmid_read rr = { - .rmid = rmid, - .evt_type = evt_type, - .value = ATOMIC64_INIT(0), - }; - - /* on each socket, init sample */ - on_each_cpu_mask(&cqm_cpumask, __intel_mbm_event_init, &rr, 1); -} - -/* - * Find a group and setup RMID. - * - * If we're part of a group, we use the group's RMID. - */ -static void intel_cqm_setup_event(struct perf_event *event, - struct perf_event **group) -{ - struct perf_event *iter; - bool conflict = false; - u32 rmid; - - event->hw.is_group_event = false; - list_for_each_entry(iter, &cache_groups, hw.cqm_groups_entry) { - rmid = iter->hw.cqm_rmid; - - if (__match_event(iter, event)) { - /* All tasks in a group share an RMID */ - event->hw.cqm_rmid = rmid; - *group = iter; - if (is_mbm_event(event->attr.config) && __rmid_valid(rmid)) - init_mbm_sample(rmid, event->attr.config); - return; - } - - /* - * We only care about conflicts for events that are - * actually scheduled in (and hence have a valid RMID). - */ - if (__conflict_event(iter, event) && __rmid_valid(rmid)) - conflict = true; - } - - if (conflict) - rmid = INVALID_RMID; - else - rmid = __get_rmid(); - - if (is_mbm_event(event->attr.config) && __rmid_valid(rmid)) - init_mbm_sample(rmid, event->attr.config); - - event->hw.cqm_rmid = rmid; -} - -static void intel_cqm_event_read(struct perf_event *event) -{ - unsigned long flags; - u32 rmid; - u64 val; - - /* - * Task events are handled by intel_cqm_event_count(). - */ - if (event->cpu == -1) - return; - - raw_spin_lock_irqsave(&cache_lock, flags); - rmid = event->hw.cqm_rmid; - - if (!__rmid_valid(rmid)) - goto out; - - if (is_mbm_event(event->attr.config)) - val = rmid_read_mbm(rmid, event->attr.config); - else - val = __rmid_read(rmid); - - /* - * Ignore this reading on error states and do not update the value. - */ - if (val & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL)) - goto out; - - local64_set(&event->count, val); -out: - raw_spin_unlock_irqrestore(&cache_lock, flags); -} - -static void __intel_cqm_event_count(void *info) -{ - struct rmid_read *rr = info; - u64 val; - - val = __rmid_read(rr->rmid); - - if (val & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL)) - return; - - atomic64_add(val, &rr->value); -} - -static inline bool cqm_group_leader(struct perf_event *event) -{ - return !list_empty(&event->hw.cqm_groups_entry); -} - -static void __intel_mbm_event_count(void *info) -{ - struct rmid_read *rr = info; - u64 val; - - val = rmid_read_mbm(rr->rmid, rr->evt_type); - if (val & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL)) - return; - atomic64_add(val, &rr->value); -} - -static enum hrtimer_restart mbm_hrtimer_handle(struct hrtimer *hrtimer) -{ - struct perf_event *iter, *iter1; - int ret = HRTIMER_RESTART; - struct list_head *head; - unsigned long flags; - u32 grp_rmid; - - /* - * Need to cache_lock as the timer Event Select MSR reads - * can race with the mbm/cqm count() and mbm_init() reads. - */ - raw_spin_lock_irqsave(&cache_lock, flags); - - if (list_empty(&cache_groups)) { - ret = HRTIMER_NORESTART; - goto out; - } - - list_for_each_entry(iter, &cache_groups, hw.cqm_groups_entry) { - grp_rmid = iter->hw.cqm_rmid; - if (!__rmid_valid(grp_rmid)) - continue; - if (is_mbm_event(iter->attr.config)) - update_sample(grp_rmid, iter->attr.config, 0); - - head = &iter->hw.cqm_group_entry; - if (list_empty(head)) - continue; - list_for_each_entry(iter1, head, hw.cqm_group_entry) { - if (!iter1->hw.is_group_event) - break; - if (is_mbm_event(iter1->attr.config)) - update_sample(iter1->hw.cqm_rmid, - iter1->attr.config, 0); - } - } - - hrtimer_forward_now(hrtimer, ms_to_ktime(MBM_CTR_OVERFLOW_TIME)); -out: - raw_spin_unlock_irqrestore(&cache_lock, flags); - - return ret; -} - -static void __mbm_start_timer(void *info) -{ - hrtimer_start(&mbm_timers[pkg_id], ms_to_ktime(MBM_CTR_OVERFLOW_TIME), - HRTIMER_MODE_REL_PINNED); -} - -static void __mbm_stop_timer(void *info) -{ - hrtimer_cancel(&mbm_timers[pkg_id]); -} - -static void mbm_start_timers(void) -{ - on_each_cpu_mask(&cqm_cpumask, __mbm_start_timer, NULL, 1); -} - -static void mbm_stop_timers(void) -{ - on_each_cpu_mask(&cqm_cpumask, __mbm_stop_timer, NULL, 1); -} - -static void mbm_hrtimer_init(void) -{ - struct hrtimer *hr; - int i; - - for (i = 0; i < mbm_socket_max; i++) { - hr = &mbm_timers[i]; - hrtimer_init(hr, CLOCK_MONOTONIC, HRTIMER_MODE_REL); - hr->function = mbm_hrtimer_handle; - } -} - -static u64 intel_cqm_event_count(struct perf_event *event) -{ - unsigned long flags; - struct rmid_read rr = { - .evt_type = event->attr.config, - .value = ATOMIC64_INIT(0), - }; - - /* - * We only need to worry about task events. System-wide events - * are handled like usual, i.e. entirely with - * intel_cqm_event_read(). - */ - if (event->cpu != -1) - return __perf_event_count(event); - - /* - * Only the group leader gets to report values except in case of - * multiple events in the same group, we still need to read the - * other events.This stops us - * reporting duplicate values to userspace, and gives us a clear - * rule for which task gets to report the values. - * - * Note that it is impossible to attribute these values to - * specific packages - we forfeit that ability when we create - * task events. - */ - if (!cqm_group_leader(event) && !event->hw.is_group_event) - return 0; - - /* - * Getting up-to-date values requires an SMP IPI which is not - * possible if we're being called in interrupt context. Return - * the cached values instead. - */ - if (unlikely(in_interrupt())) - goto out; - - /* - * Notice that we don't perform the reading of an RMID - * atomically, because we can't hold a spin lock across the - * IPIs. - * - * Speculatively perform the read, since @event might be - * assigned a different (possibly invalid) RMID while we're - * busying performing the IPI calls. It's therefore necessary to - * check @event's RMID afterwards, and if it has changed, - * discard the result of the read. - */ - rr.rmid = ACCESS_ONCE(event->hw.cqm_rmid); - - if (!__rmid_valid(rr.rmid)) - goto out; - - cqm_mask_call(&rr); - - raw_spin_lock_irqsave(&cache_lock, flags); - if (event->hw.cqm_rmid == rr.rmid) - local64_set(&event->count, atomic64_read(&rr.value)); - raw_spin_unlock_irqrestore(&cache_lock, flags); -out: - return __perf_event_count(event); -} - -static void intel_cqm_event_start(struct perf_event *event, int mode) -{ - struct intel_pqr_state *state = this_cpu_ptr(&pqr_state); - u32 rmid = event->hw.cqm_rmid; - - if (!(event->hw.cqm_state & PERF_HES_STOPPED)) - return; - - event->hw.cqm_state &= ~PERF_HES_STOPPED; - - if (state->rmid_usecnt++) { - if (!WARN_ON_ONCE(state->rmid != rmid)) - return; - } else { - WARN_ON_ONCE(state->rmid); - } - - state->rmid = rmid; - wrmsr(MSR_IA32_PQR_ASSOC, rmid, state->closid); -} - -static void intel_cqm_event_stop(struct perf_event *event, int mode) -{ - struct intel_pqr_state *state = this_cpu_ptr(&pqr_state); - - if (event->hw.cqm_state & PERF_HES_STOPPED) - return; - - event->hw.cqm_state |= PERF_HES_STOPPED; - - intel_cqm_event_read(event); - - if (!--state->rmid_usecnt) { - state->rmid = 0; - wrmsr(MSR_IA32_PQR_ASSOC, 0, state->closid); - } else { - WARN_ON_ONCE(!state->rmid); - } -} - -static int intel_cqm_event_add(struct perf_event *event, int mode) -{ - unsigned long flags; - u32 rmid; - - raw_spin_lock_irqsave(&cache_lock, flags); - - event->hw.cqm_state = PERF_HES_STOPPED; - rmid = event->hw.cqm_rmid; - - if (__rmid_valid(rmid) && (mode & PERF_EF_START)) - intel_cqm_event_start(event, mode); - - raw_spin_unlock_irqrestore(&cache_lock, flags); - - return 0; -} - -static void intel_cqm_event_destroy(struct perf_event *event) -{ - struct perf_event *group_other = NULL; - unsigned long flags; - - mutex_lock(&cache_mutex); - /* - * Hold the cache_lock as mbm timer handlers could be - * scanning the list of events. - */ - raw_spin_lock_irqsave(&cache_lock, flags); - - /* - * If there's another event in this group... - */ - if (!list_empty(&event->hw.cqm_group_entry)) { - group_other = list_first_entry(&event->hw.cqm_group_entry, - struct perf_event, - hw.cqm_group_entry); - list_del(&event->hw.cqm_group_entry); - } - - /* - * And we're the group leader.. - */ - if (cqm_group_leader(event)) { - /* - * If there was a group_other, make that leader, otherwise - * destroy the group and return the RMID. - */ - if (group_other) { - list_replace(&event->hw.cqm_groups_entry, - &group_other->hw.cqm_groups_entry); - } else { - u32 rmid = event->hw.cqm_rmid; - - if (__rmid_valid(rmid)) - __put_rmid(rmid); - list_del(&event->hw.cqm_groups_entry); - } - } - - raw_spin_unlock_irqrestore(&cache_lock, flags); - - /* - * Stop the mbm overflow timers when the last event is destroyed. - */ - if (mbm_enabled && list_empty(&cache_groups)) - mbm_stop_timers(); - - mutex_unlock(&cache_mutex); -} - -static int intel_cqm_event_init(struct perf_event *event) -{ - struct perf_event *group = NULL; - bool rotate = false; - unsigned long flags; - - if (event->attr.type != intel_cqm_pmu.type) - return -ENOENT; - - if ((event->attr.config < QOS_L3_OCCUP_EVENT_ID) || - (event->attr.config > QOS_MBM_LOCAL_EVENT_ID)) - return -EINVAL; - - if ((is_cqm_event(event->attr.config) && !cqm_enabled) || - (is_mbm_event(event->attr.config) && !mbm_enabled)) - return -EINVAL; - - /* unsupported modes and filters */ - if (event->attr.exclude_user || - event->attr.exclude_kernel || - event->attr.exclude_hv || - event->attr.exclude_idle || - event->attr.exclude_host || - event->attr.exclude_guest || - event->attr.sample_period) /* no sampling */ - return -EINVAL; - - INIT_LIST_HEAD(&event->hw.cqm_group_entry); - INIT_LIST_HEAD(&event->hw.cqm_groups_entry); - - event->destroy = intel_cqm_event_destroy; - - mutex_lock(&cache_mutex); - - /* - * Start the mbm overflow timers when the first event is created. - */ - if (mbm_enabled && list_empty(&cache_groups)) - mbm_start_timers(); - - /* Will also set rmid */ - intel_cqm_setup_event(event, &group); - - /* - * Hold the cache_lock as mbm timer handlers be - * scanning the list of events. - */ - raw_spin_lock_irqsave(&cache_lock, flags); - - if (group) { - list_add_tail(&event->hw.cqm_group_entry, - &group->hw.cqm_group_entry); - } else { - list_add_tail(&event->hw.cqm_groups_entry, - &cache_groups); - - /* - * All RMIDs are either in use or have recently been - * used. Kick the rotation worker to clean/free some. - * - * We only do this for the group leader, rather than for - * every event in a group to save on needless work. - */ - if (!__rmid_valid(event->hw.cqm_rmid)) - rotate = true; - } - - raw_spin_unlock_irqrestore(&cache_lock, flags); - mutex_unlock(&cache_mutex); - - if (rotate) - schedule_delayed_work(&intel_cqm_rmid_work, 0); - - return 0; -} - -EVENT_ATTR_STR(llc_occupancy, intel_cqm_llc, "event=0x01"); -EVENT_ATTR_STR(llc_occupancy.per-pkg, intel_cqm_llc_pkg, "1"); -EVENT_ATTR_STR(llc_occupancy.unit, intel_cqm_llc_unit, "Bytes"); -EVENT_ATTR_STR(llc_occupancy.scale, intel_cqm_llc_scale, NULL); -EVENT_ATTR_STR(llc_occupancy.snapshot, intel_cqm_llc_snapshot, "1"); - -EVENT_ATTR_STR(total_bytes, intel_cqm_total_bytes, "event=0x02"); -EVENT_ATTR_STR(total_bytes.per-pkg, intel_cqm_total_bytes_pkg, "1"); -EVENT_ATTR_STR(total_bytes.unit, intel_cqm_total_bytes_unit, "MB"); -EVENT_ATTR_STR(total_bytes.scale, intel_cqm_total_bytes_scale, "1e-6"); - -EVENT_ATTR_STR(local_bytes, intel_cqm_local_bytes, "event=0x03"); -EVENT_ATTR_STR(local_bytes.per-pkg, intel_cqm_local_bytes_pkg, "1"); -EVENT_ATTR_STR(local_bytes.unit, intel_cqm_local_bytes_unit, "MB"); -EVENT_ATTR_STR(local_bytes.scale, intel_cqm_local_bytes_scale, "1e-6"); - -static struct attribute *intel_cqm_events_attr[] = { - EVENT_PTR(intel_cqm_llc), - EVENT_PTR(intel_cqm_llc_pkg), - EVENT_PTR(intel_cqm_llc_unit), - EVENT_PTR(intel_cqm_llc_scale), - EVENT_PTR(intel_cqm_llc_snapshot), - NULL, -}; - -static struct attribute *intel_mbm_events_attr[] = { - EVENT_PTR(intel_cqm_total_bytes), - EVENT_PTR(intel_cqm_local_bytes), - EVENT_PTR(intel_cqm_total_bytes_pkg), - EVENT_PTR(intel_cqm_local_bytes_pkg), - EVENT_PTR(intel_cqm_total_bytes_unit), - EVENT_PTR(intel_cqm_local_bytes_unit), - EVENT_PTR(intel_cqm_total_bytes_scale), - EVENT_PTR(intel_cqm_local_bytes_scale), - NULL, -}; - -static struct attribute *intel_cmt_mbm_events_attr[] = { - EVENT_PTR(intel_cqm_llc), - EVENT_PTR(intel_cqm_total_bytes), - EVENT_PTR(intel_cqm_local_bytes), - EVENT_PTR(intel_cqm_llc_pkg), - EVENT_PTR(intel_cqm_total_bytes_pkg), - EVENT_PTR(intel_cqm_local_bytes_pkg), - EVENT_PTR(intel_cqm_llc_unit), - EVENT_PTR(intel_cqm_total_bytes_unit), - EVENT_PTR(intel_cqm_local_bytes_unit), - EVENT_PTR(intel_cqm_llc_scale), - EVENT_PTR(intel_cqm_total_bytes_scale), - EVENT_PTR(intel_cqm_local_bytes_scale), - EVENT_PTR(intel_cqm_llc_snapshot), - NULL, -}; - -static struct attribute_group intel_cqm_events_group = { - .name = "events", - .attrs = NULL, -}; - -PMU_FORMAT_ATTR(event, "config:0-7"); -static struct attribute *intel_cqm_formats_attr[] = { - &format_attr_event.attr, - NULL, -}; - -static struct attribute_group intel_cqm_format_group = { - .name = "format", - .attrs = intel_cqm_formats_attr, -}; - -static ssize_t -max_recycle_threshold_show(struct device *dev, struct device_attribute *attr, - char *page) -{ - ssize_t rv; - - mutex_lock(&cache_mutex); - rv = snprintf(page, PAGE_SIZE-1, "%u\n", __intel_cqm_max_threshold); - mutex_unlock(&cache_mutex); - - return rv; -} - -static ssize_t -max_recycle_threshold_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) -{ - unsigned int bytes, cachelines; - int ret; - - ret = kstrtouint(buf, 0, &bytes); - if (ret) - return ret; - - mutex_lock(&cache_mutex); - - __intel_cqm_max_threshold = bytes; - cachelines = bytes / cqm_l3_scale; - - /* - * The new maximum takes effect immediately. - */ - if (__intel_cqm_threshold > cachelines) - __intel_cqm_threshold = cachelines; - - mutex_unlock(&cache_mutex); - - return count; -} - -static DEVICE_ATTR_RW(max_recycle_threshold); - -static struct attribute *intel_cqm_attrs[] = { - &dev_attr_max_recycle_threshold.attr, - NULL, -}; - -static const struct attribute_group intel_cqm_group = { - .attrs = intel_cqm_attrs, -}; - -static const struct attribute_group *intel_cqm_attr_groups[] = { - &intel_cqm_events_group, - &intel_cqm_format_group, - &intel_cqm_group, - NULL, -}; - -static struct pmu intel_cqm_pmu = { - .hrtimer_interval_ms = RMID_DEFAULT_QUEUE_TIME, - .attr_groups = intel_cqm_attr_groups, - .task_ctx_nr = perf_sw_context, - .event_init = intel_cqm_event_init, - .add = intel_cqm_event_add, - .del = intel_cqm_event_stop, - .start = intel_cqm_event_start, - .stop = intel_cqm_event_stop, - .read = intel_cqm_event_read, - .count = intel_cqm_event_count, -}; - -static inline void cqm_pick_event_reader(int cpu) -{ - int reader; - - /* First online cpu in package becomes the reader */ - reader = cpumask_any_and(&cqm_cpumask, topology_core_cpumask(cpu)); - if (reader >= nr_cpu_ids) - cpumask_set_cpu(cpu, &cqm_cpumask); -} - -static int intel_cqm_cpu_starting(unsigned int cpu) -{ - struct intel_pqr_state *state = &per_cpu(pqr_state, cpu); - struct cpuinfo_x86 *c = &cpu_data(cpu); - - state->rmid = 0; - state->closid = 0; - state->rmid_usecnt = 0; - - WARN_ON(c->x86_cache_max_rmid != cqm_max_rmid); - WARN_ON(c->x86_cache_occ_scale != cqm_l3_scale); - - cqm_pick_event_reader(cpu); - return 0; -} - -static int intel_cqm_cpu_exit(unsigned int cpu) -{ - int target; - - /* Is @cpu the current cqm reader for this package ? */ - if (!cpumask_test_and_clear_cpu(cpu, &cqm_cpumask)) - return 0; - - /* Find another online reader in this package */ - target = cpumask_any_but(topology_core_cpumask(cpu), cpu); - - if (target < nr_cpu_ids) - cpumask_set_cpu(target, &cqm_cpumask); - - return 0; -} - -static const struct x86_cpu_id intel_cqm_match[] = { - { .vendor = X86_VENDOR_INTEL, .feature = X86_FEATURE_CQM_OCCUP_LLC }, - {} -}; - -static void mbm_cleanup(void) -{ - if (!mbm_enabled) - return; - - kfree(mbm_local); - kfree(mbm_total); - mbm_enabled = false; -} - -static const struct x86_cpu_id intel_mbm_local_match[] = { - { .vendor = X86_VENDOR_INTEL, .feature = X86_FEATURE_CQM_MBM_LOCAL }, - {} -}; - -static const struct x86_cpu_id intel_mbm_total_match[] = { - { .vendor = X86_VENDOR_INTEL, .feature = X86_FEATURE_CQM_MBM_TOTAL }, - {} -}; - -static int intel_mbm_init(void) -{ - int ret = 0, array_size, maxid = cqm_max_rmid + 1; - - mbm_socket_max = topology_max_packages(); - array_size = sizeof(struct sample) * maxid * mbm_socket_max; - mbm_local = kmalloc(array_size, GFP_KERNEL); - if (!mbm_local) - return -ENOMEM; - - mbm_total = kmalloc(array_size, GFP_KERNEL); - if (!mbm_total) { - ret = -ENOMEM; - goto out; - } - - array_size = sizeof(struct hrtimer) * mbm_socket_max; - mbm_timers = kmalloc(array_size, GFP_KERNEL); - if (!mbm_timers) { - ret = -ENOMEM; - goto out; - } - mbm_hrtimer_init(); - -out: - if (ret) - mbm_cleanup(); - - return ret; -} - -static int __init intel_cqm_init(void) -{ - char *str = NULL, scale[20]; - int cpu, ret; - - if (x86_match_cpu(intel_cqm_match)) - cqm_enabled = true; - - if (x86_match_cpu(intel_mbm_local_match) && - x86_match_cpu(intel_mbm_total_match)) - mbm_enabled = true; - - if (!cqm_enabled && !mbm_enabled) - return -ENODEV; - - cqm_l3_scale = boot_cpu_data.x86_cache_occ_scale; - - /* - * It's possible that not all resources support the same number - * of RMIDs. Instead of making scheduling much more complicated - * (where we have to match a task's RMID to a cpu that supports - * that many RMIDs) just find the minimum RMIDs supported across - * all cpus. - * - * Also, check that the scales match on all cpus. - */ - cpus_read_lock(); - for_each_online_cpu(cpu) { - struct cpuinfo_x86 *c = &cpu_data(cpu); - - if (c->x86_cache_max_rmid < cqm_max_rmid) - cqm_max_rmid = c->x86_cache_max_rmid; - - if (c->x86_cache_occ_scale != cqm_l3_scale) { - pr_err("Multiple LLC scale values, disabling\n"); - ret = -EINVAL; - goto out; - } - } - - /* - * A reasonable upper limit on the max threshold is the number - * of lines tagged per RMID if all RMIDs have the same number of - * lines tagged in the LLC. - * - * For a 35MB LLC and 56 RMIDs, this is ~1.8% of the LLC. - */ - __intel_cqm_max_threshold = - boot_cpu_data.x86_cache_size * 1024 / (cqm_max_rmid + 1); - - snprintf(scale, sizeof(scale), "%u", cqm_l3_scale); - str = kstrdup(scale, GFP_KERNEL); - if (!str) { - ret = -ENOMEM; - goto out; - } - - event_attr_intel_cqm_llc_scale.event_str = str; - - ret = intel_cqm_setup_rmid_cache(); - if (ret) - goto out; - - if (mbm_enabled) - ret = intel_mbm_init(); - if (ret && !cqm_enabled) - goto out; - - if (cqm_enabled && mbm_enabled) - intel_cqm_events_group.attrs = intel_cmt_mbm_events_attr; - else if (!cqm_enabled && mbm_enabled) - intel_cqm_events_group.attrs = intel_mbm_events_attr; - else if (cqm_enabled && !mbm_enabled) - intel_cqm_events_group.attrs = intel_cqm_events_attr; - - ret = perf_pmu_register(&intel_cqm_pmu, "intel_cqm", -1); - if (ret) { - pr_err("Intel CQM perf registration failed: %d\n", ret); - goto out; - } - - if (cqm_enabled) - pr_info("Intel CQM monitoring enabled\n"); - if (mbm_enabled) - pr_info("Intel MBM enabled\n"); - - /* - * Setup the hot cpu notifier once we are sure cqm - * is enabled to avoid notifier leak. - */ - cpuhp_setup_state_cpuslocked(CPUHP_AP_PERF_X86_CQM_STARTING, - "perf/x86/cqm:starting", - intel_cqm_cpu_starting, NULL); - cpuhp_setup_state_cpuslocked(CPUHP_AP_PERF_X86_CQM_ONLINE, - "perf/x86/cqm:online", - NULL, intel_cqm_cpu_exit); -out: - cpus_read_unlock(); - - if (ret) { - kfree(str); - cqm_cleanup(); - mbm_cleanup(); - } - - return ret; -} -device_initcall(intel_cqm_init); diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index a322fed5f8ed..e1965e5ff570 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -49,34 +49,47 @@ union intel_x86_pebs_dse { */ #define P(a, b) PERF_MEM_S(a, b) #define OP_LH (P(OP, LOAD) | P(LVL, HIT)) +#define LEVEL(x) P(LVLNUM, x) +#define REM P(REMOTE, REMOTE) #define SNOOP_NONE_MISS (P(SNOOP, NONE) | P(SNOOP, MISS)) /* Version for Sandy Bridge and later */ static u64 pebs_data_source[] = { - P(OP, LOAD) | P(LVL, MISS) | P(LVL, L3) | P(SNOOP, NA),/* 0x00:ukn L3 */ - OP_LH | P(LVL, L1) | P(SNOOP, NONE), /* 0x01: L1 local */ - OP_LH | P(LVL, LFB) | P(SNOOP, NONE), /* 0x02: LFB hit */ - OP_LH | P(LVL, L2) | P(SNOOP, NONE), /* 0x03: L2 hit */ - OP_LH | P(LVL, L3) | P(SNOOP, NONE), /* 0x04: L3 hit */ - OP_LH | P(LVL, L3) | P(SNOOP, MISS), /* 0x05: L3 hit, snoop miss */ - OP_LH | P(LVL, L3) | P(SNOOP, HIT), /* 0x06: L3 hit, snoop hit */ - OP_LH | P(LVL, L3) | P(SNOOP, HITM), /* 0x07: L3 hit, snoop hitm */ - OP_LH | P(LVL, REM_CCE1) | P(SNOOP, HIT), /* 0x08: L3 miss snoop hit */ - OP_LH | P(LVL, REM_CCE1) | P(SNOOP, HITM), /* 0x09: L3 miss snoop hitm*/ - OP_LH | P(LVL, LOC_RAM) | P(SNOOP, HIT), /* 0x0a: L3 miss, shared */ - OP_LH | P(LVL, REM_RAM1) | P(SNOOP, HIT), /* 0x0b: L3 miss, shared */ - OP_LH | P(LVL, LOC_RAM) | SNOOP_NONE_MISS,/* 0x0c: L3 miss, excl */ - OP_LH | P(LVL, REM_RAM1) | SNOOP_NONE_MISS,/* 0x0d: L3 miss, excl */ - OP_LH | P(LVL, IO) | P(SNOOP, NONE), /* 0x0e: I/O */ - OP_LH | P(LVL, UNC) | P(SNOOP, NONE), /* 0x0f: uncached */ + P(OP, LOAD) | P(LVL, MISS) | LEVEL(L3) | P(SNOOP, NA),/* 0x00:ukn L3 */ + OP_LH | P(LVL, L1) | LEVEL(L1) | P(SNOOP, NONE), /* 0x01: L1 local */ + OP_LH | P(LVL, LFB) | LEVEL(LFB) | P(SNOOP, NONE), /* 0x02: LFB hit */ + OP_LH | P(LVL, L2) | LEVEL(L2) | P(SNOOP, NONE), /* 0x03: L2 hit */ + OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, NONE), /* 0x04: L3 hit */ + OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, MISS), /* 0x05: L3 hit, snoop miss */ + OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HIT), /* 0x06: L3 hit, snoop hit */ + OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM), /* 0x07: L3 hit, snoop hitm */ + OP_LH | P(LVL, REM_CCE1) | REM | LEVEL(L3) | P(SNOOP, HIT), /* 0x08: L3 miss snoop hit */ + OP_LH | P(LVL, REM_CCE1) | REM | LEVEL(L3) | P(SNOOP, HITM), /* 0x09: L3 miss snoop hitm*/ + OP_LH | P(LVL, LOC_RAM) | LEVEL(RAM) | P(SNOOP, HIT), /* 0x0a: L3 miss, shared */ + OP_LH | P(LVL, REM_RAM1) | REM | LEVEL(L3) | P(SNOOP, HIT), /* 0x0b: L3 miss, shared */ + OP_LH | P(LVL, LOC_RAM) | LEVEL(RAM) | SNOOP_NONE_MISS, /* 0x0c: L3 miss, excl */ + OP_LH | P(LVL, REM_RAM1) | LEVEL(RAM) | REM | SNOOP_NONE_MISS, /* 0x0d: L3 miss, excl */ + OP_LH | P(LVL, IO) | LEVEL(NA) | P(SNOOP, NONE), /* 0x0e: I/O */ + OP_LH | P(LVL, UNC) | LEVEL(NA) | P(SNOOP, NONE), /* 0x0f: uncached */ }; /* Patch up minor differences in the bits */ void __init intel_pmu_pebs_data_source_nhm(void) { - pebs_data_source[0x05] = OP_LH | P(LVL, L3) | P(SNOOP, HIT); - pebs_data_source[0x06] = OP_LH | P(LVL, L3) | P(SNOOP, HITM); - pebs_data_source[0x07] = OP_LH | P(LVL, L3) | P(SNOOP, HITM); + pebs_data_source[0x05] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HIT); + pebs_data_source[0x06] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM); + pebs_data_source[0x07] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM); +} + +void __init intel_pmu_pebs_data_source_skl(bool pmem) +{ + u64 pmem_or_l4 = pmem ? LEVEL(PMEM) : LEVEL(L4); + + pebs_data_source[0x08] = OP_LH | pmem_or_l4 | P(SNOOP, HIT); + pebs_data_source[0x09] = OP_LH | pmem_or_l4 | REM | P(SNOOP, HIT); + pebs_data_source[0x0b] = OP_LH | LEVEL(RAM) | REM | P(SNOOP, NONE); + pebs_data_source[0x0c] = OP_LH | LEVEL(ANY_CACHE) | REM | P(SNOOPX, FWD); + pebs_data_source[0x0d] = OP_LH | LEVEL(ANY_CACHE) | REM | P(SNOOP, HITM); } static u64 precise_store_data(u64 status) @@ -149,8 +162,6 @@ static u64 load_latency_data(u64 status) { union intel_x86_pebs_dse dse; u64 val; - int model = boot_cpu_data.x86_model; - int fam = boot_cpu_data.x86; dse.val = status; @@ -162,8 +173,7 @@ static u64 load_latency_data(u64 status) /* * Nehalem models do not support TLB, Lock infos */ - if (fam == 0x6 && (model == 26 || model == 30 - || model == 31 || model == 46)) { + if (x86_pmu.pebs_no_tlb) { val |= P(TLB, NA) | P(LOCK, NA); return val; } @@ -1175,7 +1185,7 @@ static void setup_pebs_sample_data(struct perf_event *event, else regs->flags &= ~PERF_EFLAGS_EXACT; - if ((sample_type & PERF_SAMPLE_ADDR) && + if ((sample_type & (PERF_SAMPLE_ADDR | PERF_SAMPLE_PHYS_ADDR)) && x86_pmu.intel_cap.pebs_format >= 1) data->addr = pebs->dla; diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 955457a30197..8a6bbacd17dc 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -109,6 +109,9 @@ enum { X86_BR_ZERO_CALL = 1 << 15,/* zero length call */ X86_BR_CALL_STACK = 1 << 16,/* call stack */ X86_BR_IND_JMP = 1 << 17,/* indirect jump */ + + X86_BR_TYPE_SAVE = 1 << 18,/* indicate to save branch type */ + }; #define X86_BR_PLM (X86_BR_USER | X86_BR_KERNEL) @@ -514,6 +517,7 @@ static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc) cpuc->lbr_entries[i].in_tx = 0; cpuc->lbr_entries[i].abort = 0; cpuc->lbr_entries[i].cycles = 0; + cpuc->lbr_entries[i].type = 0; cpuc->lbr_entries[i].reserved = 0; } cpuc->lbr_stack.nr = i; @@ -600,6 +604,7 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) cpuc->lbr_entries[out].in_tx = in_tx; cpuc->lbr_entries[out].abort = abort; cpuc->lbr_entries[out].cycles = cycles; + cpuc->lbr_entries[out].type = 0; cpuc->lbr_entries[out].reserved = 0; out++; } @@ -677,6 +682,10 @@ static int intel_pmu_setup_sw_lbr_filter(struct perf_event *event) if (br_type & PERF_SAMPLE_BRANCH_CALL) mask |= X86_BR_CALL | X86_BR_ZERO_CALL; + + if (br_type & PERF_SAMPLE_BRANCH_TYPE_SAVE) + mask |= X86_BR_TYPE_SAVE; + /* * stash actual user request into reg, it may * be used by fixup code for some CPU @@ -930,6 +939,43 @@ static int branch_type(unsigned long from, unsigned long to, int abort) return ret; } +#define X86_BR_TYPE_MAP_MAX 16 + +static int branch_map[X86_BR_TYPE_MAP_MAX] = { + PERF_BR_CALL, /* X86_BR_CALL */ + PERF_BR_RET, /* X86_BR_RET */ + PERF_BR_SYSCALL, /* X86_BR_SYSCALL */ + PERF_BR_SYSRET, /* X86_BR_SYSRET */ + PERF_BR_UNKNOWN, /* X86_BR_INT */ + PERF_BR_UNKNOWN, /* X86_BR_IRET */ + PERF_BR_COND, /* X86_BR_JCC */ + PERF_BR_UNCOND, /* X86_BR_JMP */ + PERF_BR_UNKNOWN, /* X86_BR_IRQ */ + PERF_BR_IND_CALL, /* X86_BR_IND_CALL */ + PERF_BR_UNKNOWN, /* X86_BR_ABORT */ + PERF_BR_UNKNOWN, /* X86_BR_IN_TX */ + PERF_BR_UNKNOWN, /* X86_BR_NO_TX */ + PERF_BR_CALL, /* X86_BR_ZERO_CALL */ + PERF_BR_UNKNOWN, /* X86_BR_CALL_STACK */ + PERF_BR_IND, /* X86_BR_IND_JMP */ +}; + +static int +common_branch_type(int type) +{ + int i; + + type >>= 2; /* skip X86_BR_USER and X86_BR_KERNEL */ + + if (type) { + i = __ffs(type); + if (i < X86_BR_TYPE_MAP_MAX) + return branch_map[i]; + } + + return PERF_BR_UNKNOWN; +} + /* * implement actual branch filter based on user demand. * Hardware may not exactly satisfy that request, thus @@ -946,7 +992,8 @@ intel_pmu_lbr_filter(struct cpu_hw_events *cpuc) bool compress = false; /* if sampling all branches, then nothing to filter */ - if ((br_sel & X86_BR_ALL) == X86_BR_ALL) + if (((br_sel & X86_BR_ALL) == X86_BR_ALL) && + ((br_sel & X86_BR_TYPE_SAVE) != X86_BR_TYPE_SAVE)) return; for (i = 0; i < cpuc->lbr_stack.nr; i++) { @@ -967,6 +1014,9 @@ intel_pmu_lbr_filter(struct cpu_hw_events *cpuc) cpuc->lbr_entries[i].from = 0; compress = true; } + + if ((br_sel & X86_BR_TYPE_SAVE) == X86_BR_TYPE_SAVE) + cpuc->lbr_entries[i].type = common_branch_type(type); } if (!compress) diff --git a/arch/x86/events/intel/p4.c b/arch/x86/events/intel/p4.c index eb0533558c2b..d32c0eed38ca 100644 --- a/arch/x86/events/intel/p4.c +++ b/arch/x86/events/intel/p4.c @@ -587,7 +587,7 @@ static __initconst const u64 p4_hw_cache_event_ids * P4_CONFIG_ALIASABLE or bits for P4_PEBS_METRIC, they are * either up to date automatically or not applicable at all. */ -struct p4_event_alias { +static struct p4_event_alias { u64 original; u64 alternative; } p4_event_aliases[] = { diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c index ae8324d65e61..81fd41d5a0d9 100644 --- a/arch/x86/events/intel/pt.c +++ b/arch/x86/events/intel/pt.c @@ -471,8 +471,9 @@ static void pt_config(struct perf_event *event) struct pt *pt = this_cpu_ptr(&pt_ctx); u64 reg; - if (!event->hw.itrace_started) { - event->hw.itrace_started = 1; + /* First round: clear STATUS, in particular the PSB byte counter. */ + if (!event->hw.config) { + perf_event_itrace_started(event); wrmsrl(MSR_IA32_RTIT_STATUS, 0); } diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c index a45e2114a846..8e2457cb6b4a 100644 --- a/arch/x86/events/intel/rapl.c +++ b/arch/x86/events/intel/rapl.c @@ -559,7 +559,7 @@ static struct attribute_group rapl_pmu_format_group = { .attrs = rapl_formats_attr, }; -const struct attribute_group *rapl_attr_groups[] = { +static const struct attribute_group *rapl_attr_groups[] = { &rapl_pmu_attr_group, &rapl_pmu_format_group, &rapl_pmu_events_group, diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 44ec523287f6..1c5390f1cf09 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -721,7 +721,7 @@ static struct attribute *uncore_pmu_attrs[] = { NULL, }; -static struct attribute_group uncore_pmu_attr_group = { +static const struct attribute_group uncore_pmu_attr_group = { .attrs = uncore_pmu_attrs, }; diff --git a/arch/x86/events/intel/uncore_nhmex.c b/arch/x86/events/intel/uncore_nhmex.c index cda569332005..6a5cbe90f859 100644 --- a/arch/x86/events/intel/uncore_nhmex.c +++ b/arch/x86/events/intel/uncore_nhmex.c @@ -272,7 +272,7 @@ static struct attribute *nhmex_uncore_ubox_formats_attr[] = { NULL, }; -static struct attribute_group nhmex_uncore_ubox_format_group = { +static const struct attribute_group nhmex_uncore_ubox_format_group = { .name = "format", .attrs = nhmex_uncore_ubox_formats_attr, }; @@ -299,7 +299,7 @@ static struct attribute *nhmex_uncore_cbox_formats_attr[] = { NULL, }; -static struct attribute_group nhmex_uncore_cbox_format_group = { +static const struct attribute_group nhmex_uncore_cbox_format_group = { .name = "format", .attrs = nhmex_uncore_cbox_formats_attr, }; @@ -407,7 +407,7 @@ static struct attribute *nhmex_uncore_bbox_formats_attr[] = { NULL, }; -static struct attribute_group nhmex_uncore_bbox_format_group = { +static const struct attribute_group nhmex_uncore_bbox_format_group = { .name = "format", .attrs = nhmex_uncore_bbox_formats_attr, }; @@ -484,7 +484,7 @@ static struct attribute *nhmex_uncore_sbox_formats_attr[] = { NULL, }; -static struct attribute_group nhmex_uncore_sbox_format_group = { +static const struct attribute_group nhmex_uncore_sbox_format_group = { .name = "format", .attrs = nhmex_uncore_sbox_formats_attr, }; @@ -898,7 +898,7 @@ static struct attribute *nhmex_uncore_mbox_formats_attr[] = { NULL, }; -static struct attribute_group nhmex_uncore_mbox_format_group = { +static const struct attribute_group nhmex_uncore_mbox_format_group = { .name = "format", .attrs = nhmex_uncore_mbox_formats_attr, }; @@ -1163,7 +1163,7 @@ static struct attribute *nhmex_uncore_rbox_formats_attr[] = { NULL, }; -static struct attribute_group nhmex_uncore_rbox_format_group = { +static const struct attribute_group nhmex_uncore_rbox_format_group = { .name = "format", .attrs = nhmex_uncore_rbox_formats_attr, }; diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index a3dcc12bef4a..db1127ce685e 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -130,7 +130,7 @@ static struct attribute *snb_uncore_formats_attr[] = { NULL, }; -static struct attribute_group snb_uncore_format_group = { +static const struct attribute_group snb_uncore_format_group = { .name = "format", .attrs = snb_uncore_formats_attr, }; @@ -289,7 +289,7 @@ static struct attribute *snb_uncore_imc_formats_attr[] = { NULL, }; -static struct attribute_group snb_uncore_imc_format_group = { +static const struct attribute_group snb_uncore_imc_format_group = { .name = "format", .attrs = snb_uncore_imc_formats_attr, }; @@ -769,7 +769,7 @@ static struct attribute *nhm_uncore_formats_attr[] = { NULL, }; -static struct attribute_group nhm_uncore_format_group = { +static const struct attribute_group nhm_uncore_format_group = { .name = "format", .attrs = nhm_uncore_formats_attr, }; diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index dae2fedc1601..db1fe377e6dd 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -316,7 +316,7 @@ #define SKX_UPI_PCI_PMON_CTL0 0x350 #define SKX_UPI_PCI_PMON_CTR0 0x318 #define SKX_UPI_PCI_PMON_BOX_CTL 0x378 -#define SKX_PMON_CTL_UMASK_EXT 0xff +#define SKX_UPI_CTL_UMASK_EXT 0xffefff /* SKX M2M */ #define SKX_M2M_PCI_PMON_CTL0 0x228 @@ -328,7 +328,7 @@ DEFINE_UNCORE_FORMAT_ATTR(event2, event, "config:0-6"); DEFINE_UNCORE_FORMAT_ATTR(event_ext, event, "config:0-7,21"); DEFINE_UNCORE_FORMAT_ATTR(use_occ_ctr, use_occ_ctr, "config:7"); DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15"); -DEFINE_UNCORE_FORMAT_ATTR(umask_ext, umask, "config:8-15,32-39"); +DEFINE_UNCORE_FORMAT_ATTR(umask_ext, umask, "config:8-15,32-43,45-55"); DEFINE_UNCORE_FORMAT_ATTR(qor, qor, "config:16"); DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18"); DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19"); @@ -351,7 +351,6 @@ DEFINE_UNCORE_FORMAT_ATTR(filter_cid, filter_cid, "config1:5"); DEFINE_UNCORE_FORMAT_ATTR(filter_link, filter_link, "config1:5-8"); DEFINE_UNCORE_FORMAT_ATTR(filter_link2, filter_link, "config1:6-8"); DEFINE_UNCORE_FORMAT_ATTR(filter_link3, filter_link, "config1:12"); -DEFINE_UNCORE_FORMAT_ATTR(filter_link4, filter_link, "config1:9-12"); DEFINE_UNCORE_FORMAT_ATTR(filter_nid, filter_nid, "config1:10-17"); DEFINE_UNCORE_FORMAT_ATTR(filter_nid2, filter_nid, "config1:32-47"); DEFINE_UNCORE_FORMAT_ATTR(filter_state, filter_state, "config1:18-22"); @@ -603,27 +602,27 @@ static struct uncore_event_desc snbep_uncore_qpi_events[] = { { /* end: all zeroes */ }, }; -static struct attribute_group snbep_uncore_format_group = { +static const struct attribute_group snbep_uncore_format_group = { .name = "format", .attrs = snbep_uncore_formats_attr, }; -static struct attribute_group snbep_uncore_ubox_format_group = { +static const struct attribute_group snbep_uncore_ubox_format_group = { .name = "format", .attrs = snbep_uncore_ubox_formats_attr, }; -static struct attribute_group snbep_uncore_cbox_format_group = { +static const struct attribute_group snbep_uncore_cbox_format_group = { .name = "format", .attrs = snbep_uncore_cbox_formats_attr, }; -static struct attribute_group snbep_uncore_pcu_format_group = { +static const struct attribute_group snbep_uncore_pcu_format_group = { .name = "format", .attrs = snbep_uncore_pcu_formats_attr, }; -static struct attribute_group snbep_uncore_qpi_format_group = { +static const struct attribute_group snbep_uncore_qpi_format_group = { .name = "format", .attrs = snbep_uncore_qpi_formats_attr, }; @@ -1432,27 +1431,27 @@ static struct attribute *ivbep_uncore_qpi_formats_attr[] = { NULL, }; -static struct attribute_group ivbep_uncore_format_group = { +static const struct attribute_group ivbep_uncore_format_group = { .name = "format", .attrs = ivbep_uncore_formats_attr, }; -static struct attribute_group ivbep_uncore_ubox_format_group = { +static const struct attribute_group ivbep_uncore_ubox_format_group = { .name = "format", .attrs = ivbep_uncore_ubox_formats_attr, }; -static struct attribute_group ivbep_uncore_cbox_format_group = { +static const struct attribute_group ivbep_uncore_cbox_format_group = { .name = "format", .attrs = ivbep_uncore_cbox_formats_attr, }; -static struct attribute_group ivbep_uncore_pcu_format_group = { +static const struct attribute_group ivbep_uncore_pcu_format_group = { .name = "format", .attrs = ivbep_uncore_pcu_formats_attr, }; -static struct attribute_group ivbep_uncore_qpi_format_group = { +static const struct attribute_group ivbep_uncore_qpi_format_group = { .name = "format", .attrs = ivbep_uncore_qpi_formats_attr, }; @@ -1888,7 +1887,7 @@ static struct attribute *knl_uncore_ubox_formats_attr[] = { NULL, }; -static struct attribute_group knl_uncore_ubox_format_group = { +static const struct attribute_group knl_uncore_ubox_format_group = { .name = "format", .attrs = knl_uncore_ubox_formats_attr, }; @@ -1928,7 +1927,7 @@ static struct attribute *knl_uncore_cha_formats_attr[] = { NULL, }; -static struct attribute_group knl_uncore_cha_format_group = { +static const struct attribute_group knl_uncore_cha_format_group = { .name = "format", .attrs = knl_uncore_cha_formats_attr, }; @@ -2038,7 +2037,7 @@ static struct attribute *knl_uncore_pcu_formats_attr[] = { NULL, }; -static struct attribute_group knl_uncore_pcu_format_group = { +static const struct attribute_group knl_uncore_pcu_format_group = { .name = "format", .attrs = knl_uncore_pcu_formats_attr, }; @@ -2188,7 +2187,7 @@ static struct attribute *knl_uncore_irp_formats_attr[] = { NULL, }; -static struct attribute_group knl_uncore_irp_format_group = { +static const struct attribute_group knl_uncore_irp_format_group = { .name = "format", .attrs = knl_uncore_irp_formats_attr, }; @@ -2386,7 +2385,7 @@ static struct attribute *hswep_uncore_ubox_formats_attr[] = { NULL, }; -static struct attribute_group hswep_uncore_ubox_format_group = { +static const struct attribute_group hswep_uncore_ubox_format_group = { .name = "format", .attrs = hswep_uncore_ubox_formats_attr, }; @@ -2440,7 +2439,7 @@ static struct attribute *hswep_uncore_cbox_formats_attr[] = { NULL, }; -static struct attribute_group hswep_uncore_cbox_format_group = { +static const struct attribute_group hswep_uncore_cbox_format_group = { .name = "format", .attrs = hswep_uncore_cbox_formats_attr, }; @@ -2622,7 +2621,7 @@ static struct attribute *hswep_uncore_sbox_formats_attr[] = { NULL, }; -static struct attribute_group hswep_uncore_sbox_format_group = { +static const struct attribute_group hswep_uncore_sbox_format_group = { .name = "format", .attrs = hswep_uncore_sbox_formats_attr, }; @@ -3302,7 +3301,6 @@ static struct attribute *skx_uncore_cha_formats_attr[] = { &format_attr_inv.attr, &format_attr_thresh8.attr, &format_attr_filter_tid4.attr, - &format_attr_filter_link4.attr, &format_attr_filter_state5.attr, &format_attr_filter_rem.attr, &format_attr_filter_loc.attr, @@ -3312,12 +3310,11 @@ static struct attribute *skx_uncore_cha_formats_attr[] = { &format_attr_filter_opc_0.attr, &format_attr_filter_opc_1.attr, &format_attr_filter_nc.attr, - &format_attr_filter_c6.attr, &format_attr_filter_isoc.attr, NULL, }; -static struct attribute_group skx_uncore_chabox_format_group = { +static const struct attribute_group skx_uncore_chabox_format_group = { .name = "format", .attrs = skx_uncore_cha_formats_attr, }; @@ -3333,8 +3330,11 @@ static struct extra_reg skx_uncore_cha_extra_regs[] = { SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4), SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4), SNBEP_CBO_EVENT_EXTRA_REG(0x1134, 0xffff, 0x4), - SNBEP_CBO_EVENT_EXTRA_REG(0x2134, 0xffff, 0x4), - SNBEP_CBO_EVENT_EXTRA_REG(0x8134, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x3134, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x9134, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x35, 0xff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x36, 0xff, 0x8), + EVENT_EXTRA_END }; static u64 skx_cha_filter_mask(int fields) @@ -3347,6 +3347,17 @@ static u64 skx_cha_filter_mask(int fields) mask |= SKX_CHA_MSR_PMON_BOX_FILTER_LINK; if (fields & 0x4) mask |= SKX_CHA_MSR_PMON_BOX_FILTER_STATE; + if (fields & 0x8) { + mask |= SKX_CHA_MSR_PMON_BOX_FILTER_REM; + mask |= SKX_CHA_MSR_PMON_BOX_FILTER_LOC; + mask |= SKX_CHA_MSR_PMON_BOX_FILTER_ALL_OPC; + mask |= SKX_CHA_MSR_PMON_BOX_FILTER_NM; + mask |= SKX_CHA_MSR_PMON_BOX_FILTER_NOT_NM; + mask |= SKX_CHA_MSR_PMON_BOX_FILTER_OPC0; + mask |= SKX_CHA_MSR_PMON_BOX_FILTER_OPC1; + mask |= SKX_CHA_MSR_PMON_BOX_FILTER_NC; + mask |= SKX_CHA_MSR_PMON_BOX_FILTER_ISOC; + } return mask; } @@ -3416,7 +3427,7 @@ static struct attribute *skx_uncore_iio_formats_attr[] = { NULL, }; -static struct attribute_group skx_uncore_iio_format_group = { +static const struct attribute_group skx_uncore_iio_format_group = { .name = "format", .attrs = skx_uncore_iio_formats_attr, }; @@ -3473,7 +3484,7 @@ static struct attribute *skx_uncore_formats_attr[] = { NULL, }; -static struct attribute_group skx_uncore_format_group = { +static const struct attribute_group skx_uncore_format_group = { .name = "format", .attrs = skx_uncore_formats_attr, }; @@ -3492,6 +3503,26 @@ static struct intel_uncore_type skx_uncore_irp = { .format_group = &skx_uncore_format_group, }; +static struct attribute *skx_uncore_pcu_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + &format_attr_occ_invert.attr, + &format_attr_occ_edge_det.attr, + &format_attr_filter_band0.attr, + &format_attr_filter_band1.attr, + &format_attr_filter_band2.attr, + &format_attr_filter_band3.attr, + NULL, +}; + +static struct attribute_group skx_uncore_pcu_format_group = { + .name = "format", + .attrs = skx_uncore_pcu_formats_attr, +}; + static struct intel_uncore_ops skx_uncore_pcu_ops = { IVBEP_UNCORE_MSR_OPS_COMMON_INIT(), .hw_config = hswep_pcu_hw_config, @@ -3510,7 +3541,7 @@ static struct intel_uncore_type skx_uncore_pcu = { .box_ctl = HSWEP_PCU_MSR_PMON_BOX_CTL, .num_shared_regs = 1, .ops = &skx_uncore_pcu_ops, - .format_group = &snbep_uncore_pcu_format_group, + .format_group = &skx_uncore_pcu_format_group, }; static struct intel_uncore_type *skx_msr_uncores[] = { @@ -3574,7 +3605,7 @@ static struct attribute *skx_upi_uncore_formats_attr[] = { NULL, }; -static struct attribute_group skx_upi_uncore_format_group = { +static const struct attribute_group skx_upi_uncore_format_group = { .name = "format", .attrs = skx_upi_uncore_formats_attr, }; @@ -3603,8 +3634,8 @@ static struct intel_uncore_type skx_uncore_upi = { .perf_ctr_bits = 48, .perf_ctr = SKX_UPI_PCI_PMON_CTR0, .event_ctl = SKX_UPI_PCI_PMON_CTL0, - .event_mask = SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK, - .event_mask_ext = SKX_PMON_CTL_UMASK_EXT, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .event_mask_ext = SKX_UPI_CTL_UMASK_EXT, .box_ctl = SKX_UPI_PCI_PMON_BOX_CTL, .ops = &skx_upi_uncore_pci_ops, .format_group = &skx_upi_uncore_format_group, diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 476aec3a4cab..4196f81ec0e1 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -91,7 +91,7 @@ struct amd_nb { (PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_ADDR | \ PERF_SAMPLE_ID | PERF_SAMPLE_CPU | PERF_SAMPLE_STREAM_ID | \ PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER | \ - PERF_SAMPLE_TRANSACTION) + PERF_SAMPLE_TRANSACTION | PERF_SAMPLE_PHYS_ADDR) /* * A debug store configuration. @@ -558,6 +558,7 @@ struct x86_pmu { int attr_rdpmc; struct attribute **format_attrs; struct attribute **event_attrs; + struct attribute **caps_attrs; ssize_t (*events_sysfs_show)(char *page, u64 config); struct attribute **cpu_events; @@ -591,7 +592,8 @@ struct x86_pmu { pebs :1, pebs_active :1, pebs_broken :1, - pebs_prec_dist :1; + pebs_prec_dist :1, + pebs_no_tlb :1; int pebs_record_size; int pebs_buffer_size; void (*drain_pebs)(struct pt_regs *regs); @@ -741,6 +743,8 @@ int x86_reserve_hardware(void); void x86_release_hardware(void); +int x86_pmu_max_precise(void); + void hw_perf_lbr_event_destroy(struct perf_event *event); int x86_setup_perfctr(struct perf_event *event); @@ -947,6 +951,8 @@ void intel_pmu_lbr_init_knl(void); void intel_pmu_pebs_data_source_nhm(void); +void intel_pmu_pebs_data_source_skl(bool pmem); + int intel_pmu_setup_lbr_filter(struct perf_event *event); void intel_pt_interrupt(void); diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index 724153797209..e0bb46c02857 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -226,7 +226,7 @@ static void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, if (ksig->ka.sa.sa_flags & SA_ONSTACK) sp = sigsp(sp, ksig); /* This is the legacy signal stack switching. */ - else if ((regs->ss & 0xffff) != __USER32_DS && + else if (regs->ss != __USER32_DS && !(ksig->ka.sa.sa_flags & SA_RESTORER) && ksig->ka.sa.sa_restorer) sp = (unsigned long) ksig->ka.sa.sa_restorer; diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index 2efc768e4362..72d867f6b518 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -150,8 +150,6 @@ static inline void disable_acpi(void) { } extern int x86_acpi_numa_init(void); #endif /* CONFIG_ACPI_NUMA */ -#define acpi_unlazy_tlb(x) leave_mm(x) - #ifdef CONFIG_ACPI_APEI static inline pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr) { @@ -162,12 +160,13 @@ static inline pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr) * you call efi_mem_attributes() during boot and at runtime, * you could theoretically see different attributes. * - * Since we are yet to see any x86 platforms that require - * anything other than PAGE_KERNEL (some arm64 platforms - * require the equivalent of PAGE_KERNEL_NOCACHE), return that - * until we know differently. + * We are yet to see any x86 platforms that require anything + * other than PAGE_KERNEL (some ARM64 platforms require the + * equivalent of PAGE_KERNEL_NOCACHE). Additionally, if SME + * is active, the ACPI information will not be encrypted, + * so return PAGE_KERNEL_NOENC until we know differently. */ - return PAGE_KERNEL; + return PAGE_KERNEL_NOENC; } #endif diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index 7a9df3beb89b..676ee5807d86 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -74,6 +74,9 @@ # define _ASM_EXTABLE_EX(from, to) \ _ASM_EXTABLE_HANDLE(from, to, ex_handler_ext) +# define _ASM_EXTABLE_REFCOUNT(from, to) \ + _ASM_EXTABLE_HANDLE(from, to, ex_handler_refcount) + # define _ASM_NOKPROBE(entry) \ .pushsection "_kprobe_blacklist","aw" ; \ _ASM_ALIGN ; \ @@ -123,6 +126,9 @@ # define _ASM_EXTABLE_EX(from, to) \ _ASM_EXTABLE_HANDLE(from, to, ex_handler_ext) +# define _ASM_EXTABLE_REFCOUNT(from, to) \ + _ASM_EXTABLE_HANDLE(from, to, ex_handler_refcount) + /* For C file, we already have NOKPROBE_SYMBOL macro */ #endif diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h index 33380b871463..0874ebda3069 100644 --- a/arch/x86/include/asm/atomic.h +++ b/arch/x86/include/asm/atomic.h @@ -197,35 +197,56 @@ static inline int atomic_xchg(atomic_t *v, int new) return xchg(&v->counter, new); } -#define ATOMIC_OP(op) \ -static inline void atomic_##op(int i, atomic_t *v) \ -{ \ - asm volatile(LOCK_PREFIX #op"l %1,%0" \ - : "+m" (v->counter) \ - : "ir" (i) \ - : "memory"); \ +static inline void atomic_and(int i, atomic_t *v) +{ + asm volatile(LOCK_PREFIX "andl %1,%0" + : "+m" (v->counter) + : "ir" (i) + : "memory"); +} + +static inline int atomic_fetch_and(int i, atomic_t *v) +{ + int val = atomic_read(v); + + do { } while (!atomic_try_cmpxchg(v, &val, val & i)); + + return val; } -#define ATOMIC_FETCH_OP(op, c_op) \ -static inline int atomic_fetch_##op(int i, atomic_t *v) \ -{ \ - int val = atomic_read(v); \ - do { \ - } while (!atomic_try_cmpxchg(v, &val, val c_op i)); \ - return val; \ +static inline void atomic_or(int i, atomic_t *v) +{ + asm volatile(LOCK_PREFIX "orl %1,%0" + : "+m" (v->counter) + : "ir" (i) + : "memory"); } -#define ATOMIC_OPS(op, c_op) \ - ATOMIC_OP(op) \ - ATOMIC_FETCH_OP(op, c_op) +static inline int atomic_fetch_or(int i, atomic_t *v) +{ + int val = atomic_read(v); -ATOMIC_OPS(and, &) -ATOMIC_OPS(or , |) -ATOMIC_OPS(xor, ^) + do { } while (!atomic_try_cmpxchg(v, &val, val | i)); -#undef ATOMIC_OPS -#undef ATOMIC_FETCH_OP -#undef ATOMIC_OP + return val; +} + +static inline void atomic_xor(int i, atomic_t *v) +{ + asm volatile(LOCK_PREFIX "xorl %1,%0" + : "+m" (v->counter) + : "ir" (i) + : "memory"); +} + +static inline int atomic_fetch_xor(int i, atomic_t *v) +{ + int val = atomic_read(v); + + do { } while (!atomic_try_cmpxchg(v, &val, val ^ i)); + + return val; +} /** * __atomic_add_unless - add unless the number is already a given value @@ -239,10 +260,12 @@ ATOMIC_OPS(xor, ^) static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u) { int c = atomic_read(v); + do { if (unlikely(c == u)) break; } while (!atomic_try_cmpxchg(v, &c, c + a)); + return c; } diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h index 71d7705fb303..9e206f31ce2a 100644 --- a/arch/x86/include/asm/atomic64_32.h +++ b/arch/x86/include/asm/atomic64_32.h @@ -312,37 +312,70 @@ static inline long long atomic64_dec_if_positive(atomic64_t *v) #undef alternative_atomic64 #undef __alternative_atomic64 -#define ATOMIC64_OP(op, c_op) \ -static inline void atomic64_##op(long long i, atomic64_t *v) \ -{ \ - long long old, c = 0; \ - while ((old = atomic64_cmpxchg(v, c, c c_op i)) != c) \ - c = old; \ +static inline void atomic64_and(long long i, atomic64_t *v) +{ + long long old, c = 0; + + while ((old = atomic64_cmpxchg(v, c, c & i)) != c) + c = old; } -#define ATOMIC64_FETCH_OP(op, c_op) \ -static inline long long atomic64_fetch_##op(long long i, atomic64_t *v) \ -{ \ - long long old, c = 0; \ - while ((old = atomic64_cmpxchg(v, c, c c_op i)) != c) \ - c = old; \ - return old; \ +static inline long long atomic64_fetch_and(long long i, atomic64_t *v) +{ + long long old, c = 0; + + while ((old = atomic64_cmpxchg(v, c, c & i)) != c) + c = old; + + return old; } -ATOMIC64_FETCH_OP(add, +) +static inline void atomic64_or(long long i, atomic64_t *v) +{ + long long old, c = 0; -#define atomic64_fetch_sub(i, v) atomic64_fetch_add(-(i), (v)) + while ((old = atomic64_cmpxchg(v, c, c | i)) != c) + c = old; +} + +static inline long long atomic64_fetch_or(long long i, atomic64_t *v) +{ + long long old, c = 0; + + while ((old = atomic64_cmpxchg(v, c, c | i)) != c) + c = old; + + return old; +} -#define ATOMIC64_OPS(op, c_op) \ - ATOMIC64_OP(op, c_op) \ - ATOMIC64_FETCH_OP(op, c_op) +static inline void atomic64_xor(long long i, atomic64_t *v) +{ + long long old, c = 0; + + while ((old = atomic64_cmpxchg(v, c, c ^ i)) != c) + c = old; +} -ATOMIC64_OPS(and, &) -ATOMIC64_OPS(or, |) -ATOMIC64_OPS(xor, ^) +static inline long long atomic64_fetch_xor(long long i, atomic64_t *v) +{ + long long old, c = 0; + + while ((old = atomic64_cmpxchg(v, c, c ^ i)) != c) + c = old; + + return old; +} -#undef ATOMIC64_OPS -#undef ATOMIC64_FETCH_OP -#undef ATOMIC64_OP +static inline long long atomic64_fetch_add(long long i, atomic64_t *v) +{ + long long old, c = 0; + + while ((old = atomic64_cmpxchg(v, c, c + i)) != c) + c = old; + + return old; +} + +#define atomic64_fetch_sub(i, v) atomic64_fetch_add(-(i), (v)) #endif /* _ASM_X86_ATOMIC64_32_H */ diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h index 6189a433c9a9..5d9de36a2f04 100644 --- a/arch/x86/include/asm/atomic64_64.h +++ b/arch/x86/include/asm/atomic64_64.h @@ -177,7 +177,7 @@ static inline long atomic64_cmpxchg(atomic64_t *v, long old, long new) } #define atomic64_try_cmpxchg atomic64_try_cmpxchg -static __always_inline bool atomic64_try_cmpxchg(atomic64_t *v, long *old, long new) +static __always_inline bool atomic64_try_cmpxchg(atomic64_t *v, s64 *old, long new) { return try_cmpxchg(&v->counter, old, new); } @@ -198,7 +198,7 @@ static inline long atomic64_xchg(atomic64_t *v, long new) */ static inline bool atomic64_add_unless(atomic64_t *v, long a, long u) { - long c = atomic64_read(v); + s64 c = atomic64_read(v); do { if (unlikely(c == u)) return false; @@ -217,7 +217,7 @@ static inline bool atomic64_add_unless(atomic64_t *v, long a, long u) */ static inline long atomic64_dec_if_positive(atomic64_t *v) { - long dec, c = atomic64_read(v); + s64 dec, c = atomic64_read(v); do { dec = c - 1; if (unlikely(dec < 0)) @@ -226,34 +226,55 @@ static inline long atomic64_dec_if_positive(atomic64_t *v) return dec; } -#define ATOMIC64_OP(op) \ -static inline void atomic64_##op(long i, atomic64_t *v) \ -{ \ - asm volatile(LOCK_PREFIX #op"q %1,%0" \ - : "+m" (v->counter) \ - : "er" (i) \ - : "memory"); \ +static inline void atomic64_and(long i, atomic64_t *v) +{ + asm volatile(LOCK_PREFIX "andq %1,%0" + : "+m" (v->counter) + : "er" (i) + : "memory"); } -#define ATOMIC64_FETCH_OP(op, c_op) \ -static inline long atomic64_fetch_##op(long i, atomic64_t *v) \ -{ \ - long val = atomic64_read(v); \ - do { \ - } while (!atomic64_try_cmpxchg(v, &val, val c_op i)); \ - return val; \ +static inline long atomic64_fetch_and(long i, atomic64_t *v) +{ + s64 val = atomic64_read(v); + + do { + } while (!atomic64_try_cmpxchg(v, &val, val & i)); + return val; } -#define ATOMIC64_OPS(op, c_op) \ - ATOMIC64_OP(op) \ - ATOMIC64_FETCH_OP(op, c_op) +static inline void atomic64_or(long i, atomic64_t *v) +{ + asm volatile(LOCK_PREFIX "orq %1,%0" + : "+m" (v->counter) + : "er" (i) + : "memory"); +} -ATOMIC64_OPS(and, &) -ATOMIC64_OPS(or, |) -ATOMIC64_OPS(xor, ^) +static inline long atomic64_fetch_or(long i, atomic64_t *v) +{ + s64 val = atomic64_read(v); -#undef ATOMIC64_OPS -#undef ATOMIC64_FETCH_OP -#undef ATOMIC64_OP + do { + } while (!atomic64_try_cmpxchg(v, &val, val | i)); + return val; +} + +static inline void atomic64_xor(long i, atomic64_t *v) +{ + asm volatile(LOCK_PREFIX "xorq %1,%0" + : "+m" (v->counter) + : "er" (i) + : "memory"); +} + +static inline long atomic64_fetch_xor(long i, atomic64_t *v) +{ + s64 val = atomic64_read(v); + + do { + } while (!atomic64_try_cmpxchg(v, &val, val ^ i)); + return val; +} #endif /* _ASM_X86_ATOMIC64_64_H */ diff --git a/arch/x86/include/asm/cmdline.h b/arch/x86/include/asm/cmdline.h index e01f7f7ccb0c..84ae170bc3d0 100644 --- a/arch/x86/include/asm/cmdline.h +++ b/arch/x86/include/asm/cmdline.h @@ -2,5 +2,7 @@ #define _ASM_X86_CMDLINE_H int cmdline_find_option_bool(const char *cmdline_ptr, const char *option); +int cmdline_find_option(const char *cmdline_ptr, const char *option, + char *buffer, int bufsize); #endif /* _ASM_X86_CMDLINE_H */ diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h index d90296d061e8..b5069e802d5c 100644 --- a/arch/x86/include/asm/cmpxchg.h +++ b/arch/x86/include/asm/cmpxchg.h @@ -157,7 +157,7 @@ extern void __add_wrong_size(void) #define __raw_try_cmpxchg(_ptr, _pold, _new, size, lock) \ ({ \ bool success; \ - __typeof__(_ptr) _old = (_pold); \ + __typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \ __typeof__(*(_ptr)) __old = *_old; \ __typeof__(*(_ptr)) __new = (_new); \ switch (size) { \ diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index ca3c48c0872f..42bbbf0f173d 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -177,7 +177,7 @@ #define X86_FEATURE_PERFCTR_NB ( 6*32+24) /* NB performance counter extensions */ #define X86_FEATURE_BPEXT (6*32+26) /* data breakpoint extension */ #define X86_FEATURE_PTSC ( 6*32+27) /* performance time-stamp counter */ -#define X86_FEATURE_PERFCTR_L2 ( 6*32+28) /* L2 performance counter extensions */ +#define X86_FEATURE_PERFCTR_LLC ( 6*32+28) /* Last Level Cache performance counter extensions */ #define X86_FEATURE_MWAITX ( 6*32+29) /* MWAIT extension (MONITORX/MWAITX) */ /* @@ -196,6 +196,7 @@ #define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ +#define X86_FEATURE_SME ( 7*32+10) /* AMD Secure Memory Encryption */ #define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ #define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */ @@ -286,7 +287,7 @@ #define X86_FEATURE_PAUSEFILTER (15*32+10) /* filtered pause intercept */ #define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */ #define X86_FEATURE_AVIC (15*32+13) /* Virtual Interrupt Controller */ -#define X86_FEATURE_VIRTUAL_VMLOAD_VMSAVE (15*32+15) /* Virtual VMLOAD VMSAVE */ +#define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* Virtual VMSAVE VMLOAD */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */ #define X86_FEATURE_AVX512VBMI (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/ diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index d0a21b12dd58..1a2ba368da39 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -5,6 +5,7 @@ #include <asm/ldt.h> #include <asm/mmu.h> #include <asm/fixmap.h> +#include <asm/irq_vectors.h> #include <linux/smp.h> #include <linux/percpu.h> @@ -22,7 +23,7 @@ static inline void fill_ldt(struct desc_struct *desc, const struct user_desc *in desc->s = 1; desc->dpl = 0x3; desc->p = info->seg_not_present ^ 1; - desc->limit = (info->limit & 0xf0000) >> 16; + desc->limit1 = (info->limit & 0xf0000) >> 16; desc->avl = info->useable; desc->d = info->seg_32bit; desc->g = info->limit_in_pages; @@ -83,33 +84,25 @@ static inline phys_addr_t get_cpu_gdt_paddr(unsigned int cpu) return per_cpu_ptr_to_phys(get_cpu_gdt_rw(cpu)); } -#ifdef CONFIG_X86_64 - static inline void pack_gate(gate_desc *gate, unsigned type, unsigned long func, unsigned dpl, unsigned ist, unsigned seg) { - gate->offset_low = PTR_LOW(func); + gate->offset_low = (u16) func; + gate->bits.p = 1; + gate->bits.dpl = dpl; + gate->bits.zero = 0; + gate->bits.type = type; + gate->offset_middle = (u16) (func >> 16); +#ifdef CONFIG_X86_64 gate->segment = __KERNEL_CS; - gate->ist = ist; - gate->p = 1; - gate->dpl = dpl; - gate->zero0 = 0; - gate->zero1 = 0; - gate->type = type; - gate->offset_middle = PTR_MIDDLE(func); - gate->offset_high = PTR_HIGH(func); -} - + gate->bits.ist = ist; + gate->reserved = 0; + gate->offset_high = (u32) (func >> 32); #else -static inline void pack_gate(gate_desc *gate, unsigned char type, - unsigned long base, unsigned dpl, unsigned flags, - unsigned short seg) -{ - gate->a = (seg << 16) | (base & 0xffff); - gate->b = (base & 0xffff0000) | (((0x80 | type | (dpl << 5)) & 0xff) << 8); -} - + gate->segment = seg; + gate->bits.ist = 0; #endif +} static inline int desc_empty(const void *ptr) { @@ -173,35 +166,22 @@ native_write_gdt_entry(struct desc_struct *gdt, int entry, const void *desc, int memcpy(&gdt[entry], desc, size); } -static inline void pack_descriptor(struct desc_struct *desc, unsigned long base, - unsigned long limit, unsigned char type, - unsigned char flags) -{ - desc->a = ((base & 0xffff) << 16) | (limit & 0xffff); - desc->b = (base & 0xff000000) | ((base & 0xff0000) >> 16) | - (limit & 0x000f0000) | ((type & 0xff) << 8) | - ((flags & 0xf) << 20); - desc->p = 1; -} - - -static inline void set_tssldt_descriptor(void *d, unsigned long addr, unsigned type, unsigned size) +static inline void set_tssldt_descriptor(void *d, unsigned long addr, + unsigned type, unsigned size) { -#ifdef CONFIG_X86_64 - struct ldttss_desc64 *desc = d; + struct ldttss_desc *desc = d; memset(desc, 0, sizeof(*desc)); - desc->limit0 = size & 0xFFFF; - desc->base0 = PTR_LOW(addr); - desc->base1 = PTR_MIDDLE(addr) & 0xFF; + desc->limit0 = (u16) size; + desc->base0 = (u16) addr; + desc->base1 = (addr >> 16) & 0xFF; desc->type = type; desc->p = 1; desc->limit1 = (size >> 16) & 0xF; - desc->base2 = (PTR_MIDDLE(addr) >> 8) & 0xFF; - desc->base3 = PTR_HIGH(addr); -#else - pack_descriptor((struct desc_struct *)d, addr, size, 0x80 | type, 0); + desc->base2 = (addr >> 24) & 0xFF; +#ifdef CONFIG_X86_64 + desc->base3 = (u32) (addr >> 32); #endif } @@ -401,147 +381,20 @@ static inline void set_desc_base(struct desc_struct *desc, unsigned long base) static inline unsigned long get_desc_limit(const struct desc_struct *desc) { - return desc->limit0 | (desc->limit << 16); + return desc->limit0 | (desc->limit1 << 16); } static inline void set_desc_limit(struct desc_struct *desc, unsigned long limit) { desc->limit0 = limit & 0xffff; - desc->limit = (limit >> 16) & 0xf; -} - -#ifdef CONFIG_X86_64 -static inline void set_nmi_gate(int gate, void *addr) -{ - gate_desc s; - - pack_gate(&s, GATE_INTERRUPT, (unsigned long)addr, 0, 0, __KERNEL_CS); - write_idt_entry(debug_idt_table, gate, &s); + desc->limit1 = (limit >> 16) & 0xf; } -#endif -#ifdef CONFIG_TRACING -extern struct desc_ptr trace_idt_descr; -extern gate_desc trace_idt_table[]; -static inline void write_trace_idt_entry(int entry, const gate_desc *gate) -{ - write_idt_entry(trace_idt_table, entry, gate); -} +void update_intr_gate(unsigned int n, const void *addr); +void alloc_intr_gate(unsigned int n, const void *addr); -static inline void _trace_set_gate(int gate, unsigned type, void *addr, - unsigned dpl, unsigned ist, unsigned seg) -{ - gate_desc s; - - pack_gate(&s, type, (unsigned long)addr, dpl, ist, seg); - /* - * does not need to be atomic because it is only done once at - * setup time - */ - write_trace_idt_entry(gate, &s); -} -#else -static inline void write_trace_idt_entry(int entry, const gate_desc *gate) -{ -} - -#define _trace_set_gate(gate, type, addr, dpl, ist, seg) -#endif - -static inline void _set_gate(int gate, unsigned type, void *addr, - unsigned dpl, unsigned ist, unsigned seg) -{ - gate_desc s; - - pack_gate(&s, type, (unsigned long)addr, dpl, ist, seg); - /* - * does not need to be atomic because it is only done once at - * setup time - */ - write_idt_entry(idt_table, gate, &s); - write_trace_idt_entry(gate, &s); -} - -/* - * This needs to use 'idt_table' rather than 'idt', and - * thus use the _nonmapped_ version of the IDT, as the - * Pentium F0 0F bugfix can have resulted in the mapped - * IDT being write-protected. - */ -#define set_intr_gate_notrace(n, addr) \ - do { \ - BUG_ON((unsigned)n > 0xFF); \ - _set_gate(n, GATE_INTERRUPT, (void *)addr, 0, 0, \ - __KERNEL_CS); \ - } while (0) - -#define set_intr_gate(n, addr) \ - do { \ - set_intr_gate_notrace(n, addr); \ - _trace_set_gate(n, GATE_INTERRUPT, (void *)trace_##addr,\ - 0, 0, __KERNEL_CS); \ - } while (0) - -extern int first_system_vector; -/* used_vectors is BITMAP for irq is not managed by percpu vector_irq */ extern unsigned long used_vectors[]; -static inline void alloc_system_vector(int vector) -{ - if (!test_bit(vector, used_vectors)) { - set_bit(vector, used_vectors); - if (first_system_vector > vector) - first_system_vector = vector; - } else { - BUG(); - } -} - -#define alloc_intr_gate(n, addr) \ - do { \ - alloc_system_vector(n); \ - set_intr_gate(n, addr); \ - } while (0) - -/* - * This routine sets up an interrupt gate at directory privilege level 3. - */ -static inline void set_system_intr_gate(unsigned int n, void *addr) -{ - BUG_ON((unsigned)n > 0xFF); - _set_gate(n, GATE_INTERRUPT, addr, 0x3, 0, __KERNEL_CS); -} - -static inline void set_system_trap_gate(unsigned int n, void *addr) -{ - BUG_ON((unsigned)n > 0xFF); - _set_gate(n, GATE_TRAP, addr, 0x3, 0, __KERNEL_CS); -} - -static inline void set_trap_gate(unsigned int n, void *addr) -{ - BUG_ON((unsigned)n > 0xFF); - _set_gate(n, GATE_TRAP, addr, 0, 0, __KERNEL_CS); -} - -static inline void set_task_gate(unsigned int n, unsigned int gdt_entry) -{ - BUG_ON((unsigned)n > 0xFF); - _set_gate(n, GATE_TASK, (void *)0, 0, 0, (gdt_entry<<3)); -} - -static inline void set_intr_gate_ist(int n, void *addr, unsigned ist) -{ - BUG_ON((unsigned)n > 0xFF); - _set_gate(n, GATE_INTERRUPT, addr, 0, ist, __KERNEL_CS); -} - -static inline void set_system_intr_gate_ist(int n, void *addr, unsigned ist) -{ - BUG_ON((unsigned)n > 0xFF); - _set_gate(n, GATE_INTERRUPT, addr, 0x3, ist, __KERNEL_CS); -} - #ifdef CONFIG_X86_64 DECLARE_PER_CPU(u32, debug_idt_ctr); static inline bool is_debug_idt_enabled(void) @@ -567,31 +420,6 @@ static inline void load_debug_idt(void) } #endif -#ifdef CONFIG_TRACING -extern atomic_t trace_idt_ctr; -static inline bool is_trace_idt_enabled(void) -{ - if (atomic_read(&trace_idt_ctr)) - return true; - - return false; -} - -static inline void load_trace_idt(void) -{ - load_idt((const struct desc_ptr *)&trace_idt_descr); -} -#else -static inline bool is_trace_idt_enabled(void) -{ - return false; -} - -static inline void load_trace_idt(void) -{ -} -#endif - /* * The load_current_idt() must be called with interrupts disabled * to avoid races. That way the IDT will always be set back to the expected @@ -603,9 +431,25 @@ static inline void load_current_idt(void) { if (is_debug_idt_enabled()) load_debug_idt(); - else if (is_trace_idt_enabled()) - load_trace_idt(); else load_idt((const struct desc_ptr *)&idt_descr); } + +extern void idt_setup_early_handler(void); +extern void idt_setup_early_traps(void); +extern void idt_setup_traps(void); +extern void idt_setup_apic_and_irq_gates(void); + +#ifdef CONFIG_X86_64 +extern void idt_setup_early_pf(void); +extern void idt_setup_ist_traps(void); +extern void idt_setup_debugidt_traps(void); +#else +static inline void idt_setup_early_pf(void) { } +static inline void idt_setup_ist_traps(void) { } +static inline void idt_setup_debugidt_traps(void) { } +#endif + +extern void idt_invalidate(void *addr); + #endif /* _ASM_X86_DESC_H */ diff --git a/arch/x86/include/asm/desc_defs.h b/arch/x86/include/asm/desc_defs.h index 49265345d4d2..346d252029b7 100644 --- a/arch/x86/include/asm/desc_defs.h +++ b/arch/x86/include/asm/desc_defs.h @@ -11,34 +11,30 @@ #include <linux/types.h> -/* - * FIXME: Accessing the desc_struct through its fields is more elegant, - * and should be the one valid thing to do. However, a lot of open code - * still touches the a and b accessors, and doing this allow us to do it - * incrementally. We keep the signature as a struct, rather than a union, - * so we can get rid of it transparently in the future -- glommer - */ /* 8 byte segment descriptor */ struct desc_struct { - union { - struct { - unsigned int a; - unsigned int b; - }; - struct { - u16 limit0; - u16 base0; - unsigned base1: 8, type: 4, s: 1, dpl: 2, p: 1; - unsigned limit: 4, avl: 1, l: 1, d: 1, g: 1, base2: 8; - }; - }; + u16 limit0; + u16 base0; + u16 base1: 8, type: 4, s: 1, dpl: 2, p: 1; + u16 limit1: 4, avl: 1, l: 1, d: 1, g: 1, base2: 8; } __attribute__((packed)); -#define GDT_ENTRY_INIT(flags, base, limit) { { { \ - .a = ((limit) & 0xffff) | (((base) & 0xffff) << 16), \ - .b = (((base) & 0xff0000) >> 16) | (((flags) & 0xf0ff) << 8) | \ - ((limit) & 0xf0000) | ((base) & 0xff000000), \ - } } } +#define GDT_ENTRY_INIT(flags, base, limit) \ + { \ + .limit0 = (u16) (limit), \ + .limit1 = ((limit) >> 16) & 0x0F, \ + .base0 = (u16) (base), \ + .base1 = ((base) >> 16) & 0xFF, \ + .base2 = ((base) >> 24) & 0xFF, \ + .type = (flags & 0x0f), \ + .s = (flags >> 4) & 0x01, \ + .dpl = (flags >> 5) & 0x03, \ + .p = (flags >> 7) & 0x01, \ + .avl = (flags >> 12) & 0x01, \ + .l = (flags >> 13) & 0x01, \ + .d = (flags >> 14) & 0x01, \ + .g = (flags >> 15) & 0x01, \ + } enum { GATE_INTERRUPT = 0xE, @@ -47,49 +43,63 @@ enum { GATE_TASK = 0x5, }; -/* 16byte gate */ -struct gate_struct64 { - u16 offset_low; - u16 segment; - unsigned ist : 3, zero0 : 5, type : 5, dpl : 2, p : 1; - u16 offset_middle; - u32 offset_high; - u32 zero1; -} __attribute__((packed)); - -#define PTR_LOW(x) ((unsigned long long)(x) & 0xFFFF) -#define PTR_MIDDLE(x) (((unsigned long long)(x) >> 16) & 0xFFFF) -#define PTR_HIGH(x) ((unsigned long long)(x) >> 32) - enum { DESC_TSS = 0x9, DESC_LDT = 0x2, DESCTYPE_S = 0x10, /* !system */ }; -/* LDT or TSS descriptor in the GDT. 16 bytes. */ -struct ldttss_desc64 { - u16 limit0; - u16 base0; - unsigned base1 : 8, type : 5, dpl : 2, p : 1; - unsigned limit1 : 4, zero0 : 3, g : 1, base2 : 8; - u32 base3; - u32 zero1; +/* LDT or TSS descriptor in the GDT. */ +struct ldttss_desc { + u16 limit0; + u16 base0; + + u16 base1 : 8, type : 5, dpl : 2, p : 1; + u16 limit1 : 4, zero0 : 3, g : 1, base2 : 8; +#ifdef CONFIG_X86_64 + u32 base3; + u32 zero1; +#endif } __attribute__((packed)); +typedef struct ldttss_desc ldt_desc; +typedef struct ldttss_desc tss_desc; + +struct idt_bits { + u16 ist : 3, + zero : 5, + type : 5, + dpl : 2, + p : 1; +} __attribute__((packed)); + +struct gate_struct { + u16 offset_low; + u16 segment; + struct idt_bits bits; + u16 offset_middle; +#ifdef CONFIG_X86_64 + u32 offset_high; + u32 reserved; +#endif +} __attribute__((packed)); + +typedef struct gate_struct gate_desc; + +static inline unsigned long gate_offset(const gate_desc *g) +{ #ifdef CONFIG_X86_64 -typedef struct gate_struct64 gate_desc; -typedef struct ldttss_desc64 ldt_desc; -typedef struct ldttss_desc64 tss_desc; -#define gate_offset(g) ((g).offset_low | ((unsigned long)(g).offset_middle << 16) | ((unsigned long)(g).offset_high << 32)) -#define gate_segment(g) ((g).segment) + return g->offset_low | ((unsigned long)g->offset_middle << 16) | + ((unsigned long) g->offset_high << 32); #else -typedef struct desc_struct gate_desc; -typedef struct desc_struct ldt_desc; -typedef struct desc_struct tss_desc; -#define gate_offset(g) (((g).b & 0xffff0000) | ((g).a & 0x0000ffff)) -#define gate_segment(g) ((g).a >> 16) + return g->offset_low | ((unsigned long)g->offset_middle << 16); #endif +} + +static inline unsigned long gate_segment(const gate_desc *g) +{ + return g->segment; +} struct desc_ptr { unsigned short size; diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index 5dff775af7cd..c10c9128f54e 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -21,11 +21,13 @@ # define DISABLE_K6_MTRR (1<<(X86_FEATURE_K6_MTRR & 31)) # define DISABLE_CYRIX_ARR (1<<(X86_FEATURE_CYRIX_ARR & 31)) # define DISABLE_CENTAUR_MCR (1<<(X86_FEATURE_CENTAUR_MCR & 31)) +# define DISABLE_PCID 0 #else # define DISABLE_VME 0 # define DISABLE_K6_MTRR 0 # define DISABLE_CYRIX_ARR 0 # define DISABLE_CENTAUR_MCR 0 +# define DISABLE_PCID (1<<(X86_FEATURE_PCID & 31)) #endif /* CONFIG_X86_64 */ #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS @@ -49,7 +51,7 @@ #define DISABLED_MASK1 0 #define DISABLED_MASK2 0 #define DISABLED_MASK3 (DISABLE_CYRIX_ARR|DISABLE_CENTAUR_MCR|DISABLE_K6_MTRR) -#define DISABLED_MASK4 0 +#define DISABLED_MASK4 (DISABLE_PCID) #define DISABLED_MASK5 0 #define DISABLED_MASK6 0 #define DISABLED_MASK7 0 diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h index 398c79889f5c..1387dafdba2d 100644 --- a/arch/x86/include/asm/dma-mapping.h +++ b/arch/x86/include/asm/dma-mapping.h @@ -12,6 +12,7 @@ #include <asm/io.h> #include <asm/swiotlb.h> #include <linux/dma-contiguous.h> +#include <linux/mem_encrypt.h> #ifdef CONFIG_ISA # define ISA_DMA_BIT_MASK DMA_BIT_MASK(24) @@ -57,12 +58,12 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size) static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr) { - return paddr; + return __sme_set(paddr); } static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr) { - return daddr; + return __sme_clr(daddr); } #endif /* CONFIG_X86_DMA_REMAP */ diff --git a/arch/x86/include/asm/dmi.h b/arch/x86/include/asm/dmi.h index 3c69fed215c5..a8e15b04565b 100644 --- a/arch/x86/include/asm/dmi.h +++ b/arch/x86/include/asm/dmi.h @@ -13,9 +13,9 @@ static __always_inline __init void *dmi_alloc(unsigned len) } /* Use early IO mappings for DMI because it's initialized early */ -#define dmi_early_remap early_ioremap -#define dmi_early_unmap early_iounmap -#define dmi_remap ioremap_cache -#define dmi_unmap iounmap +#define dmi_early_remap early_memremap +#define dmi_early_unmap early_memunmap +#define dmi_remap(_x, _l) memremap(_x, _l, MEMREMAP_WB) +#define dmi_unmap(_x) memunmap(_x) #endif /* _ASM_X86_DMI_H */ diff --git a/arch/x86/include/asm/e820/api.h b/arch/x86/include/asm/e820/api.h index a504adc661a4..cd266d830e49 100644 --- a/arch/x86/include/asm/e820/api.h +++ b/arch/x86/include/asm/e820/api.h @@ -39,6 +39,8 @@ extern void e820__setup_pci_gap(void); extern void e820__reallocate_tables(void); extern void e820__register_nosave_regions(unsigned long limit_pfn); +extern int e820__get_entry_type(u64 start, u64 end); + /* * Returns true iff the specified range [start,end) is completely contained inside * the ISA region. diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index 1c18d83d3f09..04330c8d9af9 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -126,15 +126,15 @@ do { \ pr_reg[4] = regs->di; \ pr_reg[5] = regs->bp; \ pr_reg[6] = regs->ax; \ - pr_reg[7] = regs->ds & 0xffff; \ - pr_reg[8] = regs->es & 0xffff; \ - pr_reg[9] = regs->fs & 0xffff; \ + pr_reg[7] = regs->ds; \ + pr_reg[8] = regs->es; \ + pr_reg[9] = regs->fs; \ pr_reg[11] = regs->orig_ax; \ pr_reg[12] = regs->ip; \ - pr_reg[13] = regs->cs & 0xffff; \ + pr_reg[13] = regs->cs; \ pr_reg[14] = regs->flags; \ pr_reg[15] = regs->sp; \ - pr_reg[16] = regs->ss & 0xffff; \ + pr_reg[16] = regs->ss; \ } while (0); #define ELF_CORE_COPY_REGS(pr_reg, regs) \ @@ -204,6 +204,7 @@ void set_personality_ia32(bool); #define ELF_CORE_COPY_REGS(pr_reg, regs) \ do { \ + unsigned long base; \ unsigned v; \ (pr_reg)[0] = (regs)->r15; \ (pr_reg)[1] = (regs)->r14; \ @@ -226,8 +227,8 @@ do { \ (pr_reg)[18] = (regs)->flags; \ (pr_reg)[19] = (regs)->sp; \ (pr_reg)[20] = (regs)->ss; \ - (pr_reg)[21] = current->thread.fsbase; \ - (pr_reg)[22] = current->thread.gsbase; \ + rdmsrl(MSR_FS_BASE, base); (pr_reg)[21] = base; \ + rdmsrl(MSR_KERNEL_GS_BASE, base); (pr_reg)[22] = base; \ asm("movl %%ds,%0" : "=r" (v)); (pr_reg)[23] = v; \ asm("movl %%es,%0" : "=r" (v)); (pr_reg)[24] = v; \ asm("movl %%fs,%0" : "=r" (v)); (pr_reg)[25] = v; \ @@ -247,11 +248,11 @@ extern int force_personality32; /* * This is the base location for PIE (ET_DYN with INTERP) loads. On - * 64-bit, this is raised to 4GB to leave the entire 32-bit address + * 64-bit, this is above 4GB to leave the entire 32-bit address * space open for things that want to use the area for 32-bit pointers. */ #define ELF_ET_DYN_BASE (mmap_is_ia32() ? 0x000400000UL : \ - 0x100000000UL) + (TASK_SIZE / 3 * 2)) /* This yields a mask that user programs can use to figure out what instruction set this CPU supports. This could be done in user space, @@ -304,8 +305,8 @@ static inline int mmap_is_ia32(void) test_thread_flag(TIF_ADDR32)); } -extern unsigned long tasksize_32bit(void); -extern unsigned long tasksize_64bit(void); +extern unsigned long task_size_32bit(void); +extern unsigned long task_size_64bit(int full_addr_space); extern unsigned long get_mmap_base(int is_legacy); #ifdef CONFIG_X86_32 diff --git a/arch/x86/include/asm/entry_arch.h b/arch/x86/include/asm/entry_arch.h index df002992d8fd..aa15d1f7e530 100644 --- a/arch/x86/include/asm/entry_arch.h +++ b/arch/x86/include/asm/entry_arch.h @@ -13,18 +13,14 @@ BUILD_INTERRUPT(reschedule_interrupt,RESCHEDULE_VECTOR) BUILD_INTERRUPT(call_function_interrupt,CALL_FUNCTION_VECTOR) BUILD_INTERRUPT(call_function_single_interrupt,CALL_FUNCTION_SINGLE_VECTOR) -BUILD_INTERRUPT3(irq_move_cleanup_interrupt, IRQ_MOVE_CLEANUP_VECTOR, - smp_irq_move_cleanup_interrupt) -BUILD_INTERRUPT3(reboot_interrupt, REBOOT_VECTOR, smp_reboot_interrupt) +BUILD_INTERRUPT(irq_move_cleanup_interrupt, IRQ_MOVE_CLEANUP_VECTOR) +BUILD_INTERRUPT(reboot_interrupt, REBOOT_VECTOR) #endif -BUILD_INTERRUPT(x86_platform_ipi, X86_PLATFORM_IPI_VECTOR) - #ifdef CONFIG_HAVE_KVM -BUILD_INTERRUPT3(kvm_posted_intr_ipi, POSTED_INTR_VECTOR, - smp_kvm_posted_intr_ipi) -BUILD_INTERRUPT3(kvm_posted_intr_wakeup_ipi, POSTED_INTR_WAKEUP_VECTOR, - smp_kvm_posted_intr_wakeup_ipi) +BUILD_INTERRUPT(kvm_posted_intr_ipi, POSTED_INTR_VECTOR) +BUILD_INTERRUPT(kvm_posted_intr_wakeup_ipi, POSTED_INTR_WAKEUP_VECTOR) +BUILD_INTERRUPT(kvm_posted_intr_nested_ipi, POSTED_INTR_NESTED_VECTOR) #endif /* @@ -39,6 +35,7 @@ BUILD_INTERRUPT3(kvm_posted_intr_wakeup_ipi, POSTED_INTR_WAKEUP_VECTOR, BUILD_INTERRUPT(apic_timer_interrupt,LOCAL_TIMER_VECTOR) BUILD_INTERRUPT(error_interrupt,ERROR_APIC_VECTOR) BUILD_INTERRUPT(spurious_interrupt,SPURIOUS_APIC_VECTOR) +BUILD_INTERRUPT(x86_platform_ipi, X86_PLATFORM_IPI_VECTOR) #ifdef CONFIG_IRQ_WORK BUILD_INTERRUPT(irq_work_interrupt, IRQ_WORK_VECTOR) diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index b65155cc3760..dcd9fb55e679 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -157,6 +157,26 @@ static inline void __set_fixmap(enum fixed_addresses idx, } #endif +/* + * FIXMAP_PAGE_NOCACHE is used for MMIO. Memory encryption is not + * supported for MMIO addresses, so make sure that the memory encryption + * mask is not part of the page attributes. + */ +#define FIXMAP_PAGE_NOCACHE PAGE_KERNEL_IO_NOCACHE + +/* + * Early memremap routines used for in-place encryption. The mappings created + * by these routines are intended to be used as temporary mappings. + */ +void __init *early_memremap_encrypted(resource_size_t phys_addr, + unsigned long size); +void __init *early_memremap_encrypted_wp(resource_size_t phys_addr, + unsigned long size); +void __init *early_memremap_decrypted(resource_size_t phys_addr, + unsigned long size); +void __init *early_memremap_decrypted_wp(resource_size_t phys_addr, + unsigned long size); + #include <asm-generic/fixmap.h> #define __late_set_fixmap(idx, phys, flags) __set_fixmap(idx, phys, flags) diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 255645f60ca2..554cdb205d17 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -450,10 +450,10 @@ static inline int copy_fpregs_to_fpstate(struct fpu *fpu) return 0; } -static inline void __copy_kernel_to_fpregs(union fpregs_state *fpstate) +static inline void __copy_kernel_to_fpregs(union fpregs_state *fpstate, u64 mask) { if (use_xsave()) { - copy_kernel_to_xregs(&fpstate->xsave, -1); + copy_kernel_to_xregs(&fpstate->xsave, mask); } else { if (use_fxsr()) copy_kernel_to_fxregs(&fpstate->fxsave); @@ -477,7 +477,7 @@ static inline void copy_kernel_to_fpregs(union fpregs_state *fpstate) : : [addr] "m" (fpstate)); } - __copy_kernel_to_fpregs(fpstate); + __copy_kernel_to_fpregs(fpstate, -1); } extern int copy_fpstate_to_sigframe(void __user *buf, void __user *fp, int size); diff --git a/arch/x86/include/asm/futex.h b/arch/x86/include/asm/futex.h index b4c1f5453436..f4dc9b63bdda 100644 --- a/arch/x86/include/asm/futex.h +++ b/arch/x86/include/asm/futex.h @@ -41,20 +41,11 @@ "+m" (*uaddr), "=&r" (tem) \ : "r" (oparg), "i" (-EFAULT), "1" (0)) -static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr) +static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, + u32 __user *uaddr) { - int op = (encoded_op >> 28) & 7; - int cmp = (encoded_op >> 24) & 15; - int oparg = (encoded_op << 8) >> 20; - int cmparg = (encoded_op << 20) >> 20; int oldval = 0, ret, tem; - if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) - oparg = 1 << oparg; - - if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) - return -EFAULT; - pagefault_disable(); switch (op) { @@ -80,30 +71,9 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr) pagefault_enable(); - if (!ret) { - switch (cmp) { - case FUTEX_OP_CMP_EQ: - ret = (oldval == cmparg); - break; - case FUTEX_OP_CMP_NE: - ret = (oldval != cmparg); - break; - case FUTEX_OP_CMP_LT: - ret = (oldval < cmparg); - break; - case FUTEX_OP_CMP_GE: - ret = (oldval >= cmparg); - break; - case FUTEX_OP_CMP_LE: - ret = (oldval <= cmparg); - break; - case FUTEX_OP_CMP_GT: - ret = (oldval > cmparg); - break; - default: - ret = -ENOSYS; - } - } + if (!ret) + *oval = oldval; + return ret; } diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h index 9b76cd331990..ad1ed531febc 100644 --- a/arch/x86/include/asm/hardirq.h +++ b/arch/x86/include/asm/hardirq.h @@ -15,6 +15,7 @@ typedef struct { #ifdef CONFIG_HAVE_KVM unsigned int kvm_posted_intr_ipis; unsigned int kvm_posted_intr_wakeup_ipis; + unsigned int kvm_posted_intr_nested_ipis; #endif unsigned int x86_platform_ipis; /* arch dependent */ unsigned int apic_perf_irqs; diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h index b90e1053049b..6dfe366a8804 100644 --- a/arch/x86/include/asm/hw_irq.h +++ b/arch/x86/include/asm/hw_irq.h @@ -30,6 +30,7 @@ extern asmlinkage void apic_timer_interrupt(void); extern asmlinkage void x86_platform_ipi(void); extern asmlinkage void kvm_posted_intr_ipi(void); extern asmlinkage void kvm_posted_intr_wakeup_ipi(void); +extern asmlinkage void kvm_posted_intr_nested_ipi(void); extern asmlinkage void error_interrupt(void); extern asmlinkage void irq_work_interrupt(void); @@ -45,25 +46,6 @@ extern asmlinkage void deferred_error_interrupt(void); extern asmlinkage void call_function_interrupt(void); extern asmlinkage void call_function_single_interrupt(void); -#ifdef CONFIG_TRACING -/* Interrupt handlers registered during init_IRQ */ -extern void trace_apic_timer_interrupt(void); -extern void trace_x86_platform_ipi(void); -extern void trace_error_interrupt(void); -extern void trace_irq_work_interrupt(void); -extern void trace_spurious_interrupt(void); -extern void trace_thermal_interrupt(void); -extern void trace_reschedule_interrupt(void); -extern void trace_threshold_interrupt(void); -extern void trace_deferred_error_interrupt(void); -extern void trace_call_function_interrupt(void); -extern void trace_call_function_single_interrupt(void); -#define trace_irq_move_cleanup_interrupt irq_move_cleanup_interrupt -#define trace_reboot_interrupt reboot_interrupt -#define trace_kvm_posted_intr_ipi kvm_posted_intr_ipi -#define trace_kvm_posted_intr_wakeup_ipi kvm_posted_intr_wakeup_ipi -#endif /* CONFIG_TRACING */ - #ifdef CONFIG_X86_LOCAL_APIC struct irq_data; struct pci_dev; diff --git a/arch/x86/include/asm/hypervisor.h b/arch/x86/include/asm/hypervisor.h index 21126155a739..0ead9dbb9130 100644 --- a/arch/x86/include/asm/hypervisor.h +++ b/arch/x86/include/asm/hypervisor.h @@ -43,6 +43,9 @@ struct hypervisor_x86 { /* pin current vcpu to specified physical cpu (run rarely) */ void (*pin_vcpu)(int); + + /* called during init_mem_mapping() to setup early mappings. */ + void (*init_mem_mapping)(void); }; extern const struct hypervisor_x86 *x86_hyper; @@ -57,8 +60,15 @@ extern const struct hypervisor_x86 x86_hyper_kvm; extern void init_hypervisor_platform(void); extern bool hypervisor_x2apic_available(void); extern void hypervisor_pin_vcpu(int cpu); + +static inline void hypervisor_init_mem_mapping(void) +{ + if (x86_hyper && x86_hyper->init_mem_mapping) + x86_hyper->init_mem_mapping(); +} #else static inline void init_hypervisor_platform(void) { } static inline bool hypervisor_x2apic_available(void) { return false; } +static inline void hypervisor_init_mem_mapping(void) { } #endif /* CONFIG_HYPERVISOR_GUEST */ #endif /* _ASM_X86_HYPERVISOR_H */ diff --git a/arch/x86/include/asm/init.h b/arch/x86/include/asm/init.h index 474eb8c66fee..05c4aa00cc86 100644 --- a/arch/x86/include/asm/init.h +++ b/arch/x86/include/asm/init.h @@ -7,6 +7,7 @@ struct x86_mapping_info { unsigned long page_flag; /* page flag for PMD or PUD entry */ unsigned long offset; /* ident mapping offset */ bool direct_gbpages; /* PUD level 1GB page support */ + unsigned long kernpg_flag; /* kernel pagetable flag override */ }; int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page, diff --git a/arch/x86/include/asm/intel_rdt.h b/arch/x86/include/asm/intel_rdt.h deleted file mode 100644 index 597dc4995678..000000000000 --- a/arch/x86/include/asm/intel_rdt.h +++ /dev/null @@ -1,286 +0,0 @@ -#ifndef _ASM_X86_INTEL_RDT_H -#define _ASM_X86_INTEL_RDT_H - -#ifdef CONFIG_INTEL_RDT_A - -#include <linux/sched.h> -#include <linux/kernfs.h> -#include <linux/jump_label.h> - -#include <asm/intel_rdt_common.h> - -#define IA32_L3_QOS_CFG 0xc81 -#define IA32_L3_CBM_BASE 0xc90 -#define IA32_L2_CBM_BASE 0xd10 -#define IA32_MBA_THRTL_BASE 0xd50 - -#define L3_QOS_CDP_ENABLE 0x01ULL - -/** - * struct rdtgroup - store rdtgroup's data in resctrl file system. - * @kn: kernfs node - * @rdtgroup_list: linked list for all rdtgroups - * @closid: closid for this rdtgroup - * @cpu_mask: CPUs assigned to this rdtgroup - * @flags: status bits - * @waitcount: how many cpus expect to find this - * group when they acquire rdtgroup_mutex - */ -struct rdtgroup { - struct kernfs_node *kn; - struct list_head rdtgroup_list; - int closid; - struct cpumask cpu_mask; - int flags; - atomic_t waitcount; -}; - -/* rdtgroup.flags */ -#define RDT_DELETED 1 - -/* rftype.flags */ -#define RFTYPE_FLAGS_CPUS_LIST 1 - -/* List of all resource groups */ -extern struct list_head rdt_all_groups; - -extern int max_name_width, max_data_width; - -int __init rdtgroup_init(void); - -/** - * struct rftype - describe each file in the resctrl file system - * @name: File name - * @mode: Access mode - * @kf_ops: File operations - * @flags: File specific RFTYPE_FLAGS_* flags - * @seq_show: Show content of the file - * @write: Write to the file - */ -struct rftype { - char *name; - umode_t mode; - struct kernfs_ops *kf_ops; - unsigned long flags; - - int (*seq_show)(struct kernfs_open_file *of, - struct seq_file *sf, void *v); - /* - * write() is the generic write callback which maps directly to - * kernfs write operation and overrides all other operations. - * Maximum write size is determined by ->max_write_len. - */ - ssize_t (*write)(struct kernfs_open_file *of, - char *buf, size_t nbytes, loff_t off); -}; - -/** - * struct rdt_domain - group of cpus sharing an RDT resource - * @list: all instances of this resource - * @id: unique id for this instance - * @cpu_mask: which cpus share this resource - * @ctrl_val: array of cache or mem ctrl values (indexed by CLOSID) - * @new_ctrl: new ctrl value to be loaded - * @have_new_ctrl: did user provide new_ctrl for this domain - */ -struct rdt_domain { - struct list_head list; - int id; - struct cpumask cpu_mask; - u32 *ctrl_val; - u32 new_ctrl; - bool have_new_ctrl; -}; - -/** - * struct msr_param - set a range of MSRs from a domain - * @res: The resource to use - * @low: Beginning index from base MSR - * @high: End index - */ -struct msr_param { - struct rdt_resource *res; - int low; - int high; -}; - -/** - * struct rdt_cache - Cache allocation related data - * @cbm_len: Length of the cache bit mask - * @min_cbm_bits: Minimum number of consecutive bits to be set - * @cbm_idx_mult: Multiplier of CBM index - * @cbm_idx_offset: Offset of CBM index. CBM index is computed by: - * closid * cbm_idx_multi + cbm_idx_offset - * in a cache bit mask - */ -struct rdt_cache { - unsigned int cbm_len; - unsigned int min_cbm_bits; - unsigned int cbm_idx_mult; - unsigned int cbm_idx_offset; -}; - -/** - * 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 - * @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; - u32 *mb_map; -}; - -/** - * struct rdt_resource - attributes of an RDT resource - * @enabled: Is this feature enabled on this machine - * @capable: Is this feature available on this machine - * @name: Name to use in "schemata" file - * @num_closid: Number of CLOSIDs available - * @cache_level: Which cache level defines scope of this resource - * @default_ctrl: Specifies default cache cbm or memory B/W percent. - * @msr_base: Base MSR address for CBMs - * @msr_update: Function pointer to update QOS MSRs - * @data_width: Character width of data when displaying - * @domains: All domains for this resource - * @cache: Cache allocation related data - * @info_files: resctrl info files for the resource - * @nr_info_files: Number of info files - * @format_str: Per resource format string to show domain value - * @parse_ctrlval: Per resource function pointer to parse control values - */ -struct rdt_resource { - bool enabled; - bool capable; - char *name; - int num_closid; - int cache_level; - u32 default_ctrl; - unsigned int msr_base; - void (*msr_update) (struct rdt_domain *d, struct msr_param *m, - struct rdt_resource *r); - int data_width; - struct list_head domains; - struct rdt_cache cache; - struct rdt_membw membw; - struct rftype *info_files; - int nr_info_files; - const char *format_str; - int (*parse_ctrlval) (char *buf, struct rdt_resource *r, - struct rdt_domain *d); -}; - -void rdt_get_cache_infofile(struct rdt_resource *r); -void rdt_get_mba_infofile(struct rdt_resource *r); -int parse_cbm(char *buf, struct rdt_resource *r, struct rdt_domain *d); -int parse_bw(char *buf, struct rdt_resource *r, struct rdt_domain *d); - -extern struct mutex rdtgroup_mutex; - -extern struct rdt_resource rdt_resources_all[]; -extern struct rdtgroup rdtgroup_default; -DECLARE_STATIC_KEY_FALSE(rdt_enable_key); - -int __init rdtgroup_init(void); - -enum { - RDT_RESOURCE_L3, - RDT_RESOURCE_L3DATA, - RDT_RESOURCE_L3CODE, - RDT_RESOURCE_L2, - RDT_RESOURCE_MBA, - - /* Must be the last */ - RDT_NUM_RESOURCES, -}; - -#define for_each_capable_rdt_resource(r) \ - for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\ - r++) \ - if (r->capable) - -#define for_each_enabled_rdt_resource(r) \ - for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\ - r++) \ - if (r->enabled) - -/* CPUID.(EAX=10H, ECX=ResID=1).EAX */ -union cpuid_0x10_1_eax { - struct { - unsigned int cbm_len:5; - } split; - unsigned int full; -}; - -/* CPUID.(EAX=10H, ECX=ResID=3).EAX */ -union cpuid_0x10_3_eax { - struct { - unsigned int max_delay:12; - } split; - unsigned int full; -}; - -/* CPUID.(EAX=10H, ECX=ResID).EDX */ -union cpuid_0x10_x_edx { - struct { - unsigned int cos_max:16; - } split; - unsigned int full; -}; - -DECLARE_PER_CPU_READ_MOSTLY(int, cpu_closid); - -void rdt_ctrl_update(void *arg); -struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn); -void rdtgroup_kn_unlock(struct kernfs_node *kn); -ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, - char *buf, size_t nbytes, loff_t off); -int rdtgroup_schemata_show(struct kernfs_open_file *of, - struct seq_file *s, void *v); - -/* - * intel_rdt_sched_in() - Writes the task's CLOSid to IA32_PQR_MSR - * - * Following considerations are made so that this has minimal impact - * on scheduler hot path: - * - This will stay as no-op unless we are running on an Intel SKU - * which supports resource control and we enable by mounting the - * resctrl file system. - * - Caches the per cpu CLOSid values and does the MSR write only - * when a task with a different CLOSid is scheduled in. - * - * Must be called with preemption disabled. - */ -static inline void intel_rdt_sched_in(void) -{ - if (static_branch_likely(&rdt_enable_key)) { - struct intel_pqr_state *state = this_cpu_ptr(&pqr_state); - int closid; - - /* - * If this task has a closid assigned, use it. - * Else use the closid assigned to this cpu. - */ - closid = current->closid; - if (closid == 0) - closid = this_cpu_read(cpu_closid); - - if (closid != state->closid) { - state->closid = closid; - wrmsr(MSR_IA32_PQR_ASSOC, state->rmid, closid); - } - } -} - -#else - -static inline void intel_rdt_sched_in(void) {} - -#endif /* CONFIG_INTEL_RDT_A */ -#endif /* _ASM_X86_INTEL_RDT_H */ diff --git a/arch/x86/include/asm/intel_rdt_common.h b/arch/x86/include/asm/intel_rdt_common.h deleted file mode 100644 index b31081b89407..000000000000 --- a/arch/x86/include/asm/intel_rdt_common.h +++ /dev/null @@ -1,27 +0,0 @@ -#ifndef _ASM_X86_INTEL_RDT_COMMON_H -#define _ASM_X86_INTEL_RDT_COMMON_H - -#define MSR_IA32_PQR_ASSOC 0x0c8f - -/** - * struct intel_pqr_state - State cache for the PQR MSR - * @rmid: The cached Resource Monitoring ID - * @closid: The cached Class Of Service ID - * @rmid_usecnt: The usage counter for rmid - * - * The upper 32 bits of MSR_IA32_PQR_ASSOC contain closid and the - * lower 10 bits rmid. The update to MSR_IA32_PQR_ASSOC always - * contains both parts, so we need to cache them. - * - * The cache also helps to avoid pointless updates if the value does - * not change. - */ -struct intel_pqr_state { - u32 rmid; - u32 closid; - int rmid_usecnt; -}; - -DECLARE_PER_CPU(struct intel_pqr_state, pqr_state); - -#endif /* _ASM_X86_INTEL_RDT_COMMON_H */ diff --git a/arch/x86/include/asm/intel_rdt_sched.h b/arch/x86/include/asm/intel_rdt_sched.h new file mode 100644 index 000000000000..b4bbf8b21512 --- /dev/null +++ b/arch/x86/include/asm/intel_rdt_sched.h @@ -0,0 +1,92 @@ +#ifndef _ASM_X86_INTEL_RDT_SCHED_H +#define _ASM_X86_INTEL_RDT_SCHED_H + +#ifdef CONFIG_INTEL_RDT + +#include <linux/sched.h> +#include <linux/jump_label.h> + +#define IA32_PQR_ASSOC 0x0c8f + +/** + * struct intel_pqr_state - State cache for the PQR MSR + * @cur_rmid: The cached Resource Monitoring ID + * @cur_closid: The cached Class Of Service ID + * @default_rmid: The user assigned Resource Monitoring ID + * @default_closid: The user assigned cached Class Of Service ID + * + * The upper 32 bits of IA32_PQR_ASSOC contain closid and the + * lower 10 bits rmid. The update to IA32_PQR_ASSOC always + * contains both parts, so we need to cache them. This also + * stores the user configured per cpu CLOSID and RMID. + * + * The cache also helps to avoid pointless updates if the value does + * not change. + */ +struct intel_pqr_state { + u32 cur_rmid; + u32 cur_closid; + u32 default_rmid; + u32 default_closid; +}; + +DECLARE_PER_CPU(struct intel_pqr_state, pqr_state); + +DECLARE_STATIC_KEY_FALSE(rdt_enable_key); +DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key); +DECLARE_STATIC_KEY_FALSE(rdt_mon_enable_key); + +/* + * __intel_rdt_sched_in() - Writes the task's CLOSid/RMID to IA32_PQR_MSR + * + * Following considerations are made so that this has minimal impact + * on scheduler hot path: + * - This will stay as no-op unless we are running on an Intel SKU + * which supports resource control or monitoring and we enable by + * mounting the resctrl file system. + * - Caches the per cpu CLOSid/RMID values and does the MSR write only + * when a task with a different CLOSid/RMID is scheduled in. + * - We allocate RMIDs/CLOSids globally in order to keep this as + * simple as possible. + * Must be called with preemption disabled. + */ +static void __intel_rdt_sched_in(void) +{ + struct intel_pqr_state *state = this_cpu_ptr(&pqr_state); + u32 closid = state->default_closid; + u32 rmid = state->default_rmid; + + /* + * If this task has a closid/rmid assigned, use it. + * Else use the closid/rmid assigned to this cpu. + */ + if (static_branch_likely(&rdt_alloc_enable_key)) { + if (current->closid) + closid = current->closid; + } + + if (static_branch_likely(&rdt_mon_enable_key)) { + if (current->rmid) + rmid = current->rmid; + } + + if (closid != state->cur_closid || rmid != state->cur_rmid) { + state->cur_closid = closid; + state->cur_rmid = rmid; + wrmsr(IA32_PQR_ASSOC, rmid, closid); + } +} + +static inline void intel_rdt_sched_in(void) +{ + if (static_branch_likely(&rdt_enable_key)) + __intel_rdt_sched_in(); +} + +#else + +static inline void intel_rdt_sched_in(void) {} + +#endif /* CONFIG_INTEL_RDT */ + +#endif /* _ASM_X86_INTEL_RDT_SCHED_H */ diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index 48febf07e828..c40a95c33bb8 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -69,6 +69,9 @@ build_mmio_write(__writeb, "b", unsigned char, "q", ) build_mmio_write(__writew, "w", unsigned short, "r", ) build_mmio_write(__writel, "l", unsigned int, "r", ) +#define readb readb +#define readw readw +#define readl readl #define readb_relaxed(a) __readb(a) #define readw_relaxed(a) __readw(a) #define readl_relaxed(a) __readl(a) @@ -76,6 +79,9 @@ build_mmio_write(__writel, "l", unsigned int, "r", ) #define __raw_readw __readw #define __raw_readl __readl +#define writeb writeb +#define writew writew +#define writel writel #define writeb_relaxed(v, a) __writeb(v, a) #define writew_relaxed(v, a) __writew(v, a) #define writel_relaxed(v, a) __writel(v, a) @@ -88,13 +94,15 @@ build_mmio_write(__writel, "l", unsigned int, "r", ) #ifdef CONFIG_X86_64 build_mmio_read(readq, "q", unsigned long, "=r", :"memory") +build_mmio_read(__readq, "q", unsigned long, "=r", ) build_mmio_write(writeq, "q", unsigned long, "r", :"memory") +build_mmio_write(__writeq, "q", unsigned long, "r", ) -#define readq_relaxed(a) readq(a) -#define writeq_relaxed(v, a) writeq(v, a) +#define readq_relaxed(a) __readq(a) +#define writeq_relaxed(v, a) __writeq(v, a) -#define __raw_readq(a) readq(a) -#define __raw_writeq(val, addr) writeq(val, addr) +#define __raw_readq __readq +#define __raw_writeq __writeq /* Let people know that we have them */ #define readq readq @@ -119,6 +127,7 @@ static inline phys_addr_t virt_to_phys(volatile void *address) { return __pa(address); } +#define virt_to_phys virt_to_phys /** * phys_to_virt - map physical address to virtual @@ -137,6 +146,7 @@ static inline void *phys_to_virt(phys_addr_t address) { return __va(address); } +#define phys_to_virt phys_to_virt /* * Change "struct page" to physical address. @@ -169,11 +179,14 @@ static inline unsigned int isa_virt_to_bus(volatile void *address) * else, you probably want one of the following. */ extern void __iomem *ioremap_nocache(resource_size_t offset, unsigned long size); +#define ioremap_nocache ioremap_nocache extern void __iomem *ioremap_uc(resource_size_t offset, unsigned long size); #define ioremap_uc ioremap_uc extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size); +#define ioremap_cache ioremap_cache extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size, unsigned long prot_val); +#define ioremap_prot ioremap_prot /** * ioremap - map bus memory into CPU space @@ -193,8 +206,10 @@ static inline void __iomem *ioremap(resource_size_t offset, unsigned long size) { return ioremap_nocache(offset, size); } +#define ioremap ioremap extern void iounmap(volatile void __iomem *addr); +#define iounmap iounmap extern void set_iounmap_nonlazy(void); @@ -203,53 +218,6 @@ extern void set_iounmap_nonlazy(void); #include <asm-generic/iomap.h> /* - * Convert a virtual cached pointer to an uncached pointer - */ -#define xlate_dev_kmem_ptr(p) p - -/** - * memset_io Set a range of I/O memory to a constant value - * @addr: The beginning of the I/O-memory range to set - * @val: The value to set the memory to - * @count: The number of bytes to set - * - * Set a range of I/O memory to a given value. - */ -static inline void -memset_io(volatile void __iomem *addr, unsigned char val, size_t count) -{ - memset((void __force *)addr, val, count); -} - -/** - * memcpy_fromio Copy a block of data from I/O memory - * @dst: The (RAM) destination for the copy - * @src: The (I/O memory) source for the data - * @count: The number of bytes to copy - * - * Copy a block of data from I/O memory. - */ -static inline void -memcpy_fromio(void *dst, const volatile void __iomem *src, size_t count) -{ - memcpy(dst, (const void __force *)src, count); -} - -/** - * memcpy_toio Copy a block of data into I/O memory - * @dst: The (I/O memory) destination for the copy - * @src: The (RAM) source for the data - * @count: The number of bytes to copy - * - * Copy a block of data to I/O memory. - */ -static inline void -memcpy_toio(volatile void __iomem *dst, const void *src, size_t count) -{ - memcpy((void __force *)dst, src, count); -} - -/* * ISA space is 'always mapped' on a typical x86 system, no need to * explicitly ioremap() it. The fact that the ISA IO space is mapped * to PAGE_OFFSET is pure coincidence - it does not mean ISA values @@ -341,13 +309,38 @@ BUILDIO(b, b, char) BUILDIO(w, w, short) BUILDIO(l, , int) +#define inb inb +#define inw inw +#define inl inl +#define inb_p inb_p +#define inw_p inw_p +#define inl_p inl_p +#define insb insb +#define insw insw +#define insl insl + +#define outb outb +#define outw outw +#define outl outl +#define outb_p outb_p +#define outw_p outw_p +#define outl_p outl_p +#define outsb outsb +#define outsw outsw +#define outsl outsl + extern void *xlate_dev_mem_ptr(phys_addr_t phys); extern void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr); +#define xlate_dev_mem_ptr xlate_dev_mem_ptr +#define unxlate_dev_mem_ptr unxlate_dev_mem_ptr + extern int ioremap_change_attr(unsigned long vaddr, unsigned long size, enum page_cache_mode pcm); extern void __iomem *ioremap_wc(resource_size_t offset, unsigned long size); +#define ioremap_wc ioremap_wc extern void __iomem *ioremap_wt(resource_size_t offset, unsigned long size); +#define ioremap_wt ioremap_wt extern bool is_early_ioremap_ptep(pte_t *ptep); @@ -365,6 +358,9 @@ extern bool xen_biovec_phys_mergeable(const struct bio_vec *vec1, #define IO_SPACE_LIMIT 0xffff +#include <asm-generic/io.h> +#undef PCI_IOBASE + #ifdef CONFIG_MTRR extern int __must_check arch_phys_wc_index(int handle); #define arch_phys_wc_index arch_phys_wc_index @@ -381,4 +377,12 @@ extern void arch_io_free_memtype_wc(resource_size_t start, resource_size_t size) #define arch_io_reserve_memtype_wc arch_io_reserve_memtype_wc #endif +extern bool arch_memremap_can_ram_remap(resource_size_t offset, + unsigned long size, + unsigned long flags); +#define arch_memremap_can_ram_remap arch_memremap_can_ram_remap + +extern bool phys_mem_access_encrypted(unsigned long phys_addr, + unsigned long size); + #endif /* _ASM_X86_IO_H */ diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h index 668cca540025..9958ceea2fa3 100644 --- a/arch/x86/include/asm/irq.h +++ b/arch/x86/include/asm/irq.h @@ -42,10 +42,6 @@ extern bool handle_irq(struct irq_desc *desc, struct pt_regs *regs); extern __visible unsigned int do_IRQ(struct pt_regs *regs); -/* Interrupt vector management */ -extern DECLARE_BITMAP(used_vectors, NR_VECTORS); -extern int vector_used_by_percpu_irq(unsigned int vector); - extern void init_ISA_irqs(void); #ifdef CONFIG_X86_LOCAL_APIC diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h index 6ca9fd6234e1..aaf8d28b5d00 100644 --- a/arch/x86/include/asm/irq_vectors.h +++ b/arch/x86/include/asm/irq_vectors.h @@ -83,7 +83,6 @@ */ #define X86_PLATFORM_IPI_VECTOR 0xf7 -#define POSTED_INTR_WAKEUP_VECTOR 0xf1 /* * IRQ work vector: */ @@ -98,6 +97,8 @@ /* Vector for KVM to deliver posted interrupt IPI */ #ifdef CONFIG_HAVE_KVM #define POSTED_INTR_VECTOR 0xf2 +#define POSTED_INTR_WAKEUP_VECTOR 0xf1 +#define POSTED_INTR_NESTED_VECTOR 0xf0 #endif /* diff --git a/arch/x86/include/asm/irq_work.h b/arch/x86/include/asm/irq_work.h index f70604125286..ddbb8ea0f5a9 100644 --- a/arch/x86/include/asm/irq_work.h +++ b/arch/x86/include/asm/irq_work.h @@ -3,9 +3,17 @@ #include <asm/cpufeature.h> +#ifdef CONFIG_X86_LOCAL_APIC static inline bool arch_irq_work_has_interrupt(void) { return boot_cpu_has(X86_FEATURE_APIC); } +extern void arch_irq_work_raise(void); +#else +static inline bool arch_irq_work_has_interrupt(void) +{ + return false; +} +#endif #endif /* _ASM_IRQ_WORK_H */ diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h index 70ef205489f0..942c1f444da8 100644 --- a/arch/x86/include/asm/kexec.h +++ b/arch/x86/include/asm/kexec.h @@ -147,7 +147,8 @@ unsigned long relocate_kernel(unsigned long indirection_page, unsigned long page_list, unsigned long start_address, - unsigned int preserve_context); + unsigned int preserve_context, + unsigned int sme_active); #endif #define ARCH_HAS_KIMAGE_ARCH @@ -207,6 +208,14 @@ struct kexec_entry64_regs { uint64_t r15; uint64_t rip; }; + +extern int arch_kexec_post_alloc_pages(void *vaddr, unsigned int pages, + gfp_t gfp); +#define arch_kexec_post_alloc_pages arch_kexec_post_alloc_pages + +extern void arch_kexec_pre_free_pages(void *vaddr, unsigned int pages); +#define arch_kexec_pre_free_pages arch_kexec_pre_free_pages + #endif typedef void crash_vmclear_fn(void); diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 87ac4fba6d8e..369e41c23f07 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -492,6 +492,7 @@ struct kvm_vcpu_arch { unsigned long cr4; unsigned long cr4_guest_owned_bits; unsigned long cr8; + u32 pkru; u32 hflags; u64 efer; u64 apic_base; @@ -1078,7 +1079,7 @@ void kvm_mmu_init_vm(struct kvm *kvm); void kvm_mmu_uninit_vm(struct kvm *kvm); void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 p_mask, - u64 acc_track_mask); + u64 acc_track_mask, u64 me_mask); void kvm_mmu_reset_context(struct kvm_vcpu *vcpu); void kvm_mmu_slot_remove_write_access(struct kvm *kvm, @@ -1374,8 +1375,6 @@ int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu); int kvm_cpu_get_interrupt(struct kvm_vcpu *v); void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event); void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu); -void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm, - unsigned long address); void kvm_define_shared_msr(unsigned index, u32 msr); int kvm_set_shared_msr(unsigned index, u64 val, u64 mask); diff --git a/arch/x86/include/asm/lguest.h b/arch/x86/include/asm/lguest.h deleted file mode 100644 index 73d0c9b92087..000000000000 --- a/arch/x86/include/asm/lguest.h +++ /dev/null @@ -1,91 +0,0 @@ -#ifndef _ASM_X86_LGUEST_H -#define _ASM_X86_LGUEST_H - -#define GDT_ENTRY_LGUEST_CS 10 -#define GDT_ENTRY_LGUEST_DS 11 -#define LGUEST_CS (GDT_ENTRY_LGUEST_CS * 8) -#define LGUEST_DS (GDT_ENTRY_LGUEST_DS * 8) - -#ifndef __ASSEMBLY__ -#include <asm/desc.h> - -#define GUEST_PL 1 - -/* Page for Switcher text itself, then two pages per cpu */ -#define SWITCHER_TEXT_PAGES (1) -#define SWITCHER_STACK_PAGES (2 * nr_cpu_ids) -#define TOTAL_SWITCHER_PAGES (SWITCHER_TEXT_PAGES + SWITCHER_STACK_PAGES) - -/* Where we map the Switcher, in both Host and Guest. */ -extern unsigned long switcher_addr; - -/* Found in switcher.S */ -extern unsigned long default_idt_entries[]; - -/* Declarations for definitions in arch/x86/lguest/head_32.S */ -extern char lguest_noirq_iret[]; -extern const char lgstart_cli[], lgend_cli[]; -extern const char lgstart_pushf[], lgend_pushf[]; - -extern void lguest_iret(void); -extern void lguest_init(void); - -struct lguest_regs { - /* Manually saved part. */ - unsigned long eax, ebx, ecx, edx; - unsigned long esi, edi, ebp; - unsigned long gs; - unsigned long fs, ds, es; - unsigned long trapnum, errcode; - /* Trap pushed part */ - unsigned long eip; - unsigned long cs; - unsigned long eflags; - unsigned long esp; - unsigned long ss; -}; - -/* This is a guest-specific page (mapped ro) into the guest. */ -struct lguest_ro_state { - /* Host information we need to restore when we switch back. */ - u32 host_cr3; - struct desc_ptr host_idt_desc; - struct desc_ptr host_gdt_desc; - u32 host_sp; - - /* Fields which are used when guest is running. */ - struct desc_ptr guest_idt_desc; - struct desc_ptr guest_gdt_desc; - struct x86_hw_tss guest_tss; - struct desc_struct guest_idt[IDT_ENTRIES]; - struct desc_struct guest_gdt[GDT_ENTRIES]; -}; - -struct lg_cpu_arch { - /* The GDT entries copied into lguest_ro_state when running. */ - struct desc_struct gdt[GDT_ENTRIES]; - - /* The IDT entries: some copied into lguest_ro_state when running. */ - struct desc_struct idt[IDT_ENTRIES]; - - /* The address of the last guest-visible pagefault (ie. cr2). */ - unsigned long last_pagefault; -}; - -static inline void lguest_set_ts(void) -{ - u32 cr0; - - cr0 = read_cr0(); - if (!(cr0 & 8)) - write_cr0(cr0 | 8); -} - -/* Full 4G segment descriptors, suitable for CS and DS. */ -#define FULL_EXEC_SEGMENT \ - ((struct desc_struct)GDT_ENTRY_INIT(0xc09b, 0, 0xfffff)) -#define FULL_SEGMENT ((struct desc_struct)GDT_ENTRY_INIT(0xc093, 0, 0xfffff)) - -#endif /* __ASSEMBLY__ */ - -#endif /* _ASM_X86_LGUEST_H */ diff --git a/arch/x86/include/asm/lguest_hcall.h b/arch/x86/include/asm/lguest_hcall.h deleted file mode 100644 index 6c119cfae218..000000000000 --- a/arch/x86/include/asm/lguest_hcall.h +++ /dev/null @@ -1,74 +0,0 @@ -/* Architecture specific portion of the lguest hypercalls */ -#ifndef _ASM_X86_LGUEST_HCALL_H -#define _ASM_X86_LGUEST_HCALL_H - -#define LHCALL_FLUSH_ASYNC 0 -#define LHCALL_LGUEST_INIT 1 -#define LHCALL_SHUTDOWN 2 -#define LHCALL_NEW_PGTABLE 4 -#define LHCALL_FLUSH_TLB 5 -#define LHCALL_LOAD_IDT_ENTRY 6 -#define LHCALL_SET_STACK 7 -#define LHCALL_SET_CLOCKEVENT 9 -#define LHCALL_HALT 10 -#define LHCALL_SET_PMD 13 -#define LHCALL_SET_PTE 14 -#define LHCALL_SET_PGD 15 -#define LHCALL_LOAD_TLS 16 -#define LHCALL_LOAD_GDT_ENTRY 18 -#define LHCALL_SEND_INTERRUPTS 19 - -#define LGUEST_TRAP_ENTRY 0x1F - -/* Argument number 3 to LHCALL_LGUEST_SHUTDOWN */ -#define LGUEST_SHUTDOWN_POWEROFF 1 -#define LGUEST_SHUTDOWN_RESTART 2 - -#ifndef __ASSEMBLY__ -#include <asm/hw_irq.h> - -/*G:030 - * But first, how does our Guest contact the Host to ask for privileged - * operations? There are two ways: the direct way is to make a "hypercall", - * to make requests of the Host Itself. - * - * Our hypercall mechanism uses the highest unused trap code (traps 32 and - * above are used by real hardware interrupts). Seventeen hypercalls are - * available: the hypercall number is put in the %eax register, and the - * arguments (when required) are placed in %ebx, %ecx, %edx and %esi. - * If a return value makes sense, it's returned in %eax. - * - * Grossly invalid calls result in Sudden Death at the hands of the vengeful - * Host, rather than returning failure. This reflects Winston Churchill's - * definition of a gentleman: "someone who is only rude intentionally". - */ -static inline unsigned long -hcall(unsigned long call, - unsigned long arg1, unsigned long arg2, unsigned long arg3, - unsigned long arg4) -{ - /* "int" is the Intel instruction to trigger a trap. */ - asm volatile("int $" __stringify(LGUEST_TRAP_ENTRY) - /* The call in %eax (aka "a") might be overwritten */ - : "=a"(call) - /* The arguments are in %eax, %ebx, %ecx, %edx & %esi */ - : "a"(call), "b"(arg1), "c"(arg2), "d"(arg3), "S"(arg4) - /* "memory" means this might write somewhere in memory. - * This isn't true for all calls, but it's safe to tell - * gcc that it might happen so it doesn't get clever. */ - : "memory"); - return call; -} -/*:*/ - -/* Can't use our min() macro here: needs to be a constant */ -#define LGUEST_IRQS (NR_IRQS < 32 ? NR_IRQS: 32) - -#define LHCALL_RING_SIZE 64 -struct hcall_args { - /* These map directly onto eax/ebx/ecx/edx/esi in struct lguest_regs */ - unsigned long arg0, arg1, arg2, arg3, arg4; -}; - -#endif /* !__ASSEMBLY__ */ -#endif /* _ASM_X86_LGUEST_HCALL_H */ diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h new file mode 100644 index 000000000000..8e618fcf1f7c --- /dev/null +++ b/arch/x86/include/asm/mem_encrypt.h @@ -0,0 +1,80 @@ +/* + * AMD Memory Encryption Support + * + * Copyright (C) 2016 Advanced Micro Devices, Inc. + * + * Author: Tom Lendacky <thomas.lendacky@amd.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef __X86_MEM_ENCRYPT_H__ +#define __X86_MEM_ENCRYPT_H__ + +#ifndef __ASSEMBLY__ + +#include <linux/init.h> + +#include <asm/bootparam.h> + +#ifdef CONFIG_AMD_MEM_ENCRYPT + +extern unsigned long sme_me_mask; + +void sme_encrypt_execute(unsigned long encrypted_kernel_vaddr, + unsigned long decrypted_kernel_vaddr, + unsigned long kernel_len, + unsigned long encryption_wa, + unsigned long encryption_pgd); + +void __init sme_early_encrypt(resource_size_t paddr, + unsigned long size); +void __init sme_early_decrypt(resource_size_t paddr, + unsigned long size); + +void __init sme_map_bootdata(char *real_mode_data); +void __init sme_unmap_bootdata(char *real_mode_data); + +void __init sme_early_init(void); + +void __init sme_encrypt_kernel(void); +void __init sme_enable(struct boot_params *bp); + +/* Architecture __weak replacement functions */ +void __init mem_encrypt_init(void); + +void swiotlb_set_mem_attributes(void *vaddr, unsigned long size); + +#else /* !CONFIG_AMD_MEM_ENCRYPT */ + +#define sme_me_mask 0UL + +static inline void __init sme_early_encrypt(resource_size_t paddr, + unsigned long size) { } +static inline void __init sme_early_decrypt(resource_size_t paddr, + unsigned long size) { } + +static inline void __init sme_map_bootdata(char *real_mode_data) { } +static inline void __init sme_unmap_bootdata(char *real_mode_data) { } + +static inline void __init sme_early_init(void) { } + +static inline void __init sme_encrypt_kernel(void) { } +static inline void __init sme_enable(struct boot_params *bp) { } + +#endif /* CONFIG_AMD_MEM_ENCRYPT */ + +/* + * The __sme_pa() and __sme_pa_nodebug() macros are meant for use when + * writing to or comparing values from the cr3 register. Having the + * encryption mask set in cr3 enables the PGD entry to be encrypted and + * avoid special case handling of PGD allocations. + */ +#define __sme_pa(x) (__pa(x) | sme_me_mask) +#define __sme_pa_nodebug(x) (__pa_nodebug(x) | sme_me_mask) + +#endif /* __ASSEMBLY__ */ + +#endif /* __X86_MEM_ENCRYPT_H__ */ diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h index 79b647a7ebd0..bb8c597c2248 100644 --- a/arch/x86/include/asm/mmu.h +++ b/arch/x86/include/asm/mmu.h @@ -3,12 +3,28 @@ #include <linux/spinlock.h> #include <linux/mutex.h> +#include <linux/atomic.h> /* - * The x86 doesn't have a mmu context, but - * we put the segment information here. + * x86 has arch-specific MMU state beyond what lives in mm_struct. */ typedef struct { + /* + * ctx_id uniquely identifies this mm_struct. A ctx_id will never + * be reused, and zero is not a valid ctx_id. + */ + u64 ctx_id; + + /* + * Any code that needs to do any sort of TLB flushing for this + * mm will first make its changes to the page tables, then + * increment tlb_gen, then flush. This lets the low-level + * flushing code keep track of what needs flushing. + * + * This is not used on Xen PV. + */ + atomic64_t tlb_gen; + #ifdef CONFIG_MODIFY_LDT_SYSCALL struct ldt_struct *ldt; #endif @@ -37,6 +53,11 @@ typedef struct { #endif } mm_context_t; +#define INIT_MM_CONTEXT(mm) \ + .context = { \ + .ctx_id = 1, \ + } + void leave_mm(int cpu); #endif /* _ASM_X86_MMU_H */ diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 265c907d7d4c..7ae318c340d9 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -12,6 +12,9 @@ #include <asm/tlbflush.h> #include <asm/paravirt.h> #include <asm/mpx.h> + +extern atomic64_t last_mm_ctx_id; + #ifndef CONFIG_PARAVIRT static inline void paravirt_activate_mm(struct mm_struct *prev, struct mm_struct *next) @@ -125,13 +128,18 @@ static inline void switch_ldt(struct mm_struct *prev, struct mm_struct *next) static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) { - if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) - this_cpu_write(cpu_tlbstate.state, TLBSTATE_LAZY); + int cpu = smp_processor_id(); + + if (cpumask_test_cpu(cpu, mm_cpumask(mm))) + cpumask_clear_cpu(cpu, mm_cpumask(mm)); } static inline int init_new_context(struct task_struct *tsk, struct mm_struct *mm) { + mm->context.ctx_id = atomic64_inc_return(&last_mm_ctx_id); + atomic64_set(&mm->context.tlb_gen, 0); + #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS if (cpu_feature_enabled(X86_FEATURE_OSPKE)) { /* pkey 0 is the default and always allocated */ @@ -140,9 +148,7 @@ static inline int init_new_context(struct task_struct *tsk, mm->context.execute_only_pkey = -1; } #endif - init_new_context_ldt(tsk, mm); - - return 0; + return init_new_context_ldt(tsk, mm); } static inline void destroy_context(struct mm_struct *mm) { @@ -292,6 +298,9 @@ static inline unsigned long __get_current_cr3_fast(void) { unsigned long cr3 = __pa(this_cpu_read(cpu_tlbstate.loaded_mm)->pgd); + if (static_cpu_has(X86_FEATURE_PCID)) + cr3 |= this_cpu_read(cpu_tlbstate.loaded_mm_asid); + /* For now, be very restrictive about when this can be called. */ VM_WARN_ON(in_nmi() || preemptible()); diff --git a/arch/x86/include/asm/module.h b/arch/x86/include/asm/module.h index e3b7819caeef..9eb7c718aaf8 100644 --- a/arch/x86/include/asm/module.h +++ b/arch/x86/include/asm/module.h @@ -2,6 +2,15 @@ #define _ASM_X86_MODULE_H #include <asm-generic/module.h> +#include <asm/orc_types.h> + +struct mod_arch_specific { +#ifdef CONFIG_ORC_UNWINDER + unsigned int num_orcs; + int *orc_unwind_ip; + struct orc_entry *orc_unwind; +#endif +}; #ifdef CONFIG_X86_64 /* X86_64 does not define MODULE_PROC_FAMILY */ diff --git a/arch/x86/include/asm/mpx.h b/arch/x86/include/asm/mpx.h index a0d662be4c5b..7d7404756bb4 100644 --- a/arch/x86/include/asm/mpx.h +++ b/arch/x86/include/asm/mpx.h @@ -73,6 +73,9 @@ static inline void mpx_mm_init(struct mm_struct *mm) } void mpx_notify_unmap(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long start, unsigned long end); + +unsigned long mpx_unmapped_area_check(unsigned long addr, unsigned long len, + unsigned long flags); #else static inline siginfo_t *mpx_generate_siginfo(struct pt_regs *regs) { @@ -94,6 +97,12 @@ static inline void mpx_notify_unmap(struct mm_struct *mm, unsigned long start, unsigned long end) { } + +static inline unsigned long mpx_unmapped_area_check(unsigned long addr, + unsigned long len, unsigned long flags) +{ + return addr; +} #endif /* CONFIG_X86_INTEL_MPX */ #endif /* _ASM_X86_MPX_H */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 5573c75f8e4c..17f5c12e1afd 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -356,6 +356,8 @@ #define MSR_K8_TOP_MEM1 0xc001001a #define MSR_K8_TOP_MEM2 0xc001001d #define MSR_K8_SYSCFG 0xc0010010 +#define MSR_K8_SYSCFG_MEM_ENCRYPT_BIT 23 +#define MSR_K8_SYSCFG_MEM_ENCRYPT BIT_ULL(MSR_K8_SYSCFG_MEM_ENCRYPT_BIT) #define MSR_K8_INT_PENDING_MSG 0xc0010055 /* C1E active bits in int pending message */ #define K8_INTP_C1E_ACTIVE_MASK 0x18000000 diff --git a/arch/x86/include/asm/orc_lookup.h b/arch/x86/include/asm/orc_lookup.h new file mode 100644 index 000000000000..91c8d868424d --- /dev/null +++ b/arch/x86/include/asm/orc_lookup.h @@ -0,0 +1,46 @@ +/* + * Copyright (C) 2017 Josh Poimboeuf <jpoimboe@redhat.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see <http://www.gnu.org/licenses/>. + */ +#ifndef _ORC_LOOKUP_H +#define _ORC_LOOKUP_H + +/* + * This is a lookup table for speeding up access to the .orc_unwind table. + * Given an input address offset, the corresponding lookup table entry + * specifies a subset of the .orc_unwind table to search. + * + * Each block represents the end of the previous range and the start of the + * next range. An extra block is added to give the last range an end. + * + * The block size should be a power of 2 to avoid a costly 'div' instruction. + * + * A block size of 256 was chosen because it roughly doubles unwinder + * performance while only adding ~5% to the ORC data footprint. + */ +#define LOOKUP_BLOCK_ORDER 8 +#define LOOKUP_BLOCK_SIZE (1 << LOOKUP_BLOCK_ORDER) + +#ifndef LINKER_SCRIPT + +extern unsigned int orc_lookup[]; +extern unsigned int orc_lookup_end[]; + +#define LOOKUP_START_IP (unsigned long)_stext +#define LOOKUP_STOP_IP (unsigned long)_etext + +#endif /* LINKER_SCRIPT */ + +#endif /* _ORC_LOOKUP_H */ diff --git a/arch/x86/include/asm/orc_types.h b/arch/x86/include/asm/orc_types.h new file mode 100644 index 000000000000..9c9dc579bd7d --- /dev/null +++ b/arch/x86/include/asm/orc_types.h @@ -0,0 +1,107 @@ +/* + * Copyright (C) 2017 Josh Poimboeuf <jpoimboe@redhat.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef _ORC_TYPES_H +#define _ORC_TYPES_H + +#include <linux/types.h> +#include <linux/compiler.h> + +/* + * The ORC_REG_* registers are base registers which are used to find other + * registers on the stack. + * + * ORC_REG_PREV_SP, also known as DWARF Call Frame Address (CFA), is the + * address of the previous frame: the caller's SP before it called the current + * function. + * + * ORC_REG_UNDEFINED means the corresponding register's value didn't change in + * the current frame. + * + * The most commonly used base registers are SP and BP -- which the previous SP + * is usually based on -- and PREV_SP and UNDEFINED -- which the previous BP is + * usually based on. + * + * The rest of the base registers are needed for special cases like entry code + * and GCC realigned stacks. + */ +#define ORC_REG_UNDEFINED 0 +#define ORC_REG_PREV_SP 1 +#define ORC_REG_DX 2 +#define ORC_REG_DI 3 +#define ORC_REG_BP 4 +#define ORC_REG_SP 5 +#define ORC_REG_R10 6 +#define ORC_REG_R13 7 +#define ORC_REG_BP_INDIRECT 8 +#define ORC_REG_SP_INDIRECT 9 +#define ORC_REG_MAX 15 + +/* + * ORC_TYPE_CALL: Indicates that sp_reg+sp_offset resolves to PREV_SP (the + * caller's SP right before it made the call). Used for all callable + * functions, i.e. all C code and all callable asm functions. + * + * ORC_TYPE_REGS: Used in entry code to indicate that sp_reg+sp_offset points + * to a fully populated pt_regs from a syscall, interrupt, or exception. + * + * ORC_TYPE_REGS_IRET: Used in entry code to indicate that sp_reg+sp_offset + * points to the iret return frame. + * + * The UNWIND_HINT macros are used only for the unwind_hint struct. They + * aren't used in struct orc_entry due to size and complexity constraints. + * Objtool converts them to real types when it converts the hints to orc + * entries. + */ +#define ORC_TYPE_CALL 0 +#define ORC_TYPE_REGS 1 +#define ORC_TYPE_REGS_IRET 2 +#define UNWIND_HINT_TYPE_SAVE 3 +#define UNWIND_HINT_TYPE_RESTORE 4 + +#ifndef __ASSEMBLY__ +/* + * This struct is more or less a vastly simplified version of the DWARF Call + * Frame Information standard. It contains only the necessary parts of DWARF + * CFI, simplified for ease of access by the in-kernel unwinder. It tells the + * unwinder how to find the previous SP and BP (and sometimes entry regs) on + * the stack for a given code address. Each instance of the struct corresponds + * to one or more code locations. + */ +struct orc_entry { + s16 sp_offset; + s16 bp_offset; + unsigned sp_reg:4; + unsigned bp_reg:4; + unsigned type:2; +} __packed; + +/* + * This struct is used by asm and inline asm code to manually annotate the + * location of registers on the stack for the ORC unwinder. + * + * Type can be either ORC_TYPE_* or UNWIND_HINT_TYPE_*. + */ +struct unwind_hint { + u32 ip; + s16 sp_offset; + u8 sp_reg; + u8 type; +}; +#endif /* __ASSEMBLY__ */ + +#endif /* _ORC_TYPES_H */ diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h index b4a0d43248cf..b50df06ad251 100644 --- a/arch/x86/include/asm/page_64.h +++ b/arch/x86/include/asm/page_64.h @@ -51,6 +51,10 @@ static inline void clear_page(void *page) void copy_page(void *to, void *from); +#ifdef CONFIG_X86_MCE +#define arch_unmap_kpfn arch_unmap_kpfn +#endif + #endif /* !__ASSEMBLY__ */ #ifdef CONFIG_X86_VSYSCALL_EMULATION diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h index 7bd0099384ca..b98ed9d14630 100644 --- a/arch/x86/include/asm/page_types.h +++ b/arch/x86/include/asm/page_types.h @@ -3,6 +3,7 @@ #include <linux/const.h> #include <linux/types.h> +#include <linux/mem_encrypt.h> /* PAGE_SHIFT determines the page size */ #define PAGE_SHIFT 12 @@ -15,7 +16,7 @@ #define PUD_PAGE_SIZE (_AC(1, UL) << PUD_SHIFT) #define PUD_PAGE_MASK (~(PUD_PAGE_SIZE-1)) -#define __PHYSICAL_MASK ((phys_addr_t)((1ULL << __PHYSICAL_MASK_SHIFT) - 1)) +#define __PHYSICAL_MASK ((phys_addr_t)(__sme_clr((1ULL << __PHYSICAL_MASK_SHIFT) - 1))) #define __VIRTUAL_MASK ((1UL << __VIRTUAL_MASK_SHIFT) - 1) /* Cast *PAGE_MASK to a signed type so that it is sign-extended if diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 9ccac1926587..c25dd22f7c70 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -960,11 +960,6 @@ extern void default_banner(void); #define GET_CR2_INTO_RAX \ call PARA_INDIRECT(pv_mmu_ops+PV_MMU_read_cr2) -#define PARAVIRT_ADJUST_EXCEPTION_FRAME \ - PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_adjust_exception_frame), \ - CLBR_NONE, \ - call PARA_INDIRECT(pv_irq_ops+PV_IRQ_adjust_exception_frame)) - #define USERGS_SYSRET64 \ PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret64), \ CLBR_NONE, \ diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 9ffc36bfe4cd..6b64fc6367f2 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -196,9 +196,6 @@ struct pv_irq_ops { void (*safe_halt)(void); void (*halt)(void); -#ifdef CONFIG_X86_64 - void (*adjust_exception_frame)(void); -#endif } __no_randomize_layout; struct pv_mmu_ops { diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 77037b6f1caa..bbeae4a2bd01 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -1,6 +1,7 @@ #ifndef _ASM_X86_PGTABLE_H #define _ASM_X86_PGTABLE_H +#include <linux/mem_encrypt.h> #include <asm/page.h> #include <asm/pgtable_types.h> @@ -13,9 +14,18 @@ cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS))) \ : (prot)) +/* + * Macros to add or remove encryption attribute + */ +#define pgprot_encrypted(prot) __pgprot(__sme_set(pgprot_val(prot))) +#define pgprot_decrypted(prot) __pgprot(__sme_clr(pgprot_val(prot))) + #ifndef __ASSEMBLY__ #include <asm/x86_init.h> +extern pgd_t early_top_pgt[PTRS_PER_PGD]; +int __init __early_make_pgtable(unsigned long address, pmdval_t pmd); + void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd); void ptdump_walk_pgd_level_checkwx(void); @@ -38,6 +48,8 @@ extern struct list_head pgd_list; extern struct mm_struct *pgd_page_get_mm(struct page *page); +extern pmdval_t early_pmd_flags; + #ifdef CONFIG_PARAVIRT #include <asm/paravirt.h> #else /* !CONFIG_PARAVIRT */ @@ -195,6 +207,11 @@ static inline unsigned long p4d_pfn(p4d_t p4d) return (p4d_val(p4d) & p4d_pfn_mask(p4d)) >> PAGE_SHIFT; } +static inline unsigned long pgd_pfn(pgd_t pgd) +{ + return (pgd_val(pgd) & PTE_PFN_MASK) >> PAGE_SHIFT; +} + static inline int p4d_large(p4d_t p4d) { /* No 512 GiB pages yet */ @@ -704,8 +721,7 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd) * Currently stuck as a macro due to indirect forward reference to * linux/mmzone.h's __section_mem_map_addr() definition: */ -#define pmd_page(pmd) \ - pfn_to_page((pmd_val(pmd) & pmd_pfn_mask(pmd)) >> PAGE_SHIFT) +#define pmd_page(pmd) pfn_to_page(pmd_pfn(pmd)) /* * the pmd page can be thought of an array like this: pmd_t[PTRS_PER_PMD] @@ -773,8 +789,7 @@ static inline unsigned long pud_page_vaddr(pud_t pud) * Currently stuck as a macro due to indirect forward reference to * linux/mmzone.h's __section_mem_map_addr() definition: */ -#define pud_page(pud) \ - pfn_to_page((pud_val(pud) & pud_pfn_mask(pud)) >> PAGE_SHIFT) +#define pud_page(pud) pfn_to_page(pud_pfn(pud)) /* Find an entry in the second-level page table.. */ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address) @@ -824,8 +839,7 @@ static inline unsigned long p4d_page_vaddr(p4d_t p4d) * Currently stuck as a macro due to indirect forward reference to * linux/mmzone.h's __section_mem_map_addr() definition: */ -#define p4d_page(p4d) \ - pfn_to_page((p4d_val(p4d) & p4d_pfn_mask(p4d)) >> PAGE_SHIFT) +#define p4d_page(p4d) pfn_to_page(p4d_pfn(p4d)) /* Find an entry in the third-level page table.. */ static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address) @@ -859,7 +873,7 @@ static inline unsigned long pgd_page_vaddr(pgd_t pgd) * Currently stuck as a macro due to indirect forward reference to * linux/mmzone.h's __section_mem_map_addr() definition: */ -#define pgd_page(pgd) pfn_to_page(pgd_val(pgd) >> PAGE_SHIFT) +#define pgd_page(pgd) pfn_to_page(pgd_pfn(pgd)) /* to find an entry in a page-table-directory. */ static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address) diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index bf9638e1ee42..399261ce904c 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -2,6 +2,8 @@ #define _ASM_X86_PGTABLE_DEFS_H #include <linux/const.h> +#include <linux/mem_encrypt.h> + #include <asm/page_types.h> #define FIRST_USER_ADDRESS 0UL @@ -121,10 +123,10 @@ #define _PAGE_PROTNONE (_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE) -#define _PAGE_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | \ - _PAGE_ACCESSED | _PAGE_DIRTY) -#define _KERNPG_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | \ - _PAGE_DIRTY) +#define _PAGE_TABLE_NOENC (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER |\ + _PAGE_ACCESSED | _PAGE_DIRTY) +#define _KERNPG_TABLE_NOENC (_PAGE_PRESENT | _PAGE_RW | \ + _PAGE_ACCESSED | _PAGE_DIRTY) /* * Set of bits not changed in pte_modify. The pte's @@ -159,6 +161,7 @@ enum page_cache_mode { #define _PAGE_CACHE_MASK (_PAGE_PAT | _PAGE_PCD | _PAGE_PWT) #define _PAGE_NOCACHE (cachemode2protval(_PAGE_CACHE_MODE_UC)) +#define _PAGE_CACHE_WP (cachemode2protval(_PAGE_CACHE_MODE_WP)) #define PAGE_NONE __pgprot(_PAGE_PROTNONE | _PAGE_ACCESSED) #define PAGE_SHARED __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | \ @@ -187,22 +190,42 @@ enum page_cache_mode { #define __PAGE_KERNEL_VVAR (__PAGE_KERNEL_RO | _PAGE_USER) #define __PAGE_KERNEL_LARGE (__PAGE_KERNEL | _PAGE_PSE) #define __PAGE_KERNEL_LARGE_EXEC (__PAGE_KERNEL_EXEC | _PAGE_PSE) +#define __PAGE_KERNEL_WP (__PAGE_KERNEL | _PAGE_CACHE_WP) #define __PAGE_KERNEL_IO (__PAGE_KERNEL) #define __PAGE_KERNEL_IO_NOCACHE (__PAGE_KERNEL_NOCACHE) -#define PAGE_KERNEL __pgprot(__PAGE_KERNEL) -#define PAGE_KERNEL_RO __pgprot(__PAGE_KERNEL_RO) -#define PAGE_KERNEL_EXEC __pgprot(__PAGE_KERNEL_EXEC) -#define PAGE_KERNEL_RX __pgprot(__PAGE_KERNEL_RX) -#define PAGE_KERNEL_NOCACHE __pgprot(__PAGE_KERNEL_NOCACHE) -#define PAGE_KERNEL_LARGE __pgprot(__PAGE_KERNEL_LARGE) -#define PAGE_KERNEL_LARGE_EXEC __pgprot(__PAGE_KERNEL_LARGE_EXEC) -#define PAGE_KERNEL_VSYSCALL __pgprot(__PAGE_KERNEL_VSYSCALL) -#define PAGE_KERNEL_VVAR __pgprot(__PAGE_KERNEL_VVAR) +#ifndef __ASSEMBLY__ + +#define _PAGE_ENC (_AT(pteval_t, sme_me_mask)) + +#define _PAGE_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | \ + _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_ENC) +#define _KERNPG_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | \ + _PAGE_DIRTY | _PAGE_ENC) + +#define __PAGE_KERNEL_ENC (__PAGE_KERNEL | _PAGE_ENC) +#define __PAGE_KERNEL_ENC_WP (__PAGE_KERNEL_WP | _PAGE_ENC) + +#define __PAGE_KERNEL_NOENC (__PAGE_KERNEL) +#define __PAGE_KERNEL_NOENC_WP (__PAGE_KERNEL_WP) + +#define PAGE_KERNEL __pgprot(__PAGE_KERNEL | _PAGE_ENC) +#define PAGE_KERNEL_NOENC __pgprot(__PAGE_KERNEL) +#define PAGE_KERNEL_RO __pgprot(__PAGE_KERNEL_RO | _PAGE_ENC) +#define PAGE_KERNEL_EXEC __pgprot(__PAGE_KERNEL_EXEC | _PAGE_ENC) +#define PAGE_KERNEL_EXEC_NOENC __pgprot(__PAGE_KERNEL_EXEC) +#define PAGE_KERNEL_RX __pgprot(__PAGE_KERNEL_RX | _PAGE_ENC) +#define PAGE_KERNEL_NOCACHE __pgprot(__PAGE_KERNEL_NOCACHE | _PAGE_ENC) +#define PAGE_KERNEL_LARGE __pgprot(__PAGE_KERNEL_LARGE | _PAGE_ENC) +#define PAGE_KERNEL_LARGE_EXEC __pgprot(__PAGE_KERNEL_LARGE_EXEC | _PAGE_ENC) +#define PAGE_KERNEL_VSYSCALL __pgprot(__PAGE_KERNEL_VSYSCALL | _PAGE_ENC) +#define PAGE_KERNEL_VVAR __pgprot(__PAGE_KERNEL_VVAR | _PAGE_ENC) + +#define PAGE_KERNEL_IO __pgprot(__PAGE_KERNEL_IO) +#define PAGE_KERNEL_IO_NOCACHE __pgprot(__PAGE_KERNEL_IO_NOCACHE) -#define PAGE_KERNEL_IO __pgprot(__PAGE_KERNEL_IO) -#define PAGE_KERNEL_IO_NOCACHE __pgprot(__PAGE_KERNEL_IO_NOCACHE) +#endif /* __ASSEMBLY__ */ /* xwr */ #define __P000 PAGE_NONE @@ -287,6 +310,11 @@ static inline p4dval_t native_p4d_val(p4d_t p4d) #else #include <asm-generic/pgtable-nop4d.h> +static inline p4d_t native_make_p4d(pudval_t val) +{ + return (p4d_t) { .pgd = native_make_pgd((pgdval_t)val) }; +} + static inline p4dval_t native_p4d_val(p4d_t p4d) { return native_pgd_val(p4d.pgd); diff --git a/arch/x86/include/asm/processor-flags.h b/arch/x86/include/asm/processor-flags.h index 79aa2f98398d..dc723b64acf0 100644 --- a/arch/x86/include/asm/processor-flags.h +++ b/arch/x86/include/asm/processor-flags.h @@ -2,6 +2,7 @@ #define _ASM_X86_PROCESSOR_FLAGS_H #include <uapi/asm/processor-flags.h> +#include <linux/mem_encrypt.h> #ifdef CONFIG_VM86 #define X86_VM_MASK X86_EFLAGS_VM @@ -32,16 +33,18 @@ * CR3_ADDR_MASK is the mask used by read_cr3_pa(). */ #ifdef CONFIG_X86_64 -/* Mask off the address space ID bits. */ -#define CR3_ADDR_MASK 0x7FFFFFFFFFFFF000ull -#define CR3_PCID_MASK 0xFFFull +/* Mask off the address space ID and SME encryption bits. */ +#define CR3_ADDR_MASK __sme_clr(0x7FFFFFFFFFFFF000ull) +#define CR3_PCID_MASK 0xFFFull +#define CR3_NOFLUSH BIT_ULL(63) #else /* * CR3_ADDR_MASK needs at least bits 31:5 set on PAE systems, and we save * a tiny bit of code size by setting all the bits. */ -#define CR3_ADDR_MASK 0xFFFFFFFFull -#define CR3_PCID_MASK 0ull +#define CR3_ADDR_MASK 0xFFFFFFFFull +#define CR3_PCID_MASK 0ull +#define CR3_NOFLUSH 0 #endif #endif /* _ASM_X86_PROCESSOR_FLAGS_H */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 028245e1c42b..3fa26a61eabc 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -22,6 +22,7 @@ struct vm86; #include <asm/nops.h> #include <asm/special_insns.h> #include <asm/fpu/types.h> +#include <asm/unwind_hints.h> #include <linux/personality.h> #include <linux/cache.h> @@ -29,6 +30,7 @@ struct vm86; #include <linux/math64.h> #include <linux/err.h> #include <linux/irqflags.h> +#include <linux/mem_encrypt.h> /* * We handle most unaligned accesses in hardware. On the other hand @@ -239,9 +241,14 @@ static inline unsigned long read_cr3_pa(void) return __read_cr3() & CR3_ADDR_MASK; } +static inline unsigned long native_read_cr3_pa(void) +{ + return __native_read_cr3() & CR3_ADDR_MASK; +} + static inline void load_cr3(pgd_t *pgdir) { - write_cr3(__pa(pgdir)); + write_cr3(__sme_pa(pgdir)); } #ifdef CONFIG_X86_32 @@ -661,7 +668,7 @@ static inline void sync_core(void) * In case NMI unmasking or performance ever becomes a problem, * the next best option appears to be MOV-to-CR2 and an * unconditional jump. That sequence also works on all CPUs, - * but it will fault at CPL3 (i.e. Xen PV and lguest). + * but it will fault at CPL3 (i.e. Xen PV). * * CPUID is the conventional way, but it's nasty: it doesn't * exist on some 486-like CPUs, and it usually exits to a @@ -684,6 +691,7 @@ static inline void sync_core(void) unsigned int tmp; asm volatile ( + UNWIND_HINT_SAVE "mov %%ss, %0\n\t" "pushq %q0\n\t" "pushq %%rsp\n\t" @@ -693,6 +701,7 @@ static inline void sync_core(void) "pushq %q0\n\t" "pushq $1f\n\t" "iretq\n\t" + UNWIND_HINT_RESTORE "1:" : "=&r" (tmp), "+r" (__sp) : : "cc", "memory"); #endif @@ -802,7 +811,9 @@ static inline void spin_lock_prefetch(const void *x) */ #define IA32_PAGE_OFFSET PAGE_OFFSET #define TASK_SIZE PAGE_OFFSET +#define TASK_SIZE_LOW TASK_SIZE #define TASK_SIZE_MAX TASK_SIZE +#define DEFAULT_MAP_WINDOW TASK_SIZE #define STACK_TOP TASK_SIZE #define STACK_TOP_MAX STACK_TOP @@ -842,7 +853,9 @@ static inline void spin_lock_prefetch(const void *x) * particular problem by preventing anything from being mapped * at the maximum canonical address. */ -#define TASK_SIZE_MAX ((1UL << 47) - PAGE_SIZE) +#define TASK_SIZE_MAX ((1UL << __VIRTUAL_MASK_SHIFT) - PAGE_SIZE) + +#define DEFAULT_MAP_WINDOW ((1UL << 47) - PAGE_SIZE) /* This decides where the kernel will search for a free chunk of vm * space during mmap's. @@ -850,12 +863,14 @@ static inline void spin_lock_prefetch(const void *x) #define IA32_PAGE_OFFSET ((current->personality & ADDR_LIMIT_3GB) ? \ 0xc0000000 : 0xFFFFe000) +#define TASK_SIZE_LOW (test_thread_flag(TIF_ADDR32) ? \ + IA32_PAGE_OFFSET : DEFAULT_MAP_WINDOW) #define TASK_SIZE (test_thread_flag(TIF_ADDR32) ? \ IA32_PAGE_OFFSET : TASK_SIZE_MAX) #define TASK_SIZE_OF(child) ((test_tsk_thread_flag(child, TIF_ADDR32)) ? \ IA32_PAGE_OFFSET : TASK_SIZE_MAX) -#define STACK_TOP TASK_SIZE +#define STACK_TOP TASK_SIZE_LOW #define STACK_TOP_MAX TASK_SIZE_MAX #define INIT_THREAD { \ @@ -876,7 +891,7 @@ extern void start_thread(struct pt_regs *regs, unsigned long new_ip, * space during mmap's. */ #define __TASK_UNMAPPED_BASE(task_size) (PAGE_ALIGN(task_size / 3)) -#define TASK_UNMAPPED_BASE __TASK_UNMAPPED_BASE(TASK_SIZE) +#define TASK_UNMAPPED_BASE __TASK_UNMAPPED_BASE(TASK_SIZE_LOW) #define KSTK_EIP(task) (task_pt_regs(task)->ip) diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h index 8d3964fc5f91..b408b1886195 100644 --- a/arch/x86/include/asm/proto.h +++ b/arch/x86/include/asm/proto.h @@ -24,6 +24,9 @@ void entry_SYSENTER_compat(void); void __end_entry_SYSENTER_compat(void); void entry_SYSCALL_compat(void); void entry_INT80_compat(void); +#if defined(CONFIG_X86_64) && defined(CONFIG_XEN_PV) +void xen_entry_INT80_compat(void); +#endif #endif void x86_configure_nx(void); diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 2b5d686ea9f3..91c04c8e67fa 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -9,6 +9,20 @@ #ifdef __i386__ struct pt_regs { + /* + * NB: 32-bit x86 CPUs are inconsistent as what happens in the + * following cases (where %seg represents a segment register): + * + * - pushl %seg: some do a 16-bit write and leave the high + * bits alone + * - movl %seg, [mem]: some do a 16-bit write despite the movl + * - IDT entry: some (e.g. 486) will leave the high bits of CS + * and (if applicable) SS undefined. + * + * Fortunately, x86-32 doesn't read the high bits on POP or IRET, + * so we can just treat all of the segment registers as 16-bit + * values. + */ unsigned long bx; unsigned long cx; unsigned long dx; @@ -16,16 +30,22 @@ struct pt_regs { unsigned long di; unsigned long bp; unsigned long ax; - unsigned long ds; - unsigned long es; - unsigned long fs; - unsigned long gs; + unsigned short ds; + unsigned short __dsh; + unsigned short es; + unsigned short __esh; + unsigned short fs; + unsigned short __fsh; + unsigned short gs; + unsigned short __gsh; unsigned long orig_ax; unsigned long ip; - unsigned long cs; + unsigned short cs; + unsigned short __csh; unsigned long flags; unsigned long sp; - unsigned long ss; + unsigned short ss; + unsigned short __ssh; }; #else /* __i386__ */ @@ -176,6 +196,17 @@ static inline unsigned long regs_get_register(struct pt_regs *regs, if (offset == offsetof(struct pt_regs, sp) && regs->cs == __KERNEL_CS) return kernel_stack_pointer(regs); + + /* The selector fields are 16-bit. */ + if (offset == offsetof(struct pt_regs, cs) || + offset == offsetof(struct pt_regs, ss) || + offset == offsetof(struct pt_regs, ds) || + offset == offsetof(struct pt_regs, es) || + offset == offsetof(struct pt_regs, fs) || + offset == offsetof(struct pt_regs, gs)) { + return *(u16 *)((unsigned long)regs + offset); + + } #endif return *(unsigned long *)((unsigned long)regs + offset); } diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h index 230e1903acf0..90d91520c13a 100644 --- a/arch/x86/include/asm/realmode.h +++ b/arch/x86/include/asm/realmode.h @@ -1,6 +1,15 @@ #ifndef _ARCH_X86_REALMODE_H #define _ARCH_X86_REALMODE_H +/* + * Flag bit definitions for use with the flags field of the trampoline header + * in the CONFIG_X86_64 variant. + */ +#define TH_FLAGS_SME_ACTIVE_BIT 0 +#define TH_FLAGS_SME_ACTIVE BIT(TH_FLAGS_SME_ACTIVE_BIT) + +#ifndef __ASSEMBLY__ + #include <linux/types.h> #include <asm/io.h> @@ -38,6 +47,7 @@ struct trampoline_header { u64 start; u64 efer; u32 cr4; + u32 flags; #endif }; @@ -69,4 +79,6 @@ static inline size_t real_mode_size_needed(void) void set_real_mode_mem(phys_addr_t mem, size_t size); void reserve_real_mode(void); +#endif /* __ASSEMBLY__ */ + #endif /* _ARCH_X86_REALMODE_H */ diff --git a/arch/x86/include/asm/refcount.h b/arch/x86/include/asm/refcount.h new file mode 100644 index 000000000000..ff871210b9f2 --- /dev/null +++ b/arch/x86/include/asm/refcount.h @@ -0,0 +1,109 @@ +#ifndef __ASM_X86_REFCOUNT_H +#define __ASM_X86_REFCOUNT_H +/* + * x86-specific implementation of refcount_t. Based on PAX_REFCOUNT from + * PaX/grsecurity. + */ +#include <linux/refcount.h> + +/* + * This is the first portion of the refcount error handling, which lives in + * .text.unlikely, and is jumped to from the CPU flag check (in the + * following macros). This saves the refcount value location into CX for + * the exception handler to use (in mm/extable.c), and then triggers the + * central refcount exception. The fixup address for the exception points + * back to the regular execution flow in .text. + */ +#define _REFCOUNT_EXCEPTION \ + ".pushsection .text.unlikely\n" \ + "111:\tlea %[counter], %%" _ASM_CX "\n" \ + "112:\t" ASM_UD0 "\n" \ + ASM_UNREACHABLE \ + ".popsection\n" \ + "113:\n" \ + _ASM_EXTABLE_REFCOUNT(112b, 113b) + +/* Trigger refcount exception if refcount result is negative. */ +#define REFCOUNT_CHECK_LT_ZERO \ + "js 111f\n\t" \ + _REFCOUNT_EXCEPTION + +/* Trigger refcount exception if refcount result is zero or negative. */ +#define REFCOUNT_CHECK_LE_ZERO \ + "jz 111f\n\t" \ + REFCOUNT_CHECK_LT_ZERO + +/* Trigger refcount exception unconditionally. */ +#define REFCOUNT_ERROR \ + "jmp 111f\n\t" \ + _REFCOUNT_EXCEPTION + +static __always_inline void refcount_add(unsigned int i, refcount_t *r) +{ + asm volatile(LOCK_PREFIX "addl %1,%0\n\t" + REFCOUNT_CHECK_LT_ZERO + : [counter] "+m" (r->refs.counter) + : "ir" (i) + : "cc", "cx"); +} + +static __always_inline void refcount_inc(refcount_t *r) +{ + asm volatile(LOCK_PREFIX "incl %0\n\t" + REFCOUNT_CHECK_LT_ZERO + : [counter] "+m" (r->refs.counter) + : : "cc", "cx"); +} + +static __always_inline void refcount_dec(refcount_t *r) +{ + asm volatile(LOCK_PREFIX "decl %0\n\t" + REFCOUNT_CHECK_LE_ZERO + : [counter] "+m" (r->refs.counter) + : : "cc", "cx"); +} + +static __always_inline __must_check +bool refcount_sub_and_test(unsigned int i, refcount_t *r) +{ + GEN_BINARY_SUFFIXED_RMWcc(LOCK_PREFIX "subl", REFCOUNT_CHECK_LT_ZERO, + r->refs.counter, "er", i, "%0", e); +} + +static __always_inline __must_check bool refcount_dec_and_test(refcount_t *r) +{ + GEN_UNARY_SUFFIXED_RMWcc(LOCK_PREFIX "decl", REFCOUNT_CHECK_LT_ZERO, + r->refs.counter, "%0", e); +} + +static __always_inline __must_check +bool refcount_add_not_zero(unsigned int i, refcount_t *r) +{ + int c, result; + + c = atomic_read(&(r->refs)); + do { + if (unlikely(c == 0)) + return false; + + result = c + i; + + /* Did we try to increment from/to an undesirable state? */ + if (unlikely(c < 0 || c == INT_MAX || result < c)) { + asm volatile(REFCOUNT_ERROR + : : [counter] "m" (r->refs.counter) + : "cc", "cx"); + break; + } + + } while (!atomic_try_cmpxchg(&(r->refs), &c, result)); + + return c != 0; +} + +static __always_inline __must_check bool refcount_inc_not_zero(refcount_t *r) +{ + return refcount_add_not_zero(1, r); +} + +#endif diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h index 661dd305694a..045f99211a99 100644 --- a/arch/x86/include/asm/rmwcc.h +++ b/arch/x86/include/asm/rmwcc.h @@ -1,45 +1,56 @@ #ifndef _ASM_X86_RMWcc #define _ASM_X86_RMWcc +#define __CLOBBERS_MEM "memory" +#define __CLOBBERS_MEM_CC_CX "memory", "cc", "cx" + #if !defined(__GCC_ASM_FLAG_OUTPUTS__) && defined(CC_HAVE_ASM_GOTO) /* Use asm goto */ -#define __GEN_RMWcc(fullop, var, cc, ...) \ +#define __GEN_RMWcc(fullop, var, cc, clobbers, ...) \ do { \ asm_volatile_goto (fullop "; j" #cc " %l[cc_label]" \ - : : "m" (var), ## __VA_ARGS__ \ - : "memory" : cc_label); \ + : : [counter] "m" (var), ## __VA_ARGS__ \ + : clobbers : cc_label); \ return 0; \ cc_label: \ return 1; \ } while (0) -#define GEN_UNARY_RMWcc(op, var, arg0, cc) \ - __GEN_RMWcc(op " " arg0, var, cc) +#define __BINARY_RMWcc_ARG " %1, " -#define GEN_BINARY_RMWcc(op, var, vcon, val, arg0, cc) \ - __GEN_RMWcc(op " %1, " arg0, var, cc, vcon (val)) #else /* defined(__GCC_ASM_FLAG_OUTPUTS__) || !defined(CC_HAVE_ASM_GOTO) */ /* Use flags output or a set instruction */ -#define __GEN_RMWcc(fullop, var, cc, ...) \ +#define __GEN_RMWcc(fullop, var, cc, clobbers, ...) \ do { \ bool c; \ asm volatile (fullop ";" CC_SET(cc) \ - : "+m" (var), CC_OUT(cc) (c) \ - : __VA_ARGS__ : "memory"); \ + : [counter] "+m" (var), CC_OUT(cc) (c) \ + : __VA_ARGS__ : clobbers); \ return c; \ } while (0) +#define __BINARY_RMWcc_ARG " %2, " + +#endif /* defined(__GCC_ASM_FLAG_OUTPUTS__) || !defined(CC_HAVE_ASM_GOTO) */ + #define GEN_UNARY_RMWcc(op, var, arg0, cc) \ - __GEN_RMWcc(op " " arg0, var, cc) + __GEN_RMWcc(op " " arg0, var, cc, __CLOBBERS_MEM) + +#define GEN_UNARY_SUFFIXED_RMWcc(op, suffix, var, arg0, cc) \ + __GEN_RMWcc(op " " arg0 "\n\t" suffix, var, cc, \ + __CLOBBERS_MEM_CC_CX) #define GEN_BINARY_RMWcc(op, var, vcon, val, arg0, cc) \ - __GEN_RMWcc(op " %2, " arg0, var, cc, vcon (val)) + __GEN_RMWcc(op __BINARY_RMWcc_ARG arg0, var, cc, \ + __CLOBBERS_MEM, vcon (val)) -#endif /* defined(__GCC_ASM_FLAG_OUTPUTS__) || !defined(CC_HAVE_ASM_GOTO) */ +#define GEN_BINARY_SUFFIXED_RMWcc(op, suffix, var, vcon, val, arg0, cc) \ + __GEN_RMWcc(op __BINARY_RMWcc_ARG arg0 "\n\t" suffix, var, cc, \ + __CLOBBERS_MEM_CC_CX, vcon (val)) #endif /* _ASM_X86_RMWcc */ diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h index 1549caa098f0..066aaf813141 100644 --- a/arch/x86/include/asm/segment.h +++ b/arch/x86/include/asm/segment.h @@ -238,9 +238,7 @@ #ifndef __ASSEMBLY__ extern const char early_idt_handler_array[NUM_EXCEPTION_VECTORS][EARLY_IDT_HANDLER_SIZE]; -#ifdef CONFIG_TRACING -# define trace_early_idt_handler_array early_idt_handler_array -#endif +extern void early_ignore_irq(void); /* * Load a segment. Fall back on loading the zero segment if something goes diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h index eaec6c364e42..cd71273ec49d 100644 --- a/arch/x86/include/asm/set_memory.h +++ b/arch/x86/include/asm/set_memory.h @@ -11,6 +11,7 @@ * Executability : eXeutable, NoteXecutable * Read/Write : ReadOnly, ReadWrite * Presence : NotPresent + * Encryption : Encrypted, Decrypted * * Within a category, the attributes are mutually exclusive. * @@ -42,6 +43,8 @@ int set_memory_wt(unsigned long addr, int numpages); int set_memory_wb(unsigned long addr, int numpages); int set_memory_np(unsigned long addr, int numpages); int set_memory_4k(unsigned long addr, int numpages); +int set_memory_encrypted(unsigned long addr, int numpages); +int set_memory_decrypted(unsigned long addr, int numpages); int set_memory_array_uc(unsigned long *addr, int addrinarray); int set_memory_array_wc(unsigned long *addr, int addrinarray); diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index e00e1bd6e7b3..5161da1a0fa0 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -98,6 +98,7 @@ struct thread_info { #define TIF_SYSCALL_TRACEPOINT 28 /* syscall tracepoint instrumentation */ #define TIF_ADDR32 29 /* 32-bit address space on 64 bits */ #define TIF_X32 30 /* 32-bit native x86-64 binary */ +#define TIF_FSCHECK 31 /* Check FS is USER_DS on return */ #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) @@ -122,6 +123,7 @@ struct thread_info { #define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT) #define _TIF_ADDR32 (1 << TIF_ADDR32) #define _TIF_X32 (1 << TIF_X32) +#define _TIF_FSCHECK (1 << TIF_FSCHECK) /* * work to do in syscall_trace_enter(). Also includes TIF_NOHZ for @@ -137,7 +139,8 @@ struct thread_info { (_TIF_SYSCALL_TRACE | _TIF_NOTIFY_RESUME | _TIF_SIGPENDING | \ _TIF_NEED_RESCHED | _TIF_SINGLESTEP | _TIF_SYSCALL_EMU | \ _TIF_SYSCALL_AUDIT | _TIF_USER_RETURN_NOTIFY | _TIF_UPROBE | \ - _TIF_PATCH_PENDING | _TIF_NOHZ | _TIF_SYSCALL_TRACEPOINT) + _TIF_PATCH_PENDING | _TIF_NOHZ | _TIF_SYSCALL_TRACEPOINT | \ + _TIF_FSCHECK) /* flags to check in __switch_to() */ #define _TIF_WORK_CTXSW \ diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h index c7797307fc2b..79a4ca6a9606 100644 --- a/arch/x86/include/asm/tlb.h +++ b/arch/x86/include/asm/tlb.h @@ -15,4 +15,18 @@ #include <asm-generic/tlb.h> +/* + * While x86 architecture in general requires an IPI to perform TLB + * shootdown, enablement code for several hypervisors overrides + * .flush_tlb_others hook in pv_mmu_ops and implements it by issuing + * a hypercall. To keep software pagetable walkers safe in this case we + * switch to RCU based table free (HAVE_RCU_TABLE_FREE). See the comment + * below 'ifdef CONFIG_HAVE_RCU_TABLE_FREE' in include/asm-generic/tlb.h + * for more details. + */ +static inline void __tlb_remove_table(void *table) +{ + free_page_and_swap_cache(table); +} + #endif /* _ASM_X86_TLB_H */ diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 50ea3482e1d1..d23e61dc0640 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -57,6 +57,23 @@ static inline void invpcid_flush_all_nonglobals(void) __invpcid(0, 0, INVPCID_TYPE_ALL_NON_GLOBAL); } +static inline u64 inc_mm_tlb_gen(struct mm_struct *mm) +{ + u64 new_tlb_gen; + + /* + * Bump the generation count. This also serves as a full barrier + * that synchronizes with switch_mm(): callers are required to order + * their read of mm_cpumask after their writes to the paging + * structures. + */ + smp_mb__before_atomic(); + new_tlb_gen = atomic64_inc_return(&mm->context.tlb_gen); + smp_mb__after_atomic(); + + return new_tlb_gen; +} + #ifdef CONFIG_PARAVIRT #include <asm/paravirt.h> #else @@ -65,6 +82,17 @@ static inline void invpcid_flush_all_nonglobals(void) #define __flush_tlb_single(addr) __native_flush_tlb_single(addr) #endif +/* + * 6 because 6 should be plenty and struct tlb_state will fit in + * two cache lines. + */ +#define TLB_NR_DYN_ASIDS 6 + +struct tlb_context { + u64 ctx_id; + u64 tlb_gen; +}; + struct tlb_state { /* * cpu_tlbstate.loaded_mm should match CR3 whenever interrupts @@ -73,13 +101,35 @@ struct tlb_state { * mode even if we've already switched back to swapper_pg_dir. */ struct mm_struct *loaded_mm; - int state; + u16 loaded_mm_asid; + u16 next_asid; /* * Access to this CR4 shadow and to H/W CR4 is protected by * disabling interrupts when modifying either one. */ unsigned long cr4; + + /* + * This is a list of all contexts that might exist in the TLB. + * There is one per ASID that we use, and the ASID (what the + * CPU calls PCID) is the index into ctxts. + * + * For each context, ctx_id indicates which mm the TLB's user + * entries came from. As an invariant, the TLB will never + * contain entries that are out-of-date as when that mm reached + * the tlb_gen in the list. + * + * To be clear, this means that it's legal for the TLB code to + * flush the TLB without updating tlb_gen. This can happen + * (for now, at least) due to paravirt remote flushes. + * + * NB: context 0 is a bit special, since it's also used by + * various bits of init code. This is fine -- code that + * isn't aware of PCID will end up harmlessly flushing + * context 0. + */ + struct tlb_context ctxs[TLB_NR_DYN_ASIDS]; }; DECLARE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate); @@ -207,6 +257,14 @@ static inline void __flush_tlb_all(void) __flush_tlb_global(); else __flush_tlb(); + + /* + * Note: if we somehow had PCID but not PGE, then this wouldn't work -- + * we'd end up flushing kernel translations for the current ASID but + * we might fail to flush kernel translations for other cached ASIDs. + * + * To avoid this issue, we force PCID off if PGE is off. + */ } static inline void __flush_tlb_one(unsigned long addr) @@ -231,9 +289,26 @@ static inline void __flush_tlb_one(unsigned long addr) * and page-granular flushes are available only on i486 and up. */ struct flush_tlb_info { - struct mm_struct *mm; - unsigned long start; - unsigned long end; + /* + * We support several kinds of flushes. + * + * - Fully flush a single mm. .mm will be set, .end will be + * TLB_FLUSH_ALL, and .new_tlb_gen will be the tlb_gen to + * which the IPI sender is trying to catch us up. + * + * - Partially flush a single mm. .mm will be set, .start and + * .end will indicate the range, and .new_tlb_gen will be set + * such that the changes between generation .new_tlb_gen-1 and + * .new_tlb_gen are entirely contained in the indicated range. + * + * - Fully flush all mms whose tlb_gens have been updated. .mm + * will be NULL, .end will be TLB_FLUSH_ALL, and .new_tlb_gen + * will be zero. + */ + struct mm_struct *mm; + unsigned long start; + unsigned long end; + u64 new_tlb_gen; }; #define local_flush_tlb() __flush_tlb() @@ -256,12 +331,10 @@ static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long a) void native_flush_tlb_others(const struct cpumask *cpumask, const struct flush_tlb_info *info); -#define TLBSTATE_OK 1 -#define TLBSTATE_LAZY 2 - static inline void arch_tlbbatch_add_mm(struct arch_tlbflush_unmap_batch *batch, struct mm_struct *mm) { + inc_mm_tlb_gen(mm); cpumask_or(&batch->cpumask, &batch->cpumask, mm_cpumask(mm)); } diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index 6358a85e2270..c1d2a9892352 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -75,12 +75,6 @@ static inline const struct cpumask *cpumask_of_node(int node) extern void setup_node_to_cpumask_map(void); -/* - * Returns the number of the node containing Node 'node'. This - * architecture is flat, so it is a pretty simple function! - */ -#define parent_node(node) (node) - #define pcibus_to_node(bus) __pcibus_to_node(bus) extern int __node_distance(int, int); diff --git a/arch/x86/include/asm/trace/common.h b/arch/x86/include/asm/trace/common.h new file mode 100644 index 000000000000..57c8da027d99 --- /dev/null +++ b/arch/x86/include/asm/trace/common.h @@ -0,0 +1,16 @@ +#ifndef _ASM_TRACE_COMMON_H +#define _ASM_TRACE_COMMON_H + +#ifdef CONFIG_TRACING +DECLARE_STATIC_KEY_FALSE(trace_pagefault_key); +#define trace_pagefault_enabled() \ + static_branch_unlikely(&trace_pagefault_key) +DECLARE_STATIC_KEY_FALSE(trace_resched_ipi_key); +#define trace_resched_ipi_enabled() \ + static_branch_unlikely(&trace_resched_ipi_key) +#else +static inline bool trace_pagefault_enabled(void) { return false; } +static inline bool trace_resched_ipi_enabled(void) { return false; } +#endif + +#endif diff --git a/arch/x86/include/asm/trace/exceptions.h b/arch/x86/include/asm/trace/exceptions.h index 2422b14c50a7..5665bf205b8d 100644 --- a/arch/x86/include/asm/trace/exceptions.h +++ b/arch/x86/include/asm/trace/exceptions.h @@ -5,9 +5,10 @@ #define _TRACE_PAGE_FAULT_H #include <linux/tracepoint.h> +#include <asm/trace/common.h> -extern int trace_irq_vector_regfunc(void); -extern void trace_irq_vector_unregfunc(void); +extern int trace_pagefault_reg(void); +extern void trace_pagefault_unreg(void); DECLARE_EVENT_CLASS(x86_exceptions, @@ -37,8 +38,7 @@ DEFINE_EVENT_FN(x86_exceptions, name, \ TP_PROTO(unsigned long address, struct pt_regs *regs, \ unsigned long error_code), \ TP_ARGS(address, regs, error_code), \ - trace_irq_vector_regfunc, \ - trace_irq_vector_unregfunc); + trace_pagefault_reg, trace_pagefault_unreg); DEFINE_PAGE_FAULT_EVENT(page_fault_user); DEFINE_PAGE_FAULT_EVENT(page_fault_kernel); diff --git a/arch/x86/include/asm/trace/irq_vectors.h b/arch/x86/include/asm/trace/irq_vectors.h index 32dd6a9e343c..1599d394c8c1 100644 --- a/arch/x86/include/asm/trace/irq_vectors.h +++ b/arch/x86/include/asm/trace/irq_vectors.h @@ -5,9 +5,12 @@ #define _TRACE_IRQ_VECTORS_H #include <linux/tracepoint.h> +#include <asm/trace/common.h> -extern int trace_irq_vector_regfunc(void); -extern void trace_irq_vector_unregfunc(void); +#ifdef CONFIG_X86_LOCAL_APIC + +extern int trace_resched_ipi_reg(void); +extern void trace_resched_ipi_unreg(void); DECLARE_EVENT_CLASS(x86_irq_vector, @@ -28,15 +31,22 @@ DECLARE_EVENT_CLASS(x86_irq_vector, #define DEFINE_IRQ_VECTOR_EVENT(name) \ DEFINE_EVENT_FN(x86_irq_vector, name##_entry, \ TP_PROTO(int vector), \ + TP_ARGS(vector), NULL, NULL); \ +DEFINE_EVENT_FN(x86_irq_vector, name##_exit, \ + TP_PROTO(int vector), \ + TP_ARGS(vector), NULL, NULL); + +#define DEFINE_RESCHED_IPI_EVENT(name) \ +DEFINE_EVENT_FN(x86_irq_vector, name##_entry, \ + TP_PROTO(int vector), \ TP_ARGS(vector), \ - trace_irq_vector_regfunc, \ - trace_irq_vector_unregfunc); \ + trace_resched_ipi_reg, \ + trace_resched_ipi_unreg); \ DEFINE_EVENT_FN(x86_irq_vector, name##_exit, \ TP_PROTO(int vector), \ TP_ARGS(vector), \ - trace_irq_vector_regfunc, \ - trace_irq_vector_unregfunc); - + trace_resched_ipi_reg, \ + trace_resched_ipi_unreg); /* * local_timer - called when entering/exiting a local timer interrupt @@ -45,11 +55,6 @@ DEFINE_EVENT_FN(x86_irq_vector, name##_exit, \ DEFINE_IRQ_VECTOR_EVENT(local_timer); /* - * reschedule - called when entering/exiting a reschedule vector handler - */ -DEFINE_IRQ_VECTOR_EVENT(reschedule); - -/* * spurious_apic - called when entering/exiting a spurious apic vector handler */ DEFINE_IRQ_VECTOR_EVENT(spurious_apic); @@ -65,6 +70,7 @@ DEFINE_IRQ_VECTOR_EVENT(error_apic); */ DEFINE_IRQ_VECTOR_EVENT(x86_platform_ipi); +#ifdef CONFIG_IRQ_WORK /* * irq_work - called when entering/exiting a irq work interrupt * vector handler @@ -81,6 +87,18 @@ DEFINE_IRQ_VECTOR_EVENT(irq_work); * 4) goto 1 */ TRACE_EVENT_PERF_PERM(irq_work_exit, is_sampling_event(p_event) ? -EPERM : 0); +#endif + +/* + * The ifdef is required because that tracepoint macro hell emits tracepoint + * code in files which include this header even if the tracepoint is not + * enabled. Brilliant stuff that. + */ +#ifdef CONFIG_SMP +/* + * reschedule - called when entering/exiting a reschedule vector handler + */ +DEFINE_RESCHED_IPI_EVENT(reschedule); /* * call_function - called when entering/exiting a call function interrupt @@ -93,24 +111,33 @@ DEFINE_IRQ_VECTOR_EVENT(call_function); * single interrupt vector handler */ DEFINE_IRQ_VECTOR_EVENT(call_function_single); +#endif +#ifdef CONFIG_X86_MCE_THRESHOLD /* * threshold_apic - called when entering/exiting a threshold apic interrupt * vector handler */ DEFINE_IRQ_VECTOR_EVENT(threshold_apic); +#endif +#ifdef CONFIG_X86_MCE_AMD /* * deferred_error_apic - called when entering/exiting a deferred apic interrupt * vector handler */ DEFINE_IRQ_VECTOR_EVENT(deferred_error_apic); +#endif +#ifdef CONFIG_X86_THERMAL_VECTOR /* * thermal_apic - called when entering/exiting a thermal apic interrupt * vector handler */ DEFINE_IRQ_VECTOR_EVENT(thermal_apic); +#endif + +#endif /* CONFIG_X86_LOCAL_APIC */ #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH . diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 01fd0a7f48cd..5545f6459bf5 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -13,9 +13,6 @@ asmlinkage void divide_error(void); asmlinkage void debug(void); asmlinkage void nmi(void); asmlinkage void int3(void); -asmlinkage void xen_debug(void); -asmlinkage void xen_int3(void); -asmlinkage void xen_stack_segment(void); asmlinkage void overflow(void); asmlinkage void bounds(void); asmlinkage void invalid_op(void); @@ -38,22 +35,29 @@ asmlinkage void machine_check(void); #endif /* CONFIG_X86_MCE */ asmlinkage void simd_coprocessor_error(void); -#ifdef CONFIG_TRACING -asmlinkage void trace_page_fault(void); -#define trace_stack_segment stack_segment -#define trace_divide_error divide_error -#define trace_bounds bounds -#define trace_invalid_op invalid_op -#define trace_device_not_available device_not_available -#define trace_coprocessor_segment_overrun coprocessor_segment_overrun -#define trace_invalid_TSS invalid_TSS -#define trace_segment_not_present segment_not_present -#define trace_general_protection general_protection -#define trace_spurious_interrupt_bug spurious_interrupt_bug -#define trace_coprocessor_error coprocessor_error -#define trace_alignment_check alignment_check -#define trace_simd_coprocessor_error simd_coprocessor_error -#define trace_async_page_fault async_page_fault +#if defined(CONFIG_X86_64) && defined(CONFIG_XEN_PV) +asmlinkage void xen_divide_error(void); +asmlinkage void xen_xendebug(void); +asmlinkage void xen_xenint3(void); +asmlinkage void xen_nmi(void); +asmlinkage void xen_overflow(void); +asmlinkage void xen_bounds(void); +asmlinkage void xen_invalid_op(void); +asmlinkage void xen_device_not_available(void); +asmlinkage void xen_double_fault(void); +asmlinkage void xen_coprocessor_segment_overrun(void); +asmlinkage void xen_invalid_TSS(void); +asmlinkage void xen_segment_not_present(void); +asmlinkage void xen_stack_segment(void); +asmlinkage void xen_general_protection(void); +asmlinkage void xen_page_fault(void); +asmlinkage void xen_spurious_interrupt_bug(void); +asmlinkage void xen_coprocessor_error(void); +asmlinkage void xen_alignment_check(void); +#ifdef CONFIG_X86_MCE +asmlinkage void xen_machine_check(void); +#endif /* CONFIG_X86_MCE */ +asmlinkage void xen_simd_coprocessor_error(void); #endif dotraplinkage void do_divide_error(struct pt_regs *, long); @@ -74,14 +78,6 @@ asmlinkage struct pt_regs *sync_regs(struct pt_regs *); #endif dotraplinkage void do_general_protection(struct pt_regs *, long); dotraplinkage void do_page_fault(struct pt_regs *, unsigned long); -#ifdef CONFIG_TRACING -dotraplinkage void trace_do_page_fault(struct pt_regs *, unsigned long); -#else -static inline void trace_do_page_fault(struct pt_regs *regs, unsigned long error) -{ - do_page_fault(regs, error); -} -#endif dotraplinkage void do_spurious_interrupt_bug(struct pt_regs *, long); dotraplinkage void do_coprocessor_error(struct pt_regs *, long); dotraplinkage void do_alignment_check(struct pt_regs *, long); diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 30269dafec47..184eb9894dae 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -26,7 +26,12 @@ #define get_ds() (KERNEL_DS) #define get_fs() (current->thread.addr_limit) -#define set_fs(x) (current->thread.addr_limit = (x)) +static inline void set_fs(mm_segment_t fs) +{ + current->thread.addr_limit = fs; + /* On user-mode return, check fs is correct */ + set_thread_flag(TIF_FSCHECK); +} #define segment_eq(a, b) ((a).seg == (b).seg) diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h index e6676495b125..e9f793e2df7a 100644 --- a/arch/x86/include/asm/unwind.h +++ b/arch/x86/include/asm/unwind.h @@ -12,11 +12,14 @@ struct unwind_state { struct task_struct *task; int graph_idx; bool error; -#ifdef CONFIG_FRAME_POINTER +#if defined(CONFIG_ORC_UNWINDER) + bool signal, full_regs; + unsigned long sp, bp, ip; + struct pt_regs *regs; +#elif defined(CONFIG_FRAME_POINTER_UNWINDER) bool got_irq; - unsigned long *bp, *orig_sp; + unsigned long *bp, *orig_sp, ip; struct pt_regs *regs; - unsigned long ip; #else unsigned long *sp; #endif @@ -24,41 +27,30 @@ struct unwind_state { void __unwind_start(struct unwind_state *state, struct task_struct *task, struct pt_regs *regs, unsigned long *first_frame); - bool unwind_next_frame(struct unwind_state *state); - unsigned long unwind_get_return_address(struct unwind_state *state); +unsigned long *unwind_get_return_address_ptr(struct unwind_state *state); static inline bool unwind_done(struct unwind_state *state) { return state->stack_info.type == STACK_TYPE_UNKNOWN; } -static inline -void unwind_start(struct unwind_state *state, struct task_struct *task, - struct pt_regs *regs, unsigned long *first_frame) -{ - first_frame = first_frame ? : get_stack_pointer(task, regs); - - __unwind_start(state, task, regs, first_frame); -} - static inline bool unwind_error(struct unwind_state *state) { return state->error; } -#ifdef CONFIG_FRAME_POINTER - static inline -unsigned long *unwind_get_return_address_ptr(struct unwind_state *state) +void unwind_start(struct unwind_state *state, struct task_struct *task, + struct pt_regs *regs, unsigned long *first_frame) { - if (unwind_done(state)) - return NULL; + first_frame = first_frame ? : get_stack_pointer(task, regs); - return state->regs ? &state->regs->ip : state->bp + 1; + __unwind_start(state, task, regs, first_frame); } +#if defined(CONFIG_ORC_UNWINDER) || defined(CONFIG_FRAME_POINTER_UNWINDER) static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state) { if (unwind_done(state)) @@ -66,20 +58,46 @@ static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state) return state->regs; } - -#else /* !CONFIG_FRAME_POINTER */ - -static inline -unsigned long *unwind_get_return_address_ptr(struct unwind_state *state) +#else +static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state) { return NULL; } +#endif -static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state) +#ifdef CONFIG_ORC_UNWINDER +void unwind_init(void); +void unwind_module_init(struct module *mod, void *orc_ip, size_t orc_ip_size, + void *orc, size_t orc_size); +#else +static inline void unwind_init(void) {} +static inline +void unwind_module_init(struct module *mod, void *orc_ip, size_t orc_ip_size, + void *orc, size_t orc_size) {} +#endif + +/* + * This disables KASAN checking when reading a value from another task's stack, + * since the other task could be running on another CPU and could have poisoned + * the stack in the meantime. + */ +#define READ_ONCE_TASK_STACK(task, x) \ +({ \ + unsigned long val; \ + if (task == current) \ + val = READ_ONCE(x); \ + else \ + val = READ_ONCE_NOCHECK(x); \ + val; \ +}) + +static inline bool task_on_another_cpu(struct task_struct *task) { - return NULL; +#ifdef CONFIG_SMP + return task != current && task->on_cpu; +#else + return false; +#endif } -#endif /* CONFIG_FRAME_POINTER */ - #endif /* _ASM_X86_UNWIND_H */ diff --git a/arch/x86/include/asm/unwind_hints.h b/arch/x86/include/asm/unwind_hints.h new file mode 100644 index 000000000000..bae46fc6b9de --- /dev/null +++ b/arch/x86/include/asm/unwind_hints.h @@ -0,0 +1,105 @@ +#ifndef _ASM_X86_UNWIND_HINTS_H +#define _ASM_X86_UNWIND_HINTS_H + +#include "orc_types.h" + +#ifdef __ASSEMBLY__ + +/* + * In asm, there are two kinds of code: normal C-type callable functions and + * the rest. The normal callable functions can be called by other code, and + * don't do anything unusual with the stack. Such normal callable functions + * are annotated with the ENTRY/ENDPROC macros. Most asm code falls in this + * category. In this case, no special debugging annotations are needed because + * objtool can automatically generate the ORC data for the ORC unwinder to read + * at runtime. + * + * Anything which doesn't fall into the above category, such as syscall and + * interrupt handlers, tends to not be called directly by other functions, and + * often does unusual non-C-function-type things with the stack pointer. Such + * code needs to be annotated such that objtool can understand it. The + * following CFI hint macros are for this type of code. + * + * These macros provide hints to objtool about the state of the stack at each + * instruction. Objtool starts from the hints and follows the code flow, + * making automatic CFI adjustments when it sees pushes and pops, filling out + * the debuginfo as necessary. It will also warn if it sees any + * inconsistencies. + */ +.macro UNWIND_HINT sp_reg=ORC_REG_SP sp_offset=0 type=ORC_TYPE_CALL +#ifdef CONFIG_STACK_VALIDATION +.Lunwind_hint_ip_\@: + .pushsection .discard.unwind_hints + /* struct unwind_hint */ + .long .Lunwind_hint_ip_\@ - . + .short \sp_offset + .byte \sp_reg + .byte \type + .popsection +#endif +.endm + +.macro UNWIND_HINT_EMPTY + UNWIND_HINT sp_reg=ORC_REG_UNDEFINED +.endm + +.macro UNWIND_HINT_REGS base=%rsp offset=0 indirect=0 extra=1 iret=0 + .if \base == %rsp + .if \indirect + .set sp_reg, ORC_REG_SP_INDIRECT + .else + .set sp_reg, ORC_REG_SP + .endif + .elseif \base == %rbp + .set sp_reg, ORC_REG_BP + .elseif \base == %rdi + .set sp_reg, ORC_REG_DI + .elseif \base == %rdx + .set sp_reg, ORC_REG_DX + .elseif \base == %r10 + .set sp_reg, ORC_REG_R10 + .else + .error "UNWIND_HINT_REGS: bad base register" + .endif + + .set sp_offset, \offset + + .if \iret + .set type, ORC_TYPE_REGS_IRET + .elseif \extra == 0 + .set type, ORC_TYPE_REGS_IRET + .set sp_offset, \offset + (16*8) + .else + .set type, ORC_TYPE_REGS + .endif + + UNWIND_HINT sp_reg=sp_reg sp_offset=sp_offset type=type +.endm + +.macro UNWIND_HINT_IRET_REGS base=%rsp offset=0 + UNWIND_HINT_REGS base=\base offset=\offset iret=1 +.endm + +.macro UNWIND_HINT_FUNC sp_offset=8 + UNWIND_HINT sp_offset=\sp_offset +.endm + +#else /* !__ASSEMBLY__ */ + +#define UNWIND_HINT(sp_reg, sp_offset, type) \ + "987: \n\t" \ + ".pushsection .discard.unwind_hints\n\t" \ + /* struct unwind_hint */ \ + ".long 987b - .\n\t" \ + ".short " __stringify(sp_offset) "\n\t" \ + ".byte " __stringify(sp_reg) "\n\t" \ + ".byte " __stringify(type) "\n\t" \ + ".popsection\n\t" + +#define UNWIND_HINT_SAVE UNWIND_HINT(0, 0, UNWIND_HINT_TYPE_SAVE) + +#define UNWIND_HINT_RESTORE UNWIND_HINT(0, 0, UNWIND_HINT_TYPE_RESTORE) + +#endif /* __ASSEMBLY__ */ + +#endif /* _ASM_X86_UNWIND_HINTS_H */ diff --git a/arch/x86/include/asm/vga.h b/arch/x86/include/asm/vga.h index c4b9dc2f67c5..9f42beefc67a 100644 --- a/arch/x86/include/asm/vga.h +++ b/arch/x86/include/asm/vga.h @@ -7,12 +7,24 @@ #ifndef _ASM_X86_VGA_H #define _ASM_X86_VGA_H +#include <asm/set_memory.h> + /* * On the PC, we can just recalculate addresses and then * access the videoram directly without any black magic. + * To support memory encryption however, we need to access + * the videoram as decrypted memory. */ -#define VGA_MAP_MEM(x, s) (unsigned long)phys_to_virt(x) +#define VGA_MAP_MEM(x, s) \ +({ \ + unsigned long start = (unsigned long)phys_to_virt(x); \ + \ + if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT)) \ + set_memory_decrypted(start, (s) >> PAGE_SHIFT); \ + \ + start; \ +}) #define vga_readb(x) (*(x)) #define vga_writeb(x, y) (*(y) = (x)) diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index 11071fcd630e..9606688caa4b 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -552,6 +552,8 @@ static inline void MULTI_update_descriptor(struct multicall_entry *mcl, u64 maddr, struct desc_struct desc) { + u32 *p = (u32 *) &desc; + mcl->op = __HYPERVISOR_update_descriptor; if (sizeof(maddr) == sizeof(long)) { mcl->args[0] = maddr; @@ -559,8 +561,8 @@ MULTI_update_descriptor(struct multicall_entry *mcl, u64 maddr, } else { mcl->args[0] = maddr; mcl->args[1] = maddr >> 32; - mcl->args[2] = desc.a; - mcl->args[3] = desc.b; + mcl->args[2] = *p++; + mcl->args[3] = *p; } trace_xen_mc_entry(mcl, sizeof(maddr) == sizeof(long) ? 2 : 4); diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h index ddef37b16af2..66b8f93333d1 100644 --- a/arch/x86/include/uapi/asm/bootparam.h +++ b/arch/x86/include/uapi/asm/bootparam.h @@ -201,7 +201,7 @@ struct boot_params { * * @X86_SUBARCH_PC: Should be used if the hardware is enumerable using standard * PC mechanisms (PCI, ACPI) and doesn't need a special boot flow. - * @X86_SUBARCH_LGUEST: Used for x86 hypervisor demo, lguest + * @X86_SUBARCH_LGUEST: Used for x86 hypervisor demo, lguest, deprecated * @X86_SUBARCH_XEN: Used for Xen guest types which follow the PV boot path, * which start at asm startup_xen() entry point and later jump to the C * xen_start_kernel() entry point. Both domU and dom0 type of guests are diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index a01892bdd61a..fd0a7895b63f 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -42,7 +42,7 @@ CFLAGS_irq.o := -I$(src)/../include/asm/trace obj-y := process_$(BITS).o signal.o obj-$(CONFIG_COMPAT) += signal_compat.o -obj-y += traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o +obj-y += traps.o idt.o irq.o irq_$(BITS).o dumpstack_$(BITS).o obj-y += time.o ioport.o dumpstack.o nmi.o obj-$(CONFIG_MODIFY_LDT_SYSCALL) += ldt.o obj-y += setup.o x86_init.o i8259.o irqinit.o jump_label.o @@ -111,6 +111,7 @@ obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= paravirt-spinlocks.o obj-$(CONFIG_PARAVIRT_CLOCK) += pvclock.o obj-$(CONFIG_X86_PMEM_LEGACY_DEVICE) += pmem.o +obj-$(CONFIG_EISA) += eisa.o obj-$(CONFIG_PCSPKR_PLATFORM) += pcspeaker.o obj-$(CONFIG_X86_CHECK_BIOS_CORRUPTION) += check.o @@ -126,11 +127,9 @@ obj-$(CONFIG_PERF_EVENTS) += perf_regs.o obj-$(CONFIG_TRACING) += tracepoint.o obj-$(CONFIG_SCHED_MC_PRIO) += itmt.o -ifdef CONFIG_FRAME_POINTER -obj-y += unwind_frame.o -else -obj-y += unwind_guess.o -endif +obj-$(CONFIG_ORC_UNWINDER) += unwind_orc.o +obj-$(CONFIG_FRAME_POINTER_UNWINDER) += unwind_frame.o +obj-$(CONFIG_GUESS_UNWINDER) += unwind_guess.o ### # 64 bit specific files diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 7491e73d9253..97bb2caf3428 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -115,7 +115,7 @@ static u32 isa_irq_to_gsi[NR_IRQS_LEGACY] __read_mostly = { #define ACPI_INVALID_GSI INT_MIN /* - * This is just a simple wrapper around early_ioremap(), + * This is just a simple wrapper around early_memremap(), * with sanity checks for phys == 0 and size == 0. */ char *__init __acpi_map_table(unsigned long phys, unsigned long size) @@ -124,7 +124,7 @@ char *__init __acpi_map_table(unsigned long phys, unsigned long size) if (!phys || !size) return NULL; - return early_ioremap(phys, size); + return early_memremap(phys, size); } void __init __acpi_unmap_table(char *map, unsigned long size) @@ -132,7 +132,7 @@ void __init __acpi_unmap_table(char *map, unsigned long size) if (!map || !size) return; - early_iounmap(map, size); + early_memunmap(map, size); } #ifdef CONFIG_X86_LOCAL_APIC diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 32e14d137416..3344d3382e91 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -742,7 +742,16 @@ static void *bp_int3_handler, *bp_int3_addr; int poke_int3_handler(struct pt_regs *regs) { - /* bp_patching_in_progress */ + /* + * Having observed our INT3 instruction, we now must observe + * bp_patching_in_progress. + * + * in_progress = TRUE INT3 + * WMB RMB + * write INT3 if (in_progress) + * + * Idem for bp_int3_handler. + */ smp_rmb(); if (likely(!bp_patching_in_progress)) @@ -788,9 +797,8 @@ void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler) bp_int3_addr = (u8 *)addr + sizeof(int3); bp_patching_in_progress = true; /* - * Corresponding read barrier in int3 notifier for - * making sure the in_progress flags is correctly ordered wrt. - * patching + * Corresponding read barrier in int3 notifier for making sure the + * in_progress and handler are correctly ordered wrt. patching. */ smp_wmb(); @@ -815,9 +823,11 @@ void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler) text_poke(addr, opcode, sizeof(int3)); on_each_cpu(do_sync_core, NULL, 1); - + /* + * sync_core() implies an smp_mb() and orders this store against + * the writing of the new instruction. + */ bp_patching_in_progress = false; - smp_wmb(); return addr; } diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 98b3dd8cf2bf..7834f73efbf1 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -177,8 +177,6 @@ static int disable_apic_timer __initdata; int local_apic_timer_c2_ok; EXPORT_SYMBOL_GPL(local_apic_timer_c2_ok); -int first_system_vector = FIRST_SYSTEM_VECTOR; - /* * Debug level, exported for io_apic.c */ @@ -599,9 +597,13 @@ static const struct x86_cpu_id deadline_match[] = { static void apic_check_deadline_errata(void) { - const struct x86_cpu_id *m = x86_match_cpu(deadline_match); + const struct x86_cpu_id *m; u32 rev; + if (!boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) + return; + + m = x86_match_cpu(deadline_match); if (!m) return; @@ -990,8 +992,7 @@ void setup_secondary_APIC_clock(void) */ static void local_apic_timer_interrupt(void) { - int cpu = smp_processor_id(); - struct clock_event_device *evt = &per_cpu(lapic_events, cpu); + struct clock_event_device *evt = this_cpu_ptr(&lapic_events); /* * Normally we should not be here till LAPIC has been initialized but @@ -1005,7 +1006,8 @@ static void local_apic_timer_interrupt(void) * spurious. */ if (!evt->event_handler) { - pr_warning("Spurious LAPIC timer interrupt on cpu %d\n", cpu); + pr_warning("Spurious LAPIC timer interrupt on cpu %d\n", + smp_processor_id()); /* Switch it off */ lapic_timer_shutdown(evt); return; @@ -1040,25 +1042,6 @@ __visible void __irq_entry smp_apic_timer_interrupt(struct pt_regs *regs) * interrupt lock, which is the WrongThing (tm) to do. */ entering_ack_irq(); - local_apic_timer_interrupt(); - exiting_irq(); - - set_irq_regs(old_regs); -} - -__visible void __irq_entry smp_trace_apic_timer_interrupt(struct pt_regs *regs) -{ - struct pt_regs *old_regs = set_irq_regs(regs); - - /* - * NOTE! We'd better ACK the irq immediately, - * because timer handling can be slow. - * - * update_process_times() expects us to have done irq_enter(). - * Besides, if we don't timer interrupts ignore the global - * interrupt lock, which is the WrongThing (tm) to do. - */ - entering_ack_irq(); trace_local_timer_entry(LOCAL_TIMER_VECTOR); local_apic_timer_interrupt(); trace_local_timer_exit(LOCAL_TIMER_VECTOR); @@ -1920,10 +1903,14 @@ void __init register_lapic_address(unsigned long address) /* * This interrupt should _never_ happen with our APIC/SMP architecture */ -static void __smp_spurious_interrupt(u8 vector) +__visible void __irq_entry smp_spurious_interrupt(struct pt_regs *regs) { + u8 vector = ~regs->orig_ax; u32 v; + entering_irq(); + trace_spurious_apic_entry(vector); + /* * Check if this really is a spurious interrupt and ACK it * if it is a vectored one. Just in case... @@ -1938,22 +1925,7 @@ static void __smp_spurious_interrupt(u8 vector) /* see sw-dev-man vol 3, chapter 7.4.13.5 */ pr_info("spurious APIC interrupt through vector %02x on CPU#%d, " "should never happen.\n", vector, smp_processor_id()); -} -__visible void __irq_entry smp_spurious_interrupt(struct pt_regs *regs) -{ - entering_irq(); - __smp_spurious_interrupt(~regs->orig_ax); - exiting_irq(); -} - -__visible void __irq_entry smp_trace_spurious_interrupt(struct pt_regs *regs) -{ - u8 vector = ~regs->orig_ax; - - entering_irq(); - trace_spurious_apic_entry(vector); - __smp_spurious_interrupt(vector); trace_spurious_apic_exit(vector); exiting_irq(); } @@ -1961,10 +1933,8 @@ __visible void __irq_entry smp_trace_spurious_interrupt(struct pt_regs *regs) /* * This interrupt should never happen with our APIC/SMP architecture */ -static void __smp_error_interrupt(struct pt_regs *regs) +__visible void __irq_entry smp_error_interrupt(struct pt_regs *regs) { - u32 v; - u32 i = 0; static const char * const error_interrupt_reason[] = { "Send CS error", /* APIC Error Bit 0 */ "Receive CS error", /* APIC Error Bit 1 */ @@ -1975,6 +1945,10 @@ static void __smp_error_interrupt(struct pt_regs *regs) "Received illegal vector", /* APIC Error Bit 6 */ "Illegal register address", /* APIC Error Bit 7 */ }; + u32 v, i = 0; + + entering_irq(); + trace_error_apic_entry(ERROR_APIC_VECTOR); /* First tickle the hardware, only then report what went on. -- REW */ if (lapic_get_maxlvt() > 3) /* Due to the Pentium erratum 3AP. */ @@ -1996,20 +1970,6 @@ static void __smp_error_interrupt(struct pt_regs *regs) apic_printk(APIC_DEBUG, KERN_CONT "\n"); -} - -__visible void __irq_entry smp_error_interrupt(struct pt_regs *regs) -{ - entering_irq(); - __smp_error_interrupt(regs); - exiting_irq(); -} - -__visible void __irq_entry smp_trace_error_interrupt(struct pt_regs *regs) -{ - entering_irq(); - trace_error_apic_entry(ERROR_APIC_VECTOR); - __smp_error_interrupt(regs); trace_error_apic_exit(ERROR_APIC_VECTOR); exiting_irq(); } diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 237e9c2341c7..70e48aa6af98 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1243,7 +1243,7 @@ static void io_apic_print_entries(unsigned int apic, unsigned int nr_entries) entry.vector, entry.irr, entry.delivery_status); if (ir_entry->format) printk(KERN_DEBUG "%s, remapped, I(%04X), Z(%X)\n", - buf, (ir_entry->index << 15) | ir_entry->index, + buf, (ir_entry->index2 << 15) | ir_entry->index, ir_entry->zero); else printk(KERN_DEBUG "%s, %s, D(%02X), M(%1d)\n", diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index b3af457ed667..88c214e75a6b 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -166,7 +166,7 @@ static int __assign_irq_vector(int irq, struct apic_chip_data *d, offset = current_offset; next: vector += 16; - if (vector >= first_system_vector) { + if (vector >= FIRST_SYSTEM_VECTOR) { offset = (offset + 1) % 16; vector = FIRST_EXTERNAL_VECTOR + offset; } diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c index 880aa093268d..710edab9e644 100644 --- a/arch/x86/kernel/asm-offsets_32.c +++ b/arch/x86/kernel/asm-offsets_32.c @@ -4,9 +4,6 @@ #include <asm/ucontext.h> -#include <linux/lguest.h> -#include "../../../drivers/lguest/lg.h" - #define __SYSCALL_I386(nr, sym, qual) [nr] = 1, static char syscalls[] = { #include <asm/syscalls_32.h> @@ -62,23 +59,6 @@ void foo(void) OFFSET(stack_canary_offset, stack_canary, canary); #endif -#if defined(CONFIG_LGUEST) || defined(CONFIG_LGUEST_GUEST) || defined(CONFIG_LGUEST_MODULE) - BLANK(); - OFFSET(LGUEST_DATA_irq_enabled, lguest_data, irq_enabled); - OFFSET(LGUEST_DATA_irq_pending, lguest_data, irq_pending); - - BLANK(); - OFFSET(LGUEST_PAGES_host_gdt_desc, lguest_pages, state.host_gdt_desc); - OFFSET(LGUEST_PAGES_host_idt_desc, lguest_pages, state.host_idt_desc); - OFFSET(LGUEST_PAGES_host_cr3, lguest_pages, state.host_cr3); - OFFSET(LGUEST_PAGES_host_sp, lguest_pages, state.host_sp); - OFFSET(LGUEST_PAGES_guest_gdt_desc, lguest_pages,state.guest_gdt_desc); - OFFSET(LGUEST_PAGES_guest_idt_desc, lguest_pages,state.guest_idt_desc); - OFFSET(LGUEST_PAGES_guest_gdt, lguest_pages, state.guest_gdt); - OFFSET(LGUEST_PAGES_regs_trapnum, lguest_pages, regs.trapnum); - OFFSET(LGUEST_PAGES_regs_errcode, lguest_pages, regs.errcode); - OFFSET(LGUEST_PAGES_regs, lguest_pages, regs); -#endif BLANK(); DEFINE(__NR_syscall_max, sizeof(syscalls) - 1); DEFINE(NR_syscalls, sizeof(syscalls)); diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index 99332f550c48..cf42206926af 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -20,7 +20,6 @@ static char syscalls_ia32[] = { int main(void) { #ifdef CONFIG_PARAVIRT - OFFSET(PV_IRQ_adjust_exception_frame, pv_irq_ops, adjust_exception_frame); OFFSET(PV_CPU_usergs_sysret64, pv_cpu_ops, usergs_sysret64); OFFSET(PV_CPU_swapgs, pv_cpu_ops, swapgs); BLANK(); diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index cdf82492b770..e17942c131c8 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -33,7 +33,7 @@ obj-$(CONFIG_CPU_SUP_CENTAUR) += centaur.o obj-$(CONFIG_CPU_SUP_TRANSMETA_32) += transmeta.o obj-$(CONFIG_CPU_SUP_UMC_32) += umc.o -obj-$(CONFIG_INTEL_RDT_A) += intel_rdt.o intel_rdt_rdtgroup.o intel_rdt_schemata.o +obj-$(CONFIG_INTEL_RDT) += intel_rdt.o intel_rdt_rdtgroup.o intel_rdt_monitor.o intel_rdt_ctrlmondata.o obj-$(CONFIG_X86_MCE) += mcheck/ obj-$(CONFIG_MTRR) += mtrr/ diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 3b9e220621f8..9862e2cd6d93 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -297,13 +297,29 @@ static int nearby_node(int apicid) } #endif +#ifdef CONFIG_SMP +/* + * Fix up cpu_core_id for pre-F17h systems to be in the + * [0 .. cores_per_node - 1] range. Not really needed but + * kept so as not to break existing setups. + */ +static void legacy_fixup_core_id(struct cpuinfo_x86 *c) +{ + u32 cus_per_node; + + if (c->x86 >= 0x17) + return; + + cus_per_node = c->x86_max_cores / nodes_per_socket; + c->cpu_core_id %= cus_per_node; +} + /* * Fixup core topology information for * (1) AMD multi-node processors * Assumption: Number of cores in each internal node is the same. * (2) AMD processors supporting compute units */ -#ifdef CONFIG_SMP static void amd_get_topology(struct cpuinfo_x86 *c) { u8 node_id; @@ -354,15 +370,9 @@ static void amd_get_topology(struct cpuinfo_x86 *c) } else return; - /* fixup multi-node processor information */ if (nodes_per_socket > 1) { - u32 cus_per_node; - set_cpu_cap(c, X86_FEATURE_AMD_DCM); - cus_per_node = c->x86_max_cores / nodes_per_socket; - - /* core id has to be in the [0 .. cores_per_node - 1] range */ - c->cpu_core_id %= cus_per_node; + legacy_fixup_core_id(c); } } #endif @@ -548,8 +558,12 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) static void early_init_amd(struct cpuinfo_x86 *c) { + u32 dummy; + early_init_amd_mc(c); + rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy); + /* * c->x86_power is 8000_0007 edx. Bit 8 is TSC runs at constant rate * with P/T states and does not stop in deep C-states @@ -612,6 +626,27 @@ static void early_init_amd(struct cpuinfo_x86 *c) */ if (cpu_has_amd_erratum(c, amd_erratum_400)) set_cpu_bug(c, X86_BUG_AMD_E400); + + /* + * BIOS support is required for SME. If BIOS has enabled SME then + * adjust x86_phys_bits by the SME physical address space reduction + * value. If BIOS has not enabled SME then don't advertise the + * feature (set in scattered.c). Also, since the SME support requires + * long mode, don't advertise the feature under CONFIG_X86_32. + */ + if (cpu_has(c, X86_FEATURE_SME)) { + u64 msr; + + /* Check if SME is enabled */ + rdmsrl(MSR_K8_SYSCFG, msr); + if (msr & MSR_K8_SYSCFG_MEM_ENCRYPT) { + c->x86_phys_bits -= (cpuid_ebx(0x8000001f) >> 6) & 0x3f; + if (IS_ENABLED(CONFIG_X86_32)) + clear_cpu_cap(c, X86_FEATURE_SME); + } else { + clear_cpu_cap(c, X86_FEATURE_SME); + } + } } static void init_amd_k8(struct cpuinfo_x86 *c) @@ -730,8 +765,6 @@ static void init_amd_bd(struct cpuinfo_x86 *c) static void init_amd(struct cpuinfo_x86 *c) { - u32 dummy; - early_init_amd(c); /* @@ -793,8 +826,6 @@ static void init_amd(struct cpuinfo_x86 *c) if (c->x86 > 0x11) set_cpu_cap(c, X86_FEATURE_ARAT); - rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy); - /* 3DNow or LM implies PREFETCHW */ if (!cpu_has(c, X86_FEATURE_3DNOWPREFETCH)) if (cpu_has(c, X86_FEATURE_3DNOW) || cpu_has(c, X86_FEATURE_LM)) diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c index d869c8671e36..0ee83321a313 100644 --- a/arch/x86/kernel/cpu/aperfmperf.c +++ b/arch/x86/kernel/cpu/aperfmperf.c @@ -8,20 +8,25 @@ * This file is licensed under GPLv2. */ -#include <linux/jiffies.h> +#include <linux/delay.h> +#include <linux/ktime.h> #include <linux/math64.h> #include <linux/percpu.h> #include <linux/smp.h> struct aperfmperf_sample { unsigned int khz; - unsigned long jiffies; + ktime_t time; u64 aperf; u64 mperf; }; static DEFINE_PER_CPU(struct aperfmperf_sample, samples); +#define APERFMPERF_CACHE_THRESHOLD_MS 10 +#define APERFMPERF_REFRESH_DELAY_MS 20 +#define APERFMPERF_STALE_THRESHOLD_MS 1000 + /* * aperfmperf_snapshot_khz() * On the current CPU, snapshot APERF, MPERF, and jiffies @@ -33,13 +38,18 @@ static void aperfmperf_snapshot_khz(void *dummy) u64 aperf, aperf_delta; u64 mperf, mperf_delta; struct aperfmperf_sample *s = this_cpu_ptr(&samples); + ktime_t now = ktime_get(); + s64 time_delta = ktime_ms_delta(now, s->time); + unsigned long flags; - /* Don't bother re-computing within 10 ms */ - if (time_before(jiffies, s->jiffies + HZ/100)) + /* Don't bother re-computing within the cache threshold time. */ + if (time_delta < APERFMPERF_CACHE_THRESHOLD_MS) return; + local_irq_save(flags); rdmsrl(MSR_IA32_APERF, aperf); rdmsrl(MSR_IA32_MPERF, mperf); + local_irq_restore(flags); aperf_delta = aperf - s->aperf; mperf_delta = mperf - s->mperf; @@ -51,22 +61,21 @@ static void aperfmperf_snapshot_khz(void *dummy) if (mperf_delta == 0) return; - /* - * if (cpu_khz * aperf_delta) fits into ULLONG_MAX, then - * khz = (cpu_khz * aperf_delta) / mperf_delta - */ - if (div64_u64(ULLONG_MAX, cpu_khz) > aperf_delta) - s->khz = div64_u64((cpu_khz * aperf_delta), mperf_delta); - else /* khz = aperf_delta / (mperf_delta / cpu_khz) */ - s->khz = div64_u64(aperf_delta, - div64_u64(mperf_delta, cpu_khz)); - s->jiffies = jiffies; + s->time = now; s->aperf = aperf; s->mperf = mperf; + + /* If the previous iteration was too long ago, discard it. */ + if (time_delta > APERFMPERF_STALE_THRESHOLD_MS) + s->khz = 0; + else + s->khz = div64_u64((cpu_khz * aperf_delta), mperf_delta); } unsigned int arch_freq_get_on_cpu(int cpu) { + unsigned int khz; + if (!cpu_khz) return 0; @@ -74,6 +83,12 @@ unsigned int arch_freq_get_on_cpu(int cpu) return 0; smp_call_function_single(cpu, aperfmperf_snapshot_khz, NULL, 1); + khz = per_cpu(samples.khz, cpu); + if (khz) + return khz; + + msleep(APERFMPERF_REFRESH_DELAY_MS); + smp_call_function_single(cpu, aperfmperf_snapshot_khz, NULL, 1); return per_cpu(samples.khz, cpu); } diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 0af86d9242da..db684880d74a 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -21,6 +21,14 @@ void __init check_bugs(void) { +#ifdef CONFIG_X86_32 + /* + * Regardless of whether PCID is enumerated, the SDM says + * that it can't be enabled in 32-bit mode. + */ + setup_clear_cpu_cap(X86_FEATURE_PCID); +#endif + identify_boot_cpu(); if (!IS_ENABLED(CONFIG_SMP)) { diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index c8b39870f33e..efba8e3da3e2 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -168,6 +168,24 @@ static int __init x86_mpx_setup(char *s) } __setup("nompx", x86_mpx_setup); +#ifdef CONFIG_X86_64 +static int __init x86_pcid_setup(char *s) +{ + /* require an exact match without trailing characters */ + if (strlen(s)) + return 0; + + /* do not emit a message if the feature is not present */ + if (!boot_cpu_has(X86_FEATURE_PCID)) + return 1; + + setup_clear_cpu_cap(X86_FEATURE_PCID); + pr_info("nopcid: PCID feature disabled\n"); + return 1; +} +__setup("nopcid", x86_pcid_setup); +#endif + static int __init x86_noinvpcid_setup(char *s) { /* noinvpcid doesn't accept parameters */ @@ -311,6 +329,25 @@ static __always_inline void setup_smap(struct cpuinfo_x86 *c) } } +static void setup_pcid(struct cpuinfo_x86 *c) +{ + if (cpu_has(c, X86_FEATURE_PCID)) { + if (cpu_has(c, X86_FEATURE_PGE)) { + cr4_set_bits(X86_CR4_PCIDE); + } else { + /* + * flush_tlb_all(), as currently implemented, won't + * work if PCID is on but PGE is not. Since that + * combination doesn't exist on real hardware, there's + * no reason to try to fully support it, but it's + * polite to avoid corrupting data if we're on + * an improperly configured VM. + */ + clear_cpu_cap(c, X86_FEATURE_PCID); + } + } +} + /* * Protection Keys are not available in 32-bit mode. */ @@ -1125,6 +1162,9 @@ static void identify_cpu(struct cpuinfo_x86 *c) setup_smep(c); setup_smap(c); + /* Set up PCID */ + setup_pcid(c); + /* * The vendor-specific functions might have changed features. * Now we do "generic changes." @@ -1289,15 +1329,6 @@ static __init int setup_disablecpuid(char *arg) __setup("clearcpuid=", setup_disablecpuid); #ifdef CONFIG_X86_64 -struct desc_ptr idt_descr __ro_after_init = { - .size = NR_VECTORS * 16 - 1, - .address = (unsigned long) idt_table, -}; -const struct desc_ptr debug_idt_descr = { - .size = NR_VECTORS * 16 - 1, - .address = (unsigned long) debug_idt_table, -}; - DEFINE_PER_CPU_FIRST(union irq_stack_union, irq_stack_union) __aligned(PAGE_SIZE) __visible; diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index c55fb2cb2acc..24f749324c0f 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -811,7 +811,24 @@ static int __cache_amd_cpumap_setup(unsigned int cpu, int index, struct cacheinfo *this_leaf; int i, sibling; - if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { + /* + * For L3, always use the pre-calculated cpu_llc_shared_mask + * to derive shared_cpu_map. + */ + if (index == 3) { + for_each_cpu(i, cpu_llc_shared_mask(cpu)) { + this_cpu_ci = get_cpu_cacheinfo(i); + if (!this_cpu_ci->info_list) + continue; + this_leaf = this_cpu_ci->info_list + index; + for_each_cpu(sibling, cpu_llc_shared_mask(cpu)) { + if (!cpu_online(sibling)) + continue; + cpumask_set_cpu(sibling, + &this_leaf->shared_cpu_map); + } + } + } else if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { unsigned int apicid, nshared, first, last; this_leaf = this_cpu_ci->info_list + index; @@ -839,19 +856,6 @@ static int __cache_amd_cpumap_setup(unsigned int cpu, int index, &this_leaf->shared_cpu_map); } } - } else if (index == 3) { - for_each_cpu(i, cpu_llc_shared_mask(cpu)) { - this_cpu_ci = get_cpu_cacheinfo(i); - if (!this_cpu_ci->info_list) - continue; - this_leaf = this_cpu_ci->info_list + index; - for_each_cpu(sibling, cpu_llc_shared_mask(cpu)) { - if (!cpu_online(sibling)) - continue; - cpumask_set_cpu(sibling, - &this_leaf->shared_cpu_map); - } - } } else return 0; diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c index 5b366462f579..cd5fc61ba450 100644 --- a/arch/x86/kernel/cpu/intel_rdt.c +++ b/arch/x86/kernel/cpu/intel_rdt.c @@ -30,7 +30,8 @@ #include <linux/cpuhotplug.h> #include <asm/intel-family.h> -#include <asm/intel_rdt.h> +#include <asm/intel_rdt_sched.h> +#include "intel_rdt.h" #define MAX_MBA_BW 100u #define MBA_IS_LINEAR 0x4 @@ -38,7 +39,13 @@ /* Mutex to protect rdtgroup access. */ DEFINE_MUTEX(rdtgroup_mutex); -DEFINE_PER_CPU_READ_MOSTLY(int, cpu_closid); +/* + * The cached intel_pqr_state is strictly per CPU and can never be + * updated from a remote CPU. Functions which modify the state + * are called with interrupts disabled and no preemption, which + * is sufficient for the protection. + */ +DEFINE_PER_CPU(struct intel_pqr_state, pqr_state); /* * Used to store the max resource name width and max resource data width @@ -46,6 +53,12 @@ DEFINE_PER_CPU_READ_MOSTLY(int, cpu_closid); */ int max_name_width, max_data_width; +/* + * Global boolean for rdt_alloc which is true if any + * resource allocation is enabled. + */ +bool rdt_alloc_capable; + static void mba_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r); static void @@ -54,7 +67,9 @@ cat_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r); #define domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].domains) struct rdt_resource rdt_resources_all[] = { + [RDT_RESOURCE_L3] = { + .rid = RDT_RESOURCE_L3, .name = "L3", .domains = domain_init(RDT_RESOURCE_L3), .msr_base = IA32_L3_CBM_BASE, @@ -67,8 +82,11 @@ struct rdt_resource rdt_resources_all[] = { }, .parse_ctrlval = parse_cbm, .format_str = "%d=%0*x", + .fflags = RFTYPE_RES_CACHE, }, + [RDT_RESOURCE_L3DATA] = { + .rid = RDT_RESOURCE_L3DATA, .name = "L3DATA", .domains = domain_init(RDT_RESOURCE_L3DATA), .msr_base = IA32_L3_CBM_BASE, @@ -81,8 +99,11 @@ struct rdt_resource rdt_resources_all[] = { }, .parse_ctrlval = parse_cbm, .format_str = "%d=%0*x", + .fflags = RFTYPE_RES_CACHE, }, + [RDT_RESOURCE_L3CODE] = { + .rid = RDT_RESOURCE_L3CODE, .name = "L3CODE", .domains = domain_init(RDT_RESOURCE_L3CODE), .msr_base = IA32_L3_CBM_BASE, @@ -95,8 +116,11 @@ struct rdt_resource rdt_resources_all[] = { }, .parse_ctrlval = parse_cbm, .format_str = "%d=%0*x", + .fflags = RFTYPE_RES_CACHE, }, + [RDT_RESOURCE_L2] = { + .rid = RDT_RESOURCE_L2, .name = "L2", .domains = domain_init(RDT_RESOURCE_L2), .msr_base = IA32_L2_CBM_BASE, @@ -109,8 +133,11 @@ struct rdt_resource rdt_resources_all[] = { }, .parse_ctrlval = parse_cbm, .format_str = "%d=%0*x", + .fflags = RFTYPE_RES_CACHE, }, + [RDT_RESOURCE_MBA] = { + .rid = RDT_RESOURCE_MBA, .name = "MB", .domains = domain_init(RDT_RESOURCE_MBA), .msr_base = IA32_MBA_THRTL_BASE, @@ -118,6 +145,7 @@ struct rdt_resource rdt_resources_all[] = { .cache_level = 3, .parse_ctrlval = parse_bw, .format_str = "%d=%*d", + .fflags = RFTYPE_RES_MB, }, }; @@ -144,33 +172,28 @@ static unsigned int cbm_idx(struct rdt_resource *r, unsigned int closid) * is always 20 on hsw server parts. The minimum cache bitmask length * allowed for HSW server is always 2 bits. Hardcode all of them. */ -static inline bool cache_alloc_hsw_probe(void) +static inline void cache_alloc_hsw_probe(void) { - if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL && - boot_cpu_data.x86 == 6 && - boot_cpu_data.x86_model == INTEL_FAM6_HASWELL_X) { - struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3]; - u32 l, h, max_cbm = BIT_MASK(20) - 1; - - if (wrmsr_safe(IA32_L3_CBM_BASE, max_cbm, 0)) - return false; - rdmsr(IA32_L3_CBM_BASE, l, h); + struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3]; + u32 l, h, max_cbm = BIT_MASK(20) - 1; - /* If all the bits were set in MSR, return success */ - if (l != max_cbm) - return false; + if (wrmsr_safe(IA32_L3_CBM_BASE, max_cbm, 0)) + return; + rdmsr(IA32_L3_CBM_BASE, l, h); - r->num_closid = 4; - r->default_ctrl = max_cbm; - r->cache.cbm_len = 20; - r->cache.min_cbm_bits = 2; - r->capable = true; - r->enabled = true; + /* If all the bits were set in MSR, return success */ + if (l != max_cbm) + return; - return true; - } + r->num_closid = 4; + r->default_ctrl = max_cbm; + r->cache.cbm_len = 20; + r->cache.shareable_bits = 0xc0000; + r->cache.min_cbm_bits = 2; + r->alloc_capable = true; + r->alloc_enabled = true; - return false; + rdt_alloc_capable = true; } /* @@ -213,15 +236,14 @@ static bool rdt_get_mem_config(struct rdt_resource *r) return false; } r->data_width = 3; - rdt_get_mba_infofile(r); - r->capable = true; - r->enabled = true; + r->alloc_capable = true; + r->alloc_enabled = true; return true; } -static void rdt_get_cache_config(int idx, struct rdt_resource *r) +static void rdt_get_cache_alloc_cfg(int idx, struct rdt_resource *r) { union cpuid_0x10_1_eax eax; union cpuid_0x10_x_edx edx; @@ -231,10 +253,10 @@ static void rdt_get_cache_config(int idx, struct rdt_resource *r) r->num_closid = edx.split.cos_max + 1; r->cache.cbm_len = eax.split.cbm_len + 1; r->default_ctrl = BIT_MASK(eax.split.cbm_len + 1) - 1; + r->cache.shareable_bits = ebx & r->default_ctrl; r->data_width = (r->cache.cbm_len + 3) / 4; - rdt_get_cache_infofile(r); - r->capable = true; - r->enabled = true; + r->alloc_capable = true; + r->alloc_enabled = true; } static void rdt_get_cdp_l3_config(int type) @@ -246,12 +268,12 @@ static void rdt_get_cdp_l3_config(int type) r->cache.cbm_len = r_l3->cache.cbm_len; r->default_ctrl = r_l3->default_ctrl; r->data_width = (r->cache.cbm_len + 3) / 4; - r->capable = true; + r->alloc_capable = true; /* * By default, CDP is disabled. CDP can be enabled by mount parameter * "cdp" during resctrl file system mount time. */ - r->enabled = false; + r->alloc_enabled = false; } static int get_cache_id(int cpu, int level) @@ -300,6 +322,19 @@ cat_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r) wrmsrl(r->msr_base + cbm_idx(r, i), d->ctrl_val[i]); } +struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r) +{ + struct rdt_domain *d; + + list_for_each_entry(d, &r->domains, list) { + /* Find the domain that contains this CPU */ + if (cpumask_test_cpu(cpu, &d->cpu_mask)) + return d; + } + + return NULL; +} + void rdt_ctrl_update(void *arg) { struct msr_param *m = arg; @@ -307,12 +342,10 @@ void rdt_ctrl_update(void *arg) int cpu = smp_processor_id(); struct rdt_domain *d; - list_for_each_entry(d, &r->domains, list) { - /* Find the domain that contains this CPU */ - if (cpumask_test_cpu(cpu, &d->cpu_mask)) { - r->msr_update(d, m, r); - return; - } + d = get_domain_from_cpu(cpu, r); + if (d) { + r->msr_update(d, m, r); + return; } pr_warn_once("cpu %d not found in any domain for resource %s\n", cpu, r->name); @@ -326,8 +359,8 @@ void rdt_ctrl_update(void *arg) * caller, return the first domain whose id is bigger than the input id. * The domain list is sorted by id in ascending order. */ -static struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id, - struct list_head **pos) +struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id, + struct list_head **pos) { struct rdt_domain *d; struct list_head *l; @@ -377,6 +410,44 @@ static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_domain *d) return 0; } +static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d) +{ + size_t tsize; + + if (is_llc_occupancy_enabled()) { + d->rmid_busy_llc = kcalloc(BITS_TO_LONGS(r->num_rmid), + sizeof(unsigned long), + GFP_KERNEL); + if (!d->rmid_busy_llc) + return -ENOMEM; + INIT_DELAYED_WORK(&d->cqm_limbo, cqm_handle_limbo); + } + if (is_mbm_total_enabled()) { + tsize = sizeof(*d->mbm_total); + d->mbm_total = kcalloc(r->num_rmid, tsize, GFP_KERNEL); + if (!d->mbm_total) { + kfree(d->rmid_busy_llc); + return -ENOMEM; + } + } + if (is_mbm_local_enabled()) { + tsize = sizeof(*d->mbm_local); + d->mbm_local = kcalloc(r->num_rmid, tsize, GFP_KERNEL); + if (!d->mbm_local) { + kfree(d->rmid_busy_llc); + kfree(d->mbm_total); + return -ENOMEM; + } + } + + if (is_mbm_enabled()) { + INIT_DELAYED_WORK(&d->mbm_over, mbm_handle_overflow); + mbm_setup_overflow_handler(d, MBM_OVERFLOW_INTERVAL); + } + + return 0; +} + /* * domain_add_cpu - Add a cpu to a resource's domain list. * @@ -412,14 +483,26 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r) return; d->id = id; + cpumask_set_cpu(cpu, &d->cpu_mask); - if (domain_setup_ctrlval(r, d)) { + if (r->alloc_capable && domain_setup_ctrlval(r, d)) { + kfree(d); + return; + } + + if (r->mon_capable && domain_setup_mon_state(r, d)) { kfree(d); return; } - cpumask_set_cpu(cpu, &d->cpu_mask); list_add_tail(&d->list, add_pos); + + /* + * If resctrl is mounted, add + * per domain monitor data directories. + */ + if (static_branch_unlikely(&rdt_mon_enable_key)) + mkdir_mondata_subdir_allrdtgrp(r, d); } static void domain_remove_cpu(int cpu, struct rdt_resource *r) @@ -435,19 +518,58 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r) cpumask_clear_cpu(cpu, &d->cpu_mask); if (cpumask_empty(&d->cpu_mask)) { + /* + * If resctrl is mounted, remove all the + * per domain monitor data directories. + */ + if (static_branch_unlikely(&rdt_mon_enable_key)) + rmdir_mondata_subdir_allrdtgrp(r, d->id); kfree(d->ctrl_val); + kfree(d->rmid_busy_llc); + kfree(d->mbm_total); + kfree(d->mbm_local); list_del(&d->list); + if (is_mbm_enabled()) + cancel_delayed_work(&d->mbm_over); + if (is_llc_occupancy_enabled() && has_busy_rmid(r, d)) { + /* + * When a package is going down, forcefully + * decrement rmid->ebusy. There is no way to know + * that the L3 was flushed and hence may lead to + * incorrect counts in rare scenarios, but leaving + * the RMID as busy creates RMID leaks if the + * package never comes back. + */ + __check_limbo(d, true); + cancel_delayed_work(&d->cqm_limbo); + } + kfree(d); + return; + } + + if (r == &rdt_resources_all[RDT_RESOURCE_L3]) { + if (is_mbm_enabled() && cpu == d->mbm_work_cpu) { + cancel_delayed_work(&d->mbm_over); + mbm_setup_overflow_handler(d, 0); + } + if (is_llc_occupancy_enabled() && cpu == d->cqm_work_cpu && + has_busy_rmid(r, d)) { + cancel_delayed_work(&d->cqm_limbo); + cqm_setup_limbo_handler(d, 0); + } } } -static void clear_closid(int cpu) +static void clear_closid_rmid(int cpu) { struct intel_pqr_state *state = this_cpu_ptr(&pqr_state); - per_cpu(cpu_closid, cpu) = 0; - state->closid = 0; - wrmsr(MSR_IA32_PQR_ASSOC, state->rmid, 0); + state->default_closid = 0; + state->default_rmid = 0; + state->cur_closid = 0; + state->cur_rmid = 0; + wrmsr(IA32_PQR_ASSOC, 0, 0); } static int intel_rdt_online_cpu(unsigned int cpu) @@ -459,12 +581,23 @@ static int intel_rdt_online_cpu(unsigned int cpu) domain_add_cpu(cpu, r); /* The cpu is set in default rdtgroup after online. */ cpumask_set_cpu(cpu, &rdtgroup_default.cpu_mask); - clear_closid(cpu); + clear_closid_rmid(cpu); mutex_unlock(&rdtgroup_mutex); return 0; } +static void clear_childcpus(struct rdtgroup *r, unsigned int cpu) +{ + struct rdtgroup *cr; + + list_for_each_entry(cr, &r->mon.crdtgrp_list, mon.crdtgrp_list) { + if (cpumask_test_and_clear_cpu(cpu, &cr->cpu_mask)) { + break; + } + } +} + static int intel_rdt_offline_cpu(unsigned int cpu) { struct rdtgroup *rdtgrp; @@ -474,10 +607,12 @@ static int intel_rdt_offline_cpu(unsigned int cpu) for_each_capable_rdt_resource(r) domain_remove_cpu(cpu, r); list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) { - if (cpumask_test_and_clear_cpu(cpu, &rdtgrp->cpu_mask)) + if (cpumask_test_and_clear_cpu(cpu, &rdtgrp->cpu_mask)) { + clear_childcpus(rdtgrp, cpu); break; + } } - clear_closid(cpu); + clear_closid_rmid(cpu); mutex_unlock(&rdtgroup_mutex); return 0; @@ -492,7 +627,7 @@ static __init void rdt_init_padding(void) struct rdt_resource *r; int cl; - for_each_capable_rdt_resource(r) { + for_each_alloc_capable_rdt_resource(r) { cl = strlen(r->name); if (cl > max_name_width) max_name_width = cl; @@ -502,38 +637,153 @@ static __init void rdt_init_padding(void) } } -static __init bool get_rdt_resources(void) +enum { + RDT_FLAG_CMT, + RDT_FLAG_MBM_TOTAL, + RDT_FLAG_MBM_LOCAL, + RDT_FLAG_L3_CAT, + RDT_FLAG_L3_CDP, + RDT_FLAG_L2_CAT, + RDT_FLAG_MBA, +}; + +#define RDT_OPT(idx, n, f) \ +[idx] = { \ + .name = n, \ + .flag = f \ +} + +struct rdt_options { + char *name; + int flag; + bool force_off, force_on; +}; + +static struct rdt_options rdt_options[] __initdata = { + RDT_OPT(RDT_FLAG_CMT, "cmt", X86_FEATURE_CQM_OCCUP_LLC), + RDT_OPT(RDT_FLAG_MBM_TOTAL, "mbmtotal", X86_FEATURE_CQM_MBM_TOTAL), + RDT_OPT(RDT_FLAG_MBM_LOCAL, "mbmlocal", X86_FEATURE_CQM_MBM_LOCAL), + RDT_OPT(RDT_FLAG_L3_CAT, "l3cat", X86_FEATURE_CAT_L3), + RDT_OPT(RDT_FLAG_L3_CDP, "l3cdp", X86_FEATURE_CDP_L3), + RDT_OPT(RDT_FLAG_L2_CAT, "l2cat", X86_FEATURE_CAT_L2), + RDT_OPT(RDT_FLAG_MBA, "mba", X86_FEATURE_MBA), +}; +#define NUM_RDT_OPTIONS ARRAY_SIZE(rdt_options) + +static int __init set_rdt_options(char *str) +{ + struct rdt_options *o; + bool force_off; + char *tok; + + if (*str == '=') + str++; + while ((tok = strsep(&str, ",")) != NULL) { + force_off = *tok == '!'; + if (force_off) + tok++; + for (o = rdt_options; o < &rdt_options[NUM_RDT_OPTIONS]; o++) { + if (strcmp(tok, o->name) == 0) { + if (force_off) + o->force_off = true; + else + o->force_on = true; + break; + } + } + } + return 1; +} +__setup("rdt", set_rdt_options); + +static bool __init rdt_cpu_has(int flag) +{ + bool ret = boot_cpu_has(flag); + struct rdt_options *o; + + if (!ret) + return ret; + + for (o = rdt_options; o < &rdt_options[NUM_RDT_OPTIONS]; o++) { + if (flag == o->flag) { + if (o->force_off) + ret = false; + if (o->force_on) + ret = true; + break; + } + } + return ret; +} + +static __init bool get_rdt_alloc_resources(void) { bool ret = false; - if (cache_alloc_hsw_probe()) + if (rdt_alloc_capable) return true; if (!boot_cpu_has(X86_FEATURE_RDT_A)) return false; - if (boot_cpu_has(X86_FEATURE_CAT_L3)) { - rdt_get_cache_config(1, &rdt_resources_all[RDT_RESOURCE_L3]); - if (boot_cpu_has(X86_FEATURE_CDP_L3)) { + if (rdt_cpu_has(X86_FEATURE_CAT_L3)) { + rdt_get_cache_alloc_cfg(1, &rdt_resources_all[RDT_RESOURCE_L3]); + if (rdt_cpu_has(X86_FEATURE_CDP_L3)) { rdt_get_cdp_l3_config(RDT_RESOURCE_L3DATA); rdt_get_cdp_l3_config(RDT_RESOURCE_L3CODE); } ret = true; } - if (boot_cpu_has(X86_FEATURE_CAT_L2)) { + if (rdt_cpu_has(X86_FEATURE_CAT_L2)) { /* CPUID 0x10.2 fields are same format at 0x10.1 */ - rdt_get_cache_config(2, &rdt_resources_all[RDT_RESOURCE_L2]); + rdt_get_cache_alloc_cfg(2, &rdt_resources_all[RDT_RESOURCE_L2]); ret = true; } - if (boot_cpu_has(X86_FEATURE_MBA)) { + if (rdt_cpu_has(X86_FEATURE_MBA)) { if (rdt_get_mem_config(&rdt_resources_all[RDT_RESOURCE_MBA])) ret = true; } - return ret; } +static __init bool get_rdt_mon_resources(void) +{ + if (rdt_cpu_has(X86_FEATURE_CQM_OCCUP_LLC)) + rdt_mon_features |= (1 << QOS_L3_OCCUP_EVENT_ID); + if (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL)) + rdt_mon_features |= (1 << QOS_L3_MBM_TOTAL_EVENT_ID); + if (rdt_cpu_has(X86_FEATURE_CQM_MBM_LOCAL)) + rdt_mon_features |= (1 << QOS_L3_MBM_LOCAL_EVENT_ID); + + if (!rdt_mon_features) + return false; + + return !rdt_get_mon_l3_config(&rdt_resources_all[RDT_RESOURCE_L3]); +} + +static __init void rdt_quirks(void) +{ + switch (boot_cpu_data.x86_model) { + case INTEL_FAM6_HASWELL_X: + if (!rdt_options[RDT_FLAG_L3_CAT].force_off) + cache_alloc_hsw_probe(); + break; + case INTEL_FAM6_SKYLAKE_X: + if (boot_cpu_data.x86_mask <= 4) + set_rdt_options("!cmt,!mbmtotal,!mbmlocal,!l3cat"); + } +} + +static __init bool get_rdt_resources(void) +{ + rdt_quirks(); + rdt_alloc_capable = get_rdt_alloc_resources(); + rdt_mon_capable = get_rdt_mon_resources(); + + return (rdt_mon_capable || rdt_alloc_capable); +} + static int __init intel_rdt_late_init(void) { struct rdt_resource *r; @@ -556,9 +806,12 @@ static int __init intel_rdt_late_init(void) return ret; } - for_each_capable_rdt_resource(r) + for_each_alloc_capable_rdt_resource(r) pr_info("Intel RDT %s allocation detected\n", r->name); + for_each_mon_capable_rdt_resource(r) + pr_info("Intel RDT %s monitoring detected\n", r->name); + return 0; } diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h new file mode 100644 index 000000000000..ebaddaeef023 --- /dev/null +++ b/arch/x86/kernel/cpu/intel_rdt.h @@ -0,0 +1,440 @@ +#ifndef _ASM_X86_INTEL_RDT_H +#define _ASM_X86_INTEL_RDT_H + +#include <linux/sched.h> +#include <linux/kernfs.h> +#include <linux/jump_label.h> + +#define IA32_L3_QOS_CFG 0xc81 +#define IA32_L3_CBM_BASE 0xc90 +#define IA32_L2_CBM_BASE 0xd10 +#define IA32_MBA_THRTL_BASE 0xd50 + +#define L3_QOS_CDP_ENABLE 0x01ULL + +/* + * Event IDs are used to program IA32_QM_EVTSEL before reading event + * counter from IA32_QM_CTR + */ +#define QOS_L3_OCCUP_EVENT_ID 0x01 +#define QOS_L3_MBM_TOTAL_EVENT_ID 0x02 +#define QOS_L3_MBM_LOCAL_EVENT_ID 0x03 + +#define CQM_LIMBOCHECK_INTERVAL 1000 + +#define MBM_CNTR_WIDTH 24 +#define MBM_OVERFLOW_INTERVAL 1000 + +#define RMID_VAL_ERROR BIT_ULL(63) +#define RMID_VAL_UNAVAIL BIT_ULL(62) + +DECLARE_STATIC_KEY_FALSE(rdt_enable_key); + +/** + * struct mon_evt - Entry in the event list of a resource + * @evtid: event id + * @name: name of the event + */ +struct mon_evt { + u32 evtid; + char *name; + struct list_head list; +}; + +/** + * struct mon_data_bits - Monitoring details for each event file + * @rid: Resource id associated with the event file. + * @evtid: Event id associated with the event file + * @domid: The domain to which the event file belongs + */ +union mon_data_bits { + void *priv; + struct { + unsigned int rid : 10; + unsigned int evtid : 8; + unsigned int domid : 14; + } u; +}; + +struct rmid_read { + struct rdtgroup *rgrp; + struct rdt_domain *d; + int evtid; + bool first; + u64 val; +}; + +extern unsigned int intel_cqm_threshold; +extern bool rdt_alloc_capable; +extern bool rdt_mon_capable; +extern unsigned int rdt_mon_features; + +enum rdt_group_type { + RDTCTRL_GROUP = 0, + RDTMON_GROUP, + RDT_NUM_GROUP, +}; + +/** + * struct mongroup - store mon group's data in resctrl fs. + * @mon_data_kn kernlfs node for the mon_data directory + * @parent: parent rdtgrp + * @crdtgrp_list: child rdtgroup node list + * @rmid: rmid for this rdtgroup + */ +struct mongroup { + struct kernfs_node *mon_data_kn; + struct rdtgroup *parent; + struct list_head crdtgrp_list; + u32 rmid; +}; + +/** + * struct rdtgroup - store rdtgroup's data in resctrl file system. + * @kn: kernfs node + * @rdtgroup_list: linked list for all rdtgroups + * @closid: closid for this rdtgroup + * @cpu_mask: CPUs assigned to this rdtgroup + * @flags: status bits + * @waitcount: how many cpus expect to find this + * group when they acquire rdtgroup_mutex + * @type: indicates type of this rdtgroup - either + * monitor only or ctrl_mon group + * @mon: mongroup related data + */ +struct rdtgroup { + struct kernfs_node *kn; + struct list_head rdtgroup_list; + u32 closid; + struct cpumask cpu_mask; + int flags; + atomic_t waitcount; + enum rdt_group_type type; + struct mongroup mon; +}; + +/* rdtgroup.flags */ +#define RDT_DELETED 1 + +/* rftype.flags */ +#define RFTYPE_FLAGS_CPUS_LIST 1 + +/* + * Define the file type flags for base and info directories. + */ +#define RFTYPE_INFO BIT(0) +#define RFTYPE_BASE BIT(1) +#define RF_CTRLSHIFT 4 +#define RF_MONSHIFT 5 +#define RFTYPE_CTRL BIT(RF_CTRLSHIFT) +#define RFTYPE_MON BIT(RF_MONSHIFT) +#define RFTYPE_RES_CACHE BIT(8) +#define RFTYPE_RES_MB BIT(9) +#define RF_CTRL_INFO (RFTYPE_INFO | RFTYPE_CTRL) +#define RF_MON_INFO (RFTYPE_INFO | RFTYPE_MON) +#define RF_CTRL_BASE (RFTYPE_BASE | RFTYPE_CTRL) + +/* List of all resource groups */ +extern struct list_head rdt_all_groups; + +extern int max_name_width, max_data_width; + +int __init rdtgroup_init(void); + +/** + * struct rftype - describe each file in the resctrl file system + * @name: File name + * @mode: Access mode + * @kf_ops: File operations + * @flags: File specific RFTYPE_FLAGS_* flags + * @fflags: File specific RF_* or RFTYPE_* flags + * @seq_show: Show content of the file + * @write: Write to the file + */ +struct rftype { + char *name; + umode_t mode; + struct kernfs_ops *kf_ops; + unsigned long flags; + unsigned long fflags; + + int (*seq_show)(struct kernfs_open_file *of, + struct seq_file *sf, void *v); + /* + * write() is the generic write callback which maps directly to + * kernfs write operation and overrides all other operations. + * Maximum write size is determined by ->max_write_len. + */ + ssize_t (*write)(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off); +}; + +/** + * 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 + */ +struct mbm_state { + u64 chunks; + u64 prev_msr; +}; + +/** + * struct rdt_domain - group of cpus sharing an RDT resource + * @list: all instances of this resource + * @id: unique id for this instance + * @cpu_mask: which cpus share this resource + * @rmid_busy_llc: + * bitmap of which limbo RMIDs are above threshold + * @mbm_total: saved state for MBM total bandwidth + * @mbm_local: saved state for MBM local bandwidth + * @mbm_over: worker to periodically read MBM h/w counters + * @cqm_limbo: worker to periodically read CQM h/w counters + * @mbm_work_cpu: + * worker cpu for MBM h/w counters + * @cqm_work_cpu: + * worker cpu for CQM h/w counters + * @ctrl_val: array of cache or mem ctrl values (indexed by CLOSID) + * @new_ctrl: new ctrl value to be loaded + * @have_new_ctrl: did user provide new_ctrl for this domain + */ +struct rdt_domain { + struct list_head list; + int id; + struct cpumask cpu_mask; + unsigned long *rmid_busy_llc; + struct mbm_state *mbm_total; + struct mbm_state *mbm_local; + struct delayed_work mbm_over; + struct delayed_work cqm_limbo; + int mbm_work_cpu; + int cqm_work_cpu; + u32 *ctrl_val; + u32 new_ctrl; + bool have_new_ctrl; +}; + +/** + * struct msr_param - set a range of MSRs from a domain + * @res: The resource to use + * @low: Beginning index from base MSR + * @high: End index + */ +struct msr_param { + struct rdt_resource *res; + int low; + int high; +}; + +/** + * struct rdt_cache - Cache allocation related data + * @cbm_len: Length of the cache bit mask + * @min_cbm_bits: Minimum number of consecutive bits to be set + * @cbm_idx_mult: Multiplier of CBM index + * @cbm_idx_offset: Offset of CBM index. CBM index is computed by: + * closid * cbm_idx_multi + cbm_idx_offset + * in a cache bit mask + * @shareable_bits: Bitmask of shareable resource with other + * executing entities + */ +struct rdt_cache { + unsigned int cbm_len; + unsigned int min_cbm_bits; + unsigned int cbm_idx_mult; + unsigned int cbm_idx_offset; + unsigned int shareable_bits; +}; + +/** + * 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 + * @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; + u32 *mb_map; +}; + +static inline bool is_llc_occupancy_enabled(void) +{ + return (rdt_mon_features & (1 << QOS_L3_OCCUP_EVENT_ID)); +} + +static inline bool is_mbm_total_enabled(void) +{ + return (rdt_mon_features & (1 << QOS_L3_MBM_TOTAL_EVENT_ID)); +} + +static inline bool is_mbm_local_enabled(void) +{ + return (rdt_mon_features & (1 << QOS_L3_MBM_LOCAL_EVENT_ID)); +} + +static inline bool is_mbm_enabled(void) +{ + return (is_mbm_total_enabled() || is_mbm_local_enabled()); +} + +static inline bool is_mbm_event(int e) +{ + return (e >= QOS_L3_MBM_TOTAL_EVENT_ID && + e <= QOS_L3_MBM_LOCAL_EVENT_ID); +} + +/** + * struct rdt_resource - attributes of an RDT resource + * @rid: The index of the resource + * @alloc_enabled: Is allocation enabled on this machine + * @mon_enabled: Is monitoring enabled for this feature + * @alloc_capable: Is allocation available on this machine + * @mon_capable: Is monitor feature available on this machine + * @name: Name to use in "schemata" file + * @num_closid: Number of CLOSIDs available + * @cache_level: Which cache level defines scope of this resource + * @default_ctrl: Specifies default cache cbm or memory B/W percent. + * @msr_base: Base MSR address for CBMs + * @msr_update: Function pointer to update QOS MSRs + * @data_width: Character width of data when displaying + * @domains: All domains for this resource + * @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 + * @evt_list: List of monitoring events + * @num_rmid: Number of RMIDs available + * @mon_scale: cqm counter * mon_scale = occupancy in bytes + * @fflags: flags to choose base and info files + */ +struct rdt_resource { + int rid; + bool alloc_enabled; + bool mon_enabled; + bool alloc_capable; + bool mon_capable; + char *name; + int num_closid; + int cache_level; + u32 default_ctrl; + unsigned int msr_base; + void (*msr_update) (struct rdt_domain *d, struct msr_param *m, + struct rdt_resource *r); + int data_width; + struct list_head domains; + struct rdt_cache cache; + struct rdt_membw membw; + const char *format_str; + int (*parse_ctrlval) (char *buf, struct rdt_resource *r, + struct rdt_domain *d); + struct list_head evt_list; + int num_rmid; + unsigned int mon_scale; + unsigned long fflags; +}; + +int parse_cbm(char *buf, struct rdt_resource *r, struct rdt_domain *d); +int parse_bw(char *buf, struct rdt_resource *r, struct rdt_domain *d); + +extern struct mutex rdtgroup_mutex; + +extern struct rdt_resource rdt_resources_all[]; +extern struct rdtgroup rdtgroup_default; +DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key); + +int __init rdtgroup_init(void); + +enum { + RDT_RESOURCE_L3, + RDT_RESOURCE_L3DATA, + RDT_RESOURCE_L3CODE, + RDT_RESOURCE_L2, + RDT_RESOURCE_MBA, + + /* Must be the last */ + RDT_NUM_RESOURCES, +}; + +#define for_each_capable_rdt_resource(r) \ + for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\ + r++) \ + if (r->alloc_capable || r->mon_capable) + +#define for_each_alloc_capable_rdt_resource(r) \ + for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\ + r++) \ + if (r->alloc_capable) + +#define for_each_mon_capable_rdt_resource(r) \ + for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\ + r++) \ + if (r->mon_capable) + +#define for_each_alloc_enabled_rdt_resource(r) \ + for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\ + r++) \ + if (r->alloc_enabled) + +#define for_each_mon_enabled_rdt_resource(r) \ + for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\ + r++) \ + if (r->mon_enabled) + +/* CPUID.(EAX=10H, ECX=ResID=1).EAX */ +union cpuid_0x10_1_eax { + struct { + unsigned int cbm_len:5; + } split; + unsigned int full; +}; + +/* CPUID.(EAX=10H, ECX=ResID=3).EAX */ +union cpuid_0x10_3_eax { + struct { + unsigned int max_delay:12; + } split; + unsigned int full; +}; + +/* CPUID.(EAX=10H, ECX=ResID).EDX */ +union cpuid_0x10_x_edx { + struct { + unsigned int cos_max:16; + } split; + unsigned int full; +}; + +void rdt_ctrl_update(void *arg); +struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn); +void rdtgroup_kn_unlock(struct kernfs_node *kn); +struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id, + struct list_head **pos); +ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off); +int rdtgroup_schemata_show(struct kernfs_open_file *of, + struct seq_file *s, void *v); +struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r); +int alloc_rmid(void); +void free_rmid(u32 rmid); +int rdt_get_mon_l3_config(struct rdt_resource *r); +void mon_event_count(void *info); +int rdtgroup_mondata_show(struct seq_file *m, void *arg); +void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r, + unsigned int dom_id); +void mkdir_mondata_subdir_allrdtgrp(struct rdt_resource *r, + struct rdt_domain *d); +void mon_event_read(struct rmid_read *rr, struct rdt_domain *d, + struct rdtgroup *rdtgrp, int evtid, int first); +void mbm_setup_overflow_handler(struct rdt_domain *dom, + unsigned long delay_ms); +void mbm_handle_overflow(struct work_struct *work); +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); + +#endif /* _ASM_X86_INTEL_RDT_H */ diff --git a/arch/x86/kernel/cpu/intel_rdt_schemata.c b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c index 406d7a6532f9..f6ea94f8954a 100644 --- a/arch/x86/kernel/cpu/intel_rdt_schemata.c +++ b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c @@ -26,7 +26,7 @@ #include <linux/kernfs.h> #include <linux/seq_file.h> #include <linux/slab.h> -#include <asm/intel_rdt.h> +#include "intel_rdt.h" /* * Check whether MBA bandwidth percentage value is correct. The value is @@ -192,7 +192,7 @@ static int rdtgroup_parse_resource(char *resname, char *tok, int closid) { struct rdt_resource *r; - for_each_enabled_rdt_resource(r) { + for_each_alloc_enabled_rdt_resource(r) { if (!strcmp(resname, r->name) && closid < r->num_closid) return parse_line(tok, r); } @@ -221,7 +221,7 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, closid = rdtgrp->closid; - for_each_enabled_rdt_resource(r) { + for_each_alloc_enabled_rdt_resource(r) { list_for_each_entry(dom, &r->domains, list) dom->have_new_ctrl = false; } @@ -237,7 +237,7 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, goto out; } - for_each_enabled_rdt_resource(r) { + for_each_alloc_enabled_rdt_resource(r) { ret = update_domains(r, closid); if (ret) goto out; @@ -269,12 +269,13 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of, { struct rdtgroup *rdtgrp; struct rdt_resource *r; - int closid, ret = 0; + int ret = 0; + u32 closid; rdtgrp = rdtgroup_kn_lock_live(of->kn); if (rdtgrp) { closid = rdtgrp->closid; - for_each_enabled_rdt_resource(r) { + for_each_alloc_enabled_rdt_resource(r) { if (closid < r->num_closid) show_doms(s, r, closid); } @@ -284,3 +285,57 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of, rdtgroup_kn_unlock(of->kn); return ret; } + +void mon_event_read(struct rmid_read *rr, struct rdt_domain *d, + struct rdtgroup *rdtgrp, int evtid, int first) +{ + /* + * setup the parameters to send to the IPI to read the data. + */ + rr->rgrp = rdtgrp; + rr->evtid = evtid; + rr->d = d; + rr->val = 0; + rr->first = first; + + smp_call_function_any(&d->cpu_mask, mon_event_count, rr, 1); +} + +int rdtgroup_mondata_show(struct seq_file *m, void *arg) +{ + struct kernfs_open_file *of = m->private; + u32 resid, evtid, domid; + struct rdtgroup *rdtgrp; + struct rdt_resource *r; + union mon_data_bits md; + struct rdt_domain *d; + struct rmid_read rr; + int ret = 0; + + rdtgrp = rdtgroup_kn_lock_live(of->kn); + + md.priv = of->kn->priv; + resid = md.u.rid; + domid = md.u.domid; + evtid = md.u.evtid; + + r = &rdt_resources_all[resid]; + d = rdt_find_domain(r, domid, NULL); + if (!d) { + ret = -ENOENT; + goto out; + } + + mon_event_read(&rr, d, rdtgrp, evtid, false); + + if (rr.val & RMID_VAL_ERROR) + seq_puts(m, "Error\n"); + else if (rr.val & RMID_VAL_UNAVAIL) + seq_puts(m, "Unavailable\n"); + else + seq_printf(m, "%llu\n", rr.val * r->mon_scale); + +out: + rdtgroup_kn_unlock(of->kn); + return ret; +} diff --git a/arch/x86/kernel/cpu/intel_rdt_monitor.c b/arch/x86/kernel/cpu/intel_rdt_monitor.c new file mode 100644 index 000000000000..30827510094b --- /dev/null +++ b/arch/x86/kernel/cpu/intel_rdt_monitor.c @@ -0,0 +1,499 @@ +/* + * Resource Director Technology(RDT) + * - Monitoring code + * + * Copyright (C) 2017 Intel Corporation + * + * Author: + * Vikas Shivappa <vikas.shivappa@intel.com> + * + * This replaces the cqm.c based on perf but we reuse a lot of + * code and datastructures originally from Peter Zijlstra and Matt Fleming. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * More information about RDT be found in the Intel (R) x86 Architecture + * Software Developer Manual June 2016, volume 3, section 17.17. + */ + +#include <linux/module.h> +#include <linux/slab.h> +#include <asm/cpu_device_id.h> +#include "intel_rdt.h" + +#define MSR_IA32_QM_CTR 0x0c8e +#define MSR_IA32_QM_EVTSEL 0x0c8d + +struct rmid_entry { + u32 rmid; + int busy; + struct list_head list; +}; + +/** + * @rmid_free_lru A least recently used list of free RMIDs + * These RMIDs are guaranteed to have an occupancy less than the + * threshold occupancy + */ +static LIST_HEAD(rmid_free_lru); + +/** + * @rmid_limbo_count count of currently unused but (potentially) + * dirty RMIDs. + * This counts RMIDs that no one is currently using but that + * may have a occupancy value > intel_cqm_threshold. User can change + * the threshold occupancy value. + */ +unsigned int rmid_limbo_count; + +/** + * @rmid_entry - The entry in the limbo and free lists. + */ +static struct rmid_entry *rmid_ptrs; + +/* + * Global boolean for rdt_monitor which is true if any + * resource monitoring is enabled. + */ +bool rdt_mon_capable; + +/* + * Global to indicate which monitoring events are enabled. + */ +unsigned int rdt_mon_features; + +/* + * This is the threshold cache occupancy at which we will consider an + * RMID available for re-allocation. + */ +unsigned int intel_cqm_threshold; + +static inline struct rmid_entry *__rmid_entry(u32 rmid) +{ + struct rmid_entry *entry; + + entry = &rmid_ptrs[rmid]; + WARN_ON(entry->rmid != rmid); + + return entry; +} + +static u64 __rmid_read(u32 rmid, u32 eventid) +{ + u64 val; + + /* + * As per the SDM, when IA32_QM_EVTSEL.EvtID (bits 7:0) is configured + * with a valid event code for supported resource type and the bits + * IA32_QM_EVTSEL.RMID (bits 41:32) are configured with valid RMID, + * IA32_QM_CTR.data (bits 61:0) reports the monitored data. + * IA32_QM_CTR.Error (bit 63) and IA32_QM_CTR.Unavailable (bit 62) + * are error bits. + */ + wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid); + rdmsrl(MSR_IA32_QM_CTR, val); + + return val; +} + +static bool rmid_dirty(struct rmid_entry *entry) +{ + u64 val = __rmid_read(entry->rmid, QOS_L3_OCCUP_EVENT_ID); + + return val >= intel_cqm_threshold; +} + +/* + * Check the RMIDs that are marked as busy for this domain. If the + * reported LLC occupancy is below the threshold clear the busy bit and + * decrement the count. If the busy count gets to zero on an RMID, we + * free the RMID + */ +void __check_limbo(struct rdt_domain *d, bool force_free) +{ + struct rmid_entry *entry; + struct rdt_resource *r; + u32 crmid = 1, nrmid; + + r = &rdt_resources_all[RDT_RESOURCE_L3]; + + /* + * Skip RMID 0 and start from RMID 1 and check all the RMIDs that + * are marked as busy for occupancy < threshold. If the occupancy + * is less than the threshold decrement the busy counter of the + * RMID and move it to the free list when the counter reaches 0. + */ + for (;;) { + nrmid = find_next_bit(d->rmid_busy_llc, r->num_rmid, crmid); + if (nrmid >= r->num_rmid) + break; + + entry = __rmid_entry(nrmid); + if (force_free || !rmid_dirty(entry)) { + clear_bit(entry->rmid, d->rmid_busy_llc); + if (!--entry->busy) { + rmid_limbo_count--; + list_add_tail(&entry->list, &rmid_free_lru); + } + } + crmid = nrmid + 1; + } +} + +bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d) +{ + return find_first_bit(d->rmid_busy_llc, r->num_rmid) != r->num_rmid; +} + +/* + * As of now the RMIDs allocation is global. + * However we keep track of which packages the RMIDs + * are used to optimize the limbo list management. + */ +int alloc_rmid(void) +{ + struct rmid_entry *entry; + + lockdep_assert_held(&rdtgroup_mutex); + + if (list_empty(&rmid_free_lru)) + return rmid_limbo_count ? -EBUSY : -ENOSPC; + + entry = list_first_entry(&rmid_free_lru, + struct rmid_entry, list); + list_del(&entry->list); + + return entry->rmid; +} + +static void add_rmid_to_limbo(struct rmid_entry *entry) +{ + struct rdt_resource *r; + struct rdt_domain *d; + int cpu; + u64 val; + + r = &rdt_resources_all[RDT_RESOURCE_L3]; + + entry->busy = 0; + cpu = get_cpu(); + list_for_each_entry(d, &r->domains, list) { + if (cpumask_test_cpu(cpu, &d->cpu_mask)) { + val = __rmid_read(entry->rmid, QOS_L3_OCCUP_EVENT_ID); + if (val <= intel_cqm_threshold) + continue; + } + + /* + * For the first limbo RMID in the domain, + * setup up the limbo worker. + */ + if (!has_busy_rmid(r, d)) + cqm_setup_limbo_handler(d, CQM_LIMBOCHECK_INTERVAL); + set_bit(entry->rmid, d->rmid_busy_llc); + entry->busy++; + } + put_cpu(); + + if (entry->busy) + rmid_limbo_count++; + else + list_add_tail(&entry->list, &rmid_free_lru); +} + +void free_rmid(u32 rmid) +{ + struct rmid_entry *entry; + + if (!rmid) + return; + + lockdep_assert_held(&rdtgroup_mutex); + + entry = __rmid_entry(rmid); + + if (is_llc_occupancy_enabled()) + add_rmid_to_limbo(entry); + else + list_add_tail(&entry->list, &rmid_free_lru); +} + +static int __mon_event_count(u32 rmid, struct rmid_read *rr) +{ + u64 chunks, shift, tval; + struct mbm_state *m; + + tval = __rmid_read(rmid, rr->evtid); + if (tval & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL)) { + rr->val = tval; + return -EINVAL; + } + switch (rr->evtid) { + case QOS_L3_OCCUP_EVENT_ID: + rr->val += tval; + return 0; + case QOS_L3_MBM_TOTAL_EVENT_ID: + m = &rr->d->mbm_total[rmid]; + break; + case QOS_L3_MBM_LOCAL_EVENT_ID: + m = &rr->d->mbm_local[rmid]; + break; + default: + /* + * Code would never reach here because + * an invalid event id would fail the __rmid_read. + */ + return -EINVAL; + } + + if (rr->first) { + m->prev_msr = tval; + m->chunks = 0; + return 0; + } + + shift = 64 - MBM_CNTR_WIDTH; + chunks = (tval << shift) - (m->prev_msr << shift); + chunks >>= shift; + m->chunks += chunks; + m->prev_msr = tval; + + rr->val += m->chunks; + return 0; +} + +/* + * This is called via IPI to read the CQM/MBM counters + * on a domain. + */ +void mon_event_count(void *info) +{ + struct rdtgroup *rdtgrp, *entry; + struct rmid_read *rr = info; + struct list_head *head; + + rdtgrp = rr->rgrp; + + if (__mon_event_count(rdtgrp->mon.rmid, rr)) + return; + + /* + * For Ctrl groups read data from child monitor groups. + */ + head = &rdtgrp->mon.crdtgrp_list; + + if (rdtgrp->type == RDTCTRL_GROUP) { + list_for_each_entry(entry, head, mon.crdtgrp_list) { + if (__mon_event_count(entry->mon.rmid, rr)) + return; + } + } +} + +static void mbm_update(struct rdt_domain *d, int rmid) +{ + struct rmid_read rr; + + rr.first = false; + rr.d = d; + + /* + * This is protected from concurrent reads from user + * as both the user and we hold the global mutex. + */ + if (is_mbm_total_enabled()) { + rr.evtid = QOS_L3_MBM_TOTAL_EVENT_ID; + __mon_event_count(rmid, &rr); + } + if (is_mbm_local_enabled()) { + rr.evtid = QOS_L3_MBM_LOCAL_EVENT_ID; + __mon_event_count(rmid, &rr); + } +} + +/* + * Handler to scan the limbo list and move the RMIDs + * to free list whose occupancy < threshold_occupancy. + */ +void cqm_handle_limbo(struct work_struct *work) +{ + unsigned long delay = msecs_to_jiffies(CQM_LIMBOCHECK_INTERVAL); + int cpu = smp_processor_id(); + struct rdt_resource *r; + struct rdt_domain *d; + + 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; + } + + __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); +} + +void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms) +{ + unsigned long delay = msecs_to_jiffies(delay_ms); + struct rdt_resource *r; + int cpu; + + r = &rdt_resources_all[RDT_RESOURCE_L3]; + + cpu = cpumask_any(&dom->cpu_mask); + dom->cqm_work_cpu = cpu; + + schedule_delayed_work_on(cpu, &dom->cqm_limbo, delay); +} + +void mbm_handle_overflow(struct work_struct *work) +{ + unsigned long delay = msecs_to_jiffies(MBM_OVERFLOW_INTERVAL); + struct rdtgroup *prgrp, *crgrp; + int cpu = smp_processor_id(); + struct list_head *head; + struct rdt_domain *d; + + mutex_lock(&rdtgroup_mutex); + + if (!static_branch_likely(&rdt_enable_key)) + goto out_unlock; + + d = get_domain_from_cpu(cpu, &rdt_resources_all[RDT_RESOURCE_L3]); + if (!d) + goto out_unlock; + + list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) { + mbm_update(d, prgrp->mon.rmid); + + head = &prgrp->mon.crdtgrp_list; + list_for_each_entry(crgrp, head, mon.crdtgrp_list) + mbm_update(d, crgrp->mon.rmid); + } + + schedule_delayed_work_on(cpu, &d->mbm_over, delay); + +out_unlock: + mutex_unlock(&rdtgroup_mutex); +} + +void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms) +{ + unsigned long delay = msecs_to_jiffies(delay_ms); + int cpu; + + if (!static_branch_likely(&rdt_enable_key)) + return; + cpu = cpumask_any(&dom->cpu_mask); + dom->mbm_work_cpu = cpu; + schedule_delayed_work_on(cpu, &dom->mbm_over, delay); +} + +static int dom_data_init(struct rdt_resource *r) +{ + struct rmid_entry *entry = NULL; + int i, nr_rmids; + + nr_rmids = r->num_rmid; + rmid_ptrs = kcalloc(nr_rmids, sizeof(struct rmid_entry), GFP_KERNEL); + if (!rmid_ptrs) + return -ENOMEM; + + for (i = 0; i < nr_rmids; i++) { + entry = &rmid_ptrs[i]; + INIT_LIST_HEAD(&entry->list); + + entry->rmid = i; + list_add_tail(&entry->list, &rmid_free_lru); + } + + /* + * RMID 0 is special and is always allocated. It's used for all + * tasks that are not monitored. + */ + entry = __rmid_entry(0); + list_del(&entry->list); + + return 0; +} + +static struct mon_evt llc_occupancy_event = { + .name = "llc_occupancy", + .evtid = QOS_L3_OCCUP_EVENT_ID, +}; + +static struct mon_evt mbm_total_event = { + .name = "mbm_total_bytes", + .evtid = QOS_L3_MBM_TOTAL_EVENT_ID, +}; + +static struct mon_evt mbm_local_event = { + .name = "mbm_local_bytes", + .evtid = QOS_L3_MBM_LOCAL_EVENT_ID, +}; + +/* + * Initialize the event list for the resource. + * + * Note that MBM events are also part of RDT_RESOURCE_L3 resource + * because as per the SDM the total and local memory bandwidth + * are enumerated as part of L3 monitoring. + */ +static void l3_mon_evt_init(struct rdt_resource *r) +{ + INIT_LIST_HEAD(&r->evt_list); + + if (is_llc_occupancy_enabled()) + list_add_tail(&llc_occupancy_event.list, &r->evt_list); + if (is_mbm_total_enabled()) + list_add_tail(&mbm_total_event.list, &r->evt_list); + if (is_mbm_local_enabled()) + list_add_tail(&mbm_local_event.list, &r->evt_list); +} + +int rdt_get_mon_l3_config(struct rdt_resource *r) +{ + int ret; + + r->mon_scale = boot_cpu_data.x86_cache_occ_scale; + r->num_rmid = boot_cpu_data.x86_cache_max_rmid + 1; + + /* + * A reasonable upper limit on the max threshold is the number + * of lines tagged per RMID if all RMIDs have the same number of + * lines tagged in the LLC. + * + * For a 35MB LLC and 56 RMIDs, this is ~1.8% of the LLC. + */ + intel_cqm_threshold = boot_cpu_data.x86_cache_size * 1024 / r->num_rmid; + + /* h/w works in units of "boot_cpu_data.x86_cache_occ_scale" */ + intel_cqm_threshold /= r->mon_scale; + + ret = dom_data_init(r); + if (ret) + return ret; + + l3_mon_evt_init(r); + + r->mon_capable = true; + r->mon_enabled = true; + + return 0; +} diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c index 9257bd9dc664..a869d4a073c5 100644 --- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c +++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c @@ -32,17 +32,25 @@ #include <uapi/linux/magic.h> -#include <asm/intel_rdt.h> -#include <asm/intel_rdt_common.h> +#include <asm/intel_rdt_sched.h> +#include "intel_rdt.h" DEFINE_STATIC_KEY_FALSE(rdt_enable_key); -struct kernfs_root *rdt_root; +DEFINE_STATIC_KEY_FALSE(rdt_mon_enable_key); +DEFINE_STATIC_KEY_FALSE(rdt_alloc_enable_key); +static struct kernfs_root *rdt_root; struct rdtgroup rdtgroup_default; LIST_HEAD(rdt_all_groups); /* Kernel fs node for "info" directory under root */ static struct kernfs_node *kn_info; +/* Kernel fs node for "mon_groups" directory under root */ +static struct kernfs_node *kn_mongrp; + +/* Kernel fs node for "mon_data" directory under root */ +static struct kernfs_node *kn_mondata; + /* * Trivial allocator for CLOSIDs. Since h/w only supports a small number, * we can keep a bitmap of free CLOSIDs in a single integer. @@ -66,7 +74,7 @@ static void closid_init(void) int rdt_min_closid = 32; /* Compute rdt_min_closid across all resources */ - for_each_enabled_rdt_resource(r) + for_each_alloc_enabled_rdt_resource(r) rdt_min_closid = min(rdt_min_closid, r->num_closid); closid_free_map = BIT_MASK(rdt_min_closid) - 1; @@ -75,9 +83,9 @@ static void closid_init(void) closid_free_map &= ~1; } -int closid_alloc(void) +static int closid_alloc(void) { - int closid = ffs(closid_free_map); + u32 closid = ffs(closid_free_map); if (closid == 0) return -ENOSPC; @@ -125,28 +133,6 @@ static int rdtgroup_add_file(struct kernfs_node *parent_kn, struct rftype *rft) return 0; } -static int rdtgroup_add_files(struct kernfs_node *kn, struct rftype *rfts, - int len) -{ - struct rftype *rft; - int ret; - - lockdep_assert_held(&rdtgroup_mutex); - - for (rft = rfts; rft < rfts + len; rft++) { - ret = rdtgroup_add_file(kn, rft); - if (ret) - goto error; - } - - return 0; -error: - pr_warn("Failed to add %s, err=%d\n", rft->name, ret); - while (--rft >= rfts) - kernfs_remove_by_name(kn, rft->name); - return ret; -} - static int rdtgroup_seqfile_show(struct seq_file *m, void *arg) { struct kernfs_open_file *of = m->private; @@ -174,6 +160,11 @@ static struct kernfs_ops rdtgroup_kf_single_ops = { .seq_show = rdtgroup_seqfile_show, }; +static struct kernfs_ops kf_mondata_ops = { + .atomic_write_len = PAGE_SIZE, + .seq_show = rdtgroup_mondata_show, +}; + static bool is_cpu_list(struct kernfs_open_file *of) { struct rftype *rft = of->kn->priv; @@ -203,13 +194,18 @@ static int rdtgroup_cpus_show(struct kernfs_open_file *of, /* * This is safe against intel_rdt_sched_in() called from __switch_to() * because __switch_to() is executed with interrupts disabled. A local call - * from rdt_update_closid() is proteced against __switch_to() because + * from update_closid_rmid() is proteced against __switch_to() because * preemption is disabled. */ -static void rdt_update_cpu_closid(void *closid) +static void update_cpu_closid_rmid(void *info) { - if (closid) - this_cpu_write(cpu_closid, *(int *)closid); + struct rdtgroup *r = info; + + if (r) { + this_cpu_write(pqr_state.default_closid, r->closid); + this_cpu_write(pqr_state.default_rmid, r->mon.rmid); + } + /* * We cannot unconditionally write the MSR because the current * executing task might have its own closid selected. Just reuse @@ -221,28 +217,128 @@ static void rdt_update_cpu_closid(void *closid) /* * Update the PGR_ASSOC MSR on all cpus in @cpu_mask, * - * Per task closids must have been set up before calling this function. - * - * The per cpu closids are updated with the smp function call, when @closid - * is not NULL. If @closid is NULL then all affected percpu closids must - * have been set up before calling this function. + * Per task closids/rmids must have been set up before calling this function. */ static void -rdt_update_closid(const struct cpumask *cpu_mask, int *closid) +update_closid_rmid(const struct cpumask *cpu_mask, struct rdtgroup *r) { int cpu = get_cpu(); if (cpumask_test_cpu(cpu, cpu_mask)) - rdt_update_cpu_closid(closid); - smp_call_function_many(cpu_mask, rdt_update_cpu_closid, closid, 1); + update_cpu_closid_rmid(r); + smp_call_function_many(cpu_mask, update_cpu_closid_rmid, r, 1); put_cpu(); } +static int cpus_mon_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask, + cpumask_var_t tmpmask) +{ + struct rdtgroup *prgrp = rdtgrp->mon.parent, *crgrp; + struct list_head *head; + + /* Check whether cpus belong to parent ctrl group */ + cpumask_andnot(tmpmask, newmask, &prgrp->cpu_mask); + if (cpumask_weight(tmpmask)) + return -EINVAL; + + /* Check whether cpus are dropped from this group */ + cpumask_andnot(tmpmask, &rdtgrp->cpu_mask, newmask); + if (cpumask_weight(tmpmask)) { + /* Give any dropped cpus to parent rdtgroup */ + cpumask_or(&prgrp->cpu_mask, &prgrp->cpu_mask, tmpmask); + update_closid_rmid(tmpmask, prgrp); + } + + /* + * If we added cpus, remove them from previous group that owned them + * and update per-cpu rmid + */ + cpumask_andnot(tmpmask, newmask, &rdtgrp->cpu_mask); + if (cpumask_weight(tmpmask)) { + head = &prgrp->mon.crdtgrp_list; + list_for_each_entry(crgrp, head, mon.crdtgrp_list) { + if (crgrp == rdtgrp) + continue; + cpumask_andnot(&crgrp->cpu_mask, &crgrp->cpu_mask, + tmpmask); + } + update_closid_rmid(tmpmask, rdtgrp); + } + + /* Done pushing/pulling - update this group with new mask */ + cpumask_copy(&rdtgrp->cpu_mask, newmask); + + return 0; +} + +static void cpumask_rdtgrp_clear(struct rdtgroup *r, struct cpumask *m) +{ + struct rdtgroup *crgrp; + + cpumask_andnot(&r->cpu_mask, &r->cpu_mask, m); + /* update the child mon group masks as well*/ + list_for_each_entry(crgrp, &r->mon.crdtgrp_list, mon.crdtgrp_list) + cpumask_and(&crgrp->cpu_mask, &r->cpu_mask, &crgrp->cpu_mask); +} + +static int cpus_ctrl_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask, + cpumask_var_t tmpmask, cpumask_var_t tmpmask1) +{ + struct rdtgroup *r, *crgrp; + struct list_head *head; + + /* Check whether cpus are dropped from this group */ + cpumask_andnot(tmpmask, &rdtgrp->cpu_mask, newmask); + if (cpumask_weight(tmpmask)) { + /* Can't drop from default group */ + if (rdtgrp == &rdtgroup_default) + return -EINVAL; + + /* Give any dropped cpus to rdtgroup_default */ + cpumask_or(&rdtgroup_default.cpu_mask, + &rdtgroup_default.cpu_mask, tmpmask); + update_closid_rmid(tmpmask, &rdtgroup_default); + } + + /* + * If we added cpus, remove them from previous group and + * the prev group's child groups that owned them + * and update per-cpu closid/rmid. + */ + cpumask_andnot(tmpmask, newmask, &rdtgrp->cpu_mask); + if (cpumask_weight(tmpmask)) { + list_for_each_entry(r, &rdt_all_groups, rdtgroup_list) { + if (r == rdtgrp) + continue; + cpumask_and(tmpmask1, &r->cpu_mask, tmpmask); + if (cpumask_weight(tmpmask1)) + cpumask_rdtgrp_clear(r, tmpmask1); + } + update_closid_rmid(tmpmask, rdtgrp); + } + + /* Done pushing/pulling - update this group with new mask */ + cpumask_copy(&rdtgrp->cpu_mask, newmask); + + /* + * Clear child mon group masks since there is a new parent mask + * now and update the rmid for the cpus the child lost. + */ + head = &rdtgrp->mon.crdtgrp_list; + list_for_each_entry(crgrp, head, mon.crdtgrp_list) { + cpumask_and(tmpmask, &rdtgrp->cpu_mask, &crgrp->cpu_mask); + update_closid_rmid(tmpmask, rdtgrp); + cpumask_clear(&crgrp->cpu_mask); + } + + return 0; +} + static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { - cpumask_var_t tmpmask, newmask; - struct rdtgroup *rdtgrp, *r; + cpumask_var_t tmpmask, newmask, tmpmask1; + struct rdtgroup *rdtgrp; int ret; if (!buf) @@ -254,6 +350,11 @@ static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of, free_cpumask_var(tmpmask); return -ENOMEM; } + if (!zalloc_cpumask_var(&tmpmask1, GFP_KERNEL)) { + free_cpumask_var(tmpmask); + free_cpumask_var(newmask); + return -ENOMEM; + } rdtgrp = rdtgroup_kn_lock_live(of->kn); if (!rdtgrp) { @@ -276,41 +377,18 @@ static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of, goto unlock; } - /* Check whether cpus are dropped from this group */ - cpumask_andnot(tmpmask, &rdtgrp->cpu_mask, newmask); - if (cpumask_weight(tmpmask)) { - /* Can't drop from default group */ - if (rdtgrp == &rdtgroup_default) { - ret = -EINVAL; - goto unlock; - } - /* Give any dropped cpus to rdtgroup_default */ - cpumask_or(&rdtgroup_default.cpu_mask, - &rdtgroup_default.cpu_mask, tmpmask); - rdt_update_closid(tmpmask, &rdtgroup_default.closid); - } - - /* - * If we added cpus, remove them from previous group that owned them - * and update per-cpu closid - */ - cpumask_andnot(tmpmask, newmask, &rdtgrp->cpu_mask); - if (cpumask_weight(tmpmask)) { - list_for_each_entry(r, &rdt_all_groups, rdtgroup_list) { - if (r == rdtgrp) - continue; - cpumask_andnot(&r->cpu_mask, &r->cpu_mask, tmpmask); - } - rdt_update_closid(tmpmask, &rdtgrp->closid); - } - - /* Done pushing/pulling - update this group with new mask */ - cpumask_copy(&rdtgrp->cpu_mask, newmask); + if (rdtgrp->type == RDTCTRL_GROUP) + ret = cpus_ctrl_write(rdtgrp, newmask, tmpmask, tmpmask1); + else if (rdtgrp->type == RDTMON_GROUP) + ret = cpus_mon_write(rdtgrp, newmask, tmpmask); + else + ret = -EINVAL; unlock: rdtgroup_kn_unlock(of->kn); free_cpumask_var(tmpmask); free_cpumask_var(newmask); + free_cpumask_var(tmpmask1); return ret ?: nbytes; } @@ -336,6 +414,7 @@ static void move_myself(struct callback_head *head) if (atomic_dec_and_test(&rdtgrp->waitcount) && (rdtgrp->flags & RDT_DELETED)) { current->closid = 0; + current->rmid = 0; kfree(rdtgrp); } @@ -374,7 +453,20 @@ static int __rdtgroup_move_task(struct task_struct *tsk, atomic_dec(&rdtgrp->waitcount); kfree(callback); } else { - tsk->closid = rdtgrp->closid; + /* + * For ctrl_mon groups move both closid and rmid. + * For monitor groups, can move the tasks only from + * their parent CTRL group. + */ + if (rdtgrp->type == RDTCTRL_GROUP) { + tsk->closid = rdtgrp->closid; + tsk->rmid = rdtgrp->mon.rmid; + } else if (rdtgrp->type == RDTMON_GROUP) { + if (rdtgrp->mon.parent->closid == tsk->closid) + tsk->rmid = rdtgrp->mon.rmid; + else + ret = -EINVAL; + } } return ret; } @@ -454,7 +546,8 @@ static void show_rdt_tasks(struct rdtgroup *r, struct seq_file *s) rcu_read_lock(); for_each_process_thread(p, t) { - if (t->closid == r->closid) + if ((r->type == RDTCTRL_GROUP && t->closid == r->closid) || + (r->type == RDTMON_GROUP && t->rmid == r->mon.rmid)) seq_printf(s, "%d\n", t->pid); } rcu_read_unlock(); @@ -476,39 +569,6 @@ static int rdtgroup_tasks_show(struct kernfs_open_file *of, return ret; } -/* Files in each rdtgroup */ -static struct rftype rdtgroup_base_files[] = { - { - .name = "cpus", - .mode = 0644, - .kf_ops = &rdtgroup_kf_single_ops, - .write = rdtgroup_cpus_write, - .seq_show = rdtgroup_cpus_show, - }, - { - .name = "cpus_list", - .mode = 0644, - .kf_ops = &rdtgroup_kf_single_ops, - .write = rdtgroup_cpus_write, - .seq_show = rdtgroup_cpus_show, - .flags = RFTYPE_FLAGS_CPUS_LIST, - }, - { - .name = "tasks", - .mode = 0644, - .kf_ops = &rdtgroup_kf_single_ops, - .write = rdtgroup_tasks_write, - .seq_show = rdtgroup_tasks_show, - }, - { - .name = "schemata", - .mode = 0644, - .kf_ops = &rdtgroup_kf_single_ops, - .write = rdtgroup_schemata_write, - .seq_show = rdtgroup_schemata_show, - }, -}; - static int rdt_num_closids_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { @@ -536,6 +596,15 @@ static int rdt_min_cbm_bits_show(struct kernfs_open_file *of, return 0; } +static int rdt_shareable_bits_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct rdt_resource *r = of->kn->parent->priv; + + seq_printf(seq, "%x\n", r->cache.shareable_bits); + return 0; +} + static int rdt_min_bw_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { @@ -545,6 +614,28 @@ static int rdt_min_bw_show(struct kernfs_open_file *of, return 0; } +static int rdt_num_rmids_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct rdt_resource *r = of->kn->parent->priv; + + seq_printf(seq, "%d\n", r->num_rmid); + + return 0; +} + +static int rdt_mon_features_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct rdt_resource *r = of->kn->parent->priv; + struct mon_evt *mevt; + + list_for_each_entry(mevt, &r->evt_list, list) + seq_printf(seq, "%s\n", mevt->name); + + return 0; +} + static int rdt_bw_gran_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { @@ -563,74 +654,200 @@ static int rdt_delay_linear_show(struct kernfs_open_file *of, return 0; } +static int max_threshold_occ_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct rdt_resource *r = of->kn->parent->priv; + + seq_printf(seq, "%u\n", intel_cqm_threshold * r->mon_scale); + + return 0; +} + +static ssize_t max_threshold_occ_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct rdt_resource *r = of->kn->parent->priv; + unsigned int bytes; + int ret; + + ret = kstrtouint(buf, 0, &bytes); + if (ret) + return ret; + + if (bytes > (boot_cpu_data.x86_cache_size * 1024)) + return -EINVAL; + + intel_cqm_threshold = bytes / r->mon_scale; + + return nbytes; +} + /* rdtgroup information files for one cache resource. */ -static struct rftype res_cache_info_files[] = { +static struct rftype res_common_files[] = { { .name = "num_closids", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, .seq_show = rdt_num_closids_show, + .fflags = RF_CTRL_INFO, + }, + { + .name = "mon_features", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_mon_features_show, + .fflags = RF_MON_INFO, + }, + { + .name = "num_rmids", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_num_rmids_show, + .fflags = RF_MON_INFO, }, { .name = "cbm_mask", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, .seq_show = rdt_default_ctrl_show, + .fflags = RF_CTRL_INFO | RFTYPE_RES_CACHE, }, { .name = "min_cbm_bits", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, .seq_show = rdt_min_cbm_bits_show, + .fflags = RF_CTRL_INFO | RFTYPE_RES_CACHE, }, -}; - -/* rdtgroup information files for memory bandwidth. */ -static struct rftype res_mba_info_files[] = { { - .name = "num_closids", + .name = "shareable_bits", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, - .seq_show = rdt_num_closids_show, + .seq_show = rdt_shareable_bits_show, + .fflags = RF_CTRL_INFO | RFTYPE_RES_CACHE, }, { .name = "min_bandwidth", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, .seq_show = rdt_min_bw_show, + .fflags = RF_CTRL_INFO | RFTYPE_RES_MB, }, { .name = "bandwidth_gran", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, .seq_show = rdt_bw_gran_show, + .fflags = RF_CTRL_INFO | RFTYPE_RES_MB, }, { .name = "delay_linear", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, .seq_show = rdt_delay_linear_show, + .fflags = RF_CTRL_INFO | RFTYPE_RES_MB, + }, + { + .name = "max_threshold_occupancy", + .mode = 0644, + .kf_ops = &rdtgroup_kf_single_ops, + .write = max_threshold_occ_write, + .seq_show = max_threshold_occ_show, + .fflags = RF_MON_INFO | RFTYPE_RES_CACHE, + }, + { + .name = "cpus", + .mode = 0644, + .kf_ops = &rdtgroup_kf_single_ops, + .write = rdtgroup_cpus_write, + .seq_show = rdtgroup_cpus_show, + .fflags = RFTYPE_BASE, + }, + { + .name = "cpus_list", + .mode = 0644, + .kf_ops = &rdtgroup_kf_single_ops, + .write = rdtgroup_cpus_write, + .seq_show = rdtgroup_cpus_show, + .flags = RFTYPE_FLAGS_CPUS_LIST, + .fflags = RFTYPE_BASE, + }, + { + .name = "tasks", + .mode = 0644, + .kf_ops = &rdtgroup_kf_single_ops, + .write = rdtgroup_tasks_write, + .seq_show = rdtgroup_tasks_show, + .fflags = RFTYPE_BASE, + }, + { + .name = "schemata", + .mode = 0644, + .kf_ops = &rdtgroup_kf_single_ops, + .write = rdtgroup_schemata_write, + .seq_show = rdtgroup_schemata_show, + .fflags = RF_CTRL_BASE, }, }; -void rdt_get_mba_infofile(struct rdt_resource *r) +static int rdtgroup_add_files(struct kernfs_node *kn, unsigned long fflags) { - r->info_files = res_mba_info_files; - r->nr_info_files = ARRAY_SIZE(res_mba_info_files); + struct rftype *rfts, *rft; + int ret, len; + + rfts = res_common_files; + len = ARRAY_SIZE(res_common_files); + + lockdep_assert_held(&rdtgroup_mutex); + + for (rft = rfts; rft < rfts + len; rft++) { + if ((fflags & rft->fflags) == rft->fflags) { + ret = rdtgroup_add_file(kn, rft); + if (ret) + goto error; + } + } + + return 0; +error: + pr_warn("Failed to add %s, err=%d\n", rft->name, ret); + while (--rft >= rfts) { + if ((fflags & rft->fflags) == rft->fflags) + kernfs_remove_by_name(kn, rft->name); + } + return ret; } -void rdt_get_cache_infofile(struct rdt_resource *r) +static int rdtgroup_mkdir_info_resdir(struct rdt_resource *r, char *name, + unsigned long fflags) { - r->info_files = res_cache_info_files; - r->nr_info_files = ARRAY_SIZE(res_cache_info_files); + struct kernfs_node *kn_subdir; + int ret; + + kn_subdir = kernfs_create_dir(kn_info, name, + kn_info->mode, r); + if (IS_ERR(kn_subdir)) + return PTR_ERR(kn_subdir); + + kernfs_get(kn_subdir); + ret = rdtgroup_kn_set_ugid(kn_subdir); + if (ret) + return ret; + + ret = rdtgroup_add_files(kn_subdir, fflags); + if (!ret) + kernfs_activate(kn_subdir); + + return ret; } static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn) { - struct kernfs_node *kn_subdir; - struct rftype *res_info_files; struct rdt_resource *r; - int ret, len; + unsigned long fflags; + char name[32]; + int ret; /* create the directory */ kn_info = kernfs_create_dir(parent_kn, "info", parent_kn->mode, NULL); @@ -638,25 +855,19 @@ static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn) return PTR_ERR(kn_info); kernfs_get(kn_info); - for_each_enabled_rdt_resource(r) { - kn_subdir = kernfs_create_dir(kn_info, r->name, - kn_info->mode, r); - if (IS_ERR(kn_subdir)) { - ret = PTR_ERR(kn_subdir); - goto out_destroy; - } - kernfs_get(kn_subdir); - ret = rdtgroup_kn_set_ugid(kn_subdir); + for_each_alloc_enabled_rdt_resource(r) { + fflags = r->fflags | RF_CTRL_INFO; + ret = rdtgroup_mkdir_info_resdir(r, r->name, fflags); if (ret) goto out_destroy; + } - res_info_files = r->info_files; - len = r->nr_info_files; - - ret = rdtgroup_add_files(kn_subdir, res_info_files, len); + for_each_mon_enabled_rdt_resource(r) { + fflags = r->fflags | RF_MON_INFO; + sprintf(name, "%s_MON", r->name); + ret = rdtgroup_mkdir_info_resdir(r, name, fflags); if (ret) goto out_destroy; - kernfs_activate(kn_subdir); } /* @@ -678,6 +889,39 @@ out_destroy: return ret; } +static int +mongroup_create_dir(struct kernfs_node *parent_kn, struct rdtgroup *prgrp, + char *name, struct kernfs_node **dest_kn) +{ + struct kernfs_node *kn; + int ret; + + /* create the directory */ + kn = kernfs_create_dir(parent_kn, name, parent_kn->mode, prgrp); + if (IS_ERR(kn)) + return PTR_ERR(kn); + + if (dest_kn) + *dest_kn = kn; + + /* + * This extra ref will be put in kernfs_remove() and guarantees + * that @rdtgrp->kn is always accessible. + */ + kernfs_get(kn); + + ret = rdtgroup_kn_set_ugid(kn); + if (ret) + goto out_destroy; + + kernfs_activate(kn); + + return 0; + +out_destroy: + kernfs_remove(kn); + return ret; +} static void l3_qos_cfg_update(void *arg) { bool *enable = arg; @@ -718,14 +962,15 @@ static int cdp_enable(void) struct rdt_resource *r_l3 = &rdt_resources_all[RDT_RESOURCE_L3]; int ret; - if (!r_l3->capable || !r_l3data->capable || !r_l3code->capable) + if (!r_l3->alloc_capable || !r_l3data->alloc_capable || + !r_l3code->alloc_capable) return -EINVAL; ret = set_l3_qos_cfg(r_l3, true); if (!ret) { - r_l3->enabled = false; - r_l3data->enabled = true; - r_l3code->enabled = true; + r_l3->alloc_enabled = false; + r_l3data->alloc_enabled = true; + r_l3code->alloc_enabled = true; } return ret; } @@ -734,11 +979,11 @@ static void cdp_disable(void) { struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3]; - r->enabled = r->capable; + r->alloc_enabled = r->alloc_capable; - if (rdt_resources_all[RDT_RESOURCE_L3DATA].enabled) { - rdt_resources_all[RDT_RESOURCE_L3DATA].enabled = false; - rdt_resources_all[RDT_RESOURCE_L3CODE].enabled = false; + if (rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled) { + rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled = false; + rdt_resources_all[RDT_RESOURCE_L3CODE].alloc_enabled = false; set_l3_qos_cfg(r, false); } } @@ -823,10 +1068,16 @@ void rdtgroup_kn_unlock(struct kernfs_node *kn) } } +static int mkdir_mondata_all(struct kernfs_node *parent_kn, + struct rdtgroup *prgrp, + struct kernfs_node **mon_data_kn); + static struct dentry *rdt_mount(struct file_system_type *fs_type, int flags, const char *unused_dev_name, void *data) { + struct rdt_domain *dom; + struct rdt_resource *r; struct dentry *dentry; int ret; @@ -853,15 +1104,54 @@ static struct dentry *rdt_mount(struct file_system_type *fs_type, goto out_cdp; } + if (rdt_mon_capable) { + ret = mongroup_create_dir(rdtgroup_default.kn, + NULL, "mon_groups", + &kn_mongrp); + if (ret) { + dentry = ERR_PTR(ret); + goto out_info; + } + kernfs_get(kn_mongrp); + + ret = mkdir_mondata_all(rdtgroup_default.kn, + &rdtgroup_default, &kn_mondata); + if (ret) { + dentry = ERR_PTR(ret); + goto out_mongrp; + } + kernfs_get(kn_mondata); + rdtgroup_default.mon.mon_data_kn = kn_mondata; + } + dentry = kernfs_mount(fs_type, flags, rdt_root, RDTGROUP_SUPER_MAGIC, NULL); if (IS_ERR(dentry)) - goto out_destroy; + goto out_mondata; + + if (rdt_alloc_capable) + static_branch_enable(&rdt_alloc_enable_key); + if (rdt_mon_capable) + static_branch_enable(&rdt_mon_enable_key); + + if (rdt_alloc_capable || rdt_mon_capable) + static_branch_enable(&rdt_enable_key); + + if (is_mbm_enabled()) { + r = &rdt_resources_all[RDT_RESOURCE_L3]; + list_for_each_entry(dom, &r->domains, list) + mbm_setup_overflow_handler(dom, MBM_OVERFLOW_INTERVAL); + } - static_branch_enable(&rdt_enable_key); goto out; -out_destroy: +out_mondata: + if (rdt_mon_capable) + kernfs_remove(kn_mondata); +out_mongrp: + if (rdt_mon_capable) + kernfs_remove(kn_mongrp); +out_info: kernfs_remove(kn_info); out_cdp: cdp_disable(); @@ -909,6 +1199,18 @@ 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). @@ -924,8 +1226,11 @@ static void rdt_move_group_tasks(struct rdtgroup *from, struct rdtgroup *to, read_lock(&tasklist_lock); for_each_process_thread(p, t) { - if (!from || t->closid == from->closid) { + if (!from || is_closid_match(t, from) || + is_rmid_match(t, from)) { t->closid = to->closid; + t->rmid = to->mon.rmid; + #ifdef CONFIG_SMP /* * This is safe on x86 w/o barriers as the ordering @@ -944,6 +1249,19 @@ static void rdt_move_group_tasks(struct rdtgroup *from, struct rdtgroup *to, read_unlock(&tasklist_lock); } +static void free_all_child_rdtgrp(struct rdtgroup *rdtgrp) +{ + struct rdtgroup *sentry, *stmp; + struct list_head *head; + + head = &rdtgrp->mon.crdtgrp_list; + list_for_each_entry_safe(sentry, stmp, head, mon.crdtgrp_list) { + free_rmid(sentry->mon.rmid); + list_del(&sentry->mon.crdtgrp_list); + kfree(sentry); + } +} + /* * Forcibly remove all of subdirectories under root. */ @@ -955,6 +1273,9 @@ static void rmdir_all_sub(void) rdt_move_group_tasks(NULL, &rdtgroup_default, NULL); list_for_each_entry_safe(rdtgrp, tmp, &rdt_all_groups, rdtgroup_list) { + /* Free any child rmids */ + free_all_child_rdtgrp(rdtgrp); + /* Remove each rdtgroup other than root */ if (rdtgrp == &rdtgroup_default) continue; @@ -967,16 +1288,20 @@ static void rmdir_all_sub(void) cpumask_or(&rdtgroup_default.cpu_mask, &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask); + free_rmid(rdtgrp->mon.rmid); + kernfs_remove(rdtgrp->kn); list_del(&rdtgrp->rdtgroup_list); kfree(rdtgrp); } /* Notify online CPUs to update per cpu storage and PQR_ASSOC MSR */ get_online_cpus(); - rdt_update_closid(cpu_online_mask, &rdtgroup_default.closid); + update_closid_rmid(cpu_online_mask, &rdtgroup_default); put_online_cpus(); kernfs_remove(kn_info); + kernfs_remove(kn_mongrp); + kernfs_remove(kn_mondata); } static void rdt_kill_sb(struct super_block *sb) @@ -986,10 +1311,12 @@ static void rdt_kill_sb(struct super_block *sb) mutex_lock(&rdtgroup_mutex); /*Put everything back to default values. */ - for_each_enabled_rdt_resource(r) + for_each_alloc_enabled_rdt_resource(r) reset_all_ctrls(r); cdp_disable(); rmdir_all_sub(); + static_branch_disable(&rdt_alloc_enable_key); + static_branch_disable(&rdt_mon_enable_key); static_branch_disable(&rdt_enable_key); kernfs_kill_sb(sb); mutex_unlock(&rdtgroup_mutex); @@ -1001,46 +1328,223 @@ static struct file_system_type rdt_fs_type = { .kill_sb = rdt_kill_sb, }; -static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name, - umode_t mode) +static int mon_addfile(struct kernfs_node *parent_kn, const char *name, + void *priv) { - struct rdtgroup *parent, *rdtgrp; struct kernfs_node *kn; - int ret, closid; + int ret = 0; - /* Only allow mkdir in the root directory */ - if (parent_kn != rdtgroup_default.kn) - return -EPERM; + kn = __kernfs_create_file(parent_kn, name, 0444, 0, + &kf_mondata_ops, priv, NULL, NULL); + if (IS_ERR(kn)) + return PTR_ERR(kn); - /* Do not accept '\n' to avoid unparsable situation. */ - if (strchr(name, '\n')) - return -EINVAL; + ret = rdtgroup_kn_set_ugid(kn); + if (ret) { + kernfs_remove(kn); + return ret; + } - parent = rdtgroup_kn_lock_live(parent_kn); - if (!parent) { - ret = -ENODEV; - goto out_unlock; + return ret; +} + +/* + * Remove all subdirectories of mon_data of ctrl_mon groups + * and monitor groups with given domain id. + */ +void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r, unsigned int dom_id) +{ + struct rdtgroup *prgrp, *crgrp; + char name[32]; + + if (!r->mon_enabled) + return; + + list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) { + sprintf(name, "mon_%s_%02d", r->name, dom_id); + kernfs_remove_by_name(prgrp->mon.mon_data_kn, name); + + list_for_each_entry(crgrp, &prgrp->mon.crdtgrp_list, mon.crdtgrp_list) + kernfs_remove_by_name(crgrp->mon.mon_data_kn, name); } +} - ret = closid_alloc(); - if (ret < 0) +static int mkdir_mondata_subdir(struct kernfs_node *parent_kn, + struct rdt_domain *d, + struct rdt_resource *r, struct rdtgroup *prgrp) +{ + union mon_data_bits priv; + struct kernfs_node *kn; + struct mon_evt *mevt; + struct rmid_read rr; + char name[32]; + int ret; + + sprintf(name, "mon_%s_%02d", r->name, d->id); + /* create the directory */ + kn = kernfs_create_dir(parent_kn, name, parent_kn->mode, prgrp); + if (IS_ERR(kn)) + return PTR_ERR(kn); + + /* + * This extra ref will be put in kernfs_remove() and guarantees + * that kn is always accessible. + */ + kernfs_get(kn); + ret = rdtgroup_kn_set_ugid(kn); + if (ret) + goto out_destroy; + + if (WARN_ON(list_empty(&r->evt_list))) { + ret = -EPERM; + goto out_destroy; + } + + priv.u.rid = r->rid; + priv.u.domid = d->id; + list_for_each_entry(mevt, &r->evt_list, list) { + priv.u.evtid = mevt->evtid; + ret = mon_addfile(kn, mevt->name, priv.priv); + if (ret) + goto out_destroy; + + if (is_mbm_event(mevt->evtid)) + mon_event_read(&rr, d, prgrp, mevt->evtid, true); + } + kernfs_activate(kn); + return 0; + +out_destroy: + kernfs_remove(kn); + return ret; +} + +/* + * Add all subdirectories of mon_data for "ctrl_mon" groups + * and "monitor" groups with given domain id. + */ +void mkdir_mondata_subdir_allrdtgrp(struct rdt_resource *r, + struct rdt_domain *d) +{ + struct kernfs_node *parent_kn; + struct rdtgroup *prgrp, *crgrp; + struct list_head *head; + + if (!r->mon_enabled) + return; + + list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) { + parent_kn = prgrp->mon.mon_data_kn; + mkdir_mondata_subdir(parent_kn, d, r, prgrp); + + head = &prgrp->mon.crdtgrp_list; + list_for_each_entry(crgrp, head, mon.crdtgrp_list) { + parent_kn = crgrp->mon.mon_data_kn; + mkdir_mondata_subdir(parent_kn, d, r, crgrp); + } + } +} + +static int mkdir_mondata_subdir_alldom(struct kernfs_node *parent_kn, + struct rdt_resource *r, + struct rdtgroup *prgrp) +{ + struct rdt_domain *dom; + int ret; + + list_for_each_entry(dom, &r->domains, list) { + ret = mkdir_mondata_subdir(parent_kn, dom, r, prgrp); + if (ret) + return ret; + } + + return 0; +} + +/* + * This creates a directory mon_data which contains the monitored data. + * + * mon_data has one directory for each domain whic are named + * in the format mon_<domain_name>_<domain_id>. For ex: A mon_data + * with L3 domain looks as below: + * ./mon_data: + * mon_L3_00 + * mon_L3_01 + * mon_L3_02 + * ... + * + * Each domain directory has one file per event: + * ./mon_L3_00/: + * llc_occupancy + * + */ +static int mkdir_mondata_all(struct kernfs_node *parent_kn, + struct rdtgroup *prgrp, + struct kernfs_node **dest_kn) +{ + struct rdt_resource *r; + struct kernfs_node *kn; + int ret; + + /* + * Create the mon_data directory first. + */ + ret = mongroup_create_dir(parent_kn, NULL, "mon_data", &kn); + if (ret) + return ret; + + if (dest_kn) + *dest_kn = kn; + + /* + * Create the subdirectories for each domain. Note that all events + * in a domain like L3 are grouped into a resource whose domain is L3 + */ + for_each_mon_enabled_rdt_resource(r) { + ret = mkdir_mondata_subdir_alldom(kn, r, prgrp); + if (ret) + goto out_destroy; + } + + return 0; + +out_destroy: + kernfs_remove(kn); + return ret; +} + +static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, + struct kernfs_node *prgrp_kn, + const char *name, umode_t mode, + enum rdt_group_type rtype, struct rdtgroup **r) +{ + struct rdtgroup *prdtgrp, *rdtgrp; + struct kernfs_node *kn; + uint files = 0; + int ret; + + prdtgrp = rdtgroup_kn_lock_live(prgrp_kn); + if (!prdtgrp) { + ret = -ENODEV; goto out_unlock; - closid = ret; + } /* allocate the rdtgroup. */ rdtgrp = kzalloc(sizeof(*rdtgrp), GFP_KERNEL); if (!rdtgrp) { ret = -ENOSPC; - goto out_closid_free; + goto out_unlock; } - rdtgrp->closid = closid; - list_add(&rdtgrp->rdtgroup_list, &rdt_all_groups); + *r = rdtgrp; + rdtgrp->mon.parent = prdtgrp; + rdtgrp->type = rtype; + INIT_LIST_HEAD(&rdtgrp->mon.crdtgrp_list); /* kernfs creates the directory for rdtgrp */ - kn = kernfs_create_dir(parent->kn, name, mode, rdtgrp); + kn = kernfs_create_dir(parent_kn, name, mode, rdtgrp); if (IS_ERR(kn)) { ret = PTR_ERR(kn); - goto out_cancel_ref; + goto out_free_rgrp; } rdtgrp->kn = kn; @@ -1056,43 +1560,211 @@ static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name, if (ret) goto out_destroy; - ret = rdtgroup_add_files(kn, rdtgroup_base_files, - ARRAY_SIZE(rdtgroup_base_files)); + files = RFTYPE_BASE | RFTYPE_CTRL; + files = RFTYPE_BASE | BIT(RF_CTRLSHIFT + rtype); + ret = rdtgroup_add_files(kn, files); if (ret) goto out_destroy; + if (rdt_mon_capable) { + ret = alloc_rmid(); + if (ret < 0) + goto out_destroy; + rdtgrp->mon.rmid = ret; + + ret = mkdir_mondata_all(kn, rdtgrp, &rdtgrp->mon.mon_data_kn); + if (ret) + goto out_idfree; + } kernfs_activate(kn); - ret = 0; - goto out_unlock; + /* + * The caller unlocks the prgrp_kn upon success. + */ + return 0; +out_idfree: + free_rmid(rdtgrp->mon.rmid); out_destroy: kernfs_remove(rdtgrp->kn); -out_cancel_ref: - list_del(&rdtgrp->rdtgroup_list); +out_free_rgrp: kfree(rdtgrp); -out_closid_free: - closid_free(closid); out_unlock: - rdtgroup_kn_unlock(parent_kn); + rdtgroup_kn_unlock(prgrp_kn); return ret; } -static int rdtgroup_rmdir(struct kernfs_node *kn) +static void mkdir_rdt_prepare_clean(struct rdtgroup *rgrp) +{ + kernfs_remove(rgrp->kn); + free_rmid(rgrp->mon.rmid); + kfree(rgrp); +} + +/* + * Create a monitor group under "mon_groups" directory of a control + * and monitor group(ctrl_mon). This is a resource group + * to monitor a subset of tasks and cpus in its parent ctrl_mon group. + */ +static int rdtgroup_mkdir_mon(struct kernfs_node *parent_kn, + struct kernfs_node *prgrp_kn, + const char *name, + umode_t mode) +{ + struct rdtgroup *rdtgrp, *prgrp; + int ret; + + ret = mkdir_rdt_prepare(parent_kn, prgrp_kn, name, mode, RDTMON_GROUP, + &rdtgrp); + if (ret) + return ret; + + prgrp = rdtgrp->mon.parent; + rdtgrp->closid = prgrp->closid; + + /* + * Add the rdtgrp to the list of rdtgrps the parent + * ctrl_mon group has to track. + */ + list_add_tail(&rdtgrp->mon.crdtgrp_list, &prgrp->mon.crdtgrp_list); + + rdtgroup_kn_unlock(prgrp_kn); + return ret; +} + +/* + * These are rdtgroups created under the root directory. Can be used + * to allocate and monitor resources. + */ +static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn, + struct kernfs_node *prgrp_kn, + const char *name, umode_t mode) { - int ret, cpu, closid = rdtgroup_default.closid; struct rdtgroup *rdtgrp; - cpumask_var_t tmpmask; + struct kernfs_node *kn; + u32 closid; + int ret; - if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL)) - return -ENOMEM; + ret = mkdir_rdt_prepare(parent_kn, prgrp_kn, name, mode, RDTCTRL_GROUP, + &rdtgrp); + if (ret) + return ret; - rdtgrp = rdtgroup_kn_lock_live(kn); - if (!rdtgrp) { - ret = -EPERM; - goto out; + kn = rdtgrp->kn; + ret = closid_alloc(); + if (ret < 0) + goto out_common_fail; + closid = ret; + + rdtgrp->closid = closid; + list_add(&rdtgrp->rdtgroup_list, &rdt_all_groups); + + if (rdt_mon_capable) { + /* + * Create an empty mon_groups directory to hold the subset + * of tasks and cpus to monitor. + */ + ret = mongroup_create_dir(kn, NULL, "mon_groups", NULL); + if (ret) + goto out_id_free; } + goto out_unlock; + +out_id_free: + closid_free(closid); + list_del(&rdtgrp->rdtgroup_list); +out_common_fail: + mkdir_rdt_prepare_clean(rdtgrp); +out_unlock: + rdtgroup_kn_unlock(prgrp_kn); + return ret; +} + +/* + * We allow creating mon groups only with in a directory called "mon_groups" + * which is present in every ctrl_mon group. Check if this is a valid + * "mon_groups" directory. + * + * 1. The directory should be named "mon_groups". + * 2. The mon group itself should "not" be named "mon_groups". + * This makes sure "mon_groups" directory always has a ctrl_mon group + * as parent. + */ +static bool is_mon_groups(struct kernfs_node *kn, const char *name) +{ + return (!strcmp(kn->name, "mon_groups") && + strcmp(name, "mon_groups")); +} + +static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name, + umode_t mode) +{ + /* Do not accept '\n' to avoid unparsable situation. */ + if (strchr(name, '\n')) + return -EINVAL; + + /* + * If the parent directory is the root directory and RDT + * allocation is supported, add a control and monitoring + * subdirectory + */ + if (rdt_alloc_capable && parent_kn == rdtgroup_default.kn) + return rdtgroup_mkdir_ctrl_mon(parent_kn, parent_kn, name, mode); + + /* + * If RDT monitoring is supported and the parent directory is a valid + * "mon_groups" directory, add a monitoring subdirectory. + */ + if (rdt_mon_capable && is_mon_groups(parent_kn, name)) + return rdtgroup_mkdir_mon(parent_kn, parent_kn->parent, name, mode); + + return -EPERM; +} + +static int rdtgroup_rmdir_mon(struct kernfs_node *kn, struct rdtgroup *rdtgrp, + cpumask_var_t tmpmask) +{ + struct rdtgroup *prdtgrp = rdtgrp->mon.parent; + int cpu; + + /* Give any tasks back to the parent group */ + rdt_move_group_tasks(rdtgrp, prdtgrp, tmpmask); + + /* Update per cpu rmid of the moved CPUs first */ + for_each_cpu(cpu, &rdtgrp->cpu_mask) + per_cpu(pqr_state.default_rmid, cpu) = prdtgrp->mon.rmid; + /* + * Update the MSR on moved CPUs and CPUs which have moved + * task running on them. + */ + cpumask_or(tmpmask, tmpmask, &rdtgrp->cpu_mask); + update_closid_rmid(tmpmask, NULL); + + rdtgrp->flags = RDT_DELETED; + free_rmid(rdtgrp->mon.rmid); + + /* + * Remove the rdtgrp from the parent ctrl_mon group's list + */ + WARN_ON(list_empty(&prdtgrp->mon.crdtgrp_list)); + list_del(&rdtgrp->mon.crdtgrp_list); + + /* + * one extra hold on this, will drop when we kfree(rdtgrp) + * in rdtgroup_kn_unlock() + */ + kernfs_get(kn); + kernfs_remove(rdtgrp->kn); + + return 0; +} + +static int rdtgroup_rmdir_ctrl(struct kernfs_node *kn, struct rdtgroup *rdtgrp, + cpumask_var_t tmpmask) +{ + int cpu; + /* Give any tasks back to the default group */ rdt_move_group_tasks(rdtgrp, &rdtgroup_default, tmpmask); @@ -1100,18 +1772,28 @@ static int rdtgroup_rmdir(struct kernfs_node *kn) cpumask_or(&rdtgroup_default.cpu_mask, &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask); - /* Update per cpu closid of the moved CPUs first */ - for_each_cpu(cpu, &rdtgrp->cpu_mask) - per_cpu(cpu_closid, cpu) = closid; + /* Update per cpu closid and rmid of the moved CPUs first */ + for_each_cpu(cpu, &rdtgrp->cpu_mask) { + per_cpu(pqr_state.default_closid, cpu) = rdtgroup_default.closid; + per_cpu(pqr_state.default_rmid, cpu) = rdtgroup_default.mon.rmid; + } + /* * Update the MSR on moved CPUs and CPUs which have moved * task running on them. */ cpumask_or(tmpmask, tmpmask, &rdtgrp->cpu_mask); - rdt_update_closid(tmpmask, NULL); + update_closid_rmid(tmpmask, NULL); rdtgrp->flags = RDT_DELETED; closid_free(rdtgrp->closid); + free_rmid(rdtgrp->mon.rmid); + + /* + * Free all the child monitor group rmids. + */ + free_all_child_rdtgrp(rdtgrp); + list_del(&rdtgrp->rdtgroup_list); /* @@ -1120,7 +1802,41 @@ static int rdtgroup_rmdir(struct kernfs_node *kn) */ kernfs_get(kn); kernfs_remove(rdtgrp->kn); - ret = 0; + + return 0; +} + +static int rdtgroup_rmdir(struct kernfs_node *kn) +{ + struct kernfs_node *parent_kn = kn->parent; + struct rdtgroup *rdtgrp; + cpumask_var_t tmpmask; + int ret = 0; + + if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL)) + return -ENOMEM; + + rdtgrp = rdtgroup_kn_lock_live(kn); + if (!rdtgrp) { + ret = -EPERM; + goto out; + } + + /* + * If the rdtgroup is a ctrl_mon group and parent directory + * is the root directory, remove the ctrl_mon group. + * + * If the rdtgroup is a mon group and parent directory + * is a valid "mon_groups" directory, remove the mon group. + */ + if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn) + ret = rdtgroup_rmdir_ctrl(kn, rdtgrp, tmpmask); + else if (rdtgrp->type == RDTMON_GROUP && + is_mon_groups(parent_kn, kn->name)) + ret = rdtgroup_rmdir_mon(kn, rdtgrp, tmpmask); + else + ret = -EPERM; + out: rdtgroup_kn_unlock(kn); free_cpumask_var(tmpmask); @@ -1129,7 +1845,7 @@ out: static int rdtgroup_show_options(struct seq_file *seq, struct kernfs_root *kf) { - if (rdt_resources_all[RDT_RESOURCE_L3DATA].enabled) + if (rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled) seq_puts(seq, ",cdp"); return 0; } @@ -1153,10 +1869,13 @@ static int __init rdtgroup_setup_root(void) mutex_lock(&rdtgroup_mutex); rdtgroup_default.closid = 0; + rdtgroup_default.mon.rmid = 0; + rdtgroup_default.type = RDTCTRL_GROUP; + INIT_LIST_HEAD(&rdtgroup_default.mon.crdtgrp_list); + list_add(&rdtgroup_default.rdtgroup_list, &rdt_all_groups); - ret = rdtgroup_add_files(rdt_root->kn, rdtgroup_base_files, - ARRAY_SIZE(rdtgroup_base_files)); + ret = rdtgroup_add_files(rdt_root->kn, RF_CTRL_BASE); if (ret) { kernfs_destroy_root(rdt_root); goto out; diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 6dde0497efc7..3b413065c613 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -51,6 +51,7 @@ #include <asm/mce.h> #include <asm/msr.h> #include <asm/reboot.h> +#include <asm/set_memory.h> #include "mce-internal.h" @@ -1051,6 +1052,48 @@ static int do_memory_failure(struct mce *m) return ret; } +#if defined(arch_unmap_kpfn) && defined(CONFIG_MEMORY_FAILURE) + +void arch_unmap_kpfn(unsigned long pfn) +{ + unsigned long decoy_addr; + + /* + * Unmap this page from the kernel 1:1 mappings to make sure + * we don't log more errors because of speculative access to + * the page. + * We would like to just call: + * set_memory_np((unsigned long)pfn_to_kaddr(pfn), 1); + * but doing that would radically increase the odds of a + * speculative access to the posion page because we'd have + * the virtual address of the kernel 1:1 mapping sitting + * around in registers. + * Instead we get tricky. We create a non-canonical address + * that looks just like the one we want, but has bit 63 flipped. + * This relies on set_memory_np() not checking whether we passed + * a legal address. + */ + +/* + * Build time check to see if we have a spare virtual bit. Don't want + * to leave this until run time because most developers don't have a + * system that can exercise this code path. This will only become a + * problem if/when we move beyond 5-level page tables. + * + * Hard code "9" here because cpp doesn't grok ilog2(PTRS_PER_PGD) + */ +#if PGDIR_SHIFT + 9 < 63 + decoy_addr = (pfn << PAGE_SHIFT) + (PAGE_OFFSET ^ BIT(63)); +#else +#error "no unused virtual bit available" +#endif + + if (set_memory_np(decoy_addr, 1)) + pr_warn("Could not invalidate pfn=0x%lx from 1:1 map\n", pfn); + +} +#endif + /* * The actual machine check handler. This only handles real * exceptions when something got corrupted coming in through int 18. diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 9e314bcf67cc..40e28ed77fbf 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -201,8 +201,8 @@ static void smca_configure(unsigned int bank, unsigned int cpu) wrmsr(smca_config, low, high); } - /* Collect bank_info using CPU 0 for now. */ - if (cpu) + /* Return early if this bank was already initialized. */ + if (smca_banks[bank].hwid) return; if (rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_IPID(bank), &low, &high)) { @@ -216,11 +216,6 @@ static void smca_configure(unsigned int bank, unsigned int cpu) for (i = 0; i < ARRAY_SIZE(smca_hwid_mcatypes); i++) { s_hwid = &smca_hwid_mcatypes[i]; if (hwid_mcatype == s_hwid->hwid_mcatype) { - - WARN(smca_banks[bank].hwid, - "Bank %s already initialized!\n", - smca_get_name(s_hwid->bank_type)); - smca_banks[bank].hwid = s_hwid; smca_banks[bank].id = low; smca_banks[bank].sysfs_id = s_hwid->count++; @@ -776,24 +771,12 @@ static void __log_error(unsigned int bank, u64 status, u64 addr, u64 misc) mce_log(&m); } -static inline void __smp_deferred_error_interrupt(void) -{ - inc_irq_stat(irq_deferred_error_count); - deferred_error_int_vector(); -} - asmlinkage __visible void __irq_entry smp_deferred_error_interrupt(void) { entering_irq(); - __smp_deferred_error_interrupt(); - exiting_ack_irq(); -} - -asmlinkage __visible void __irq_entry smp_trace_deferred_error_interrupt(void) -{ - entering_irq(); trace_deferred_error_apic_entry(DEFERRED_ERROR_VECTOR); - __smp_deferred_error_interrupt(); + inc_irq_stat(irq_deferred_error_count); + deferred_error_int_vector(); trace_deferred_error_apic_exit(DEFERRED_ERROR_VECTOR); exiting_ack_irq(); } diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index d7cc190ae457..2da67b70ba98 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -122,7 +122,7 @@ static struct attribute *thermal_throttle_attrs[] = { NULL }; -static struct attribute_group thermal_attr_group = { +static const struct attribute_group thermal_attr_group = { .attrs = thermal_throttle_attrs, .name = "thermal_throttle" }; @@ -390,26 +390,12 @@ static void unexpected_thermal_interrupt(void) static void (*smp_thermal_vector)(void) = unexpected_thermal_interrupt; -static inline void __smp_thermal_interrupt(void) -{ - inc_irq_stat(irq_thermal_count); - smp_thermal_vector(); -} - -asmlinkage __visible void __irq_entry -smp_thermal_interrupt(struct pt_regs *regs) -{ - entering_irq(); - __smp_thermal_interrupt(); - exiting_ack_irq(); -} - -asmlinkage __visible void __irq_entry -smp_trace_thermal_interrupt(struct pt_regs *regs) +asmlinkage __visible void __irq_entry smp_thermal_interrupt(struct pt_regs *r) { entering_irq(); trace_thermal_apic_entry(THERMAL_APIC_VECTOR); - __smp_thermal_interrupt(); + inc_irq_stat(irq_thermal_count); + smp_thermal_vector(); trace_thermal_apic_exit(THERMAL_APIC_VECTOR); exiting_ack_irq(); } diff --git a/arch/x86/kernel/cpu/mcheck/threshold.c b/arch/x86/kernel/cpu/mcheck/threshold.c index bb0e75eed10a..5e7249e42f8f 100644 --- a/arch/x86/kernel/cpu/mcheck/threshold.c +++ b/arch/x86/kernel/cpu/mcheck/threshold.c @@ -17,24 +17,12 @@ static void default_threshold_interrupt(void) void (*mce_threshold_vector)(void) = default_threshold_interrupt; -static inline void __smp_threshold_interrupt(void) -{ - inc_irq_stat(irq_threshold_count); - mce_threshold_vector(); -} - asmlinkage __visible void __irq_entry smp_threshold_interrupt(void) { entering_irq(); - __smp_threshold_interrupt(); - exiting_ack_irq(); -} - -asmlinkage __visible void __irq_entry smp_trace_threshold_interrupt(void) -{ - entering_irq(); trace_threshold_apic_entry(THRESHOLD_APIC_VECTOR); - __smp_threshold_interrupt(); + inc_irq_stat(irq_threshold_count); + mce_threshold_vector(); trace_threshold_apic_exit(THRESHOLD_APIC_VECTOR); exiting_ack_irq(); } diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 21b185793c80..c6daec4bdba5 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -400,9 +400,12 @@ static void update_cache(struct ucode_patch *new_patch) list_for_each_entry(p, µcode_cache, plist) { if (p->equiv_cpu == new_patch->equiv_cpu) { - if (p->patch_id >= new_patch->patch_id) + if (p->patch_id >= new_patch->patch_id) { /* we already have the latest patch */ + kfree(new_patch->data); + kfree(new_patch); return; + } list_replace(&p->plist, &new_patch->plist); kfree(p->data); diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 9cb98ee103db..86e8f0b2537b 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -561,7 +561,7 @@ static struct attribute *mc_default_attrs[] = { NULL }; -static struct attribute_group mc_attr_group = { +static const struct attribute_group mc_attr_group = { .attrs = mc_default_attrs, .name = "microcode", }; @@ -707,7 +707,7 @@ static struct attribute *cpu_root_microcode_attrs[] = { NULL }; -static struct attribute_group cpu_root_microcode_group = { +static const struct attribute_group cpu_root_microcode_group = { .name = "microcode", .attrs = cpu_root_microcode_attrs, }; diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 59edbe9d4ccb..8f7a9bbad514 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -146,18 +146,18 @@ static bool microcode_matches(struct microcode_header_intel *mc_header, return false; } -static struct ucode_patch *__alloc_microcode_buf(void *data, unsigned int size) +static struct ucode_patch *memdup_patch(void *data, unsigned int size) { struct ucode_patch *p; p = kzalloc(sizeof(struct ucode_patch), GFP_KERNEL); if (!p) - return ERR_PTR(-ENOMEM); + return NULL; p->data = kmemdup(data, size, GFP_KERNEL); if (!p->data) { kfree(p); - return ERR_PTR(-ENOMEM); + return NULL; } return p; @@ -183,8 +183,8 @@ static void save_microcode_patch(void *data, unsigned int size) if (mc_hdr->rev <= mc_saved_hdr->rev) continue; - p = __alloc_microcode_buf(data, size); - if (IS_ERR(p)) + p = memdup_patch(data, size); + if (!p) pr_err("Error allocating buffer %p\n", data); else list_replace(&iter->plist, &p->plist); @@ -196,24 +196,25 @@ static void save_microcode_patch(void *data, unsigned int size) * newly found. */ if (!prev_found) { - p = __alloc_microcode_buf(data, size); - if (IS_ERR(p)) + p = memdup_patch(data, size); + if (!p) pr_err("Error allocating buffer for %p\n", data); else list_add_tail(&p->plist, µcode_cache); } + if (!p) + return; + /* * Save for early loading. On 32-bit, that needs to be a physical * address as the APs are running from physical addresses, before * paging has been enabled. */ - if (p) { - if (IS_ENABLED(CONFIG_X86_32)) - intel_ucode_patch = (struct microcode_intel *)__pa_nodebug(p->data); - else - intel_ucode_patch = p->data; - } + if (IS_ENABLED(CONFIG_X86_32)) + intel_ucode_patch = (struct microcode_intel *)__pa_nodebug(p->data); + else + intel_ucode_patch = p->data; } static int microcode_sanity_check(void *mc, int print_err) diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 70e717fccdd6..9fc32651c911 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -59,13 +59,8 @@ void hyperv_vector_handler(struct pt_regs *regs) void hv_setup_vmbus_irq(void (*handler)(void)) { vmbus_handler = handler; - /* - * Setup the IDT for hypervisor callback. Prevent reallocation - * at module reload. - */ - if (!test_bit(HYPERVISOR_CALLBACK_VECTOR, used_vectors)) - alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, - hyperv_callback_vector); + /* Setup the IDT for hypervisor callback */ + alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, hyperv_callback_vector); } void hv_remove_vmbus_irq(void) diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index c5bb63be4ba1..40d5a8a75212 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -237,6 +237,18 @@ set_mtrr(unsigned int reg, unsigned long base, unsigned long size, mtrr_type typ stop_machine(mtrr_rendezvous_handler, &data, cpu_online_mask); } +static void set_mtrr_cpuslocked(unsigned int reg, unsigned long base, + unsigned long size, mtrr_type type) +{ + struct set_mtrr_data data = { .smp_reg = reg, + .smp_base = base, + .smp_size = size, + .smp_type = type + }; + + stop_machine_cpuslocked(mtrr_rendezvous_handler, &data, cpu_online_mask); +} + static void set_mtrr_from_inactive_cpu(unsigned int reg, unsigned long base, unsigned long size, mtrr_type type) { @@ -370,7 +382,7 @@ int mtrr_add_page(unsigned long base, unsigned long size, /* Search for an empty MTRR */ i = mtrr_if->get_free_region(base, size, replace); if (i >= 0) { - set_mtrr(i, base, size, type); + set_mtrr_cpuslocked(i, base, size, type); if (likely(replace < 0)) { mtrr_usage_table[i] = 1; } else { @@ -378,7 +390,7 @@ int mtrr_add_page(unsigned long base, unsigned long size, if (increment) mtrr_usage_table[i]++; if (unlikely(replace != i)) { - set_mtrr(replace, 0, 0, 0); + set_mtrr_cpuslocked(replace, 0, 0, 0); mtrr_usage_table[replace] = 0; } } @@ -506,7 +518,7 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size) goto out; } if (--mtrr_usage_table[reg] < 1) - set_mtrr(reg, 0, 0, 0); + set_mtrr_cpuslocked(reg, 0, 0, 0); error = reg; out: mutex_unlock(&mtrr_mutex); diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index 23c23508c012..05459ad3db46 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -31,6 +31,7 @@ static const struct cpuid_bit cpuid_bits[] = { { 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 }, + { X86_FEATURE_SME, CPUID_EAX, 0, 0x8000001f, 0 }, { 0, 0, 0, 0, 0 } }; diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index dbce3cca94cb..f13b4c00a5de 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -94,6 +94,9 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, if (stack_name) printk("%s <%s>\n", log_lvl, stack_name); + if (regs && on_stack(&stack_info, regs, sizeof(*regs))) + __show_regs(regs, 0); + /* * Scan the stack, printing any text addresses we find. At the * same time, follow proper stack frames with the unwinder. @@ -118,10 +121,8 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, * Don't print regs->ip again if it was already printed * by __show_regs() below. */ - if (regs && stack == ®s->ip) { - unwind_next_frame(&state); - continue; - } + if (regs && stack == ®s->ip) + goto next; if (stack == ret_addr_p) reliable = 1; @@ -144,6 +145,7 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, if (!reliable) continue; +next: /* * Get the next frame from the unwinder. No need to * check for an error: if anything goes wrong, the rest @@ -153,7 +155,7 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, /* if the frame has entry regs, print them */ regs = unwind_get_entry_regs(&state); - if (regs) + if (regs && on_stack(&stack_info, regs, sizeof(*regs))) __show_regs(regs, 0); } @@ -265,7 +267,7 @@ int __die(const char *str, struct pt_regs *regs, long err) #ifdef CONFIG_X86_32 if (user_mode(regs)) { sp = regs->sp; - ss = regs->ss & 0xffff; + ss = regs->ss; } else { sp = kernel_stack_pointer(regs); savesegment(ss, ss); diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c index e5f0b40e66d2..4f0481474903 100644 --- a/arch/x86/kernel/dumpstack_32.c +++ b/arch/x86/kernel/dumpstack_32.c @@ -37,7 +37,7 @@ static bool in_hardirq_stack(unsigned long *stack, struct stack_info *info) * This is a software stack, so 'end' can be a valid stack pointer. * It just means the stack is empty. */ - if (stack < begin || stack > end) + if (stack <= begin || stack > end) return false; info->type = STACK_TYPE_IRQ; @@ -62,7 +62,7 @@ static bool in_softirq_stack(unsigned long *stack, struct stack_info *info) * This is a software stack, so 'end' can be a valid stack pointer. * It just means the stack is empty. */ - if (stack < begin || stack > end) + if (stack <= begin || stack > end) return false; info->type = STACK_TYPE_SOFTIRQ; diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 3e1471d57487..225af4184f06 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -55,7 +55,7 @@ static bool in_exception_stack(unsigned long *stack, struct stack_info *info) begin = end - (exception_stack_sizes[k] / sizeof(long)); regs = (struct pt_regs *)end - 1; - if (stack < begin || stack >= end) + if (stack <= begin || stack >= end) continue; info->type = STACK_TYPE_EXCEPTION + k; @@ -78,7 +78,7 @@ static bool in_irq_stack(unsigned long *stack, struct stack_info *info) * This is a software stack, so 'end' can be a valid stack pointer. * It just means the stack is empty. */ - if (stack < begin || stack > end) + if (stack <= begin || stack > end) return false; info->type = STACK_TYPE_IRQ; diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 532da61d605c..71c11ad5643e 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -96,7 +96,8 @@ EXPORT_SYMBOL_GPL(e820__mapped_any); * Note: this function only works correctly once the E820 table is sorted and * not-overlapping (at least for the range specified), which is the case normally. */ -bool __init e820__mapped_all(u64 start, u64 end, enum e820_type type) +static struct e820_entry *__e820__mapped_all(u64 start, u64 end, + enum e820_type type) { int i; @@ -122,9 +123,28 @@ bool __init e820__mapped_all(u64 start, u64 end, enum e820_type type) * coverage of the desired range exists: */ if (start >= end) - return 1; + return entry; } - return 0; + + return NULL; +} + +/* + * This function checks if the entire range <start,end> is mapped with type. + */ +bool __init e820__mapped_all(u64 start, u64 end, enum e820_type type) +{ + return __e820__mapped_all(start, end, type); +} + +/* + * This function returns the type associated with the range <start,end>. + */ +int e820__get_entry_type(u64 start, u64 end) +{ + struct e820_entry *entry = __e820__mapped_all(start, end, 0); + + return entry ? entry->type : -EINVAL; } /* diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index d907c3d8633f..a4516ca4c4f3 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -527,6 +527,7 @@ static const struct pci_device_id intel_early_ids[] __initconst = { INTEL_BXT_IDS(&gen9_early_ops), INTEL_KBL_IDS(&gen9_early_ops), INTEL_GLK_IDS(&gen9_early_ops), + INTEL_CNL_IDS(&gen9_early_ops), }; static void __init diff --git a/arch/x86/kernel/eisa.c b/arch/x86/kernel/eisa.c new file mode 100644 index 000000000000..f260e452e4f8 --- /dev/null +++ b/arch/x86/kernel/eisa.c @@ -0,0 +1,19 @@ +/* + * EISA specific code + * + * This file is licensed under the GPL V2 + */ +#include <linux/ioport.h> +#include <linux/eisa.h> +#include <linux/io.h> + +static __init int eisa_bus_probe(void) +{ + void __iomem *p = ioremap(0x0FFFD9, 4); + + if (readl(p) == 'E' + ('I'<<8) + ('S'<<16) + ('A'<<24)) + EISA_bus = 1; + iounmap(p); + return 0; +} +subsys_initcall(eisa_bus_probe); diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c index 6b91e2eb8d3f..9c4e7ba6870c 100644 --- a/arch/x86/kernel/espfix_64.c +++ b/arch/x86/kernel/espfix_64.c @@ -195,7 +195,7 @@ void init_espfix_ap(int cpu) pte_p = pte_offset_kernel(&pmd, addr); stack_page = page_address(alloc_pages_node(node, GFP_KERNEL, 0)); - pte = __pte(__pa(stack_page) | (__PAGE_KERNEL_RO & ptemask)); + pte = __pte(__pa(stack_page) | ((__PAGE_KERNEL_RO | _PAGE_ENC) & ptemask)); for (n = 0; n < ESPFIX_PTE_CLONES; n++) set_pte(&pte_p[n*PTE_STRIDE], pte); diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index 538ec012b371..cf2ce063f65a 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -10,6 +10,7 @@ #include <linux/mm.h> #include <linux/memblock.h> +#include <asm/desc.h> #include <asm/setup.h> #include <asm/sections.h> #include <asm/e820/api.h> @@ -30,6 +31,9 @@ static void __init i386_default_early_setup(void) asmlinkage __visible void __init i386_start_kernel(void) { cr4_init_shadow(); + + idt_setup_early_handler(); + sanitize_boot_params(&boot_params); x86_early_init_platform_quirks(); diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 46c3c73e7f43..bab4fa579450 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -14,6 +14,7 @@ #include <linux/start_kernel.h> #include <linux/io.h> #include <linux/memblock.h> +#include <linux/mem_encrypt.h> #include <asm/processor.h> #include <asm/proto.h> @@ -33,7 +34,6 @@ /* * Manage page tables very early on. */ -extern pgd_t early_top_pgt[PTRS_PER_PGD]; extern pmd_t early_dynamic_pgts[EARLY_DYNAMIC_PAGE_TABLES][PTRS_PER_PMD]; static unsigned int __initdata next_early_pgt; pmdval_t early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX); @@ -45,14 +45,17 @@ static void __head *fixup_pointer(void *ptr, unsigned long physaddr) return ptr - (void *)_text + (void *)physaddr; } -void __head __startup_64(unsigned long physaddr) +unsigned long __head __startup_64(unsigned long physaddr, + struct boot_params *bp) { unsigned long load_delta, *p; + unsigned long pgtable_flags; pgdval_t *pgd; p4dval_t *p4d; pudval_t *pud; pmdval_t *pmd, pmd_entry; int i; + unsigned int *next_pgt_ptr; /* Is the address too large? */ if (physaddr >> MAX_PHYSMEM_BITS) @@ -68,6 +71,12 @@ void __head __startup_64(unsigned long physaddr) if (load_delta & ~PMD_PAGE_MASK) for (;;); + /* Activate Secure Memory Encryption (SME) if supported and enabled */ + sme_enable(bp); + + /* Include the SME encryption mask in the fixup value */ + load_delta += sme_get_me_mask(); + /* Fixup the physical addresses in the page table */ pgd = fixup_pointer(&early_top_pgt, physaddr); @@ -92,30 +101,34 @@ void __head __startup_64(unsigned long physaddr) * it avoids problems around wraparound. */ - pud = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr); - pmd = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr); + next_pgt_ptr = fixup_pointer(&next_early_pgt, physaddr); + pud = fixup_pointer(early_dynamic_pgts[(*next_pgt_ptr)++], physaddr); + pmd = fixup_pointer(early_dynamic_pgts[(*next_pgt_ptr)++], physaddr); + + pgtable_flags = _KERNPG_TABLE_NOENC + sme_get_me_mask(); if (IS_ENABLED(CONFIG_X86_5LEVEL)) { p4d = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr); i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD; - pgd[i + 0] = (pgdval_t)p4d + _KERNPG_TABLE; - pgd[i + 1] = (pgdval_t)p4d + _KERNPG_TABLE; + pgd[i + 0] = (pgdval_t)p4d + pgtable_flags; + pgd[i + 1] = (pgdval_t)p4d + pgtable_flags; i = (physaddr >> P4D_SHIFT) % PTRS_PER_P4D; - p4d[i + 0] = (pgdval_t)pud + _KERNPG_TABLE; - p4d[i + 1] = (pgdval_t)pud + _KERNPG_TABLE; + p4d[i + 0] = (pgdval_t)pud + pgtable_flags; + p4d[i + 1] = (pgdval_t)pud + pgtable_flags; } else { i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD; - pgd[i + 0] = (pgdval_t)pud + _KERNPG_TABLE; - pgd[i + 1] = (pgdval_t)pud + _KERNPG_TABLE; + pgd[i + 0] = (pgdval_t)pud + pgtable_flags; + pgd[i + 1] = (pgdval_t)pud + pgtable_flags; } i = (physaddr >> PUD_SHIFT) % PTRS_PER_PUD; - pud[i + 0] = (pudval_t)pmd + _KERNPG_TABLE; - pud[i + 1] = (pudval_t)pmd + _KERNPG_TABLE; + pud[i + 0] = (pudval_t)pmd + pgtable_flags; + pud[i + 1] = (pudval_t)pmd + pgtable_flags; pmd_entry = __PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL; + pmd_entry += sme_get_me_mask(); pmd_entry += physaddr; for (i = 0; i < DIV_ROUND_UP(_end - _text, PMD_SIZE); i++) { @@ -136,9 +149,30 @@ void __head __startup_64(unsigned long physaddr) pmd[i] += load_delta; } - /* Fixup phys_base */ + /* + * Fixup phys_base - remove the memory encryption mask to obtain + * the true physical address. + */ p = fixup_pointer(&phys_base, physaddr); - *p += load_delta; + *p += load_delta - sme_get_me_mask(); + + /* Encrypt the kernel (if SME is active) */ + sme_encrypt_kernel(); + + /* + * Return the SME encryption mask (if SME is active) to be used as a + * modifier for the initial pgdir entry programmed into CR3. + */ + return sme_get_me_mask(); +} + +unsigned long __startup_secondary_64(void) +{ + /* + * Return the SME encryption mask (if SME is active) to be used as a + * modifier for the initial pgdir entry programmed into CR3. + */ + return sme_get_me_mask(); } /* Wipe all early page tables except for the kernel symbol map */ @@ -146,17 +180,17 @@ static void __init reset_early_page_tables(void) { memset(early_top_pgt, 0, sizeof(pgd_t)*(PTRS_PER_PGD-1)); next_early_pgt = 0; - write_cr3(__pa_nodebug(early_top_pgt)); + write_cr3(__sme_pa_nodebug(early_top_pgt)); } /* Create a new PMD entry */ -int __init early_make_pgtable(unsigned long address) +int __init __early_make_pgtable(unsigned long address, pmdval_t pmd) { unsigned long physaddr = address - __PAGE_OFFSET; pgdval_t pgd, *pgd_p; p4dval_t p4d, *p4d_p; pudval_t pud, *pud_p; - pmdval_t pmd, *pmd_p; + pmdval_t *pmd_p; /* Invalid address or early pgt is done ? */ if (physaddr >= MAXMEM || read_cr3_pa() != __pa_nodebug(early_top_pgt)) @@ -215,12 +249,21 @@ again: memset(pmd_p, 0, sizeof(*pmd_p) * PTRS_PER_PMD); *pud_p = (pudval_t)pmd_p - __START_KERNEL_map + phys_base + _KERNPG_TABLE; } - pmd = (physaddr & PMD_MASK) + early_pmd_flags; pmd_p[pmd_index(address)] = pmd; return 0; } +int __init early_make_pgtable(unsigned long address) +{ + unsigned long physaddr = address - __PAGE_OFFSET; + pmdval_t pmd; + + pmd = (physaddr & PMD_MASK) + early_pmd_flags; + + return __early_make_pgtable(address, pmd); +} + /* Don't add a printk in there. printk relies on the PDA which is not initialized yet. */ static void __init clear_bss(void) @@ -243,6 +286,12 @@ static void __init copy_bootdata(char *real_mode_data) char * command_line; unsigned long cmd_line_ptr; + /* + * If SME is active, this will create decrypted mappings of the + * boot data in advance of the copy operations. + */ + sme_map_bootdata(real_mode_data); + memcpy(&boot_params, real_mode_data, sizeof boot_params); sanitize_boot_params(&boot_params); cmd_line_ptr = get_cmd_line_ptr(); @@ -250,12 +299,18 @@ static void __init copy_bootdata(char *real_mode_data) command_line = __va(cmd_line_ptr); memcpy(boot_command_line, command_line, COMMAND_LINE_SIZE); } + + /* + * The old boot data is no longer needed and won't be reserved, + * freeing up that memory for use by the system. If SME is active, + * we need to remove the mappings that were created so that the + * memory doesn't remain mapped as decrypted. + */ + sme_unmap_bootdata(real_mode_data); } asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data) { - int i; - /* * Build-time sanity checks on the kernel image and module * area mappings. (these are purely build-time and produce no code) @@ -279,11 +334,16 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data) clear_page(init_top_pgt); + /* + * SME support may update early_pmd_flags to include the memory + * encryption mask, so it needs to be called before anything + * that may generate a page fault. + */ + sme_early_init(); + kasan_early_init(); - for (i = 0; i < NUM_EXCEPTION_VECTORS; i++) - set_intr_gate(i, early_idt_handler_array[i]); - load_idt((const struct desc_ptr *)&idt_descr); + idt_setup_early_handler(); copy_bootdata(__va(real_mode_data)); diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 1f85ee8f9439..9ed3074d0d27 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -155,7 +155,6 @@ ENTRY(startup_32) jmp *%eax .Lbad_subarch: -WEAK(lguest_entry) WEAK(xen_entry) /* Unknown implementation; there's really nothing we can do at this point. */ @@ -165,7 +164,6 @@ WEAK(xen_entry) subarch_entries: .long .Ldefault_entry /* normal x86/PC */ - .long lguest_entry /* lguest hypervisor */ .long xen_entry /* Xen hypervisor */ .long .Ldefault_entry /* Moorestown MID */ num_subarch_entries = (. - subarch_entries) / 4 @@ -347,7 +345,6 @@ ENTRY(startup_32_smp) movl %eax,%cr0 lgdt early_gdt_descr - lidt idt_descr ljmp $(__KERNEL_CS),$1f 1: movl $(__KERNEL_DS),%eax # reload all the segment registers movl %eax,%ss # after changing gdt. @@ -380,37 +377,6 @@ ENDPROC(startup_32_smp) */ __INIT setup_once: - /* - * Set up a idt with 256 interrupt gates that push zero if there - * is no error code and then jump to early_idt_handler_common. - * It doesn't actually load the idt - that needs to be done on - * each CPU. Interrupts are enabled elsewhere, when we can be - * relatively sure everything is ok. - */ - - movl $idt_table,%edi - movl $early_idt_handler_array,%eax - movl $NUM_EXCEPTION_VECTORS,%ecx -1: - movl %eax,(%edi) - movl %eax,4(%edi) - /* interrupt gate, dpl=0, present */ - movl $(0x8E000000 + __KERNEL_CS),2(%edi) - addl $EARLY_IDT_HANDLER_SIZE,%eax - addl $8,%edi - loop 1b - - movl $256 - NUM_EXCEPTION_VECTORS,%ecx - movl $ignore_int,%edx - movl $(__KERNEL_CS << 16),%eax - movw %dx,%ax /* selector = 0x0010 = cs */ - movw $0x8E00,%dx /* interrupt gate - dpl=0, present */ -2: - movl %eax,(%edi) - movl %edx,4(%edi) - addl $8,%edi - loop 2b - #ifdef CONFIG_CC_STACKPROTECTOR /* * Configure the stack canary. The linker can't handle this by @@ -457,12 +423,9 @@ early_idt_handler_common: /* The vector number is in pt_regs->gs */ cld - pushl %fs /* pt_regs->fs */ - movw $0, 2(%esp) /* clear high bits (some CPUs leave garbage) */ - pushl %es /* pt_regs->es */ - movw $0, 2(%esp) /* clear high bits (some CPUs leave garbage) */ - pushl %ds /* pt_regs->ds */ - movw $0, 2(%esp) /* clear high bits (some CPUs leave garbage) */ + pushl %fs /* pt_regs->fs (__fsh varies by model) */ + pushl %es /* pt_regs->es (__esh varies by model) */ + pushl %ds /* pt_regs->ds (__dsh varies by model) */ pushl %eax /* pt_regs->ax */ pushl %ebp /* pt_regs->bp */ pushl %edi /* pt_regs->di */ @@ -479,9 +442,8 @@ early_idt_handler_common: /* Load the vector number into EDX */ movl PT_GS(%esp), %edx - /* Load GS into pt_regs->gs and clear high bits */ + /* Load GS into pt_regs->gs (and maybe clobber __gsh) */ movw %gs, PT_GS(%esp) - movw $0, PT_GS+2(%esp) movl %esp, %eax /* args are pt_regs (EAX), trapnr (EDX) */ call early_fixup_exception @@ -493,18 +455,17 @@ early_idt_handler_common: popl %edi /* pt_regs->di */ popl %ebp /* pt_regs->bp */ popl %eax /* pt_regs->ax */ - popl %ds /* pt_regs->ds */ - popl %es /* pt_regs->es */ - popl %fs /* pt_regs->fs */ - popl %gs /* pt_regs->gs */ + popl %ds /* pt_regs->ds (always ignores __dsh) */ + popl %es /* pt_regs->es (always ignores __esh) */ + popl %fs /* pt_regs->fs (always ignores __fsh) */ + popl %gs /* pt_regs->gs (always ignores __gsh) */ decl %ss:early_recursion_flag addl $4, %esp /* pop pt_regs->orig_ax */ iret ENDPROC(early_idt_handler_common) /* This is the default interrupt "handler" :-) */ - ALIGN -ignore_int: +ENTRY(early_ignore_irq) cld #ifdef CONFIG_PRINTK pushl %eax @@ -539,7 +500,8 @@ ignore_int: hlt_loop: hlt jmp hlt_loop -ENDPROC(ignore_int) +ENDPROC(early_ignore_irq) + __INITDATA .align 4 GLOBAL(early_recursion_flag) @@ -628,7 +590,6 @@ int_msg: .data .globl boot_gdt_descr -.globl idt_descr ALIGN # early boot GDT descriptor (must use 1:1 address mapping) @@ -637,11 +598,6 @@ boot_gdt_descr: .word __BOOT_DS+7 .long boot_gdt - __PAGE_OFFSET - .word 0 # 32-bit align idt_desc.address -idt_descr: - .word IDT_ENTRIES*8-1 # idt contains 256 entries - .long idt_table - # boot GDT descriptor (later on used by CPU#0): .word 0 # 32 bit align gdt_desc.address ENTRY(early_gdt_descr) diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 6225550883df..513cbb012ecc 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -73,12 +73,19 @@ startup_64: /* Sanitize CPU configuration */ call verify_cpu + /* + * Perform pagetable fixups. Additionally, if SME is active, encrypt + * the kernel and retrieve the modifier (SME encryption mask if SME + * is active) to be added to the initial pgdir entry that will be + * programmed into CR3. + */ leaq _text(%rip), %rdi pushq %rsi call __startup_64 popq %rsi - movq $(early_top_pgt - __START_KERNEL_map), %rax + /* Form the CR3 value being sure to include the CR3 modifier */ + addq $(early_top_pgt - __START_KERNEL_map), %rax jmp 1f ENTRY(secondary_startup_64) /* @@ -98,7 +105,16 @@ ENTRY(secondary_startup_64) /* Sanitize CPU configuration */ call verify_cpu - movq $(init_top_pgt - __START_KERNEL_map), %rax + /* + * Retrieve the modifier (SME encryption mask if SME is active) to be + * added to the initial pgdir entry that will be programmed into CR3. + */ + pushq %rsi + call __startup_secondary_64 + popq %rsi + + /* Form the CR3 value being sure to include the CR3 modifier */ + addq $(init_top_pgt - __START_KERNEL_map), %rax 1: /* Enable PAE mode, PGE and LA57 */ @@ -335,9 +351,9 @@ GLOBAL(name) NEXT_PAGE(early_top_pgt) .fill 511,8,0 #ifdef CONFIG_X86_5LEVEL - .quad level4_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE + .quad level4_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC #else - .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE + .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC #endif NEXT_PAGE(early_dynamic_pgts) @@ -350,15 +366,15 @@ NEXT_PAGE(init_top_pgt) .fill 512,8,0 #else NEXT_PAGE(init_top_pgt) - .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE + .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC .org init_top_pgt + PGD_PAGE_OFFSET*8, 0 - .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE + .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC .org init_top_pgt + PGD_START_KERNEL*8, 0 /* (2^48-(2*1024*1024*1024))/(2^39) = 511 */ - .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE + .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC NEXT_PAGE(level3_ident_pgt) - .quad level2_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE + .quad level2_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC .fill 511, 8, 0 NEXT_PAGE(level2_ident_pgt) /* Since I easily can, map the first 1G. @@ -370,14 +386,14 @@ NEXT_PAGE(level2_ident_pgt) #ifdef CONFIG_X86_5LEVEL NEXT_PAGE(level4_kernel_pgt) .fill 511,8,0 - .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE + .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC #endif NEXT_PAGE(level3_kernel_pgt) .fill L3_START_KERNEL,8,0 /* (2^48-(2*1024*1024*1024)-((2^39)*511))/(2^30) = 510 */ - .quad level2_kernel_pgt - __START_KERNEL_map + _KERNPG_TABLE - .quad level2_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE + .quad level2_kernel_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC + .quad level2_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC NEXT_PAGE(level2_kernel_pgt) /* @@ -395,7 +411,7 @@ NEXT_PAGE(level2_kernel_pgt) NEXT_PAGE(level2_fixmap_pgt) .fill 506,8,0 - .quad level1_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE + .quad level1_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC /* 8MB reserved for vsyscalls + a 2MB hole = 4 + 1 entries */ .fill 5,8,0 diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 16f82a3aaec7..8ce4212e2b8d 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -345,21 +345,10 @@ static int hpet_shutdown(struct clock_event_device *evt, int timer) return 0; } -static int hpet_resume(struct clock_event_device *evt, int timer) -{ - if (!timer) { - hpet_enable_legacy_int(); - } else { - struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt); - - irq_domain_deactivate_irq(irq_get_irq_data(hdev->irq)); - irq_domain_activate_irq(irq_get_irq_data(hdev->irq)); - disable_hardirq(hdev->irq); - irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu)); - enable_irq(hdev->irq); - } +static int hpet_resume(struct clock_event_device *evt) +{ + hpet_enable_legacy_int(); hpet_print_config(); - return 0; } @@ -417,7 +406,7 @@ static int hpet_legacy_set_periodic(struct clock_event_device *evt) static int hpet_legacy_resume(struct clock_event_device *evt) { - return hpet_resume(evt, 0); + return hpet_resume(evt); } static int hpet_legacy_next_event(unsigned long delta, @@ -510,8 +499,14 @@ static int hpet_msi_set_periodic(struct clock_event_device *evt) static int hpet_msi_resume(struct clock_event_device *evt) { struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt); + struct irq_data *data = irq_get_irq_data(hdev->irq); + struct msi_msg msg; - return hpet_resume(evt, hdev->num); + /* Restore the MSI msg and unmask the interrupt */ + irq_chip_compose_msi_msg(data, &msg); + hpet_msi_write(hdev, &msg); + hpet_msi_unmask(data); + return 0; } static int hpet_msi_next_event(unsigned long delta, diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c new file mode 100644 index 000000000000..6107ee1cb8d5 --- /dev/null +++ b/arch/x86/kernel/idt.c @@ -0,0 +1,371 @@ +/* + * Interrupt descriptor table related code + * + * This file is licensed under the GPL V2 + */ +#include <linux/interrupt.h> + +#include <asm/traps.h> +#include <asm/proto.h> +#include <asm/desc.h> + +struct idt_data { + unsigned int vector; + unsigned int segment; + struct idt_bits bits; + const void *addr; +}; + +#define DPL0 0x0 +#define DPL3 0x3 + +#define DEFAULT_STACK 0 + +#define G(_vector, _addr, _ist, _type, _dpl, _segment) \ + { \ + .vector = _vector, \ + .bits.ist = _ist, \ + .bits.type = _type, \ + .bits.dpl = _dpl, \ + .bits.p = 1, \ + .addr = _addr, \ + .segment = _segment, \ + } + +/* Interrupt gate */ +#define INTG(_vector, _addr) \ + G(_vector, _addr, DEFAULT_STACK, GATE_INTERRUPT, DPL0, __KERNEL_CS) + +/* System interrupt gate */ +#define SYSG(_vector, _addr) \ + G(_vector, _addr, DEFAULT_STACK, GATE_INTERRUPT, DPL3, __KERNEL_CS) + +/* Interrupt gate with interrupt stack */ +#define ISTG(_vector, _addr, _ist) \ + G(_vector, _addr, _ist, GATE_INTERRUPT, DPL0, __KERNEL_CS) + +/* System interrupt gate with interrupt stack */ +#define SISTG(_vector, _addr, _ist) \ + G(_vector, _addr, _ist, GATE_INTERRUPT, DPL3, __KERNEL_CS) + +/* Task gate */ +#define TSKG(_vector, _gdt) \ + G(_vector, NULL, DEFAULT_STACK, GATE_TASK, DPL0, _gdt << 3) + +/* + * Early traps running on the DEFAULT_STACK because the other interrupt + * stacks work only after cpu_init(). + */ +static const __initdata struct idt_data early_idts[] = { + INTG(X86_TRAP_DB, debug), + SYSG(X86_TRAP_BP, int3), +#ifdef CONFIG_X86_32 + INTG(X86_TRAP_PF, page_fault), +#endif +}; + +/* + * The default IDT entries which are set up in trap_init() before + * cpu_init() is invoked. Interrupt stacks cannot be used at that point and + * the traps which use them are reinitialized with IST after cpu_init() has + * set up TSS. + */ +static const __initdata struct idt_data def_idts[] = { + INTG(X86_TRAP_DE, divide_error), + INTG(X86_TRAP_NMI, nmi), + INTG(X86_TRAP_BR, bounds), + INTG(X86_TRAP_UD, invalid_op), + INTG(X86_TRAP_NM, device_not_available), + INTG(X86_TRAP_OLD_MF, coprocessor_segment_overrun), + INTG(X86_TRAP_TS, invalid_TSS), + INTG(X86_TRAP_NP, segment_not_present), + INTG(X86_TRAP_SS, stack_segment), + INTG(X86_TRAP_GP, general_protection), + INTG(X86_TRAP_SPURIOUS, spurious_interrupt_bug), + INTG(X86_TRAP_MF, coprocessor_error), + INTG(X86_TRAP_AC, alignment_check), + INTG(X86_TRAP_XF, simd_coprocessor_error), + +#ifdef CONFIG_X86_32 + TSKG(X86_TRAP_DF, GDT_ENTRY_DOUBLEFAULT_TSS), +#else + INTG(X86_TRAP_DF, double_fault), +#endif + INTG(X86_TRAP_DB, debug), + INTG(X86_TRAP_NMI, nmi), + INTG(X86_TRAP_BP, int3), + +#ifdef CONFIG_X86_MCE + INTG(X86_TRAP_MC, &machine_check), +#endif + + SYSG(X86_TRAP_OF, overflow), +#if defined(CONFIG_IA32_EMULATION) + SYSG(IA32_SYSCALL_VECTOR, entry_INT80_compat), +#elif defined(CONFIG_X86_32) + SYSG(IA32_SYSCALL_VECTOR, entry_INT80_32), +#endif +}; + +/* + * The APIC and SMP idt entries + */ +static const __initdata struct idt_data apic_idts[] = { +#ifdef CONFIG_SMP + INTG(RESCHEDULE_VECTOR, reschedule_interrupt), + INTG(CALL_FUNCTION_VECTOR, call_function_interrupt), + INTG(CALL_FUNCTION_SINGLE_VECTOR, call_function_single_interrupt), + INTG(IRQ_MOVE_CLEANUP_VECTOR, irq_move_cleanup_interrupt), + INTG(REBOOT_VECTOR, reboot_interrupt), +#endif + +#ifdef CONFIG_X86_THERMAL_VECTOR + INTG(THERMAL_APIC_VECTOR, thermal_interrupt), +#endif + +#ifdef CONFIG_X86_MCE_THRESHOLD + INTG(THRESHOLD_APIC_VECTOR, threshold_interrupt), +#endif + +#ifdef CONFIG_X86_MCE_AMD + INTG(DEFERRED_ERROR_VECTOR, deferred_error_interrupt), +#endif + +#ifdef CONFIG_X86_LOCAL_APIC + INTG(LOCAL_TIMER_VECTOR, apic_timer_interrupt), + INTG(X86_PLATFORM_IPI_VECTOR, x86_platform_ipi), +# ifdef CONFIG_HAVE_KVM + INTG(POSTED_INTR_VECTOR, kvm_posted_intr_ipi), + INTG(POSTED_INTR_WAKEUP_VECTOR, kvm_posted_intr_wakeup_ipi), + INTG(POSTED_INTR_NESTED_VECTOR, kvm_posted_intr_nested_ipi), +# endif +# ifdef CONFIG_IRQ_WORK + INTG(IRQ_WORK_VECTOR, irq_work_interrupt), +# endif + INTG(SPURIOUS_APIC_VECTOR, spurious_interrupt), + INTG(ERROR_APIC_VECTOR, error_interrupt), +#endif +}; + +#ifdef CONFIG_X86_64 +/* + * Early traps running on the DEFAULT_STACK because the other interrupt + * stacks work only after cpu_init(). + */ +static const __initdata struct idt_data early_pf_idts[] = { + INTG(X86_TRAP_PF, page_fault), +}; + +/* + * Override for the debug_idt. Same as the default, but with interrupt + * stack set to DEFAULT_STACK (0). Required for NMI trap handling. + */ +static const __initdata struct idt_data dbg_idts[] = { + INTG(X86_TRAP_DB, debug), + INTG(X86_TRAP_BP, int3), +}; +#endif + +/* Must be page-aligned because the real IDT is used in a fixmap. */ +gate_desc idt_table[IDT_ENTRIES] __page_aligned_bss; + +struct desc_ptr idt_descr __ro_after_init = { + .size = (IDT_ENTRIES * 2 * sizeof(unsigned long)) - 1, + .address = (unsigned long) idt_table, +}; + +#ifdef CONFIG_X86_64 +/* No need to be aligned, but done to keep all IDTs defined the same way. */ +gate_desc debug_idt_table[IDT_ENTRIES] __page_aligned_bss; + +/* + * The exceptions which use Interrupt stacks. They are setup after + * cpu_init() when the TSS has been initialized. + */ +static const __initdata struct idt_data ist_idts[] = { + ISTG(X86_TRAP_DB, debug, DEBUG_STACK), + ISTG(X86_TRAP_NMI, nmi, NMI_STACK), + SISTG(X86_TRAP_BP, int3, DEBUG_STACK), + ISTG(X86_TRAP_DF, double_fault, DOUBLEFAULT_STACK), +#ifdef CONFIG_X86_MCE + ISTG(X86_TRAP_MC, &machine_check, MCE_STACK), +#endif +}; + +/* + * Override for the debug_idt. Same as the default, but with interrupt + * stack set to DEFAULT_STACK (0). Required for NMI trap handling. + */ +const struct desc_ptr debug_idt_descr = { + .size = IDT_ENTRIES * 16 - 1, + .address = (unsigned long) debug_idt_table, +}; +#endif + +static inline void idt_init_desc(gate_desc *gate, const struct idt_data *d) +{ + unsigned long addr = (unsigned long) d->addr; + + gate->offset_low = (u16) addr; + gate->segment = (u16) d->segment; + gate->bits = d->bits; + gate->offset_middle = (u16) (addr >> 16); +#ifdef CONFIG_X86_64 + gate->offset_high = (u32) (addr >> 32); + gate->reserved = 0; +#endif +} + +static void +idt_setup_from_table(gate_desc *idt, const struct idt_data *t, int size, bool sys) +{ + gate_desc desc; + + for (; size > 0; t++, size--) { + idt_init_desc(&desc, t); + write_idt_entry(idt, t->vector, &desc); + if (sys) + set_bit(t->vector, used_vectors); + } +} + +static void set_intr_gate(unsigned int n, const void *addr) +{ + struct idt_data data; + + BUG_ON(n > 0xFF); + + memset(&data, 0, sizeof(data)); + data.vector = n; + data.addr = addr; + data.segment = __KERNEL_CS; + data.bits.type = GATE_INTERRUPT; + data.bits.p = 1; + + idt_setup_from_table(idt_table, &data, 1, false); +} + +/** + * idt_setup_early_traps - Initialize the idt table with early traps + * + * On X8664 these traps do not use interrupt stacks as they can't work + * before cpu_init() is invoked and sets up TSS. The IST variants are + * installed after that. + */ +void __init idt_setup_early_traps(void) +{ + idt_setup_from_table(idt_table, early_idts, ARRAY_SIZE(early_idts), + true); + load_idt(&idt_descr); +} + +/** + * idt_setup_traps - Initialize the idt table with default traps + */ +void __init idt_setup_traps(void) +{ + idt_setup_from_table(idt_table, def_idts, ARRAY_SIZE(def_idts), true); +} + +#ifdef CONFIG_X86_64 +/** + * idt_setup_early_pf - Initialize the idt table with early pagefault handler + * + * On X8664 this does not use interrupt stacks as they can't work before + * cpu_init() is invoked and sets up TSS. The IST variant is installed + * after that. + * + * FIXME: Why is 32bit and 64bit installing the PF handler at different + * places in the early setup code? + */ +void __init idt_setup_early_pf(void) +{ + idt_setup_from_table(idt_table, early_pf_idts, + ARRAY_SIZE(early_pf_idts), true); +} + +/** + * idt_setup_ist_traps - Initialize the idt table with traps using IST + */ +void __init idt_setup_ist_traps(void) +{ + idt_setup_from_table(idt_table, ist_idts, ARRAY_SIZE(ist_idts), true); +} + +/** + * idt_setup_debugidt_traps - Initialize the debug idt table with debug traps + */ +void __init idt_setup_debugidt_traps(void) +{ + memcpy(&debug_idt_table, &idt_table, IDT_ENTRIES * 16); + + idt_setup_from_table(debug_idt_table, dbg_idts, ARRAY_SIZE(dbg_idts), false); +} +#endif + +/** + * idt_setup_apic_and_irq_gates - Setup APIC/SMP and normal interrupt gates + */ +void __init idt_setup_apic_and_irq_gates(void) +{ + int i = FIRST_EXTERNAL_VECTOR; + void *entry; + + idt_setup_from_table(idt_table, apic_idts, ARRAY_SIZE(apic_idts), true); + + for_each_clear_bit_from(i, used_vectors, FIRST_SYSTEM_VECTOR) { + entry = irq_entries_start + 8 * (i - FIRST_EXTERNAL_VECTOR); + set_intr_gate(i, entry); + } + + for_each_clear_bit_from(i, used_vectors, NR_VECTORS) { +#ifdef CONFIG_X86_LOCAL_APIC + set_bit(i, used_vectors); + set_intr_gate(i, spurious_interrupt); +#else + entry = irq_entries_start + 8 * (i - FIRST_EXTERNAL_VECTOR); + set_intr_gate(i, entry); +#endif + } +} + +/** + * idt_setup_early_handler - Initializes the idt table with early handlers + */ +void __init idt_setup_early_handler(void) +{ + int i; + + for (i = 0; i < NUM_EXCEPTION_VECTORS; i++) + set_intr_gate(i, early_idt_handler_array[i]); +#ifdef CONFIG_X86_32 + for ( ; i < NR_VECTORS; i++) + set_intr_gate(i, early_ignore_irq); +#endif + load_idt(&idt_descr); +} + +/** + * idt_invalidate - Invalidate interrupt descriptor table + * @addr: The virtual address of the 'invalid' IDT + */ +void idt_invalidate(void *addr) +{ + struct desc_ptr idt = { .address = (unsigned long) addr, .size = 0 }; + + load_idt(&idt); +} + +void __init update_intr_gate(unsigned int n, const void *addr) +{ + if (WARN_ON_ONCE(!test_bit(n, used_vectors))) + return; + set_intr_gate(n, addr); +} + +void alloc_intr_gate(unsigned int n, const void *addr) +{ + BUG_ON(n < FIRST_SYSTEM_VECTOR); + if (!test_and_set_bit(n, used_vectors)) + set_intr_gate(n, addr); +} diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 4aa03c5a14c9..52089c043160 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -29,9 +29,6 @@ EXPORT_PER_CPU_SYMBOL(irq_regs); atomic_t irq_err_count; -/* Function pointer for generic interrupt vector handling */ -void (*x86_platform_ipi_callback)(void) = NULL; - /* * 'what should we do if we get a hw irq event on an illegal vector'. * each architecture has to answer this themselves. @@ -87,13 +84,13 @@ int arch_show_interrupts(struct seq_file *p, int prec) for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->icr_read_retry_count); seq_puts(p, " APIC ICR read retries\n"); -#endif if (x86_platform_ipi_callback) { seq_printf(p, "%*s: ", prec, "PLT"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->x86_platform_ipis); seq_puts(p, " Platform interrupts\n"); } +#endif #ifdef CONFIG_SMP seq_printf(p, "%*s: ", prec, "RES"); for_each_online_cpu(j) @@ -155,6 +152,12 @@ int arch_show_interrupts(struct seq_file *p, int prec) seq_printf(p, "%10u ", irq_stats(j)->kvm_posted_intr_ipis); seq_puts(p, " Posted-interrupt notification event\n"); + seq_printf(p, "%*s: ", prec, "NPI"); + for_each_online_cpu(j) + seq_printf(p, "%10u ", + irq_stats(j)->kvm_posted_intr_nested_ipis); + seq_puts(p, " Nested posted-interrupt event\n"); + seq_printf(p, "%*s: ", prec, "PIW"); for_each_online_cpu(j) seq_printf(p, "%10u ", @@ -177,9 +180,9 @@ u64 arch_irq_stat_cpu(unsigned int cpu) sum += irq_stats(cpu)->apic_perf_irqs; sum += irq_stats(cpu)->apic_irq_work_irqs; sum += irq_stats(cpu)->icr_read_retry_count; -#endif if (x86_platform_ipi_callback) sum += irq_stats(cpu)->x86_platform_ipis; +#endif #ifdef CONFIG_SMP sum += irq_stats(cpu)->irq_resched_count; sum += irq_stats(cpu)->irq_call_count; @@ -253,26 +256,26 @@ __visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs) return 1; } +#ifdef CONFIG_X86_LOCAL_APIC +/* Function pointer for generic interrupt vector handling */ +void (*x86_platform_ipi_callback)(void) = NULL; /* * Handler for X86_PLATFORM_IPI_VECTOR. */ -void __smp_x86_platform_ipi(void) -{ - inc_irq_stat(x86_platform_ipis); - - if (x86_platform_ipi_callback) - x86_platform_ipi_callback(); -} - __visible void __irq_entry smp_x86_platform_ipi(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); entering_ack_irq(); - __smp_x86_platform_ipi(); + trace_x86_platform_ipi_entry(X86_PLATFORM_IPI_VECTOR); + inc_irq_stat(x86_platform_ipis); + if (x86_platform_ipi_callback) + x86_platform_ipi_callback(); + trace_x86_platform_ipi_exit(X86_PLATFORM_IPI_VECTOR); exiting_irq(); set_irq_regs(old_regs); } +#endif #ifdef CONFIG_HAVE_KVM static void dummy_handler(void) {} @@ -313,21 +316,21 @@ __visible void smp_kvm_posted_intr_wakeup_ipi(struct pt_regs *regs) exiting_irq(); set_irq_regs(old_regs); } -#endif -__visible void __irq_entry smp_trace_x86_platform_ipi(struct pt_regs *regs) +/* + * Handler for POSTED_INTERRUPT_NESTED_VECTOR. + */ +__visible void smp_kvm_posted_intr_nested_ipi(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); entering_ack_irq(); - trace_x86_platform_ipi_entry(X86_PLATFORM_IPI_VECTOR); - __smp_x86_platform_ipi(); - trace_x86_platform_ipi_exit(X86_PLATFORM_IPI_VECTOR); + inc_irq_stat(kvm_posted_intr_nested_ipis); exiting_irq(); set_irq_regs(old_regs); } +#endif -EXPORT_SYMBOL_GPL(vector_used_by_percpu_irq); #ifdef CONFIG_HOTPLUG_CPU @@ -412,7 +415,7 @@ int check_irq_vectors_for_cpu_disable(void) * this w/o holding vector_lock. */ for (vector = FIRST_EXTERNAL_VECTOR; - vector < first_system_vector; vector++) { + vector < FIRST_SYSTEM_VECTOR; vector++) { if (!test_bit(vector, used_vectors) && IS_ERR_OR_NULL(per_cpu(vector_irq, cpu)[vector])) { if (++count == this_count) diff --git a/arch/x86/kernel/irq_work.c b/arch/x86/kernel/irq_work.c index 275487872be2..70dee056f92b 100644 --- a/arch/x86/kernel/irq_work.c +++ b/arch/x86/kernel/irq_work.c @@ -11,35 +11,23 @@ #include <asm/trace/irq_vectors.h> #include <linux/interrupt.h> -static inline void __smp_irq_work_interrupt(void) -{ - inc_irq_stat(apic_irq_work_irqs); - irq_work_run(); -} - +#ifdef CONFIG_X86_LOCAL_APIC __visible void __irq_entry smp_irq_work_interrupt(struct pt_regs *regs) { ipi_entering_ack_irq(); - __smp_irq_work_interrupt(); - exiting_irq(); -} - -__visible void __irq_entry smp_trace_irq_work_interrupt(struct pt_regs *regs) -{ - ipi_entering_ack_irq(); trace_irq_work_entry(IRQ_WORK_VECTOR); - __smp_irq_work_interrupt(); + inc_irq_stat(apic_irq_work_irqs); + irq_work_run(); trace_irq_work_exit(IRQ_WORK_VECTOR); exiting_irq(); } void arch_irq_work_raise(void) { -#ifdef CONFIG_X86_LOCAL_APIC if (!arch_irq_work_has_interrupt()) return; apic->send_IPI_self(IRQ_WORK_VECTOR); apic_wait_icr_idle(); -#endif } +#endif diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index 7468c6987547..1add9e08e83e 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -55,18 +55,6 @@ DEFINE_PER_CPU(vector_irq_t, vector_irq) = { [0 ... NR_VECTORS - 1] = VECTOR_UNUSED, }; -int vector_used_by_percpu_irq(unsigned int vector) -{ - int cpu; - - for_each_online_cpu(cpu) { - if (!IS_ERR_OR_NULL(per_cpu(vector_irq, cpu)[vector])) - return 1; - } - - return 0; -} - void __init init_ISA_irqs(void) { struct irq_chip *chip = legacy_pic->chip; @@ -99,98 +87,12 @@ void __init init_IRQ(void) x86_init.irqs.intr_init(); } -static void __init smp_intr_init(void) -{ -#ifdef CONFIG_SMP - /* - * The reschedule interrupt is a CPU-to-CPU reschedule-helper - * IPI, driven by wakeup. - */ - alloc_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt); - - /* IPI for generic function call */ - alloc_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt); - - /* IPI for generic single function call */ - alloc_intr_gate(CALL_FUNCTION_SINGLE_VECTOR, - call_function_single_interrupt); - - /* Low priority IPI to cleanup after moving an irq */ - set_intr_gate(IRQ_MOVE_CLEANUP_VECTOR, irq_move_cleanup_interrupt); - set_bit(IRQ_MOVE_CLEANUP_VECTOR, used_vectors); - - /* IPI used for rebooting/stopping */ - alloc_intr_gate(REBOOT_VECTOR, reboot_interrupt); -#endif /* CONFIG_SMP */ -} - -static void __init apic_intr_init(void) -{ - smp_intr_init(); - -#ifdef CONFIG_X86_THERMAL_VECTOR - alloc_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt); -#endif -#ifdef CONFIG_X86_MCE_THRESHOLD - alloc_intr_gate(THRESHOLD_APIC_VECTOR, threshold_interrupt); -#endif - -#ifdef CONFIG_X86_MCE_AMD - alloc_intr_gate(DEFERRED_ERROR_VECTOR, deferred_error_interrupt); -#endif - -#ifdef CONFIG_X86_LOCAL_APIC - /* self generated IPI for local APIC timer */ - alloc_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt); - - /* IPI for X86 platform specific use */ - alloc_intr_gate(X86_PLATFORM_IPI_VECTOR, x86_platform_ipi); -#ifdef CONFIG_HAVE_KVM - /* IPI for KVM to deliver posted interrupt */ - alloc_intr_gate(POSTED_INTR_VECTOR, kvm_posted_intr_ipi); - /* IPI for KVM to deliver interrupt to wake up tasks */ - alloc_intr_gate(POSTED_INTR_WAKEUP_VECTOR, kvm_posted_intr_wakeup_ipi); -#endif - - /* IPI vectors for APIC spurious and error interrupts */ - alloc_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt); - alloc_intr_gate(ERROR_APIC_VECTOR, error_interrupt); - - /* IRQ work interrupts: */ -# ifdef CONFIG_IRQ_WORK - alloc_intr_gate(IRQ_WORK_VECTOR, irq_work_interrupt); -# endif - -#endif -} - void __init native_init_IRQ(void) { - int i; - /* Execute any quirks before the call gates are initialised: */ x86_init.irqs.pre_vector_init(); - apic_intr_init(); - - /* - * Cover the whole vector space, no vector can escape - * us. (some of these will be overridden and become - * 'special' SMP interrupts) - */ - i = FIRST_EXTERNAL_VECTOR; -#ifndef CONFIG_X86_LOCAL_APIC -#define first_system_vector NR_VECTORS -#endif - for_each_clear_bit_from(i, used_vectors, first_system_vector) { - /* IA32_SYSCALL_VECTOR could be used in trap_init already. */ - set_intr_gate(i, irq_entries_start + - 8 * (i - FIRST_EXTERNAL_VECTOR)); - } -#ifdef CONFIG_X86_LOCAL_APIC - for_each_clear_bit_from(i, used_vectors, NR_VECTORS) - set_intr_gate(i, spurious_interrupt); -#endif + idt_setup_apic_and_irq_gates(); if (!acpi_ioapic && !of_ioapic && nr_legacy_irqs()) setup_irq(2, &irq2); diff --git a/arch/x86/kernel/kdebugfs.c b/arch/x86/kernel/kdebugfs.c index 38b64587b31b..fd6f8fbbe6f2 100644 --- a/arch/x86/kernel/kdebugfs.c +++ b/arch/x86/kernel/kdebugfs.c @@ -33,7 +33,6 @@ static ssize_t setup_data_read(struct file *file, char __user *user_buf, struct setup_data_node *node = file->private_data; unsigned long remain; loff_t pos = *ppos; - struct page *pg; void *p; u64 pa; @@ -47,18 +46,13 @@ static ssize_t setup_data_read(struct file *file, char __user *user_buf, count = node->len - pos; pa = node->paddr + sizeof(struct setup_data) + pos; - pg = pfn_to_page((pa + count - 1) >> PAGE_SHIFT); - if (PageHighMem(pg)) { - p = ioremap_cache(pa, count); - if (!p) - return -ENXIO; - } else - p = __va(pa); + p = memremap(pa, count, MEMREMAP_WB); + if (!p) + return -ENOMEM; remain = copy_to_user(user_buf, p, count); - if (PageHighMem(pg)) - iounmap(p); + memunmap(p); if (remain) return -EFAULT; @@ -109,7 +103,6 @@ static int __init create_setup_data_nodes(struct dentry *parent) struct setup_data *data; int error; struct dentry *d; - struct page *pg; u64 pa_data; int no = 0; @@ -126,16 +119,12 @@ static int __init create_setup_data_nodes(struct dentry *parent) goto err_dir; } - pg = pfn_to_page((pa_data+sizeof(*data)-1) >> PAGE_SHIFT); - if (PageHighMem(pg)) { - data = ioremap_cache(pa_data, sizeof(*data)); - if (!data) { - kfree(node); - error = -ENXIO; - goto err_dir; - } - } else - data = __va(pa_data); + data = memremap(pa_data, sizeof(*data), MEMREMAP_WB); + if (!data) { + kfree(node); + error = -ENOMEM; + goto err_dir; + } node->paddr = pa_data; node->type = data->type; @@ -143,8 +132,7 @@ static int __init create_setup_data_nodes(struct dentry *parent) error = create_setup_data_node(d, no, node); pa_data = data->next; - if (PageHighMem(pg)) - iounmap(data); + memunmap(data); if (error) goto err_dir; no++; diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 6b877807598b..f0153714ddac 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -457,6 +457,8 @@ static int arch_copy_kprobe(struct kprobe *p) int arch_prepare_kprobe(struct kprobe *p) { + int ret; + if (alternatives_text_reserved(p->addr, p->addr)) return -EINVAL; @@ -467,7 +469,13 @@ int arch_prepare_kprobe(struct kprobe *p) if (!p->ainsn.insn) return -ENOMEM; - return arch_copy_kprobe(p); + ret = arch_copy_kprobe(p); + if (ret) { + free_insn_slot(p->ainsn.insn, 0); + p->ainsn.insn = NULL; + } + + return ret; } void arch_arm_kprobe(struct kprobe *p) diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 69ea0bc1cfa3..4f98aad38237 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -39,6 +39,7 @@ #include <asm/insn.h> #include <asm/debugreg.h> #include <asm/set_memory.h> +#include <asm/sections.h> #include "common.h" @@ -251,10 +252,12 @@ static int can_optimize(unsigned long paddr) /* * Do not optimize in the entry code due to the unstable - * stack handling. + * stack handling and registers setup. */ - if ((paddr >= (unsigned long)__entry_text_start) && - (paddr < (unsigned long)__entry_text_end)) + if (((paddr >= (unsigned long)__entry_text_start) && + (paddr < (unsigned long)__entry_text_end)) || + ((paddr >= (unsigned long)__irqentry_text_start) && + (paddr < (unsigned long)__irqentry_text_end))) return 0; /* Check there is enough space for a relative jump. */ diff --git a/arch/x86/kernel/ksysfs.c b/arch/x86/kernel/ksysfs.c index 4afc67f5facc..4b0592ca9e47 100644 --- a/arch/x86/kernel/ksysfs.c +++ b/arch/x86/kernel/ksysfs.c @@ -16,8 +16,8 @@ #include <linux/stat.h> #include <linux/slab.h> #include <linux/mm.h> +#include <linux/io.h> -#include <asm/io.h> #include <asm/setup.h> static ssize_t version_show(struct kobject *kobj, @@ -55,7 +55,7 @@ static struct bin_attribute *boot_params_data_attrs[] = { NULL, }; -static struct attribute_group boot_params_attr_group = { +static const struct attribute_group boot_params_attr_group = { .attrs = boot_params_version_attrs, .bin_attrs = boot_params_data_attrs, }; @@ -79,12 +79,12 @@ static int get_setup_data_paddr(int nr, u64 *paddr) *paddr = pa_data; return 0; } - data = ioremap_cache(pa_data, sizeof(*data)); + data = memremap(pa_data, sizeof(*data), MEMREMAP_WB); if (!data) return -ENOMEM; pa_data = data->next; - iounmap(data); + memunmap(data); i++; } return -EINVAL; @@ -97,17 +97,17 @@ static int __init get_setup_data_size(int nr, size_t *size) u64 pa_data = boot_params.hdr.setup_data; while (pa_data) { - data = ioremap_cache(pa_data, sizeof(*data)); + data = memremap(pa_data, sizeof(*data), MEMREMAP_WB); if (!data) return -ENOMEM; if (nr == i) { *size = data->len; - iounmap(data); + memunmap(data); return 0; } pa_data = data->next; - iounmap(data); + memunmap(data); i++; } return -EINVAL; @@ -127,12 +127,12 @@ static ssize_t type_show(struct kobject *kobj, ret = get_setup_data_paddr(nr, &paddr); if (ret) return ret; - data = ioremap_cache(paddr, sizeof(*data)); + data = memremap(paddr, sizeof(*data), MEMREMAP_WB); if (!data) return -ENOMEM; ret = sprintf(buf, "0x%x\n", data->type); - iounmap(data); + memunmap(data); return ret; } @@ -154,7 +154,7 @@ static ssize_t setup_data_data_read(struct file *fp, ret = get_setup_data_paddr(nr, &paddr); if (ret) return ret; - data = ioremap_cache(paddr, sizeof(*data)); + data = memremap(paddr, sizeof(*data), MEMREMAP_WB); if (!data) return -ENOMEM; @@ -170,15 +170,15 @@ static ssize_t setup_data_data_read(struct file *fp, goto out; ret = count; - p = ioremap_cache(paddr + sizeof(*data), data->len); + p = memremap(paddr + sizeof(*data), data->len, MEMREMAP_WB); if (!p) { ret = -ENOMEM; goto out; } memcpy(buf, p + off, count); - iounmap(p); + memunmap(p); out: - iounmap(data); + memunmap(data); return ret; } @@ -202,7 +202,7 @@ static struct bin_attribute *setup_data_data_attrs[] = { NULL, }; -static struct attribute_group setup_data_attr_group = { +static const struct attribute_group setup_data_attr_group = { .attrs = setup_data_type_attrs, .bin_attrs = setup_data_data_attrs, }; @@ -250,13 +250,13 @@ static int __init get_setup_data_total_num(u64 pa_data, int *nr) *nr = 0; while (pa_data) { *nr += 1; - data = ioremap_cache(pa_data, sizeof(*data)); + data = memremap(pa_data, sizeof(*data), MEMREMAP_WB); if (!data) { ret = -ENOMEM; goto out; } pa_data = data->next; - iounmap(data); + memunmap(data); } out: diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 71c17a5be983..874827b0d7ca 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -151,6 +151,8 @@ void kvm_async_pf_task_wait(u32 token) if (hlist_unhashed(&n.link)) break; + rcu_irq_exit(); + if (!n.halted) { local_irq_enable(); schedule(); @@ -159,11 +161,11 @@ void kvm_async_pf_task_wait(u32 token) /* * We cannot reschedule. So halt. */ - rcu_irq_exit(); native_safe_halt(); local_irq_disable(); - rcu_irq_enter(); } + + rcu_irq_enter(); } if (!n.halted) finish_swait(&n.wq, &wait); @@ -261,7 +263,7 @@ do_async_page_fault(struct pt_regs *regs, unsigned long error_code) switch (kvm_read_and_reset_pf_reason()) { default: - trace_do_page_fault(regs, error_code); + do_page_fault(regs, error_code); break; case KVM_PV_REASON_PAGE_NOT_PRESENT: /* page is swapped out by the host. */ @@ -453,7 +455,7 @@ static int kvm_cpu_down_prepare(unsigned int cpu) static void __init kvm_apf_trap_init(void) { - set_intr_gate(14, async_page_fault); + update_intr_gate(X86_TRAP_PF, async_page_fault); } void __init kvm_guest_init(void) diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index a870910c8565..f0e64db18ac8 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -21,6 +21,25 @@ #include <asm/mmu_context.h> #include <asm/syscalls.h> +static void refresh_ldt_segments(void) +{ +#ifdef CONFIG_X86_64 + unsigned short sel; + + /* + * Make sure that the cached DS and ES descriptors match the updated + * LDT. + */ + savesegment(ds, sel); + if ((sel & SEGMENT_TI_MASK) == SEGMENT_LDT) + loadsegment(ds, sel); + + savesegment(es, sel); + if ((sel & SEGMENT_TI_MASK) == SEGMENT_LDT) + loadsegment(es, sel); +#endif +} + /* context.lock is held for us, so we don't need any locking. */ static void flush_ldt(void *__mm) { @@ -32,6 +51,8 @@ static void flush_ldt(void *__mm) pc = &mm->context; set_ldt(pc->ldt->entries, pc->ldt->nr_entries); + + refresh_ldt_segments(); } /* The caller must call finalize_ldt_struct on the result. LDT starts zeroed. */ diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index 8c53c5d7a1bc..00bc751c861c 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -26,18 +26,6 @@ #include <asm/set_memory.h> #include <asm/debugreg.h> -static void set_idt(void *newidt, __u16 limit) -{ - struct desc_ptr curidt; - - /* ia32 supports unaliged loads & stores */ - curidt.size = limit; - curidt.address = (unsigned long)newidt; - - load_idt(&curidt); -} - - static void set_gdt(void *newgdt, __u16 limit) { struct desc_ptr curgdt; @@ -245,7 +233,7 @@ void machine_kexec(struct kimage *image) * If you want to load them you must set up your own idt & gdt. */ set_gdt(phys_to_virt(0), 0); - set_idt(phys_to_virt(0), 0); + idt_invalidate(phys_to_virt(0)); /* now call it */ image->start = relocate_kernel_ptr((unsigned long)image->head, diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index cb0a30473c23..1f790cf9d38f 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -87,7 +87,7 @@ static int init_transition_pgtable(struct kimage *image, pgd_t *pgd) set_pmd(pmd, __pmd(__pa(pte) | _KERNPG_TABLE)); } pte = pte_offset_kernel(pmd, vaddr); - set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, PAGE_KERNEL_EXEC)); + set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, PAGE_KERNEL_EXEC_NOENC)); return 0; err: free_transition_pgtable(image); @@ -115,6 +115,7 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable) .alloc_pgt_page = alloc_pgt_page, .context = image, .page_flag = __PAGE_KERNEL_LARGE_EXEC, + .kernpg_flag = _KERNPG_TABLE_NOENC, }; unsigned long mstart, mend; pgd_t *level4p; @@ -334,7 +335,8 @@ void machine_kexec(struct kimage *image) image->start = relocate_kernel((unsigned long)image->head, (unsigned long)page_list, image->start, - image->preserve_context); + image->preserve_context, + sme_active()); #ifdef CONFIG_KEXEC_JUMP if (image->preserve_context) @@ -602,3 +604,22 @@ void arch_kexec_unprotect_crashkres(void) { kexec_mark_crashkres(false); } + +int arch_kexec_post_alloc_pages(void *vaddr, unsigned int pages, gfp_t gfp) +{ + /* + * If SME is active we need to be sure that kexec pages are + * not encrypted because when we boot to the new kernel the + * pages won't be accessed encrypted (initially). + */ + return set_memory_decrypted((unsigned long)vaddr, pages); +} + +void arch_kexec_pre_free_pages(void *vaddr, unsigned int pages) +{ + /* + * If SME is active we need to reset the pages back to being + * an encrypted mapping before freeing them. + */ + set_memory_encrypted((unsigned long)vaddr, pages); +} diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index f67bd3205df7..62e7d70aadd5 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -35,6 +35,7 @@ #include <asm/page.h> #include <asm/pgtable.h> #include <asm/setup.h> +#include <asm/unwind.h> #if 0 #define DEBUGP(fmt, ...) \ @@ -213,7 +214,7 @@ int module_finalize(const Elf_Ehdr *hdr, struct module *me) { const Elf_Shdr *s, *text = NULL, *alt = NULL, *locks = NULL, - *para = NULL; + *para = NULL, *orc = NULL, *orc_ip = NULL; char *secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) { @@ -225,6 +226,10 @@ int module_finalize(const Elf_Ehdr *hdr, locks = s; if (!strcmp(".parainstructions", secstrings + s->sh_name)) para = s; + if (!strcmp(".orc_unwind", secstrings + s->sh_name)) + orc = s; + if (!strcmp(".orc_unwind_ip", secstrings + s->sh_name)) + orc_ip = s; } if (alt) { @@ -248,6 +253,10 @@ int module_finalize(const Elf_Ehdr *hdr, /* make jump label nops */ jump_label_apply_nops(me); + if (orc && orc_ip) + unwind_module_init(me, (void *)orc_ip->sh_addr, orc_ip->sh_size, + (void *)orc->sh_addr, orc->sh_size); + return 0; } diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 0d904d759ff1..5cbb3177ed17 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -429,16 +429,16 @@ static inline void __init construct_default_ISA_mptable(int mpc_default_type) } } -static struct mpf_intel *mpf_found; +static unsigned long mpf_base; static unsigned long __init get_mpc_size(unsigned long physptr) { struct mpc_table *mpc; unsigned long size; - mpc = early_ioremap(physptr, PAGE_SIZE); + mpc = early_memremap(physptr, PAGE_SIZE); size = mpc->length; - early_iounmap(mpc, PAGE_SIZE); + early_memunmap(mpc, PAGE_SIZE); apic_printk(APIC_VERBOSE, " mpc: %lx-%lx\n", physptr, physptr + size); return size; @@ -450,7 +450,8 @@ static int __init check_physptr(struct mpf_intel *mpf, unsigned int early) unsigned long size; size = get_mpc_size(mpf->physptr); - mpc = early_ioremap(mpf->physptr, size); + mpc = early_memremap(mpf->physptr, size); + /* * Read the physical hardware table. Anything here will * override the defaults. @@ -461,10 +462,10 @@ static int __init check_physptr(struct mpf_intel *mpf, unsigned int early) #endif pr_err("BIOS bug, MP table errors detected!...\n"); pr_cont("... disabling SMP support. (tell your hw vendor)\n"); - early_iounmap(mpc, size); + early_memunmap(mpc, size); return -1; } - early_iounmap(mpc, size); + early_memunmap(mpc, size); if (early) return -1; @@ -497,12 +498,12 @@ static int __init check_physptr(struct mpf_intel *mpf, unsigned int early) */ void __init default_get_smp_config(unsigned int early) { - struct mpf_intel *mpf = mpf_found; + struct mpf_intel *mpf; if (!smp_found_config) return; - if (!mpf) + if (!mpf_base) return; if (acpi_lapic && early) @@ -515,6 +516,12 @@ void __init default_get_smp_config(unsigned int early) if (acpi_lapic && acpi_ioapic) return; + mpf = early_memremap(mpf_base, sizeof(*mpf)); + if (!mpf) { + pr_err("MPTABLE: error mapping MP table\n"); + return; + } + pr_info("Intel MultiProcessor Specification v1.%d\n", mpf->specification); #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_32) @@ -529,7 +536,7 @@ void __init default_get_smp_config(unsigned int early) /* * Now see if we need to read further. */ - if (mpf->feature1 != 0) { + if (mpf->feature1) { if (early) { /* * local APIC has default address @@ -542,8 +549,10 @@ void __init default_get_smp_config(unsigned int early) construct_default_ISA_mptable(mpf->feature1); } else if (mpf->physptr) { - if (check_physptr(mpf, early)) + if (check_physptr(mpf, early)) { + early_memunmap(mpf, sizeof(*mpf)); return; + } } else BUG(); @@ -552,6 +561,8 @@ void __init default_get_smp_config(unsigned int early) /* * Only use the first configuration found. */ + + early_memunmap(mpf, sizeof(*mpf)); } static void __init smp_reserve_memory(struct mpf_intel *mpf) @@ -561,15 +572,16 @@ static void __init smp_reserve_memory(struct mpf_intel *mpf) static int __init smp_scan_config(unsigned long base, unsigned long length) { - unsigned int *bp = phys_to_virt(base); + unsigned int *bp; struct mpf_intel *mpf; - unsigned long mem; + int ret = 0; apic_printk(APIC_VERBOSE, "Scan for SMP in [mem %#010lx-%#010lx]\n", base, base + length - 1); BUILD_BUG_ON(sizeof(*mpf) != 16); while (length > 0) { + bp = early_memremap(base, length); mpf = (struct mpf_intel *)bp; if ((*bp == SMP_MAGIC_IDENT) && (mpf->length == 1) && @@ -579,24 +591,26 @@ static int __init smp_scan_config(unsigned long base, unsigned long length) #ifdef CONFIG_X86_LOCAL_APIC smp_found_config = 1; #endif - mpf_found = mpf; + mpf_base = base; - pr_info("found SMP MP-table at [mem %#010llx-%#010llx] mapped at [%p]\n", - (unsigned long long) virt_to_phys(mpf), - (unsigned long long) virt_to_phys(mpf) + - sizeof(*mpf) - 1, mpf); + pr_info("found SMP MP-table at [mem %#010lx-%#010lx] mapped at [%p]\n", + base, base + sizeof(*mpf) - 1, mpf); - mem = virt_to_phys(mpf); - memblock_reserve(mem, sizeof(*mpf)); + memblock_reserve(base, sizeof(*mpf)); if (mpf->physptr) smp_reserve_memory(mpf); - return 1; + ret = 1; } - bp += 4; + early_memunmap(bp, length); + + if (ret) + break; + + base += 16; length -= 16; } - return 0; + return ret; } void __init default_find_smp_config(void) @@ -838,29 +852,40 @@ static int __init update_mp_table(void) char oem[10]; struct mpf_intel *mpf; struct mpc_table *mpc, *mpc_new; + unsigned long size; if (!enable_update_mptable) return 0; - mpf = mpf_found; - if (!mpf) + if (!mpf_base) return 0; + mpf = early_memremap(mpf_base, sizeof(*mpf)); + if (!mpf) { + pr_err("MPTABLE: mpf early_memremap() failed\n"); + return 0; + } + /* * Now see if we need to go further. */ - if (mpf->feature1 != 0) - return 0; + if (mpf->feature1) + goto do_unmap_mpf; if (!mpf->physptr) - return 0; + goto do_unmap_mpf; - mpc = phys_to_virt(mpf->physptr); + size = get_mpc_size(mpf->physptr); + mpc = early_memremap(mpf->physptr, size); + if (!mpc) { + pr_err("MPTABLE: mpc early_memremap() failed\n"); + goto do_unmap_mpf; + } if (!smp_check_mpc(mpc, oem, str)) - return 0; + goto do_unmap_mpc; - pr_info("mpf: %llx\n", (u64)virt_to_phys(mpf)); + pr_info("mpf: %llx\n", (u64)mpf_base); pr_info("physptr: %x\n", mpf->physptr); if (mpc_new_phys && mpc->length > mpc_new_length) { @@ -878,21 +903,32 @@ static int __init update_mp_table(void) new = mpf_checksum((unsigned char *)mpc, mpc->length); if (old == new) { pr_info("mpc is readonly, please try alloc_mptable instead\n"); - return 0; + goto do_unmap_mpc; } pr_info("use in-position replacing\n"); } else { + mpc_new = early_memremap(mpc_new_phys, mpc_new_length); + if (!mpc_new) { + pr_err("MPTABLE: new mpc early_memremap() failed\n"); + goto do_unmap_mpc; + } mpf->physptr = mpc_new_phys; - mpc_new = phys_to_virt(mpc_new_phys); memcpy(mpc_new, mpc, mpc->length); + early_memunmap(mpc, size); mpc = mpc_new; + size = mpc_new_length; /* check if we can modify that */ if (mpc_new_phys - mpf->physptr) { struct mpf_intel *mpf_new; /* steal 16 bytes from [0, 1k) */ + mpf_new = early_memremap(0x400 - 16, sizeof(*mpf_new)); + if (!mpf_new) { + pr_err("MPTABLE: new mpf early_memremap() failed\n"); + goto do_unmap_mpc; + } pr_info("mpf new: %x\n", 0x400 - 16); - mpf_new = phys_to_virt(0x400 - 16); memcpy(mpf_new, mpf, 16); + early_memunmap(mpf, sizeof(*mpf)); mpf = mpf_new; mpf->physptr = mpc_new_phys; } @@ -909,6 +945,12 @@ static int __init update_mp_table(void) */ replace_intsrc_all(mpc, mpc_new_phys, mpc_new_length); +do_unmap_mpc: + early_memunmap(mpc, size); + +do_unmap_mpf: + early_memunmap(mpf, sizeof(*mpf)); + return 0; } diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 446c8aa09b9b..35aafc95e4b8 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -39,26 +39,26 @@ #include <trace/events/nmi.h> struct nmi_desc { - spinlock_t lock; + raw_spinlock_t lock; struct list_head head; }; static struct nmi_desc nmi_desc[NMI_MAX] = { { - .lock = __SPIN_LOCK_UNLOCKED(&nmi_desc[0].lock), + .lock = __RAW_SPIN_LOCK_UNLOCKED(&nmi_desc[0].lock), .head = LIST_HEAD_INIT(nmi_desc[0].head), }, { - .lock = __SPIN_LOCK_UNLOCKED(&nmi_desc[1].lock), + .lock = __RAW_SPIN_LOCK_UNLOCKED(&nmi_desc[1].lock), .head = LIST_HEAD_INIT(nmi_desc[1].head), }, { - .lock = __SPIN_LOCK_UNLOCKED(&nmi_desc[2].lock), + .lock = __RAW_SPIN_LOCK_UNLOCKED(&nmi_desc[2].lock), .head = LIST_HEAD_INIT(nmi_desc[2].head), }, { - .lock = __SPIN_LOCK_UNLOCKED(&nmi_desc[3].lock), + .lock = __RAW_SPIN_LOCK_UNLOCKED(&nmi_desc[3].lock), .head = LIST_HEAD_INIT(nmi_desc[3].head), }, @@ -163,7 +163,7 @@ int __register_nmi_handler(unsigned int type, struct nmiaction *action) init_irq_work(&action->irq_work, nmi_max_handler); - spin_lock_irqsave(&desc->lock, flags); + raw_spin_lock_irqsave(&desc->lock, flags); /* * Indicate if there are multiple registrations on the @@ -181,7 +181,7 @@ int __register_nmi_handler(unsigned int type, struct nmiaction *action) else list_add_tail_rcu(&action->list, &desc->head); - spin_unlock_irqrestore(&desc->lock, flags); + raw_spin_unlock_irqrestore(&desc->lock, flags); return 0; } EXPORT_SYMBOL(__register_nmi_handler); @@ -192,7 +192,7 @@ void unregister_nmi_handler(unsigned int type, const char *name) struct nmiaction *n; unsigned long flags; - spin_lock_irqsave(&desc->lock, flags); + raw_spin_lock_irqsave(&desc->lock, flags); list_for_each_entry_rcu(n, &desc->head, list) { /* @@ -207,7 +207,7 @@ void unregister_nmi_handler(unsigned int type, const char *name) } } - spin_unlock_irqrestore(&desc->lock, flags); + raw_spin_unlock_irqrestore(&desc->lock, flags); synchronize_rcu(); } EXPORT_SYMBOL_GPL(unregister_nmi_handler); diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index bc0a849589bb..a14df9eecfed 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -319,9 +319,6 @@ __visible struct pv_irq_ops pv_irq_ops = { .irq_enable = __PV_IS_CALLEE_SAVE(native_irq_enable), .safe_halt = native_safe_halt, .halt = native_halt, -#ifdef CONFIG_X86_64 - .adjust_exception_frame = paravirt_nop, -#endif }; __visible struct pv_cpu_ops pv_cpu_ops = { diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index 5e16d3f29594..0accc2404b92 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -93,9 +93,12 @@ again: if (gfpflags_allow_blocking(flag)) { page = dma_alloc_from_contiguous(dev, count, get_order(size), flag); - if (page && page_to_phys(page) + size > dma_mask) { - dma_release_from_contiguous(dev, page, count); - page = NULL; + if (page) { + addr = phys_to_dma(dev, page_to_phys(page)); + if (addr + size > dma_mask) { + dma_release_from_contiguous(dev, page, count); + page = NULL; + } } } /* fallback */ @@ -104,7 +107,7 @@ again: if (!page) return NULL; - addr = page_to_phys(page); + addr = phys_to_dma(dev, page_to_phys(page)); if (addr + size > dma_mask) { __free_pages(page, get_order(size)); diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c index a6d404087fe3..4fc3cb60ea11 100644 --- a/arch/x86/kernel/pci-nommu.c +++ b/arch/x86/kernel/pci-nommu.c @@ -32,7 +32,7 @@ static dma_addr_t nommu_map_page(struct device *dev, struct page *page, enum dma_data_direction dir, unsigned long attrs) { - dma_addr_t bus = page_to_phys(page) + offset; + dma_addr_t bus = phys_to_dma(dev, page_to_phys(page)) + offset; WARN_ON(size == 0); if (!check_addr("map_single", dev, bus, size)) return NOMMU_MAPPING_ERROR; diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c index 1e23577e17cf..677077510e30 100644 --- a/arch/x86/kernel/pci-swiotlb.c +++ b/arch/x86/kernel/pci-swiotlb.c @@ -6,12 +6,14 @@ #include <linux/swiotlb.h> #include <linux/bootmem.h> #include <linux/dma-mapping.h> +#include <linux/mem_encrypt.h> #include <asm/iommu.h> #include <asm/swiotlb.h> #include <asm/dma.h> #include <asm/xen/swiotlb-xen.h> #include <asm/iommu_table.h> + int swiotlb __read_mostly; void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size, @@ -79,8 +81,8 @@ IOMMU_INIT_FINISH(pci_swiotlb_detect_override, pci_swiotlb_late_init); /* - * if 4GB or more detected (and iommu=off not set) return 1 - * and set swiotlb to 1. + * If 4GB or more detected (and iommu=off not set) or if SME is active + * then set swiotlb to 1 and return 1. */ int __init pci_swiotlb_detect_4gb(void) { @@ -89,6 +91,15 @@ int __init pci_swiotlb_detect_4gb(void) if (!no_iommu && max_possible_pfn > MAX_DMA32_PFN) swiotlb = 1; #endif + + /* + * If SME is active then swiotlb will be set to 1 so that bounce + * buffers are allocated and used for devices that do not support + * the addressing range required for the encryption mask. + */ + if (sme_active()) + swiotlb = 1; + return swiotlb; } IOMMU_INIT(pci_swiotlb_detect_4gb, diff --git a/arch/x86/kernel/platform-quirks.c b/arch/x86/kernel/platform-quirks.c index 91271122f0df..502a77d0adb0 100644 --- a/arch/x86/kernel/platform-quirks.c +++ b/arch/x86/kernel/platform-quirks.c @@ -16,7 +16,6 @@ void __init x86_early_init_platform_quirks(void) x86_platform.legacy.reserve_bios_regions = 1; break; case X86_SUBARCH_XEN: - case X86_SUBARCH_LGUEST: x86_platform.legacy.devices.pnpbios = 0; x86_platform.legacy.rtc = 0; break; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 3ca198080ea9..bd6b85fac666 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -355,6 +355,7 @@ bool xen_set_default_idle(void) return ret; } #endif + void stop_this_cpu(void *dummy) { local_irq_disable(); @@ -365,8 +366,20 @@ void stop_this_cpu(void *dummy) disable_local_APIC(); mcheck_cpu_clear(this_cpu_ptr(&cpu_info)); - for (;;) - halt(); + for (;;) { + /* + * Use wbinvd followed by hlt to stop the processor. This + * provides support for kexec on a processor that supports + * SME. With kexec, going from SME inactive to SME active + * requires clearing cache entries so that addresses without + * the encryption bit set don't corrupt the same physical + * address that has the encryption bit set when caches are + * flushed. To achieve this a wbinvd is performed followed by + * a hlt. Even if the processor is not in the kexec/SME + * scenario this only adds a wbinvd to a halting processor. + */ + asm volatile("wbinvd; hlt" : : : "memory"); + } } /* diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index c6d6dc5f8bb2..11966251cd42 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -56,7 +56,7 @@ #include <asm/debugreg.h> #include <asm/switch_to.h> #include <asm/vm86.h> -#include <asm/intel_rdt.h> +#include <asm/intel_rdt_sched.h> #include <asm/proto.h> void __show_regs(struct pt_regs *regs, int all) @@ -68,7 +68,7 @@ void __show_regs(struct pt_regs *regs, int all) if (user_mode(regs)) { sp = regs->sp; - ss = regs->ss & 0xffff; + ss = regs->ss; gs = get_user_gs(regs); } else { sp = kernel_stack_pointer(regs); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index c3169be4c596..302e7b2572d1 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -52,7 +52,7 @@ #include <asm/switch_to.h> #include <asm/xen/hypervisor.h> #include <asm/vdso.h> -#include <asm/intel_rdt.h> +#include <asm/intel_rdt_sched.h> #include <asm/unistd.h> #ifdef CONFIG_IA32_EMULATION /* Not included via unistd.h */ @@ -69,8 +69,7 @@ void __show_regs(struct pt_regs *regs, int all) unsigned int fsindex, gsindex; unsigned int ds, cs, es; - printk(KERN_DEFAULT "RIP: %04lx:%pS\n", regs->cs & 0xffff, - (void *)regs->ip); + printk(KERN_DEFAULT "RIP: %04lx:%pS\n", regs->cs, (void *)regs->ip); printk(KERN_DEFAULT "RSP: %04lx:%016lx EFLAGS: %08lx", regs->ss, regs->sp, regs->flags); if (regs->orig_ax != -1) @@ -149,6 +148,123 @@ void release_thread(struct task_struct *dead_task) } } +enum which_selector { + FS, + GS +}; + +/* + * Saves the FS or GS base for an outgoing thread if FSGSBASE extensions are + * not available. The goal is to be reasonably fast on non-FSGSBASE systems. + * It's forcibly inlined because it'll generate better code and this function + * is hot. + */ +static __always_inline void save_base_legacy(struct task_struct *prev_p, + unsigned short selector, + enum which_selector which) +{ + if (likely(selector == 0)) { + /* + * On Intel (without X86_BUG_NULL_SEG), the segment base could + * be the pre-existing saved base or it could be zero. On AMD + * (with X86_BUG_NULL_SEG), the segment base could be almost + * anything. + * + * This branch is very hot (it's hit twice on almost every + * context switch between 64-bit programs), and avoiding + * the RDMSR helps a lot, so we just assume that whatever + * value is already saved is correct. This matches historical + * Linux behavior, so it won't break existing applications. + * + * To avoid leaking state, on non-X86_BUG_NULL_SEG CPUs, if we + * report that the base is zero, it needs to actually be zero: + * see the corresponding logic in load_seg_legacy. + */ + } else { + /* + * If the selector is 1, 2, or 3, then the base is zero on + * !X86_BUG_NULL_SEG CPUs and could be anything on + * X86_BUG_NULL_SEG CPUs. In the latter case, Linux + * has never attempted to preserve the base across context + * switches. + * + * If selector > 3, then it refers to a real segment, and + * saving the base isn't necessary. + */ + if (which == FS) + prev_p->thread.fsbase = 0; + else + prev_p->thread.gsbase = 0; + } +} + +static __always_inline void save_fsgs(struct task_struct *task) +{ + savesegment(fs, task->thread.fsindex); + savesegment(gs, task->thread.gsindex); + save_base_legacy(task, task->thread.fsindex, FS); + save_base_legacy(task, task->thread.gsindex, GS); +} + +static __always_inline void loadseg(enum which_selector which, + unsigned short sel) +{ + if (which == FS) + loadsegment(fs, sel); + else + load_gs_index(sel); +} + +static __always_inline void load_seg_legacy(unsigned short prev_index, + unsigned long prev_base, + unsigned short next_index, + unsigned long next_base, + enum which_selector which) +{ + if (likely(next_index <= 3)) { + /* + * The next task is using 64-bit TLS, is not using this + * segment at all, or is having fun with arcane CPU features. + */ + if (next_base == 0) { + /* + * Nasty case: on AMD CPUs, we need to forcibly zero + * the base. + */ + if (static_cpu_has_bug(X86_BUG_NULL_SEG)) { + loadseg(which, __USER_DS); + loadseg(which, next_index); + } else { + /* + * We could try to exhaustively detect cases + * under which we can skip the segment load, + * but there's really only one case that matters + * for performance: if both the previous and + * next states are fully zeroed, we can skip + * the load. + * + * (This assumes that prev_base == 0 has no + * false positives. This is the case on + * Intel-style CPUs.) + */ + if (likely(prev_index | next_index | prev_base)) + loadseg(which, next_index); + } + } else { + if (prev_index != next_index) + loadseg(which, next_index); + wrmsrl(which == FS ? MSR_FS_BASE : MSR_KERNEL_GS_BASE, + next_base); + } + } else { + /* + * The next task is using a real segment. Loading the selector + * is sufficient. + */ + loadseg(which, next_index); + } +} + int copy_thread_tls(unsigned long clone_flags, unsigned long sp, unsigned long arg, struct task_struct *p, unsigned long tls) { @@ -229,10 +345,19 @@ start_thread_common(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp, unsigned int _cs, unsigned int _ss, unsigned int _ds) { + WARN_ON_ONCE(regs != current_pt_regs()); + + if (static_cpu_has(X86_BUG_NULL_SEG)) { + /* Loading zero below won't clear the base. */ + loadsegment(fs, __USER_DS); + load_gs_index(__USER_DS); + } + loadsegment(fs, 0); loadsegment(es, _ds); loadsegment(ds, _ds); load_gs_index(0); + regs->ip = new_ip; regs->sp = new_sp; regs->cs = _cs; @@ -277,7 +402,9 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) struct fpu *next_fpu = &next->fpu; int cpu = smp_processor_id(); struct tss_struct *tss = &per_cpu(cpu_tss, cpu); - unsigned prev_fsindex, prev_gsindex; + + WARN_ON_ONCE(IS_ENABLED(CONFIG_DEBUG_ENTRY) && + this_cpu_read(irq_count) != -1); switch_fpu_prepare(prev_fpu, cpu); @@ -286,8 +413,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) * * (e.g. xen_load_tls()) */ - savesegment(fs, prev_fsindex); - savesegment(gs, prev_gsindex); + save_fsgs(prev_p); /* * Load TLS before restoring any segments so that segment loads @@ -326,108 +452,10 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) if (unlikely(next->ds | prev->ds)) loadsegment(ds, next->ds); - /* - * Switch FS and GS. - * - * These are even more complicated than DS and ES: they have - * 64-bit bases are that controlled by arch_prctl. The bases - * don't necessarily match the selectors, as user code can do - * any number of things to cause them to be inconsistent. - * - * We don't promise to preserve the bases if the selectors are - * nonzero. We also don't promise to preserve the base if the - * selector is zero and the base doesn't match whatever was - * most recently passed to ARCH_SET_FS/GS. (If/when the - * FSGSBASE instructions are enabled, we'll need to offer - * stronger guarantees.) - * - * As an invariant, - * (fsbase != 0 && fsindex != 0) || (gsbase != 0 && gsindex != 0) is - * impossible. - */ - if (next->fsindex) { - /* Loading a nonzero value into FS sets the index and base. */ - loadsegment(fs, next->fsindex); - } else { - if (next->fsbase) { - /* Next index is zero but next base is nonzero. */ - if (prev_fsindex) - loadsegment(fs, 0); - wrmsrl(MSR_FS_BASE, next->fsbase); - } else { - /* Next base and index are both zero. */ - if (static_cpu_has_bug(X86_BUG_NULL_SEG)) { - /* - * We don't know the previous base and can't - * find out without RDMSR. Forcibly clear it. - */ - loadsegment(fs, __USER_DS); - loadsegment(fs, 0); - } else { - /* - * If the previous index is zero and ARCH_SET_FS - * didn't change the base, then the base is - * also zero and we don't need to do anything. - */ - if (prev->fsbase || prev_fsindex) - loadsegment(fs, 0); - } - } - } - /* - * Save the old state and preserve the invariant. - * NB: if prev_fsindex == 0, then we can't reliably learn the base - * without RDMSR because Intel user code can zero it without telling - * us and AMD user code can program any 32-bit value without telling - * us. - */ - if (prev_fsindex) - prev->fsbase = 0; - prev->fsindex = prev_fsindex; - - if (next->gsindex) { - /* Loading a nonzero value into GS sets the index and base. */ - load_gs_index(next->gsindex); - } else { - if (next->gsbase) { - /* Next index is zero but next base is nonzero. */ - if (prev_gsindex) - load_gs_index(0); - wrmsrl(MSR_KERNEL_GS_BASE, next->gsbase); - } else { - /* Next base and index are both zero. */ - if (static_cpu_has_bug(X86_BUG_NULL_SEG)) { - /* - * We don't know the previous base and can't - * find out without RDMSR. Forcibly clear it. - * - * This contains a pointless SWAPGS pair. - * Fixing it would involve an explicit check - * for Xen or a new pvop. - */ - load_gs_index(__USER_DS); - load_gs_index(0); - } else { - /* - * If the previous index is zero and ARCH_SET_GS - * didn't change the base, then the base is - * also zero and we don't need to do anything. - */ - if (prev->gsbase || prev_gsindex) - load_gs_index(0); - } - } - } - /* - * Save the old state and preserve the invariant. - * NB: if prev_gsindex == 0, then we can't reliably learn the base - * without RDMSR because Intel user code can zero it without telling - * us and AMD user code can program any 32-bit value without telling - * us. - */ - if (prev_gsindex) - prev->gsbase = 0; - prev->gsindex = prev_gsindex; + load_seg_legacy(prev->fsindex, prev->fsbase, + next->fsindex, next->fsbase, FS); + load_seg_legacy(prev->gsindex, prev->gsbase, + next->gsindex, next->gsbase, GS); switch_fpu_finish(next_fpu, cpu); diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 67393fc88353..54984b142641 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -38,8 +38,6 @@ void (*pm_power_off)(void); EXPORT_SYMBOL(pm_power_off); -static const struct desc_ptr no_idt = {}; - /* * This is set if we need to go through the 'emergency' path. * When machine_emergency_restart() is called, we may be on @@ -471,12 +469,12 @@ static int __init reboot_init(void) /* * The DMI quirks table takes precedence. If no quirks entry - * matches and the ACPI Hardware Reduced bit is set, force EFI - * reboot. + * matches and the ACPI Hardware Reduced bit is set and EFI + * runtime services are enabled, force EFI reboot. */ rv = dmi_check_system(reboot_dmi_table); - if (!rv && efi_reboot_required()) + if (!rv && efi_reboot_required() && !efi_runtime_disabled()) reboot_type = BOOT_EFI; return 0; @@ -638,7 +636,7 @@ static void native_machine_emergency_restart(void) break; case BOOT_TRIPLE: - load_idt(&no_idt); + idt_invalidate(NULL); __asm__ __volatile__("int3"); /* We're probably dead after this, but... */ diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S index 98111b38ebfd..307d3bac5f04 100644 --- a/arch/x86/kernel/relocate_kernel_64.S +++ b/arch/x86/kernel/relocate_kernel_64.S @@ -47,6 +47,7 @@ relocate_kernel: * %rsi page_list * %rdx start address * %rcx preserve_context + * %r8 sme_active */ /* Save the CPU context, used for jumping back */ @@ -71,6 +72,9 @@ relocate_kernel: pushq $0 popfq + /* Save SME active flag */ + movq %r8, %r12 + /* * get physical address of control page now * this is impossible after page table switch @@ -132,6 +136,16 @@ identity_mapped: /* Flush the TLB (needed?) */ movq %r9, %cr3 + /* + * If SME is active, there could be old encrypted cache line + * entries that will conflict with the now unencrypted memory + * used by kexec. Flush the caches before copying the kernel. + */ + testq %r12, %r12 + jz 1f + wbinvd +1: + movq %rcx, %r11 call swap_pages diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 3486d0498800..9cc16a841745 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -69,6 +69,7 @@ #include <linux/crash_dump.h> #include <linux/tboot.h> #include <linux/jiffies.h> +#include <linux/mem_encrypt.h> #include <linux/usb/xhci-dbgp.h> #include <video/edid.h> @@ -115,6 +116,7 @@ #include <asm/microcode.h> #include <asm/mmu_context.h> #include <asm/kaslr.h> +#include <asm/unwind.h> /* * max_low_pfn_mapped: highest direct mapped pfn under 4GB @@ -374,6 +376,14 @@ static void __init reserve_initrd(void) !ramdisk_image || !ramdisk_size) return; /* No initrd provided by bootloader */ + /* + * If SME is active, this memory will be marked encrypted by the + * kernel when it is accessed (including relocation). However, the + * ramdisk image was loaded decrypted by the bootloader, so make + * sure that it is encrypted before accessing it. + */ + sme_early_encrypt(ramdisk_image, ramdisk_end - ramdisk_image); + initrd_start = 0; mapped_size = memblock_mem_size(max_pfn_mapped); @@ -890,7 +900,7 @@ void __init setup_arch(char **cmdline_p) */ olpc_ofw_detect(); - early_trap_init(); + idt_setup_early_traps(); early_cpu_init(); early_ioremap_init(); @@ -1161,7 +1171,7 @@ void __init setup_arch(char **cmdline_p) init_mem_mapping(); - early_trap_pf_init(); + idt_setup_early_pf(); /* * Update mmu_cr4_features (and, indirectly, trampoline_cr4_features) @@ -1310,6 +1320,8 @@ void __init setup_arch(char **cmdline_p) if (efi_enabled(EFI_BOOT)) efi_apply_memmap_quirks(); #endif + + unwind_init(); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 10edd1e69a68..6e8fcb6f7e1e 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -155,13 +155,10 @@ static void __init pcpup_populate_pte(unsigned long addr) static inline void setup_percpu_segment(int cpu) { #ifdef CONFIG_X86_32 - struct desc_struct gdt; + struct desc_struct d = GDT_ENTRY_INIT(0x8092, per_cpu_offset(cpu), + 0xFFFFF); - pack_descriptor(&gdt, per_cpu_offset(cpu), 0xFFFFF, - 0x2 | DESCTYPE_S, 0x8); - gdt.s = 1; - write_gdt_entry(get_cpu_gdt_rw(cpu), - GDT_ENTRY_PERCPU, &gdt, DESCTYPE_S); + write_gdt_entry(get_cpu_gdt_rw(cpu), GDT_ENTRY_PERCPU, &d, DESCTYPE_S); #endif } diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index cc30a74e4adb..e04442345fc0 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -256,7 +256,7 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, sp = current->sas_ss_sp + current->sas_ss_size; } else if (IS_ENABLED(CONFIG_X86_32) && !onsigstack && - (regs->ss & 0xffff) != __USER_DS && + regs->ss != __USER_DS && !(ka->sa.sa_flags & SA_RESTORER) && ka->sa.sa_restorer) { /* This is the legacy signal stack switching. */ diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index d798c0da451c..5c574dff4c1a 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -254,84 +254,45 @@ finish: } /* - * Reschedule call back. + * Reschedule call back. KVM uses this interrupt to force a cpu out of + * guest mode */ -static inline void __smp_reschedule_interrupt(void) -{ - inc_irq_stat(irq_resched_count); - scheduler_ipi(); -} - __visible void __irq_entry smp_reschedule_interrupt(struct pt_regs *regs) { ack_APIC_irq(); - __smp_reschedule_interrupt(); - /* - * KVM uses this interrupt to force a cpu out of guest mode - */ -} - -__visible void __irq_entry smp_trace_reschedule_interrupt(struct pt_regs *regs) -{ - /* - * Need to call irq_enter() before calling the trace point. - * __smp_reschedule_interrupt() calls irq_enter/exit() too (in - * scheduler_ipi(). This is OK, since those functions are allowed - * to nest. - */ - ipi_entering_ack_irq(); - trace_reschedule_entry(RESCHEDULE_VECTOR); - __smp_reschedule_interrupt(); - trace_reschedule_exit(RESCHEDULE_VECTOR); - exiting_irq(); - /* - * KVM uses this interrupt to force a cpu out of guest mode - */ -} + inc_irq_stat(irq_resched_count); -static inline void __smp_call_function_interrupt(void) -{ - generic_smp_call_function_interrupt(); - inc_irq_stat(irq_call_count); + if (trace_resched_ipi_enabled()) { + /* + * scheduler_ipi() might call irq_enter() as well, but + * nested calls are fine. + */ + irq_enter(); + trace_reschedule_entry(RESCHEDULE_VECTOR); + scheduler_ipi(); + trace_reschedule_exit(RESCHEDULE_VECTOR); + irq_exit(); + return; + } + scheduler_ipi(); } __visible void __irq_entry smp_call_function_interrupt(struct pt_regs *regs) { ipi_entering_ack_irq(); - __smp_call_function_interrupt(); - exiting_irq(); -} - -__visible void __irq_entry -smp_trace_call_function_interrupt(struct pt_regs *regs) -{ - ipi_entering_ack_irq(); trace_call_function_entry(CALL_FUNCTION_VECTOR); - __smp_call_function_interrupt(); - trace_call_function_exit(CALL_FUNCTION_VECTOR); - exiting_irq(); -} - -static inline void __smp_call_function_single_interrupt(void) -{ - generic_smp_call_function_single_interrupt(); inc_irq_stat(irq_call_count); -} - -__visible void __irq_entry -smp_call_function_single_interrupt(struct pt_regs *regs) -{ - ipi_entering_ack_irq(); - __smp_call_function_single_interrupt(); + generic_smp_call_function_interrupt(); + trace_call_function_exit(CALL_FUNCTION_VECTOR); exiting_irq(); } -__visible void __irq_entry -smp_trace_call_function_single_interrupt(struct pt_regs *regs) +__visible void __irq_entry smp_call_function_single_interrupt(struct pt_regs *r) { ipi_entering_ack_irq(); trace_call_function_single_entry(CALL_FUNCTION_SINGLE_VECTOR); - __smp_call_function_single_interrupt(); + inc_irq_stat(irq_call_count); + generic_smp_call_function_single_interrupt(); trace_call_function_single_exit(CALL_FUNCTION_SINGLE_VECTOR); exiting_irq(); } diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index b474c8de7fba..54b9e89d4d6b 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -971,7 +971,8 @@ void common_cpu_up(unsigned int cpu, struct task_struct *idle) * Returns zero if CPU booted OK, else error code from * ->wakeup_secondary_cpu. */ -static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) +static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle, + int *cpu0_nmi_registered) { volatile u32 *trampoline_status = (volatile u32 *) __va(real_mode_header->trampoline_status); @@ -979,7 +980,6 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) unsigned long start_ip = real_mode_header->trampoline_start; unsigned long boot_error = 0; - int cpu0_nmi_registered = 0; unsigned long timeout; idle->thread.sp = (unsigned long)task_pt_regs(idle); @@ -1035,7 +1035,7 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) boot_error = apic->wakeup_secondary_cpu(apicid, start_ip); else boot_error = wakeup_cpu_via_init_nmi(cpu, start_ip, apicid, - &cpu0_nmi_registered); + cpu0_nmi_registered); if (!boot_error) { /* @@ -1080,12 +1080,6 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) */ smpboot_restore_warm_reset_vector(); } - /* - * Clean up the nmi handler. Do this after the callin and callout sync - * to avoid impact of possible long unregister time. - */ - if (cpu0_nmi_registered) - unregister_nmi_handler(NMI_LOCAL, "wake_cpu0"); return boot_error; } @@ -1093,8 +1087,9 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) int native_cpu_up(unsigned int cpu, struct task_struct *tidle) { int apicid = apic->cpu_present_to_apicid(cpu); + int cpu0_nmi_registered = 0; unsigned long flags; - int err; + int err, ret = 0; WARN_ON(irqs_disabled()); @@ -1131,10 +1126,11 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle) common_cpu_up(cpu, tidle); - err = do_boot_cpu(apicid, cpu, tidle); + err = do_boot_cpu(apicid, cpu, tidle, &cpu0_nmi_registered); if (err) { pr_err("do_boot_cpu failed(%d) to wakeup CPU#%u\n", err, cpu); - return -EIO; + ret = -EIO; + goto unreg_nmi; } /* @@ -1150,7 +1146,15 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle) touch_nmi_watchdog(); } - return 0; +unreg_nmi: + /* + * Clean up the nmi handler. Do this after the callin and callout sync + * to avoid impact of possible long unregister time. + */ + if (cpu0_nmi_registered) + unregister_nmi_handler(NMI_LOCAL, "wake_cpu0"); + + return ret; } /** diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c index 5f25cfbd952e..5ee663836c08 100644 --- a/arch/x86/kernel/step.c +++ b/arch/x86/kernel/step.c @@ -13,7 +13,7 @@ unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *re unsigned long addr, seg; addr = regs->ip; - seg = regs->cs & 0xffff; + seg = regs->cs; if (v8086_mode(regs)) { addr = (addr & 0xffff) + (seg << 4); return addr; diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index 213ddf3e937d..73e4d28112f8 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -21,6 +21,7 @@ #include <asm/compat.h> #include <asm/ia32.h> #include <asm/syscalls.h> +#include <asm/mpx.h> /* * Align a virtual address to avoid aliasing in the I$ on AMD F15h. @@ -100,8 +101,8 @@ out: return error; } -static void find_start_end(unsigned long flags, unsigned long *begin, - unsigned long *end) +static void find_start_end(unsigned long addr, unsigned long flags, + unsigned long *begin, unsigned long *end) { if (!in_compat_syscall() && (flags & MAP_32BIT)) { /* This is usually used needed to map code in small @@ -120,7 +121,10 @@ static void find_start_end(unsigned long flags, unsigned long *begin, } *begin = get_mmap_base(1); - *end = in_compat_syscall() ? tasksize_32bit() : tasksize_64bit(); + if (in_compat_syscall()) + *end = task_size_32bit(); + else + *end = task_size_64bit(addr > DEFAULT_MAP_WINDOW); } unsigned long @@ -132,10 +136,14 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, struct vm_unmapped_area_info info; unsigned long begin, end; + addr = mpx_unmapped_area_check(addr, len, flags); + if (IS_ERR_VALUE(addr)) + return addr; + if (flags & MAP_FIXED) return addr; - find_start_end(flags, &begin, &end); + find_start_end(addr, flags, &begin, &end); if (len > end) return -ENOMEM; @@ -171,6 +179,10 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, unsigned long addr = addr0; struct vm_unmapped_area_info info; + addr = mpx_unmapped_area_check(addr, len, flags); + if (IS_ERR_VALUE(addr)) + return addr; + /* requested length too big for entire address space */ if (len > TASK_SIZE) return -ENOMEM; @@ -195,6 +207,16 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, info.length = len; info.low_limit = PAGE_SIZE; info.high_limit = get_mmap_base(0); + + /* + * If hint address is above DEFAULT_MAP_WINDOW, look for unmapped area + * in the full address space. + * + * !in_compat_syscall() check to avoid high addresses for x32. + */ + if (addr > DEFAULT_MAP_WINDOW && !in_compat_syscall()) + info.high_limit += TASK_SIZE_MAX - DEFAULT_MAP_WINDOW; + info.align_mask = 0; info.align_offset = pgoff << PAGE_SHIFT; if (filp) { diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c index dcd699baea1b..a106b9719c58 100644 --- a/arch/x86/kernel/tls.c +++ b/arch/x86/kernel/tls.c @@ -93,7 +93,7 @@ static void set_tls_desc(struct task_struct *p, int idx, while (n-- > 0) { if (LDT_empty(info) || LDT_zero(info)) { - desc->a = desc->b = 0; + memset(desc, 0, sizeof(*desc)); } else { fill_ldt(desc, info); diff --git a/arch/x86/kernel/tracepoint.c b/arch/x86/kernel/tracepoint.c index 15515132bf0d..c6636d1f60b9 100644 --- a/arch/x86/kernel/tracepoint.c +++ b/arch/x86/kernel/tracepoint.c @@ -4,57 +4,38 @@ * Copyright (C) 2013 Seiji Aguchi <seiji.aguchi@hds.com> * */ -#include <asm/hw_irq.h> -#include <asm/desc.h> +#include <linux/jump_label.h> #include <linux/atomic.h> -atomic_t trace_idt_ctr = ATOMIC_INIT(0); -struct desc_ptr trace_idt_descr = { NR_VECTORS * 16 - 1, - (unsigned long) trace_idt_table }; - -/* No need to be aligned, but done to keep all IDTs defined the same way. */ -gate_desc trace_idt_table[NR_VECTORS] __page_aligned_bss; +#include <asm/hw_irq.h> +#include <asm/desc.h> -static int trace_irq_vector_refcount; -static DEFINE_MUTEX(irq_vector_mutex); +DEFINE_STATIC_KEY_FALSE(trace_pagefault_key); -static void set_trace_idt_ctr(int val) +int trace_pagefault_reg(void) { - atomic_set(&trace_idt_ctr, val); - /* Ensure the trace_idt_ctr is set before sending IPI */ - wmb(); + static_branch_inc(&trace_pagefault_key); + return 0; } -static void switch_idt(void *arg) +void trace_pagefault_unreg(void) { - unsigned long flags; - - local_irq_save(flags); - load_current_idt(); - local_irq_restore(flags); + static_branch_dec(&trace_pagefault_key); } -int trace_irq_vector_regfunc(void) +#ifdef CONFIG_SMP + +DEFINE_STATIC_KEY_FALSE(trace_resched_ipi_key); + +int trace_resched_ipi_reg(void) { - mutex_lock(&irq_vector_mutex); - if (!trace_irq_vector_refcount) { - set_trace_idt_ctr(1); - smp_call_function(switch_idt, NULL, 0); - switch_idt(NULL); - } - trace_irq_vector_refcount++; - mutex_unlock(&irq_vector_mutex); + static_branch_inc(&trace_resched_ipi_key); return 0; } -void trace_irq_vector_unregfunc(void) +void trace_resched_ipi_unreg(void) { - mutex_lock(&irq_vector_mutex); - trace_irq_vector_refcount--; - if (!trace_irq_vector_refcount) { - set_trace_idt_ctr(0); - smp_call_function(switch_idt, NULL, 0); - switch_idt(NULL); - } - mutex_unlock(&irq_vector_mutex); + static_branch_dec(&trace_resched_ipi_key); } + +#endif diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index bf54309b85da..34ea3651362e 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -38,11 +38,6 @@ #include <linux/smp.h> #include <linux/io.h> -#ifdef CONFIG_EISA -#include <linux/ioport.h> -#include <linux/eisa.h> -#endif - #if defined(CONFIG_EDAC) #include <linux/edac.h> #endif @@ -70,20 +65,13 @@ #include <asm/x86_init.h> #include <asm/pgalloc.h> #include <asm/proto.h> - -/* No need to be aligned, but done to keep all IDTs defined the same way. */ -gate_desc debug_idt_table[NR_VECTORS] __page_aligned_bss; #else #include <asm/processor-flags.h> #include <asm/setup.h> #include <asm/proto.h> #endif -/* Must be page-aligned because the real IDT is used in a fixmap. */ -gate_desc idt_table[NR_VECTORS] __page_aligned_bss; - DECLARE_BITMAP(used_vectors, NR_VECTORS); -EXPORT_SYMBOL_GPL(used_vectors); static inline void cond_local_irq_enable(struct pt_regs *regs) { @@ -935,87 +923,9 @@ dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code) } #endif -/* Set of traps needed for early debugging. */ -void __init early_trap_init(void) -{ - /* - * Don't use IST to set DEBUG_STACK as it doesn't work until TSS - * is ready in cpu_init() <-- trap_init(). Before trap_init(), - * CPU runs at ring 0 so it is impossible to hit an invalid - * stack. Using the original stack works well enough at this - * early stage. DEBUG_STACK will be equipped after cpu_init() in - * trap_init(). - * - * We don't need to set trace_idt_table like set_intr_gate(), - * since we don't have trace_debug and it will be reset to - * 'debug' in trap_init() by set_intr_gate_ist(). - */ - set_intr_gate_notrace(X86_TRAP_DB, debug); - /* int3 can be called from all */ - set_system_intr_gate(X86_TRAP_BP, &int3); -#ifdef CONFIG_X86_32 - set_intr_gate(X86_TRAP_PF, page_fault); -#endif - load_idt(&idt_descr); -} - -void __init early_trap_pf_init(void) -{ -#ifdef CONFIG_X86_64 - set_intr_gate(X86_TRAP_PF, page_fault); -#endif -} - void __init trap_init(void) { - int i; - -#ifdef CONFIG_EISA - void __iomem *p = early_ioremap(0x0FFFD9, 4); - - if (readl(p) == 'E' + ('I'<<8) + ('S'<<16) + ('A'<<24)) - EISA_bus = 1; - early_iounmap(p, 4); -#endif - - set_intr_gate(X86_TRAP_DE, divide_error); - set_intr_gate_ist(X86_TRAP_NMI, &nmi, NMI_STACK); - /* int4 can be called from all */ - set_system_intr_gate(X86_TRAP_OF, &overflow); - set_intr_gate(X86_TRAP_BR, bounds); - set_intr_gate(X86_TRAP_UD, invalid_op); - set_intr_gate(X86_TRAP_NM, device_not_available); -#ifdef CONFIG_X86_32 - set_task_gate(X86_TRAP_DF, GDT_ENTRY_DOUBLEFAULT_TSS); -#else - set_intr_gate_ist(X86_TRAP_DF, &double_fault, DOUBLEFAULT_STACK); -#endif - set_intr_gate(X86_TRAP_OLD_MF, coprocessor_segment_overrun); - set_intr_gate(X86_TRAP_TS, invalid_TSS); - set_intr_gate(X86_TRAP_NP, segment_not_present); - set_intr_gate(X86_TRAP_SS, stack_segment); - set_intr_gate(X86_TRAP_GP, general_protection); - set_intr_gate(X86_TRAP_SPURIOUS, spurious_interrupt_bug); - set_intr_gate(X86_TRAP_MF, coprocessor_error); - set_intr_gate(X86_TRAP_AC, alignment_check); -#ifdef CONFIG_X86_MCE - set_intr_gate_ist(X86_TRAP_MC, &machine_check, MCE_STACK); -#endif - set_intr_gate(X86_TRAP_XF, simd_coprocessor_error); - - /* Reserve all the builtin and the syscall vector: */ - for (i = 0; i < FIRST_EXTERNAL_VECTOR; i++) - set_bit(i, used_vectors); - -#ifdef CONFIG_IA32_EMULATION - set_system_intr_gate(IA32_SYSCALL_VECTOR, entry_INT80_compat); - set_bit(IA32_SYSCALL_VECTOR, used_vectors); -#endif - -#ifdef CONFIG_X86_32 - set_system_intr_gate(IA32_SYSCALL_VECTOR, entry_INT80_32); - set_bit(IA32_SYSCALL_VECTOR, used_vectors); -#endif + idt_setup_traps(); /* * Set the IDT descriptor to a fixed read-only location, so that the @@ -1030,20 +940,9 @@ void __init trap_init(void) */ cpu_init(); - /* - * X86_TRAP_DB and X86_TRAP_BP have been set - * in early_trap_init(). However, ITS works only after - * cpu_init() loads TSS. See comments in early_trap_init(). - */ - set_intr_gate_ist(X86_TRAP_DB, &debug, DEBUG_STACK); - /* int3 can be called from all */ - set_system_intr_gate_ist(X86_TRAP_BP, &int3, DEBUG_STACK); + idt_setup_ist_traps(); x86_init.irqs.trap_init(); -#ifdef CONFIG_X86_64 - memcpy(&debug_idt_table, &idt_table, IDT_ENTRIES * 16); - set_nmi_gate(X86_TRAP_DB, &debug); - set_nmi_gate(X86_TRAP_BP, &int3); -#endif + idt_setup_debugidt_traps(); } diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c index b9389d72b2f7..d145a0b1f529 100644 --- a/arch/x86/kernel/unwind_frame.c +++ b/arch/x86/kernel/unwind_frame.c @@ -10,20 +10,22 @@ #define FRAME_HEADER_SIZE (sizeof(long) * 2) -/* - * This disables KASAN checking when reading a value from another task's stack, - * since the other task could be running on another CPU and could have poisoned - * the stack in the meantime. - */ -#define READ_ONCE_TASK_STACK(task, x) \ -({ \ - unsigned long val; \ - if (task == current) \ - val = READ_ONCE(x); \ - else \ - val = READ_ONCE_NOCHECK(x); \ - val; \ -}) +unsigned long unwind_get_return_address(struct unwind_state *state) +{ + if (unwind_done(state)) + return 0; + + return __kernel_text_address(state->ip) ? state->ip : 0; +} +EXPORT_SYMBOL_GPL(unwind_get_return_address); + +unsigned long *unwind_get_return_address_ptr(struct unwind_state *state) +{ + if (unwind_done(state)) + return NULL; + + return state->regs ? &state->regs->ip : state->bp + 1; +} static void unwind_dump(struct unwind_state *state) { @@ -66,15 +68,6 @@ static void unwind_dump(struct unwind_state *state) } } -unsigned long unwind_get_return_address(struct unwind_state *state) -{ - if (unwind_done(state)) - return 0; - - return __kernel_text_address(state->ip) ? state->ip : 0; -} -EXPORT_SYMBOL_GPL(unwind_get_return_address); - static size_t regs_size(struct pt_regs *regs) { /* x86_32 regs from kernel mode are two words shorter: */ @@ -91,10 +84,8 @@ static bool in_entry_code(unsigned long ip) if (addr >= __entry_text_start && addr < __entry_text_end) return true; -#if defined(CONFIG_FUNCTION_GRAPH_TRACER) || defined(CONFIG_KASAN) if (addr >= __irqentry_text_start && addr < __irqentry_text_end) return true; -#endif return false; } diff --git a/arch/x86/kernel/unwind_guess.c b/arch/x86/kernel/unwind_guess.c index 039f36738e49..4f0e17b90463 100644 --- a/arch/x86/kernel/unwind_guess.c +++ b/arch/x86/kernel/unwind_guess.c @@ -19,6 +19,11 @@ unsigned long unwind_get_return_address(struct unwind_state *state) } EXPORT_SYMBOL_GPL(unwind_get_return_address); +unsigned long *unwind_get_return_address_ptr(struct unwind_state *state) +{ + return NULL; +} + bool unwind_next_frame(struct unwind_state *state) { struct stack_info *info = &state->stack_info; diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c new file mode 100644 index 000000000000..570b70d3f604 --- /dev/null +++ b/arch/x86/kernel/unwind_orc.c @@ -0,0 +1,582 @@ +#include <linux/module.h> +#include <linux/sort.h> +#include <asm/ptrace.h> +#include <asm/stacktrace.h> +#include <asm/unwind.h> +#include <asm/orc_types.h> +#include <asm/orc_lookup.h> +#include <asm/sections.h> + +#define orc_warn(fmt, ...) \ + printk_deferred_once(KERN_WARNING pr_fmt("WARNING: " fmt), ##__VA_ARGS__) + +extern int __start_orc_unwind_ip[]; +extern int __stop_orc_unwind_ip[]; +extern struct orc_entry __start_orc_unwind[]; +extern struct orc_entry __stop_orc_unwind[]; + +static DEFINE_MUTEX(sort_mutex); +int *cur_orc_ip_table = __start_orc_unwind_ip; +struct orc_entry *cur_orc_table = __start_orc_unwind; + +unsigned int lookup_num_blocks; +bool orc_init; + +static inline unsigned long orc_ip(const int *ip) +{ + return (unsigned long)ip + *ip; +} + +static struct orc_entry *__orc_find(int *ip_table, struct orc_entry *u_table, + unsigned int num_entries, unsigned long ip) +{ + int *first = ip_table; + int *last = ip_table + num_entries - 1; + int *mid = first, *found = first; + + if (!num_entries) + return NULL; + + /* + * Do a binary range search to find the rightmost duplicate of a given + * starting address. Some entries are section terminators which are + * "weak" entries for ensuring there are no gaps. They should be + * ignored when they conflict with a real entry. + */ + while (first <= last) { + mid = first + ((last - first) / 2); + + if (orc_ip(mid) <= ip) { + found = mid; + first = mid + 1; + } else + last = mid - 1; + } + + return u_table + (found - ip_table); +} + +#ifdef CONFIG_MODULES +static struct orc_entry *orc_module_find(unsigned long ip) +{ + struct module *mod; + + mod = __module_address(ip); + if (!mod || !mod->arch.orc_unwind || !mod->arch.orc_unwind_ip) + return NULL; + return __orc_find(mod->arch.orc_unwind_ip, mod->arch.orc_unwind, + mod->arch.num_orcs, ip); +} +#else +static struct orc_entry *orc_module_find(unsigned long ip) +{ + return NULL; +} +#endif + +static struct orc_entry *orc_find(unsigned long ip) +{ + if (!orc_init) + return NULL; + + /* For non-init vmlinux addresses, use the fast lookup table: */ + if (ip >= LOOKUP_START_IP && ip < LOOKUP_STOP_IP) { + unsigned int idx, start, stop; + + idx = (ip - LOOKUP_START_IP) / LOOKUP_BLOCK_SIZE; + + if (unlikely((idx >= lookup_num_blocks-1))) { + orc_warn("WARNING: bad lookup idx: idx=%u num=%u ip=%lx\n", + idx, lookup_num_blocks, ip); + return NULL; + } + + start = orc_lookup[idx]; + stop = orc_lookup[idx + 1] + 1; + + if (unlikely((__start_orc_unwind + start >= __stop_orc_unwind) || + (__start_orc_unwind + stop > __stop_orc_unwind))) { + orc_warn("WARNING: bad lookup value: idx=%u num=%u start=%u stop=%u ip=%lx\n", + idx, lookup_num_blocks, start, stop, ip); + return NULL; + } + + return __orc_find(__start_orc_unwind_ip + start, + __start_orc_unwind + start, stop - start, ip); + } + + /* vmlinux .init slow lookup: */ + if (ip >= (unsigned long)_sinittext && ip < (unsigned long)_einittext) + return __orc_find(__start_orc_unwind_ip, __start_orc_unwind, + __stop_orc_unwind_ip - __start_orc_unwind_ip, ip); + + /* Module lookup: */ + return orc_module_find(ip); +} + +static void orc_sort_swap(void *_a, void *_b, int size) +{ + struct orc_entry *orc_a, *orc_b; + struct orc_entry orc_tmp; + int *a = _a, *b = _b, tmp; + int delta = _b - _a; + + /* Swap the .orc_unwind_ip entries: */ + tmp = *a; + *a = *b + delta; + *b = tmp - delta; + + /* Swap the corresponding .orc_unwind entries: */ + orc_a = cur_orc_table + (a - cur_orc_ip_table); + orc_b = cur_orc_table + (b - cur_orc_ip_table); + orc_tmp = *orc_a; + *orc_a = *orc_b; + *orc_b = orc_tmp; +} + +static int orc_sort_cmp(const void *_a, const void *_b) +{ + struct orc_entry *orc_a; + const int *a = _a, *b = _b; + unsigned long a_val = orc_ip(a); + unsigned long b_val = orc_ip(b); + + if (a_val > b_val) + return 1; + if (a_val < b_val) + return -1; + + /* + * The "weak" section terminator entries need to always be on the left + * to ensure the lookup code skips them in favor of real entries. + * These terminator entries exist to handle any gaps created by + * whitelisted .o files which didn't get objtool generation. + */ + orc_a = cur_orc_table + (a - cur_orc_ip_table); + return orc_a->sp_reg == ORC_REG_UNDEFINED ? -1 : 1; +} + +#ifdef CONFIG_MODULES +void unwind_module_init(struct module *mod, void *_orc_ip, size_t orc_ip_size, + void *_orc, size_t orc_size) +{ + int *orc_ip = _orc_ip; + struct orc_entry *orc = _orc; + unsigned int num_entries = orc_ip_size / sizeof(int); + + WARN_ON_ONCE(orc_ip_size % sizeof(int) != 0 || + orc_size % sizeof(*orc) != 0 || + num_entries != orc_size / sizeof(*orc)); + + /* + * The 'cur_orc_*' globals allow the orc_sort_swap() callback to + * associate an .orc_unwind_ip table entry with its corresponding + * .orc_unwind entry so they can both be swapped. + */ + mutex_lock(&sort_mutex); + cur_orc_ip_table = orc_ip; + cur_orc_table = orc; + sort(orc_ip, num_entries, sizeof(int), orc_sort_cmp, orc_sort_swap); + mutex_unlock(&sort_mutex); + + mod->arch.orc_unwind_ip = orc_ip; + mod->arch.orc_unwind = orc; + mod->arch.num_orcs = num_entries; +} +#endif + +void __init unwind_init(void) +{ + size_t orc_ip_size = (void *)__stop_orc_unwind_ip - (void *)__start_orc_unwind_ip; + size_t orc_size = (void *)__stop_orc_unwind - (void *)__start_orc_unwind; + size_t num_entries = orc_ip_size / sizeof(int); + struct orc_entry *orc; + int i; + + if (!num_entries || orc_ip_size % sizeof(int) != 0 || + orc_size % sizeof(struct orc_entry) != 0 || + num_entries != orc_size / sizeof(struct orc_entry)) { + orc_warn("WARNING: Bad or missing .orc_unwind table. Disabling unwinder.\n"); + return; + } + + /* Sort the .orc_unwind and .orc_unwind_ip tables: */ + sort(__start_orc_unwind_ip, num_entries, sizeof(int), orc_sort_cmp, + orc_sort_swap); + + /* Initialize the fast lookup table: */ + lookup_num_blocks = orc_lookup_end - orc_lookup; + for (i = 0; i < lookup_num_blocks-1; i++) { + orc = __orc_find(__start_orc_unwind_ip, __start_orc_unwind, + num_entries, + LOOKUP_START_IP + (LOOKUP_BLOCK_SIZE * i)); + if (!orc) { + orc_warn("WARNING: Corrupt .orc_unwind table. Disabling unwinder.\n"); + return; + } + + orc_lookup[i] = orc - __start_orc_unwind; + } + + /* Initialize the ending block: */ + orc = __orc_find(__start_orc_unwind_ip, __start_orc_unwind, num_entries, + LOOKUP_STOP_IP); + if (!orc) { + orc_warn("WARNING: Corrupt .orc_unwind table. Disabling unwinder.\n"); + return; + } + orc_lookup[lookup_num_blocks-1] = orc - __start_orc_unwind; + + orc_init = true; +} + +unsigned long unwind_get_return_address(struct unwind_state *state) +{ + if (unwind_done(state)) + return 0; + + return __kernel_text_address(state->ip) ? state->ip : 0; +} +EXPORT_SYMBOL_GPL(unwind_get_return_address); + +unsigned long *unwind_get_return_address_ptr(struct unwind_state *state) +{ + if (unwind_done(state)) + return NULL; + + if (state->regs) + return &state->regs->ip; + + if (state->sp) + return (unsigned long *)state->sp - 1; + + return NULL; +} + +static bool stack_access_ok(struct unwind_state *state, unsigned long addr, + size_t len) +{ + struct stack_info *info = &state->stack_info; + + /* + * If the address isn't on the current stack, switch to the next one. + * + * We may have to traverse multiple stacks to deal with the possibility + * that info->next_sp could point to an empty stack and the address + * could be on a subsequent stack. + */ + while (!on_stack(info, (void *)addr, len)) + if (get_stack_info(info->next_sp, state->task, info, + &state->stack_mask)) + return false; + + return true; +} + +static bool deref_stack_reg(struct unwind_state *state, unsigned long addr, + unsigned long *val) +{ + if (!stack_access_ok(state, addr, sizeof(long))) + return false; + + *val = READ_ONCE_TASK_STACK(state->task, *(unsigned long *)addr); + return true; +} + +#define REGS_SIZE (sizeof(struct pt_regs)) +#define SP_OFFSET (offsetof(struct pt_regs, sp)) +#define IRET_REGS_SIZE (REGS_SIZE - offsetof(struct pt_regs, ip)) +#define IRET_SP_OFFSET (SP_OFFSET - offsetof(struct pt_regs, ip)) + +static bool deref_stack_regs(struct unwind_state *state, unsigned long addr, + unsigned long *ip, unsigned long *sp, bool full) +{ + size_t regs_size = full ? REGS_SIZE : IRET_REGS_SIZE; + size_t sp_offset = full ? SP_OFFSET : IRET_SP_OFFSET; + struct pt_regs *regs = (struct pt_regs *)(addr + regs_size - REGS_SIZE); + + if (IS_ENABLED(CONFIG_X86_64)) { + if (!stack_access_ok(state, addr, regs_size)) + return false; + + *ip = regs->ip; + *sp = regs->sp; + + return true; + } + + if (!stack_access_ok(state, addr, sp_offset)) + return false; + + *ip = regs->ip; + + if (user_mode(regs)) { + if (!stack_access_ok(state, addr + sp_offset, + REGS_SIZE - SP_OFFSET)) + return false; + + *sp = regs->sp; + } else + *sp = (unsigned long)®s->sp; + + return true; +} + +bool unwind_next_frame(struct unwind_state *state) +{ + unsigned long ip_p, sp, orig_ip, prev_sp = state->sp; + enum stack_type prev_type = state->stack_info.type; + struct orc_entry *orc; + struct pt_regs *ptregs; + bool indirect = false; + + if (unwind_done(state)) + return false; + + /* Don't let modules unload while we're reading their ORC data. */ + preempt_disable(); + + /* Have we reached the end? */ + if (state->regs && user_mode(state->regs)) + goto done; + + /* + * Find the orc_entry associated with the text address. + * + * Decrement call return addresses by one so they work for sibling + * calls and calls to noreturn functions. + */ + orc = orc_find(state->signal ? state->ip : state->ip - 1); + if (!orc || orc->sp_reg == ORC_REG_UNDEFINED) + goto done; + orig_ip = state->ip; + + /* Find the previous frame's stack: */ + switch (orc->sp_reg) { + case ORC_REG_SP: + sp = state->sp + orc->sp_offset; + break; + + case ORC_REG_BP: + sp = state->bp + orc->sp_offset; + break; + + case ORC_REG_SP_INDIRECT: + sp = state->sp + orc->sp_offset; + indirect = true; + break; + + case ORC_REG_BP_INDIRECT: + sp = state->bp + orc->sp_offset; + indirect = true; + break; + + case ORC_REG_R10: + if (!state->regs || !state->full_regs) { + orc_warn("missing regs for base reg R10 at ip %p\n", + (void *)state->ip); + goto done; + } + sp = state->regs->r10; + break; + + case ORC_REG_R13: + if (!state->regs || !state->full_regs) { + orc_warn("missing regs for base reg R13 at ip %p\n", + (void *)state->ip); + goto done; + } + sp = state->regs->r13; + break; + + case ORC_REG_DI: + if (!state->regs || !state->full_regs) { + orc_warn("missing regs for base reg DI at ip %p\n", + (void *)state->ip); + goto done; + } + sp = state->regs->di; + break; + + case ORC_REG_DX: + if (!state->regs || !state->full_regs) { + orc_warn("missing regs for base reg DX at ip %p\n", + (void *)state->ip); + goto done; + } + sp = state->regs->dx; + break; + + default: + orc_warn("unknown SP base reg %d for ip %p\n", + orc->sp_reg, (void *)state->ip); + goto done; + } + + if (indirect) { + if (!deref_stack_reg(state, sp, &sp)) + goto done; + } + + /* Find IP, SP and possibly regs: */ + switch (orc->type) { + case ORC_TYPE_CALL: + ip_p = sp - sizeof(long); + + if (!deref_stack_reg(state, ip_p, &state->ip)) + goto done; + + state->ip = ftrace_graph_ret_addr(state->task, &state->graph_idx, + state->ip, (void *)ip_p); + + state->sp = sp; + state->regs = NULL; + state->signal = false; + break; + + case ORC_TYPE_REGS: + if (!deref_stack_regs(state, sp, &state->ip, &state->sp, true)) { + orc_warn("can't dereference registers at %p for ip %p\n", + (void *)sp, (void *)orig_ip); + goto done; + } + + state->regs = (struct pt_regs *)sp; + state->full_regs = true; + state->signal = true; + break; + + case ORC_TYPE_REGS_IRET: + if (!deref_stack_regs(state, sp, &state->ip, &state->sp, false)) { + orc_warn("can't dereference iret registers at %p for ip %p\n", + (void *)sp, (void *)orig_ip); + goto done; + } + + ptregs = container_of((void *)sp, struct pt_regs, ip); + if ((unsigned long)ptregs >= prev_sp && + on_stack(&state->stack_info, ptregs, REGS_SIZE)) { + state->regs = ptregs; + state->full_regs = false; + } else + state->regs = NULL; + + state->signal = true; + break; + + default: + orc_warn("unknown .orc_unwind entry type %d\n", orc->type); + break; + } + + /* Find BP: */ + switch (orc->bp_reg) { + case ORC_REG_UNDEFINED: + if (state->regs && state->full_regs) + state->bp = state->regs->bp; + break; + + case ORC_REG_PREV_SP: + if (!deref_stack_reg(state, sp + orc->bp_offset, &state->bp)) + goto done; + break; + + case ORC_REG_BP: + if (!deref_stack_reg(state, state->bp + orc->bp_offset, &state->bp)) + goto done; + break; + + default: + orc_warn("unknown BP base reg %d for ip %p\n", + orc->bp_reg, (void *)orig_ip); + goto done; + } + + /* Prevent a recursive loop due to bad ORC data: */ + if (state->stack_info.type == prev_type && + on_stack(&state->stack_info, (void *)state->sp, sizeof(long)) && + state->sp <= prev_sp) { + orc_warn("stack going in the wrong direction? ip=%p\n", + (void *)orig_ip); + goto done; + } + + preempt_enable(); + return true; + +done: + preempt_enable(); + state->stack_info.type = STACK_TYPE_UNKNOWN; + return false; +} +EXPORT_SYMBOL_GPL(unwind_next_frame); + +void __unwind_start(struct unwind_state *state, struct task_struct *task, + struct pt_regs *regs, unsigned long *first_frame) +{ + memset(state, 0, sizeof(*state)); + state->task = task; + + /* + * Refuse to unwind the stack of a task while it's executing on another + * CPU. This check is racy, but that's ok: the unwinder has other + * checks to prevent it from going off the rails. + */ + if (task_on_another_cpu(task)) + goto done; + + if (regs) { + if (user_mode(regs)) + goto done; + + state->ip = regs->ip; + state->sp = kernel_stack_pointer(regs); + state->bp = regs->bp; + state->regs = regs; + state->full_regs = true; + state->signal = true; + + } else if (task == current) { + asm volatile("lea (%%rip), %0\n\t" + "mov %%rsp, %1\n\t" + "mov %%rbp, %2\n\t" + : "=r" (state->ip), "=r" (state->sp), + "=r" (state->bp)); + + } else { + struct inactive_task_frame *frame = (void *)task->thread.sp; + + state->sp = task->thread.sp; + state->bp = READ_ONCE_NOCHECK(frame->bp); + state->ip = READ_ONCE_NOCHECK(frame->ret_addr); + } + + if (get_stack_info((unsigned long *)state->sp, state->task, + &state->stack_info, &state->stack_mask)) + return; + + /* + * The caller can provide the address of the first frame directly + * (first_frame) or indirectly (regs->sp) to indicate which stack frame + * to start unwinding at. Skip ahead until we reach it. + */ + + /* When starting from regs, skip the regs frame: */ + if (regs) { + unwind_next_frame(state); + return; + } + + /* Otherwise, skip ahead to the user-specified starting frame: */ + while (!unwind_done(state) && + (!on_stack(&state->stack_info, first_frame, sizeof(long)) || + state->sp <= (unsigned long)first_frame)) + unwind_next_frame(state); + + return; + +done: + state->stack_info.type = STACK_TYPE_UNKNOWN; + return; +} +EXPORT_SYMBOL_GPL(__unwind_start); diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index c8a3b61be0aa..f05f00acac89 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -24,6 +24,7 @@ #include <asm/asm-offsets.h> #include <asm/thread_info.h> #include <asm/page_types.h> +#include <asm/orc_lookup.h> #include <asm/cache.h> #include <asm/boot.h> @@ -148,6 +149,8 @@ SECTIONS BUG_TABLE + ORC_UNWIND_TABLE + . = ALIGN(PAGE_SIZE); __vvar_page = .; diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 2688c7dc5323..3ea624452f93 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -89,6 +89,5 @@ config KVM_MMU_AUDIT # OK, it's a little counter-intuitive to do this, but it puts it neatly under # the virtualization menu. source drivers/vhost/Kconfig -source drivers/lguest/Kconfig endif # VIRTUALIZATION diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 59ca2eea522c..19adbb418443 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -469,7 +469,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, entry->ecx &= kvm_cpuid_7_0_ecx_x86_features; cpuid_mask(&entry->ecx, CPUID_7_ECX); /* PKU is not yet implemented for shadow paging. */ - if (!tdp_enabled) + if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE)) entry->ecx &= ~F(PKU); entry->edx &= kvm_cpuid_7_0_edx_x86_features; entry->edx &= get_scattered_cpuid_leaf(7, 0, CPUID_EDX); diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index 762cdf2595f9..e1e89ee4af75 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -84,11 +84,6 @@ static inline u64 kvm_read_edx_eax(struct kvm_vcpu *vcpu) | ((u64)(kvm_register_read(vcpu, VCPU_REGS_RDX) & -1u) << 32); } -static inline u32 kvm_read_pkru(struct kvm_vcpu *vcpu) -{ - return kvm_x86_ops->get_pkru(vcpu); -} - static inline void enter_guest_mode(struct kvm_vcpu *vcpu) { vcpu->arch.hflags |= HF_GUEST_MASK; diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 2819d4c123eb..589dcc117086 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1495,11 +1495,10 @@ EXPORT_SYMBOL_GPL(kvm_lapic_hv_timer_in_use); static void cancel_hv_timer(struct kvm_lapic *apic) { + WARN_ON(preemptible()); WARN_ON(!apic->lapic_timer.hv_timer_in_use); - preempt_disable(); kvm_x86_ops->cancel_hv_timer(apic->vcpu); apic->lapic_timer.hv_timer_in_use = false; - preempt_enable(); } static bool start_hv_timer(struct kvm_lapic *apic) @@ -1507,6 +1506,7 @@ static bool start_hv_timer(struct kvm_lapic *apic) struct kvm_timer *ktimer = &apic->lapic_timer; int r; + WARN_ON(preemptible()); if (!kvm_x86_ops->set_hv_timer) return false; @@ -1538,6 +1538,8 @@ static bool start_hv_timer(struct kvm_lapic *apic) static void start_sw_timer(struct kvm_lapic *apic) { struct kvm_timer *ktimer = &apic->lapic_timer; + + WARN_ON(preemptible()); if (apic->lapic_timer.hv_timer_in_use) cancel_hv_timer(apic); if (!apic_lvtt_period(apic) && atomic_read(&ktimer->pending)) @@ -1552,15 +1554,20 @@ static void start_sw_timer(struct kvm_lapic *apic) static void restart_apic_timer(struct kvm_lapic *apic) { + preempt_disable(); if (!start_hv_timer(apic)) start_sw_timer(apic); + preempt_enable(); } void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; - WARN_ON(!apic->lapic_timer.hv_timer_in_use); + preempt_disable(); + /* If the preempt notifier has already run, it also called apic_timer_expired */ + if (!apic->lapic_timer.hv_timer_in_use) + goto out; WARN_ON(swait_active(&vcpu->wq)); cancel_hv_timer(apic); apic_timer_expired(apic); @@ -1569,6 +1576,8 @@ void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu) advance_periodic_target_expiration(apic); restart_apic_timer(apic); } +out: + preempt_enable(); } EXPORT_SYMBOL_GPL(kvm_lapic_expired_hv_timer); @@ -1582,9 +1591,11 @@ void kvm_lapic_switch_to_sw_timer(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; + preempt_disable(); /* Possibly the TSC deadline timer is not enabled yet */ if (apic->lapic_timer.hv_timer_in_use) start_sw_timer(apic); + preempt_enable(); } EXPORT_SYMBOL_GPL(kvm_lapic_switch_to_sw_timer); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 9b1dd114956a..04d750813c9d 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -108,7 +108,7 @@ module_param(dbg, bool, 0644); (((address) >> PT32_LEVEL_SHIFT(level)) & ((1 << PT32_LEVEL_BITS) - 1)) -#define PT64_BASE_ADDR_MASK (((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1)) +#define PT64_BASE_ADDR_MASK __sme_clr((((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1))) #define PT64_DIR_BASE_ADDR_MASK \ (PT64_BASE_ADDR_MASK & ~((1ULL << (PAGE_SHIFT + PT64_LEVEL_BITS)) - 1)) #define PT64_LVL_ADDR_MASK(level) \ @@ -126,7 +126,7 @@ module_param(dbg, bool, 0644); * PT32_LEVEL_BITS))) - 1)) #define PT64_PERM_MASK (PT_PRESENT_MASK | PT_WRITABLE_MASK | shadow_user_mask \ - | shadow_x_mask | shadow_nx_mask) + | shadow_x_mask | shadow_nx_mask | shadow_me_mask) #define ACC_EXEC_MASK 1 #define ACC_WRITE_MASK PT_WRITABLE_MASK @@ -186,6 +186,7 @@ static u64 __read_mostly shadow_dirty_mask; static u64 __read_mostly shadow_mmio_mask; static u64 __read_mostly shadow_mmio_value; static u64 __read_mostly shadow_present_mask; +static u64 __read_mostly shadow_me_mask; /* * SPTEs used by MMUs without A/D bits are marked with shadow_acc_track_value. @@ -349,7 +350,7 @@ static bool check_mmio_spte(struct kvm_vcpu *vcpu, u64 spte) */ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 p_mask, - u64 acc_track_mask) + u64 acc_track_mask, u64 me_mask) { BUG_ON(!dirty_mask != !accessed_mask); BUG_ON(!accessed_mask && !acc_track_mask); @@ -362,6 +363,7 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, shadow_x_mask = x_mask; shadow_present_mask = p_mask; shadow_acc_track_mask = acc_track_mask; + shadow_me_mask = me_mask; } EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes); @@ -2433,7 +2435,7 @@ static void link_shadow_page(struct kvm_vcpu *vcpu, u64 *sptep, BUILD_BUG_ON(VMX_EPT_WRITABLE_MASK != PT_WRITABLE_MASK); spte = __pa(sp->spt) | shadow_present_mask | PT_WRITABLE_MASK | - shadow_user_mask | shadow_x_mask; + shadow_user_mask | shadow_x_mask | shadow_me_mask; if (sp_ad_disabled(sp)) spte |= shadow_acc_track_value; @@ -2745,6 +2747,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, pte_access &= ~ACC_WRITE_MASK; spte |= (u64)pfn << PAGE_SHIFT; + spte |= shadow_me_mask; if (pte_access & ACC_WRITE_MASK) { @@ -4106,16 +4109,28 @@ void reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context) { bool uses_nx = context->nx || context->base_role.smep_andnot_wp; + struct rsvd_bits_validate *shadow_zero_check; + int i; /* * Passing "true" to the last argument is okay; it adds a check * on bit 8 of the SPTEs which KVM doesn't use anyway. */ - __reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check, + shadow_zero_check = &context->shadow_zero_check; + __reset_rsvds_bits_mask(vcpu, shadow_zero_check, boot_cpu_data.x86_phys_bits, context->shadow_root_level, uses_nx, guest_cpuid_has_gbpages(vcpu), is_pse(vcpu), true); + + if (!shadow_me_mask) + return; + + for (i = context->shadow_root_level; --i >= 0;) { + shadow_zero_check->rsvd_bits_mask[0][i] &= ~shadow_me_mask; + shadow_zero_check->rsvd_bits_mask[1][i] &= ~shadow_me_mask; + } + } EXPORT_SYMBOL_GPL(reset_shadow_zero_bits_mask); @@ -4133,17 +4148,29 @@ static void reset_tdp_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context) { + struct rsvd_bits_validate *shadow_zero_check; + int i; + + shadow_zero_check = &context->shadow_zero_check; + if (boot_cpu_is_amd()) - __reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check, + __reset_rsvds_bits_mask(vcpu, shadow_zero_check, boot_cpu_data.x86_phys_bits, context->shadow_root_level, false, boot_cpu_has(X86_FEATURE_GBPAGES), true, true); else - __reset_rsvds_bits_mask_ept(&context->shadow_zero_check, + __reset_rsvds_bits_mask_ept(shadow_zero_check, boot_cpu_data.x86_phys_bits, false); + if (!shadow_me_mask) + return; + + for (i = context->shadow_root_level; --i >= 0;) { + shadow_zero_check->rsvd_bits_mask[0][i] &= ~shadow_me_mask; + shadow_zero_check->rsvd_bits_mask[1][i] &= ~shadow_me_mask; + } } /* diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index d7d248a000dd..4b9a3ae6b725 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -185,7 +185,7 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, * index of the protection domain, so pte_pkey * 2 is * is the index of the first bit for the domain. */ - pkru_bits = (kvm_read_pkru(vcpu) >> (pte_pkey * 2)) & 3; + pkru_bits = (vcpu->arch.pkru >> (pte_pkey * 2)) & 3; /* clear present bit, replace PFEC.RSVD with ACC_USER_MASK. */ offset = (pfec & ~1) + diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 4d8141e533c3..8dbd8dbc83eb 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1100,7 +1100,7 @@ static __init int svm_hardware_setup(void) if (vls) { if (!npt_enabled || - !boot_cpu_has(X86_FEATURE_VIRTUAL_VMLOAD_VMSAVE) || + !boot_cpu_has(X86_FEATURE_V_VMSAVE_VMLOAD) || !IS_ENABLED(CONFIG_X86_64)) { vls = false; } else { @@ -1167,9 +1167,9 @@ static void avic_init_vmcb(struct vcpu_svm *svm) { struct vmcb *vmcb = svm->vmcb; struct kvm_arch *vm_data = &svm->vcpu.kvm->arch; - phys_addr_t bpa = page_to_phys(svm->avic_backing_page); - phys_addr_t lpa = page_to_phys(vm_data->avic_logical_id_table_page); - phys_addr_t ppa = page_to_phys(vm_data->avic_physical_id_table_page); + phys_addr_t bpa = __sme_set(page_to_phys(svm->avic_backing_page)); + phys_addr_t lpa = __sme_set(page_to_phys(vm_data->avic_logical_id_table_page)); + phys_addr_t ppa = __sme_set(page_to_phys(vm_data->avic_physical_id_table_page)); vmcb->control.avic_backing_page = bpa & AVIC_HPA_MASK; vmcb->control.avic_logical_id = lpa & AVIC_HPA_MASK; @@ -1232,8 +1232,8 @@ static void init_vmcb(struct vcpu_svm *svm) set_intercept(svm, INTERCEPT_MWAIT); } - control->iopm_base_pa = iopm_base; - control->msrpm_base_pa = __pa(svm->msrpm); + control->iopm_base_pa = __sme_set(iopm_base); + control->msrpm_base_pa = __sme_set(__pa(svm->msrpm)); control->int_ctl = V_INTR_MASKING_MASK; init_seg(&save->es); @@ -1377,9 +1377,9 @@ static int avic_init_backing_page(struct kvm_vcpu *vcpu) return -EINVAL; new_entry = READ_ONCE(*entry); - new_entry = (page_to_phys(svm->avic_backing_page) & - AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK) | - AVIC_PHYSICAL_ID_ENTRY_VALID_MASK; + new_entry = __sme_set((page_to_phys(svm->avic_backing_page) & + AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK) | + AVIC_PHYSICAL_ID_ENTRY_VALID_MASK); WRITE_ONCE(*entry, new_entry); svm->avic_physical_id_cache = entry; @@ -1647,7 +1647,7 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) svm->vmcb = page_address(page); clear_page(svm->vmcb); - svm->vmcb_pa = page_to_pfn(page) << PAGE_SHIFT; + svm->vmcb_pa = __sme_set(page_to_pfn(page) << PAGE_SHIFT); svm->asid_generation = 0; init_vmcb(svm); @@ -1675,7 +1675,7 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - __free_page(pfn_to_page(svm->vmcb_pa >> PAGE_SHIFT)); + __free_page(pfn_to_page(__sme_clr(svm->vmcb_pa) >> PAGE_SHIFT)); __free_pages(virt_to_page(svm->msrpm), MSRPM_ALLOC_ORDER); __free_page(virt_to_page(svm->nested.hsave)); __free_pages(virt_to_page(svm->nested.msrpm), MSRPM_ALLOC_ORDER); @@ -1777,11 +1777,6 @@ static void svm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) to_svm(vcpu)->vmcb->save.rflags = rflags; } -static u32 svm_get_pkru(struct kvm_vcpu *vcpu) -{ - return 0; -} - static void svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) { switch (reg) { @@ -2335,7 +2330,7 @@ static u64 nested_svm_get_tdp_pdptr(struct kvm_vcpu *vcpu, int index) u64 pdpte; int ret; - ret = kvm_vcpu_read_guest_page(vcpu, gpa_to_gfn(cr3), &pdpte, + ret = kvm_vcpu_read_guest_page(vcpu, gpa_to_gfn(__sme_clr(cr3)), &pdpte, offset_in_page(cr3) + index * 8, 8); if (ret) return 0; @@ -2347,7 +2342,7 @@ static void nested_svm_set_tdp_cr3(struct kvm_vcpu *vcpu, { struct vcpu_svm *svm = to_svm(vcpu); - svm->vmcb->control.nested_cr3 = root; + svm->vmcb->control.nested_cr3 = __sme_set(root); mark_dirty(svm->vmcb, VMCB_NPT); svm_flush_tlb(vcpu); } @@ -2430,6 +2425,16 @@ static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, svm->vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + nr; svm->vmcb->control.exit_code_hi = 0; svm->vmcb->control.exit_info_1 = error_code; + + /* + * FIXME: we should not write CR2 when L1 intercepts an L2 #PF exception. + * The fix is to add the ancillary datum (CR2 or DR6) to structs + * kvm_queued_exception and kvm_vcpu_events, so that CR2 and DR6 can be + * written only when inject_pending_event runs (DR6 would written here + * too). This should be conditional on a new capability---if the + * capability is disabled, kvm_multiple_exception would write the + * ancillary information to CR2 or DR6, for backwards ABI-compatibility. + */ if (svm->vcpu.arch.exception.nested_apf) svm->vmcb->control.exit_info_2 = svm->vcpu.arch.apf.nested_apf_token; else @@ -2868,7 +2873,7 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) svm->nested.msrpm[p] = svm->msrpm[p] | value; } - svm->vmcb->control.msrpm_base_pa = __pa(svm->nested.msrpm); + svm->vmcb->control.msrpm_base_pa = __sme_set(__pa(svm->nested.msrpm)); return true; } @@ -4501,7 +4506,7 @@ get_pi_vcpu_info(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, pr_debug("SVM: %s: use GA mode for irq %u\n", __func__, irq.vector); *svm = to_svm(vcpu); - vcpu_info->pi_desc_addr = page_to_phys((*svm)->avic_backing_page); + vcpu_info->pi_desc_addr = __sme_set(page_to_phys((*svm)->avic_backing_page)); vcpu_info->vector = irq.vector; return 0; @@ -4552,7 +4557,8 @@ static int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq, struct amd_iommu_pi_data pi; /* Try to enable guest_mode in IRTE */ - pi.base = page_to_phys(svm->avic_backing_page) & AVIC_HPA_MASK; + pi.base = __sme_set(page_to_phys(svm->avic_backing_page) & + AVIC_HPA_MASK); pi.ga_tag = AVIC_GATAG(kvm->arch.avic_vm_id, svm->vcpu.vcpu_id); pi.is_guest_mode = true; @@ -5001,7 +5007,7 @@ static void svm_set_cr3(struct kvm_vcpu *vcpu, unsigned long root) { struct vcpu_svm *svm = to_svm(vcpu); - svm->vmcb->save.cr3 = root; + svm->vmcb->save.cr3 = __sme_set(root); mark_dirty(svm->vmcb, VMCB_CR); svm_flush_tlb(vcpu); } @@ -5010,7 +5016,7 @@ static void set_tdp_cr3(struct kvm_vcpu *vcpu, unsigned long root) { struct vcpu_svm *svm = to_svm(vcpu); - svm->vmcb->control.nested_cr3 = root; + svm->vmcb->control.nested_cr3 = __sme_set(root); mark_dirty(svm->vmcb, VMCB_NPT); /* Also sync guest cr3 here in case we live migrate */ @@ -5403,8 +5409,6 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .get_rflags = svm_get_rflags, .set_rflags = svm_set_rflags, - .get_pkru = svm_get_pkru, - .tlb_flush = svm_flush_tlb, .run = svm_vcpu_run, diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 29fd8af5c347..70b90c0810d0 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -416,13 +416,10 @@ struct nested_vmx { /* The guest-physical address of the current VMCS L1 keeps for L2 */ gpa_t current_vmptr; - /* The host-usable pointer to the above */ - struct page *current_vmcs12_page; - struct vmcs12 *current_vmcs12; /* * Cache of the guest's VMCS, existing outside of guest memory. * Loaded from guest memory during VMPTRLD. Flushed to guest - * memory during VMXOFF, VMCLEAR, VMPTRLD. + * memory during VMCLEAR and VMPTRLD. */ struct vmcs12 *cached_vmcs12; /* @@ -563,7 +560,6 @@ struct vcpu_vmx { struct kvm_vcpu vcpu; unsigned long host_rsp; u8 fail; - bool nmi_known_unmasked; u32 exit_intr_info; u32 idt_vectoring_info; ulong rflags; @@ -640,8 +636,6 @@ struct vcpu_vmx { u64 current_tsc_ratio; - bool guest_pkru_valid; - u32 guest_pkru; u32 host_pkru; /* @@ -928,6 +922,10 @@ static u32 vmx_segment_access_rights(struct kvm_segment *var); static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx); static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx); static int alloc_identity_pagetable(struct kvm *kvm); +static bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu); +static void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked); +static bool nested_vmx_is_page_fault_vmexit(struct vmcs12 *vmcs12, + u16 error_code); static DEFINE_PER_CPU(struct vmcs *, vmxarea); static DEFINE_PER_CPU(struct vmcs *, current_vmcs); @@ -2383,11 +2381,6 @@ static void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) to_vmx(vcpu)->emulation_required = emulation_required(vcpu); } -static u32 vmx_get_pkru(struct kvm_vcpu *vcpu) -{ - return to_vmx(vcpu)->guest_pkru; -} - static u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu) { u32 interruptibility = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO); @@ -2429,6 +2422,30 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) vmx_set_interrupt_shadow(vcpu, 0); } +static void nested_vmx_inject_exception_vmexit(struct kvm_vcpu *vcpu, + unsigned long exit_qual) +{ + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + unsigned int nr = vcpu->arch.exception.nr; + u32 intr_info = nr | INTR_INFO_VALID_MASK; + + if (vcpu->arch.exception.has_error_code) { + vmcs12->vm_exit_intr_error_code = vcpu->arch.exception.error_code; + intr_info |= INTR_INFO_DELIVER_CODE_MASK; + } + + if (kvm_exception_is_soft(nr)) + intr_info |= INTR_TYPE_SOFT_EXCEPTION; + else + intr_info |= INTR_TYPE_HARD_EXCEPTION; + + if (!(vmcs12->idt_vectoring_info_field & VECTORING_INFO_VALID_MASK) && + vmx_get_nmi_mask(vcpu)) + intr_info |= INTR_INFO_UNBLOCK_NMI; + + nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, intr_info, exit_qual); +} + /* * KVM wants to inject page-faults which it got to the guest. This function * checks whether in a nested guest, we need to inject them to L1 or L2. @@ -2438,23 +2455,38 @@ static int nested_vmx_check_exception(struct kvm_vcpu *vcpu) struct vmcs12 *vmcs12 = get_vmcs12(vcpu); unsigned int nr = vcpu->arch.exception.nr; - if (!((vmcs12->exception_bitmap & (1u << nr)) || - (nr == PF_VECTOR && vcpu->arch.exception.nested_apf))) - return 0; + if (nr == PF_VECTOR) { + if (vcpu->arch.exception.nested_apf) { + nested_vmx_inject_exception_vmexit(vcpu, + vcpu->arch.apf.nested_apf_token); + return 1; + } + /* + * FIXME: we must not write CR2 when L1 intercepts an L2 #PF exception. + * The fix is to add the ancillary datum (CR2 or DR6) to structs + * kvm_queued_exception and kvm_vcpu_events, so that CR2 and DR6 + * can be written only when inject_pending_event runs. This should be + * conditional on a new capability---if the capability is disabled, + * kvm_multiple_exception would write the ancillary information to + * CR2 or DR6, for backwards ABI-compatibility. + */ + if (nested_vmx_is_page_fault_vmexit(vmcs12, + vcpu->arch.exception.error_code)) { + nested_vmx_inject_exception_vmexit(vcpu, vcpu->arch.cr2); + return 1; + } + } else { + unsigned long exit_qual = 0; + if (nr == DB_VECTOR) + exit_qual = vcpu->arch.dr6; - if (vcpu->arch.exception.nested_apf) { - vmcs_write32(VM_EXIT_INTR_ERROR_CODE, vcpu->arch.exception.error_code); - nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, - PF_VECTOR | INTR_TYPE_HARD_EXCEPTION | - INTR_INFO_DELIVER_CODE_MASK | INTR_INFO_VALID_MASK, - vcpu->arch.apf.nested_apf_token); - return 1; + if (vmcs12->exception_bitmap & (1u << nr)) { + nested_vmx_inject_exception_vmexit(vcpu, exit_qual); + return 1; + } } - nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, - vmcs_read32(VM_EXIT_INTR_INFO), - vmcs_readl(EXIT_QUALIFICATION)); - return 1; + return 0; } static void vmx_queue_exception(struct kvm_vcpu *vcpu) @@ -2668,7 +2700,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) * reason is that if one of these bits is necessary, it will appear * in vmcs01 and prepare_vmcs02, when it bitwise-or's the control * fields of vmcs01 and vmcs02, will turn these bits off - and - * nested_vmx_exit_handled() will not pass related exits to L1. + * nested_vmx_exit_reflected() will not pass related exits to L1. * These rules have exceptions below. */ @@ -4956,6 +4988,28 @@ static bool vmx_get_enable_apicv(void) return enable_apicv; } +static void nested_mark_vmcs12_pages_dirty(struct kvm_vcpu *vcpu) +{ + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + gfn_t gfn; + + /* + * Don't need to mark the APIC access page dirty; it is never + * written to by the CPU during APIC virtualization. + */ + + if (nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) { + gfn = vmcs12->virtual_apic_page_addr >> PAGE_SHIFT; + kvm_vcpu_mark_page_dirty(vcpu, gfn); + } + + if (nested_cpu_has_posted_intr(vmcs12)) { + gfn = vmcs12->posted_intr_desc_addr >> PAGE_SHIFT; + kvm_vcpu_mark_page_dirty(vcpu, gfn); + } +} + + static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -4963,18 +5017,15 @@ static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) void *vapic_page; u16 status; - if (vmx->nested.pi_desc && - vmx->nested.pi_pending) { - vmx->nested.pi_pending = false; - if (!pi_test_and_clear_on(vmx->nested.pi_desc)) - return; - - max_irr = find_last_bit( - (unsigned long *)vmx->nested.pi_desc->pir, 256); + if (!vmx->nested.pi_desc || !vmx->nested.pi_pending) + return; - if (max_irr == 256) - return; + vmx->nested.pi_pending = false; + if (!pi_test_and_clear_on(vmx->nested.pi_desc)) + return; + max_irr = find_last_bit((unsigned long *)vmx->nested.pi_desc->pir, 256); + if (max_irr != 256) { vapic_page = kmap(vmx->nested.virtual_apic_page); __kvm_apic_update_irr(vmx->nested.pi_desc->pir, vapic_page); kunmap(vmx->nested.virtual_apic_page); @@ -4986,11 +5037,16 @@ static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) vmcs_write16(GUEST_INTR_STATUS, status); } } + + nested_mark_vmcs12_pages_dirty(vcpu); } -static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu) +static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu, + bool nested) { #ifdef CONFIG_SMP + int pi_vec = nested ? POSTED_INTR_NESTED_VECTOR : POSTED_INTR_VECTOR; + if (vcpu->mode == IN_GUEST_MODE) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -5008,8 +5064,7 @@ static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu) */ WARN_ON_ONCE(pi_test_sn(&vmx->pi_desc)); - apic->send_IPI_mask(get_cpu_mask(vcpu->cpu), - POSTED_INTR_VECTOR); + apic->send_IPI_mask(get_cpu_mask(vcpu->cpu), pi_vec); return true; } #endif @@ -5024,7 +5079,7 @@ static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu, if (is_guest_mode(vcpu) && vector == vmx->nested.posted_intr_nv) { /* the PIR and ON have been set by L1. */ - kvm_vcpu_trigger_posted_interrupt(vcpu); + kvm_vcpu_trigger_posted_interrupt(vcpu, true); /* * If a posted intr is not recognized by hardware, * we will accomplish it in the next vmentry. @@ -5058,7 +5113,7 @@ static void vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector) if (pi_test_and_set_on(&vmx->pi_desc)) return; - if (!kvm_vcpu_trigger_posted_interrupt(vcpu)) + if (!kvm_vcpu_trigger_posted_interrupt(vcpu, false)) kvm_vcpu_kick(vcpu); } @@ -6501,7 +6556,7 @@ void vmx_enable_tdp(void) enable_ept_ad_bits ? VMX_EPT_DIRTY_BIT : 0ull, 0ull, VMX_EPT_EXECUTABLE_MASK, cpu_has_vmx_ept_execute_only() ? 0ull : VMX_EPT_READABLE_MASK, - VMX_EPT_RWX_MASK); + VMX_EPT_RWX_MASK, 0ull); ept_set_mmio_spte_mask(); kvm_enable_tdp(); @@ -7133,34 +7188,32 @@ static int nested_vmx_check_permission(struct kvm_vcpu *vcpu) return 1; } +static void vmx_disable_shadow_vmcs(struct vcpu_vmx *vmx) +{ + vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL, SECONDARY_EXEC_SHADOW_VMCS); + vmcs_write64(VMCS_LINK_POINTER, -1ull); +} + static inline void nested_release_vmcs12(struct vcpu_vmx *vmx) { if (vmx->nested.current_vmptr == -1ull) return; - /* current_vmptr and current_vmcs12 are always set/reset together */ - if (WARN_ON(vmx->nested.current_vmcs12 == NULL)) - return; - if (enable_shadow_vmcs) { /* copy to memory all shadowed fields in case they were modified */ copy_shadow_to_vmcs12(vmx); vmx->nested.sync_shadow_vmcs = false; - vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL, - SECONDARY_EXEC_SHADOW_VMCS); - vmcs_write64(VMCS_LINK_POINTER, -1ull); + vmx_disable_shadow_vmcs(vmx); } vmx->nested.posted_intr_nv = -1; /* Flush VMCS12 to guest memory */ - memcpy(vmx->nested.current_vmcs12, vmx->nested.cached_vmcs12, - VMCS12_SIZE); + kvm_vcpu_write_guest_page(&vmx->vcpu, + vmx->nested.current_vmptr >> PAGE_SHIFT, + vmx->nested.cached_vmcs12, 0, VMCS12_SIZE); - kunmap(vmx->nested.current_vmcs12_page); - nested_release_page(vmx->nested.current_vmcs12_page); vmx->nested.current_vmptr = -1ull; - vmx->nested.current_vmcs12 = NULL; } /* @@ -7174,12 +7227,14 @@ static void free_nested(struct vcpu_vmx *vmx) vmx->nested.vmxon = false; free_vpid(vmx->nested.vpid02); - nested_release_vmcs12(vmx); + vmx->nested.posted_intr_nv = -1; + vmx->nested.current_vmptr = -1ull; if (vmx->nested.msr_bitmap) { free_page((unsigned long)vmx->nested.msr_bitmap); vmx->nested.msr_bitmap = NULL; } if (enable_shadow_vmcs) { + vmx_disable_shadow_vmcs(vmx); vmcs_clear(vmx->vmcs01.shadow_vmcs); free_vmcs(vmx->vmcs01.shadow_vmcs); vmx->vmcs01.shadow_vmcs = NULL; @@ -7578,14 +7633,14 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) } nested_release_vmcs12(vmx); - vmx->nested.current_vmcs12 = new_vmcs12; - vmx->nested.current_vmcs12_page = page; /* * Load VMCS12 from guest memory since it is not already * cached. */ - memcpy(vmx->nested.cached_vmcs12, - vmx->nested.current_vmcs12, VMCS12_SIZE); + memcpy(vmx->nested.cached_vmcs12, new_vmcs12, VMCS12_SIZE); + kunmap(page); + nested_release_page_clean(page); + set_current_vmptr(vmx, vmptr); } @@ -8018,12 +8073,11 @@ static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu, * should handle it ourselves in L0 (and then continue L2). Only call this * when in is_guest_mode (L2). */ -static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) +static bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason) { u32 intr_info = vmcs_read32(VM_EXIT_INTR_INFO); struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - u32 exit_reason = vmx->exit_reason; trace_kvm_nested_vmexit(kvm_rip_read(vcpu), exit_reason, vmcs_readl(EXIT_QUALIFICATION), @@ -8032,6 +8086,18 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) vmcs_read32(VM_EXIT_INTR_ERROR_CODE), KVM_ISA_VMX); + /* + * The host physical addresses of some pages of guest memory + * are loaded into VMCS02 (e.g. L1's Virtual APIC Page). The CPU + * may write to these pages via their host physical address while + * L2 is running, bypassing any address-translation-based dirty + * tracking (e.g. EPT write protection). + * + * Mark them dirty on every exit from L2 to prevent them from + * getting out of sync with dirty tracking. + */ + nested_mark_vmcs12_pages_dirty(vcpu); + if (vmx->nested.nested_run_pending) return false; @@ -8168,6 +8234,29 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) } } +static int nested_vmx_reflect_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason) +{ + u32 exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO); + + /* + * At this point, the exit interruption info in exit_intr_info + * is only valid for EXCEPTION_NMI exits. For EXTERNAL_INTERRUPT + * we need to query the in-kernel LAPIC. + */ + WARN_ON(exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT); + if ((exit_intr_info & + (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK)) == + (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK)) { + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + vmcs12->vm_exit_intr_error_code = + vmcs_read32(VM_EXIT_INTR_ERROR_CODE); + } + + nested_vmx_vmexit(vcpu, exit_reason, exit_intr_info, + vmcs_readl(EXIT_QUALIFICATION)); + return 1; +} + static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2) { *info1 = vmcs_readl(EXIT_QUALIFICATION); @@ -8414,12 +8503,8 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) if (vmx->emulation_required) return handle_invalid_guest_state(vcpu); - if (is_guest_mode(vcpu) && nested_vmx_exit_handled(vcpu)) { - nested_vmx_vmexit(vcpu, exit_reason, - vmcs_read32(VM_EXIT_INTR_INFO), - vmcs_readl(EXIT_QUALIFICATION)); - return 1; - } + if (is_guest_mode(vcpu) && nested_vmx_exit_reflected(vcpu, exit_reason)) + return nested_vmx_reflect_vmexit(vcpu, exit_reason); if (exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY) { dump_vmcs(); @@ -8694,7 +8779,7 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu) vector = exit_intr_info & INTR_INFO_VECTOR_MASK; desc = (gate_desc *)vmx->host_idt_base + vector; - entry = gate_offset(*desc); + entry = gate_offset(desc); asm volatile( #ifdef CONFIG_X86_64 "mov %%" _ASM_SP ", %[sp]\n\t" @@ -8928,8 +9013,10 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) vmx_set_interrupt_shadow(vcpu, 0); - if (vmx->guest_pkru_valid) - __write_pkru(vmx->guest_pkru); + if (static_cpu_has(X86_FEATURE_PKU) && + kvm_read_cr4_bits(vcpu, X86_CR4_PKE) && + vcpu->arch.pkru != vmx->host_pkru) + __write_pkru(vcpu->arch.pkru); atomic_switch_perf_msrs(vmx); debugctlmsr = get_debugctlmsr(); @@ -9077,13 +9164,11 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) * back on host, so it is safe to read guest PKRU from current * XSAVE. */ - if (boot_cpu_has(X86_FEATURE_OSPKE)) { - vmx->guest_pkru = __read_pkru(); - if (vmx->guest_pkru != vmx->host_pkru) { - vmx->guest_pkru_valid = true; + if (static_cpu_has(X86_FEATURE_PKU) && + kvm_read_cr4_bits(vcpu, X86_CR4_PKE)) { + vcpu->arch.pkru = __read_pkru(); + if (vcpu->arch.pkru != vmx->host_pkru) __write_pkru(vmx->host_pkru); - } else - vmx->guest_pkru_valid = false; } /* @@ -9222,7 +9307,6 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) vmx->nested.posted_intr_nv = -1; vmx->nested.current_vmptr = -1ull; - vmx->nested.current_vmcs12 = NULL; vmx->msr_ia32_feature_control_valid_bits = FEATURE_CONTROL_LOCKED; @@ -9508,12 +9592,15 @@ static void vmx_inject_page_fault_nested(struct kvm_vcpu *vcpu, WARN_ON(!is_guest_mode(vcpu)); - if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code)) - nested_vmx_vmexit(vcpu, to_vmx(vcpu)->exit_reason, - vmcs_read32(VM_EXIT_INTR_INFO), - vmcs_readl(EXIT_QUALIFICATION)); - else + if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code)) { + vmcs12->vm_exit_intr_error_code = fault->error_code; + nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, + PF_VECTOR | INTR_TYPE_HARD_EXCEPTION | + INTR_INFO_DELIVER_CODE_MASK | INTR_INFO_VALID_MASK, + fault->address); + } else { kvm_inject_page_fault(vcpu, fault); + } } static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu, @@ -10041,6 +10128,8 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmcs12->vm_entry_instruction_len); vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, vmcs12->guest_interruptibility_info); + vmx->loaded_vmcs->nmi_known_unmasked = + !(vmcs12->guest_interruptibility_info & GUEST_INTR_STATE_NMI); } else { vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0); } @@ -10065,13 +10154,9 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, /* Posted interrupts setting is only taken from vmcs12. */ if (nested_cpu_has_posted_intr(vmcs12)) { - /* - * Note that we use L0's vector here and in - * vmx_deliver_nested_posted_interrupt. - */ vmx->nested.posted_intr_nv = vmcs12->posted_intr_nv; vmx->nested.pi_pending = false; - vmcs_write16(POSTED_INTR_NV, POSTED_INTR_VECTOR); + vmcs_write16(POSTED_INTR_NV, POSTED_INTR_NESTED_VECTOR); } else { exec_control &= ~PIN_BASED_POSTED_INTR; } @@ -10095,12 +10180,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, * "or"ing of the EB of vmcs01 and vmcs12, because when enable_ept, * vmcs01's EB.PF is 0 so the "or" will take vmcs12's value, and when * !enable_ept, EB.PF is 1, so the "or" will always be 1. - * - * A problem with this approach (when !enable_ept) is that L1 may be - * injected with more page faults than it asked for. This could have - * caused problems, but in practice existing hypervisors don't care. - * To fix this, we will need to emulate the PFEC checking (on the L1 - * page tables), using walk_addr(), when injecting PFs to L1. */ vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, enable_ept ? vmcs12->page_fault_error_code_mask : 0); @@ -10848,13 +10927,8 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmcs12->vm_exit_reason = exit_reason; vmcs12->exit_qualification = exit_qualification; - vmcs12->vm_exit_intr_info = exit_intr_info; - if ((vmcs12->vm_exit_intr_info & - (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK)) == - (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK)) - vmcs12->vm_exit_intr_error_code = - vmcs_read32(VM_EXIT_INTR_ERROR_CODE); + vmcs12->idt_vectoring_info_field = 0; vmcs12->vm_exit_instruction_len = vmcs_read32(VM_EXIT_INSTRUCTION_LEN); vmcs12->vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); @@ -10942,7 +11016,9 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, */ vmx_flush_tlb(vcpu); } - + /* Restore posted intr vector. */ + if (nested_cpu_has_posted_intr(vmcs12)) + vmcs_write16(POSTED_INTR_NV, POSTED_INTR_VECTOR); vmcs_write32(GUEST_SYSENTER_CS, vmcs12->host_ia32_sysenter_cs); vmcs_writel(GUEST_SYSENTER_ESP, vmcs12->host_ia32_sysenter_esp); @@ -11048,8 +11124,15 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, vmx_switch_vmcs(vcpu, &vmx->vmcs01); - if ((exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT) - && nested_exit_intr_ack_set(vcpu)) { + /* + * TODO: SDM says that with acknowledge interrupt on exit, bit 31 of + * the VM-exit interrupt information (valid interrupt) is always set to + * 1 on EXIT_REASON_EXTERNAL_INTERRUPT, so we shouldn't need + * kvm_cpu_has_interrupt(). See the commit message for details. + */ + if (nested_exit_intr_ack_set(vcpu) && + exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT && + kvm_cpu_has_interrupt(vcpu)) { int irq = kvm_cpu_get_interrupt(vcpu); WARN_ON(irq < 0); vmcs12->vm_exit_intr_info = irq | @@ -11592,8 +11675,6 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .get_rflags = vmx_get_rflags, .set_rflags = vmx_set_rflags, - .get_pkru = vmx_get_pkru, - .tlb_flush = vmx_flush_tlb, .run = vmx_vcpu_run, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 82a63c59f77b..ef5102f80497 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -54,6 +54,7 @@ #include <linux/kvm_irqfd.h> #include <linux/irqbypass.h> #include <linux/sched/stat.h> +#include <linux/mem_encrypt.h> #include <trace/events/kvm.h> @@ -597,8 +598,8 @@ bool pdptrs_changed(struct kvm_vcpu *vcpu) (unsigned long *)&vcpu->arch.regs_avail)) return true; - gfn = (kvm_read_cr3(vcpu) & ~31ul) >> PAGE_SHIFT; - offset = (kvm_read_cr3(vcpu) & ~31ul) & (PAGE_SIZE - 1); + gfn = (kvm_read_cr3(vcpu) & 0xffffffe0ul) >> PAGE_SHIFT; + offset = (kvm_read_cr3(vcpu) & 0xffffffe0ul) & (PAGE_SIZE - 1); r = kvm_read_nested_guest_page(vcpu, gfn, pdpte, offset, sizeof(pdpte), PFERR_USER_MASK | PFERR_WRITE_MASK); if (r < 0) @@ -3159,15 +3160,18 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, kvm_set_hflags(vcpu, hflags); vcpu->arch.smi_pending = events->smi.pending; - if (events->smi.smm_inside_nmi) - vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK; - else - vcpu->arch.hflags &= ~HF_SMM_INSIDE_NMI_MASK; - if (lapic_in_kernel(vcpu)) { - if (events->smi.latched_init) - set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); + + if (events->smi.smm) { + if (events->smi.smm_inside_nmi) + vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK; else - clear_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); + vcpu->arch.hflags &= ~HF_SMM_INSIDE_NMI_MASK; + if (lapic_in_kernel(vcpu)) { + if (events->smi.latched_init) + set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); + else + clear_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); + } } } @@ -3242,7 +3246,12 @@ static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu) u32 size, offset, ecx, edx; cpuid_count(XSTATE_CPUID, index, &size, &offset, &ecx, &edx); - memcpy(dest + offset, src, size); + if (feature == XFEATURE_MASK_PKRU) + memcpy(dest + offset, &vcpu->arch.pkru, + sizeof(vcpu->arch.pkru)); + else + memcpy(dest + offset, src, size); + } valid -= feature; @@ -3280,7 +3289,11 @@ static void load_xsave(struct kvm_vcpu *vcpu, u8 *src) u32 size, offset, ecx, edx; cpuid_count(XSTATE_CPUID, index, &size, &offset, &ecx, &edx); - memcpy(dest, src + offset, size); + if (feature == XFEATURE_MASK_PKRU) + memcpy(&vcpu->arch.pkru, src + offset, + sizeof(vcpu->arch.pkru)); + else + memcpy(dest, src + offset, size); } valid -= feature; @@ -6113,7 +6126,7 @@ int kvm_arch_init(void *opaque) kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK, PT_DIRTY_MASK, PT64_NX_MASK, 0, - PT_PRESENT_MASK, 0); + PT_PRESENT_MASK, 0, sme_me_mask); kvm_timer_init(); perf_register_guest_info_callbacks(&kvm_guest_cbs); @@ -6215,6 +6228,7 @@ static void kvm_pv_kick_cpu_op(struct kvm *kvm, unsigned long flags, int apicid) lapic_irq.shorthand = 0; lapic_irq.dest_mode = 0; + lapic_irq.level = 0; lapic_irq.dest_id = apicid; lapic_irq.msi_redir_hint = false; @@ -6721,17 +6735,6 @@ void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_vcpu_reload_apic_access_page); -void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm, - unsigned long address) -{ - /* - * The physical address of apic access page is stored in the VMCS. - * Update it when it becomes invalid. - */ - if (address == gfn_to_hva(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT)) - kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD); -} - /* * Returns 1 to let vcpu_run() continue the guest execution loop without * exiting to the userspace. Otherwise, the value will be returned to the @@ -7629,7 +7632,9 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) */ vcpu->guest_fpu_loaded = 1; __kernel_fpu_begin(); - __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state); + /* PKRU is separately restored in kvm_x86_ops->run. */ + __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state, + ~XFEATURE_MASK_PKRU); trace_kvm_fpu(1); } diff --git a/arch/x86/lguest/Kconfig b/arch/x86/lguest/Kconfig deleted file mode 100644 index 08f41caada45..000000000000 --- a/arch/x86/lguest/Kconfig +++ /dev/null @@ -1,14 +0,0 @@ -config LGUEST_GUEST - bool "Lguest guest support" - depends on X86_32 && PARAVIRT && PCI - select TTY - select VIRTUALIZATION - select VIRTIO - select VIRTIO_CONSOLE - help - Lguest is a tiny in-kernel hypervisor. Selecting this will - allow your kernel to boot under lguest. This option will increase - your kernel size by about 10k. If in doubt, say N. - - If you say Y here, make sure you say Y (or M) to the virtio block - and net drivers which lguest needs. diff --git a/arch/x86/lguest/Makefile b/arch/x86/lguest/Makefile deleted file mode 100644 index 8f38d577a2fa..000000000000 --- a/arch/x86/lguest/Makefile +++ /dev/null @@ -1,2 +0,0 @@ -obj-y := head_32.o boot.o -CFLAGS_boot.o := $(call cc-option, -fno-stack-protector) diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c deleted file mode 100644 index 99472698c931..000000000000 --- a/arch/x86/lguest/boot.c +++ /dev/null @@ -1,1558 +0,0 @@ -/*P:010 - * A hypervisor allows multiple Operating Systems to run on a single machine. - * To quote David Wheeler: "Any problem in computer science can be solved with - * another layer of indirection." - * - * We keep things simple in two ways. First, we start with a normal Linux - * kernel and insert a module (lg.ko) which allows us to run other Linux - * kernels the same way we'd run processes. We call the first kernel the Host, - * and the others the Guests. The program which sets up and configures Guests - * (such as the example in tools/lguest/lguest.c) is called the Launcher. - * - * Secondly, we only run specially modified Guests, not normal kernels: setting - * CONFIG_LGUEST_GUEST to "y" compiles this file into the kernel so it knows - * how to be a Guest at boot time. This means that you can use the same kernel - * you boot normally (ie. as a Host) as a Guest. - * - * These Guests know that they cannot do privileged operations, such as disable - * interrupts, and that they have to ask the Host to do such things explicitly. - * This file consists of all the replacements for such low-level native - * hardware operations: these special Guest versions call the Host. - * - * So how does the kernel know it's a Guest? We'll see that later, but let's - * just say that we end up here where we replace the native functions various - * "paravirt" structures with our Guest versions, then boot like normal. -:*/ - -/* - * Copyright (C) 2006, Rusty Russell <rusty@rustcorp.com.au> IBM Corporation. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or - * NON INFRINGEMENT. See the GNU General Public License for more - * details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. - */ -#include <linux/kernel.h> -#include <linux/start_kernel.h> -#include <linux/string.h> -#include <linux/console.h> -#include <linux/screen_info.h> -#include <linux/irq.h> -#include <linux/interrupt.h> -#include <linux/clocksource.h> -#include <linux/clockchips.h> -#include <linux/lguest.h> -#include <linux/lguest_launcher.h> -#include <linux/virtio_console.h> -#include <linux/pm.h> -#include <linux/export.h> -#include <linux/pci.h> -#include <linux/virtio_pci.h> -#include <asm/acpi.h> -#include <asm/apic.h> -#include <asm/lguest.h> -#include <asm/paravirt.h> -#include <asm/param.h> -#include <asm/page.h> -#include <asm/pgtable.h> -#include <asm/desc.h> -#include <asm/setup.h> -#include <asm/e820/api.h> -#include <asm/mce.h> -#include <asm/io.h> -#include <asm/fpu/api.h> -#include <asm/stackprotector.h> -#include <asm/reboot.h> /* for struct machine_ops */ -#include <asm/kvm_para.h> -#include <asm/pci_x86.h> -#include <asm/pci-direct.h> - -/*G:010 - * Welcome to the Guest! - * - * The Guest in our tale is a simple creature: identical to the Host but - * behaving in simplified but equivalent ways. In particular, the Guest is the - * same kernel as the Host (or at least, built from the same source code). -:*/ - -struct lguest_data lguest_data = { - .hcall_status = { [0 ... LHCALL_RING_SIZE-1] = 0xFF }, - .noirq_iret = (u32)lguest_noirq_iret, - .kernel_address = PAGE_OFFSET, - .blocked_interrupts = { 1 }, /* Block timer interrupts */ - .syscall_vec = IA32_SYSCALL_VECTOR, -}; - -/*G:037 - * async_hcall() is pretty simple: I'm quite proud of it really. We have a - * ring buffer of stored hypercalls which the Host will run though next time we - * do a normal hypercall. Each entry in the ring has 5 slots for the hypercall - * arguments, and a "hcall_status" word which is 0 if the call is ready to go, - * and 255 once the Host has finished with it. - * - * If we come around to a slot which hasn't been finished, then the table is - * full and we just make the hypercall directly. This has the nice side - * effect of causing the Host to run all the stored calls in the ring buffer - * which empties it for next time! - */ -static void async_hcall(unsigned long call, unsigned long arg1, - unsigned long arg2, unsigned long arg3, - unsigned long arg4) -{ - /* Note: This code assumes we're uniprocessor. */ - static unsigned int next_call; - unsigned long flags; - - /* - * Disable interrupts if not already disabled: we don't want an - * interrupt handler making a hypercall while we're already doing - * one! - */ - local_irq_save(flags); - if (lguest_data.hcall_status[next_call] != 0xFF) { - /* Table full, so do normal hcall which will flush table. */ - hcall(call, arg1, arg2, arg3, arg4); - } else { - lguest_data.hcalls[next_call].arg0 = call; - lguest_data.hcalls[next_call].arg1 = arg1; - lguest_data.hcalls[next_call].arg2 = arg2; - lguest_data.hcalls[next_call].arg3 = arg3; - lguest_data.hcalls[next_call].arg4 = arg4; - /* Arguments must all be written before we mark it to go */ - wmb(); - lguest_data.hcall_status[next_call] = 0; - if (++next_call == LHCALL_RING_SIZE) - next_call = 0; - } - local_irq_restore(flags); -} - -/*G:035 - * Notice the lazy_hcall() above, rather than hcall(). This is our first real - * optimization trick! - * - * When lazy_mode is set, it means we're allowed to defer all hypercalls and do - * them as a batch when lazy_mode is eventually turned off. Because hypercalls - * are reasonably expensive, batching them up makes sense. For example, a - * large munmap might update dozens of page table entries: that code calls - * paravirt_enter_lazy_mmu(), does the dozen updates, then calls - * lguest_leave_lazy_mode(). - * - * So, when we're in lazy mode, we call async_hcall() to store the call for - * future processing: - */ -static void lazy_hcall1(unsigned long call, unsigned long arg1) -{ - if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) - hcall(call, arg1, 0, 0, 0); - else - async_hcall(call, arg1, 0, 0, 0); -} - -/* You can imagine what lazy_hcall2, 3 and 4 look like. :*/ -static void lazy_hcall2(unsigned long call, - unsigned long arg1, - unsigned long arg2) -{ - if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) - hcall(call, arg1, arg2, 0, 0); - else - async_hcall(call, arg1, arg2, 0, 0); -} - -static void lazy_hcall3(unsigned long call, - unsigned long arg1, - unsigned long arg2, - unsigned long arg3) -{ - if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) - hcall(call, arg1, arg2, arg3, 0); - else - async_hcall(call, arg1, arg2, arg3, 0); -} - -#ifdef CONFIG_X86_PAE -static void lazy_hcall4(unsigned long call, - unsigned long arg1, - unsigned long arg2, - unsigned long arg3, - unsigned long arg4) -{ - if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) - hcall(call, arg1, arg2, arg3, arg4); - else - async_hcall(call, arg1, arg2, arg3, arg4); -} -#endif - -/*G:036 - * When lazy mode is turned off, we issue the do-nothing hypercall to - * flush any stored calls, and call the generic helper to reset the - * per-cpu lazy mode variable. - */ -static void lguest_leave_lazy_mmu_mode(void) -{ - hcall(LHCALL_FLUSH_ASYNC, 0, 0, 0, 0); - paravirt_leave_lazy_mmu(); -} - -/* - * We also catch the end of context switch; we enter lazy mode for much of - * that too, so again we need to flush here. - * - * (Technically, this is lazy CPU mode, and normally we're in lazy MMU - * mode, but unlike Xen, lguest doesn't care about the difference). - */ -static void lguest_end_context_switch(struct task_struct *next) -{ - hcall(LHCALL_FLUSH_ASYNC, 0, 0, 0, 0); - paravirt_end_context_switch(next); -} - -/*G:032 - * After that diversion we return to our first native-instruction - * replacements: four functions for interrupt control. - * - * The simplest way of implementing these would be to have "turn interrupts - * off" and "turn interrupts on" hypercalls. Unfortunately, this is too slow: - * these are by far the most commonly called functions of those we override. - * - * So instead we keep an "irq_enabled" field inside our "struct lguest_data", - * which the Guest can update with a single instruction. The Host knows to - * check there before it tries to deliver an interrupt. - */ - -/* - * save_flags() is expected to return the processor state (ie. "flags"). The - * flags word contains all kind of stuff, but in practice Linux only cares - * about the interrupt flag. Our "save_flags()" just returns that. - */ -asmlinkage __visible unsigned long lguest_save_fl(void) -{ - return lguest_data.irq_enabled; -} - -/* Interrupts go off... */ -asmlinkage __visible void lguest_irq_disable(void) -{ - lguest_data.irq_enabled = 0; -} - -/* - * Let's pause a moment. Remember how I said these are called so often? - * Jeremy Fitzhardinge optimized them so hard early in 2009 that he had to - * break some rules. In particular, these functions are assumed to save their - * own registers if they need to: normal C functions assume they can trash the - * eax register. To use normal C functions, we use - * PV_CALLEE_SAVE_REGS_THUNK(), which pushes %eax onto the stack, calls the - * C function, then restores it. - */ -PV_CALLEE_SAVE_REGS_THUNK(lguest_save_fl); -PV_CALLEE_SAVE_REGS_THUNK(lguest_irq_disable); -/*:*/ - -/* These are in head_32.S */ -extern void lg_irq_enable(void); -extern void lg_restore_fl(unsigned long flags); - -/*M:003 - * We could be more efficient in our checking of outstanding interrupts, rather - * than using a branch. One way would be to put the "irq_enabled" field in a - * page by itself, and have the Host write-protect it when an interrupt comes - * in when irqs are disabled. There will then be a page fault as soon as - * interrupts are re-enabled. - * - * A better method is to implement soft interrupt disable generally for x86: - * instead of disabling interrupts, we set a flag. If an interrupt does come - * in, we then disable them for real. This is uncommon, so we could simply use - * a hypercall for interrupt control and not worry about efficiency. -:*/ - -/*G:034 - * The Interrupt Descriptor Table (IDT). - * - * The IDT tells the processor what to do when an interrupt comes in. Each - * entry in the table is a 64-bit descriptor: this holds the privilege level, - * address of the handler, and... well, who cares? The Guest just asks the - * Host to make the change anyway, because the Host controls the real IDT. - */ -static void lguest_write_idt_entry(gate_desc *dt, - int entrynum, const gate_desc *g) -{ - /* - * The gate_desc structure is 8 bytes long: we hand it to the Host in - * two 32-bit chunks. The whole 32-bit kernel used to hand descriptors - * around like this; typesafety wasn't a big concern in Linux's early - * years. - */ - u32 *desc = (u32 *)g; - /* Keep the local copy up to date. */ - native_write_idt_entry(dt, entrynum, g); - /* Tell Host about this new entry. */ - hcall(LHCALL_LOAD_IDT_ENTRY, entrynum, desc[0], desc[1], 0); -} - -/* - * Changing to a different IDT is very rare: we keep the IDT up-to-date every - * time it is written, so we can simply loop through all entries and tell the - * Host about them. - */ -static void lguest_load_idt(const struct desc_ptr *desc) -{ - unsigned int i; - struct desc_struct *idt = (void *)desc->address; - - for (i = 0; i < (desc->size+1)/8; i++) - hcall(LHCALL_LOAD_IDT_ENTRY, i, idt[i].a, idt[i].b, 0); -} - -/* - * The Global Descriptor Table. - * - * The Intel architecture defines another table, called the Global Descriptor - * Table (GDT). You tell the CPU where it is (and its size) using the "lgdt" - * instruction, and then several other instructions refer to entries in the - * table. There are three entries which the Switcher needs, so the Host simply - * controls the entire thing and the Guest asks it to make changes using the - * LOAD_GDT hypercall. - * - * This is the exactly like the IDT code. - */ -static void lguest_load_gdt(const struct desc_ptr *desc) -{ - unsigned int i; - struct desc_struct *gdt = (void *)desc->address; - - for (i = 0; i < (desc->size+1)/8; i++) - hcall(LHCALL_LOAD_GDT_ENTRY, i, gdt[i].a, gdt[i].b, 0); -} - -/* - * For a single GDT entry which changes, we simply change our copy and - * then tell the host about it. - */ -static void lguest_write_gdt_entry(struct desc_struct *dt, int entrynum, - const void *desc, int type) -{ - native_write_gdt_entry(dt, entrynum, desc, type); - /* Tell Host about this new entry. */ - hcall(LHCALL_LOAD_GDT_ENTRY, entrynum, - dt[entrynum].a, dt[entrynum].b, 0); -} - -/* - * There are three "thread local storage" GDT entries which change - * on every context switch (these three entries are how glibc implements - * __thread variables). As an optimization, we have a hypercall - * specifically for this case. - * - * Wouldn't it be nicer to have a general LOAD_GDT_ENTRIES hypercall - * which took a range of entries? - */ -static void lguest_load_tls(struct thread_struct *t, unsigned int cpu) -{ - /* - * There's one problem which normal hardware doesn't have: the Host - * can't handle us removing entries we're currently using. So we clear - * the GS register here: if it's needed it'll be reloaded anyway. - */ - lazy_load_gs(0); - lazy_hcall2(LHCALL_LOAD_TLS, __pa(&t->tls_array), cpu); -} - -/*G:038 - * That's enough excitement for now, back to ploughing through each of the - * different pv_ops structures (we're about 1/3 of the way through). - * - * This is the Local Descriptor Table, another weird Intel thingy. Linux only - * uses this for some strange applications like Wine. We don't do anything - * here, so they'll get an informative and friendly Segmentation Fault. - */ -static void lguest_set_ldt(const void *addr, unsigned entries) -{ -} - -/* - * This loads a GDT entry into the "Task Register": that entry points to a - * structure called the Task State Segment. Some comments scattered though the - * kernel code indicate that this used for task switching in ages past, along - * with blood sacrifice and astrology. - * - * Now there's nothing interesting in here that we don't get told elsewhere. - * But the native version uses the "ltr" instruction, which makes the Host - * complain to the Guest about a Segmentation Fault and it'll oops. So we - * override the native version with a do-nothing version. - */ -static void lguest_load_tr_desc(void) -{ -} - -/* - * The "cpuid" instruction is a way of querying both the CPU identity - * (manufacturer, model, etc) and its features. It was introduced before the - * Pentium in 1993 and keeps getting extended by both Intel, AMD and others. - * As you might imagine, after a decade and a half this treatment, it is now a - * giant ball of hair. Its entry in the current Intel manual runs to 28 pages. - * - * This instruction even it has its own Wikipedia entry. The Wikipedia entry - * has been translated into 6 languages. I am not making this up! - * - * We could get funky here and identify ourselves as "GenuineLguest", but - * instead we just use the real "cpuid" instruction. Then I pretty much turned - * off feature bits until the Guest booted. (Don't say that: you'll damage - * lguest sales!) Shut up, inner voice! (Hey, just pointing out that this is - * hardly future proof.) No one's listening! They don't like you anyway, - * parenthetic weirdo! - * - * Replacing the cpuid so we can turn features off is great for the kernel, but - * anyone (including userspace) can just use the raw "cpuid" instruction and - * the Host won't even notice since it isn't privileged. So we try not to get - * too worked up about it. - */ -static void lguest_cpuid(unsigned int *ax, unsigned int *bx, - unsigned int *cx, unsigned int *dx) -{ - int function = *ax; - - native_cpuid(ax, bx, cx, dx); - switch (function) { - /* - * CPUID 0 gives the highest legal CPUID number (and the ID string). - * We futureproof our code a little by sticking to known CPUID values. - */ - case 0: - if (*ax > 5) - *ax = 5; - break; - - /* - * CPUID 1 is a basic feature request. - * - * CX: we only allow kernel to see SSE3, CMPXCHG16B and SSSE3 - * DX: SSE, SSE2, FXSR, MMX, CMOV, CMPXCHG8B, TSC, FPU and PAE. - */ - case 1: - *cx &= 0x00002201; - *dx &= 0x07808151; - /* - * The Host can do a nice optimization if it knows that the - * kernel mappings (addresses above 0xC0000000 or whatever - * PAGE_OFFSET is set to) haven't changed. But Linux calls - * flush_tlb_user() for both user and kernel mappings unless - * the Page Global Enable (PGE) feature bit is set. - */ - *dx |= 0x00002000; - /* - * We also lie, and say we're family id 5. 6 or greater - * leads to a rdmsr in early_init_intel which we can't handle. - * Family ID is returned as bits 8-12 in ax. - */ - *ax &= 0xFFFFF0FF; - *ax |= 0x00000500; - break; - - /* - * This is used to detect if we're running under KVM. We might be, - * but that's a Host matter, not us. So say we're not. - */ - case KVM_CPUID_SIGNATURE: - *bx = *cx = *dx = 0; - break; - - /* - * 0x80000000 returns the highest Extended Function, so we futureproof - * like we do above by limiting it to known fields. - */ - case 0x80000000: - if (*ax > 0x80000008) - *ax = 0x80000008; - break; - - /* - * PAE systems can mark pages as non-executable. Linux calls this the - * NX bit. Intel calls it XD (eXecute Disable), AMD EVP (Enhanced - * Virus Protection). We just switch it off here, since we don't - * support it. - */ - case 0x80000001: - *dx &= ~(1 << 20); - break; - } -} - -/* - * Intel has four control registers, imaginatively named cr0, cr2, cr3 and cr4. - * I assume there's a cr1, but it hasn't bothered us yet, so we'll not bother - * it. The Host needs to know when the Guest wants to change them, so we have - * a whole series of functions like read_cr0() and write_cr0(). - * - * We start with cr0. cr0 allows you to turn on and off all kinds of basic - * features, but the only cr0 bit that Linux ever used at runtime was the - * horrifically-named Task Switched (TS) bit at bit 3 (ie. 8) - * - * What does the TS bit do? Well, it causes the CPU to trap (interrupt 7) if - * the floating point unit is used. Which allows us to restore FPU state - * lazily after a task switch if we wanted to, but wouldn't a name like - * "FPUTRAP bit" be a little less cryptic? - * - * Fortunately, Linux keeps it simple and doesn't use TS, so we can ignore - * cr0. - */ -static void lguest_write_cr0(unsigned long val) -{ -} - -static unsigned long lguest_read_cr0(void) -{ - return 0; -} - -/* - * cr2 is the virtual address of the last page fault, which the Guest only ever - * reads. The Host kindly writes this into our "struct lguest_data", so we - * just read it out of there. - */ -static unsigned long lguest_read_cr2(void) -{ - return lguest_data.cr2; -} - -/* See lguest_set_pte() below. */ -static bool cr3_changed = false; -static unsigned long current_cr3; - -/* - * cr3 is the current toplevel pagetable page: the principle is the same as - * cr0. Keep a local copy, and tell the Host when it changes. - */ -static void lguest_write_cr3(unsigned long cr3) -{ - lazy_hcall1(LHCALL_NEW_PGTABLE, cr3); - current_cr3 = cr3; - - /* These two page tables are simple, linear, and used during boot */ - if (cr3 != __pa_symbol(swapper_pg_dir) && - cr3 != __pa_symbol(initial_page_table)) - cr3_changed = true; -} - -static unsigned long lguest_read_cr3(void) -{ - return current_cr3; -} - -/* cr4 is used to enable and disable PGE, but we don't care. */ -static unsigned long lguest_read_cr4(void) -{ - return 0; -} - -static void lguest_write_cr4(unsigned long val) -{ -} - -/* - * Page Table Handling. - * - * Now would be a good time to take a rest and grab a coffee or similarly - * relaxing stimulant. The easy parts are behind us, and the trek gradually - * winds uphill from here. - * - * Quick refresher: memory is divided into "pages" of 4096 bytes each. The CPU - * maps virtual addresses to physical addresses using "page tables". We could - * use one huge index of 1 million entries: each address is 4 bytes, so that's - * 1024 pages just to hold the page tables. But since most virtual addresses - * are unused, we use a two level index which saves space. The cr3 register - * contains the physical address of the top level "page directory" page, which - * contains physical addresses of up to 1024 second-level pages. Each of these - * second level pages contains up to 1024 physical addresses of actual pages, - * or Page Table Entries (PTEs). - * - * Here's a diagram, where arrows indicate physical addresses: - * - * cr3 ---> +---------+ - * | --------->+---------+ - * | | | PADDR1 | - * Mid-level | | PADDR2 | - * (PMD) page | | | - * | | Lower-level | - * | | (PTE) page | - * | | | | - * .... .... - * - * So to convert a virtual address to a physical address, we look up the top - * level, which points us to the second level, which gives us the physical - * address of that page. If the top level entry was not present, or the second - * level entry was not present, then the virtual address is invalid (we - * say "the page was not mapped"). - * - * Put another way, a 32-bit virtual address is divided up like so: - * - * 1 1 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 - * |<---- 10 bits ---->|<---- 10 bits ---->|<------ 12 bits ------>| - * Index into top Index into second Offset within page - * page directory page pagetable page - * - * Now, unfortunately, this isn't the whole story: Intel added Physical Address - * Extension (PAE) to allow 32 bit systems to use 64GB of memory (ie. 36 bits). - * These are held in 64-bit page table entries, so we can now only fit 512 - * entries in a page, and the neat three-level tree breaks down. - * - * The result is a four level page table: - * - * cr3 --> [ 4 Upper ] - * [ Level ] - * [ Entries ] - * [(PUD Page)]---> +---------+ - * | --------->+---------+ - * | | | PADDR1 | - * Mid-level | | PADDR2 | - * (PMD) page | | | - * | | Lower-level | - * | | (PTE) page | - * | | | | - * .... .... - * - * - * And the virtual address is decoded as: - * - * 1 1 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 - * |<-2->|<--- 9 bits ---->|<---- 9 bits --->|<------ 12 bits ------>| - * Index into Index into mid Index into lower Offset within page - * top entries directory page pagetable page - * - * It's too hard to switch between these two formats at runtime, so Linux only - * supports one or the other depending on whether CONFIG_X86_PAE is set. Many - * distributions turn it on, and not just for people with silly amounts of - * memory: the larger PTE entries allow room for the NX bit, which lets the - * kernel disable execution of pages and increase security. - * - * This was a problem for lguest, which couldn't run on these distributions; - * then Matias Zabaljauregui figured it all out and implemented it, and only a - * handful of puppies were crushed in the process! - * - * Back to our point: the kernel spends a lot of time changing both the - * top-level page directory and lower-level pagetable pages. The Guest doesn't - * know physical addresses, so while it maintains these page tables exactly - * like normal, it also needs to keep the Host informed whenever it makes a - * change: the Host will create the real page tables based on the Guests'. - */ - -/* - * The Guest calls this after it has set a second-level entry (pte), ie. to map - * a page into a process' address space. We tell the Host the toplevel and - * address this corresponds to. The Guest uses one pagetable per process, so - * we need to tell the Host which one we're changing (mm->pgd). - */ -static void lguest_pte_update(struct mm_struct *mm, unsigned long addr, - pte_t *ptep) -{ -#ifdef CONFIG_X86_PAE - /* PAE needs to hand a 64 bit page table entry, so it uses two args. */ - lazy_hcall4(LHCALL_SET_PTE, __pa(mm->pgd), addr, - ptep->pte_low, ptep->pte_high); -#else - lazy_hcall3(LHCALL_SET_PTE, __pa(mm->pgd), addr, ptep->pte_low); -#endif -} - -/* This is the "set and update" combo-meal-deal version. */ -static void lguest_set_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pteval) -{ - native_set_pte(ptep, pteval); - lguest_pte_update(mm, addr, ptep); -} - -/* - * The Guest calls lguest_set_pud to set a top-level entry and lguest_set_pmd - * to set a middle-level entry when PAE is activated. - * - * Again, we set the entry then tell the Host which page we changed, - * and the index of the entry we changed. - */ -#ifdef CONFIG_X86_PAE -static void lguest_set_pud(pud_t *pudp, pud_t pudval) -{ - native_set_pud(pudp, pudval); - - /* 32 bytes aligned pdpt address and the index. */ - lazy_hcall2(LHCALL_SET_PGD, __pa(pudp) & 0xFFFFFFE0, - (__pa(pudp) & 0x1F) / sizeof(pud_t)); -} - -static void lguest_set_pmd(pmd_t *pmdp, pmd_t pmdval) -{ - native_set_pmd(pmdp, pmdval); - lazy_hcall2(LHCALL_SET_PMD, __pa(pmdp) & PAGE_MASK, - (__pa(pmdp) & (PAGE_SIZE - 1)) / sizeof(pmd_t)); -} -#else - -/* The Guest calls lguest_set_pmd to set a top-level entry when !PAE. */ -static void lguest_set_pmd(pmd_t *pmdp, pmd_t pmdval) -{ - native_set_pmd(pmdp, pmdval); - lazy_hcall2(LHCALL_SET_PGD, __pa(pmdp) & PAGE_MASK, - (__pa(pmdp) & (PAGE_SIZE - 1)) / sizeof(pmd_t)); -} -#endif - -/* - * There are a couple of legacy places where the kernel sets a PTE, but we - * don't know the top level any more. This is useless for us, since we don't - * know which pagetable is changing or what address, so we just tell the Host - * to forget all of them. Fortunately, this is very rare. - * - * ... except in early boot when the kernel sets up the initial pagetables, - * which makes booting astonishingly slow: 48 seconds! So we don't even tell - * the Host anything changed until we've done the first real page table switch, - * which brings boot back to 4.3 seconds. - */ -static void lguest_set_pte(pte_t *ptep, pte_t pteval) -{ - native_set_pte(ptep, pteval); - if (cr3_changed) - lazy_hcall1(LHCALL_FLUSH_TLB, 1); -} - -#ifdef CONFIG_X86_PAE -/* - * With 64-bit PTE values, we need to be careful setting them: if we set 32 - * bits at a time, the hardware could see a weird half-set entry. These - * versions ensure we update all 64 bits at once. - */ -static void lguest_set_pte_atomic(pte_t *ptep, pte_t pte) -{ - native_set_pte_atomic(ptep, pte); - if (cr3_changed) - lazy_hcall1(LHCALL_FLUSH_TLB, 1); -} - -static void lguest_pte_clear(struct mm_struct *mm, unsigned long addr, - pte_t *ptep) -{ - native_pte_clear(mm, addr, ptep); - lguest_pte_update(mm, addr, ptep); -} - -static void lguest_pmd_clear(pmd_t *pmdp) -{ - lguest_set_pmd(pmdp, __pmd(0)); -} -#endif - -/* - * Unfortunately for Lguest, the pv_mmu_ops for page tables were based on - * native page table operations. On native hardware you can set a new page - * table entry whenever you want, but if you want to remove one you have to do - * a TLB flush (a TLB is a little cache of page table entries kept by the CPU). - * - * So the lguest_set_pte_at() and lguest_set_pmd() functions above are only - * called when a valid entry is written, not when it's removed (ie. marked not - * present). Instead, this is where we come when the Guest wants to remove a - * page table entry: we tell the Host to set that entry to 0 (ie. the present - * bit is zero). - */ -static void lguest_flush_tlb_single(unsigned long addr) -{ - /* Simply set it to zero: if it was not, it will fault back in. */ - lazy_hcall3(LHCALL_SET_PTE, current_cr3, addr, 0); -} - -/* - * This is what happens after the Guest has removed a large number of entries. - * This tells the Host that any of the page table entries for userspace might - * have changed, ie. virtual addresses below PAGE_OFFSET. - */ -static void lguest_flush_tlb_user(void) -{ - lazy_hcall1(LHCALL_FLUSH_TLB, 0); -} - -/* - * This is called when the kernel page tables have changed. That's not very - * common (unless the Guest is using highmem, which makes the Guest extremely - * slow), so it's worth separating this from the user flushing above. - */ -static void lguest_flush_tlb_kernel(void) -{ - lazy_hcall1(LHCALL_FLUSH_TLB, 1); -} - -/* - * The Unadvanced Programmable Interrupt Controller. - * - * This is an attempt to implement the simplest possible interrupt controller. - * I spent some time looking though routines like set_irq_chip_and_handler, - * set_irq_chip_and_handler_name, set_irq_chip_data and set_phasers_to_stun and - * I *think* this is as simple as it gets. - * - * We can tell the Host what interrupts we want blocked ready for using the - * lguest_data.interrupts bitmap, so disabling (aka "masking") them is as - * simple as setting a bit. We don't actually "ack" interrupts as such, we - * just mask and unmask them. I wonder if we should be cleverer? - */ -static void disable_lguest_irq(struct irq_data *data) -{ - set_bit(data->irq, lguest_data.blocked_interrupts); -} - -static void enable_lguest_irq(struct irq_data *data) -{ - clear_bit(data->irq, lguest_data.blocked_interrupts); -} - -/* This structure describes the lguest IRQ controller. */ -static struct irq_chip lguest_irq_controller = { - .name = "lguest", - .irq_mask = disable_lguest_irq, - .irq_mask_ack = disable_lguest_irq, - .irq_unmask = enable_lguest_irq, -}; - -/* - * Interrupt descriptors are allocated as-needed, but low-numbered ones are - * reserved by the generic x86 code. So we ignore irq_alloc_desc_at if it - * tells us the irq is already used: other errors (ie. ENOMEM) we take - * seriously. - */ -static int lguest_setup_irq(unsigned int irq) -{ - struct irq_desc *desc; - int err; - - /* Returns -ve error or vector number. */ - err = irq_alloc_desc_at(irq, 0); - if (err < 0 && err != -EEXIST) - return err; - - /* - * Tell the Linux infrastructure that the interrupt is - * controlled by our level-based lguest interrupt controller. - */ - irq_set_chip_and_handler_name(irq, &lguest_irq_controller, - handle_level_irq, "level"); - - /* Some systems map "vectors" to interrupts weirdly. Not us! */ - desc = irq_to_desc(irq); - __this_cpu_write(vector_irq[FIRST_EXTERNAL_VECTOR + irq], desc); - return 0; -} - -static int lguest_enable_irq(struct pci_dev *dev) -{ - int err; - u8 line = 0; - - /* We literally use the PCI interrupt line as the irq number. */ - pci_read_config_byte(dev, PCI_INTERRUPT_LINE, &line); - err = lguest_setup_irq(line); - if (!err) - dev->irq = line; - return err; -} - -/* We don't do hotplug PCI, so this shouldn't be called. */ -static void lguest_disable_irq(struct pci_dev *dev) -{ - WARN_ON(1); -} - -/* - * This sets up the Interrupt Descriptor Table (IDT) entry for each hardware - * interrupt (except 128, which is used for system calls). - */ -static void __init lguest_init_IRQ(void) -{ - unsigned int i; - - for (i = FIRST_EXTERNAL_VECTOR; i < FIRST_SYSTEM_VECTOR; i++) { - if (i != IA32_SYSCALL_VECTOR) - set_intr_gate(i, irq_entries_start + - 8 * (i - FIRST_EXTERNAL_VECTOR)); - } - - /* - * This call is required to set up for 4k stacks, where we have - * separate stacks for hard and soft interrupts. - */ - irq_ctx_init(smp_processor_id()); -} - -/* - * Time. - * - * It would be far better for everyone if the Guest had its own clock, but - * until then the Host gives us the time on every interrupt. - */ -static void lguest_get_wallclock(struct timespec *now) -{ - *now = lguest_data.time; -} - -/* - * The TSC is an Intel thing called the Time Stamp Counter. The Host tells us - * what speed it runs at, or 0 if it's unusable as a reliable clock source. - * This matches what we want here: if we return 0 from this function, the x86 - * TSC clock will give up and not register itself. - */ -static unsigned long lguest_tsc_khz(void) -{ - return lguest_data.tsc_khz; -} - -/* - * If we can't use the TSC, the kernel falls back to our lower-priority - * "lguest_clock", where we read the time value given to us by the Host. - */ -static u64 lguest_clock_read(struct clocksource *cs) -{ - unsigned long sec, nsec; - - /* - * Since the time is in two parts (seconds and nanoseconds), we risk - * reading it just as it's changing from 99 & 0.999999999 to 100 and 0, - * and getting 99 and 0. As Linux tends to come apart under the stress - * of time travel, we must be careful: - */ - do { - /* First we read the seconds part. */ - sec = lguest_data.time.tv_sec; - /* - * This read memory barrier tells the compiler and the CPU that - * this can't be reordered: we have to complete the above - * before going on. - */ - rmb(); - /* Now we read the nanoseconds part. */ - nsec = lguest_data.time.tv_nsec; - /* Make sure we've done that. */ - rmb(); - /* Now if the seconds part has changed, try again. */ - } while (unlikely(lguest_data.time.tv_sec != sec)); - - /* Our lguest clock is in real nanoseconds. */ - return sec*1000000000ULL + nsec; -} - -/* This is the fallback clocksource: lower priority than the TSC clocksource. */ -static struct clocksource lguest_clock = { - .name = "lguest", - .rating = 200, - .read = lguest_clock_read, - .mask = CLOCKSOURCE_MASK(64), - .flags = CLOCK_SOURCE_IS_CONTINUOUS, -}; - -/* - * We also need a "struct clock_event_device": Linux asks us to set it to go - * off some time in the future. Actually, James Morris figured all this out, I - * just applied the patch. - */ -static int lguest_clockevent_set_next_event(unsigned long delta, - struct clock_event_device *evt) -{ - /* FIXME: I don't think this can ever happen, but James tells me he had - * to put this code in. Maybe we should remove it now. Anyone? */ - if (delta < LG_CLOCK_MIN_DELTA) { - if (printk_ratelimit()) - printk(KERN_DEBUG "%s: small delta %lu ns\n", - __func__, delta); - return -ETIME; - } - - /* Please wake us this far in the future. */ - hcall(LHCALL_SET_CLOCKEVENT, delta, 0, 0, 0); - return 0; -} - -static int lguest_clockevent_shutdown(struct clock_event_device *evt) -{ - /* A 0 argument shuts the clock down. */ - hcall(LHCALL_SET_CLOCKEVENT, 0, 0, 0, 0); - return 0; -} - -/* This describes our primitive timer chip. */ -static struct clock_event_device lguest_clockevent = { - .name = "lguest", - .features = CLOCK_EVT_FEAT_ONESHOT, - .set_next_event = lguest_clockevent_set_next_event, - .set_state_shutdown = lguest_clockevent_shutdown, - .rating = INT_MAX, - .mult = 1, - .shift = 0, - .min_delta_ns = LG_CLOCK_MIN_DELTA, - .min_delta_ticks = LG_CLOCK_MIN_DELTA, - .max_delta_ns = LG_CLOCK_MAX_DELTA, - .max_delta_ticks = LG_CLOCK_MAX_DELTA, -}; - -/* - * This is the Guest timer interrupt handler (hardware interrupt 0). We just - * call the clockevent infrastructure and it does whatever needs doing. - */ -static void lguest_time_irq(struct irq_desc *desc) -{ - unsigned long flags; - - /* Don't interrupt us while this is running. */ - local_irq_save(flags); - lguest_clockevent.event_handler(&lguest_clockevent); - local_irq_restore(flags); -} - -/* - * At some point in the boot process, we get asked to set up our timing - * infrastructure. The kernel doesn't expect timer interrupts before this, but - * we cleverly initialized the "blocked_interrupts" field of "struct - * lguest_data" so that timer interrupts were blocked until now. - */ -static void lguest_time_init(void) -{ - /* Set up the timer interrupt (0) to go to our simple timer routine */ - if (lguest_setup_irq(0) != 0) - panic("Could not set up timer irq"); - irq_set_handler(0, lguest_time_irq); - - clocksource_register_hz(&lguest_clock, NSEC_PER_SEC); - - /* We can't set cpumask in the initializer: damn C limitations! Set it - * here and register our timer device. */ - lguest_clockevent.cpumask = cpumask_of(0); - clockevents_register_device(&lguest_clockevent); - - /* Finally, we unblock the timer interrupt. */ - clear_bit(0, lguest_data.blocked_interrupts); -} - -/* - * Miscellaneous bits and pieces. - * - * Here is an oddball collection of functions which the Guest needs for things - * to work. They're pretty simple. - */ - -/* - * The Guest needs to tell the Host what stack it expects traps to use. For - * native hardware, this is part of the Task State Segment mentioned above in - * lguest_load_tr_desc(), but to help hypervisors there's this special call. - * - * We tell the Host the segment we want to use (__KERNEL_DS is the kernel data - * segment), the privilege level (we're privilege level 1, the Host is 0 and - * will not tolerate us trying to use that), the stack pointer, and the number - * of pages in the stack. - */ -static void lguest_load_sp0(struct tss_struct *tss, - struct thread_struct *thread) -{ - lazy_hcall3(LHCALL_SET_STACK, __KERNEL_DS | 0x1, thread->sp0, - THREAD_SIZE / PAGE_SIZE); - tss->x86_tss.sp0 = thread->sp0; -} - -/* Let's just say, I wouldn't do debugging under a Guest. */ -static unsigned long lguest_get_debugreg(int regno) -{ - /* FIXME: Implement */ - return 0; -} - -static void lguest_set_debugreg(int regno, unsigned long value) -{ - /* FIXME: Implement */ -} - -/* - * There are times when the kernel wants to make sure that no memory writes are - * caught in the cache (that they've all reached real hardware devices). This - * doesn't matter for the Guest which has virtual hardware. - * - * On the Pentium 4 and above, cpuid() indicates that the Cache Line Flush - * (clflush) instruction is available and the kernel uses that. Otherwise, it - * uses the older "Write Back and Invalidate Cache" (wbinvd) instruction. - * Unlike clflush, wbinvd can only be run at privilege level 0. So we can - * ignore clflush, but replace wbinvd. - */ -static void lguest_wbinvd(void) -{ -} - -/* - * If the Guest expects to have an Advanced Programmable Interrupt Controller, - * we play dumb by ignoring writes and returning 0 for reads. So it's no - * longer Programmable nor Controlling anything, and I don't think 8 lines of - * code qualifies for Advanced. It will also never interrupt anything. It - * does, however, allow us to get through the Linux boot code. - */ -#ifdef CONFIG_X86_LOCAL_APIC -static void lguest_apic_write(u32 reg, u32 v) -{ -} - -static u32 lguest_apic_read(u32 reg) -{ - return 0; -} - -static u64 lguest_apic_icr_read(void) -{ - return 0; -} - -static void lguest_apic_icr_write(u32 low, u32 id) -{ - /* Warn to see if there's any stray references */ - WARN_ON(1); -} - -static void lguest_apic_wait_icr_idle(void) -{ - return; -} - -static u32 lguest_apic_safe_wait_icr_idle(void) -{ - return 0; -} - -static void set_lguest_basic_apic_ops(void) -{ - apic->read = lguest_apic_read; - apic->write = lguest_apic_write; - apic->icr_read = lguest_apic_icr_read; - apic->icr_write = lguest_apic_icr_write; - apic->wait_icr_idle = lguest_apic_wait_icr_idle; - apic->safe_wait_icr_idle = lguest_apic_safe_wait_icr_idle; -}; -#endif - -/* STOP! Until an interrupt comes in. */ -static void lguest_safe_halt(void) -{ - hcall(LHCALL_HALT, 0, 0, 0, 0); -} - -/* - * The SHUTDOWN hypercall takes a string to describe what's happening, and - * an argument which says whether this to restart (reboot) the Guest or not. - * - * Note that the Host always prefers that the Guest speak in physical addresses - * rather than virtual addresses, so we use __pa() here. - */ -static void lguest_power_off(void) -{ - hcall(LHCALL_SHUTDOWN, __pa("Power down"), - LGUEST_SHUTDOWN_POWEROFF, 0, 0); -} - -/* - * Panicing. - * - * Don't. But if you did, this is what happens. - */ -static int lguest_panic(struct notifier_block *nb, unsigned long l, void *p) -{ - hcall(LHCALL_SHUTDOWN, __pa(p), LGUEST_SHUTDOWN_POWEROFF, 0, 0); - /* The hcall won't return, but to keep gcc happy, we're "done". */ - return NOTIFY_DONE; -} - -static struct notifier_block paniced = { - .notifier_call = lguest_panic -}; - -/* Setting up memory is fairly easy. */ -static __init char *lguest_memory_setup(void) -{ - /* - * The Linux bootloader header contains an "e820" memory map: the - * Launcher populated the first entry with our memory limit. - */ - e820__range_add(boot_params.e820_table[0].addr, - boot_params.e820_table[0].size, - boot_params.e820_table[0].type); - - /* This string is for the boot messages. */ - return "LGUEST"; -} - -/* Offset within PCI config space of BAR access capability. */ -static int console_cfg_offset = 0; -static int console_access_cap; - -/* Set up so that we access off in bar0 (on bus 0, device 1, function 0) */ -static void set_cfg_window(u32 cfg_offset, u32 off) -{ - write_pci_config_byte(0, 1, 0, - cfg_offset + offsetof(struct virtio_pci_cap, bar), - 0); - write_pci_config(0, 1, 0, - cfg_offset + offsetof(struct virtio_pci_cap, length), - 4); - write_pci_config(0, 1, 0, - cfg_offset + offsetof(struct virtio_pci_cap, offset), - off); -} - -static void write_bar_via_cfg(u32 cfg_offset, u32 off, u32 val) -{ - /* - * We could set this up once, then leave it; nothing else in the * - * kernel should touch these registers. But if it went wrong, that - * would be a horrible bug to find. - */ - set_cfg_window(cfg_offset, off); - write_pci_config(0, 1, 0, - cfg_offset + sizeof(struct virtio_pci_cap), val); -} - -static void probe_pci_console(void) -{ - u8 cap, common_cap = 0, device_cap = 0; - u32 device_len; - - /* Avoid recursive printk into here. */ - console_cfg_offset = -1; - - if (!early_pci_allowed()) { - printk(KERN_ERR "lguest: early PCI access not allowed!\n"); - return; - } - - /* We expect a console PCI device at BUS0, slot 1. */ - if (read_pci_config(0, 1, 0, 0) != 0x10431AF4) { - printk(KERN_ERR "lguest: PCI device is %#x!\n", - read_pci_config(0, 1, 0, 0)); - return; - } - - /* Find the capabilities we need (must be in bar0) */ - cap = read_pci_config_byte(0, 1, 0, PCI_CAPABILITY_LIST); - while (cap) { - u8 vndr = read_pci_config_byte(0, 1, 0, cap); - if (vndr == PCI_CAP_ID_VNDR) { - u8 type, bar; - - type = read_pci_config_byte(0, 1, 0, - cap + offsetof(struct virtio_pci_cap, cfg_type)); - bar = read_pci_config_byte(0, 1, 0, - cap + offsetof(struct virtio_pci_cap, bar)); - - switch (type) { - case VIRTIO_PCI_CAP_DEVICE_CFG: - if (bar == 0) - device_cap = cap; - break; - case VIRTIO_PCI_CAP_PCI_CFG: - console_access_cap = cap; - break; - } - } - cap = read_pci_config_byte(0, 1, 0, cap + PCI_CAP_LIST_NEXT); - } - if (!device_cap || !console_access_cap) { - printk(KERN_ERR "lguest: No caps (%u/%u/%u) in console!\n", - common_cap, device_cap, console_access_cap); - return; - } - - /* - * Note that we can't check features, until we've set the DRIVER - * status bit. We don't want to do that until we have a real driver, - * so we just check that the device-specific config has room for - * emerg_wr. If it doesn't support VIRTIO_CONSOLE_F_EMERG_WRITE - * it should ignore the access. - */ - device_len = read_pci_config(0, 1, 0, - device_cap + offsetof(struct virtio_pci_cap, length)); - if (device_len < (offsetof(struct virtio_console_config, emerg_wr) - + sizeof(u32))) { - printk(KERN_ERR "lguest: console missing emerg_wr field\n"); - return; - } - - console_cfg_offset = read_pci_config(0, 1, 0, - device_cap + offsetof(struct virtio_pci_cap, offset)); - printk(KERN_INFO "lguest: Console via virtio-pci emerg_wr\n"); -} - -/* - * We will eventually use the virtio console device to produce console output, - * but before that is set up we use the virtio PCI console's backdoor mmio - * access and the "emergency" write facility (which is legal even before the - * device is configured). - */ -static __init int early_put_chars(u32 vtermno, const char *buf, int count) -{ - /* If we couldn't find PCI console, forget it. */ - if (console_cfg_offset < 0) - return count; - - if (unlikely(!console_cfg_offset)) { - probe_pci_console(); - if (console_cfg_offset < 0) - return count; - } - - write_bar_via_cfg(console_access_cap, - console_cfg_offset - + offsetof(struct virtio_console_config, emerg_wr), - buf[0]); - return 1; -} - -/* - * Rebooting also tells the Host we're finished, but the RESTART flag tells the - * Launcher to reboot us. - */ -static void lguest_restart(char *reason) -{ - hcall(LHCALL_SHUTDOWN, __pa(reason), LGUEST_SHUTDOWN_RESTART, 0, 0); -} - -/*G:050 - * Patching (Powerfully Placating Performance Pedants) - * - * We have already seen that pv_ops structures let us replace simple native - * instructions with calls to the appropriate back end all throughout the - * kernel. This allows the same kernel to run as a Guest and as a native - * kernel, but it's slow because of all the indirect branches. - * - * Remember that David Wheeler quote about "Any problem in computer science can - * be solved with another layer of indirection"? The rest of that quote is - * "... But that usually will create another problem." This is the first of - * those problems. - * - * Our current solution is to allow the paravirt back end to optionally patch - * over the indirect calls to replace them with something more efficient. We - * patch two of the simplest of the most commonly called functions: disable - * interrupts and save interrupts. We usually have 6 or 10 bytes to patch - * into: the Guest versions of these operations are small enough that we can - * fit comfortably. - * - * First we need assembly templates of each of the patchable Guest operations, - * and these are in head_32.S. - */ - -/*G:060 We construct a table from the assembler templates: */ -static const struct lguest_insns -{ - const char *start, *end; -} lguest_insns[] = { - [PARAVIRT_PATCH(pv_irq_ops.irq_disable)] = { lgstart_cli, lgend_cli }, - [PARAVIRT_PATCH(pv_irq_ops.save_fl)] = { lgstart_pushf, lgend_pushf }, -}; - -/* - * Now our patch routine is fairly simple (based on the native one in - * paravirt.c). If we have a replacement, we copy it in and return how much of - * the available space we used. - */ -static unsigned lguest_patch(u8 type, u16 clobber, void *ibuf, - unsigned long addr, unsigned len) -{ - unsigned int insn_len; - - /* Don't do anything special if we don't have a replacement */ - if (type >= ARRAY_SIZE(lguest_insns) || !lguest_insns[type].start) - return paravirt_patch_default(type, clobber, ibuf, addr, len); - - insn_len = lguest_insns[type].end - lguest_insns[type].start; - - /* Similarly if it can't fit (doesn't happen, but let's be thorough). */ - if (len < insn_len) - return paravirt_patch_default(type, clobber, ibuf, addr, len); - - /* Copy in our instructions. */ - memcpy(ibuf, lguest_insns[type].start, insn_len); - return insn_len; -} - -/*G:029 - * Once we get to lguest_init(), we know we're a Guest. The various - * pv_ops structures in the kernel provide points for (almost) every routine we - * have to override to avoid privileged instructions. - */ -__init void lguest_init(void) -{ - /* We're under lguest. */ - pv_info.name = "lguest"; - /* We're running at privilege level 1, not 0 as normal. */ - pv_info.kernel_rpl = 1; - /* Everyone except Xen runs with this set. */ - pv_info.shared_kernel_pmd = 1; - - /* - * We set up all the lguest overrides for sensitive operations. These - * are detailed with the operations themselves. - */ - - /* Interrupt-related operations */ - pv_irq_ops.save_fl = PV_CALLEE_SAVE(lguest_save_fl); - pv_irq_ops.restore_fl = __PV_IS_CALLEE_SAVE(lg_restore_fl); - pv_irq_ops.irq_disable = PV_CALLEE_SAVE(lguest_irq_disable); - pv_irq_ops.irq_enable = __PV_IS_CALLEE_SAVE(lg_irq_enable); - pv_irq_ops.safe_halt = lguest_safe_halt; - - /* Setup operations */ - pv_init_ops.patch = lguest_patch; - - /* Intercepts of various CPU instructions */ - pv_cpu_ops.load_gdt = lguest_load_gdt; - pv_cpu_ops.cpuid = lguest_cpuid; - pv_cpu_ops.load_idt = lguest_load_idt; - pv_cpu_ops.iret = lguest_iret; - pv_cpu_ops.load_sp0 = lguest_load_sp0; - pv_cpu_ops.load_tr_desc = lguest_load_tr_desc; - pv_cpu_ops.set_ldt = lguest_set_ldt; - pv_cpu_ops.load_tls = lguest_load_tls; - pv_cpu_ops.get_debugreg = lguest_get_debugreg; - pv_cpu_ops.set_debugreg = lguest_set_debugreg; - pv_cpu_ops.read_cr0 = lguest_read_cr0; - pv_cpu_ops.write_cr0 = lguest_write_cr0; - pv_cpu_ops.read_cr4 = lguest_read_cr4; - pv_cpu_ops.write_cr4 = lguest_write_cr4; - pv_cpu_ops.write_gdt_entry = lguest_write_gdt_entry; - pv_cpu_ops.write_idt_entry = lguest_write_idt_entry; - pv_cpu_ops.wbinvd = lguest_wbinvd; - pv_cpu_ops.start_context_switch = paravirt_start_context_switch; - pv_cpu_ops.end_context_switch = lguest_end_context_switch; - - /* Pagetable management */ - pv_mmu_ops.write_cr3 = lguest_write_cr3; - pv_mmu_ops.flush_tlb_user = lguest_flush_tlb_user; - pv_mmu_ops.flush_tlb_single = lguest_flush_tlb_single; - pv_mmu_ops.flush_tlb_kernel = lguest_flush_tlb_kernel; - pv_mmu_ops.set_pte = lguest_set_pte; - pv_mmu_ops.set_pte_at = lguest_set_pte_at; - pv_mmu_ops.set_pmd = lguest_set_pmd; -#ifdef CONFIG_X86_PAE - pv_mmu_ops.set_pte_atomic = lguest_set_pte_atomic; - pv_mmu_ops.pte_clear = lguest_pte_clear; - pv_mmu_ops.pmd_clear = lguest_pmd_clear; - pv_mmu_ops.set_pud = lguest_set_pud; -#endif - pv_mmu_ops.read_cr2 = lguest_read_cr2; - pv_mmu_ops.read_cr3 = lguest_read_cr3; - pv_mmu_ops.lazy_mode.enter = paravirt_enter_lazy_mmu; - pv_mmu_ops.lazy_mode.leave = lguest_leave_lazy_mmu_mode; - pv_mmu_ops.lazy_mode.flush = paravirt_flush_lazy_mmu; - pv_mmu_ops.pte_update = lguest_pte_update; - -#ifdef CONFIG_X86_LOCAL_APIC - /* APIC read/write intercepts */ - set_lguest_basic_apic_ops(); -#endif - - x86_init.resources.memory_setup = lguest_memory_setup; - x86_init.irqs.intr_init = lguest_init_IRQ; - x86_init.timers.timer_init = lguest_time_init; - x86_platform.calibrate_tsc = lguest_tsc_khz; - x86_platform.get_wallclock = lguest_get_wallclock; - - /* - * Now is a good time to look at the implementations of these functions - * before returning to the rest of lguest_init(). - */ - - /*G:070 - * Now we've seen all the paravirt_ops, we return to - * lguest_init() where the rest of the fairly chaotic boot setup - * occurs. - */ - - /* - * The stack protector is a weird thing where gcc places a canary - * value on the stack and then checks it on return. This file is - * compiled with -fno-stack-protector it, so we got this far without - * problems. The value of the canary is kept at offset 20 from the - * %gs register, so we need to set that up before calling C functions - * in other files. - */ - setup_stack_canary_segment(0); - - /* - * We could just call load_stack_canary_segment(), but we might as well - * call switch_to_new_gdt() which loads the whole table and sets up the - * per-cpu segment descriptor register %fs as well. - */ - switch_to_new_gdt(0); - - /* - * The Host<->Guest Switcher lives at the top of our address space, and - * the Host told us how big it is when we made LGUEST_INIT hypercall: - * it put the answer in lguest_data.reserve_mem - */ - reserve_top_address(lguest_data.reserve_mem); - - /* Hook in our special panic hypercall code. */ - atomic_notifier_chain_register(&panic_notifier_list, &paniced); - - /* - * This is messy CPU setup stuff which the native boot code does before - * start_kernel, so we have to do, too: - */ - cpu_detect(&new_cpu_data); - /* head.S usually sets up the first capability word, so do it here. */ - new_cpu_data.x86_capability[CPUID_1_EDX] = cpuid_edx(1); - - /* Math is always hard! */ - set_cpu_cap(&new_cpu_data, X86_FEATURE_FPU); - - /* We don't have features. We have puppies! Puppies! */ -#ifdef CONFIG_X86_MCE - mca_cfg.disabled = true; -#endif -#ifdef CONFIG_ACPI - acpi_disabled = 1; -#endif - - /* - * We set the preferred console to "hvc". This is the "hypervisor - * virtual console" driver written by the PowerPC people, which we also - * adapted for lguest's use. - */ - add_preferred_console("hvc", 0, NULL); - - /* Register our very early console. */ - virtio_cons_early_init(early_put_chars); - - /* Don't let ACPI try to control our PCI interrupts. */ - disable_acpi(); - - /* We control them ourselves, by overriding these two hooks. */ - pcibios_enable_irq = lguest_enable_irq; - pcibios_disable_irq = lguest_disable_irq; - - /* - * Last of all, we set the power management poweroff hook to point to - * the Guest routine to power off, and the reboot hook to our restart - * routine. - */ - pm_power_off = lguest_power_off; - machine_ops.restart = lguest_restart; - - /* - * Now we're set up, call i386_start_kernel() in head32.c and we proceed - * to boot as normal. It never returns. - */ - i386_start_kernel(); -} -/* - * This marks the end of stage II of our journey, The Guest. - * - * It is now time for us to explore the layer of virtual drivers and complete - * our understanding of the Guest in "make Drivers". - */ diff --git a/arch/x86/lguest/head_32.S b/arch/x86/lguest/head_32.S deleted file mode 100644 index d5ae63f5ec5d..000000000000 --- a/arch/x86/lguest/head_32.S +++ /dev/null @@ -1,192 +0,0 @@ -#include <linux/linkage.h> -#include <linux/lguest.h> -#include <asm/lguest_hcall.h> -#include <asm/asm-offsets.h> -#include <asm/thread_info.h> -#include <asm/processor-flags.h> - -/*G:020 - - * Our story starts with the bzImage: booting starts at startup_32 in - * arch/x86/boot/compressed/head_32.S. This merely uncompresses the real - * kernel in place and then jumps into it: startup_32 in - * arch/x86/kernel/head_32.S. Both routines expects a boot header in the %esi - * register, which is created by the bootloader (the Launcher in our case). - * - * The startup_32 function does very little: it clears the uninitialized global - * C variables which we expect to be zero (ie. BSS) and then copies the boot - * header and kernel command line somewhere safe, and populates some initial - * page tables. Finally it checks the 'hardware_subarch' field. This was - * introduced in 2.6.24 for lguest and Xen: if it's set to '1' (lguest's - * assigned number), then it calls us here. - * - * WARNING: be very careful here! We're running at addresses equal to physical - * addresses (around 0), not above PAGE_OFFSET as most code expects - * (eg. 0xC0000000). Jumps are relative, so they're OK, but we can't touch any - * data without remembering to subtract __PAGE_OFFSET! - * - * The .section line puts this code in .init.text so it will be discarded after - * boot. - */ -.section .init.text, "ax", @progbits -ENTRY(lguest_entry) - /* - * We make the "initialization" hypercall now to tell the Host where - * our lguest_data struct is. - */ - movl $LHCALL_LGUEST_INIT, %eax - movl $lguest_data - __PAGE_OFFSET, %ebx - int $LGUEST_TRAP_ENTRY - - /* Now turn our pagetables on; setup by arch/x86/kernel/head_32.S. */ - movl $LHCALL_NEW_PGTABLE, %eax - movl $(initial_page_table - __PAGE_OFFSET), %ebx - int $LGUEST_TRAP_ENTRY - - /* Set up the initial stack so we can run C code. */ - movl $(init_thread_union+THREAD_SIZE),%esp - - /* Jumps are relative: we're running __PAGE_OFFSET too low. */ - jmp lguest_init+__PAGE_OFFSET - -/*G:055 - * We create a macro which puts the assembler code between lgstart_ and lgend_ - * markers. These templates are put in the .text section: they can't be - * discarded after boot as we may need to patch modules, too. - */ -.text -#define LGUEST_PATCH(name, insns...) \ - lgstart_##name: insns; lgend_##name:; \ - .globl lgstart_##name; .globl lgend_##name - -LGUEST_PATCH(cli, movl $0, lguest_data+LGUEST_DATA_irq_enabled) -LGUEST_PATCH(pushf, movl lguest_data+LGUEST_DATA_irq_enabled, %eax) - -/*G:033 - * But using those wrappers is inefficient (we'll see why that doesn't matter - * for save_fl and irq_disable later). If we write our routines carefully in - * assembler, we can avoid clobbering any registers and avoid jumping through - * the wrapper functions. - * - * I skipped over our first piece of assembler, but this one is worth studying - * in a bit more detail so I'll describe in easy stages. First, the routine to - * enable interrupts: - */ -ENTRY(lg_irq_enable) - /* - * The reverse of irq_disable, this sets lguest_data.irq_enabled to - * X86_EFLAGS_IF (ie. "Interrupts enabled"). - */ - movl $X86_EFLAGS_IF, lguest_data+LGUEST_DATA_irq_enabled - /* - * But now we need to check if the Host wants to know: there might have - * been interrupts waiting to be delivered, in which case it will have - * set lguest_data.irq_pending to X86_EFLAGS_IF. If it's not zero, we - * jump to send_interrupts, otherwise we're done. - */ - cmpl $0, lguest_data+LGUEST_DATA_irq_pending - jnz send_interrupts - /* - * One cool thing about x86 is that you can do many things without using - * a register. In this case, the normal path hasn't needed to save or - * restore any registers at all! - */ - ret -send_interrupts: - /* - * OK, now we need a register: eax is used for the hypercall number, - * which is LHCALL_SEND_INTERRUPTS. - * - * We used not to bother with this pending detection at all, which was - * much simpler. Sooner or later the Host would realize it had to - * send us an interrupt. But that turns out to make performance 7 - * times worse on a simple tcp benchmark. So now we do this the hard - * way. - */ - pushl %eax - movl $LHCALL_SEND_INTERRUPTS, %eax - /* This is the actual hypercall trap. */ - int $LGUEST_TRAP_ENTRY - /* Put eax back the way we found it. */ - popl %eax - ret - -/* - * Finally, the "popf" or "restore flags" routine. The %eax register holds the - * flags (in practice, either X86_EFLAGS_IF or 0): if it's X86_EFLAGS_IF we're - * enabling interrupts again, if it's 0 we're leaving them off. - */ -ENTRY(lg_restore_fl) - /* This is just "lguest_data.irq_enabled = flags;" */ - movl %eax, lguest_data+LGUEST_DATA_irq_enabled - /* - * Now, if the %eax value has enabled interrupts and - * lguest_data.irq_pending is set, we want to tell the Host so it can - * deliver any outstanding interrupts. Fortunately, both values will - * be X86_EFLAGS_IF (ie. 512) in that case, and the "testl" - * instruction will AND them together for us. If both are set, we - * jump to send_interrupts. - */ - testl lguest_data+LGUEST_DATA_irq_pending, %eax - jnz send_interrupts - /* Again, the normal path has used no extra registers. Clever, huh? */ - ret -/*:*/ - -/* These demark the EIP where host should never deliver interrupts. */ -.global lguest_noirq_iret - -/*M:004 - * When the Host reflects a trap or injects an interrupt into the Guest, it - * sets the eflags interrupt bit on the stack based on lguest_data.irq_enabled, - * so the Guest iret logic does the right thing when restoring it. However, - * when the Host sets the Guest up for direct traps, such as system calls, the - * processor is the one to push eflags onto the stack, and the interrupt bit - * will be 1 (in reality, interrupts are always enabled in the Guest). - * - * This turns out to be harmless: the only trap which should happen under Linux - * with interrupts disabled is Page Fault (due to our lazy mapping of vmalloc - * regions), which has to be reflected through the Host anyway. If another - * trap *does* go off when interrupts are disabled, the Guest will panic, and - * we'll never get to this iret! -:*/ - -/*G:045 - * There is one final paravirt_op that the Guest implements, and glancing at it - * you can see why I left it to last. It's *cool*! It's in *assembler*! - * - * The "iret" instruction is used to return from an interrupt or trap. The - * stack looks like this: - * old address - * old code segment & privilege level - * old processor flags ("eflags") - * - * The "iret" instruction pops those values off the stack and restores them all - * at once. The only problem is that eflags includes the Interrupt Flag which - * the Guest can't change: the CPU will simply ignore it when we do an "iret". - * So we have to copy eflags from the stack to lguest_data.irq_enabled before - * we do the "iret". - * - * There are two problems with this: firstly, we can't clobber any registers - * and secondly, the whole thing needs to be atomic. The first problem - * is solved by using "push memory"/"pop memory" instruction pair for copying. - * - * The second is harder: copying eflags to lguest_data.irq_enabled will turn - * interrupts on before we're finished, so we could be interrupted before we - * return to userspace or wherever. Our solution to this is to tell the - * Host that it is *never* to interrupt us there, even if interrupts seem to be - * enabled. (It's not necessary to protect pop instruction, since - * data gets updated only after it completes, so we only need to protect - * one instruction, iret). - */ -ENTRY(lguest_iret) - pushl 2*4(%esp) - /* - * Note the %ss: segment prefix here. Normal data accesses use the - * "ds" segment, but that will have already been restored for whatever - * we're returning to (such as userspace): we can't trust it. The %ss: - * prefix makes sure we use the stack segment, which is still valid. - */ - popl %ss:lguest_data+LGUEST_DATA_irq_enabled -lguest_noirq_iret: - iret diff --git a/arch/x86/lib/cmdline.c b/arch/x86/lib/cmdline.c index 5cc78bf57232..3261abb21ef4 100644 --- a/arch/x86/lib/cmdline.c +++ b/arch/x86/lib/cmdline.c @@ -104,7 +104,112 @@ __cmdline_find_option_bool(const char *cmdline, int max_cmdline_size, return 0; /* Buffer overrun */ } +/* + * Find a non-boolean option (i.e. option=argument). In accordance with + * standard Linux practice, if this option is repeated, this returns the + * last instance on the command line. + * + * @cmdline: the cmdline string + * @max_cmdline_size: the maximum size of cmdline + * @option: option string to look for + * @buffer: memory buffer to return the option argument + * @bufsize: size of the supplied memory buffer + * + * Returns the length of the argument (regardless of if it was + * truncated to fit in the buffer), or -1 on not found. + */ +static int +__cmdline_find_option(const char *cmdline, int max_cmdline_size, + const char *option, char *buffer, int bufsize) +{ + char c; + int pos = 0, len = -1; + const char *opptr = NULL; + char *bufptr = buffer; + enum { + st_wordstart = 0, /* Start of word/after whitespace */ + st_wordcmp, /* Comparing this word */ + st_wordskip, /* Miscompare, skip */ + st_bufcpy, /* Copying this to buffer */ + } state = st_wordstart; + + if (!cmdline) + return -1; /* No command line */ + + /* + * This 'pos' check ensures we do not overrun + * a non-NULL-terminated 'cmdline' + */ + while (pos++ < max_cmdline_size) { + c = *(char *)cmdline++; + if (!c) + break; + + switch (state) { + case st_wordstart: + if (myisspace(c)) + break; + + state = st_wordcmp; + opptr = option; + /* fall through */ + + case st_wordcmp: + if ((c == '=') && !*opptr) { + /* + * We matched all the way to the end of the + * option we were looking for, prepare to + * copy the argument. + */ + len = 0; + bufptr = buffer; + state = st_bufcpy; + break; + } else if (c == *opptr++) { + /* + * We are currently matching, so continue + * to the next character on the cmdline. + */ + break; + } + state = st_wordskip; + /* fall through */ + + case st_wordskip: + if (myisspace(c)) + state = st_wordstart; + break; + + case st_bufcpy: + if (myisspace(c)) { + state = st_wordstart; + } else { + /* + * Increment len, but don't overrun the + * supplied buffer and leave room for the + * NULL terminator. + */ + if (++len < bufsize) + *bufptr++ = c; + } + break; + } + } + + if (bufsize) + *bufptr = '\0'; + + return len; +} + int cmdline_find_option_bool(const char *cmdline, const char *option) { return __cmdline_find_option_bool(cmdline, COMMAND_LINE_SIZE, option); } + +int cmdline_find_option(const char *cmdline, const char *option, char *buffer, + int bufsize) +{ + return __cmdline_find_option(cmdline, COMMAND_LINE_SIZE, option, + buffer, bufsize); +} diff --git a/arch/x86/math-emu/div_Xsig.S b/arch/x86/math-emu/div_Xsig.S index f77ba3058b31..066996dba6a2 100644 --- a/arch/x86/math-emu/div_Xsig.S +++ b/arch/x86/math-emu/div_Xsig.S @@ -363,3 +363,4 @@ L_bugged_2: pop %ebx jmp L_exit #endif /* PARANOID */ +ENDPROC(div_Xsig) diff --git a/arch/x86/math-emu/div_small.S b/arch/x86/math-emu/div_small.S index 47099628fa4c..2c71527bd917 100644 --- a/arch/x86/math-emu/div_small.S +++ b/arch/x86/math-emu/div_small.S @@ -44,4 +44,4 @@ ENTRY(FPU_div_small) leave ret - +ENDPROC(FPU_div_small) diff --git a/arch/x86/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c index 0203baefb5c0..d4a7df2205b8 100644 --- a/arch/x86/math-emu/fpu_entry.c +++ b/arch/x86/math-emu/fpu_entry.c @@ -147,7 +147,7 @@ void math_emulate(struct math_emu_info *info) } code_descriptor = FPU_get_ldt_descriptor(FPU_CS); - if (SEG_D_SIZE(code_descriptor)) { + if (code_descriptor.d) { /* The above test may be wrong, the book is not clear */ /* Segmented 32 bit protected mode */ addr_modes.default_mode = SEG32; @@ -155,11 +155,10 @@ void math_emulate(struct math_emu_info *info) /* 16 bit protected mode */ addr_modes.default_mode = PM16; } - FPU_EIP += code_base = SEG_BASE_ADDR(code_descriptor); - code_limit = code_base - + (SEG_LIMIT(code_descriptor) + - 1) * SEG_GRANULARITY(code_descriptor) - - 1; + FPU_EIP += code_base = seg_get_base(&code_descriptor); + code_limit = seg_get_limit(&code_descriptor) + 1; + code_limit *= seg_get_granularity(&code_descriptor); + code_limit += code_base - 1; if (code_limit < code_base) code_limit = 0xffffffff; } diff --git a/arch/x86/math-emu/fpu_system.h b/arch/x86/math-emu/fpu_system.h index a179254a5122..699f329f1d40 100644 --- a/arch/x86/math-emu/fpu_system.h +++ b/arch/x86/math-emu/fpu_system.h @@ -34,17 +34,43 @@ static inline struct desc_struct FPU_get_ldt_descriptor(unsigned seg) return ret; } -#define SEG_D_SIZE(x) ((x).b & (3 << 21)) -#define SEG_G_BIT(x) ((x).b & (1 << 23)) -#define SEG_GRANULARITY(x) (((x).b & (1 << 23)) ? 4096 : 1) -#define SEG_286_MODE(x) ((x).b & ( 0xff000000 | 0xf0000 | (1 << 23))) -#define SEG_BASE_ADDR(s) (((s).b & 0xff000000) \ - | (((s).b & 0xff) << 16) | ((s).a >> 16)) -#define SEG_LIMIT(s) (((s).b & 0xff0000) | ((s).a & 0xffff)) -#define SEG_EXECUTE_ONLY(s) (((s).b & ((1 << 11) | (1 << 9))) == (1 << 11)) -#define SEG_WRITE_PERM(s) (((s).b & ((1 << 11) | (1 << 9))) == (1 << 9)) -#define SEG_EXPAND_DOWN(s) (((s).b & ((1 << 11) | (1 << 10))) \ - == (1 << 10)) +#define SEG_TYPE_WRITABLE (1U << 1) +#define SEG_TYPE_EXPANDS_DOWN (1U << 2) +#define SEG_TYPE_EXECUTE (1U << 3) +#define SEG_TYPE_EXPAND_MASK (SEG_TYPE_EXPANDS_DOWN | SEG_TYPE_EXECUTE) +#define SEG_TYPE_EXECUTE_MASK (SEG_TYPE_WRITABLE | SEG_TYPE_EXECUTE) + +static inline unsigned long seg_get_base(struct desc_struct *d) +{ + unsigned long base = (unsigned long)d->base2 << 24; + + return base | ((unsigned long)d->base1 << 16) | d->base0; +} + +static inline unsigned long seg_get_limit(struct desc_struct *d) +{ + return ((unsigned long)d->limit1 << 16) | d->limit0; +} + +static inline unsigned long seg_get_granularity(struct desc_struct *d) +{ + return d->g ? 4096 : 1; +} + +static inline bool seg_expands_down(struct desc_struct *d) +{ + return (d->type & SEG_TYPE_EXPAND_MASK) == SEG_TYPE_EXPANDS_DOWN; +} + +static inline bool seg_execute_only(struct desc_struct *d) +{ + return (d->type & SEG_TYPE_EXECUTE_MASK) == SEG_TYPE_EXECUTE; +} + +static inline bool seg_writable(struct desc_struct *d) +{ + return (d->type & SEG_TYPE_EXECUTE_MASK) == SEG_TYPE_WRITABLE; +} #define I387 (¤t->thread.fpu.state) #define FPU_info (I387->soft.info) diff --git a/arch/x86/math-emu/get_address.c b/arch/x86/math-emu/get_address.c index b8ef9f9d2ffc..c48967c6a0e2 100644 --- a/arch/x86/math-emu/get_address.c +++ b/arch/x86/math-emu/get_address.c @@ -159,17 +159,18 @@ static long pm_address(u_char FPU_modrm, u_char segment, } descriptor = FPU_get_ldt_descriptor(addr->selector); - base_address = SEG_BASE_ADDR(descriptor); + base_address = seg_get_base(&descriptor); address = base_address + offset; - limit = base_address - + (SEG_LIMIT(descriptor) + 1) * SEG_GRANULARITY(descriptor) - 1; + limit = seg_get_limit(&descriptor) + 1; + limit *= seg_get_granularity(&descriptor); + limit += base_address - 1; if (limit < base_address) limit = 0xffffffff; - if (SEG_EXPAND_DOWN(descriptor)) { - if (SEG_G_BIT(descriptor)) + if (seg_expands_down(&descriptor)) { + if (descriptor.g) { seg_top = 0xffffffff; - else { + } else { seg_top = base_address + (1 << 20); if (seg_top < base_address) seg_top = 0xffffffff; @@ -182,8 +183,8 @@ static long pm_address(u_char FPU_modrm, u_char segment, (address > limit) || (address < base_address) ? 0 : ((limit - address) >= 254 ? 255 : limit - address + 1); } - if (SEG_EXECUTE_ONLY(descriptor) || - (!SEG_WRITE_PERM(descriptor) && (FPU_modrm & FPU_WRITE_BIT))) { + if (seg_execute_only(&descriptor) || + (!seg_writable(&descriptor) && (FPU_modrm & FPU_WRITE_BIT))) { access_limit = 0; } return address; diff --git a/arch/x86/math-emu/mul_Xsig.S b/arch/x86/math-emu/mul_Xsig.S index 717785a53eb4..22e0631bb85a 100644 --- a/arch/x86/math-emu/mul_Xsig.S +++ b/arch/x86/math-emu/mul_Xsig.S @@ -62,6 +62,7 @@ ENTRY(mul32_Xsig) popl %esi leave ret +ENDPROC(mul32_Xsig) ENTRY(mul64_Xsig) @@ -114,6 +115,7 @@ ENTRY(mul64_Xsig) popl %esi leave ret +ENDPROC(mul64_Xsig) @@ -173,4 +175,4 @@ ENTRY(mul_Xsig_Xsig) popl %esi leave ret - +ENDPROC(mul_Xsig_Xsig) diff --git a/arch/x86/math-emu/polynom_Xsig.S b/arch/x86/math-emu/polynom_Xsig.S index 17315c89ff3d..a9aaf414135d 100644 --- a/arch/x86/math-emu/polynom_Xsig.S +++ b/arch/x86/math-emu/polynom_Xsig.S @@ -133,3 +133,4 @@ L_accum_done: popl %esi leave ret +ENDPROC(polynomial_Xsig) diff --git a/arch/x86/math-emu/reg_norm.S b/arch/x86/math-emu/reg_norm.S index 8b6352efceef..53ac1a343c69 100644 --- a/arch/x86/math-emu/reg_norm.S +++ b/arch/x86/math-emu/reg_norm.S @@ -94,6 +94,7 @@ L_overflow: call arith_overflow pop %ebx jmp L_exit +ENDPROC(FPU_normalize) @@ -145,3 +146,4 @@ L_exit_nuo_zero: popl %ebx leave ret +ENDPROC(FPU_normalize_nuo) diff --git a/arch/x86/math-emu/reg_round.S b/arch/x86/math-emu/reg_round.S index d1d4e48b4f67..41af5b208d88 100644 --- a/arch/x86/math-emu/reg_round.S +++ b/arch/x86/math-emu/reg_round.S @@ -706,3 +706,5 @@ L_exception_exit: mov $-1,%eax jmp fpu_reg_round_special_exit #endif /* PARANOID */ + +ENDPROC(FPU_round) diff --git a/arch/x86/math-emu/reg_u_add.S b/arch/x86/math-emu/reg_u_add.S index 47c4c2434d85..3b1bc5e9b2f6 100644 --- a/arch/x86/math-emu/reg_u_add.S +++ b/arch/x86/math-emu/reg_u_add.S @@ -165,3 +165,4 @@ L_exit: leave ret #endif /* PARANOID */ +ENDPROC(FPU_u_add) diff --git a/arch/x86/math-emu/reg_u_div.S b/arch/x86/math-emu/reg_u_div.S index cc00654b6f9a..796eb5ab921b 100644 --- a/arch/x86/math-emu/reg_u_div.S +++ b/arch/x86/math-emu/reg_u_div.S @@ -469,3 +469,5 @@ L_exit: leave ret #endif /* PARANOID */ + +ENDPROC(FPU_u_div) diff --git a/arch/x86/math-emu/reg_u_mul.S b/arch/x86/math-emu/reg_u_mul.S index 973f12af97df..6196f68cf3c1 100644 --- a/arch/x86/math-emu/reg_u_mul.S +++ b/arch/x86/math-emu/reg_u_mul.S @@ -146,3 +146,4 @@ L_exit: ret #endif /* PARANOID */ +ENDPROC(FPU_u_mul) diff --git a/arch/x86/math-emu/reg_u_sub.S b/arch/x86/math-emu/reg_u_sub.S index 1b6c24801d22..d115b900919a 100644 --- a/arch/x86/math-emu/reg_u_sub.S +++ b/arch/x86/math-emu/reg_u_sub.S @@ -270,3 +270,4 @@ L_exit: popl %esi leave ret +ENDPROC(FPU_u_sub) diff --git a/arch/x86/math-emu/round_Xsig.S b/arch/x86/math-emu/round_Xsig.S index bbe0e87718e4..87c99749a495 100644 --- a/arch/x86/math-emu/round_Xsig.S +++ b/arch/x86/math-emu/round_Xsig.S @@ -78,7 +78,7 @@ L_exit: popl %ebx leave ret - +ENDPROC(round_Xsig) @@ -138,4 +138,4 @@ L_n_exit: popl %ebx leave ret - +ENDPROC(norm_Xsig) diff --git a/arch/x86/math-emu/shr_Xsig.S b/arch/x86/math-emu/shr_Xsig.S index 31cdd118e918..c8552edeec75 100644 --- a/arch/x86/math-emu/shr_Xsig.S +++ b/arch/x86/math-emu/shr_Xsig.S @@ -85,3 +85,4 @@ L_more_than_95: popl %esi leave ret +ENDPROC(shr_Xsig) diff --git a/arch/x86/math-emu/wm_shrx.S b/arch/x86/math-emu/wm_shrx.S index 518428317985..340dd6897f85 100644 --- a/arch/x86/math-emu/wm_shrx.S +++ b/arch/x86/math-emu/wm_shrx.S @@ -92,6 +92,7 @@ L_more_than_95: popl %esi leave ret +ENDPROC(FPU_shrx) /*---------------------------------------------------------------------------+ @@ -202,3 +203,4 @@ Ls_more_than_95: popl %esi leave ret +ENDPROC(FPU_shrxs) diff --git a/arch/x86/math-emu/wm_sqrt.S b/arch/x86/math-emu/wm_sqrt.S index d258f59564e1..695afae38fdf 100644 --- a/arch/x86/math-emu/wm_sqrt.S +++ b/arch/x86/math-emu/wm_sqrt.S @@ -468,3 +468,4 @@ sqrt_more_prec_large: /* Our estimate is too large */ movl $0x7fffff00,%eax jmp sqrt_round_result +ENDPROC(wm_sqrt) diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 0fbdcb64f9f8..72bf8c01c6e3 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -39,3 +39,5 @@ obj-$(CONFIG_X86_INTEL_MPX) += mpx.o obj-$(CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS) += pkeys.o obj-$(CONFIG_RANDOMIZE_MEMORY) += kaslr.o +obj-$(CONFIG_AMD_MEM_ENCRYPT) += mem_encrypt.o +obj-$(CONFIG_AMD_MEM_ENCRYPT) += mem_encrypt_boot.o diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index 0470826d2bdc..5e3ac6fe6c9e 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -13,12 +13,12 @@ */ #include <linux/debugfs.h> +#include <linux/kasan.h> #include <linux/mm.h> #include <linux/init.h> #include <linux/sched.h> #include <linux/seq_file.h> -#include <asm/kasan.h> #include <asm/pgtable.h> /* @@ -138,7 +138,7 @@ static void printk_prot(struct seq_file *m, pgprot_t prot, int level, bool dmsg) { pgprotval_t pr = pgprot_val(prot); static const char * const level_name[] = - { "cr3", "pgd", "pud", "pmd", "pte" }; + { "cr3", "pgd", "p4d", "pud", "pmd", "pte" }; if (!pgprot_val(prot)) { /* Not present */ @@ -162,12 +162,12 @@ static void printk_prot(struct seq_file *m, pgprot_t prot, int level, bool dmsg) pt_dump_cont_printf(m, dmsg, " "); /* Bit 7 has a different meaning on level 3 vs 4 */ - if (level <= 3 && pr & _PAGE_PSE) + if (level <= 4 && pr & _PAGE_PSE) pt_dump_cont_printf(m, dmsg, "PSE "); else pt_dump_cont_printf(m, dmsg, " "); - if ((level == 4 && pr & _PAGE_PAT) || - ((level == 3 || level == 2) && pr & _PAGE_PAT_LARGE)) + if ((level == 5 && pr & _PAGE_PAT) || + ((level == 4 || level == 3) && pr & _PAGE_PAT_LARGE)) pt_dump_cont_printf(m, dmsg, "PAT "); else pt_dump_cont_printf(m, dmsg, " "); @@ -188,11 +188,12 @@ static void printk_prot(struct seq_file *m, pgprot_t prot, int level, bool dmsg) */ static unsigned long normalize_addr(unsigned long u) { -#ifdef CONFIG_X86_64 - return (signed long)(u << 16) >> 16; -#else - return u; -#endif + int shift; + if (!IS_ENABLED(CONFIG_X86_64)) + return u; + + shift = 64 - (__VIRTUAL_MASK_SHIFT + 1); + return (signed long)(u << shift) >> shift; } /* @@ -297,32 +298,62 @@ static void walk_pte_level(struct seq_file *m, struct pg_state *st, pmd_t addr, for (i = 0; i < PTRS_PER_PTE; i++) { prot = pte_flags(*start); st->current_address = normalize_addr(P + i * PTE_LEVEL_MULT); - note_page(m, st, __pgprot(prot), 4); + note_page(m, st, __pgprot(prot), 5); start++; } } +#ifdef CONFIG_KASAN + +/* + * This is an optimization for KASAN=y case. Since all kasan page tables + * eventually point to the kasan_zero_page we could call note_page() + * right away without walking through lower level page tables. This saves + * us dozens of seconds (minutes for 5-level config) while checking for + * W+X mapping or reading kernel_page_tables debugfs file. + */ +static inline bool kasan_page_table(struct seq_file *m, struct pg_state *st, + void *pt) +{ + if (__pa(pt) == __pa(kasan_zero_pmd) || +#ifdef CONFIG_X86_5LEVEL + __pa(pt) == __pa(kasan_zero_p4d) || +#endif + __pa(pt) == __pa(kasan_zero_pud)) { + pgprotval_t prot = pte_flags(kasan_zero_pte[0]); + note_page(m, st, __pgprot(prot), 5); + return true; + } + return false; +} +#else +static inline bool kasan_page_table(struct seq_file *m, struct pg_state *st, + void *pt) +{ + return false; +} +#endif #if PTRS_PER_PMD > 1 static void walk_pmd_level(struct seq_file *m, struct pg_state *st, pud_t addr, unsigned long P) { int i; - pmd_t *start; + pmd_t *start, *pmd_start; pgprotval_t prot; - start = (pmd_t *)pud_page_vaddr(addr); + pmd_start = start = (pmd_t *)pud_page_vaddr(addr); for (i = 0; i < PTRS_PER_PMD; i++) { st->current_address = normalize_addr(P + i * PMD_LEVEL_MULT); if (!pmd_none(*start)) { if (pmd_large(*start) || !pmd_present(*start)) { prot = pmd_flags(*start); - note_page(m, st, __pgprot(prot), 3); - } else { + note_page(m, st, __pgprot(prot), 4); + } else if (!kasan_page_table(m, st, pmd_start)) { walk_pte_level(m, st, *start, P + i * PMD_LEVEL_MULT); } } else - note_page(m, st, __pgprot(0), 3); + note_page(m, st, __pgprot(0), 4); start++; } } @@ -335,39 +366,27 @@ static void walk_pmd_level(struct seq_file *m, struct pg_state *st, pud_t addr, #if PTRS_PER_PUD > 1 -/* - * This is an optimization for CONFIG_DEBUG_WX=y + CONFIG_KASAN=y - * KASAN fills page tables with the same values. Since there is no - * point in checking page table more than once we just skip repeated - * entries. This saves us dozens of seconds during boot. - */ -static bool pud_already_checked(pud_t *prev_pud, pud_t *pud, bool checkwx) -{ - return checkwx && prev_pud && (pud_val(*prev_pud) == pud_val(*pud)); -} - static void walk_pud_level(struct seq_file *m, struct pg_state *st, p4d_t addr, unsigned long P) { int i; - pud_t *start; + pud_t *start, *pud_start; pgprotval_t prot; pud_t *prev_pud = NULL; - start = (pud_t *)p4d_page_vaddr(addr); + pud_start = start = (pud_t *)p4d_page_vaddr(addr); for (i = 0; i < PTRS_PER_PUD; i++) { st->current_address = normalize_addr(P + i * PUD_LEVEL_MULT); - if (!pud_none(*start) && - !pud_already_checked(prev_pud, start, st->check_wx)) { + if (!pud_none(*start)) { if (pud_large(*start) || !pud_present(*start)) { prot = pud_flags(*start); - note_page(m, st, __pgprot(prot), 2); - } else { + note_page(m, st, __pgprot(prot), 3); + } else if (!kasan_page_table(m, st, pud_start)) { walk_pmd_level(m, st, *start, P + i * PUD_LEVEL_MULT); } } else - note_page(m, st, __pgprot(0), 2); + note_page(m, st, __pgprot(0), 3); prev_pud = start; start++; @@ -385,10 +404,10 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st, p4d_t addr, static void walk_p4d_level(struct seq_file *m, struct pg_state *st, pgd_t addr, unsigned long P) { int i; - p4d_t *start; + p4d_t *start, *p4d_start; pgprotval_t prot; - start = (p4d_t *)pgd_page_vaddr(addr); + p4d_start = start = (p4d_t *)pgd_page_vaddr(addr); for (i = 0; i < PTRS_PER_P4D; i++) { st->current_address = normalize_addr(P + i * P4D_LEVEL_MULT); @@ -396,7 +415,7 @@ static void walk_p4d_level(struct seq_file *m, struct pg_state *st, pgd_t addr, if (p4d_large(*start) || !p4d_present(*start)) { prot = p4d_flags(*start); note_page(m, st, __pgprot(prot), 2); - } else { + } else if (!kasan_page_table(m, st, p4d_start)) { walk_pud_level(m, st, *start, P + i * P4D_LEVEL_MULT); } diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c index 0ea8afcb929c..c076f710de4c 100644 --- a/arch/x86/mm/extable.c +++ b/arch/x86/mm/extable.c @@ -36,6 +36,48 @@ bool ex_handler_fault(const struct exception_table_entry *fixup, } EXPORT_SYMBOL_GPL(ex_handler_fault); +/* + * Handler for UD0 exception following a failed test against the + * result of a refcount inc/dec/add/sub. + */ +bool ex_handler_refcount(const struct exception_table_entry *fixup, + struct pt_regs *regs, int trapnr) +{ + /* First unconditionally saturate the refcount. */ + *(int *)regs->cx = INT_MIN / 2; + + /* + * Strictly speaking, this reports the fixup destination, not + * the fault location, and not the actually overflowing + * instruction, which is the instruction before the "js", but + * since that instruction could be a variety of lengths, just + * report the location after the overflow, which should be close + * enough for finding the overflow, as it's at least back in + * the function, having returned from .text.unlikely. + */ + regs->ip = ex_fixup_addr(fixup); + + /* + * This function has been called because either a negative refcount + * value was seen by any of the refcount functions, or a zero + * refcount value was seen by refcount_dec(). + * + * If we crossed from INT_MAX to INT_MIN, OF (Overflow Flag: result + * wrapped around) will be set. Additionally, seeing the refcount + * reach 0 will set ZF (Zero Flag: result was zero). In each of + * these cases we want a report, since it's a boundary condition. + * + */ + if (regs->flags & (X86_EFLAGS_OF | X86_EFLAGS_ZF)) { + bool zero = regs->flags & X86_EFLAGS_ZF; + + refcount_error_report(regs, zero ? "hit zero" : "overflow"); + } + + return true; +} +EXPORT_SYMBOL_GPL(ex_handler_refcount); + bool ex_handler_ext(const struct exception_table_entry *fixup, struct pt_regs *regs, int trapnr) { @@ -142,7 +184,7 @@ void __init early_fixup_exception(struct pt_regs *regs, int trapnr) * undefined. I'm not sure which CPUs do this, but at least * the 486 DX works this way. */ - if ((regs->cs & 0xFFFF) != __KERNEL_CS) + if (regs->cs != __KERNEL_CS) goto fail; /* diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 2a1fa10c6a98..b836a7274e12 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -396,14 +396,18 @@ static void dump_pagetable(unsigned long address) pte_t *pte; #ifdef CONFIG_X86_PAE - printk("*pdpt = %016Lx ", pgd_val(*pgd)); + pr_info("*pdpt = %016Lx ", pgd_val(*pgd)); if (!low_pfn(pgd_val(*pgd) >> PAGE_SHIFT) || !pgd_present(*pgd)) goto out; +#define pr_pde pr_cont +#else +#define pr_pde pr_info #endif p4d = p4d_offset(pgd, address); pud = pud_offset(p4d, address); pmd = pmd_offset(pud, address); - printk(KERN_CONT "*pde = %0*Lx ", sizeof(*pmd) * 2, (u64)pmd_val(*pmd)); + pr_pde("*pde = %0*Lx ", sizeof(*pmd) * 2, (u64)pmd_val(*pmd)); +#undef pr_pde /* * We must not directly access the pte in the highpte @@ -415,9 +419,9 @@ static void dump_pagetable(unsigned long address) goto out; pte = pte_offset_kernel(pmd, address); - printk("*pte = %0*Lx ", sizeof(*pte) * 2, (u64)pte_val(*pte)); + pr_cont("*pte = %0*Lx ", sizeof(*pte) * 2, (u64)pte_val(*pte)); out: - printk("\n"); + pr_cont("\n"); } #else /* CONFIG_X86_64: */ @@ -565,7 +569,7 @@ static void dump_pagetable(unsigned long address) if (bad_address(pgd)) goto bad; - printk("PGD %lx ", pgd_val(*pgd)); + pr_info("PGD %lx ", pgd_val(*pgd)); if (!pgd_present(*pgd)) goto out; @@ -574,7 +578,7 @@ static void dump_pagetable(unsigned long address) if (bad_address(p4d)) goto bad; - printk("P4D %lx ", p4d_val(*p4d)); + pr_cont("P4D %lx ", p4d_val(*p4d)); if (!p4d_present(*p4d) || p4d_large(*p4d)) goto out; @@ -582,7 +586,7 @@ static void dump_pagetable(unsigned long address) if (bad_address(pud)) goto bad; - printk("PUD %lx ", pud_val(*pud)); + pr_cont("PUD %lx ", pud_val(*pud)); if (!pud_present(*pud) || pud_large(*pud)) goto out; @@ -590,7 +594,7 @@ static void dump_pagetable(unsigned long address) if (bad_address(pmd)) goto bad; - printk("PMD %lx ", pmd_val(*pmd)); + pr_cont("PMD %lx ", pmd_val(*pmd)); if (!pmd_present(*pmd) || pmd_large(*pmd)) goto out; @@ -598,12 +602,12 @@ static void dump_pagetable(unsigned long address) if (bad_address(pte)) goto bad; - printk("PTE %lx", pte_val(*pte)); + pr_cont("PTE %lx", pte_val(*pte)); out: - printk("\n"); + pr_cont("\n"); return; bad: - printk("BAD\n"); + pr_info("BAD\n"); } #endif /* CONFIG_X86_64 */ @@ -1254,10 +1258,6 @@ static inline bool smap_violation(int error_code, struct pt_regs *regs) * This routine handles page faults. It determines the address, * and the problem, and then passes it off to one of the appropriate * routines. - * - * This function must have noinline because both callers - * {,trace_}do_page_fault() have notrace on. Having this an actual function - * guarantees there's a function trace entry. */ static noinline void __do_page_fault(struct pt_regs *regs, unsigned long error_code, @@ -1490,27 +1490,6 @@ good_area: } NOKPROBE_SYMBOL(__do_page_fault); -dotraplinkage void notrace -do_page_fault(struct pt_regs *regs, unsigned long error_code) -{ - unsigned long address = read_cr2(); /* Get the faulting address */ - enum ctx_state prev_state; - - /* - * We must have this function tagged with __kprobes, notrace and call - * read_cr2() before calling anything else. To avoid calling any kind - * of tracing machinery before we've observed the CR2 value. - * - * exception_{enter,exit}() contain all sorts of tracepoints. - */ - - prev_state = exception_enter(); - __do_page_fault(regs, error_code, address); - exception_exit(prev_state); -} -NOKPROBE_SYMBOL(do_page_fault); - -#ifdef CONFIG_TRACING static nokprobe_inline void trace_page_fault_entries(unsigned long address, struct pt_regs *regs, unsigned long error_code) @@ -1521,22 +1500,24 @@ trace_page_fault_entries(unsigned long address, struct pt_regs *regs, trace_page_fault_kernel(address, regs, error_code); } +/* + * We must have this function blacklisted from kprobes, tagged with notrace + * and call read_cr2() before calling anything else. To avoid calling any + * kind of tracing machinery before we've observed the CR2 value. + * + * exception_{enter,exit}() contains all sorts of tracepoints. + */ dotraplinkage void notrace -trace_do_page_fault(struct pt_regs *regs, unsigned long error_code) +do_page_fault(struct pt_regs *regs, unsigned long error_code) { - /* - * The exception_enter and tracepoint processing could - * trigger another page faults (user space callchain - * reading) and destroy the original cr2 value, so read - * the faulting address now. - */ - unsigned long address = read_cr2(); + unsigned long address = read_cr2(); /* Get the faulting address */ enum ctx_state prev_state; prev_state = exception_enter(); - trace_page_fault_entries(address, regs, error_code); + if (trace_pagefault_enabled()) + trace_page_fault_entries(address, regs, error_code); + __do_page_fault(regs, error_code, address); exception_exit(prev_state); } -NOKPROBE_SYMBOL(trace_do_page_fault); -#endif /* CONFIG_TRACING */ +NOKPROBE_SYMBOL(do_page_fault); diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 2824607df108..6d06cf33e3de 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -18,6 +18,7 @@ #include <asm/tlbflush.h> #include <asm/pgalloc.h> #include <asm/elf.h> +#include <asm/mpx.h> #if 0 /* This is just for testing */ struct page * @@ -85,25 +86,38 @@ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file, info.flags = 0; info.length = len; info.low_limit = get_mmap_base(1); + + /* + * If hint address is above DEFAULT_MAP_WINDOW, look for unmapped area + * in the full address space. + */ info.high_limit = in_compat_syscall() ? - tasksize_32bit() : tasksize_64bit(); + task_size_32bit() : task_size_64bit(addr > DEFAULT_MAP_WINDOW); + info.align_mask = PAGE_MASK & ~huge_page_mask(h); info.align_offset = 0; return vm_unmapped_area(&info); } static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file, - unsigned long addr0, unsigned long len, + unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct hstate *h = hstate_file(file); struct vm_unmapped_area_info info; - unsigned long addr; info.flags = VM_UNMAPPED_AREA_TOPDOWN; info.length = len; info.low_limit = PAGE_SIZE; info.high_limit = get_mmap_base(0); + + /* + * If hint address is above DEFAULT_MAP_WINDOW, look for unmapped area + * in the full address space. + */ + if (addr > DEFAULT_MAP_WINDOW && !in_compat_syscall()) + info.high_limit += TASK_SIZE_MAX - DEFAULT_MAP_WINDOW; + info.align_mask = PAGE_MASK & ~huge_page_mask(h); info.align_offset = 0; addr = vm_unmapped_area(&info); @@ -118,7 +132,7 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file, VM_BUG_ON(addr != -ENOMEM); info.flags = 0; info.low_limit = TASK_UNMAPPED_BASE; - info.high_limit = TASK_SIZE; + info.high_limit = TASK_SIZE_LOW; addr = vm_unmapped_area(&info); } @@ -135,6 +149,11 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, if (len & ~huge_page_mask(h)) return -EINVAL; + + addr = mpx_unmapped_area_check(addr, len, flags); + if (IS_ERR_VALUE(addr)) + return addr; + if (len > TASK_SIZE) return -ENOMEM; diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c index adab1595f4bd..31cea988fa36 100644 --- a/arch/x86/mm/ident_map.c +++ b/arch/x86/mm/ident_map.c @@ -51,7 +51,7 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page, if (!pmd) return -ENOMEM; ident_pmd_init(info, pmd, addr, next); - set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE)); + set_pud(pud, __pud(__pa(pmd) | info->kernpg_flag)); } return 0; @@ -79,7 +79,7 @@ static int ident_p4d_init(struct x86_mapping_info *info, p4d_t *p4d_page, if (!pud) return -ENOMEM; ident_pud_init(info, pud, addr, next); - set_p4d(p4d, __p4d(__pa(pud) | _KERNPG_TABLE)); + set_p4d(p4d, __p4d(__pa(pud) | info->kernpg_flag)); } return 0; @@ -93,6 +93,10 @@ int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page, unsigned long next; int result; + /* Set the default pagetable flags if not supplied */ + if (!info->kernpg_flag) + info->kernpg_flag = _KERNPG_TABLE; + for (; addr < end; addr = next) { pgd_t *pgd = pgd_page + pgd_index(addr); p4d_t *p4d; @@ -116,14 +120,14 @@ int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page, if (result) return result; if (IS_ENABLED(CONFIG_X86_5LEVEL)) { - set_pgd(pgd, __pgd(__pa(p4d) | _KERNPG_TABLE)); + set_pgd(pgd, __pgd(__pa(p4d) | info->kernpg_flag)); } else { /* * With p4d folded, pgd is equal to p4d. * The pgd entry has to point to the pud page table in this case. */ pud_t *pud = pud_offset(p4d, 0); - set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE)); + set_pgd(pgd, __pgd(__pa(pud) | info->kernpg_flag)); } } diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 673541eb3b3f..7777ccc0e9f9 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -18,6 +18,7 @@ #include <asm/dma.h> /* for MAX_DMA_PFN */ #include <asm/microcode.h> #include <asm/kaslr.h> +#include <asm/hypervisor.h> /* * We need to define the tracepoints somewhere, and tlb.c @@ -636,6 +637,8 @@ void __init init_mem_mapping(void) load_cr3(swapper_pg_dir); __flush_tlb_all(); + hypervisor_init_mem_mapping(); + early_memtest(0, max_pfn_mapped << PAGE_SHIFT); } @@ -812,7 +815,7 @@ void __init zone_sizes_init(void) DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate) = { .loaded_mm = &init_mm, - .state = 0, + .next_asid = 1, .cr4 = ~0UL, /* fail hard if we screw up cr4 shadow initialization */ }; EXPORT_SYMBOL_GPL(cpu_tlbstate); diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 4c1b5fd0c7ad..34f0e1847dd6 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -13,6 +13,8 @@ #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/mmiotrace.h> +#include <linux/mem_encrypt.h> +#include <linux/efi.h> #include <asm/set_memory.h> #include <asm/e820/api.h> @@ -21,6 +23,7 @@ #include <asm/tlbflush.h> #include <asm/pgalloc.h> #include <asm/pat.h> +#include <asm/setup.h> #include "physaddr.h" @@ -106,12 +109,6 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, } /* - * Don't remap the low PCI/ISA area, it's always mapped.. - */ - if (is_ISA_range(phys_addr, last_addr)) - return (__force void __iomem *)phys_to_virt(phys_addr); - - /* * Don't allow anybody to remap normal RAM that we're using.. */ pfn = phys_addr >> PAGE_SHIFT; @@ -340,13 +337,17 @@ void iounmap(volatile void __iomem *addr) return; /* - * __ioremap special-cases the PCI/ISA range by not instantiating a - * vm_area and by simply returning an address into the kernel mapping - * of ISA space. So handle that here. + * The PCI/ISA range special-casing was removed from __ioremap() + * so this check, in theory, can be removed. However, there are + * cases where iounmap() is called for addresses not obtained via + * ioremap() (vga16fb for example). Add a warning so that these + * cases can be caught and fixed. */ if ((void __force *)addr >= phys_to_virt(ISA_START_ADDRESS) && - (void __force *)addr < phys_to_virt(ISA_END_ADDRESS)) + (void __force *)addr < phys_to_virt(ISA_END_ADDRESS)) { + WARN(1, "iounmap() called for ISA range not obtained using ioremap()\n"); return; + } addr = (volatile void __iomem *) (PAGE_MASK & (unsigned long __force)addr); @@ -399,12 +400,10 @@ void *xlate_dev_mem_ptr(phys_addr_t phys) unsigned long offset = phys & ~PAGE_MASK; void *vaddr; - /* If page is RAM, we can use __va. Otherwise ioremap and unmap. */ - if (page_is_ram(start >> PAGE_SHIFT)) - return __va(phys); + /* memremap() maps if RAM, otherwise falls back to ioremap() */ + vaddr = memremap(start, PAGE_SIZE, MEMREMAP_WB); - vaddr = ioremap_cache(start, PAGE_SIZE); - /* Only add the offset on success and return NULL if the ioremap() failed: */ + /* Only add the offset on success and return NULL if memremap() failed */ if (vaddr) vaddr += offset; @@ -413,11 +412,263 @@ void *xlate_dev_mem_ptr(phys_addr_t phys) void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr) { - if (page_is_ram(phys >> PAGE_SHIFT)) - return; + memunmap((void *)((unsigned long)addr & PAGE_MASK)); +} + +/* + * Examine the physical address to determine if it is an area of memory + * that should be mapped decrypted. If the memory is not part of the + * kernel usable area it was accessed and created decrypted, so these + * areas should be mapped decrypted. And since the encryption key can + * change across reboots, persistent memory should also be mapped + * decrypted. + */ +static bool memremap_should_map_decrypted(resource_size_t phys_addr, + unsigned long size) +{ + int is_pmem; + + /* + * Check if the address is part of a persistent memory region. + * This check covers areas added by E820, EFI and ACPI. + */ + is_pmem = region_intersects(phys_addr, size, IORESOURCE_MEM, + IORES_DESC_PERSISTENT_MEMORY); + if (is_pmem != REGION_DISJOINT) + return true; + + /* + * Check if the non-volatile attribute is set for an EFI + * reserved area. + */ + if (efi_enabled(EFI_BOOT)) { + switch (efi_mem_type(phys_addr)) { + case EFI_RESERVED_TYPE: + if (efi_mem_attributes(phys_addr) & EFI_MEMORY_NV) + return true; + break; + default: + break; + } + } + + /* Check if the address is outside kernel usable area */ + switch (e820__get_entry_type(phys_addr, phys_addr + size - 1)) { + case E820_TYPE_RESERVED: + case E820_TYPE_ACPI: + case E820_TYPE_NVS: + case E820_TYPE_UNUSABLE: + case E820_TYPE_PRAM: + return true; + default: + break; + } + + return false; +} + +/* + * Examine the physical address to determine if it is EFI data. Check + * it against the boot params structure and EFI tables and memory types. + */ +static bool memremap_is_efi_data(resource_size_t phys_addr, + unsigned long size) +{ + u64 paddr; + + /* Check if the address is part of EFI boot/runtime data */ + if (!efi_enabled(EFI_BOOT)) + return false; + + paddr = boot_params.efi_info.efi_memmap_hi; + paddr <<= 32; + paddr |= boot_params.efi_info.efi_memmap; + if (phys_addr == paddr) + return true; + + paddr = boot_params.efi_info.efi_systab_hi; + paddr <<= 32; + paddr |= boot_params.efi_info.efi_systab; + if (phys_addr == paddr) + return true; + + if (efi_is_table_address(phys_addr)) + return true; + + switch (efi_mem_type(phys_addr)) { + case EFI_BOOT_SERVICES_DATA: + case EFI_RUNTIME_SERVICES_DATA: + return true; + default: + break; + } + + return false; +} + +/* + * Examine the physical address to determine if it is boot data by checking + * it against the boot params setup_data chain. + */ +static bool memremap_is_setup_data(resource_size_t phys_addr, + unsigned long size) +{ + struct setup_data *data; + u64 paddr, paddr_next; + + paddr = boot_params.hdr.setup_data; + while (paddr) { + unsigned int len; + + if (phys_addr == paddr) + return true; + + data = memremap(paddr, sizeof(*data), + MEMREMAP_WB | MEMREMAP_DEC); + + paddr_next = data->next; + len = data->len; + + memunmap(data); + + if ((phys_addr > paddr) && (phys_addr < (paddr + len))) + return true; + + paddr = paddr_next; + } + + return false; +} + +/* + * Examine the physical address to determine if it is boot data by checking + * it against the boot params setup_data chain (early boot version). + */ +static bool __init early_memremap_is_setup_data(resource_size_t phys_addr, + unsigned long size) +{ + struct setup_data *data; + u64 paddr, paddr_next; + + paddr = boot_params.hdr.setup_data; + while (paddr) { + unsigned int len; + + if (phys_addr == paddr) + return true; + + data = early_memremap_decrypted(paddr, sizeof(*data)); + + paddr_next = data->next; + len = data->len; + + early_memunmap(data, sizeof(*data)); + + if ((phys_addr > paddr) && (phys_addr < (paddr + len))) + return true; + + paddr = paddr_next; + } + + return false; +} + +/* + * Architecture function to determine if RAM remap is allowed. By default, a + * RAM remap will map the data as encrypted. Determine if a RAM remap should + * not be done so that the data will be mapped decrypted. + */ +bool arch_memremap_can_ram_remap(resource_size_t phys_addr, unsigned long size, + unsigned long flags) +{ + if (!sme_active()) + return true; + + if (flags & MEMREMAP_ENC) + return true; + + if (flags & MEMREMAP_DEC) + return false; + + if (memremap_is_setup_data(phys_addr, size) || + memremap_is_efi_data(phys_addr, size) || + memremap_should_map_decrypted(phys_addr, size)) + return false; + + return true; +} + +/* + * Architecture override of __weak function to adjust the protection attributes + * used when remapping memory. By default, early_memremap() will map the data + * as encrypted. Determine if an encrypted mapping should not be done and set + * the appropriate protection attributes. + */ +pgprot_t __init early_memremap_pgprot_adjust(resource_size_t phys_addr, + unsigned long size, + pgprot_t prot) +{ + if (!sme_active()) + return prot; + + if (early_memremap_is_setup_data(phys_addr, size) || + memremap_is_efi_data(phys_addr, size) || + memremap_should_map_decrypted(phys_addr, size)) + prot = pgprot_decrypted(prot); + else + prot = pgprot_encrypted(prot); + + return prot; +} + +bool phys_mem_access_encrypted(unsigned long phys_addr, unsigned long size) +{ + return arch_memremap_can_ram_remap(phys_addr, size, 0); +} + +#ifdef CONFIG_ARCH_USE_MEMREMAP_PROT +/* Remap memory with encryption */ +void __init *early_memremap_encrypted(resource_size_t phys_addr, + unsigned long size) +{ + return early_memremap_prot(phys_addr, size, __PAGE_KERNEL_ENC); +} + +/* + * Remap memory with encryption and write-protected - cannot be called + * before pat_init() is called + */ +void __init *early_memremap_encrypted_wp(resource_size_t phys_addr, + unsigned long size) +{ + /* Be sure the write-protect PAT entry is set for write-protect */ + if (__pte2cachemode_tbl[_PAGE_CACHE_MODE_WP] != _PAGE_CACHE_MODE_WP) + return NULL; + + return early_memremap_prot(phys_addr, size, __PAGE_KERNEL_ENC_WP); +} + +/* Remap memory without encryption */ +void __init *early_memremap_decrypted(resource_size_t phys_addr, + unsigned long size) +{ + return early_memremap_prot(phys_addr, size, __PAGE_KERNEL_NOENC); +} + +/* + * Remap memory without encryption and write-protected - cannot be called + * before pat_init() is called + */ +void __init *early_memremap_decrypted_wp(resource_size_t phys_addr, + unsigned long size) +{ + /* Be sure the write-protect PAT entry is set for write-protect */ + if (__pte2cachemode_tbl[_PAGE_CACHE_MODE_WP] != _PAGE_CACHE_MODE_WP) + return NULL; - iounmap((void __iomem *)((unsigned long)addr & PAGE_MASK)); + return early_memremap_prot(phys_addr, size, __PAGE_KERNEL_NOENC_WP); } +#endif /* CONFIG_ARCH_USE_MEMREMAP_PROT */ static pte_t bm_pte[PAGE_SIZE/sizeof(pte_t)] __page_aligned_bss; diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index 02c9d7553409..bc84b73684b7 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -11,8 +11,8 @@ #include <asm/e820/types.h> #include <asm/tlbflush.h> #include <asm/sections.h> +#include <asm/pgtable.h> -extern pgd_t early_top_pgt[PTRS_PER_PGD]; extern struct range pfn_mapped[E820_MAX_ENTRIES]; static int __init map_range(struct range *range) @@ -87,7 +87,7 @@ static struct notifier_block kasan_die_notifier = { void __init kasan_early_init(void) { int i; - pteval_t pte_val = __pa_nodebug(kasan_zero_page) | __PAGE_KERNEL; + pteval_t pte_val = __pa_nodebug(kasan_zero_page) | __PAGE_KERNEL | _PAGE_ENC; pmdval_t pmd_val = __pa_nodebug(kasan_zero_pte) | _KERNPG_TABLE; pudval_t pud_val = __pa_nodebug(kasan_zero_pmd) | _KERNPG_TABLE; p4dval_t p4d_val = __pa_nodebug(kasan_zero_pud) | _KERNPG_TABLE; @@ -153,7 +153,7 @@ void __init kasan_init(void) */ memset(kasan_zero_page, 0, PAGE_SIZE); for (i = 0; i < PTRS_PER_PTE; i++) { - pte_t pte = __pte(__pa(kasan_zero_page) | __PAGE_KERNEL_RO); + pte_t pte = __pte(__pa(kasan_zero_page) | __PAGE_KERNEL_RO | _PAGE_ENC); set_pte(&kasan_zero_pte[i], pte); } /* Flush TLBs again to be sure that write protection applied. */ diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c new file mode 100644 index 000000000000..0fbd09269757 --- /dev/null +++ b/arch/x86/mm/mem_encrypt.c @@ -0,0 +1,593 @@ +/* + * AMD Memory Encryption Support + * + * Copyright (C) 2016 Advanced Micro Devices, Inc. + * + * Author: Tom Lendacky <thomas.lendacky@amd.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/linkage.h> +#include <linux/init.h> +#include <linux/mm.h> +#include <linux/dma-mapping.h> +#include <linux/swiotlb.h> +#include <linux/mem_encrypt.h> + +#include <asm/tlbflush.h> +#include <asm/fixmap.h> +#include <asm/setup.h> +#include <asm/bootparam.h> +#include <asm/set_memory.h> +#include <asm/cacheflush.h> +#include <asm/sections.h> +#include <asm/processor-flags.h> +#include <asm/msr.h> +#include <asm/cmdline.h> + +static char sme_cmdline_arg[] __initdata = "mem_encrypt"; +static char sme_cmdline_on[] __initdata = "on"; +static char sme_cmdline_off[] __initdata = "off"; + +/* + * Since SME related variables are set early in the boot process they must + * reside in the .data section so as not to be zeroed out when the .bss + * section is later cleared. + */ +unsigned long sme_me_mask __section(.data) = 0; +EXPORT_SYMBOL_GPL(sme_me_mask); + +/* Buffer used for early in-place encryption by BSP, no locking needed */ +static char sme_early_buffer[PAGE_SIZE] __aligned(PAGE_SIZE); + +/* + * This routine does not change the underlying encryption setting of the + * page(s) that map this memory. It assumes that eventually the memory is + * meant to be accessed as either encrypted or decrypted but the contents + * are currently not in the desired state. + * + * This routine follows the steps outlined in the AMD64 Architecture + * Programmer's Manual Volume 2, Section 7.10.8 Encrypt-in-Place. + */ +static void __init __sme_early_enc_dec(resource_size_t paddr, + unsigned long size, bool enc) +{ + void *src, *dst; + size_t len; + + if (!sme_me_mask) + return; + + local_flush_tlb(); + wbinvd(); + + /* + * There are limited number of early mapping slots, so map (at most) + * one page at time. + */ + while (size) { + len = min_t(size_t, sizeof(sme_early_buffer), size); + + /* + * Create mappings for the current and desired format of + * the memory. Use a write-protected mapping for the source. + */ + src = enc ? early_memremap_decrypted_wp(paddr, len) : + early_memremap_encrypted_wp(paddr, len); + + dst = enc ? early_memremap_encrypted(paddr, len) : + early_memremap_decrypted(paddr, len); + + /* + * If a mapping can't be obtained to perform the operation, + * then eventual access of that area in the desired mode + * will cause a crash. + */ + BUG_ON(!src || !dst); + + /* + * Use a temporary buffer, of cache-line multiple size, to + * avoid data corruption as documented in the APM. + */ + memcpy(sme_early_buffer, src, len); + memcpy(dst, sme_early_buffer, len); + + early_memunmap(dst, len); + early_memunmap(src, len); + + paddr += len; + size -= len; + } +} + +void __init sme_early_encrypt(resource_size_t paddr, unsigned long size) +{ + __sme_early_enc_dec(paddr, size, true); +} + +void __init sme_early_decrypt(resource_size_t paddr, unsigned long size) +{ + __sme_early_enc_dec(paddr, size, false); +} + +static void __init __sme_early_map_unmap_mem(void *vaddr, unsigned long size, + bool map) +{ + unsigned long paddr = (unsigned long)vaddr - __PAGE_OFFSET; + pmdval_t pmd_flags, pmd; + + /* Use early_pmd_flags but remove the encryption mask */ + pmd_flags = __sme_clr(early_pmd_flags); + + do { + pmd = map ? (paddr & PMD_MASK) + pmd_flags : 0; + __early_make_pgtable((unsigned long)vaddr, pmd); + + vaddr += PMD_SIZE; + paddr += PMD_SIZE; + size = (size <= PMD_SIZE) ? 0 : size - PMD_SIZE; + } while (size); + + __native_flush_tlb(); +} + +void __init sme_unmap_bootdata(char *real_mode_data) +{ + struct boot_params *boot_data; + unsigned long cmdline_paddr; + + if (!sme_active()) + return; + + /* Get the command line address before unmapping the real_mode_data */ + boot_data = (struct boot_params *)real_mode_data; + cmdline_paddr = boot_data->hdr.cmd_line_ptr | ((u64)boot_data->ext_cmd_line_ptr << 32); + + __sme_early_map_unmap_mem(real_mode_data, sizeof(boot_params), false); + + if (!cmdline_paddr) + return; + + __sme_early_map_unmap_mem(__va(cmdline_paddr), COMMAND_LINE_SIZE, false); +} + +void __init sme_map_bootdata(char *real_mode_data) +{ + struct boot_params *boot_data; + unsigned long cmdline_paddr; + + if (!sme_active()) + return; + + __sme_early_map_unmap_mem(real_mode_data, sizeof(boot_params), true); + + /* Get the command line address after mapping the real_mode_data */ + boot_data = (struct boot_params *)real_mode_data; + cmdline_paddr = boot_data->hdr.cmd_line_ptr | ((u64)boot_data->ext_cmd_line_ptr << 32); + + if (!cmdline_paddr) + return; + + __sme_early_map_unmap_mem(__va(cmdline_paddr), COMMAND_LINE_SIZE, true); +} + +void __init sme_early_init(void) +{ + unsigned int i; + + if (!sme_me_mask) + return; + + early_pmd_flags = __sme_set(early_pmd_flags); + + __supported_pte_mask = __sme_set(__supported_pte_mask); + + /* Update the protection map with memory encryption mask */ + for (i = 0; i < ARRAY_SIZE(protection_map); i++) + protection_map[i] = pgprot_encrypted(protection_map[i]); +} + +/* Architecture __weak replacement functions */ +void __init mem_encrypt_init(void) +{ + if (!sme_me_mask) + return; + + /* Call into SWIOTLB to update the SWIOTLB DMA buffers */ + swiotlb_update_mem_attributes(); + + pr_info("AMD Secure Memory Encryption (SME) active\n"); +} + +void swiotlb_set_mem_attributes(void *vaddr, unsigned long size) +{ + WARN(PAGE_ALIGN(size) != size, + "size is not page-aligned (%#lx)\n", size); + + /* Make the SWIOTLB buffer area decrypted */ + set_memory_decrypted((unsigned long)vaddr, size >> PAGE_SHIFT); +} + +static void __init sme_clear_pgd(pgd_t *pgd_base, unsigned long start, + unsigned long end) +{ + unsigned long pgd_start, pgd_end, pgd_size; + pgd_t *pgd_p; + + pgd_start = start & PGDIR_MASK; + pgd_end = end & PGDIR_MASK; + + pgd_size = (((pgd_end - pgd_start) / PGDIR_SIZE) + 1); + pgd_size *= sizeof(pgd_t); + + pgd_p = pgd_base + pgd_index(start); + + memset(pgd_p, 0, pgd_size); +} + +#define PGD_FLAGS _KERNPG_TABLE_NOENC +#define P4D_FLAGS _KERNPG_TABLE_NOENC +#define PUD_FLAGS _KERNPG_TABLE_NOENC +#define PMD_FLAGS (__PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL) + +static void __init *sme_populate_pgd(pgd_t *pgd_base, void *pgtable_area, + unsigned long vaddr, pmdval_t pmd_val) +{ + pgd_t *pgd_p; + p4d_t *p4d_p; + pud_t *pud_p; + pmd_t *pmd_p; + + pgd_p = pgd_base + pgd_index(vaddr); + if (native_pgd_val(*pgd_p)) { + if (IS_ENABLED(CONFIG_X86_5LEVEL)) + p4d_p = (p4d_t *)(native_pgd_val(*pgd_p) & ~PTE_FLAGS_MASK); + else + pud_p = (pud_t *)(native_pgd_val(*pgd_p) & ~PTE_FLAGS_MASK); + } else { + pgd_t pgd; + + if (IS_ENABLED(CONFIG_X86_5LEVEL)) { + p4d_p = pgtable_area; + memset(p4d_p, 0, sizeof(*p4d_p) * PTRS_PER_P4D); + pgtable_area += sizeof(*p4d_p) * PTRS_PER_P4D; + + pgd = native_make_pgd((pgdval_t)p4d_p + PGD_FLAGS); + } else { + pud_p = pgtable_area; + memset(pud_p, 0, sizeof(*pud_p) * PTRS_PER_PUD); + pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD; + + pgd = native_make_pgd((pgdval_t)pud_p + PGD_FLAGS); + } + native_set_pgd(pgd_p, pgd); + } + + if (IS_ENABLED(CONFIG_X86_5LEVEL)) { + p4d_p += p4d_index(vaddr); + if (native_p4d_val(*p4d_p)) { + pud_p = (pud_t *)(native_p4d_val(*p4d_p) & ~PTE_FLAGS_MASK); + } else { + p4d_t p4d; + + pud_p = pgtable_area; + memset(pud_p, 0, sizeof(*pud_p) * PTRS_PER_PUD); + pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD; + + p4d = native_make_p4d((pudval_t)pud_p + P4D_FLAGS); + native_set_p4d(p4d_p, p4d); + } + } + + pud_p += pud_index(vaddr); + if (native_pud_val(*pud_p)) { + if (native_pud_val(*pud_p) & _PAGE_PSE) + goto out; + + pmd_p = (pmd_t *)(native_pud_val(*pud_p) & ~PTE_FLAGS_MASK); + } else { + pud_t pud; + + pmd_p = pgtable_area; + memset(pmd_p, 0, sizeof(*pmd_p) * PTRS_PER_PMD); + pgtable_area += sizeof(*pmd_p) * PTRS_PER_PMD; + + pud = native_make_pud((pmdval_t)pmd_p + PUD_FLAGS); + native_set_pud(pud_p, pud); + } + + pmd_p += pmd_index(vaddr); + if (!native_pmd_val(*pmd_p) || !(native_pmd_val(*pmd_p) & _PAGE_PSE)) + native_set_pmd(pmd_p, native_make_pmd(pmd_val)); + +out: + return pgtable_area; +} + +static unsigned long __init sme_pgtable_calc(unsigned long len) +{ + unsigned long p4d_size, pud_size, pmd_size; + unsigned long total; + + /* + * Perform a relatively simplistic calculation of the pagetable + * entries that are needed. That mappings will be covered by 2MB + * PMD entries so we can conservatively calculate the required + * number of P4D, PUD and PMD structures needed to perform the + * mappings. Incrementing the count for each covers the case where + * the addresses cross entries. + */ + if (IS_ENABLED(CONFIG_X86_5LEVEL)) { + p4d_size = (ALIGN(len, PGDIR_SIZE) / PGDIR_SIZE) + 1; + p4d_size *= sizeof(p4d_t) * PTRS_PER_P4D; + pud_size = (ALIGN(len, P4D_SIZE) / P4D_SIZE) + 1; + pud_size *= sizeof(pud_t) * PTRS_PER_PUD; + } else { + p4d_size = 0; + pud_size = (ALIGN(len, PGDIR_SIZE) / PGDIR_SIZE) + 1; + pud_size *= sizeof(pud_t) * PTRS_PER_PUD; + } + pmd_size = (ALIGN(len, PUD_SIZE) / PUD_SIZE) + 1; + pmd_size *= sizeof(pmd_t) * PTRS_PER_PMD; + + total = p4d_size + pud_size + pmd_size; + + /* + * Now calculate the added pagetable structures needed to populate + * the new pagetables. + */ + if (IS_ENABLED(CONFIG_X86_5LEVEL)) { + p4d_size = ALIGN(total, PGDIR_SIZE) / PGDIR_SIZE; + p4d_size *= sizeof(p4d_t) * PTRS_PER_P4D; + pud_size = ALIGN(total, P4D_SIZE) / P4D_SIZE; + pud_size *= sizeof(pud_t) * PTRS_PER_PUD; + } else { + p4d_size = 0; + pud_size = ALIGN(total, PGDIR_SIZE) / PGDIR_SIZE; + pud_size *= sizeof(pud_t) * PTRS_PER_PUD; + } + pmd_size = ALIGN(total, PUD_SIZE) / PUD_SIZE; + pmd_size *= sizeof(pmd_t) * PTRS_PER_PMD; + + total += p4d_size + pud_size + pmd_size; + + return total; +} + +void __init sme_encrypt_kernel(void) +{ + unsigned long workarea_start, workarea_end, workarea_len; + unsigned long execute_start, execute_end, execute_len; + unsigned long kernel_start, kernel_end, kernel_len; + unsigned long pgtable_area_len; + unsigned long paddr, pmd_flags; + unsigned long decrypted_base; + void *pgtable_area; + pgd_t *pgd; + + if (!sme_active()) + return; + + /* + * Prepare for encrypting the kernel by building new pagetables with + * the necessary attributes needed to encrypt the kernel in place. + * + * One range of virtual addresses will map the memory occupied + * by the kernel as encrypted. + * + * Another range of virtual addresses will map the memory occupied + * by the kernel as decrypted and write-protected. + * + * The use of write-protect attribute will prevent any of the + * memory from being cached. + */ + + /* Physical addresses gives us the identity mapped virtual addresses */ + kernel_start = __pa_symbol(_text); + kernel_end = ALIGN(__pa_symbol(_end), PMD_PAGE_SIZE); + kernel_len = kernel_end - kernel_start; + + /* Set the encryption workarea to be immediately after the kernel */ + workarea_start = kernel_end; + + /* + * Calculate required number of workarea bytes needed: + * executable encryption area size: + * stack page (PAGE_SIZE) + * encryption routine page (PAGE_SIZE) + * intermediate copy buffer (PMD_PAGE_SIZE) + * pagetable structures for the encryption of the kernel + * pagetable structures for workarea (in case not currently mapped) + */ + execute_start = workarea_start; + execute_end = execute_start + (PAGE_SIZE * 2) + PMD_PAGE_SIZE; + execute_len = execute_end - execute_start; + + /* + * One PGD for both encrypted and decrypted mappings and a set of + * PUDs and PMDs for each of the encrypted and decrypted mappings. + */ + pgtable_area_len = sizeof(pgd_t) * PTRS_PER_PGD; + pgtable_area_len += sme_pgtable_calc(execute_end - kernel_start) * 2; + + /* PUDs and PMDs needed in the current pagetables for the workarea */ + pgtable_area_len += sme_pgtable_calc(execute_len + pgtable_area_len); + + /* + * The total workarea includes the executable encryption area and + * the pagetable area. + */ + workarea_len = execute_len + pgtable_area_len; + workarea_end = workarea_start + workarea_len; + + /* + * Set the address to the start of where newly created pagetable + * structures (PGDs, PUDs and PMDs) will be allocated. New pagetable + * structures are created when the workarea is added to the current + * pagetables and when the new encrypted and decrypted kernel + * mappings are populated. + */ + pgtable_area = (void *)execute_end; + + /* + * Make sure the current pagetable structure has entries for + * addressing the workarea. + */ + pgd = (pgd_t *)native_read_cr3_pa(); + paddr = workarea_start; + while (paddr < workarea_end) { + pgtable_area = sme_populate_pgd(pgd, pgtable_area, + paddr, + paddr + PMD_FLAGS); + + paddr += PMD_PAGE_SIZE; + } + + /* Flush the TLB - no globals so cr3 is enough */ + native_write_cr3(__native_read_cr3()); + + /* + * A new pagetable structure is being built to allow for the kernel + * to be encrypted. It starts with an empty PGD that will then be + * populated with new PUDs and PMDs as the encrypted and decrypted + * kernel mappings are created. + */ + pgd = pgtable_area; + memset(pgd, 0, sizeof(*pgd) * PTRS_PER_PGD); + pgtable_area += sizeof(*pgd) * PTRS_PER_PGD; + + /* Add encrypted kernel (identity) mappings */ + pmd_flags = PMD_FLAGS | _PAGE_ENC; + paddr = kernel_start; + while (paddr < kernel_end) { + pgtable_area = sme_populate_pgd(pgd, pgtable_area, + paddr, + paddr + pmd_flags); + + paddr += PMD_PAGE_SIZE; + } + + /* + * A different PGD index/entry must be used to get different + * pagetable entries for the decrypted mapping. Choose the next + * PGD index and convert it to a virtual address to be used as + * the base of the mapping. + */ + decrypted_base = (pgd_index(workarea_end) + 1) & (PTRS_PER_PGD - 1); + decrypted_base <<= PGDIR_SHIFT; + + /* Add decrypted, write-protected kernel (non-identity) mappings */ + pmd_flags = (PMD_FLAGS & ~_PAGE_CACHE_MASK) | (_PAGE_PAT | _PAGE_PWT); + paddr = kernel_start; + while (paddr < kernel_end) { + pgtable_area = sme_populate_pgd(pgd, pgtable_area, + paddr + decrypted_base, + paddr + pmd_flags); + + paddr += PMD_PAGE_SIZE; + } + + /* Add decrypted workarea mappings to both kernel mappings */ + paddr = workarea_start; + while (paddr < workarea_end) { + pgtable_area = sme_populate_pgd(pgd, pgtable_area, + paddr, + paddr + PMD_FLAGS); + + pgtable_area = sme_populate_pgd(pgd, pgtable_area, + paddr + decrypted_base, + paddr + PMD_FLAGS); + + paddr += PMD_PAGE_SIZE; + } + + /* Perform the encryption */ + sme_encrypt_execute(kernel_start, kernel_start + decrypted_base, + kernel_len, workarea_start, (unsigned long)pgd); + + /* + * At this point we are running encrypted. Remove the mappings for + * the decrypted areas - all that is needed for this is to remove + * the PGD entry/entries. + */ + sme_clear_pgd(pgd, kernel_start + decrypted_base, + kernel_end + decrypted_base); + + sme_clear_pgd(pgd, workarea_start + decrypted_base, + workarea_end + decrypted_base); + + /* Flush the TLB - no globals so cr3 is enough */ + native_write_cr3(__native_read_cr3()); +} + +void __init __nostackprotector sme_enable(struct boot_params *bp) +{ + const char *cmdline_ptr, *cmdline_arg, *cmdline_on, *cmdline_off; + unsigned int eax, ebx, ecx, edx; + bool active_by_default; + unsigned long me_mask; + char buffer[16]; + u64 msr; + + /* Check for the SME support leaf */ + eax = 0x80000000; + ecx = 0; + native_cpuid(&eax, &ebx, &ecx, &edx); + if (eax < 0x8000001f) + return; + + /* + * Check for the SME feature: + * CPUID Fn8000_001F[EAX] - Bit 0 + * Secure Memory Encryption support + * CPUID Fn8000_001F[EBX] - Bits 5:0 + * Pagetable bit position used to indicate encryption + */ + eax = 0x8000001f; + ecx = 0; + native_cpuid(&eax, &ebx, &ecx, &edx); + if (!(eax & 1)) + return; + + me_mask = 1UL << (ebx & 0x3f); + + /* Check if SME is enabled */ + msr = __rdmsr(MSR_K8_SYSCFG); + if (!(msr & MSR_K8_SYSCFG_MEM_ENCRYPT)) + return; + + /* + * Fixups have not been applied to phys_base yet and we're running + * identity mapped, so we must obtain the address to the SME command + * line argument data using rip-relative addressing. + */ + asm ("lea sme_cmdline_arg(%%rip), %0" + : "=r" (cmdline_arg) + : "p" (sme_cmdline_arg)); + asm ("lea sme_cmdline_on(%%rip), %0" + : "=r" (cmdline_on) + : "p" (sme_cmdline_on)); + asm ("lea sme_cmdline_off(%%rip), %0" + : "=r" (cmdline_off) + : "p" (sme_cmdline_off)); + + if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT)) + active_by_default = true; + else + active_by_default = false; + + cmdline_ptr = (const char *)((u64)bp->hdr.cmd_line_ptr | + ((u64)bp->ext_cmd_line_ptr << 32)); + + cmdline_find_option(cmdline_ptr, cmdline_arg, buffer, sizeof(buffer)); + + if (!strncmp(buffer, cmdline_on, sizeof(buffer))) + sme_me_mask = me_mask; + else if (!strncmp(buffer, cmdline_off, sizeof(buffer))) + sme_me_mask = 0; + else + sme_me_mask = active_by_default ? me_mask : 0; +} diff --git a/arch/x86/mm/mem_encrypt_boot.S b/arch/x86/mm/mem_encrypt_boot.S new file mode 100644 index 000000000000..730e6d541df1 --- /dev/null +++ b/arch/x86/mm/mem_encrypt_boot.S @@ -0,0 +1,149 @@ +/* + * AMD Memory Encryption Support + * + * Copyright (C) 2016 Advanced Micro Devices, Inc. + * + * Author: Tom Lendacky <thomas.lendacky@amd.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/linkage.h> +#include <asm/pgtable.h> +#include <asm/page.h> +#include <asm/processor-flags.h> +#include <asm/msr-index.h> + + .text + .code64 +ENTRY(sme_encrypt_execute) + + /* + * Entry parameters: + * RDI - virtual address for the encrypted kernel mapping + * RSI - virtual address for the decrypted kernel mapping + * RDX - length of kernel + * RCX - virtual address of the encryption workarea, including: + * - stack page (PAGE_SIZE) + * - encryption routine page (PAGE_SIZE) + * - intermediate copy buffer (PMD_PAGE_SIZE) + * R8 - physcial address of the pagetables to use for encryption + */ + + push %rbp + movq %rsp, %rbp /* RBP now has original stack pointer */ + + /* Set up a one page stack in the non-encrypted memory area */ + movq %rcx, %rax /* Workarea stack page */ + leaq PAGE_SIZE(%rax), %rsp /* Set new stack pointer */ + addq $PAGE_SIZE, %rax /* Workarea encryption routine */ + + push %r12 + movq %rdi, %r10 /* Encrypted kernel */ + movq %rsi, %r11 /* Decrypted kernel */ + movq %rdx, %r12 /* Kernel length */ + + /* Copy encryption routine into the workarea */ + movq %rax, %rdi /* Workarea encryption routine */ + leaq __enc_copy(%rip), %rsi /* Encryption routine */ + movq $(.L__enc_copy_end - __enc_copy), %rcx /* Encryption routine length */ + rep movsb + + /* Setup registers for call */ + movq %r10, %rdi /* Encrypted kernel */ + movq %r11, %rsi /* Decrypted kernel */ + movq %r8, %rdx /* Pagetables used for encryption */ + movq %r12, %rcx /* Kernel length */ + movq %rax, %r8 /* Workarea encryption routine */ + addq $PAGE_SIZE, %r8 /* Workarea intermediate copy buffer */ + + call *%rax /* Call the encryption routine */ + + pop %r12 + + movq %rbp, %rsp /* Restore original stack pointer */ + pop %rbp + + ret +ENDPROC(sme_encrypt_execute) + +ENTRY(__enc_copy) +/* + * Routine used to encrypt kernel. + * This routine must be run outside of the kernel proper since + * the kernel will be encrypted during the process. So this + * routine is defined here and then copied to an area outside + * of the kernel where it will remain and run decrypted + * during execution. + * + * On entry the registers must be: + * RDI - virtual address for the encrypted kernel mapping + * RSI - virtual address for the decrypted kernel mapping + * RDX - address of the pagetables to use for encryption + * RCX - length of kernel + * R8 - intermediate copy buffer + * + * RAX - points to this routine + * + * The kernel will be encrypted by copying from the non-encrypted + * kernel space to an intermediate buffer and then copying from the + * intermediate buffer back to the encrypted kernel space. The physical + * addresses of the two kernel space mappings are the same which + * results in the kernel being encrypted "in place". + */ + /* Enable the new page tables */ + mov %rdx, %cr3 + + /* Flush any global TLBs */ + mov %cr4, %rdx + andq $~X86_CR4_PGE, %rdx + mov %rdx, %cr4 + orq $X86_CR4_PGE, %rdx + mov %rdx, %cr4 + + /* Set the PAT register PA5 entry to write-protect */ + push %rcx + movl $MSR_IA32_CR_PAT, %ecx + rdmsr + push %rdx /* Save original PAT value */ + andl $0xffff00ff, %edx /* Clear PA5 */ + orl $0x00000500, %edx /* Set PA5 to WP */ + wrmsr + pop %rdx /* RDX contains original PAT value */ + pop %rcx + + movq %rcx, %r9 /* Save kernel length */ + movq %rdi, %r10 /* Save encrypted kernel address */ + movq %rsi, %r11 /* Save decrypted kernel address */ + + wbinvd /* Invalidate any cache entries */ + + /* Copy/encrypt 2MB at a time */ +1: + movq %r11, %rsi /* Source - decrypted kernel */ + movq %r8, %rdi /* Dest - intermediate copy buffer */ + movq $PMD_PAGE_SIZE, %rcx /* 2MB length */ + rep movsb + + movq %r8, %rsi /* Source - intermediate copy buffer */ + movq %r10, %rdi /* Dest - encrypted kernel */ + movq $PMD_PAGE_SIZE, %rcx /* 2MB length */ + rep movsb + + addq $PMD_PAGE_SIZE, %r11 + addq $PMD_PAGE_SIZE, %r10 + subq $PMD_PAGE_SIZE, %r9 /* Kernel length decrement */ + jnz 1b /* Kernel length not zero? */ + + /* Restore PAT register */ + push %rdx /* Save original PAT value */ + movl $MSR_IA32_CR_PAT, %ecx + rdmsr + pop %rdx /* Restore original PAT value */ + wrmsr + + ret +.L__enc_copy_end: +ENDPROC(__enc_copy) diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index 229d04a83f85..a99679826846 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -37,22 +37,21 @@ struct va_alignment __read_mostly va_align = { .flags = -1, }; -unsigned long tasksize_32bit(void) +unsigned long task_size_32bit(void) { return IA32_PAGE_OFFSET; } -unsigned long tasksize_64bit(void) +unsigned long task_size_64bit(int full_addr_space) { - return TASK_SIZE_MAX; + return full_addr_space ? TASK_SIZE_MAX : DEFAULT_MAP_WINDOW; } static unsigned long stack_maxrandom_size(unsigned long task_size) { unsigned long max = 0; - if ((current->flags & PF_RANDOMIZE) && - !(current->personality & ADDR_NO_RANDOMIZE)) { - max = (-1UL) & __STACK_RND_MASK(task_size == tasksize_32bit()); + if (current->flags & PF_RANDOMIZE) { + max = (-1UL) & __STACK_RND_MASK(task_size == task_size_32bit()); max <<= PAGE_SHIFT; } @@ -79,13 +78,13 @@ static int mmap_is_legacy(void) static unsigned long arch_rnd(unsigned int rndbits) { + if (!(current->flags & PF_RANDOMIZE)) + return 0; return (get_random_long() & ((1UL << rndbits) - 1)) << PAGE_SHIFT; } unsigned long arch_mmap_rnd(void) { - if (!(current->flags & PF_RANDOMIZE)) - return 0; return arch_rnd(mmap_is_ia32() ? mmap32_rnd_bits : mmap64_rnd_bits); } @@ -142,7 +141,7 @@ void arch_pick_mmap_layout(struct mm_struct *mm) mm->get_unmapped_area = arch_get_unmapped_area_topdown; arch_pick_mmap_base(&mm->mmap_base, &mm->mmap_legacy_base, - arch_rnd(mmap64_rnd_bits), tasksize_64bit()); + arch_rnd(mmap64_rnd_bits), task_size_64bit(0)); #ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES /* @@ -152,7 +151,7 @@ void arch_pick_mmap_layout(struct mm_struct *mm) * mmap_base, the compat syscall uses mmap_compat_base. */ arch_pick_mmap_base(&mm->mmap_compat_base, &mm->mmap_compat_legacy_base, - arch_rnd(mmap32_rnd_bits), tasksize_32bit()); + arch_rnd(mmap32_rnd_bits), task_size_32bit()); #endif } diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c index 1c34b767c84c..9ceaa955d2ba 100644 --- a/arch/x86/mm/mpx.c +++ b/arch/x86/mm/mpx.c @@ -355,10 +355,19 @@ int mpx_enable_management(void) */ bd_base = mpx_get_bounds_dir(); down_write(&mm->mmap_sem); + + /* MPX doesn't support addresses above 47 bits yet. */ + if (find_vma(mm, DEFAULT_MAP_WINDOW)) { + pr_warn_once("%s (%d): MPX cannot handle addresses " + "above 47-bits. Disabling.", + current->comm, current->pid); + ret = -ENXIO; + goto out; + } mm->context.bd_addr = bd_base; if (mm->context.bd_addr == MPX_INVALID_BOUNDS_DIR) ret = -ENXIO; - +out: up_write(&mm->mmap_sem); return ret; } @@ -1030,3 +1039,25 @@ void mpx_notify_unmap(struct mm_struct *mm, struct vm_area_struct *vma, if (ret) force_sig(SIGSEGV, current); } + +/* MPX cannot handle addresses above 47 bits yet. */ +unsigned long mpx_unmapped_area_check(unsigned long addr, unsigned long len, + unsigned long flags) +{ + if (!kernel_managing_mpx_tables(current->mm)) + return addr; + if (addr + len <= DEFAULT_MAP_WINDOW) + return addr; + if (flags & MAP_FIXED) + return -ENOMEM; + + /* + * Requested len is larger than the whole area we're allowed to map in. + * Resetting hinting address wouldn't do much good -- fail early. + */ + if (len > DEFAULT_MAP_WINDOW) + return -ENOMEM; + + /* Look for unmap area within DEFAULT_MAP_WINDOW */ + return 0; +} diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c index a8f90ce3dedf..d805162e6045 100644 --- a/arch/x86/mm/numa_emulation.c +++ b/arch/x86/mm/numa_emulation.c @@ -75,13 +75,15 @@ static int __init emu_setup_memblk(struct numa_meminfo *ei, /* * Sets up nr_nodes fake nodes interleaved over physical nodes ranging from addr - * to max_addr. The return value is the number of nodes allocated. + * to max_addr. + * + * Returns zero on success or negative on error. */ static int __init split_nodes_interleave(struct numa_meminfo *ei, struct numa_meminfo *pi, u64 addr, u64 max_addr, int nr_nodes) { - nodemask_t physnode_mask = NODE_MASK_NONE; + nodemask_t physnode_mask = numa_nodes_parsed; u64 size; int big; int nid = 0; @@ -116,9 +118,6 @@ static int __init split_nodes_interleave(struct numa_meminfo *ei, return -1; } - for (i = 0; i < pi->nr_blks; i++) - node_set(pi->blk[i].nid, physnode_mask); - /* * Continue to fill physical nodes with fake nodes until there is no * memory left on any of them. @@ -200,13 +199,15 @@ static u64 __init find_end_of_node(u64 start, u64 max_addr, u64 size) /* * Sets up fake nodes of `size' interleaved over physical nodes ranging from - * `addr' to `max_addr'. The return value is the number of nodes allocated. + * `addr' to `max_addr'. + * + * Returns zero on success or negative on error. */ static int __init split_nodes_size_interleave(struct numa_meminfo *ei, struct numa_meminfo *pi, u64 addr, u64 max_addr, u64 size) { - nodemask_t physnode_mask = NODE_MASK_NONE; + nodemask_t physnode_mask = numa_nodes_parsed; u64 min_size; int nid = 0; int i, ret; @@ -231,9 +232,6 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei, } size &= FAKE_NODE_MIN_HASH_MASK; - for (i = 0; i < pi->nr_blks; i++) - node_set(pi->blk[i].nid, physnode_mask); - /* * Fill physical nodes with fake nodes of size until there is no memory * left on any of them. @@ -280,6 +278,22 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei, return 0; } +int __init setup_emu2phys_nid(int *dfl_phys_nid) +{ + int i, max_emu_nid = 0; + + *dfl_phys_nid = NUMA_NO_NODE; + for (i = 0; i < ARRAY_SIZE(emu_nid_to_phys); i++) { + if (emu_nid_to_phys[i] != NUMA_NO_NODE) { + max_emu_nid = i; + if (*dfl_phys_nid == NUMA_NO_NODE) + *dfl_phys_nid = emu_nid_to_phys[i]; + } + } + + return max_emu_nid; +} + /** * numa_emulation - Emulate NUMA nodes * @numa_meminfo: NUMA configuration to massage @@ -376,23 +390,18 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt) * Determine the max emulated nid and the default phys nid to use * for unmapped nodes. */ - max_emu_nid = 0; - dfl_phys_nid = NUMA_NO_NODE; - for (i = 0; i < ARRAY_SIZE(emu_nid_to_phys); i++) { - if (emu_nid_to_phys[i] != NUMA_NO_NODE) { - max_emu_nid = i; - if (dfl_phys_nid == NUMA_NO_NODE) - dfl_phys_nid = emu_nid_to_phys[i]; - } - } - if (dfl_phys_nid == NUMA_NO_NODE) { - pr_warning("NUMA: Warning: can't determine default physical node, disabling emulation\n"); - goto no_emu; - } + max_emu_nid = setup_emu2phys_nid(&dfl_phys_nid); /* commit */ *numa_meminfo = ei; + /* Make sure numa_nodes_parsed only contains emulated nodes */ + nodes_clear(numa_nodes_parsed); + for (i = 0; i < ARRAY_SIZE(ei.blk); i++) + if (ei.blk[i].start != ei.blk[i].end && + ei.blk[i].nid != NUMA_NO_NODE) + node_set(ei.blk[i].nid, numa_nodes_parsed); + /* * Transform __apicid_to_node table to use emulated nids by * reverse-mapping phys_nid. The maps should always exist but fall diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 757b0bcdf712..dfb7d657cf43 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -1775,6 +1775,70 @@ int set_memory_4k(unsigned long addr, int numpages) __pgprot(0), 1, 0, NULL); } +static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc) +{ + struct cpa_data cpa; + unsigned long start; + int ret; + + /* Nothing to do if the SME is not active */ + if (!sme_active()) + return 0; + + /* Should not be working on unaligned addresses */ + if (WARN_ONCE(addr & ~PAGE_MASK, "misaligned address: %#lx\n", addr)) + addr &= PAGE_MASK; + + start = addr; + + memset(&cpa, 0, sizeof(cpa)); + cpa.vaddr = &addr; + cpa.numpages = numpages; + cpa.mask_set = enc ? __pgprot(_PAGE_ENC) : __pgprot(0); + cpa.mask_clr = enc ? __pgprot(0) : __pgprot(_PAGE_ENC); + cpa.pgd = init_mm.pgd; + + /* Must avoid aliasing mappings in the highmem code */ + kmap_flush_unused(); + vm_unmap_aliases(); + + /* + * Before changing the encryption attribute, we need to flush caches. + */ + if (static_cpu_has(X86_FEATURE_CLFLUSH)) + cpa_flush_range(start, numpages, 1); + else + cpa_flush_all(1); + + ret = __change_page_attr_set_clr(&cpa, 1); + + /* + * After changing the encryption attribute, we need to flush TLBs + * again in case any speculative TLB caching occurred (but no need + * to flush caches again). We could just use cpa_flush_all(), but + * in case TLB flushing gets optimized in the cpa_flush_range() + * path use the same logic as above. + */ + if (static_cpu_has(X86_FEATURE_CLFLUSH)) + cpa_flush_range(start, numpages, 0); + else + cpa_flush_all(0); + + return ret; +} + +int set_memory_encrypted(unsigned long addr, int numpages) +{ + return __set_memory_enc_dec(addr, numpages, true); +} +EXPORT_SYMBOL_GPL(set_memory_encrypted); + +int set_memory_decrypted(unsigned long addr, int numpages) +{ + return __set_memory_enc_dec(addr, numpages, false); +} +EXPORT_SYMBOL_GPL(set_memory_decrypted); + int set_pages_uc(struct page *page, int numpages) { unsigned long addr = (unsigned long)page_address(page); @@ -2020,6 +2084,9 @@ int kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address, if (!(page_flags & _PAGE_RW)) cpa.mask_clr = __pgprot(_PAGE_RW); + if (!(page_flags & _PAGE_ENC)) + cpa.mask_clr = pgprot_encrypted(cpa.mask_clr); + cpa.mask_set = __pgprot(_PAGE_PRESENT | page_flags); retval = __change_page_attr_set_clr(&cpa, 0); diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 45979502f64b..fe7d57a8fb60 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -293,7 +293,7 @@ void init_cache_modes(void) * pat_init - Initialize PAT MSR and PAT table * * This function initializes PAT MSR and PAT table with an OS-defined value - * to enable additional cache attributes, WC and WT. + * to enable additional cache attributes, WC, WT and WP. * * This function must be called on all CPUs using the specific sequence of * operations defined in Intel SDM. mtrr_rendezvous_handler() provides this @@ -352,7 +352,7 @@ void pat_init(void) * 010 2 UC-: _PAGE_CACHE_MODE_UC_MINUS * 011 3 UC : _PAGE_CACHE_MODE_UC * 100 4 WB : Reserved - * 101 5 WC : Reserved + * 101 5 WP : _PAGE_CACHE_MODE_WP * 110 6 UC-: Reserved * 111 7 WT : _PAGE_CACHE_MODE_WT * @@ -360,7 +360,7 @@ void pat_init(void) * corresponding types in the presence of PAT errata. */ pat = PAT(0, WB) | PAT(1, WC) | PAT(2, UC_MINUS) | PAT(3, UC) | - PAT(4, WB) | PAT(5, WC) | PAT(6, UC_MINUS) | PAT(7, WT); + PAT(4, WB) | PAT(5, WP) | PAT(6, UC_MINUS) | PAT(7, WT); } if (!boot_cpu_done) { @@ -744,6 +744,9 @@ EXPORT_SYMBOL(arch_io_free_memtype_wc); pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, unsigned long size, pgprot_t vma_prot) { + if (!phys_mem_access_encrypted(pfn << PAGE_SHIFT, size)) + vma_prot = pgprot_decrypted(vma_prot); + return vma_prot; } diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 508a708eb9a6..218834a3e9ad 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -56,7 +56,7 @@ void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte) { pgtable_page_dtor(pte); paravirt_release_pte(page_to_pfn(pte)); - tlb_remove_page(tlb, pte); + tlb_remove_table(tlb, pte); } #if CONFIG_PGTABLE_LEVELS > 2 @@ -72,21 +72,21 @@ void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd) tlb->need_flush_all = 1; #endif pgtable_pmd_page_dtor(page); - tlb_remove_page(tlb, page); + tlb_remove_table(tlb, page); } #if CONFIG_PGTABLE_LEVELS > 3 void ___pud_free_tlb(struct mmu_gather *tlb, pud_t *pud) { paravirt_release_pud(__pa(pud) >> PAGE_SHIFT); - tlb_remove_page(tlb, virt_to_page(pud)); + tlb_remove_table(tlb, virt_to_page(pud)); } #if CONFIG_PGTABLE_LEVELS > 4 void ___p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d) { paravirt_release_p4d(__pa(p4d) >> PAGE_SHIFT); - tlb_remove_page(tlb, virt_to_page(p4d)); + tlb_remove_table(tlb, virt_to_page(p4d)); } #endif /* CONFIG_PGTABLE_LEVELS > 4 */ #endif /* CONFIG_PGTABLE_LEVELS > 3 */ diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 014d07a80053..ce104b962a17 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -28,6 +28,42 @@ * Implement flush IPI by CALL_FUNCTION_VECTOR, Alex Shi */ +atomic64_t last_mm_ctx_id = ATOMIC64_INIT(1); + +static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen, + u16 *new_asid, bool *need_flush) +{ + u16 asid; + + if (!static_cpu_has(X86_FEATURE_PCID)) { + *new_asid = 0; + *need_flush = true; + return; + } + + for (asid = 0; asid < TLB_NR_DYN_ASIDS; asid++) { + if (this_cpu_read(cpu_tlbstate.ctxs[asid].ctx_id) != + next->context.ctx_id) + continue; + + *new_asid = asid; + *need_flush = (this_cpu_read(cpu_tlbstate.ctxs[asid].tlb_gen) < + next_tlb_gen); + return; + } + + /* + * We don't currently own an ASID slot on this CPU. + * Allocate a slot. + */ + *new_asid = this_cpu_add_return(cpu_tlbstate.next_asid, 1) - 1; + if (*new_asid >= TLB_NR_DYN_ASIDS) { + *new_asid = 0; + this_cpu_write(cpu_tlbstate.next_asid, 1); + } + *need_flush = true; +} + void leave_mm(int cpu) { struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm); @@ -43,12 +79,11 @@ void leave_mm(int cpu) if (loaded_mm == &init_mm) return; - if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) - BUG(); + /* Warn if we're not lazy. */ + WARN_ON(cpumask_test_cpu(smp_processor_id(), mm_cpumask(loaded_mm))); switch_mm(NULL, &init_mm, NULL); } -EXPORT_SYMBOL_GPL(leave_mm); void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk) @@ -63,115 +98,219 @@ void switch_mm(struct mm_struct *prev, struct mm_struct *next, void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk) { - unsigned cpu = smp_processor_id(); struct mm_struct *real_prev = this_cpu_read(cpu_tlbstate.loaded_mm); + u16 prev_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid); + unsigned cpu = smp_processor_id(); + u64 next_tlb_gen; /* - * NB: The scheduler will call us with prev == next when - * switching from lazy TLB mode to normal mode if active_mm - * isn't changing. When this happens, there is no guarantee - * that CR3 (and hence cpu_tlbstate.loaded_mm) matches next. + * NB: The scheduler will call us with prev == next when switching + * from lazy TLB mode to normal mode if active_mm isn't changing. + * When this happens, we don't assume that CR3 (and hence + * cpu_tlbstate.loaded_mm) matches next. * * NB: leave_mm() calls us with prev == NULL and tsk == NULL. */ - this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK); + /* We don't want flush_tlb_func_* to run concurrently with us. */ + if (IS_ENABLED(CONFIG_PROVE_LOCKING)) + WARN_ON_ONCE(!irqs_disabled()); + + /* + * Verify that CR3 is what we think it is. This will catch + * hypothetical buggy code that directly switches to swapper_pg_dir + * without going through leave_mm() / switch_mm_irqs_off() or that + * does something like write_cr3(read_cr3_pa()). + */ + VM_BUG_ON(__read_cr3() != (__sme_pa(real_prev->pgd) | prev_asid)); if (real_prev == next) { - /* - * There's nothing to do: we always keep the per-mm control - * regs in sync with cpu_tlbstate.loaded_mm. Just - * sanity-check mm_cpumask. - */ - if (WARN_ON_ONCE(!cpumask_test_cpu(cpu, mm_cpumask(next)))) - cpumask_set_cpu(cpu, mm_cpumask(next)); - return; - } + VM_BUG_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) != + next->context.ctx_id); + + if (cpumask_test_cpu(cpu, mm_cpumask(next))) { + /* + * There's nothing to do: we weren't lazy, and we + * aren't changing our mm. We don't need to flush + * anything, nor do we need to update CR3, CR4, or + * LDTR. + */ + return; + } + + /* Resume remote flushes and then read tlb_gen. */ + cpumask_set_cpu(cpu, mm_cpumask(next)); + next_tlb_gen = atomic64_read(&next->context.tlb_gen); + + if (this_cpu_read(cpu_tlbstate.ctxs[prev_asid].tlb_gen) < + next_tlb_gen) { + /* + * Ideally, we'd have a flush_tlb() variant that + * takes the known CR3 value as input. This would + * be faster on Xen PV and on hypothetical CPUs + * on which INVPCID is fast. + */ + this_cpu_write(cpu_tlbstate.ctxs[prev_asid].tlb_gen, + next_tlb_gen); + write_cr3(__sme_pa(next->pgd) | prev_asid); + trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, + TLB_FLUSH_ALL); + } - if (IS_ENABLED(CONFIG_VMAP_STACK)) { /* - * If our current stack is in vmalloc space and isn't - * mapped in the new pgd, we'll double-fault. Forcibly - * map it. + * We just exited lazy mode, which means that CR4 and/or LDTR + * may be stale. (Changes to the required CR4 and LDTR states + * are not reflected in tlb_gen.) */ - unsigned int stack_pgd_index = pgd_index(current_stack_pointer()); - - pgd_t *pgd = next->pgd + stack_pgd_index; - - if (unlikely(pgd_none(*pgd))) - set_pgd(pgd, init_mm.pgd[stack_pgd_index]); - } + } else { + u16 new_asid; + bool need_flush; + + if (IS_ENABLED(CONFIG_VMAP_STACK)) { + /* + * If our current stack is in vmalloc space and isn't + * mapped in the new pgd, we'll double-fault. Forcibly + * map it. + */ + unsigned int index = pgd_index(current_stack_pointer()); + pgd_t *pgd = next->pgd + index; + + if (unlikely(pgd_none(*pgd))) + set_pgd(pgd, init_mm.pgd[index]); + } - this_cpu_write(cpu_tlbstate.loaded_mm, next); + /* Stop remote flushes for the previous mm */ + if (cpumask_test_cpu(cpu, mm_cpumask(real_prev))) + cpumask_clear_cpu(cpu, mm_cpumask(real_prev)); - WARN_ON_ONCE(cpumask_test_cpu(cpu, mm_cpumask(next))); - cpumask_set_cpu(cpu, mm_cpumask(next)); + VM_WARN_ON_ONCE(cpumask_test_cpu(cpu, mm_cpumask(next))); - /* - * Re-load page tables. - * - * This logic has an ordering constraint: - * - * CPU 0: Write to a PTE for 'next' - * CPU 0: load bit 1 in mm_cpumask. if nonzero, send IPI. - * CPU 1: set bit 1 in next's mm_cpumask - * CPU 1: load from the PTE that CPU 0 writes (implicit) - * - * We need to prevent an outcome in which CPU 1 observes - * the new PTE value and CPU 0 observes bit 1 clear in - * mm_cpumask. (If that occurs, then the IPI will never - * be sent, and CPU 0's TLB will contain a stale entry.) - * - * The bad outcome can occur if either CPU's load is - * reordered before that CPU's store, so both CPUs must - * execute full barriers to prevent this from happening. - * - * Thus, switch_mm needs a full barrier between the - * store to mm_cpumask and any operation that could load - * from next->pgd. TLB fills are special and can happen - * due to instruction fetches or for no reason at all, - * and neither LOCK nor MFENCE orders them. - * Fortunately, load_cr3() is serializing and gives the - * ordering guarantee we need. - */ - load_cr3(next->pgd); - - /* - * This gets called via leave_mm() in the idle path where RCU - * functions differently. Tracing normally uses RCU, so we have to - * call the tracepoint specially here. - */ - trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); + /* + * Start remote flushes and then read tlb_gen. + */ + cpumask_set_cpu(cpu, mm_cpumask(next)); + next_tlb_gen = atomic64_read(&next->context.tlb_gen); + + choose_new_asid(next, next_tlb_gen, &new_asid, &need_flush); + + if (need_flush) { + this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id); + this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen); + write_cr3(__sme_pa(next->pgd) | new_asid); + trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, + TLB_FLUSH_ALL); + } else { + /* The new ASID is already up to date. */ + write_cr3(__sme_pa(next->pgd) | new_asid | CR3_NOFLUSH); + trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, 0); + } - /* Stop flush ipis for the previous mm */ - WARN_ON_ONCE(!cpumask_test_cpu(cpu, mm_cpumask(real_prev)) && - real_prev != &init_mm); - cpumask_clear_cpu(cpu, mm_cpumask(real_prev)); + this_cpu_write(cpu_tlbstate.loaded_mm, next); + this_cpu_write(cpu_tlbstate.loaded_mm_asid, new_asid); + } - /* Load per-mm CR4 and LDTR state */ load_mm_cr4(next); switch_ldt(real_prev, next); } +/* + * flush_tlb_func_common()'s memory ordering requirement is that any + * TLB fills that happen after we flush the TLB are ordered after we + * read active_mm's tlb_gen. We don't need any explicit barriers + * because all x86 flush operations are serializing and the + * atomic64_read operation won't be reordered by the compiler. + */ static void flush_tlb_func_common(const struct flush_tlb_info *f, bool local, enum tlb_flush_reason reason) { + /* + * We have three different tlb_gen values in here. They are: + * + * - mm_tlb_gen: the latest generation. + * - local_tlb_gen: the generation that this CPU has already caught + * up to. + * - f->new_tlb_gen: the generation that the requester of the flush + * wants us to catch up to. + */ + struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm); + u32 loaded_mm_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid); + u64 mm_tlb_gen = atomic64_read(&loaded_mm->context.tlb_gen); + u64 local_tlb_gen = this_cpu_read(cpu_tlbstate.ctxs[loaded_mm_asid].tlb_gen); + /* This code cannot presently handle being reentered. */ VM_WARN_ON(!irqs_disabled()); - if (this_cpu_read(cpu_tlbstate.state) != TLBSTATE_OK) { - leave_mm(smp_processor_id()); + VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[loaded_mm_asid].ctx_id) != + loaded_mm->context.ctx_id); + + if (!cpumask_test_cpu(smp_processor_id(), mm_cpumask(loaded_mm))) { + /* + * We're in lazy mode -- don't flush. We can get here on + * remote flushes due to races and on local flushes if a + * kernel thread coincidentally flushes the mm it's lazily + * still using. + */ return; } - if (f->end == TLB_FLUSH_ALL) { - local_flush_tlb(); - if (local) - count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); - trace_tlb_flush(reason, TLB_FLUSH_ALL); - } else { + if (unlikely(local_tlb_gen == mm_tlb_gen)) { + /* + * There's nothing to do: we're already up to date. This can + * happen if two concurrent flushes happen -- the first flush to + * be handled can catch us all the way up, leaving no work for + * the second flush. + */ + trace_tlb_flush(reason, 0); + return; + } + + WARN_ON_ONCE(local_tlb_gen > mm_tlb_gen); + WARN_ON_ONCE(f->new_tlb_gen > mm_tlb_gen); + + /* + * If we get to this point, we know that our TLB is out of date. + * This does not strictly imply that we need to flush (it's + * possible that f->new_tlb_gen <= local_tlb_gen), but we're + * going to need to flush in the very near future, so we might + * as well get it over with. + * + * The only question is whether to do a full or partial flush. + * + * We do a partial flush if requested and two extra conditions + * are met: + * + * 1. f->new_tlb_gen == local_tlb_gen + 1. We have an invariant that + * we've always done all needed flushes to catch up to + * local_tlb_gen. If, for example, local_tlb_gen == 2 and + * f->new_tlb_gen == 3, then we know that the flush needed to bring + * us up to date for tlb_gen 3 is the partial flush we're + * processing. + * + * As an example of why this check is needed, suppose that there + * are two concurrent flushes. The first is a full flush that + * changes context.tlb_gen from 1 to 2. The second is a partial + * flush that changes context.tlb_gen from 2 to 3. If they get + * processed on this CPU in reverse order, we'll see + * local_tlb_gen == 1, mm_tlb_gen == 3, and end != TLB_FLUSH_ALL. + * If we were to use __flush_tlb_single() and set local_tlb_gen to + * 3, we'd be break the invariant: we'd update local_tlb_gen above + * 1 without the full flush that's needed for tlb_gen 2. + * + * 2. f->new_tlb_gen == mm_tlb_gen. This is purely an optimiation. + * Partial TLB flushes are not all that much cheaper than full TLB + * flushes, so it seems unlikely that it would be a performance win + * to do a partial flush if that won't bring our TLB fully up to + * date. By doing a full flush instead, we can increase + * local_tlb_gen all the way to mm_tlb_gen and we can probably + * avoid another flush in the very near future. + */ + if (f->end != TLB_FLUSH_ALL && + f->new_tlb_gen == local_tlb_gen + 1 && + f->new_tlb_gen == mm_tlb_gen) { + /* Partial flush */ unsigned long addr; unsigned long nr_pages = (f->end - f->start) >> PAGE_SHIFT; + addr = f->start; while (addr < f->end) { __flush_tlb_single(addr); @@ -180,7 +319,16 @@ static void flush_tlb_func_common(const struct flush_tlb_info *f, if (local) count_vm_tlb_events(NR_TLB_LOCAL_FLUSH_ONE, nr_pages); trace_tlb_flush(reason, nr_pages); + } else { + /* Full flush. */ + local_flush_tlb(); + if (local) + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); + trace_tlb_flush(reason, TLB_FLUSH_ALL); } + + /* Both paths above update our state to mm_tlb_gen. */ + this_cpu_write(cpu_tlbstate.ctxs[loaded_mm_asid].tlb_gen, mm_tlb_gen); } static void flush_tlb_func_local(void *info, enum tlb_flush_reason reason) @@ -214,6 +362,21 @@ void native_flush_tlb_others(const struct cpumask *cpumask, (info->end - info->start) >> PAGE_SHIFT); if (is_uv_system()) { + /* + * This whole special case is confused. UV has a "Broadcast + * Assist Unit", which seems to be a fancy way to send IPIs. + * Back when x86 used an explicit TLB flush IPI, UV was + * optimized to use its own mechanism. These days, x86 uses + * smp_call_function_many(), but UV still uses a manual IPI, + * and that IPI's action is out of date -- it does a manual + * flush instead of calling flush_tlb_func_remote(). This + * means that the percpu tlb_gen variables won't be updated + * and we'll do pointless flushes on future context switches. + * + * Rather than hooking native_flush_tlb_others() here, I think + * that UV should be updated so that smp_call_function_many(), + * etc, are optimal on UV. + */ unsigned int cpu; cpu = smp_processor_id(); @@ -250,8 +413,8 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, cpu = get_cpu(); - /* Synchronize with switch_mm. */ - smp_mb(); + /* This is also a barrier that synchronizes with switch_mm(). */ + info.new_tlb_gen = inc_mm_tlb_gen(mm); /* Should we flush just the requested range? */ if ((end != TLB_FLUSH_ALL) && @@ -273,6 +436,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, if (cpumask_any_but(mm_cpumask(mm), cpu) < nr_cpu_ids) flush_tlb_others(mm_cpumask(mm), &info); + put_cpu(); } @@ -281,8 +445,6 @@ static void do_flush_tlb_all(void *info) { count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED); __flush_tlb_all(); - if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_LAZY) - leave_mm(smp_processor_id()); } void flush_tlb_all(void) @@ -335,6 +497,7 @@ void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch) if (cpumask_any_but(&batch->cpumask, cpu) < nr_cpu_ids) flush_tlb_others(&batch->cpumask, &info); + cpumask_clear(&batch->cpumask); put_cpu(); diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index dbe2132b0ed4..7a5350d08cef 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -674,7 +674,7 @@ int pcibios_add_device(struct pci_dev *dev) pa_data = boot_params.hdr.setup_data; while (pa_data) { - data = ioremap(pa_data, sizeof(*rom)); + data = memremap(pa_data, sizeof(*rom), MEMREMAP_WB); if (!data) return -ENOMEM; @@ -693,7 +693,7 @@ int pcibios_add_device(struct pci_dev *dev) } } pa_data = data->next; - iounmap(data); + memunmap(data); } set_dma_domain_ops(dev); set_dev_domain_options(dev); diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index f084d8718ac4..6217b23e85f6 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -1035,12 +1035,12 @@ void __init efi_enter_virtual_mode(void) /* * Convenience functions to obtain memory types and attributes */ -u32 efi_mem_type(unsigned long phys_addr) +int efi_mem_type(unsigned long phys_addr) { efi_memory_desc_t *md; if (!efi_enabled(EFI_MEMMAP)) - return 0; + return -ENOTSUPP; for_each_efi_memory_desc(md) { if ((md->phys_addr <= phys_addr) && @@ -1048,7 +1048,7 @@ u32 efi_mem_type(unsigned long phys_addr) (md->num_pages << EFI_PAGE_SHIFT)))) return md->type; } - return 0; + return -EINVAL; } static int __init arch_parse_efi_cmdline(char *str) diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 9bf72f5bfedb..12e83888e5b9 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -327,7 +327,7 @@ virt_to_phys_or_null_size(void *va, unsigned long size) int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) { - unsigned long pfn, text; + unsigned long pfn, text, pf; struct page *page; unsigned npages; pgd_t *pgd; @@ -335,7 +335,12 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) if (efi_enabled(EFI_OLD_MEMMAP)) return 0; - efi_scratch.efi_pgt = (pgd_t *)__pa(efi_pgd); + /* + * Since the PGD is encrypted, set the encryption mask so that when + * this value is loaded into cr3 the PGD will be decrypted during + * the pagetable walk. + */ + efi_scratch.efi_pgt = (pgd_t *)__sme_pa(efi_pgd); pgd = efi_pgd; /* @@ -345,7 +350,8 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) * phys_efi_set_virtual_address_map(). */ pfn = pa_memmap >> PAGE_SHIFT; - if (kernel_map_pages_in_pgd(pgd, pfn, pa_memmap, num_pages, _PAGE_NX | _PAGE_RW)) { + pf = _PAGE_NX | _PAGE_RW | _PAGE_ENC; + if (kernel_map_pages_in_pgd(pgd, pfn, pa_memmap, num_pages, pf)) { pr_err("Error ident-mapping new memmap (0x%lx)!\n", pa_memmap); return 1; } @@ -388,7 +394,8 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) text = __pa(_text); pfn = text >> PAGE_SHIFT; - if (kernel_map_pages_in_pgd(pgd, pfn, text, npages, _PAGE_RW)) { + pf = _PAGE_RW | _PAGE_ENC; + if (kernel_map_pages_in_pgd(pgd, pfn, text, npages, pf)) { pr_err("Failed to map kernel text 1:1\n"); return 1; } diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c index 3e4bdb442fbc..f44c0bc95aa2 100644 --- a/arch/x86/platform/uv/tlb_uv.c +++ b/arch/x86/platform/uv/tlb_uv.c @@ -26,7 +26,7 @@ static struct bau_operations ops __ro_after_init; /* timeouts in nanoseconds (indexed by UVH_AGING_PRESCALE_SEL urgency7 30:28) */ -static int timeout_base_ns[] = { +static const int timeout_base_ns[] = { 20, 160, 1280, @@ -1216,7 +1216,7 @@ static struct bau_pq_entry *find_another_by_swack(struct bau_pq_entry *msg, * set a bit in the UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE register. * Such a message must be ignored. */ -void process_uv2_message(struct msg_desc *mdp, struct bau_control *bcp) +static void process_uv2_message(struct msg_desc *mdp, struct bau_control *bcp) { unsigned long mmr_image; unsigned char swack_vec; diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c index cd4be19c36dc..1f71980fc5e0 100644 --- a/arch/x86/realmode/init.c +++ b/arch/x86/realmode/init.c @@ -1,6 +1,7 @@ #include <linux/io.h> #include <linux/slab.h> #include <linux/memblock.h> +#include <linux/mem_encrypt.h> #include <asm/set_memory.h> #include <asm/pgtable.h> @@ -59,6 +60,13 @@ static void __init setup_real_mode(void) base = (unsigned char *)real_mode_header; + /* + * If SME is active, the trampoline area will need to be in + * decrypted memory in order to bring up other processors + * successfully. + */ + set_memory_decrypted((unsigned long)base, size >> PAGE_SHIFT); + memcpy(base, real_mode_blob, size); phys_base = __pa(base); @@ -100,6 +108,10 @@ static void __init setup_real_mode(void) trampoline_cr4_features = &trampoline_header->cr4; *trampoline_cr4_features = mmu_cr4_features; + trampoline_header->flags = 0; + if (sme_active()) + trampoline_header->flags |= TH_FLAGS_SME_ACTIVE; + trampoline_pgd = (u64 *) __va(real_mode_header->trampoline_pgd); trampoline_pgd[0] = trampoline_pgd_entry.pgd; trampoline_pgd[511] = init_top_pgt[511].pgd; diff --git a/arch/x86/realmode/rm/trampoline_64.S b/arch/x86/realmode/rm/trampoline_64.S index dac7b20d2f9d..614fd7064d0a 100644 --- a/arch/x86/realmode/rm/trampoline_64.S +++ b/arch/x86/realmode/rm/trampoline_64.S @@ -30,6 +30,7 @@ #include <asm/msr.h> #include <asm/segment.h> #include <asm/processor-flags.h> +#include <asm/realmode.h> #include "realmode.h" .text @@ -92,6 +93,28 @@ ENTRY(startup_32) movl %edx, %fs movl %edx, %gs + /* + * Check for memory encryption support. This is a safety net in + * case BIOS hasn't done the necessary step of setting the bit in + * the MSR for this AP. If SME is active and we've gotten this far + * then it is safe for us to set the MSR bit and continue. If we + * don't we'll eventually crash trying to execute encrypted + * instructions. + */ + bt $TH_FLAGS_SME_ACTIVE_BIT, pa_tr_flags + jnc .Ldone + movl $MSR_K8_SYSCFG, %ecx + rdmsr + bts $MSR_K8_SYSCFG_MEM_ENCRYPT_BIT, %eax + jc .Ldone + + /* + * Memory encryption is enabled but the SME enable bit for this + * CPU has has not been set. It is safe to set it, so do so. + */ + wrmsr +.Ldone: + movl pa_tr_cr4, %eax movl %eax, %cr4 # Enable PAE mode @@ -147,6 +170,7 @@ GLOBAL(trampoline_header) tr_start: .space 8 GLOBAL(tr_efer) .space 8 GLOBAL(tr_cr4) .space 4 + GLOBAL(tr_flags) .space 4 END(trampoline_header) #include "trampoline_common.S" diff --git a/arch/x86/um/user-offsets.c b/arch/x86/um/user-offsets.c index ae4cd58c0c7a..02250b2633b8 100644 --- a/arch/x86/um/user-offsets.c +++ b/arch/x86/um/user-offsets.c @@ -50,7 +50,7 @@ void foo(void) DEFINE(HOST_GS, GS); DEFINE(HOST_ORIG_AX, ORIG_EAX); #else -#if defined(PTRACE_GETREGSET) && defined(PTRACE_SETREGSET) +#ifdef FP_XSTATE_MAGIC1 DEFINE(HOST_FP_SIZE, sizeof(struct _xstate) / sizeof(unsigned long)); #else DEFINE(HOST_FP_SIZE, sizeof(struct _fpstate) / sizeof(unsigned long)); diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig index 027987638e98..1ecd419811a2 100644 --- a/arch/x86/xen/Kconfig +++ b/arch/x86/xen/Kconfig @@ -17,6 +17,9 @@ config XEN_PV bool "Xen PV guest support" default y depends on XEN + # XEN_PV is not ready to work with 5-level paging. + # Changes to hypervisor are also required. + depends on !X86_5LEVEL select XEN_HAVE_PVMMU select XEN_HAVE_VPMU help @@ -75,4 +78,6 @@ config XEN_DEBUG_FS config XEN_PVH bool "Support for running as a PVH guest" depends on XEN && XEN_PVHVM && ACPI + # Pre-built page tables are not ready to handle 5-level paging. + depends on !X86_5LEVEL def_bool n diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c index 87d791356ea9..de503c225ae1 100644 --- a/arch/x86/xen/enlighten_hvm.c +++ b/arch/x86/xen/enlighten_hvm.c @@ -12,6 +12,7 @@ #include <asm/setup.h> #include <asm/hypervisor.h> #include <asm/e820/api.h> +#include <asm/early_ioremap.h> #include <asm/xen/cpuid.h> #include <asm/xen/hypervisor.h> @@ -21,38 +22,50 @@ #include "mmu.h" #include "smp.h" -void __ref xen_hvm_init_shared_info(void) +static unsigned long shared_info_pfn; + +void xen_hvm_init_shared_info(void) { struct xen_add_to_physmap xatp; - u64 pa; - - if (HYPERVISOR_shared_info == &xen_dummy_shared_info) { - /* - * Search for a free page starting at 4kB physical address. - * Low memory is preferred to avoid an EPT large page split up - * by the mapping. - * Starting below X86_RESERVE_LOW (usually 64kB) is fine as - * the BIOS used for HVM guests is well behaved and won't - * clobber memory other than the first 4kB. - */ - for (pa = PAGE_SIZE; - !e820__mapped_all(pa, pa + PAGE_SIZE, E820_TYPE_RAM) || - memblock_is_reserved(pa); - pa += PAGE_SIZE) - ; - - memblock_reserve(pa, PAGE_SIZE); - HYPERVISOR_shared_info = __va(pa); - } xatp.domid = DOMID_SELF; xatp.idx = 0; xatp.space = XENMAPSPACE_shared_info; - xatp.gpfn = virt_to_pfn(HYPERVISOR_shared_info); + xatp.gpfn = shared_info_pfn; if (HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp)) BUG(); } +static void __init reserve_shared_info(void) +{ + u64 pa; + + /* + * Search for a free page starting at 4kB physical address. + * Low memory is preferred to avoid an EPT large page split up + * by the mapping. + * Starting below X86_RESERVE_LOW (usually 64kB) is fine as + * the BIOS used for HVM guests is well behaved and won't + * clobber memory other than the first 4kB. + */ + for (pa = PAGE_SIZE; + !e820__mapped_all(pa, pa + PAGE_SIZE, E820_TYPE_RAM) || + memblock_is_reserved(pa); + pa += PAGE_SIZE) + ; + + shared_info_pfn = PHYS_PFN(pa); + + memblock_reserve(pa, PAGE_SIZE); + HYPERVISOR_shared_info = early_memremap(pa, PAGE_SIZE); +} + +static void __init xen_hvm_init_mem_mapping(void) +{ + early_memunmap(HYPERVISOR_shared_info, PAGE_SIZE); + HYPERVISOR_shared_info = __va(PFN_PHYS(shared_info_pfn)); +} + static void __init init_hvm_pv_info(void) { int major, minor; @@ -153,6 +166,7 @@ static void __init xen_hvm_guest_init(void) init_hvm_pv_info(); + reserve_shared_info(); xen_hvm_init_shared_info(); /* @@ -218,5 +232,6 @@ const struct hypervisor_x86 x86_hyper_xen_hvm = { .init_platform = xen_hvm_guest_init, .pin_vcpu = xen_pin_vcpu, .x2apic_available = xen_x2apic_para_available, + .init_mem_mapping = xen_hvm_init_mem_mapping, }; EXPORT_SYMBOL(x86_hyper_xen_hvm); diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 811e4ddb3f37..ae2a2e2d6362 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -263,6 +263,13 @@ static void __init xen_init_capabilities(void) setup_clear_cpu_cap(X86_FEATURE_MTRR); setup_clear_cpu_cap(X86_FEATURE_ACC); setup_clear_cpu_cap(X86_FEATURE_X2APIC); + setup_clear_cpu_cap(X86_FEATURE_SME); + + /* + * Xen PV would need some work to support PCID: CR3 handling as well + * as xen_flush_tlb_others() would need updating. + */ + setup_clear_cpu_cap(X86_FEATURE_PCID); if (!xen_initial_domain()) setup_clear_cpu_cap(X86_FEATURE_ACPI); @@ -494,7 +501,7 @@ static void __init xen_load_gdt_boot(const struct desc_ptr *dtr) static inline bool desc_equal(const struct desc_struct *d1, const struct desc_struct *d2) { - return d1->a == d2->a && d1->b == d2->b; + return !memcmp(d1, d2, sizeof(*d1)); } static void load_TLS_descriptor(struct thread_struct *t, @@ -579,59 +586,91 @@ static void xen_write_ldt_entry(struct desc_struct *dt, int entrynum, preempt_enable(); } +#ifdef CONFIG_X86_64 +struct trap_array_entry { + void (*orig)(void); + void (*xen)(void); + bool ist_okay; +}; + +static struct trap_array_entry trap_array[] = { + { debug, xen_xendebug, true }, + { int3, xen_xenint3, true }, + { double_fault, xen_double_fault, true }, +#ifdef CONFIG_X86_MCE + { machine_check, xen_machine_check, true }, +#endif + { nmi, xen_nmi, true }, + { overflow, xen_overflow, false }, +#ifdef CONFIG_IA32_EMULATION + { entry_INT80_compat, xen_entry_INT80_compat, false }, +#endif + { page_fault, xen_page_fault, false }, + { divide_error, xen_divide_error, false }, + { bounds, xen_bounds, false }, + { invalid_op, xen_invalid_op, false }, + { device_not_available, xen_device_not_available, false }, + { coprocessor_segment_overrun, xen_coprocessor_segment_overrun, false }, + { invalid_TSS, xen_invalid_TSS, false }, + { segment_not_present, xen_segment_not_present, false }, + { stack_segment, xen_stack_segment, false }, + { general_protection, xen_general_protection, false }, + { spurious_interrupt_bug, xen_spurious_interrupt_bug, false }, + { coprocessor_error, xen_coprocessor_error, false }, + { alignment_check, xen_alignment_check, false }, + { simd_coprocessor_error, xen_simd_coprocessor_error, false }, +}; + +static bool get_trap_addr(void **addr, unsigned int ist) +{ + unsigned int nr; + bool ist_okay = false; + + /* + * Replace trap handler addresses by Xen specific ones. + * Check for known traps using IST and whitelist them. + * The debugger ones are the only ones we care about. + * Xen will handle faults like double_fault, * so we should never see + * them. Warn if there's an unexpected IST-using fault handler. + */ + for (nr = 0; nr < ARRAY_SIZE(trap_array); nr++) { + struct trap_array_entry *entry = trap_array + nr; + + if (*addr == entry->orig) { + *addr = entry->xen; + ist_okay = entry->ist_okay; + break; + } + } + + if (WARN_ON(ist != 0 && !ist_okay)) + return false; + + return true; +} +#endif + static int cvt_gate_to_trap(int vector, const gate_desc *val, struct trap_info *info) { unsigned long addr; - if (val->type != GATE_TRAP && val->type != GATE_INTERRUPT) + if (val->bits.type != GATE_TRAP && val->bits.type != GATE_INTERRUPT) return 0; info->vector = vector; - addr = gate_offset(*val); + addr = gate_offset(val); #ifdef CONFIG_X86_64 - /* - * Look for known traps using IST, and substitute them - * appropriately. The debugger ones are the only ones we care - * about. Xen will handle faults like double_fault, - * so we should never see them. Warn if - * there's an unexpected IST-using fault handler. - */ - if (addr == (unsigned long)debug) - addr = (unsigned long)xen_debug; - else if (addr == (unsigned long)int3) - addr = (unsigned long)xen_int3; - else if (addr == (unsigned long)stack_segment) - addr = (unsigned long)xen_stack_segment; - else if (addr == (unsigned long)double_fault) { - /* Don't need to handle these */ + if (!get_trap_addr((void **)&addr, val->bits.ist)) return 0; -#ifdef CONFIG_X86_MCE - } else if (addr == (unsigned long)machine_check) { - /* - * when xen hypervisor inject vMCE to guest, - * use native mce handler to handle it - */ - ; -#endif - } else if (addr == (unsigned long)nmi) - /* - * Use the native version as well. - */ - ; - else { - /* Some other trap using IST? */ - if (WARN_ON(val->ist != 0)) - return 0; - } #endif /* CONFIG_X86_64 */ info->address = addr; - info->cs = gate_segment(*val); - info->flags = val->dpl; + info->cs = gate_segment(val); + info->flags = val->bits.dpl; /* interrupt gates clear IF */ - if (val->type == GATE_INTERRUPT) + if (val->bits.type == GATE_INTERRUPT) info->flags |= 1 << 2; return 1; @@ -981,59 +1020,6 @@ void __ref xen_setup_vcpu_info_placement(void) } } -static unsigned xen_patch(u8 type, u16 clobbers, void *insnbuf, - unsigned long addr, unsigned len) -{ - char *start, *end, *reloc; - unsigned ret; - - start = end = reloc = NULL; - -#define SITE(op, x) \ - case PARAVIRT_PATCH(op.x): \ - if (xen_have_vcpu_info_placement) { \ - start = (char *)xen_##x##_direct; \ - end = xen_##x##_direct_end; \ - reloc = xen_##x##_direct_reloc; \ - } \ - goto patch_site - - switch (type) { - SITE(pv_irq_ops, irq_enable); - SITE(pv_irq_ops, irq_disable); - SITE(pv_irq_ops, save_fl); - SITE(pv_irq_ops, restore_fl); -#undef SITE - - patch_site: - if (start == NULL || (end-start) > len) - goto default_patch; - - ret = paravirt_patch_insns(insnbuf, len, start, end); - - /* Note: because reloc is assigned from something that - appears to be an array, gcc assumes it's non-null, - but doesn't know its relationship with start and - end. */ - if (reloc > start && reloc < end) { - int reloc_off = reloc - start; - long *relocp = (long *)(insnbuf + reloc_off); - long delta = start - (char *)addr; - - *relocp += delta; - } - break; - - default_patch: - default: - ret = paravirt_patch_default(type, clobbers, insnbuf, - addr, len); - break; - } - - return ret; -} - static const struct pv_info xen_info __initconst = { .shared_kernel_pmd = 0, @@ -1043,10 +1029,6 @@ static const struct pv_info xen_info __initconst = { .name = "Xen", }; -static const struct pv_init_ops xen_init_ops __initconst = { - .patch = xen_patch, -}; - static const struct pv_cpu_ops xen_cpu_ops __initconst = { .cpuid = xen_cpuid, @@ -1244,7 +1226,7 @@ asmlinkage __visible void __init xen_start_kernel(void) /* Install Xen paravirt ops */ pv_info = xen_info; - pv_init_ops = xen_init_ops; + pv_init_ops.patch = paravirt_patch_default; pv_cpu_ops = xen_cpu_ops; x86_platform.get_nmi_reason = xen_get_nmi_reason; diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c index 33e92955e09d..d4eff5676cfa 100644 --- a/arch/x86/xen/irq.c +++ b/arch/x86/xen/irq.c @@ -123,9 +123,6 @@ static const struct pv_irq_ops xen_irq_ops __initconst = { .safe_halt = xen_safe_halt, .halt = xen_halt, -#ifdef CONFIG_X86_64 - .adjust_exception_frame = xen_adjust_exception_frame, -#endif }; void __init xen_init_irq_ops(void) diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index cab28cf2cffb..e437714750f8 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -1005,14 +1005,12 @@ static void xen_drop_mm_ref(struct mm_struct *mm) /* Get the "official" set of cpus referring to our pagetable. */ if (!alloc_cpumask_var(&mask, GFP_ATOMIC)) { for_each_online_cpu(cpu) { - if (!cpumask_test_cpu(cpu, mm_cpumask(mm)) - && per_cpu(xen_current_cr3, cpu) != __pa(mm->pgd)) + if (per_cpu(xen_current_cr3, cpu) != __pa(mm->pgd)) continue; smp_call_function_single(cpu, drop_mm_ref_this_cpu, mm, 1); } return; } - cpumask_copy(mask, mm_cpumask(mm)); /* * It's possible that a vcpu may have a stale reference to our @@ -1021,6 +1019,7 @@ static void xen_drop_mm_ref(struct mm_struct *mm) * look at its actual current cr3 value, and force it to flush * if needed. */ + cpumask_clear(mask); for_each_online_cpu(cpu) { if (per_cpu(xen_current_cr3, cpu) == __pa(mm->pgd)) cpumask_set_cpu(cpu, mask); diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S index eff224df813f..dcd31fa39b5d 100644 --- a/arch/x86/xen/xen-asm.S +++ b/arch/x86/xen/xen-asm.S @@ -1,14 +1,8 @@ /* - * Asm versions of Xen pv-ops, suitable for either direct use or - * inlining. The inline versions are the same as the direct-use - * versions, with the pre- and post-amble chopped off. - * - * This code is encoded for size rather than absolute efficiency, with - * a view to being able to inline as much as possible. + * Asm versions of Xen pv-ops, suitable for direct use. * * We only bother with direct forms (ie, vcpu in percpu data) of the - * operations here; the indirect forms are better handled in C, since - * they're generally too large to inline anyway. + * operations here; the indirect forms are better handled in C. */ #include <asm/asm-offsets.h> @@ -16,7 +10,7 @@ #include <asm/processor-flags.h> #include <asm/frame.h> -#include "xen-asm.h" +#include <linux/linkage.h> /* * Enable events. This clears the event mask and tests the pending @@ -38,13 +32,11 @@ ENTRY(xen_irq_enable_direct) testb $0xff, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_pending jz 1f -2: call check_events + call check_events 1: -ENDPATCH(xen_irq_enable_direct) FRAME_END ret ENDPROC(xen_irq_enable_direct) - RELOC(xen_irq_enable_direct, 2b+1) /* @@ -53,10 +45,8 @@ ENDPATCH(xen_irq_enable_direct) */ ENTRY(xen_irq_disable_direct) movb $1, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask -ENDPATCH(xen_irq_disable_direct) ret - ENDPROC(xen_irq_disable_direct) - RELOC(xen_irq_disable_direct, 0) +ENDPROC(xen_irq_disable_direct) /* * (xen_)save_fl is used to get the current interrupt enable status. @@ -71,10 +61,8 @@ ENTRY(xen_save_fl_direct) testb $0xff, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask setz %ah addb %ah, %ah -ENDPATCH(xen_save_fl_direct) ret ENDPROC(xen_save_fl_direct) - RELOC(xen_save_fl_direct, 0) /* @@ -101,13 +89,11 @@ ENTRY(xen_restore_fl_direct) /* check for unmasked and pending */ cmpw $0x0001, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_pending jnz 1f -2: call check_events + call check_events 1: -ENDPATCH(xen_restore_fl_direct) FRAME_END ret ENDPROC(xen_restore_fl_direct) - RELOC(xen_restore_fl_direct, 2b+1) /* diff --git a/arch/x86/xen/xen-asm.h b/arch/x86/xen/xen-asm.h deleted file mode 100644 index 465276467a47..000000000000 --- a/arch/x86/xen/xen-asm.h +++ /dev/null @@ -1,12 +0,0 @@ -#ifndef _XEN_XEN_ASM_H -#define _XEN_XEN_ASM_H - -#include <linux/linkage.h> - -#define RELOC(x, v) .globl x##_reloc; x##_reloc=v -#define ENDPATCH(x) .globl x##_end; x##_end=. - -/* Pseudo-flag used for virtual NMI, which we don't implement yet */ -#define XEN_EFLAGS_NMI 0x80000000 - -#endif diff --git a/arch/x86/xen/xen-asm_32.S b/arch/x86/xen/xen-asm_32.S index feb6d40a0860..1200e262a116 100644 --- a/arch/x86/xen/xen-asm_32.S +++ b/arch/x86/xen/xen-asm_32.S @@ -1,14 +1,8 @@ /* - * Asm versions of Xen pv-ops, suitable for either direct use or - * inlining. The inline versions are the same as the direct-use - * versions, with the pre- and post-amble chopped off. - * - * This code is encoded for size rather than absolute efficiency, with - * a view to being able to inline as much as possible. + * Asm versions of Xen pv-ops, suitable for direct use. * * We only bother with direct forms (ie, vcpu in pda) of the - * operations here; the indirect forms are better handled in C, since - * they're generally too large to inline anyway. + * operations here; the indirect forms are better handled in C. */ #include <asm/thread_info.h> @@ -18,21 +12,10 @@ #include <xen/interface/xen.h> -#include "xen-asm.h" +#include <linux/linkage.h> -/* - * Force an event check by making a hypercall, but preserve regs - * before making the call. - */ -check_events: - push %eax - push %ecx - push %edx - call xen_force_evtchn_callback - pop %edx - pop %ecx - pop %eax - ret +/* Pseudo-flag used for virtual NMI, which we don't implement yet */ +#define XEN_EFLAGS_NMI 0x80000000 /* * This is run where a normal iret would be run, with the same stack setup: diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S index c3df43141e70..dae2cc33afb5 100644 --- a/arch/x86/xen/xen-asm_64.S +++ b/arch/x86/xen/xen-asm_64.S @@ -1,14 +1,8 @@ /* - * Asm versions of Xen pv-ops, suitable for either direct use or - * inlining. The inline versions are the same as the direct-use - * versions, with the pre- and post-amble chopped off. - * - * This code is encoded for size rather than absolute efficiency, with - * a view to being able to inline as much as possible. + * Asm versions of Xen pv-ops, suitable for direct use. * * We only bother with direct forms (ie, vcpu in pda) of the - * operations here; the indirect forms are better handled in C, since - * they're generally too large to inline anyway. + * operations here; the indirect forms are better handled in C. */ #include <asm/errno.h> @@ -20,13 +14,44 @@ #include <xen/interface/xen.h> -#include "xen-asm.h" +#include <linux/linkage.h> + +.macro xen_pv_trap name +ENTRY(xen_\name) + pop %rcx + pop %r11 + jmp \name +END(xen_\name) +.endm -ENTRY(xen_adjust_exception_frame) - mov 8+0(%rsp), %rcx - mov 8+8(%rsp), %r11 - ret $16 -ENDPROC(xen_adjust_exception_frame) +xen_pv_trap divide_error +xen_pv_trap debug +xen_pv_trap xendebug +xen_pv_trap int3 +xen_pv_trap xenint3 +xen_pv_trap nmi +xen_pv_trap overflow +xen_pv_trap bounds +xen_pv_trap invalid_op +xen_pv_trap device_not_available +xen_pv_trap double_fault +xen_pv_trap coprocessor_segment_overrun +xen_pv_trap invalid_TSS +xen_pv_trap segment_not_present +xen_pv_trap stack_segment +xen_pv_trap general_protection +xen_pv_trap page_fault +xen_pv_trap spurious_interrupt_bug +xen_pv_trap coprocessor_error +xen_pv_trap alignment_check +#ifdef CONFIG_X86_MCE +xen_pv_trap machine_check +#endif /* CONFIG_X86_MCE */ +xen_pv_trap simd_coprocessor_error +#ifdef CONFIG_IA32_EMULATION +xen_pv_trap entry_INT80_compat +#endif +xen_pv_trap hypervisor_callback hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32 /* @@ -46,9 +71,7 @@ hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32 */ ENTRY(xen_iret) pushq $0 -1: jmp hypercall_iret -ENDPATCH(xen_iret) -RELOC(xen_iret, 1b+1) + jmp hypercall_iret ENTRY(xen_sysret64) /* @@ -65,9 +88,7 @@ ENTRY(xen_sysret64) pushq %rcx pushq $VGCF_in_syscall -1: jmp hypercall_iret -ENDPATCH(xen_sysret64) -RELOC(xen_sysret64, 1b+1) + jmp hypercall_iret /* * Xen handles syscall callbacks much like ordinary exceptions, which @@ -82,34 +103,47 @@ RELOC(xen_sysret64, 1b+1) * rip * r11 * rsp->rcx - * - * In all the entrypoints, we undo all that to make it look like a - * CPU-generated syscall/sysenter and jump to the normal entrypoint. */ -.macro undo_xen_syscall - mov 0*8(%rsp), %rcx - mov 1*8(%rsp), %r11 - mov 5*8(%rsp), %rsp -.endm - /* Normal 64-bit system call target */ ENTRY(xen_syscall_target) - undo_xen_syscall - jmp entry_SYSCALL_64_after_swapgs + popq %rcx + popq %r11 + + /* + * Neither Xen nor the kernel really knows what the old SS and + * CS were. The kernel expects __USER_DS and __USER_CS, so + * report those values even though Xen will guess its own values. + */ + movq $__USER_DS, 4*8(%rsp) + movq $__USER_CS, 1*8(%rsp) + + jmp entry_SYSCALL_64_after_hwframe ENDPROC(xen_syscall_target) #ifdef CONFIG_IA32_EMULATION /* 32-bit compat syscall target */ ENTRY(xen_syscall32_target) - undo_xen_syscall - jmp entry_SYSCALL_compat + popq %rcx + popq %r11 + + /* + * Neither Xen nor the kernel really knows what the old SS and + * CS were. The kernel expects __USER32_DS and __USER32_CS, so + * report those values even though Xen will guess its own values. + */ + movq $__USER32_DS, 4*8(%rsp) + movq $__USER32_CS, 1*8(%rsp) + + jmp entry_SYSCALL_compat_after_hwframe ENDPROC(xen_syscall32_target) /* 32-bit compat sysenter target */ ENTRY(xen_sysenter_target) - undo_xen_syscall + mov 0*8(%rsp), %rcx + mov 1*8(%rsp), %r11 + mov 5*8(%rsp), %rsp jmp entry_SYSENTER_compat ENDPROC(xen_sysenter_target) diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index 72a8e6adebe6..a7525e95d53f 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -58,7 +58,7 @@ ENTRY(hypercall_page) #else ELFNOTE(Xen, XEN_ELFNOTE_VIRT_BASE, _ASM_PTR __START_KERNEL_map) /* Map the p2m table to a 512GB-aligned user address. */ - ELFNOTE(Xen, XEN_ELFNOTE_INIT_P2M, .quad PGDIR_SIZE) + ELFNOTE(Xen, XEN_ELFNOTE_INIT_P2M, .quad (PUD_SIZE * PTRS_PER_PUD)) #endif #ifdef CONFIG_XEN_PV ELFNOTE(Xen, XEN_ELFNOTE_ENTRY, _ASM_PTR startup_xen) diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 0d5004477db6..c8a6d224f7ed 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -129,23 +129,15 @@ static inline void __init xen_efi_init(void) } #endif -/* Declare an asm function, along with symbols needed to make it - inlineable */ -#define DECL_ASM(ret, name, ...) \ - __visible ret name(__VA_ARGS__); \ - extern char name##_end[] __visible; \ - extern char name##_reloc[] __visible - -DECL_ASM(void, xen_irq_enable_direct, void); -DECL_ASM(void, xen_irq_disable_direct, void); -DECL_ASM(unsigned long, xen_save_fl_direct, void); -DECL_ASM(void, xen_restore_fl_direct, unsigned long); +__visible void xen_irq_enable_direct(void); +__visible void xen_irq_disable_direct(void); +__visible unsigned long xen_save_fl_direct(void); +__visible void xen_restore_fl_direct(unsigned long); /* These are not functions, and cannot be called normally */ __visible void xen_iret(void); __visible void xen_sysret32(void); __visible void xen_sysret64(void); -__visible void xen_adjust_exception_frame(void); extern int xen_panic_handler_init(void); |