diff options
Diffstat (limited to 'arch/x86')
224 files changed, 5763 insertions, 3981 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index cc98d5a294ee..8d4f87e5bba3 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -98,7 +98,6 @@ config X86 select HAVE_ACPI_APEI_NMI if ACPI select HAVE_ALIGNED_STRUCT_PAGE if SLUB select HAVE_ARCH_AUDITSYSCALL - select HAVE_ARCH_HARDENED_USERCOPY select HAVE_ARCH_HUGE_VMAP if X86_64 || X86_PAE select HAVE_ARCH_JUMP_LABEL select HAVE_ARCH_KASAN if X86_64 && SPARSEMEM_VMEMMAP @@ -106,6 +105,7 @@ config X86 select HAVE_ARCH_KMEMCHECK select HAVE_ARCH_MMAP_RND_BITS if MMU select HAVE_ARCH_MMAP_RND_COMPAT_BITS if MMU && COMPAT + select HAVE_ARCH_COMPAT_MMAP_BASES if MMU && COMPAT select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_TRACEHOOK select HAVE_ARCH_TRANSPARENT_HUGEPAGE @@ -127,7 +127,7 @@ config X86 select HAVE_EBPF_JIT if X86_64 select HAVE_EFFICIENT_UNALIGNED_ACCESS select HAVE_EXIT_THREAD - select HAVE_FENTRY if X86_64 + select HAVE_FENTRY if X86_64 || DYNAMIC_FTRACE select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER @@ -290,6 +290,7 @@ config ARCH_SUPPORTS_DEBUG_PAGEALLOC config KASAN_SHADOW_OFFSET hex depends on KASAN + default 0xdff8000000000000 if X86_5LEVEL default 0xdffffc0000000000 config HAVE_INTEL_TXT @@ -1043,6 +1044,14 @@ config X86_MCE The action the kernel takes depends on the severity of the problem, ranging from warning messages to halting the machine. +config X86_MCELOG_LEGACY + bool "Support for deprecated /dev/mcelog character device" + depends on X86_MCE + ---help--- + Enable support for /dev/mcelog which is needed by the old mcelog + userspace logging daemon. Consider switching to the new generation + rasdaemon solution. + config X86_MCE_INTEL def_bool y prompt "Intel MCE features" @@ -1072,7 +1081,7 @@ config X86_MCE_THRESHOLD def_bool y config X86_MCE_INJECT - depends on X86_MCE && X86_LOCAL_APIC + depends on X86_MCE && X86_LOCAL_APIC && X86_MCELOG_LEGACY tristate "Machine check injector support" ---help--- Provide support for injecting machine checks for testing purposes. @@ -1966,7 +1975,7 @@ config RELOCATABLE config RANDOMIZE_BASE bool "Randomize the address of the kernel image (KASLR)" depends on RELOCATABLE - default n + default y ---help--- In support of Kernel Address Space Layout Randomization (KASLR), this randomizes the physical address at which the kernel image @@ -1996,7 +2005,7 @@ config RANDOMIZE_BASE theoretically possible, but the implementations are further limited due to memory layouts. - If unsure, say N. + If unsure, say Y. # Relocation on x86 needs some additional build support config X86_NEED_RELOCS @@ -2045,7 +2054,7 @@ config RANDOMIZE_MEMORY configuration have in average 30,000 different possible virtual addresses for each memory section. - If unsure, say N. + If unsure, say Y. config RANDOMIZE_MEMORY_PHYSICAL_PADDING hex "Physical memory mapping padding" if EXPERT diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index 63c1d13aaf9f..fcb7604172ce 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -5,6 +5,9 @@ config TRACE_IRQFLAGS_SUPPORT source "lib/Kconfig.debug" +config EARLY_PRINTK_USB + bool + config X86_VERBOSE_BOOTUP bool "Enable verbose x86 bootup info messages" default y @@ -23,19 +26,20 @@ config EARLY_PRINTK This is useful for kernel debugging when your machine crashes very early before the console code is initialized. For normal operation it is not recommended because it looks ugly and doesn't cooperate - with klogd/syslogd or the X server. You should normally N here, + with klogd/syslogd or the X server. You should normally say N here, unless you want to debug such a crash. config EARLY_PRINTK_DBGP bool "Early printk via EHCI debug port" depends on EARLY_PRINTK && PCI + select EARLY_PRINTK_USB ---help--- Write kernel log output directly into the EHCI debug port. This is useful for kernel debugging when your machine crashes very early before the console code is initialized. For normal operation it is not recommended because it looks ugly and doesn't cooperate - with klogd/syslogd or the X server. You should normally N here, + with klogd/syslogd or the X server. You should normally say N here, unless you want to debug such a crash. You need usb debug device. config EARLY_PRINTK_EFI @@ -48,6 +52,25 @@ config EARLY_PRINTK_EFI This is useful for kernel debugging when your machine crashes very early before the console code is initialized. +config EARLY_PRINTK_USB_XDBC + bool "Early printk via the xHCI debug port" + depends on EARLY_PRINTK && PCI + select EARLY_PRINTK_USB + ---help--- + Write kernel log output directly into the xHCI debug port. + + One use for this feature is kernel debugging, for example when your + machine crashes very early before the regular console code is + initialized. Other uses include simpler, lockless logging instead of + a full-blown printk console driver + klogd. + + For normal production environments this is normally not recommended, + because it doesn't feed events into klogd/syslogd and doesn't try to + print anything on the screen. + + You should normally say N here, unless you want to debug early + crashes or need a very simple printk logging facility. + config X86_PTDUMP_CORE def_bool n diff --git a/arch/x86/Makefile b/arch/x86/Makefile index a94a4d10f2df..4430dd489620 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -88,10 +88,10 @@ else KBUILD_CFLAGS += -m64 # Align jump targets to 1 byte, not the default 16 bytes: - KBUILD_CFLAGS += -falign-jumps=1 + KBUILD_CFLAGS += $(call cc-option,-falign-jumps=1) # Pack loops tightly as well: - KBUILD_CFLAGS += -falign-loops=1 + KBUILD_CFLAGS += $(call cc-option,-falign-loops=1) # Don't autogenerate traditional x87 instructions KBUILD_CFLAGS += $(call cc-option,-mno-80387) @@ -154,6 +154,14 @@ ifdef CONFIG_FUNCTION_GRAPH_TRACER else ifeq ($(call cc-option-yn, -mfentry), n) ACCUMULATE_OUTGOING_ARGS := 1 + + # GCC ignores '-maccumulate-outgoing-args' when used with '-Os'. + # If '-Os' is enabled, disable it and print a warning. + ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE + undefine CONFIG_CC_OPTIMIZE_FOR_SIZE + $(warning Disabling CONFIG_CC_OPTIMIZE_FOR_SIZE. Your compiler does not have -mfentry so you cannot optimize for size with CONFIG_FUNCTION_GRAPH_TRACER.) + endif + endif endif endif diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h index 9b42b6d1e902..ef5a9cc66fb8 100644 --- a/arch/x86/boot/boot.h +++ b/arch/x86/boot/boot.h @@ -16,7 +16,7 @@ #ifndef BOOT_BOOT_H #define BOOT_BOOT_H -#define STACK_SIZE 512 /* Minimum number of bytes for stack */ +#define STACK_SIZE 1024 /* Minimum number of bytes for stack */ #ifndef __ASSEMBLY__ diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index 801c7a158e55..cbf4b87f55b9 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -9,7 +9,9 @@ #include <linux/efi.h> #include <linux/pci.h> + #include <asm/efi.h> +#include <asm/e820/types.h> #include <asm/setup.h> #include <asm/desc.h> @@ -729,7 +731,7 @@ static void add_e820ext(struct boot_params *params, unsigned long size; e820ext->type = SETUP_E820_EXT; - e820ext->len = nr_entries * sizeof(struct e820entry); + e820ext->len = nr_entries * sizeof(struct boot_e820_entry); e820ext->next = 0; data = (struct setup_data *)(unsigned long)params->hdr.setup_data; @@ -746,9 +748,9 @@ static void add_e820ext(struct boot_params *params, static efi_status_t setup_e820(struct boot_params *params, struct setup_data *e820ext, u32 e820ext_size) { - struct e820entry *e820_map = ¶ms->e820_map[0]; + struct boot_e820_entry *entry = params->e820_table; struct efi_info *efi = ¶ms->efi_info; - struct e820entry *prev = NULL; + struct boot_e820_entry *prev = NULL; u32 nr_entries; u32 nr_desc; int i; @@ -773,15 +775,15 @@ static efi_status_t setup_e820(struct boot_params *params, case EFI_MEMORY_MAPPED_IO: case EFI_MEMORY_MAPPED_IO_PORT_SPACE: case EFI_PAL_CODE: - e820_type = E820_RESERVED; + e820_type = E820_TYPE_RESERVED; break; case EFI_UNUSABLE_MEMORY: - e820_type = E820_UNUSABLE; + e820_type = E820_TYPE_UNUSABLE; break; case EFI_ACPI_RECLAIM_MEMORY: - e820_type = E820_ACPI; + e820_type = E820_TYPE_ACPI; break; case EFI_LOADER_CODE: @@ -789,15 +791,15 @@ static efi_status_t setup_e820(struct boot_params *params, case EFI_BOOT_SERVICES_CODE: case EFI_BOOT_SERVICES_DATA: case EFI_CONVENTIONAL_MEMORY: - e820_type = E820_RAM; + e820_type = E820_TYPE_RAM; break; case EFI_ACPI_MEMORY_NVS: - e820_type = E820_NVS; + e820_type = E820_TYPE_NVS; break; case EFI_PERSISTENT_MEMORY: - e820_type = E820_PMEM; + e820_type = E820_TYPE_PMEM; break; default: @@ -811,26 +813,26 @@ static efi_status_t setup_e820(struct boot_params *params, continue; } - if (nr_entries == ARRAY_SIZE(params->e820_map)) { - u32 need = (nr_desc - i) * sizeof(struct e820entry) + + if (nr_entries == ARRAY_SIZE(params->e820_table)) { + u32 need = (nr_desc - i) * sizeof(struct e820_entry) + sizeof(struct setup_data); if (!e820ext || e820ext_size < need) return EFI_BUFFER_TOO_SMALL; /* boot_params map full, switch to e820 extended */ - e820_map = (struct e820entry *)e820ext->data; + entry = (struct boot_e820_entry *)e820ext->data; } - e820_map->addr = d->phys_addr; - e820_map->size = d->num_pages << PAGE_SHIFT; - e820_map->type = e820_type; - prev = e820_map++; + entry->addr = d->phys_addr; + entry->size = d->num_pages << PAGE_SHIFT; + entry->type = e820_type; + prev = entry++; nr_entries++; } - if (nr_entries > ARRAY_SIZE(params->e820_map)) { - u32 nr_e820ext = nr_entries - ARRAY_SIZE(params->e820_map); + if (nr_entries > ARRAY_SIZE(params->e820_table)) { + u32 nr_e820ext = nr_entries - ARRAY_SIZE(params->e820_table); add_e820ext(params, e820ext, nr_e820ext); nr_entries -= nr_e820ext; @@ -848,7 +850,7 @@ static efi_status_t alloc_e820ext(u32 nr_desc, struct setup_data **e820ext, unsigned long size; size = sizeof(struct setup_data) + - sizeof(struct e820entry) * nr_desc; + sizeof(struct e820_entry) * nr_desc; if (*e820ext) { efi_call_early(free_pool, *e820ext); @@ -884,9 +886,9 @@ static efi_status_t exit_boot_func(efi_system_table_t *sys_table_arg, if (first) { nr_desc = *map->buff_size / *map->desc_size; - if (nr_desc > ARRAY_SIZE(p->boot_params->e820_map)) { + if (nr_desc > ARRAY_SIZE(p->boot_params->e820_table)) { u32 nr_e820ext = nr_desc - - ARRAY_SIZE(p->boot_params->e820_map); + ARRAY_SIZE(p->boot_params->e820_table); status = alloc_e820ext(nr_e820ext, &p->e820ext, &p->e820ext_size); diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index 8b7c9e75edcb..54c24f0a43d3 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -426,7 +426,7 @@ static unsigned long slots_fetch_random(void) return 0; } -static void process_e820_entry(struct e820entry *entry, +static void process_e820_entry(struct boot_e820_entry *entry, unsigned long minimum, unsigned long image_size) { @@ -435,7 +435,7 @@ static void process_e820_entry(struct e820entry *entry, unsigned long start_orig; /* Skip non-RAM entries. */ - if (entry->type != E820_RAM) + if (entry->type != E820_TYPE_RAM) return; /* On 32-bit, ignore entries entirely above our maximum. */ @@ -518,7 +518,7 @@ static unsigned long find_random_phys_addr(unsigned long minimum, /* Verify potential e820 positions, appending to slots list. */ for (i = 0; i < boot_params->e820_entries; i++) { - process_e820_entry(&boot_params->e820_map[i], minimum, + process_e820_entry(&boot_params->e820_table[i], minimum, image_size); if (slot_area_index == MAX_SLOT_AREA) { debug_putstr("Aborted e820 scan (slot_areas full)!\n"); @@ -597,10 +597,17 @@ void choose_random_location(unsigned long input, add_identity_map(random_addr, output_size); *output = random_addr; } + + /* + * This loads the identity mapping page table. + * This should only be done if a new physical address + * is found for the kernel, otherwise we should keep + * the old page table to make it be like the "nokaslr" + * case. + */ + finalize_identity_maps(); } - /* This actually loads the identity pagetable on x86_64. */ - finalize_identity_maps(); /* Pick random virtual address starting from LOAD_PHYSICAL_ADDR. */ if (IS_ENABLED(CONFIG_X86_64)) diff --git a/arch/x86/boot/cpucheck.c b/arch/x86/boot/cpucheck.c index 4ad7d70e8739..8f0c4c9fc904 100644 --- a/arch/x86/boot/cpucheck.c +++ b/arch/x86/boot/cpucheck.c @@ -44,6 +44,15 @@ static const u32 req_flags[NCAPINTS] = 0, /* REQUIRED_MASK5 not implemented in this file */ REQUIRED_MASK6, 0, /* REQUIRED_MASK7 not implemented in this file */ + 0, /* REQUIRED_MASK8 not implemented in this file */ + 0, /* REQUIRED_MASK9 not implemented in this file */ + 0, /* REQUIRED_MASK10 not implemented in this file */ + 0, /* REQUIRED_MASK11 not implemented in this file */ + 0, /* REQUIRED_MASK12 not implemented in this file */ + 0, /* REQUIRED_MASK13 not implemented in this file */ + 0, /* REQUIRED_MASK14 not implemented in this file */ + 0, /* REQUIRED_MASK15 not implemented in this file */ + REQUIRED_MASK16, }; #define A32(a, b, c, d) (((d) << 24)+((c) << 16)+((b) << 8)+(a)) diff --git a/arch/x86/boot/cpuflags.c b/arch/x86/boot/cpuflags.c index 6687ab953257..9e77c23c2422 100644 --- a/arch/x86/boot/cpuflags.c +++ b/arch/x86/boot/cpuflags.c @@ -70,16 +70,19 @@ int has_eflag(unsigned long mask) # define EBX_REG "=b" #endif -static inline void cpuid(u32 id, u32 *a, u32 *b, u32 *c, u32 *d) +static inline void cpuid_count(u32 id, u32 count, + u32 *a, u32 *b, u32 *c, u32 *d) { asm volatile(".ifnc %%ebx,%3 ; movl %%ebx,%3 ; .endif \n\t" "cpuid \n\t" ".ifnc %%ebx,%3 ; xchgl %%ebx,%3 ; .endif \n\t" : "=a" (*a), "=c" (*c), "=d" (*d), EBX_REG (*b) - : "a" (id) + : "a" (id), "c" (count) ); } +#define cpuid(id, a, b, c, d) cpuid_count(id, 0, a, b, c, d) + void get_cpuflags(void) { u32 max_intel_level, max_amd_level; @@ -108,6 +111,11 @@ void get_cpuflags(void) cpu.model += ((tfms >> 16) & 0xf) << 4; } + if (max_intel_level >= 0x00000007) { + cpuid_count(0x00000007, 0, &ignored, &ignored, + &cpu.flags[16], &ignored); + } + cpuid(0x80000000, &max_amd_level, &ignored, &ignored, &ignored); diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index 3dd5be33aaa7..2ed8f0c25def 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -18,7 +18,6 @@ #include <asm/segment.h> #include <generated/utsrelease.h> #include <asm/boot.h> -#include <asm/e820.h> #include <asm/page_types.h> #include <asm/setup.h> #include <asm/bootparam.h> diff --git a/arch/x86/boot/memory.c b/arch/x86/boot/memory.c index db75d07c3645..d9c28c87e477 100644 --- a/arch/x86/boot/memory.c +++ b/arch/x86/boot/memory.c @@ -21,8 +21,8 @@ static int detect_memory_e820(void) { int count = 0; struct biosregs ireg, oreg; - struct e820entry *desc = boot_params.e820_map; - static struct e820entry buf; /* static so it is zeroed */ + struct boot_e820_entry *desc = boot_params.e820_table; + static struct boot_e820_entry buf; /* static so it is zeroed */ initregs(&ireg); ireg.ax = 0xe820; @@ -66,7 +66,7 @@ static int detect_memory_e820(void) *desc++ = buf; count++; - } while (ireg.ebx && count < ARRAY_SIZE(boot_params.e820_map)); + } while (ireg.ebx && count < ARRAY_SIZE(boot_params.e820_table)); return boot_params.e820_entries = count; } diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index 5fa6ee2c2dde..6cf79e1a6830 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -57,6 +57,8 @@ CONFIG_EFI=y CONFIG_HZ_1000=y CONFIG_KEXEC=y CONFIG_CRASH_DUMP=y +CONFIG_RANDOMIZE_BASE=y +CONFIG_RANDOMIZE_MEMORY=y # CONFIG_COMPAT_VDSO is not set CONFIG_HIBERNATION=y CONFIG_PM_DEBUG=y diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index 6205d3b81e6d..de45f57b410d 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -55,6 +55,8 @@ CONFIG_EFI=y CONFIG_HZ_1000=y CONFIG_KEXEC=y CONFIG_CRASH_DUMP=y +CONFIG_RANDOMIZE_BASE=y +CONFIG_RANDOMIZE_MEMORY=y # CONFIG_COMPAT_VDSO is not set CONFIG_HIBERNATION=y CONFIG_PM_DEBUG=y diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 57f7ec35216e..50bc26949e9e 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -35,16 +35,13 @@ #include <asm/errno.h> #include <asm/segment.h> #include <asm/smp.h> -#include <asm/page_types.h> #include <asm/percpu.h> #include <asm/processor-flags.h> -#include <asm/ftrace.h> #include <asm/irq_vectors.h> #include <asm/cpufeatures.h> #include <asm/alternative-asm.h> #include <asm/asm.h> #include <asm/smap.h> -#include <asm/export.h> #include <asm/frame.h> .section .entry.text, "ax" @@ -585,7 +582,7 @@ ENTRY(iret_exc ) * will soon execute iret and the tracer was already set to * the irqstate after the IRET: */ - DISABLE_INTERRUPTS(CLBR_EAX) + DISABLE_INTERRUPTS(CLBR_ANY) lss (%esp), %esp /* switch to espfix segment */ jmp .Lrestore_nocheck #endif @@ -886,172 +883,6 @@ BUILD_INTERRUPT3(hyperv_callback_vector, HYPERVISOR_CALLBACK_VECTOR, #endif /* CONFIG_HYPERV */ -#ifdef CONFIG_FUNCTION_TRACER -#ifdef CONFIG_DYNAMIC_FTRACE - -ENTRY(mcount) - ret -END(mcount) - -ENTRY(ftrace_caller) - pushl %eax - pushl %ecx - pushl %edx - pushl $0 /* Pass NULL as regs pointer */ - movl 4*4(%esp), %eax - movl 0x4(%ebp), %edx - movl function_trace_op, %ecx - subl $MCOUNT_INSN_SIZE, %eax - -.globl ftrace_call -ftrace_call: - call ftrace_stub - - addl $4, %esp /* skip NULL pointer */ - popl %edx - popl %ecx - popl %eax -.Lftrace_ret: -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -.globl ftrace_graph_call -ftrace_graph_call: - jmp ftrace_stub -#endif - -/* This is weak to keep gas from relaxing the jumps */ -WEAK(ftrace_stub) - ret -END(ftrace_caller) - -ENTRY(ftrace_regs_caller) - pushf /* push flags before compare (in cs location) */ - - /* - * i386 does not save SS and ESP when coming from kernel. - * Instead, to get sp, ®s->sp is used (see ptrace.h). - * Unfortunately, that means eflags must be at the same location - * as the current return ip is. We move the return ip into the - * ip location, and move flags into the return ip location. - */ - pushl 4(%esp) /* save return ip into ip slot */ - - pushl $0 /* Load 0 into orig_ax */ - pushl %gs - pushl %fs - pushl %es - pushl %ds - pushl %eax - pushl %ebp - pushl %edi - pushl %esi - pushl %edx - pushl %ecx - pushl %ebx - - movl 13*4(%esp), %eax /* Get the saved flags */ - movl %eax, 14*4(%esp) /* Move saved flags into regs->flags location */ - /* clobbering return ip */ - movl $__KERNEL_CS, 13*4(%esp) - - movl 12*4(%esp), %eax /* Load ip (1st parameter) */ - subl $MCOUNT_INSN_SIZE, %eax /* Adjust ip */ - movl 0x4(%ebp), %edx /* Load parent ip (2nd parameter) */ - movl function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */ - pushl %esp /* Save pt_regs as 4th parameter */ - -GLOBAL(ftrace_regs_call) - call ftrace_stub - - addl $4, %esp /* Skip pt_regs */ - movl 14*4(%esp), %eax /* Move flags back into cs */ - movl %eax, 13*4(%esp) /* Needed to keep addl from modifying flags */ - movl 12*4(%esp), %eax /* Get return ip from regs->ip */ - movl %eax, 14*4(%esp) /* Put return ip back for ret */ - - popl %ebx - popl %ecx - popl %edx - popl %esi - popl %edi - popl %ebp - popl %eax - popl %ds - popl %es - popl %fs - popl %gs - addl $8, %esp /* Skip orig_ax and ip */ - popf /* Pop flags at end (no addl to corrupt flags) */ - jmp .Lftrace_ret - - popf - jmp ftrace_stub -#else /* ! CONFIG_DYNAMIC_FTRACE */ - -ENTRY(mcount) - cmpl $__PAGE_OFFSET, %esp - jb ftrace_stub /* Paging not enabled yet? */ - - cmpl $ftrace_stub, ftrace_trace_function - jnz .Ltrace -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - cmpl $ftrace_stub, ftrace_graph_return - jnz ftrace_graph_caller - - cmpl $ftrace_graph_entry_stub, ftrace_graph_entry - jnz ftrace_graph_caller -#endif -.globl ftrace_stub -ftrace_stub: - ret - - /* taken from glibc */ -.Ltrace: - pushl %eax - pushl %ecx - pushl %edx - movl 0xc(%esp), %eax - movl 0x4(%ebp), %edx - subl $MCOUNT_INSN_SIZE, %eax - - call *ftrace_trace_function - - popl %edx - popl %ecx - popl %eax - jmp ftrace_stub -END(mcount) -#endif /* CONFIG_DYNAMIC_FTRACE */ -EXPORT_SYMBOL(mcount) -#endif /* CONFIG_FUNCTION_TRACER */ - -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -ENTRY(ftrace_graph_caller) - pushl %eax - pushl %ecx - pushl %edx - movl 0xc(%esp), %eax - lea 0x4(%ebp), %edx - movl (%ebp), %ecx - subl $MCOUNT_INSN_SIZE, %eax - call prepare_ftrace_return - popl %edx - popl %ecx - popl %eax - ret -END(ftrace_graph_caller) - -.globl return_to_handler -return_to_handler: - pushl %eax - pushl %edx - movl %ebp, %eax - call ftrace_return_to_handler - movl %eax, %ecx - popl %edx - popl %eax - jmp *%ecx -#endif - #ifdef CONFIG_TRACING ENTRY(trace_page_fault) ASM_CLAC diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 044d18ebc43c..607d72c4a485 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -212,7 +212,7 @@ entry_SYSCALL_64_fastpath: * If we see that no exit work is required (which we are required * to check with IRQs off), then we can go straight to SYSRET64. */ - DISABLE_INTERRUPTS(CLBR_NONE) + DISABLE_INTERRUPTS(CLBR_ANY) TRACE_IRQS_OFF movq PER_CPU_VAR(current_task), %r11 testl $_TIF_ALLWORK_MASK, TASK_TI_flags(%r11) @@ -233,7 +233,7 @@ entry_SYSCALL_64_fastpath: * raise(3) will trigger this, for example. IRQs are off. */ TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_NONE) + ENABLE_INTERRUPTS(CLBR_ANY) SAVE_EXTRA_REGS movq %rsp, %rdi call syscall_return_slowpath /* returns with IRQs disabled */ @@ -265,12 +265,9 @@ return_from_SYSCALL_64: * * If width of "canonical tail" ever becomes variable, this will need * to be updated to remain correct on both old and new CPUs. + * + * Change top 16 bits to be the sign-extension of 47th bit */ - .ifne __VIRTUAL_MASK_SHIFT - 47 - .error "virtual address width changed -- SYSRET checks need update" - .endif - - /* Change top 16 bits to be the sign-extension of 47th bit */ shl $(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx sar $(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx @@ -343,7 +340,7 @@ ENTRY(stub_ptregs_64) * Called from fast path -- disable IRQs again, pop return address * and jump to slow path */ - DISABLE_INTERRUPTS(CLBR_NONE) + DISABLE_INTERRUPTS(CLBR_ANY) TRACE_IRQS_OFF popq %rax jmp entry_SYSCALL64_slow_path @@ -518,7 +515,7 @@ common_interrupt: interrupt do_IRQ /* 0(%rsp): old RSP */ ret_from_intr: - DISABLE_INTERRUPTS(CLBR_NONE) + DISABLE_INTERRUPTS(CLBR_ANY) TRACE_IRQS_OFF decl PER_CPU_VAR(irq_count) @@ -1051,7 +1048,7 @@ END(paranoid_entry) * On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it) */ ENTRY(paranoid_exit) - DISABLE_INTERRUPTS(CLBR_NONE) + DISABLE_INTERRUPTS(CLBR_ANY) TRACE_IRQS_OFF_DEBUG testl %ebx, %ebx /* swapgs needed? */ jnz paranoid_exit_no_swapgs @@ -1156,10 +1153,9 @@ END(error_entry) * 0: user gsbase is loaded, we need SWAPGS and standard preparation for return to usermode */ ENTRY(error_exit) - movl %ebx, %eax - DISABLE_INTERRUPTS(CLBR_NONE) + DISABLE_INTERRUPTS(CLBR_ANY) TRACE_IRQS_OFF - testl %eax, %eax + testl %ebx, %ebx jnz retint_kernel jmp retint_user END(error_exit) diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index b1a63f6f53c0..448ac2161112 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -390,3 +390,4 @@ 381 i386 pkey_alloc sys_pkey_alloc 382 i386 pkey_free sys_pkey_free 383 i386 statx sys_statx +384 i386 arch_prctl sys_arch_prctl compat_sys_arch_prctl diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c index 9d4d6e138311..fa8dbfcf7ed3 100644 --- a/arch/x86/entry/vdso/vclock_gettime.c +++ b/arch/x86/entry/vdso/vclock_gettime.c @@ -17,6 +17,7 @@ #include <asm/unistd.h> #include <asm/msr.h> #include <asm/pvclock.h> +#include <asm/mshyperv.h> #include <linux/math64.h> #include <linux/time.h> #include <linux/kernel.h> @@ -32,6 +33,11 @@ extern u8 pvclock_page __attribute__((visibility("hidden"))); #endif +#ifdef CONFIG_HYPERV_TSCPAGE +extern u8 hvclock_page + __attribute__((visibility("hidden"))); +#endif + #ifndef BUILD_VDSO32 notrace static long vdso_fallback_gettime(long clock, struct timespec *ts) @@ -141,6 +147,20 @@ static notrace u64 vread_pvclock(int *mode) return last; } #endif +#ifdef CONFIG_HYPERV_TSCPAGE +static notrace u64 vread_hvclock(int *mode) +{ + const struct ms_hyperv_tsc_page *tsc_pg = + (const struct ms_hyperv_tsc_page *)&hvclock_page; + u64 current_tick = hv_read_tsc_page(tsc_pg); + + if (current_tick != U64_MAX) + return current_tick; + + *mode = VCLOCK_NONE; + return 0; +} +#endif notrace static u64 vread_tsc(void) { @@ -173,6 +193,10 @@ notrace static inline u64 vgetsns(int *mode) else if (gtod->vclock_mode == VCLOCK_PVCLOCK) cycles = vread_pvclock(mode); #endif +#ifdef CONFIG_HYPERV_TSCPAGE + else if (gtod->vclock_mode == VCLOCK_HVCLOCK) + cycles = vread_hvclock(mode); +#endif else return 0; v = (cycles - gtod->cycle_last) & gtod->mask; diff --git a/arch/x86/entry/vdso/vdso-layout.lds.S b/arch/x86/entry/vdso/vdso-layout.lds.S index a708aa90b507..8ebb4b6454fe 100644 --- a/arch/x86/entry/vdso/vdso-layout.lds.S +++ b/arch/x86/entry/vdso/vdso-layout.lds.S @@ -25,7 +25,7 @@ SECTIONS * segment. */ - vvar_start = . - 2 * PAGE_SIZE; + vvar_start = . - 3 * PAGE_SIZE; vvar_page = vvar_start; /* Place all vvars at the offsets in asm/vvar.h. */ @@ -36,6 +36,7 @@ SECTIONS #undef EMIT_VVAR pvclock_page = vvar_start + PAGE_SIZE; + hvclock_page = vvar_start + 2 * PAGE_SIZE; . = SIZEOF_HEADERS; diff --git a/arch/x86/entry/vdso/vdso2c.c b/arch/x86/entry/vdso/vdso2c.c index 491020b2826d..0780a443a53b 100644 --- a/arch/x86/entry/vdso/vdso2c.c +++ b/arch/x86/entry/vdso/vdso2c.c @@ -74,6 +74,7 @@ enum { sym_vvar_page, sym_hpet_page, sym_pvclock_page, + sym_hvclock_page, sym_VDSO_FAKE_SECTION_TABLE_START, sym_VDSO_FAKE_SECTION_TABLE_END, }; @@ -82,6 +83,7 @@ const int special_pages[] = { sym_vvar_page, sym_hpet_page, sym_pvclock_page, + sym_hvclock_page, }; struct vdso_sym { @@ -94,6 +96,7 @@ struct vdso_sym required_syms[] = { [sym_vvar_page] = {"vvar_page", true}, [sym_hpet_page] = {"hpet_page", true}, [sym_pvclock_page] = {"pvclock_page", true}, + [sym_hvclock_page] = {"hvclock_page", true}, [sym_VDSO_FAKE_SECTION_TABLE_START] = { "VDSO_FAKE_SECTION_TABLE_START", false }, diff --git a/arch/x86/entry/vdso/vdso32-setup.c b/arch/x86/entry/vdso/vdso32-setup.c index 7853b53959cd..3f9d1a83891a 100644 --- a/arch/x86/entry/vdso/vdso32-setup.c +++ b/arch/x86/entry/vdso/vdso32-setup.c @@ -30,8 +30,10 @@ static int __init vdso32_setup(char *s) { vdso32_enabled = simple_strtoul(s, NULL, 0); - if (vdso32_enabled > 1) + if (vdso32_enabled > 1) { pr_warn("vdso32 values other than 0 and 1 are no longer allowed; vdso disabled\n"); + vdso32_enabled = 0; + } return 1; } @@ -62,13 +64,18 @@ subsys_initcall(sysenter_setup); /* Register vsyscall32 into the ABI table */ #include <linux/sysctl.h> +static const int zero; +static const int one = 1; + static struct ctl_table abi_table2[] = { { .procname = "vsyscall32", .data = &vdso32_enabled, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = (int *)&zero, + .extra2 = (int *)&one, }, {} }; diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index 226ca70dc6bd..139ad7726e10 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -22,6 +22,7 @@ #include <asm/page.h> #include <asm/desc.h> #include <asm/cpufeature.h> +#include <asm/mshyperv.h> #if defined(CONFIG_X86_64) unsigned int __read_mostly vdso64_enabled = 1; @@ -121,6 +122,12 @@ static int vvar_fault(const struct vm_special_mapping *sm, vmf->address, __pa(pvti) >> PAGE_SHIFT); } + } else if (sym_offset == image->sym_hvclock_page) { + struct ms_hyperv_tsc_page *tsc_pg = hv_get_tsc_page(); + + if (tsc_pg && vclock_was_used(VCLOCK_HVCLOCK)) + ret = vm_insert_pfn(vma, vmf->address, + vmalloc_to_pfn(tsc_pg)); } if (ret == 0 || ret == -EBUSY) @@ -354,7 +361,7 @@ static void vgetcpu_cpu_init(void *arg) d.p = 1; /* Present */ d.d = 1; /* 32-bit */ - write_gdt_entry(get_cpu_gdt_table(cpu), GDT_ENTRY_PER_CPU, &d, DESCTYPE_S); + write_gdt_entry(get_cpu_gdt_rw(cpu), GDT_ENTRY_PER_CPU, &d, DESCTYPE_S); } static int vgetcpu_online(unsigned int cpu) diff --git a/arch/x86/events/amd/iommu.c b/arch/x86/events/amd/iommu.c index b28200dea715..3641e24fdac5 100644 --- a/arch/x86/events/amd/iommu.c +++ b/arch/x86/events/amd/iommu.c @@ -11,6 +11,8 @@ * published by the Free Software Foundation. */ +#define pr_fmt(fmt) "perf/amd_iommu: " fmt + #include <linux/perf_event.h> #include <linux/init.h> #include <linux/cpumask.h> @@ -21,44 +23,42 @@ #define COUNTER_SHIFT 16 -#define _GET_BANK(ev) ((u8)(ev->hw.extra_reg.reg >> 8)) -#define _GET_CNTR(ev) ((u8)(ev->hw.extra_reg.reg)) +/* iommu pmu conf masks */ +#define GET_CSOURCE(x) ((x)->conf & 0xFFULL) +#define GET_DEVID(x) (((x)->conf >> 8) & 0xFFFFULL) +#define GET_DOMID(x) (((x)->conf >> 24) & 0xFFFFULL) +#define GET_PASID(x) (((x)->conf >> 40) & 0xFFFFFULL) -/* iommu pmu config masks */ -#define _GET_CSOURCE(ev) ((ev->hw.config & 0xFFULL)) -#define _GET_DEVID(ev) ((ev->hw.config >> 8) & 0xFFFFULL) -#define _GET_PASID(ev) ((ev->hw.config >> 24) & 0xFFFFULL) -#define _GET_DOMID(ev) ((ev->hw.config >> 40) & 0xFFFFULL) -#define _GET_DEVID_MASK(ev) ((ev->hw.extra_reg.config) & 0xFFFFULL) -#define _GET_PASID_MASK(ev) ((ev->hw.extra_reg.config >> 16) & 0xFFFFULL) -#define _GET_DOMID_MASK(ev) ((ev->hw.extra_reg.config >> 32) & 0xFFFFULL) +/* iommu pmu conf1 masks */ +#define GET_DEVID_MASK(x) ((x)->conf1 & 0xFFFFULL) +#define GET_DOMID_MASK(x) (((x)->conf1 >> 16) & 0xFFFFULL) +#define GET_PASID_MASK(x) (((x)->conf1 >> 32) & 0xFFFFFULL) -static struct perf_amd_iommu __perf_iommu; +#define IOMMU_NAME_SIZE 16 struct perf_amd_iommu { + struct list_head list; struct pmu pmu; + struct amd_iommu *iommu; + char name[IOMMU_NAME_SIZE]; u8 max_banks; u8 max_counters; u64 cntr_assign_mask; raw_spinlock_t lock; - const struct attribute_group *attr_groups[4]; }; -#define format_group attr_groups[0] -#define cpumask_group attr_groups[1] -#define events_group attr_groups[2] -#define null_group attr_groups[3] +static LIST_HEAD(perf_amd_iommu_list); /*--------------------------------------------- * sysfs format attributes *---------------------------------------------*/ PMU_FORMAT_ATTR(csource, "config:0-7"); PMU_FORMAT_ATTR(devid, "config:8-23"); -PMU_FORMAT_ATTR(pasid, "config:24-39"); -PMU_FORMAT_ATTR(domid, "config:40-55"); +PMU_FORMAT_ATTR(domid, "config:24-39"); +PMU_FORMAT_ATTR(pasid, "config:40-59"); PMU_FORMAT_ATTR(devid_mask, "config1:0-15"); -PMU_FORMAT_ATTR(pasid_mask, "config1:16-31"); -PMU_FORMAT_ATTR(domid_mask, "config1:32-47"); +PMU_FORMAT_ATTR(domid_mask, "config1:16-31"); +PMU_FORMAT_ATTR(pasid_mask, "config1:32-51"); static struct attribute *iommu_format_attrs[] = { &format_attr_csource.attr, @@ -79,6 +79,10 @@ static struct attribute_group amd_iommu_format_group = { /*--------------------------------------------- * sysfs events attributes *---------------------------------------------*/ +static struct attribute_group amd_iommu_events_group = { + .name = "events", +}; + struct amd_iommu_event_desc { struct kobj_attribute attr; const char *event; @@ -150,30 +154,34 @@ static struct attribute_group amd_iommu_cpumask_group = { /*---------------------------------------------*/ -static int get_next_avail_iommu_bnk_cntr(struct perf_amd_iommu *perf_iommu) +static int get_next_avail_iommu_bnk_cntr(struct perf_event *event) { + struct perf_amd_iommu *piommu = container_of(event->pmu, struct perf_amd_iommu, pmu); + int max_cntrs = piommu->max_counters; + int max_banks = piommu->max_banks; + u32 shift, bank, cntr; unsigned long flags; - int shift, bank, cntr, retval; - int max_banks = perf_iommu->max_banks; - int max_cntrs = perf_iommu->max_counters; + int retval; - raw_spin_lock_irqsave(&perf_iommu->lock, flags); + raw_spin_lock_irqsave(&piommu->lock, flags); for (bank = 0, shift = 0; bank < max_banks; bank++) { for (cntr = 0; cntr < max_cntrs; cntr++) { shift = bank + (bank*3) + cntr; - if (perf_iommu->cntr_assign_mask & (1ULL<<shift)) { + if (piommu->cntr_assign_mask & BIT_ULL(shift)) { continue; } else { - perf_iommu->cntr_assign_mask |= (1ULL<<shift); - retval = ((u16)((u16)bank<<8) | (u8)(cntr)); + piommu->cntr_assign_mask |= BIT_ULL(shift); + event->hw.iommu_bank = bank; + event->hw.iommu_cntr = cntr; + retval = 0; goto out; } } } retval = -ENOSPC; out: - raw_spin_unlock_irqrestore(&perf_iommu->lock, flags); + raw_spin_unlock_irqrestore(&piommu->lock, flags); return retval; } @@ -202,8 +210,6 @@ static int clear_avail_iommu_bnk_cntr(struct perf_amd_iommu *perf_iommu, static int perf_iommu_event_init(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; - struct perf_amd_iommu *perf_iommu; - u64 config, config1; /* test the event attr type check for PMU enumeration */ if (event->attr.type != event->pmu->type) @@ -225,80 +231,62 @@ static int perf_iommu_event_init(struct perf_event *event) if (event->cpu < 0) return -EINVAL; - perf_iommu = &__perf_iommu; - - if (event->pmu != &perf_iommu->pmu) - return -ENOENT; - - if (perf_iommu) { - config = event->attr.config; - config1 = event->attr.config1; - } else { - return -EINVAL; - } - - /* integrate with iommu base devid (0000), assume one iommu */ - perf_iommu->max_banks = - amd_iommu_pc_get_max_banks(IOMMU_BASE_DEVID); - perf_iommu->max_counters = - amd_iommu_pc_get_max_counters(IOMMU_BASE_DEVID); - if ((perf_iommu->max_banks == 0) || (perf_iommu->max_counters == 0)) - return -EINVAL; - /* update the hw_perf_event struct with the iommu config data */ - hwc->config = config; - hwc->extra_reg.config = config1; + hwc->conf = event->attr.config; + hwc->conf1 = event->attr.config1; return 0; } +static inline struct amd_iommu *perf_event_2_iommu(struct perf_event *ev) +{ + return (container_of(ev->pmu, struct perf_amd_iommu, pmu))->iommu; +} + static void perf_iommu_enable_event(struct perf_event *ev) { - u8 csource = _GET_CSOURCE(ev); - u16 devid = _GET_DEVID(ev); + struct amd_iommu *iommu = perf_event_2_iommu(ev); + struct hw_perf_event *hwc = &ev->hw; + u8 bank = hwc->iommu_bank; + u8 cntr = hwc->iommu_cntr; u64 reg = 0ULL; - reg = csource; - amd_iommu_pc_get_set_reg_val(devid, - _GET_BANK(ev), _GET_CNTR(ev) , - IOMMU_PC_COUNTER_SRC_REG, ®, true); + reg = GET_CSOURCE(hwc); + amd_iommu_pc_set_reg(iommu, bank, cntr, IOMMU_PC_COUNTER_SRC_REG, ®); - reg = 0ULL | devid | (_GET_DEVID_MASK(ev) << 32); + reg = GET_DEVID_MASK(hwc); + reg = GET_DEVID(hwc) | (reg << 32); if (reg) - reg |= (1UL << 31); - amd_iommu_pc_get_set_reg_val(devid, - _GET_BANK(ev), _GET_CNTR(ev) , - IOMMU_PC_DEVID_MATCH_REG, ®, true); + reg |= BIT(31); + amd_iommu_pc_set_reg(iommu, bank, cntr, IOMMU_PC_DEVID_MATCH_REG, ®); - reg = 0ULL | _GET_PASID(ev) | (_GET_PASID_MASK(ev) << 32); + reg = GET_PASID_MASK(hwc); + reg = GET_PASID(hwc) | (reg << 32); if (reg) - reg |= (1UL << 31); - amd_iommu_pc_get_set_reg_val(devid, - _GET_BANK(ev), _GET_CNTR(ev) , - IOMMU_PC_PASID_MATCH_REG, ®, true); + reg |= BIT(31); + amd_iommu_pc_set_reg(iommu, bank, cntr, IOMMU_PC_PASID_MATCH_REG, ®); - reg = 0ULL | _GET_DOMID(ev) | (_GET_DOMID_MASK(ev) << 32); + reg = GET_DOMID_MASK(hwc); + reg = GET_DOMID(hwc) | (reg << 32); if (reg) - reg |= (1UL << 31); - amd_iommu_pc_get_set_reg_val(devid, - _GET_BANK(ev), _GET_CNTR(ev) , - IOMMU_PC_DOMID_MATCH_REG, ®, true); + reg |= BIT(31); + amd_iommu_pc_set_reg(iommu, bank, cntr, IOMMU_PC_DOMID_MATCH_REG, ®); } static void perf_iommu_disable_event(struct perf_event *event) { + struct amd_iommu *iommu = perf_event_2_iommu(event); + struct hw_perf_event *hwc = &event->hw; u64 reg = 0ULL; - amd_iommu_pc_get_set_reg_val(_GET_DEVID(event), - _GET_BANK(event), _GET_CNTR(event), - IOMMU_PC_COUNTER_SRC_REG, ®, true); + amd_iommu_pc_set_reg(iommu, hwc->iommu_bank, hwc->iommu_cntr, + IOMMU_PC_COUNTER_SRC_REG, ®); } static void perf_iommu_start(struct perf_event *event, int flags) { struct hw_perf_event *hwc = &event->hw; - pr_debug("perf: amd_iommu:perf_iommu_start\n"); if (WARN_ON_ONCE(!(hwc->state & PERF_HES_STOPPED))) return; @@ -306,10 +294,11 @@ static void perf_iommu_start(struct perf_event *event, int flags) hwc->state = 0; if (flags & PERF_EF_RELOAD) { - u64 prev_raw_count = local64_read(&hwc->prev_count); - amd_iommu_pc_get_set_reg_val(_GET_DEVID(event), - _GET_BANK(event), _GET_CNTR(event), - IOMMU_PC_COUNTER_REG, &prev_raw_count, true); + u64 prev_raw_count = local64_read(&hwc->prev_count); + struct amd_iommu *iommu = perf_event_2_iommu(event); + + amd_iommu_pc_set_reg(iommu, hwc->iommu_bank, hwc->iommu_cntr, + IOMMU_PC_COUNTER_REG, &prev_raw_count); } perf_iommu_enable_event(event); @@ -319,37 +308,30 @@ static void perf_iommu_start(struct perf_event *event, int flags) static void perf_iommu_read(struct perf_event *event) { - u64 count = 0ULL; - u64 prev_raw_count = 0ULL; - u64 delta = 0ULL; + u64 count, prev, delta; struct hw_perf_event *hwc = &event->hw; - pr_debug("perf: amd_iommu:perf_iommu_read\n"); + struct amd_iommu *iommu = perf_event_2_iommu(event); - amd_iommu_pc_get_set_reg_val(_GET_DEVID(event), - _GET_BANK(event), _GET_CNTR(event), - IOMMU_PC_COUNTER_REG, &count, false); + if (amd_iommu_pc_get_reg(iommu, hwc->iommu_bank, hwc->iommu_cntr, + IOMMU_PC_COUNTER_REG, &count)) + return; /* IOMMU pc counter register is only 48 bits */ - count &= 0xFFFFFFFFFFFFULL; + count &= GENMASK_ULL(47, 0); - prev_raw_count = local64_read(&hwc->prev_count); - if (local64_cmpxchg(&hwc->prev_count, prev_raw_count, - count) != prev_raw_count) + prev = local64_read(&hwc->prev_count); + if (local64_cmpxchg(&hwc->prev_count, prev, count) != prev) return; - /* Handling 48-bit counter overflowing */ - delta = (count << COUNTER_SHIFT) - (prev_raw_count << COUNTER_SHIFT); + /* Handle 48-bit counter overflow */ + delta = (count << COUNTER_SHIFT) - (prev << COUNTER_SHIFT); delta >>= COUNTER_SHIFT; local64_add(delta, &event->count); - } static void perf_iommu_stop(struct perf_event *event, int flags) { struct hw_perf_event *hwc = &event->hw; - u64 config; - - pr_debug("perf: amd_iommu:perf_iommu_stop\n"); if (hwc->state & PERF_HES_UPTODATE) return; @@ -361,7 +343,6 @@ static void perf_iommu_stop(struct perf_event *event, int flags) if (hwc->state & PERF_HES_UPTODATE) return; - config = hwc->config; perf_iommu_read(event); hwc->state |= PERF_HES_UPTODATE; } @@ -369,17 +350,12 @@ static void perf_iommu_stop(struct perf_event *event, int flags) static int perf_iommu_add(struct perf_event *event, int flags) { int retval; - struct perf_amd_iommu *perf_iommu = - container_of(event->pmu, struct perf_amd_iommu, pmu); - pr_debug("perf: amd_iommu:perf_iommu_add\n"); event->hw.state = PERF_HES_UPTODATE | PERF_HES_STOPPED; /* request an iommu bank/counter */ - retval = get_next_avail_iommu_bnk_cntr(perf_iommu); - if (retval != -ENOSPC) - event->hw.extra_reg.reg = (u16)retval; - else + retval = get_next_avail_iommu_bnk_cntr(event); + if (retval) return retval; if (flags & PERF_EF_START) @@ -390,115 +366,124 @@ static int perf_iommu_add(struct perf_event *event, int flags) static void perf_iommu_del(struct perf_event *event, int flags) { + struct hw_perf_event *hwc = &event->hw; struct perf_amd_iommu *perf_iommu = container_of(event->pmu, struct perf_amd_iommu, pmu); - pr_debug("perf: amd_iommu:perf_iommu_del\n"); perf_iommu_stop(event, PERF_EF_UPDATE); /* clear the assigned iommu bank/counter */ clear_avail_iommu_bnk_cntr(perf_iommu, - _GET_BANK(event), - _GET_CNTR(event)); + hwc->iommu_bank, hwc->iommu_cntr); perf_event_update_userpage(event); } -static __init int _init_events_attrs(struct perf_amd_iommu *perf_iommu) +static __init int _init_events_attrs(void) { - struct attribute **attrs; - struct attribute_group *attr_group; int i = 0, j; + struct attribute **attrs; while (amd_iommu_v2_event_descs[i].attr.attr.name) i++; - attr_group = kzalloc(sizeof(struct attribute *) - * (i + 1) + sizeof(*attr_group), GFP_KERNEL); - if (!attr_group) + attrs = kzalloc(sizeof(struct attribute **) * (i + 1), GFP_KERNEL); + if (!attrs) return -ENOMEM; - attrs = (struct attribute **)(attr_group + 1); for (j = 0; j < i; j++) attrs[j] = &amd_iommu_v2_event_descs[j].attr.attr; - attr_group->name = "events"; - attr_group->attrs = attrs; - perf_iommu->events_group = attr_group; - + amd_iommu_events_group.attrs = attrs; return 0; } -static __init void amd_iommu_pc_exit(void) -{ - if (__perf_iommu.events_group != NULL) { - kfree(__perf_iommu.events_group); - __perf_iommu.events_group = NULL; - } -} +const struct attribute_group *amd_iommu_attr_groups[] = { + &amd_iommu_format_group, + &amd_iommu_cpumask_group, + &amd_iommu_events_group, + NULL, +}; + +static struct pmu iommu_pmu = { + .event_init = perf_iommu_event_init, + .add = perf_iommu_add, + .del = perf_iommu_del, + .start = perf_iommu_start, + .stop = perf_iommu_stop, + .read = perf_iommu_read, + .task_ctx_nr = perf_invalid_context, + .attr_groups = amd_iommu_attr_groups, +}; -static __init int _init_perf_amd_iommu( - struct perf_amd_iommu *perf_iommu, char *name) +static __init int init_one_iommu(unsigned int idx) { + struct perf_amd_iommu *perf_iommu; int ret; + perf_iommu = kzalloc(sizeof(struct perf_amd_iommu), GFP_KERNEL); + if (!perf_iommu) + return -ENOMEM; + raw_spin_lock_init(&perf_iommu->lock); - /* Init format attributes */ - perf_iommu->format_group = &amd_iommu_format_group; + perf_iommu->pmu = iommu_pmu; + perf_iommu->iommu = get_amd_iommu(idx); + perf_iommu->max_banks = amd_iommu_pc_get_max_banks(idx); + perf_iommu->max_counters = amd_iommu_pc_get_max_counters(idx); - /* Init cpumask attributes to only core 0 */ - cpumask_set_cpu(0, &iommu_cpumask); - perf_iommu->cpumask_group = &amd_iommu_cpumask_group; - - /* Init events attributes */ - if (_init_events_attrs(perf_iommu) != 0) - pr_err("perf: amd_iommu: Only support raw events.\n"); + if (!perf_iommu->iommu || + !perf_iommu->max_banks || + !perf_iommu->max_counters) { + kfree(perf_iommu); + return -EINVAL; + } - /* Init null attributes */ - perf_iommu->null_group = NULL; - perf_iommu->pmu.attr_groups = perf_iommu->attr_groups; + snprintf(perf_iommu->name, IOMMU_NAME_SIZE, "amd_iommu_%u", idx); - ret = perf_pmu_register(&perf_iommu->pmu, name, -1); - if (ret) { - pr_err("perf: amd_iommu: Failed to initialized.\n"); - amd_iommu_pc_exit(); + ret = perf_pmu_register(&perf_iommu->pmu, perf_iommu->name, -1); + if (!ret) { + pr_info("Detected AMD IOMMU #%d (%d banks, %d counters/bank).\n", + idx, perf_iommu->max_banks, perf_iommu->max_counters); + list_add_tail(&perf_iommu->list, &perf_amd_iommu_list); } else { - pr_info("perf: amd_iommu: Detected. (%d banks, %d counters/bank)\n", - amd_iommu_pc_get_max_banks(IOMMU_BASE_DEVID), - amd_iommu_pc_get_max_counters(IOMMU_BASE_DEVID)); + pr_warn("Error initializing IOMMU %d.\n", idx); + kfree(perf_iommu); } - return ret; } -static struct perf_amd_iommu __perf_iommu = { - .pmu = { - .task_ctx_nr = perf_invalid_context, - .event_init = perf_iommu_event_init, - .add = perf_iommu_add, - .del = perf_iommu_del, - .start = perf_iommu_start, - .stop = perf_iommu_stop, - .read = perf_iommu_read, - }, - .max_banks = 0x00, - .max_counters = 0x00, - .cntr_assign_mask = 0ULL, - .format_group = NULL, - .cpumask_group = NULL, - .events_group = NULL, - .null_group = NULL, -}; - static __init int amd_iommu_pc_init(void) { + unsigned int i, cnt = 0; + int ret; + /* Make sure the IOMMU PC resource is available */ if (!amd_iommu_pc_supported()) return -ENODEV; - _init_perf_amd_iommu(&__perf_iommu, "amd_iommu"); + ret = _init_events_attrs(); + if (ret) + return ret; + + /* + * An IOMMU PMU is specific to an IOMMU, and can function independently. + * So we go through all IOMMUs and ignore the one that fails init + * unless all IOMMU are failing. + */ + for (i = 0; i < amd_iommu_get_num_iommus(); i++) { + ret = init_one_iommu(i); + if (!ret) + cnt++; + } + + if (!cnt) { + kfree(amd_iommu_events_group.attrs); + return -ENODEV; + } + /* Init cpumask attributes to only core 0 */ + cpumask_set_cpu(0, &iommu_cpumask); return 0; } diff --git a/arch/x86/events/amd/iommu.h b/arch/x86/events/amd/iommu.h index 845d173278e3..62e0702c4374 100644 --- a/arch/x86/events/amd/iommu.h +++ b/arch/x86/events/amd/iommu.h @@ -24,17 +24,23 @@ #define PC_MAX_SPEC_BNKS 64 #define PC_MAX_SPEC_CNTRS 16 -/* iommu pc reg masks*/ -#define IOMMU_BASE_DEVID 0x0000 +struct amd_iommu; /* amd_iommu_init.c external support functions */ +extern int amd_iommu_get_num_iommus(void); + extern bool amd_iommu_pc_supported(void); -extern u8 amd_iommu_pc_get_max_banks(u16 devid); +extern u8 amd_iommu_pc_get_max_banks(unsigned int idx); + +extern u8 amd_iommu_pc_get_max_counters(unsigned int idx); + +extern int amd_iommu_pc_set_reg(struct amd_iommu *iommu, u8 bank, u8 cntr, + u8 fxn, u64 *value); -extern u8 amd_iommu_pc_get_max_counters(u16 devid); +extern int amd_iommu_pc_get_reg(struct amd_iommu *iommu, u8 bank, u8 cntr, + u8 fxn, u64 *value); -extern int amd_iommu_pc_get_set_reg_val(u16 devid, u8 bank, u8 cntr, - u8 fxn, u64 *value, bool is_write); +extern struct amd_iommu *get_amd_iommu(int idx); #endif /*_PERF_EVENT_AMD_IOMMU_H_*/ diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c index 4d1f7f2d9aff..ad44af0dd667 100644 --- a/arch/x86/events/amd/uncore.c +++ b/arch/x86/events/amd/uncore.c @@ -30,6 +30,9 @@ #define COUNTER_SHIFT 16 +#undef pr_fmt +#define pr_fmt(fmt) "amd_uncore: " fmt + static int num_counters_llc; static int num_counters_nb; @@ -509,51 +512,34 @@ static int __init amd_uncore_init(void) int ret = -ENODEV; if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) - goto fail_nodev; - - switch(boot_cpu_data.x86) { - case 23: - /* Family 17h: */ - num_counters_nb = NUM_COUNTERS_NB; - num_counters_llc = NUM_COUNTERS_L3; - /* - * For Family17h, the NorthBridge counters are - * re-purposed as Data Fabric counters. Also, support is - * added for L3 counters. The pmus are exported based on - * family as either L2 or L3 and NB or DF. - */ - amd_nb_pmu.name = "amd_df"; - amd_llc_pmu.name = "amd_l3"; - format_attr_event_df.show = &event_show_df; - format_attr_event_l3.show = &event_show_l3; - break; - case 22: - /* Family 16h - may change: */ - num_counters_nb = NUM_COUNTERS_NB; - num_counters_llc = NUM_COUNTERS_L2; - amd_nb_pmu.name = "amd_nb"; - amd_llc_pmu.name = "amd_l2"; - format_attr_event_df = format_attr_event; - format_attr_event_l3 = format_attr_event; - break; - default: - /* - * All prior families have the same number of - * NorthBridge and Last Level Cache counters - */ - num_counters_nb = NUM_COUNTERS_NB; - num_counters_llc = NUM_COUNTERS_L2; - amd_nb_pmu.name = "amd_nb"; - amd_llc_pmu.name = "amd_l2"; - format_attr_event_df = format_attr_event; - format_attr_event_l3 = format_attr_event; - break; - } - amd_nb_pmu.attr_groups = amd_uncore_attr_groups_df; - amd_llc_pmu.attr_groups = amd_uncore_attr_groups_l3; + return -ENODEV; if (!boot_cpu_has(X86_FEATURE_TOPOEXT)) - goto fail_nodev; + return -ENODEV; + + if (boot_cpu_data.x86 == 0x17) { + /* + * For F17h, the Northbridge counters are repurposed as Data + * Fabric counters. Also, L3 counters are supported too. The PMUs + * are exported based on family as either L2 or L3 and NB or DF. + */ + num_counters_nb = NUM_COUNTERS_NB; + num_counters_llc = NUM_COUNTERS_L3; + amd_nb_pmu.name = "amd_df"; + amd_llc_pmu.name = "amd_l3"; + format_attr_event_df.show = &event_show_df; + format_attr_event_l3.show = &event_show_l3; + } else { + num_counters_nb = NUM_COUNTERS_NB; + num_counters_llc = NUM_COUNTERS_L2; + amd_nb_pmu.name = "amd_nb"; + amd_llc_pmu.name = "amd_l2"; + format_attr_event_df = format_attr_event; + format_attr_event_l3 = format_attr_event; + } + + amd_nb_pmu.attr_groups = amd_uncore_attr_groups_df; + amd_llc_pmu.attr_groups = amd_uncore_attr_groups_l3; if (boot_cpu_has(X86_FEATURE_PERFCTR_NB)) { amd_uncore_nb = alloc_percpu(struct amd_uncore *); @@ -565,7 +551,7 @@ static int __init amd_uncore_init(void) if (ret) goto fail_nb; - pr_info("perf: AMD NB counters detected\n"); + pr_info("AMD NB counters detected\n"); ret = 0; } @@ -579,7 +565,7 @@ static int __init amd_uncore_init(void) if (ret) goto fail_llc; - pr_info("perf: AMD LLC counters detected\n"); + pr_info("AMD LLC counters detected\n"); ret = 0; } @@ -615,7 +601,6 @@ fail_nb: if (amd_uncore_nb) free_percpu(amd_uncore_nb); -fail_nodev: return ret; } device_initcall(amd_uncore_init); diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c index 982c9e31daca..8ae8c5ce3a1f 100644 --- a/arch/x86/events/intel/bts.c +++ b/arch/x86/events/intel/bts.c @@ -63,7 +63,6 @@ struct bts_buffer { unsigned int cur_buf; bool snapshot; local_t data_size; - local_t lost; local_t head; unsigned long end; void **data_pages; @@ -199,7 +198,8 @@ static void bts_update(struct bts_ctx *bts) return; if (ds->bts_index >= ds->bts_absolute_maximum) - local_inc(&buf->lost); + perf_aux_output_flag(&bts->handle, + PERF_AUX_FLAG_TRUNCATED); /* * old and head are always in the same physical buffer, so we @@ -276,7 +276,7 @@ static void bts_event_start(struct perf_event *event, int flags) return; fail_end_stop: - perf_aux_output_end(&bts->handle, 0, false); + perf_aux_output_end(&bts->handle, 0); fail_stop: event->hw.state = PERF_HES_STOPPED; @@ -319,9 +319,8 @@ static void bts_event_stop(struct perf_event *event, int flags) bts->handle.head = local_xchg(&buf->data_size, buf->nr_pages << PAGE_SHIFT); - - perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0), - !!local_xchg(&buf->lost, 0)); + perf_aux_output_end(&bts->handle, + local_xchg(&buf->data_size, 0)); } cpuc->ds->bts_index = bts->ds_back.bts_buffer_base; @@ -484,8 +483,7 @@ int intel_bts_interrupt(void) if (old_head == local_read(&buf->head)) return handled; - perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0), - !!local_xchg(&buf->lost, 0)); + perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0)); buf = perf_aux_output_begin(&bts->handle, event); if (buf) @@ -500,7 +498,7 @@ int intel_bts_interrupt(void) * cleared handle::event */ barrier(); - perf_aux_output_end(&bts->handle, 0, false); + perf_aux_output_end(&bts->handle, 0); } } diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index eb1484c86bb4..a6d91d4e37a1 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -1553,6 +1553,27 @@ static __initconst const u64 slm_hw_cache_event_ids }, }; +EVENT_ATTR_STR(topdown-total-slots, td_total_slots_glm, "event=0x3c"); +EVENT_ATTR_STR(topdown-total-slots.scale, td_total_slots_scale_glm, "3"); +/* UOPS_NOT_DELIVERED.ANY */ +EVENT_ATTR_STR(topdown-fetch-bubbles, td_fetch_bubbles_glm, "event=0x9c"); +/* ISSUE_SLOTS_NOT_CONSUMED.RECOVERY */ +EVENT_ATTR_STR(topdown-recovery-bubbles, td_recovery_bubbles_glm, "event=0xca,umask=0x02"); +/* UOPS_RETIRED.ANY */ +EVENT_ATTR_STR(topdown-slots-retired, td_slots_retired_glm, "event=0xc2"); +/* UOPS_ISSUED.ANY */ +EVENT_ATTR_STR(topdown-slots-issued, td_slots_issued_glm, "event=0x0e"); + +static struct attribute *glm_events_attrs[] = { + EVENT_PTR(td_total_slots_glm), + EVENT_PTR(td_total_slots_scale_glm), + EVENT_PTR(td_fetch_bubbles_glm), + EVENT_PTR(td_recovery_bubbles_glm), + EVENT_PTR(td_slots_issued_glm), + EVENT_PTR(td_slots_retired_glm), + NULL +}; + static struct extra_reg intel_glm_extra_regs[] __read_mostly = { /* must define OFFCORE_RSP_X first, see intel_fixup_er() */ INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x760005ffbfull, RSP_0), @@ -2130,7 +2151,7 @@ again: * counters from the GLOBAL_STATUS mask and we always process PEBS * events via drain_pebs(). */ - status &= ~cpuc->pebs_enabled; + status &= ~(cpuc->pebs_enabled & PEBS_COUNTER_MASK); /* * PEBS overflow sets bit 62 in the global status register @@ -3750,6 +3771,7 @@ __init int intel_pmu_init(void) x86_pmu.pebs_prec_dist = true; x86_pmu.lbr_pt_coexist = true; x86_pmu.flags |= PMU_FL_HAS_RSP_1; + x86_pmu.cpu_events = glm_events_attrs; pr_cont("Goldmont events, "); break; diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 9dfeeeca0ea8..c6d23ffe422d 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1222,7 +1222,7 @@ get_next_pebs_record_by_bit(void *base, void *top, int bit) /* clear non-PEBS bit and re-check */ pebs_status = p->status & cpuc->pebs_enabled; - pebs_status &= (1ULL << MAX_PEBS_EVENTS) - 1; + pebs_status &= PEBS_COUNTER_MASK; if (pebs_status == (1 << bit)) return at; } diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 81b321ace8e0..f924629836a8 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -507,6 +507,9 @@ static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc) cpuc->lbr_entries[i].to = msr_lastbranch.to; cpuc->lbr_entries[i].mispred = 0; cpuc->lbr_entries[i].predicted = 0; + cpuc->lbr_entries[i].in_tx = 0; + cpuc->lbr_entries[i].abort = 0; + cpuc->lbr_entries[i].cycles = 0; cpuc->lbr_entries[i].reserved = 0; } cpuc->lbr_stack.nr = i; diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c index 5900471ee508..ae8324d65e61 100644 --- a/arch/x86/events/intel/pt.c +++ b/arch/x86/events/intel/pt.c @@ -28,6 +28,7 @@ #include <asm/insn.h> #include <asm/io.h> #include <asm/intel_pt.h> +#include <asm/intel-family.h> #include "../perf_event.h" #include "pt.h" @@ -98,6 +99,7 @@ static struct attribute_group pt_cap_group = { .name = "caps", }; +PMU_FORMAT_ATTR(pt, "config:0" ); PMU_FORMAT_ATTR(cyc, "config:1" ); PMU_FORMAT_ATTR(pwr_evt, "config:4" ); PMU_FORMAT_ATTR(fup_on_ptw, "config:5" ); @@ -105,11 +107,13 @@ PMU_FORMAT_ATTR(mtc, "config:9" ); PMU_FORMAT_ATTR(tsc, "config:10" ); PMU_FORMAT_ATTR(noretcomp, "config:11" ); PMU_FORMAT_ATTR(ptw, "config:12" ); +PMU_FORMAT_ATTR(branch, "config:13" ); PMU_FORMAT_ATTR(mtc_period, "config:14-17" ); PMU_FORMAT_ATTR(cyc_thresh, "config:19-22" ); PMU_FORMAT_ATTR(psb_period, "config:24-27" ); static struct attribute *pt_formats_attr[] = { + &format_attr_pt.attr, &format_attr_cyc.attr, &format_attr_pwr_evt.attr, &format_attr_fup_on_ptw.attr, @@ -117,6 +121,7 @@ static struct attribute *pt_formats_attr[] = { &format_attr_tsc.attr, &format_attr_noretcomp.attr, &format_attr_ptw.attr, + &format_attr_branch.attr, &format_attr_mtc_period.attr, &format_attr_cyc_thresh.attr, &format_attr_psb_period.attr, @@ -197,6 +202,19 @@ static int __init pt_pmu_hw_init(void) pt_pmu.tsc_art_den = eax; } + /* model-specific quirks */ + switch (boot_cpu_data.x86_model) { + case INTEL_FAM6_BROADWELL_CORE: + case INTEL_FAM6_BROADWELL_XEON_D: + case INTEL_FAM6_BROADWELL_GT3E: + case INTEL_FAM6_BROADWELL_X: + /* not setting BRANCH_EN will #GP, erratum BDM106 */ + pt_pmu.branch_en_always_on = true; + break; + default: + break; + } + if (boot_cpu_has(X86_FEATURE_VMX)) { /* * Intel SDM, 36.5 "Tracing post-VMXON" says that @@ -263,8 +281,20 @@ fail: #define RTIT_CTL_PTW (RTIT_CTL_PTW_EN | \ RTIT_CTL_FUP_ON_PTW) -#define PT_CONFIG_MASK (RTIT_CTL_TSC_EN | \ +/* + * Bit 0 (TraceEn) in the attr.config is meaningless as the + * corresponding bit in the RTIT_CTL can only be controlled + * by the driver; therefore, repurpose it to mean: pass + * through the bit that was previously assumed to be always + * on for PT, thereby allowing the user to *not* set it if + * they so wish. See also pt_event_valid() and pt_config(). + */ +#define RTIT_CTL_PASSTHROUGH RTIT_CTL_TRACEEN + +#define PT_CONFIG_MASK (RTIT_CTL_TRACEEN | \ + RTIT_CTL_TSC_EN | \ RTIT_CTL_DISRETC | \ + RTIT_CTL_BRANCH_EN | \ RTIT_CTL_CYC_PSB | \ RTIT_CTL_MTC | \ RTIT_CTL_PWR_EVT_EN | \ @@ -332,6 +362,33 @@ static bool pt_event_valid(struct perf_event *event) return false; } + /* + * Setting bit 0 (TraceEn in RTIT_CTL MSR) in the attr.config + * clears the assomption that BranchEn must always be enabled, + * as was the case with the first implementation of PT. + * If this bit is not set, the legacy behavior is preserved + * for compatibility with the older userspace. + * + * Re-using bit 0 for this purpose is fine because it is never + * directly set by the user; previous attempts at setting it in + * the attr.config resulted in -EINVAL. + */ + if (config & RTIT_CTL_PASSTHROUGH) { + /* + * Disallow not setting BRANCH_EN where BRANCH_EN is + * always required. + */ + if (pt_pmu.branch_en_always_on && + !(config & RTIT_CTL_BRANCH_EN)) + return false; + } else { + /* + * Disallow BRANCH_EN without the PASSTHROUGH. + */ + if (config & RTIT_CTL_BRANCH_EN) + return false; + } + return true; } @@ -411,6 +468,7 @@ static u64 pt_config_filters(struct perf_event *event) static void pt_config(struct perf_event *event) { + struct pt *pt = this_cpu_ptr(&pt_ctx); u64 reg; if (!event->hw.itrace_started) { @@ -419,7 +477,20 @@ static void pt_config(struct perf_event *event) } reg = pt_config_filters(event); - reg |= RTIT_CTL_TOPA | RTIT_CTL_BRANCH_EN | RTIT_CTL_TRACEEN; + reg |= RTIT_CTL_TOPA | RTIT_CTL_TRACEEN; + + /* + * Previously, we had BRANCH_EN on by default, but now that PT has + * grown features outside of branch tracing, it is useful to allow + * the user to disable it. Setting bit 0 in the event's attr.config + * allows BRANCH_EN to pass through instead of being always on. See + * also the comment in pt_event_valid(). + */ + if (event->attr.config & BIT(0)) { + reg |= event->attr.config & RTIT_CTL_BRANCH_EN; + } else { + reg |= RTIT_CTL_BRANCH_EN; + } if (!event->attr.exclude_kernel) reg |= RTIT_CTL_OS; @@ -429,11 +500,15 @@ static void pt_config(struct perf_event *event) reg |= (event->attr.config & PT_CONFIG_MASK); event->hw.config = reg; - wrmsrl(MSR_IA32_RTIT_CTL, reg); + if (READ_ONCE(pt->vmx_on)) + perf_aux_output_flag(&pt->handle, PERF_AUX_FLAG_PARTIAL); + else + wrmsrl(MSR_IA32_RTIT_CTL, reg); } static void pt_config_stop(struct perf_event *event) { + struct pt *pt = this_cpu_ptr(&pt_ctx); u64 ctl = READ_ONCE(event->hw.config); /* may be already stopped by a PMI */ @@ -441,7 +516,8 @@ static void pt_config_stop(struct perf_event *event) return; ctl &= ~RTIT_CTL_TRACEEN; - wrmsrl(MSR_IA32_RTIT_CTL, ctl); + if (!READ_ONCE(pt->vmx_on)) + wrmsrl(MSR_IA32_RTIT_CTL, ctl); WRITE_ONCE(event->hw.config, ctl); @@ -753,7 +829,8 @@ static void pt_handle_status(struct pt *pt) */ if (!pt_cap_get(PT_CAP_topa_multiple_entries) || buf->output_off == sizes(TOPA_ENTRY(buf->cur, buf->cur_idx)->size)) { - local_inc(&buf->lost); + perf_aux_output_flag(&pt->handle, + PERF_AUX_FLAG_TRUNCATED); advance++; } } @@ -846,8 +923,10 @@ static int pt_buffer_reset_markers(struct pt_buffer *buf, /* can't stop in the middle of an output region */ if (buf->output_off + handle->size + 1 < - sizes(TOPA_ENTRY(buf->cur, buf->cur_idx)->size)) + sizes(TOPA_ENTRY(buf->cur, buf->cur_idx)->size)) { + perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED); return -EINVAL; + } /* single entry ToPA is handled by marking all regions STOP=1 INT=1 */ @@ -1171,12 +1250,6 @@ void intel_pt_interrupt(void) if (!READ_ONCE(pt->handle_nmi)) return; - /* - * If VMX is on and PT does not support it, don't touch anything. - */ - if (READ_ONCE(pt->vmx_on)) - return; - if (!event) return; @@ -1192,8 +1265,7 @@ void intel_pt_interrupt(void) pt_update_head(pt); - perf_aux_output_end(&pt->handle, local_xchg(&buf->data_size, 0), - local_xchg(&buf->lost, 0)); + perf_aux_output_end(&pt->handle, local_xchg(&buf->data_size, 0)); if (!event->hw.state) { int ret; @@ -1208,7 +1280,7 @@ void intel_pt_interrupt(void) /* snapshot counters don't use PMI, so it's safe */ ret = pt_buffer_reset_markers(buf, &pt->handle); if (ret) { - perf_aux_output_end(&pt->handle, 0, true); + perf_aux_output_end(&pt->handle, 0); return; } @@ -1237,12 +1309,19 @@ void intel_pt_handle_vmx(int on) local_irq_save(flags); WRITE_ONCE(pt->vmx_on, on); - if (on) { - /* prevent pt_config_stop() from writing RTIT_CTL */ - event = pt->handle.event; - if (event) - event->hw.config = 0; - } + /* + * If an AUX transaction is in progress, it will contain + * gap(s), so flag it PARTIAL to inform the user. + */ + event = pt->handle.event; + if (event) + perf_aux_output_flag(&pt->handle, + PERF_AUX_FLAG_PARTIAL); + + /* Turn PTs back on */ + if (!on && event) + wrmsrl(MSR_IA32_RTIT_CTL, event->hw.config); + local_irq_restore(flags); } EXPORT_SYMBOL_GPL(intel_pt_handle_vmx); @@ -1257,9 +1336,6 @@ static void pt_event_start(struct perf_event *event, int mode) struct pt *pt = this_cpu_ptr(&pt_ctx); struct pt_buffer *buf; - if (READ_ONCE(pt->vmx_on)) - return; - buf = perf_aux_output_begin(&pt->handle, event); if (!buf) goto fail_stop; @@ -1280,7 +1356,7 @@ static void pt_event_start(struct perf_event *event, int mode) return; fail_end_stop: - perf_aux_output_end(&pt->handle, 0, true); + perf_aux_output_end(&pt->handle, 0); fail_stop: hwc->state = PERF_HES_STOPPED; } @@ -1321,8 +1397,7 @@ static void pt_event_stop(struct perf_event *event, int mode) pt->handle.head = local_xchg(&buf->data_size, buf->nr_pages << PAGE_SHIFT); - perf_aux_output_end(&pt->handle, local_xchg(&buf->data_size, 0), - local_xchg(&buf->lost, 0)); + perf_aux_output_end(&pt->handle, local_xchg(&buf->data_size, 0)); } } diff --git a/arch/x86/events/intel/pt.h b/arch/x86/events/intel/pt.h index 53473c21b554..0eb41d07b79a 100644 --- a/arch/x86/events/intel/pt.h +++ b/arch/x86/events/intel/pt.h @@ -110,6 +110,7 @@ struct pt_pmu { struct pmu pmu; u32 caps[PT_CPUID_REGS_NUM * PT_CPUID_LEAVES]; bool vmx; + bool branch_en_always_on; unsigned long max_nonturbo_ratio; unsigned int tsc_art_num; unsigned int tsc_art_den; @@ -143,7 +144,6 @@ struct pt_buffer { size_t output_off; unsigned long nr_pages; local_t data_size; - local_t lost; local64_t head; bool snapshot; unsigned long stop_pos, intr_pos; diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index bcbb1d2ae10b..be3d36254040 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -79,6 +79,7 @@ struct amd_nb { /* The maximal number of PEBS events: */ #define MAX_PEBS_EVENTS 8 +#define PEBS_COUNTER_MASK ((1ULL << MAX_PEBS_EVENTS) - 1) /* * Flags PEBS can handle without an PMI. diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 8bef70e7f3cc..2b01421f7d0f 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -27,45 +27,22 @@ #include <linux/clockchips.h> -#ifdef CONFIG_X86_64 +#ifdef CONFIG_HYPERV_TSCPAGE static struct ms_hyperv_tsc_page *tsc_pg; +struct ms_hyperv_tsc_page *hv_get_tsc_page(void) +{ + return tsc_pg; +} + static u64 read_hv_clock_tsc(struct clocksource *arg) { - u64 current_tick; + u64 current_tick = hv_read_tsc_page(tsc_pg); + + if (current_tick == U64_MAX) + rdmsrl(HV_X64_MSR_TIME_REF_COUNT, current_tick); - if (tsc_pg->tsc_sequence != 0) { - /* - * Use the tsc page to compute the value. - */ - - while (1) { - u64 tmp; - u32 sequence = tsc_pg->tsc_sequence; - u64 cur_tsc; - u64 scale = tsc_pg->tsc_scale; - s64 offset = tsc_pg->tsc_offset; - - rdtscll(cur_tsc); - /* current_tick = ((cur_tsc *scale) >> 64) + offset */ - asm("mulq %3" - : "=d" (current_tick), "=a" (tmp) - : "a" (cur_tsc), "r" (scale)); - - current_tick += offset; - if (tsc_pg->tsc_sequence == sequence) - return current_tick; - - if (tsc_pg->tsc_sequence != 0) - continue; - /* - * Fallback using MSR method. - */ - break; - } - } - rdmsrl(HV_X64_MSR_TIME_REF_COUNT, current_tick); return current_tick; } @@ -139,7 +116,7 @@ void hyperv_init(void) /* * Register Hyper-V specific clocksource. */ -#ifdef CONFIG_X86_64 +#ifdef CONFIG_HYPERV_TSCPAGE if (ms_hyperv.features & HV_X64_MSR_REFERENCE_TSC_AVAILABLE) { union hv_x64_msr_hypercall_contents tsc_msr; @@ -155,6 +132,9 @@ void hyperv_init(void) tsc_msr.guest_physical_address = vmalloc_to_pfn(tsc_pg); wrmsrl(HV_X64_MSR_REFERENCE_TSC, tsc_msr.as_uint64); + + hyperv_cs_tsc.archdata.vclock_mode = VCLOCK_HVCLOCK; + clocksource_register_hz(&hyperv_cs_tsc, NSEC_PER_SEC/100); return; } diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index 395b69551fce..2efc768e4362 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -52,6 +52,8 @@ extern u8 acpi_sci_flags; extern int acpi_sci_override_gsi; void acpi_pic_sci_set_trigger(unsigned int, u16); +struct device; + extern int (*__acpi_register_gsi)(struct device *dev, u32 gsi, int trigger, int polarity); extern void (*__acpi_unregister_gsi)(u32 gsi); diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 730ef65e8393..bdffcd9eab2b 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -252,12 +252,6 @@ static inline int x2apic_enabled(void) { return 0; } #define x2apic_supported() (0) #endif /* !CONFIG_X86_X2APIC */ -#ifdef CONFIG_X86_64 -#define SET_APIC_ID(x) (apic->set_apic_id(x)) -#else - -#endif - /* * Copyright 2004 James Cleverdon, IBM. * Subject to the GNU Public License, v.2 @@ -299,6 +293,7 @@ struct apic { int (*phys_pkg_id)(int cpuid_apic, int index_msb); unsigned int (*get_apic_id)(unsigned long x); + /* Can't be NULL on 64-bit */ unsigned long (*set_apic_id)(unsigned int id); int (*cpu_mask_to_apicid_and)(const struct cpumask *cpumask, diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h index 14635c5ea025..caa5798c92f4 100644 --- a/arch/x86/include/asm/atomic.h +++ b/arch/x86/include/asm/atomic.h @@ -186,6 +186,12 @@ static __always_inline int atomic_cmpxchg(atomic_t *v, int old, int new) return cmpxchg(&v->counter, old, new); } +#define atomic_try_cmpxchg atomic_try_cmpxchg +static __always_inline bool atomic_try_cmpxchg(atomic_t *v, int *old, int new) +{ + return try_cmpxchg(&v->counter, old, new); +} + static inline int atomic_xchg(atomic_t *v, int new) { return xchg(&v->counter, new); @@ -201,16 +207,12 @@ static inline void atomic_##op(int i, atomic_t *v) \ } #define ATOMIC_FETCH_OP(op, c_op) \ -static inline int atomic_fetch_##op(int i, atomic_t *v) \ +static inline int atomic_fetch_##op(int i, atomic_t *v) \ { \ - int old, val = atomic_read(v); \ - for (;;) { \ - old = atomic_cmpxchg(v, val, val c_op i); \ - if (old == val) \ - break; \ - val = old; \ - } \ - return old; \ + int val = atomic_read(v); \ + do { \ + } while (!atomic_try_cmpxchg(v, &val, val c_op i)); \ + return val; \ } #define ATOMIC_OPS(op, c_op) \ @@ -236,16 +238,11 @@ ATOMIC_OPS(xor, ^) */ static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u) { - int c, old; - c = atomic_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic_cmpxchg((v), c, c + (a)); - if (likely(old == c)) + int c = atomic_read(v); + do { + if (unlikely(c == u)) break; - c = old; - } + } while (!atomic_try_cmpxchg(v, &c, c + a)); return c; } diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h index 89ed2f6ae2f7..6189a433c9a9 100644 --- a/arch/x86/include/asm/atomic64_64.h +++ b/arch/x86/include/asm/atomic64_64.h @@ -176,6 +176,12 @@ static inline long atomic64_cmpxchg(atomic64_t *v, long old, long new) return cmpxchg(&v->counter, old, new); } +#define atomic64_try_cmpxchg atomic64_try_cmpxchg +static __always_inline bool atomic64_try_cmpxchg(atomic64_t *v, long *old, long new) +{ + return try_cmpxchg(&v->counter, old, new); +} + static inline long atomic64_xchg(atomic64_t *v, long new) { return xchg(&v->counter, new); @@ -192,17 +198,12 @@ 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, old; - c = atomic64_read(v); - for (;;) { - if (unlikely(c == (u))) - break; - old = atomic64_cmpxchg((v), c, c + (a)); - if (likely(old == c)) - break; - c = old; - } - return c != (u); + long c = atomic64_read(v); + do { + if (unlikely(c == u)) + return false; + } while (!atomic64_try_cmpxchg(v, &c, c + a)); + return true; } #define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) @@ -216,17 +217,12 @@ static inline bool atomic64_add_unless(atomic64_t *v, long a, long u) */ static inline long atomic64_dec_if_positive(atomic64_t *v) { - long c, old, dec; - c = atomic64_read(v); - for (;;) { + long dec, c = atomic64_read(v); + do { dec = c - 1; if (unlikely(dec < 0)) break; - old = atomic64_cmpxchg((v), c, dec); - if (likely(old == c)) - break; - c = old; - } + } while (!atomic64_try_cmpxchg(v, &c, dec)); return dec; } @@ -242,14 +238,10 @@ static inline void atomic64_##op(long i, atomic64_t *v) \ #define ATOMIC64_FETCH_OP(op, c_op) \ static inline long atomic64_fetch_##op(long i, atomic64_t *v) \ { \ - long old, val = atomic64_read(v); \ - for (;;) { \ - old = atomic64_cmpxchg(v, val, val c_op i); \ - if (old == val) \ - break; \ - val = old; \ - } \ - return old; \ + long val = atomic64_read(v); \ + do { \ + } while (!atomic64_try_cmpxchg(v, &val, val c_op i)); \ + return val; \ } #define ATOMIC64_OPS(op, c_op) \ diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h index ba38ebbaced3..39e702d90cdb 100644 --- a/arch/x86/include/asm/bug.h +++ b/arch/x86/include/asm/bug.h @@ -1,36 +1,82 @@ #ifndef _ASM_X86_BUG_H #define _ASM_X86_BUG_H -#define HAVE_ARCH_BUG +#include <linux/stringify.h> -#ifdef CONFIG_DEBUG_BUGVERBOSE +/* + * Since some emulators terminate on UD2, we cannot use it for WARN. + * Since various instruction decoders disagree on the length of UD1, + * we cannot use it either. So use UD0 for WARN. + * + * (binutils knows about "ud1" but {en,de}codes it as 2 bytes, whereas + * our kernel decoder thinks it takes a ModRM byte, which seems consistent + * with various things like the Intel SDM instruction encoding rules) + */ + +#define ASM_UD0 ".byte 0x0f, 0xff" +#define ASM_UD1 ".byte 0x0f, 0xb9" /* + ModRM */ +#define ASM_UD2 ".byte 0x0f, 0x0b" + +#define INSN_UD0 0xff0f +#define INSN_UD2 0x0b0f + +#define LEN_UD0 2 + +#ifdef CONFIG_GENERIC_BUG #ifdef CONFIG_X86_32 -# define __BUG_C0 "2:\t.long 1b, %c0\n" +# define __BUG_REL(val) ".long " __stringify(val) #else -# define __BUG_C0 "2:\t.long 1b - 2b, %c0 - 2b\n" +# define __BUG_REL(val) ".long " __stringify(val) " - 2b" #endif -#define BUG() \ -do { \ - asm volatile("1:\tud2\n" \ - ".pushsection __bug_table,\"a\"\n" \ - __BUG_C0 \ - "\t.word %c1, 0\n" \ - "\t.org 2b+%c2\n" \ - ".popsection" \ - : : "i" (__FILE__), "i" (__LINE__), \ - "i" (sizeof(struct bug_entry))); \ - unreachable(); \ +#ifdef CONFIG_DEBUG_BUGVERBOSE + +#define _BUG_FLAGS(ins, flags) \ +do { \ + asm volatile("1:\t" ins "\n" \ + ".pushsection __bug_table,\"a\"\n" \ + "2:\t" __BUG_REL(1b) "\t# bug_entry::bug_addr\n" \ + "\t" __BUG_REL(%c0) "\t# bug_entry::file\n" \ + "\t.word %c1" "\t# bug_entry::line\n" \ + "\t.word %c2" "\t# bug_entry::flags\n" \ + "\t.org 2b+%c3\n" \ + ".popsection" \ + : : "i" (__FILE__), "i" (__LINE__), \ + "i" (flags), \ + "i" (sizeof(struct bug_entry))); \ } while (0) +#else /* !CONFIG_DEBUG_BUGVERBOSE */ + +#define _BUG_FLAGS(ins, flags) \ +do { \ + asm volatile("1:\t" ins "\n" \ + ".pushsection __bug_table,\"a\"\n" \ + "2:\t" __BUG_REL(1b) "\t# bug_entry::bug_addr\n" \ + "\t.word %c0" "\t# bug_entry::flags\n" \ + "\t.org 2b+%c1\n" \ + ".popsection" \ + : : "i" (flags), \ + "i" (sizeof(struct bug_entry))); \ +} while (0) + +#endif /* CONFIG_DEBUG_BUGVERBOSE */ + #else + +#define _BUG_FLAGS(ins, flags) asm volatile(ins) + +#endif /* CONFIG_GENERIC_BUG */ + +#define HAVE_ARCH_BUG #define BUG() \ do { \ - asm volatile("ud2"); \ + _BUG_FLAGS(ASM_UD2, 0); \ unreachable(); \ } while (0) -#endif + +#define __WARN_FLAGS(flags) _BUG_FLAGS(ASM_UD0, BUGFLAG_WARNING|(flags)) #include <asm-generic/bug.h> diff --git a/arch/x86/include/asm/clocksource.h b/arch/x86/include/asm/clocksource.h index eae33c7170c8..47bea8cadbd0 100644 --- a/arch/x86/include/asm/clocksource.h +++ b/arch/x86/include/asm/clocksource.h @@ -6,7 +6,8 @@ #define VCLOCK_NONE 0 /* No vDSO clock available. */ #define VCLOCK_TSC 1 /* vDSO should use vread_tsc. */ #define VCLOCK_PVCLOCK 2 /* vDSO should use vread_pvclock. */ -#define VCLOCK_MAX 2 +#define VCLOCK_HVCLOCK 3 /* vDSO should use vread_hvclock. */ +#define VCLOCK_MAX 3 struct arch_clocksource_data { int vclock_mode; diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h index 97848cdfcb1a..d90296d061e8 100644 --- a/arch/x86/include/asm/cmpxchg.h +++ b/arch/x86/include/asm/cmpxchg.h @@ -153,6 +153,76 @@ extern void __add_wrong_size(void) #define cmpxchg_local(ptr, old, new) \ __cmpxchg_local(ptr, old, new, sizeof(*(ptr))) + +#define __raw_try_cmpxchg(_ptr, _pold, _new, size, lock) \ +({ \ + bool success; \ + __typeof__(_ptr) _old = (_pold); \ + __typeof__(*(_ptr)) __old = *_old; \ + __typeof__(*(_ptr)) __new = (_new); \ + switch (size) { \ + case __X86_CASE_B: \ + { \ + volatile u8 *__ptr = (volatile u8 *)(_ptr); \ + asm volatile(lock "cmpxchgb %[new], %[ptr]" \ + CC_SET(z) \ + : CC_OUT(z) (success), \ + [ptr] "+m" (*__ptr), \ + [old] "+a" (__old) \ + : [new] "q" (__new) \ + : "memory"); \ + break; \ + } \ + case __X86_CASE_W: \ + { \ + volatile u16 *__ptr = (volatile u16 *)(_ptr); \ + asm volatile(lock "cmpxchgw %[new], %[ptr]" \ + CC_SET(z) \ + : CC_OUT(z) (success), \ + [ptr] "+m" (*__ptr), \ + [old] "+a" (__old) \ + : [new] "r" (__new) \ + : "memory"); \ + break; \ + } \ + case __X86_CASE_L: \ + { \ + volatile u32 *__ptr = (volatile u32 *)(_ptr); \ + asm volatile(lock "cmpxchgl %[new], %[ptr]" \ + CC_SET(z) \ + : CC_OUT(z) (success), \ + [ptr] "+m" (*__ptr), \ + [old] "+a" (__old) \ + : [new] "r" (__new) \ + : "memory"); \ + break; \ + } \ + case __X86_CASE_Q: \ + { \ + volatile u64 *__ptr = (volatile u64 *)(_ptr); \ + asm volatile(lock "cmpxchgq %[new], %[ptr]" \ + CC_SET(z) \ + : CC_OUT(z) (success), \ + [ptr] "+m" (*__ptr), \ + [old] "+a" (__old) \ + : [new] "r" (__new) \ + : "memory"); \ + break; \ + } \ + default: \ + __cmpxchg_wrong_size(); \ + } \ + if (unlikely(!success)) \ + *_old = __old; \ + likely(success); \ +}) + +#define __try_cmpxchg(ptr, pold, new, size) \ + __raw_try_cmpxchg((ptr), (pold), (new), (size), LOCK_PREFIX) + +#define try_cmpxchg(ptr, pold, new) \ + __try_cmpxchg((ptr), (pold), (new), sizeof(*(ptr))) + /* * xadd() adds "inc" to "*ptr" and atomically returns the previous * value of "*ptr". diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index b04bb6dfed7f..2701e5f8145b 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -187,6 +187,7 @@ * Reuse free bits when adding new feature flags! */ #define X86_FEATURE_RING3MWAIT ( 7*32+ 0) /* Ring 3 MONITOR/MWAIT */ +#define X86_FEATURE_CPUID_FAULT ( 7*32+ 1) /* Intel CPUID faulting */ #define X86_FEATURE_CPB ( 7*32+ 2) /* AMD Core Performance Boost */ #define X86_FEATURE_EPB ( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */ #define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* Cache Allocation Technology L3 */ @@ -201,6 +202,8 @@ #define X86_FEATURE_AVX512_4VNNIW (7*32+16) /* AVX-512 Neural Network Instructions */ #define X86_FEATURE_AVX512_4FMAPS (7*32+17) /* AVX-512 Multiply Accumulation Single precision */ +#define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */ + /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ #define X86_FEATURE_VNMI ( 8*32+ 1) /* Intel Virtual NMI */ diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index 1548ca92ad3f..d0a21b12dd58 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -4,6 +4,7 @@ #include <asm/desc_defs.h> #include <asm/ldt.h> #include <asm/mmu.h> +#include <asm/fixmap.h> #include <linux/smp.h> #include <linux/percpu.h> @@ -45,11 +46,43 @@ struct gdt_page { DECLARE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page); -static inline struct desc_struct *get_cpu_gdt_table(unsigned int cpu) +/* Provide the original GDT */ +static inline struct desc_struct *get_cpu_gdt_rw(unsigned int cpu) { return per_cpu(gdt_page, cpu).gdt; } +/* Provide the current original GDT */ +static inline struct desc_struct *get_current_gdt_rw(void) +{ + return this_cpu_ptr(&gdt_page)->gdt; +} + +/* Get the fixmap index for a specific processor */ +static inline unsigned int get_cpu_gdt_ro_index(int cpu) +{ + return FIX_GDT_REMAP_BEGIN + cpu; +} + +/* Provide the fixmap address of the remapped GDT */ +static inline struct desc_struct *get_cpu_gdt_ro(int cpu) +{ + unsigned int idx = get_cpu_gdt_ro_index(cpu); + return (struct desc_struct *)__fix_to_virt(idx); +} + +/* Provide the current read-only GDT */ +static inline struct desc_struct *get_current_gdt_ro(void) +{ + return get_cpu_gdt_ro(smp_processor_id()); +} + +/* Provide the physical address of the GDT page. */ +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, @@ -174,7 +207,7 @@ static inline void set_tssldt_descriptor(void *d, unsigned long addr, unsigned t static inline void __set_tss_desc(unsigned cpu, unsigned int entry, void *addr) { - struct desc_struct *d = get_cpu_gdt_table(cpu); + struct desc_struct *d = get_cpu_gdt_rw(cpu); tss_desc tss; set_tssldt_descriptor(&tss, (unsigned long)addr, DESC_TSS, @@ -194,22 +227,90 @@ static inline void native_set_ldt(const void *addr, unsigned int entries) set_tssldt_descriptor(&ldt, (unsigned long)addr, DESC_LDT, entries * LDT_ENTRY_SIZE - 1); - write_gdt_entry(get_cpu_gdt_table(cpu), GDT_ENTRY_LDT, + write_gdt_entry(get_cpu_gdt_rw(cpu), GDT_ENTRY_LDT, &ldt, DESC_LDT); asm volatile("lldt %w0"::"q" (GDT_ENTRY_LDT*8)); } } +static inline void native_load_gdt(const struct desc_ptr *dtr) +{ + asm volatile("lgdt %0"::"m" (*dtr)); +} + +static inline void native_load_idt(const struct desc_ptr *dtr) +{ + asm volatile("lidt %0"::"m" (*dtr)); +} + +static inline void native_store_gdt(struct desc_ptr *dtr) +{ + asm volatile("sgdt %0":"=m" (*dtr)); +} + +static inline void native_store_idt(struct desc_ptr *dtr) +{ + asm volatile("sidt %0":"=m" (*dtr)); +} + +/* + * The LTR instruction marks the TSS GDT entry as busy. On 64-bit, the GDT is + * a read-only remapping. To prevent a page fault, the GDT is switched to the + * original writeable version when needed. + */ +#ifdef CONFIG_X86_64 +static inline void native_load_tr_desc(void) +{ + struct desc_ptr gdt; + int cpu = raw_smp_processor_id(); + bool restore = 0; + struct desc_struct *fixmap_gdt; + + native_store_gdt(&gdt); + fixmap_gdt = get_cpu_gdt_ro(cpu); + + /* + * If the current GDT is the read-only fixmap, swap to the original + * writeable version. Swap back at the end. + */ + if (gdt.address == (unsigned long)fixmap_gdt) { + load_direct_gdt(cpu); + restore = 1; + } + asm volatile("ltr %w0"::"q" (GDT_ENTRY_TSS*8)); + if (restore) + load_fixmap_gdt(cpu); +} +#else static inline void native_load_tr_desc(void) { asm volatile("ltr %w0"::"q" (GDT_ENTRY_TSS*8)); } +#endif + +static inline unsigned long native_store_tr(void) +{ + unsigned long tr; + + asm volatile("str %0":"=r" (tr)); + + return tr; +} + +static inline void native_load_tls(struct thread_struct *t, unsigned int cpu) +{ + struct desc_struct *gdt = get_cpu_gdt_rw(cpu); + unsigned int i; + + for (i = 0; i < GDT_ENTRY_TLS_ENTRIES; i++) + gdt[GDT_ENTRY_TLS_MIN + i] = t->tls_array[i]; +} DECLARE_PER_CPU(bool, __tss_limit_invalid); static inline void force_reload_TR(void) { - struct desc_struct *d = get_cpu_gdt_table(smp_processor_id()); + struct desc_struct *d = get_current_gdt_rw(); tss_desc tss; memcpy(&tss, &d[GDT_ENTRY_TSS], sizeof(tss_desc)); @@ -257,44 +358,6 @@ static inline void invalidate_tss_limit(void) this_cpu_write(__tss_limit_invalid, true); } -static inline void native_load_gdt(const struct desc_ptr *dtr) -{ - asm volatile("lgdt %0"::"m" (*dtr)); -} - -static inline void native_load_idt(const struct desc_ptr *dtr) -{ - asm volatile("lidt %0"::"m" (*dtr)); -} - -static inline void native_store_gdt(struct desc_ptr *dtr) -{ - asm volatile("sgdt %0":"=m" (*dtr)); -} - -static inline void native_store_idt(struct desc_ptr *dtr) -{ - asm volatile("sidt %0":"=m" (*dtr)); -} - -static inline unsigned long native_store_tr(void) -{ - unsigned long tr; - - asm volatile("str %0":"=r" (tr)); - - return tr; -} - -static inline void native_load_tls(struct thread_struct *t, unsigned int cpu) -{ - struct desc_struct *gdt = get_cpu_gdt_table(cpu); - unsigned int i; - - for (i = 0; i < GDT_ENTRY_TLS_ENTRIES; i++) - gdt[GDT_ENTRY_TLS_MIN + i] = t->tls_array[i]; -} - /* This intentionally ignores lm, since 32-bit apps don't have that field. */ #define LDT_empty(info) \ ((info)->base_addr == 0 && \ diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index 85599ad4d024..5dff775af7cd 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -36,6 +36,12 @@ # define DISABLE_OSPKE (1<<(X86_FEATURE_OSPKE & 31)) #endif /* CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS */ +#ifdef CONFIG_X86_5LEVEL +# define DISABLE_LA57 0 +#else +# define DISABLE_LA57 (1<<(X86_FEATURE_LA57 & 31)) +#endif + /* * Make sure to add features to the correct mask */ @@ -55,7 +61,7 @@ #define DISABLED_MASK13 0 #define DISABLED_MASK14 0 #define DISABLED_MASK15 0 -#define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE) +#define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57) #define DISABLED_MASK17 0 #define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18) diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h deleted file mode 100644 index 67313f3a9874..000000000000 --- a/arch/x86/include/asm/e820.h +++ /dev/null @@ -1,73 +0,0 @@ -#ifndef _ASM_X86_E820_H -#define _ASM_X86_E820_H - -/* - * E820_X_MAX is the maximum size of the extended E820 table. The extended - * table may contain up to 3 extra E820 entries per possible NUMA node, so we - * make room for 3 * MAX_NUMNODES possible entries, beyond the standard 128. - * Also note that E820_X_MAX *must* be defined before we include uapi/asm/e820.h. - */ -#include <linux/numa.h> -#define E820_X_MAX (E820MAX + 3 * MAX_NUMNODES) - -#include <uapi/asm/e820.h> - -#ifndef __ASSEMBLY__ -/* see comment in arch/x86/kernel/e820.c */ -extern struct e820map *e820; -extern struct e820map *e820_saved; - -extern unsigned long pci_mem_start; -extern int e820_any_mapped(u64 start, u64 end, unsigned type); -extern int e820_all_mapped(u64 start, u64 end, unsigned type); -extern void e820_add_region(u64 start, u64 size, int type); -extern void e820_print_map(char *who); -extern int -sanitize_e820_map(struct e820entry *biosmap, int max_nr_map, u32 *pnr_map); -extern u64 e820_update_range(u64 start, u64 size, unsigned old_type, - unsigned new_type); -extern u64 e820_remove_range(u64 start, u64 size, unsigned old_type, - int checktype); -extern void update_e820(void); -extern void e820_setup_gap(void); -struct setup_data; -extern void parse_e820_ext(u64 phys_addr, u32 data_len); - -#if defined(CONFIG_X86_64) || \ - (defined(CONFIG_X86_32) && defined(CONFIG_HIBERNATION)) -extern void e820_mark_nosave_regions(unsigned long limit_pfn); -#else -static inline void e820_mark_nosave_regions(unsigned long limit_pfn) -{ -} -#endif - -extern unsigned long e820_end_of_ram_pfn(void); -extern unsigned long e820_end_of_low_ram_pfn(void); -extern u64 early_reserve_e820(u64 sizet, u64 align); - -void memblock_x86_fill(void); -void memblock_find_dma_reserve(void); - -extern void finish_e820_parsing(void); -extern void e820_reserve_resources(void); -extern void e820_reserve_resources_late(void); -extern void setup_memory_map(void); -extern char *default_machine_specific_memory_setup(void); - -extern void e820_reallocate_tables(void); - -/* - * Returns true iff the specified range [s,e) is completely contained inside - * the ISA region. - */ -static inline bool is_ISA_range(u64 s, u64 e) -{ - return s >= ISA_START_ADDRESS && e <= ISA_END_ADDRESS; -} - -#endif /* __ASSEMBLY__ */ -#include <linux/ioport.h> - -#define HIGH_MEMORY (1024*1024) -#endif /* _ASM_X86_E820_H */ diff --git a/arch/x86/include/asm/e820/api.h b/arch/x86/include/asm/e820/api.h new file mode 100644 index 000000000000..8e0f8b85b209 --- /dev/null +++ b/arch/x86/include/asm/e820/api.h @@ -0,0 +1,50 @@ +#ifndef _ASM_E820_API_H +#define _ASM_E820_API_H + +#include <asm/e820/types.h> + +extern struct e820_table *e820_table; +extern struct e820_table *e820_table_firmware; + +extern unsigned long pci_mem_start; + +extern bool e820__mapped_any(u64 start, u64 end, enum e820_type type); +extern bool e820__mapped_all(u64 start, u64 end, enum e820_type type); + +extern void e820__range_add (u64 start, u64 size, enum e820_type type); +extern u64 e820__range_update(u64 start, u64 size, enum e820_type old_type, enum e820_type new_type); +extern u64 e820__range_remove(u64 start, u64 size, enum e820_type old_type, bool check_type); + +extern void e820__print_table(char *who); +extern int e820__update_table(struct e820_table *table); +extern void e820__update_table_print(void); + +extern unsigned long e820__end_of_ram_pfn(void); +extern unsigned long e820__end_of_low_ram_pfn(void); + +extern u64 e820__memblock_alloc_reserved(u64 size, u64 align); +extern void e820__memblock_setup(void); + +extern void e820__reserve_setup_data(void); +extern void e820__finish_early_params(void); +extern void e820__reserve_resources(void); +extern void e820__reserve_resources_late(void); + +extern void e820__memory_setup(void); +extern void e820__memory_setup_extended(u64 phys_addr, u32 data_len); +extern char *e820__memory_setup_default(void); +extern void e820__setup_pci_gap(void); + +extern void e820__reallocate_tables(void); +extern void e820__register_nosave_regions(unsigned long limit_pfn); + +/* + * Returns true iff the specified range [start,end) is completely contained inside + * the ISA region. + */ +static inline bool is_ISA_range(u64 start, u64 end) +{ + return start >= ISA_START_ADDRESS && end <= ISA_END_ADDRESS; +} + +#endif /* _ASM_E820_API_H */ diff --git a/arch/x86/include/asm/e820/types.h b/arch/x86/include/asm/e820/types.h new file mode 100644 index 000000000000..4adeed03a9a1 --- /dev/null +++ b/arch/x86/include/asm/e820/types.h @@ -0,0 +1,104 @@ +#ifndef _ASM_E820_TYPES_H +#define _ASM_E820_TYPES_H + +#include <uapi/asm/bootparam.h> + +/* + * These are the E820 types known to the kernel: + */ +enum e820_type { + E820_TYPE_RAM = 1, + E820_TYPE_RESERVED = 2, + E820_TYPE_ACPI = 3, + E820_TYPE_NVS = 4, + E820_TYPE_UNUSABLE = 5, + E820_TYPE_PMEM = 7, + + /* + * This is a non-standardized way to represent ADR or + * NVDIMM regions that persist over a reboot. + * + * The kernel will ignore their special capabilities + * unless the CONFIG_X86_PMEM_LEGACY=y option is set. + * + * ( Note that older platforms also used 6 for the same + * type of memory, but newer versions switched to 12 as + * 6 was assigned differently. Some time they will learn... ) + */ + E820_TYPE_PRAM = 12, + + /* + * Reserved RAM used by the kernel itself if + * CONFIG_INTEL_TXT=y is enabled, memory of this type + * will be included in the S3 integrity calculation + * and so should not include any memory that the BIOS + * might alter over the S3 transition: + */ + E820_TYPE_RESERVED_KERN = 128, +}; + +/* + * A single E820 map entry, describing a memory range of [addr...addr+size-1], + * of 'type' memory type: + * + * (We pack it because there can be thousands of them on large systems.) + */ +struct e820_entry { + u64 addr; + u64 size; + enum e820_type type; +} __attribute__((packed)); + +/* + * The legacy E820 BIOS limits us to 128 (E820_MAX_ENTRIES_ZEROPAGE) nodes + * due to the constrained space in the zeropage. + * + * On large systems we can easily have thousands of nodes with RAM, + * which cannot be fit into so few entries - so we have a mechanism + * to extend the e820 table size at build-time, via the E820_MAX_ENTRIES + * define below. + * + * ( Those extra entries are enumerated via the EFI memory map, not + * via the legacy zeropage mechanism. ) + * + * Size our internal memory map tables to have room for these additional + * entries, based on a heuristic calculation: up to three entries per + * NUMA node, plus E820_MAX_ENTRIES_ZEROPAGE for some extra space. + * + * This allows for bootstrap/firmware quirks such as possible duplicate + * E820 entries that might need room in the same arrays, prior to the + * call to e820__update_table() to remove duplicates. The allowance + * of three memory map entries per node is "enough" entries for + * the initial hardware platform motivating this mechanism to make + * use of additional EFI map entries. Future platforms may want + * to allow more than three entries per node or otherwise refine + * this size. + */ + +#include <linux/numa.h> + +#define E820_MAX_ENTRIES (E820_MAX_ENTRIES_ZEROPAGE + 3*MAX_NUMNODES) + +/* + * The whole array of E820 entries: + */ +struct e820_table { + __u32 nr_entries; + struct e820_entry entries[E820_MAX_ENTRIES]; +}; + +/* + * Various well-known legacy memory ranges in physical memory: + */ +#define ISA_START_ADDRESS 0x000a0000 +#define ISA_END_ADDRESS 0x00100000 + +#define BIOS_BEGIN 0x000a0000 +#define BIOS_END 0x00100000 + +#define HIGH_MEMORY 0x00100000 + +#define BIOS_ROM_BASE 0xffe00000 +#define BIOS_ROM_END 0xffffffff + +#endif /* _ASM_E820_TYPES_H */ diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index 9d49c18b5ea9..e8ab9a46bc68 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -287,14 +287,29 @@ struct task_struct; #define ARCH_DLINFO_IA32 \ do { \ - if (vdso32_enabled) { \ + if (VDSO_CURRENT_BASE) { \ NEW_AUX_ENT(AT_SYSINFO, VDSO_ENTRY); \ NEW_AUX_ENT(AT_SYSINFO_EHDR, VDSO_CURRENT_BASE); \ } \ } while (0) +/* + * True on X86_32 or when emulating IA32 on X86_64 + */ +static inline int mmap_is_ia32(void) +{ + return IS_ENABLED(CONFIG_X86_32) || + (IS_ENABLED(CONFIG_COMPAT) && + test_thread_flag(TIF_ADDR32)); +} + +extern unsigned long tasksize_32bit(void); +extern unsigned long tasksize_64bit(void); +extern unsigned long get_mmap_base(int is_legacy); + #ifdef CONFIG_X86_32 +#define __STACK_RND_MASK(is32bit) (0x7ff) #define STACK_RND_MASK (0x7ff) #define ARCH_DLINFO ARCH_DLINFO_IA32 @@ -304,7 +319,8 @@ do { \ #else /* CONFIG_X86_32 */ /* 1GB for 64bit, 8MB for 32bit */ -#define STACK_RND_MASK (test_thread_flag(TIF_ADDR32) ? 0x7ff : 0x3fffff) +#define __STACK_RND_MASK(is32bit) ((is32bit) ? 0x7ff : 0x3fffff) +#define STACK_RND_MASK __STACK_RND_MASK(mmap_is_ia32()) #define ARCH_DLINFO \ do { \ @@ -348,16 +364,6 @@ extern int compat_arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp); #define compat_arch_setup_additional_pages compat_arch_setup_additional_pages -/* - * True on X86_32 or when emulating IA32 on X86_64 - */ -static inline int mmap_is_ia32(void) -{ - return IS_ENABLED(CONFIG_X86_32) || - (IS_ENABLED(CONFIG_COMPAT) && - test_thread_flag(TIF_ADDR32)); -} - /* Do not change the values. See get_align_mask() */ enum align_flags { ALIGN_VA_32 = BIT(0), diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index 8554f960e21b..b65155cc3760 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -100,6 +100,10 @@ enum fixed_addresses { #ifdef CONFIG_X86_INTEL_MID FIX_LNW_VRTC, #endif + /* Fixmap entries to remap the GDTs, one per processor. */ + FIX_GDT_REMAP_BEGIN, + FIX_GDT_REMAP_END = FIX_GDT_REMAP_BEGIN + NR_CPUS - 1, + __end_of_permanent_fixed_addresses, /* diff --git a/arch/x86/include/asm/gart.h b/arch/x86/include/asm/gart.h index 156cd5d18d2a..1d268098ac2e 100644 --- a/arch/x86/include/asm/gart.h +++ b/arch/x86/include/asm/gart.h @@ -1,7 +1,7 @@ #ifndef _ASM_X86_GART_H #define _ASM_X86_GART_H -#include <asm/e820.h> +#include <asm/e820/api.h> extern void set_up_gart_resume(u32, u32); @@ -97,7 +97,7 @@ static inline int aperture_valid(u64 aper_base, u32 aper_size, u32 min_size) printk(KERN_INFO "Aperture beyond 4GB. Ignoring.\n"); return 0; } - if (e820_any_mapped(aper_base, aper_base + aper_size, E820_RAM)) { + if (e820__mapped_any(aper_base, aper_base + aper_size, E820_TYPE_RAM)) { printk(KERN_INFO "Aperture pointing to e820 RAM. Ignoring.\n"); return 0; } diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 9814db42b790..75b748a1deb8 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -12,6 +12,7 @@ */ #define INTEL_FAM6_CORE_YONAH 0x0E + #define INTEL_FAM6_CORE2_MEROM 0x0F #define INTEL_FAM6_CORE2_MEROM_L 0x16 #define INTEL_FAM6_CORE2_PENRYN 0x17 @@ -21,6 +22,7 @@ #define INTEL_FAM6_NEHALEM_G 0x1F /* Auburndale / Havendale */ #define INTEL_FAM6_NEHALEM_EP 0x1A #define INTEL_FAM6_NEHALEM_EX 0x2E + #define INTEL_FAM6_WESTMERE 0x25 #define INTEL_FAM6_WESTMERE_EP 0x2C #define INTEL_FAM6_WESTMERE_EX 0x2F @@ -36,9 +38,9 @@ #define INTEL_FAM6_HASWELL_GT3E 0x46 #define INTEL_FAM6_BROADWELL_CORE 0x3D -#define INTEL_FAM6_BROADWELL_XEON_D 0x56 #define INTEL_FAM6_BROADWELL_GT3E 0x47 #define INTEL_FAM6_BROADWELL_X 0x4F +#define INTEL_FAM6_BROADWELL_XEON_D 0x56 #define INTEL_FAM6_SKYLAKE_MOBILE 0x4E #define INTEL_FAM6_SKYLAKE_DESKTOP 0x5E @@ -59,8 +61,8 @@ #define INTEL_FAM6_ATOM_MERRIFIELD 0x4A /* Tangier */ #define INTEL_FAM6_ATOM_MOOREFIELD 0x5A /* Anniedale */ #define INTEL_FAM6_ATOM_GOLDMONT 0x5C -#define INTEL_FAM6_ATOM_GEMINI_LAKE 0x7A #define INTEL_FAM6_ATOM_DENVERTON 0x5F /* Goldmont Microserver */ +#define INTEL_FAM6_ATOM_GEMINI_LAKE 0x7A /* Xeon Phi */ diff --git a/arch/x86/include/asm/intel_rdt.h b/arch/x86/include/asm/intel_rdt.h index 0d64397cee58..597dc4995678 100644 --- a/arch/x86/include/asm/intel_rdt.h +++ b/arch/x86/include/asm/intel_rdt.h @@ -12,6 +12,7 @@ #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 @@ -37,23 +38,30 @@ struct rdtgroup { /* 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: operations - * @seq_show: show content of the file - * @write: write to the file + * @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); @@ -67,54 +75,21 @@ struct rftype { }; /** - * 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 - * @max_cbm: Largest Cache Bit Mask allowed - * @min_cbm_bits: Minimum number of consecutive bits to be set - * in a cache bit mask - * @domains: All domains for this resource - * @num_domains: Number of domains active - * @msr_base: Base MSR address for CBMs - * @tmp_cbms: Scratch space when updating schemata - * @num_tmp_cbms: Number of CBMs in tmp_cbms - * @cache_level: Which cache level defines scope of this domain - * @cbm_idx_multi: Multiplier of CBM index - * @cbm_idx_offset: Offset of CBM index. CBM index is computed by: - * closid * cbm_idx_multi + cbm_idx_offset - */ -struct rdt_resource { - bool enabled; - bool capable; - char *name; - int num_closid; - int cbm_len; - int min_cbm_bits; - u32 max_cbm; - struct list_head domains; - int num_domains; - int msr_base; - u32 *tmp_cbms; - int num_tmp_cbms; - int cache_level; - int cbm_idx_multi; - int cbm_idx_offset; -}; - -/** * 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 - * @cbm: array of cache bit masks (indexed by CLOSID) + * @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 *cbm; + u32 *ctrl_val; + u32 new_ctrl; + bool have_new_ctrl; }; /** @@ -129,6 +104,83 @@ struct msr_param { 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[]; @@ -142,6 +194,7 @@ enum { RDT_RESOURCE_L3DATA, RDT_RESOURCE_L3CODE, RDT_RESOURCE_L2, + RDT_RESOURCE_MBA, /* Must be the last */ RDT_NUM_RESOURCES, @@ -149,7 +202,7 @@ enum { #define for_each_capable_rdt_resource(r) \ for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\ - r++) \ + r++) \ if (r->capable) #define for_each_enabled_rdt_resource(r) \ @@ -165,8 +218,16 @@ union cpuid_0x10_1_eax { unsigned int full; }; -/* CPUID.(EAX=10H, ECX=ResID=1).EDX */ -union cpuid_0x10_1_edx { +/* 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; @@ -175,7 +236,7 @@ union cpuid_0x10_1_edx { DECLARE_PER_CPU_READ_MOSTLY(int, cpu_closid); -void rdt_cbm_update(void *arg); +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, diff --git a/arch/x86/include/asm/kasan.h b/arch/x86/include/asm/kasan.h index 1410b567ecde..f527b02a0ee3 100644 --- a/arch/x86/include/asm/kasan.h +++ b/arch/x86/include/asm/kasan.h @@ -11,9 +11,12 @@ * 'kernel address space start' >> KASAN_SHADOW_SCALE_SHIFT */ #define KASAN_SHADOW_START (KASAN_SHADOW_OFFSET + \ - (0xffff800000000000ULL >> 3)) -/* 47 bits for kernel address -> (47 - 3) bits for shadow */ -#define KASAN_SHADOW_END (KASAN_SHADOW_START + (1ULL << (47 - 3))) + ((-1UL << __VIRTUAL_MASK_SHIFT) >> 3)) +/* + * 47 bits for kernel address -> (47 - 3) bits for shadow + * 56 bits for kernel address -> (56 - 3) bits for shadow + */ +#define KASAN_SHADOW_END (KASAN_SHADOW_START + (1ULL << (__VIRTUAL_MASK_SHIFT - 3))) #ifndef __ASSEMBLY__ diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h index 282630e4c6ea..70ef205489f0 100644 --- a/arch/x86/include/asm/kexec.h +++ b/arch/x86/include/asm/kexec.h @@ -164,6 +164,7 @@ struct kimage_arch { }; #else struct kimage_arch { + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h index 200581691c6e..34b984c60790 100644 --- a/arch/x86/include/asm/kprobes.h +++ b/arch/x86/include/asm/kprobes.h @@ -72,14 +72,13 @@ struct arch_specific_insn { /* copy of the original instruction */ kprobe_opcode_t *insn; /* - * boostable = -1: This instruction type is not boostable. - * boostable = 0: This instruction type is boostable. - * boostable = 1: This instruction has been boosted: we have + * boostable = false: This instruction type is not boostable. + * boostable = true: This instruction has been boosted: we have * added a relative jump after the instruction copy in insn, * so no single-step and fixup are needed (unless there's * a post_handler or break_handler). */ - int boostable; + bool boostable; bool if_modifier; }; diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index e63873683d4a..4fd5195deed0 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -128,7 +128,7 @@ * debugging tools. Each entry is only valid when its finished flag * is set. */ -struct mce_log { +struct mce_log_buffer { char signature[12]; /* "MACHINECHECK" */ unsigned len; /* = MCE_LOG_LEN */ unsigned next; @@ -191,10 +191,12 @@ extern struct mca_config mca_cfg; extern struct mca_msr_regs msr_ops; enum mce_notifier_prios { - MCE_PRIO_SRAO = INT_MAX, - MCE_PRIO_EXTLOG = INT_MAX - 1, - MCE_PRIO_NFIT = INT_MAX - 2, - MCE_PRIO_EDAC = INT_MAX - 3, + MCE_PRIO_FIRST = INT_MAX, + MCE_PRIO_SRAO = INT_MAX - 1, + MCE_PRIO_EXTLOG = INT_MAX - 2, + MCE_PRIO_NFIT = INT_MAX - 3, + MCE_PRIO_EDAC = INT_MAX - 4, + MCE_PRIO_MCELOG = 1, MCE_PRIO_LOWEST = 0, }; diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 306c7e12af55..68b329d77b3a 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -268,8 +268,4 @@ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma, return __pkru_allows_pkey(vma_pkey(vma), write); } -static inline bool arch_pte_access_permitted(pte_t pte, bool write) -{ - return __pkru_allows_pkey(pte_flags_pkey(pte_flags(pte)), write); -} #endif /* _ASM_X86_MMU_CONTEXT_H */ diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h index 32007041ef8c..831eb7895535 100644 --- a/arch/x86/include/asm/mpspec.h +++ b/arch/x86/include/asm/mpspec.h @@ -64,7 +64,7 @@ static inline void find_smp_config(void) } #ifdef CONFIG_X86_MPPARSE -extern void early_reserve_e820_mpc_new(void); +extern void e820__memblock_alloc_reserved_mpc_new(void); extern int enable_update_mptable; extern int default_mpc_apic_id(struct mpc_cpu *m); extern void default_smp_read_mpc_oem(struct mpc_table *mpc); @@ -76,7 +76,7 @@ extern void default_mpc_oem_bus_info(struct mpc_bus *m, char *str); extern void default_find_smp_config(void); extern void default_get_smp_config(unsigned int early); #else -static inline void early_reserve_e820_mpc_new(void) { } +static inline void e820__memblock_alloc_reserved_mpc_new(void) { } #define enable_update_mptable 0 #define default_mpc_apic_id NULL #define default_smp_read_mpc_oem NULL diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 7c9c895432a9..fba100713924 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -176,4 +176,58 @@ void hyperv_report_panic(struct pt_regs *regs); bool hv_is_hypercall_page_setup(void); void hyperv_cleanup(void); #endif +#ifdef CONFIG_HYPERV_TSCPAGE +struct ms_hyperv_tsc_page *hv_get_tsc_page(void); +static inline u64 hv_read_tsc_page(const struct ms_hyperv_tsc_page *tsc_pg) +{ + u64 scale, offset, cur_tsc; + u32 sequence; + + /* + * The protocol for reading Hyper-V TSC page is specified in Hypervisor + * Top-Level Functional Specification ver. 3.0 and above. To get the + * reference time we must do the following: + * - READ ReferenceTscSequence + * A special '0' value indicates the time source is unreliable and we + * need to use something else. The currently published specification + * versions (up to 4.0b) contain a mistake and wrongly claim '-1' + * instead of '0' as the special value, see commit c35b82ef0294. + * - ReferenceTime = + * ((RDTSC() * ReferenceTscScale) >> 64) + ReferenceTscOffset + * - READ ReferenceTscSequence again. In case its value has changed + * since our first reading we need to discard ReferenceTime and repeat + * the whole sequence as the hypervisor was updating the page in + * between. + */ + do { + sequence = READ_ONCE(tsc_pg->tsc_sequence); + if (!sequence) + return U64_MAX; + /* + * Make sure we read sequence before we read other values from + * TSC page. + */ + smp_rmb(); + + scale = READ_ONCE(tsc_pg->tsc_scale); + offset = READ_ONCE(tsc_pg->tsc_offset); + cur_tsc = rdtsc_ordered(); + + /* + * Make sure we read sequence after we read all other values + * from TSC page. + */ + smp_rmb(); + + } while (READ_ONCE(tsc_pg->tsc_sequence) != sequence); + + return mul_u64_u64_shr(cur_tsc, scale, 64) + offset; +} + +#else +static inline struct ms_hyperv_tsc_page *hv_get_tsc_page(void) +{ + return NULL; +} +#endif #endif diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index d8b5f8ab8ef9..673f9ac50f6d 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -45,6 +45,8 @@ #define MSR_IA32_PERFCTR1 0x000000c2 #define MSR_FSB_FREQ 0x000000cd #define MSR_PLATFORM_INFO 0x000000ce +#define MSR_PLATFORM_INFO_CPUID_FAULT_BIT 31 +#define MSR_PLATFORM_INFO_CPUID_FAULT BIT_ULL(MSR_PLATFORM_INFO_CPUID_FAULT_BIT) #define MSR_PKG_CST_CONFIG_CONTROL 0x000000e2 #define NHM_C3_AUTO_DEMOTE (1UL << 25) @@ -127,6 +129,7 @@ /* DEBUGCTLMSR bits (others vary by model): */ #define DEBUGCTLMSR_LBR (1UL << 0) /* last branch recording */ +#define DEBUGCTLMSR_BTF_SHIFT 1 #define DEBUGCTLMSR_BTF (1UL << 1) /* single-step on branches */ #define DEBUGCTLMSR_TR (1UL << 6) #define DEBUGCTLMSR_BTS (1UL << 7) @@ -552,10 +555,12 @@ #define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT 39 #define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT) -/* MISC_FEATURE_ENABLES non-architectural features */ -#define MSR_MISC_FEATURE_ENABLES 0x00000140 +/* MISC_FEATURES_ENABLES non-architectural features */ +#define MSR_MISC_FEATURES_ENABLES 0x00000140 -#define MSR_MISC_FEATURE_ENABLES_RING3MWAIT_BIT 1 +#define MSR_MISC_FEATURES_ENABLES_CPUID_FAULT_BIT 0 +#define MSR_MISC_FEATURES_ENABLES_CPUID_FAULT BIT_ULL(MSR_MISC_FEATURES_ENABLES_CPUID_FAULT_BIT) +#define MSR_MISC_FEATURES_ENABLES_RING3MWAIT_BIT 1 #define MSR_IA32_TSC_DEADLINE 0x000006E0 diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h index b3bebf9e5746..b4a0d43248cf 100644 --- a/arch/x86/include/asm/page_64.h +++ b/arch/x86/include/asm/page_64.h @@ -4,6 +4,7 @@ #include <asm/page_64_types.h> #ifndef __ASSEMBLY__ +#include <asm/alternative.h> /* duplicated to the one in bootmem.h */ extern unsigned long max_pfn; @@ -34,7 +35,20 @@ extern unsigned long __phys_addr_symbol(unsigned long); #define pfn_valid(pfn) ((pfn) < max_pfn) #endif -void clear_page(void *page); +void clear_page_orig(void *page); +void clear_page_rep(void *page); +void clear_page_erms(void *page); + +static inline void clear_page(void *page) +{ + alternative_call_2(clear_page_orig, + clear_page_rep, X86_FEATURE_REP_GOOD, + clear_page_erms, X86_FEATURE_ERMS, + "=D" (page), + "0" (page) + : "memory", "rax", "rcx"); +} + void copy_page(void *to, void *from); #endif /* !__ASSEMBLY__ */ diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h index 9215e0527647..3f5f08b010d0 100644 --- a/arch/x86/include/asm/page_64_types.h +++ b/arch/x86/include/asm/page_64_types.h @@ -36,7 +36,12 @@ * hypervisor to fit. Choosing 16 slots here is arbitrary, but it's * what Xen requires. */ +#ifdef CONFIG_X86_5LEVEL +#define __PAGE_OFFSET_BASE _AC(0xff10000000000000, UL) +#else #define __PAGE_OFFSET_BASE _AC(0xffff880000000000, UL) +#endif + #ifdef CONFIG_RANDOMIZE_MEMORY #define __PAGE_OFFSET page_offset_base #else @@ -46,8 +51,13 @@ #define __START_KERNEL_map _AC(0xffffffff80000000, UL) /* See Documentation/x86/x86_64/mm.txt for a description of the memory map. */ +#ifdef CONFIG_X86_5LEVEL +#define __PHYSICAL_MASK_SHIFT 52 +#define __VIRTUAL_MASK_SHIFT 56 +#else #define __PHYSICAL_MASK_SHIFT 46 #define __VIRTUAL_MASK_SHIFT 47 +#endif /* * Kernel image size is limited to 1GiB due to the fixmap living in the diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 0489884fdc44..55fa56fe4e45 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -357,6 +357,16 @@ static inline void paravirt_release_pud(unsigned long pfn) PVOP_VCALL1(pv_mmu_ops.release_pud, pfn); } +static inline void paravirt_alloc_p4d(struct mm_struct *mm, unsigned long pfn) +{ + PVOP_VCALL2(pv_mmu_ops.alloc_p4d, mm, pfn); +} + +static inline void paravirt_release_p4d(unsigned long pfn) +{ + PVOP_VCALL1(pv_mmu_ops.release_p4d, pfn); +} + static inline void pte_update(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { @@ -536,7 +546,7 @@ static inline void set_pud(pud_t *pudp, pud_t pud) PVOP_VCALL2(pv_mmu_ops.set_pud, pudp, val); } -#if CONFIG_PGTABLE_LEVELS == 4 +#if CONFIG_PGTABLE_LEVELS >= 4 static inline pud_t __pud(pudval_t val) { pudval_t ret; @@ -565,26 +575,54 @@ static inline pudval_t pud_val(pud_t pud) return ret; } -static inline void set_pgd(pgd_t *pgdp, pgd_t pgd) +static inline void pud_clear(pud_t *pudp) { - pgdval_t val = native_pgd_val(pgd); + set_pud(pudp, __pud(0)); +} - if (sizeof(pgdval_t) > sizeof(long)) - PVOP_VCALL3(pv_mmu_ops.set_pgd, pgdp, +static inline void set_p4d(p4d_t *p4dp, p4d_t p4d) +{ + p4dval_t val = native_p4d_val(p4d); + + if (sizeof(p4dval_t) > sizeof(long)) + PVOP_VCALL3(pv_mmu_ops.set_p4d, p4dp, val, (u64)val >> 32); else - PVOP_VCALL2(pv_mmu_ops.set_pgd, pgdp, + PVOP_VCALL2(pv_mmu_ops.set_p4d, p4dp, val); } +#if CONFIG_PGTABLE_LEVELS >= 5 + +static inline p4d_t __p4d(p4dval_t val) +{ + p4dval_t ret = PVOP_CALLEE1(p4dval_t, pv_mmu_ops.make_p4d, val); + + return (p4d_t) { ret }; +} + +static inline p4dval_t p4d_val(p4d_t p4d) +{ + return PVOP_CALLEE1(p4dval_t, pv_mmu_ops.p4d_val, p4d.p4d); +} + +static inline void set_pgd(pgd_t *pgdp, pgd_t pgd) +{ + pgdval_t val = native_pgd_val(pgd); + + PVOP_VCALL2(pv_mmu_ops.set_pgd, pgdp, val); +} + static inline void pgd_clear(pgd_t *pgdp) { set_pgd(pgdp, __pgd(0)); } -static inline void pud_clear(pud_t *pudp) +#endif /* CONFIG_PGTABLE_LEVELS == 5 */ + +static inline void p4d_clear(p4d_t *p4dp) { - set_pud(pudp, __pud(0)); + set_p4d(p4dp, __p4d(0)); } #endif /* CONFIG_PGTABLE_LEVELS == 4 */ diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index b060f962d581..7465d6fe336f 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -238,9 +238,11 @@ struct pv_mmu_ops { void (*alloc_pte)(struct mm_struct *mm, unsigned long pfn); void (*alloc_pmd)(struct mm_struct *mm, unsigned long pfn); void (*alloc_pud)(struct mm_struct *mm, unsigned long pfn); + void (*alloc_p4d)(struct mm_struct *mm, unsigned long pfn); void (*release_pte)(unsigned long pfn); void (*release_pmd)(unsigned long pfn); void (*release_pud)(unsigned long pfn); + void (*release_p4d)(unsigned long pfn); /* Pagetable manipulation functions */ void (*set_pte)(pte_t *ptep, pte_t pteval); @@ -279,12 +281,21 @@ struct pv_mmu_ops { struct paravirt_callee_save pmd_val; struct paravirt_callee_save make_pmd; -#if CONFIG_PGTABLE_LEVELS == 4 +#if CONFIG_PGTABLE_LEVELS >= 4 struct paravirt_callee_save pud_val; struct paravirt_callee_save make_pud; - void (*set_pgd)(pgd_t *pudp, pgd_t pgdval); -#endif /* CONFIG_PGTABLE_LEVELS == 4 */ + void (*set_p4d)(p4d_t *p4dp, p4d_t p4dval); + +#if CONFIG_PGTABLE_LEVELS >= 5 + struct paravirt_callee_save p4d_val; + struct paravirt_callee_save make_p4d; + + void (*set_pgd)(pgd_t *pgdp, pgd_t pgdval); +#endif /* CONFIG_PGTABLE_LEVELS >= 5 */ + +#endif /* CONFIG_PGTABLE_LEVELS >= 4 */ + #endif /* CONFIG_PGTABLE_LEVELS >= 3 */ struct pv_lazy_ops lazy_mode; diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h index d08eacd298c2..9f1b21f372fe 100644 --- a/arch/x86/include/asm/pci_x86.h +++ b/arch/x86/include/asm/pci_x86.h @@ -4,6 +4,8 @@ * (c) 1999 Martin Mares <mj@ucw.cz> */ +#include <linux/ioport.h> + #undef DEBUG #ifdef DEBUG diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h index b6d425999f99..b2d0cd8288aa 100644 --- a/arch/x86/include/asm/pgalloc.h +++ b/arch/x86/include/asm/pgalloc.h @@ -17,9 +17,11 @@ static inline void paravirt_alloc_pmd(struct mm_struct *mm, unsigned long pfn) { static inline void paravirt_alloc_pmd_clone(unsigned long pfn, unsigned long clonepfn, unsigned long start, unsigned long count) {} static inline void paravirt_alloc_pud(struct mm_struct *mm, unsigned long pfn) {} +static inline void paravirt_alloc_p4d(struct mm_struct *mm, unsigned long pfn) {} static inline void paravirt_release_pte(unsigned long pfn) {} static inline void paravirt_release_pmd(unsigned long pfn) {} static inline void paravirt_release_pud(unsigned long pfn) {} +static inline void paravirt_release_p4d(unsigned long pfn) {} #endif /* @@ -121,10 +123,10 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) #endif /* CONFIG_X86_PAE */ #if CONFIG_PGTABLE_LEVELS > 3 -static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud) +static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4d, pud_t *pud) { paravirt_alloc_pud(mm, __pa(pud) >> PAGE_SHIFT); - set_pgd(pgd, __pgd(_PAGE_TABLE | __pa(pud))); + set_p4d(p4d, __p4d(_PAGE_TABLE | __pa(pud))); } static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) @@ -150,6 +152,37 @@ static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud, ___pud_free_tlb(tlb, pud); } +#if CONFIG_PGTABLE_LEVELS > 4 +static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, p4d_t *p4d) +{ + paravirt_alloc_p4d(mm, __pa(p4d) >> PAGE_SHIFT); + set_pgd(pgd, __pgd(_PAGE_TABLE | __pa(p4d))); +} + +static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long addr) +{ + gfp_t gfp = GFP_KERNEL_ACCOUNT; + + if (mm == &init_mm) + gfp &= ~__GFP_ACCOUNT; + return (p4d_t *)get_zeroed_page(gfp); +} + +static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d) +{ + BUG_ON((unsigned long)p4d & (PAGE_SIZE-1)); + free_page((unsigned long)p4d); +} + +extern void ___p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d); + +static inline void __p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d, + unsigned long address) +{ + ___p4d_free_tlb(tlb, p4d); +} + +#endif /* CONFIG_PGTABLE_LEVELS > 4 */ #endif /* CONFIG_PGTABLE_LEVELS > 3 */ #endif /* CONFIG_PGTABLE_LEVELS > 2 */ diff --git a/arch/x86/include/asm/pgtable-2level_types.h b/arch/x86/include/asm/pgtable-2level_types.h index 392576433e77..373ab1de909f 100644 --- a/arch/x86/include/asm/pgtable-2level_types.h +++ b/arch/x86/include/asm/pgtable-2level_types.h @@ -7,6 +7,7 @@ typedef unsigned long pteval_t; typedef unsigned long pmdval_t; typedef unsigned long pudval_t; +typedef unsigned long p4dval_t; typedef unsigned long pgdval_t; typedef unsigned long pgprotval_t; diff --git a/arch/x86/include/asm/pgtable-3level_types.h b/arch/x86/include/asm/pgtable-3level_types.h index bcc89625ebe5..b8a4341faafa 100644 --- a/arch/x86/include/asm/pgtable-3level_types.h +++ b/arch/x86/include/asm/pgtable-3level_types.h @@ -7,6 +7,7 @@ typedef u64 pteval_t; typedef u64 pmdval_t; typedef u64 pudval_t; +typedef u64 p4dval_t; typedef u64 pgdval_t; typedef u64 pgprotval_t; diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 585ee0d42d18..f5af95a0c6b8 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -2,8 +2,6 @@ #define _ASM_X86_PGTABLE_H #include <asm/page.h> -#include <asm/e820.h> - #include <asm/pgtable_types.h> /* @@ -53,11 +51,19 @@ extern struct mm_struct *pgd_page_get_mm(struct page *page); #define set_pmd(pmdp, pmd) native_set_pmd(pmdp, pmd) -#ifndef __PAGETABLE_PUD_FOLDED +#ifndef __PAGETABLE_P4D_FOLDED #define set_pgd(pgdp, pgd) native_set_pgd(pgdp, pgd) #define pgd_clear(pgd) native_pgd_clear(pgd) #endif +#ifndef set_p4d +# define set_p4d(p4dp, p4d) native_set_p4d(p4dp, p4d) +#endif + +#ifndef __PAGETABLE_PUD_FOLDED +#define p4d_clear(p4d) native_p4d_clear(p4d) +#endif + #ifndef set_pud # define set_pud(pudp, pud) native_set_pud(pudp, pud) #endif @@ -74,6 +80,11 @@ extern struct mm_struct *pgd_page_get_mm(struct page *page); #define pgd_val(x) native_pgd_val(x) #define __pgd(x) native_make_pgd(x) +#ifndef __PAGETABLE_P4D_FOLDED +#define p4d_val(x) native_p4d_val(x) +#define __p4d(x) native_make_p4d(x) +#endif + #ifndef __PAGETABLE_PUD_FOLDED #define pud_val(x) native_pud_val(x) #define __pud(x) native_make_pud(x) @@ -179,6 +190,17 @@ static inline unsigned long pud_pfn(pud_t pud) return (pud_val(pud) & pud_pfn_mask(pud)) >> PAGE_SHIFT; } +static inline unsigned long p4d_pfn(p4d_t p4d) +{ + return (p4d_val(p4d) & p4d_pfn_mask(p4d)) >> PAGE_SHIFT; +} + +static inline int p4d_large(p4d_t p4d) +{ + /* No 512 GiB pages yet */ + return 0; +} + #define pte_page(pte) pfn_to_page(pte_pfn(pte)) static inline int pmd_large(pmd_t pte) @@ -538,6 +560,7 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) #define pte_pgprot(x) __pgprot(pte_flags(x)) #define pmd_pgprot(x) __pgprot(pmd_flags(x)) #define pud_pgprot(x) __pgprot(pud_flags(x)) +#define p4d_pgprot(x) __pgprot(p4d_flags(x)) #define canon_pgprot(p) __pgprot(massage_pgprot(p)) @@ -587,6 +610,7 @@ pte_t *populate_extra_pte(unsigned long vaddr); #include <linux/mm_types.h> #include <linux/mmdebug.h> #include <linux/log2.h> +#include <asm/fixmap.h> static inline int pte_none(pte_t pte) { @@ -770,7 +794,52 @@ static inline int pud_large(pud_t pud) } #endif /* CONFIG_PGTABLE_LEVELS > 2 */ +static inline unsigned long pud_index(unsigned long address) +{ + return (address >> PUD_SHIFT) & (PTRS_PER_PUD - 1); +} + #if CONFIG_PGTABLE_LEVELS > 3 +static inline int p4d_none(p4d_t p4d) +{ + return (native_p4d_val(p4d) & ~(_PAGE_KNL_ERRATUM_MASK)) == 0; +} + +static inline int p4d_present(p4d_t p4d) +{ + return p4d_flags(p4d) & _PAGE_PRESENT; +} + +static inline unsigned long p4d_page_vaddr(p4d_t p4d) +{ + return (unsigned long)__va(p4d_val(p4d) & p4d_pfn_mask(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) + +/* Find an entry in the third-level page table.. */ +static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address) +{ + return (pud_t *)p4d_page_vaddr(*p4d) + pud_index(address); +} + +static inline int p4d_bad(p4d_t p4d) +{ + return (p4d_flags(p4d) & ~(_KERNPG_TABLE | _PAGE_USER)) != 0; +} +#endif /* CONFIG_PGTABLE_LEVELS > 3 */ + +static inline unsigned long p4d_index(unsigned long address) +{ + return (address >> P4D_SHIFT) & (PTRS_PER_P4D - 1); +} + +#if CONFIG_PGTABLE_LEVELS > 4 static inline int pgd_present(pgd_t pgd) { return pgd_flags(pgd) & _PAGE_PRESENT; @@ -788,14 +857,9 @@ static inline unsigned long pgd_page_vaddr(pgd_t pgd) #define pgd_page(pgd) pfn_to_page(pgd_val(pgd) >> PAGE_SHIFT) /* to find an entry in a page-table-directory. */ -static inline unsigned long pud_index(unsigned long address) -{ - return (address >> PUD_SHIFT) & (PTRS_PER_PUD - 1); -} - -static inline pud_t *pud_offset(pgd_t *pgd, unsigned long address) +static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address) { - return (pud_t *)pgd_page_vaddr(*pgd) + pud_index(address); + return (p4d_t *)pgd_page_vaddr(*pgd) + p4d_index(address); } static inline int pgd_bad(pgd_t pgd) @@ -813,7 +877,7 @@ static inline int pgd_none(pgd_t pgd) */ return !native_pgd_val(pgd); } -#endif /* CONFIG_PGTABLE_LEVELS > 3 */ +#endif /* CONFIG_PGTABLE_LEVELS > 4 */ #endif /* __ASSEMBLY__ */ @@ -845,6 +909,7 @@ static inline int pgd_none(pgd_t pgd) extern int direct_gbpages; void init_mem_mapping(void); void early_alloc_pgt_buf(void); +extern void memblock_find_dma_reserve(void); #ifdef CONFIG_X86_64 /* Realmode trampoline initialization. */ diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h index fbc73360aea0..bfab55675c16 100644 --- a/arch/x86/include/asm/pgtable_32.h +++ b/arch/x86/include/asm/pgtable_32.h @@ -14,7 +14,6 @@ */ #ifndef __ASSEMBLY__ #include <asm/processor.h> -#include <asm/fixmap.h> #include <linux/threads.h> #include <asm/paravirt.h> diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index 73c7ccc38912..9991224f6238 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -35,15 +35,22 @@ extern void paging_init(void); #define pud_ERROR(e) \ pr_err("%s:%d: bad pud %p(%016lx)\n", \ __FILE__, __LINE__, &(e), pud_val(e)) + +#if CONFIG_PGTABLE_LEVELS >= 5 +#define p4d_ERROR(e) \ + pr_err("%s:%d: bad p4d %p(%016lx)\n", \ + __FILE__, __LINE__, &(e), p4d_val(e)) +#endif + #define pgd_ERROR(e) \ pr_err("%s:%d: bad pgd %p(%016lx)\n", \ __FILE__, __LINE__, &(e), pgd_val(e)) struct mm_struct; +void set_pte_vaddr_p4d(p4d_t *p4d_page, unsigned long vaddr, pte_t new_pte); void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte); - static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { @@ -121,6 +128,20 @@ static inline pud_t native_pudp_get_and_clear(pud_t *xp) #endif } +static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d) +{ + *p4dp = p4d; +} + +static inline void native_p4d_clear(p4d_t *p4d) +{ +#ifdef CONFIG_X86_5LEVEL + native_set_p4d(p4d, native_make_p4d(0)); +#else + native_set_p4d(p4d, (p4d_t) { .pgd = native_make_pgd(0)}); +#endif +} + static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd) { *pgdp = pgd; diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h index 3a264200c62f..06470da156ba 100644 --- a/arch/x86/include/asm/pgtable_64_types.h +++ b/arch/x86/include/asm/pgtable_64_types.h @@ -13,6 +13,7 @@ typedef unsigned long pteval_t; typedef unsigned long pmdval_t; typedef unsigned long pudval_t; +typedef unsigned long p4dval_t; typedef unsigned long pgdval_t; typedef unsigned long pgprotval_t; @@ -22,12 +23,32 @@ typedef struct { pteval_t pte; } pte_t; #define SHARED_KERNEL_PMD 0 +#ifdef CONFIG_X86_5LEVEL + +/* + * PGDIR_SHIFT determines what a top-level page table entry can map + */ +#define PGDIR_SHIFT 48 +#define PTRS_PER_PGD 512 + +/* + * 4th level page in 5-level paging case + */ +#define P4D_SHIFT 39 +#define PTRS_PER_P4D 512 +#define P4D_SIZE (_AC(1, UL) << P4D_SHIFT) +#define P4D_MASK (~(P4D_SIZE - 1)) + +#else /* CONFIG_X86_5LEVEL */ + /* * PGDIR_SHIFT determines what a top-level page table entry can map */ #define PGDIR_SHIFT 39 #define PTRS_PER_PGD 512 +#endif /* CONFIG_X86_5LEVEL */ + /* * 3rd level page */ @@ -55,9 +76,15 @@ typedef struct { pteval_t pte; } pte_t; /* See Documentation/x86/x86_64/mm.txt for a description of the memory map. */ #define MAXMEM _AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL) +#ifdef CONFIG_X86_5LEVEL +#define VMALLOC_SIZE_TB _AC(16384, UL) +#define __VMALLOC_BASE _AC(0xff92000000000000, UL) +#define __VMEMMAP_BASE _AC(0xffd4000000000000, UL) +#else #define VMALLOC_SIZE_TB _AC(32, UL) #define __VMALLOC_BASE _AC(0xffffc90000000000, UL) #define __VMEMMAP_BASE _AC(0xffffea0000000000, UL) +#endif #ifdef CONFIG_RANDOMIZE_MEMORY #define VMALLOC_START vmalloc_base #define VMEMMAP_START vmemmap_base @@ -67,10 +94,11 @@ typedef struct { pteval_t pte; } pte_t; #endif /* CONFIG_RANDOMIZE_MEMORY */ #define VMALLOC_END (VMALLOC_START + _AC((VMALLOC_SIZE_TB << 40) - 1, UL)) #define MODULES_VADDR (__START_KERNEL_map + KERNEL_IMAGE_SIZE) -#define MODULES_END _AC(0xffffffffff000000, UL) +/* The module sections ends with the start of the fixmap */ +#define MODULES_END __fix_to_virt(__end_of_fixed_addresses + 1) #define MODULES_LEN (MODULES_END - MODULES_VADDR) #define ESPFIX_PGD_ENTRY _AC(-2, UL) -#define ESPFIX_BASE_ADDR (ESPFIX_PGD_ENTRY << PGDIR_SHIFT) +#define ESPFIX_BASE_ADDR (ESPFIX_PGD_ENTRY << P4D_SHIFT) #define EFI_VA_START ( -4 * (_AC(1, UL) << 30)) #define EFI_VA_END (-68 * (_AC(1, UL) << 30)) diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 62484333673d..bf9638e1ee42 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -272,9 +272,28 @@ static inline pgdval_t pgd_flags(pgd_t pgd) return native_pgd_val(pgd) & PTE_FLAGS_MASK; } -#if CONFIG_PGTABLE_LEVELS > 3 -#include <asm-generic/5level-fixup.h> +#if CONFIG_PGTABLE_LEVELS > 4 +typedef struct { p4dval_t p4d; } p4d_t; + +static inline p4d_t native_make_p4d(pudval_t val) +{ + return (p4d_t) { val }; +} + +static inline p4dval_t native_p4d_val(p4d_t p4d) +{ + return p4d.p4d; +} +#else +#include <asm-generic/pgtable-nop4d.h> + +static inline p4dval_t native_p4d_val(p4d_t p4d) +{ + return native_pgd_val(p4d.pgd); +} +#endif +#if CONFIG_PGTABLE_LEVELS > 3 typedef struct { pudval_t pud; } pud_t; static inline pud_t native_make_pud(pmdval_t val) @@ -287,12 +306,11 @@ static inline pudval_t native_pud_val(pud_t pud) return pud.pud; } #else -#define __ARCH_USE_5LEVEL_HACK #include <asm-generic/pgtable-nopud.h> static inline pudval_t native_pud_val(pud_t pud) { - return native_pgd_val(pud.pgd); + return native_pgd_val(pud.p4d.pgd); } #endif @@ -309,15 +327,30 @@ static inline pmdval_t native_pmd_val(pmd_t pmd) return pmd.pmd; } #else -#define __ARCH_USE_5LEVEL_HACK #include <asm-generic/pgtable-nopmd.h> static inline pmdval_t native_pmd_val(pmd_t pmd) { - return native_pgd_val(pmd.pud.pgd); + return native_pgd_val(pmd.pud.p4d.pgd); } #endif +static inline p4dval_t p4d_pfn_mask(p4d_t p4d) +{ + /* No 512 GiB huge pages yet */ + return PTE_PFN_MASK; +} + +static inline p4dval_t p4d_flags_mask(p4d_t p4d) +{ + return ~p4d_pfn_mask(p4d); +} + +static inline p4dval_t p4d_flags(p4d_t p4d) +{ + return native_p4d_val(p4d) & p4d_flags_mask(p4d); +} + static inline pudval_t pud_pfn_mask(pud_t pud) { if (native_pud_val(pud) & _PAGE_PSE) @@ -461,6 +494,7 @@ enum pg_level { PG_LEVEL_4K, PG_LEVEL_2M, PG_LEVEL_1G, + PG_LEVEL_512G, PG_LEVEL_NUM }; diff --git a/arch/x86/include/asm/pmem.h b/arch/x86/include/asm/pmem.h index 2c1ebeb4d737..529bb4a6487a 100644 --- a/arch/x86/include/asm/pmem.h +++ b/arch/x86/include/asm/pmem.h @@ -55,7 +55,8 @@ static inline int arch_memcpy_from_pmem(void *dst, const void *src, size_t n) * @size: number of bytes to write back * * Write back a cache range using the CLWB (cache line write back) - * instruction. + * instruction. Note that @size is internally rounded up to be cache + * line size aligned. */ static inline void arch_wb_cache_pmem(void *addr, size_t size) { @@ -69,15 +70,6 @@ static inline void arch_wb_cache_pmem(void *addr, size_t size) clwb(p); } -/* - * copy_from_iter_nocache() on x86 only uses non-temporal stores for iovec - * iterators, so for other types (bvec & kvec) we must do a cache write-back. - */ -static inline bool __iter_needs_pmem_wb(struct iov_iter *i) -{ - return iter_is_iovec(i) == false; -} - /** * arch_copy_from_iter_pmem - copy data from an iterator to PMEM * @addr: PMEM destination address @@ -94,7 +86,35 @@ static inline size_t arch_copy_from_iter_pmem(void *addr, size_t bytes, /* TODO: skip the write-back by always using non-temporal stores */ len = copy_from_iter_nocache(addr, bytes, i); - if (__iter_needs_pmem_wb(i)) + /* + * In the iovec case on x86_64 copy_from_iter_nocache() uses + * non-temporal stores for the bulk of the transfer, but we need + * to manually flush if the transfer is unaligned. A cached + * memory copy is used when destination or size is not naturally + * aligned. That is: + * - Require 8-byte alignment when size is 8 bytes or larger. + * - Require 4-byte alignment when size is 4 bytes. + * + * In the non-iovec case the entire destination needs to be + * flushed. + */ + if (iter_is_iovec(i)) { + unsigned long flushed, dest = (unsigned long) addr; + + if (bytes < 8) { + if (!IS_ALIGNED(dest, 4) || (bytes != 4)) + arch_wb_cache_pmem(addr, 1); + } else { + if (!IS_ALIGNED(dest, 8)) { + dest = ALIGN(dest, boot_cpu_data.x86_clflush_size); + arch_wb_cache_pmem(addr, 1); + } + + flushed = dest - (unsigned long) addr; + if (bytes > flushed && !IS_ALIGNED(bytes - flushed, 8)) + arch_wb_cache_pmem(addr + bytes - 1, 1); + } + } else arch_wb_cache_pmem(addr, bytes); return len; diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index f385eca5407a..3cada998a402 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -80,7 +80,7 @@ extern u16 __read_mostly tlb_lld_1g[NR_INFO]; /* * CPU type and hardware bug flags. Kept separately for each CPU. - * Members of this structure are referenced in head.S, so think twice + * Members of this structure are referenced in head_32.S, so think twice * before touching them. [mj] */ @@ -89,14 +89,7 @@ struct cpuinfo_x86 { __u8 x86_vendor; /* CPU vendor */ __u8 x86_model; __u8 x86_mask; -#ifdef CONFIG_X86_32 - char wp_works_ok; /* It doesn't on 386's */ - - /* Problems on some 486Dx4's and old 386's: */ - char rfu; - char pad0; - char pad1; -#else +#ifdef CONFIG_X86_64 /* Number of 4K pages in DTLB/ITLB combined(in pages): */ int x86_tlbsize; #endif @@ -716,6 +709,8 @@ extern struct desc_ptr early_gdt_descr; extern void cpu_set_gdt(int); extern void switch_to_new_gdt(int); +extern void load_direct_gdt(int); +extern void load_fixmap_gdt(int); extern void load_percpu_segment(int); extern void cpu_init(void); @@ -797,6 +792,7 @@ static inline void spin_lock_prefetch(const void *x) /* * User space process size: 3GB (default). */ +#define IA32_PAGE_OFFSET PAGE_OFFSET #define TASK_SIZE PAGE_OFFSET #define TASK_SIZE_MAX TASK_SIZE #define STACK_TOP TASK_SIZE @@ -873,7 +869,8 @@ extern void start_thread(struct pt_regs *regs, unsigned long new_ip, * This decides where the kernel will search for a free chunk of vm * space during mmap's. */ -#define TASK_UNMAPPED_BASE (PAGE_ALIGN(TASK_SIZE / 3)) +#define __TASK_UNMAPPED_BASE(task_size) (PAGE_ALIGN(task_size / 3)) +#define TASK_UNMAPPED_BASE __TASK_UNMAPPED_BASE(TASK_SIZE) #define KSTK_EIP(task) (task_pt_regs(task)->ip) @@ -884,6 +881,8 @@ extern void start_thread(struct pt_regs *regs, unsigned long new_ip, extern int get_tsc_mode(unsigned long adr); extern int set_tsc_mode(unsigned int val); +DECLARE_PER_CPU(u64, msr_misc_features_shadow); + /* Register/unregister a process' MPX related resource */ #define MPX_ENABLE_MANAGEMENT() mpx_enable_management() #define MPX_DISABLE_MANAGEMENT() mpx_disable_management() diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h index 9b9b30b19441..8d3964fc5f91 100644 --- a/arch/x86/include/asm/proto.h +++ b/arch/x86/include/asm/proto.h @@ -9,6 +9,7 @@ void syscall_init(void); #ifdef CONFIG_X86_64 void entry_SYSCALL_64(void); +long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2); #endif #ifdef CONFIG_X86_32 @@ -30,6 +31,7 @@ void x86_report_nx(void); extern int reboot_force; -long do_arch_prctl(struct task_struct *task, int code, unsigned long addr); +long do_arch_prctl_common(struct task_struct *task, int option, + unsigned long cpuid_enabled); #endif /* _ASM_X86_PROTO_H */ diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h index 2cb1cc253d51..fc62ba8dce93 100644 --- a/arch/x86/include/asm/reboot.h +++ b/arch/x86/include/asm/reboot.h @@ -15,6 +15,7 @@ struct machine_ops { }; extern struct machine_ops machine_ops; +extern int crashing_cpu; void native_machine_crash_shutdown(struct pt_regs *regs); void native_machine_shutdown(void); diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h index fac9a5c0abe9..d91ba04dd007 100644 --- a/arch/x86/include/asm/required-features.h +++ b/arch/x86/include/asm/required-features.h @@ -53,6 +53,12 @@ # define NEED_MOVBE 0 #endif +#ifdef CONFIG_X86_5LEVEL +# define NEED_LA57 (1<<(X86_FEATURE_LA57 & 31)) +#else +# define NEED_LA57 0 +#endif + #ifdef CONFIG_X86_64 #ifdef CONFIG_PARAVIRT /* Paravirtualized systems may not have PSE or PGE available */ @@ -98,7 +104,7 @@ #define REQUIRED_MASK13 0 #define REQUIRED_MASK14 0 #define REQUIRED_MASK15 0 -#define REQUIRED_MASK16 0 +#define REQUIRED_MASK16 (NEED_LA57) #define REQUIRED_MASK17 0 #define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18) diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 026ea82ecc60..47103eca3775 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -149,6 +149,19 @@ void smp_store_cpu_info(int id); #define cpu_physical_id(cpu) per_cpu(x86_cpu_to_apicid, cpu) #define cpu_acpi_id(cpu) per_cpu(x86_cpu_to_acpiid, cpu) +/* + * This function is needed by all SMP systems. It must _always_ be valid + * from the initial startup. We map APIC_BASE very early in page_setup(), + * so this is correct in the x86 case. + */ +#define raw_smp_processor_id() (this_cpu_read(cpu_number)) + +#ifdef CONFIG_X86_32 +extern int safe_smp_processor_id(void); +#else +# define safe_smp_processor_id() smp_processor_id() +#endif + #else /* !CONFIG_SMP */ #define wbinvd_on_cpu(cpu) wbinvd() static inline int wbinvd_on_all_cpus(void) @@ -161,22 +174,6 @@ static inline int wbinvd_on_all_cpus(void) extern unsigned disabled_cpus; -#ifdef CONFIG_X86_32_SMP -/* - * This function is needed by all SMP systems. It must _always_ be valid - * from the initial startup. We map APIC_BASE very early in page_setup(), - * so this is correct in the x86 case. - */ -#define raw_smp_processor_id() (this_cpu_read(cpu_number)) -extern int safe_smp_processor_id(void); - -#elif defined(CONFIG_X86_64_SMP) -#define raw_smp_processor_id() (this_cpu_read(cpu_number)) - -#define safe_smp_processor_id() smp_processor_id() - -#endif - #ifdef CONFIG_X86_LOCAL_APIC #ifndef CONFIG_X86_64 @@ -191,11 +188,7 @@ static inline int logical_smp_processor_id(void) extern int hard_smp_processor_id(void); #else /* CONFIG_X86_LOCAL_APIC */ - -# ifndef CONFIG_SMP -# define hard_smp_processor_id() 0 -# endif - +#define hard_smp_processor_id() 0 #endif /* CONFIG_X86_LOCAL_APIC */ #ifdef CONFIG_DEBUG_NMI_SELFTEST diff --git a/arch/x86/include/asm/sparsemem.h b/arch/x86/include/asm/sparsemem.h index 4517d6b93188..1f5bee2c202f 100644 --- a/arch/x86/include/asm/sparsemem.h +++ b/arch/x86/include/asm/sparsemem.h @@ -26,8 +26,13 @@ # endif #else /* CONFIG_X86_32 */ # define SECTION_SIZE_BITS 27 /* matt - 128 is convenient right now */ -# define MAX_PHYSADDR_BITS 44 -# define MAX_PHYSMEM_BITS 46 +# ifdef CONFIG_X86_5LEVEL +# define MAX_PHYSADDR_BITS 52 +# define MAX_PHYSMEM_BITS 52 +# else +# define MAX_PHYSADDR_BITS 44 +# define MAX_PHYSMEM_BITS 46 +# endif #endif #endif /* CONFIG_SPARSEMEM */ diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h index 58505f01962f..dcbd9bcce714 100644 --- a/arch/x86/include/asm/stackprotector.h +++ b/arch/x86/include/asm/stackprotector.h @@ -87,7 +87,7 @@ static inline void setup_stack_canary_segment(int cpu) { #ifdef CONFIG_X86_32 unsigned long canary = (unsigned long)&per_cpu(stack_canary, cpu); - struct desc_struct *gdt_table = get_cpu_gdt_table(cpu); + struct desc_struct *gdt_table = get_cpu_gdt_rw(cpu); struct desc_struct desc; desc = gdt_table[GDT_ENTRY_STACK_CANARY]; diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index ad6f5eb07a95..f765a49103fb 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -87,6 +87,7 @@ struct thread_info { #define TIF_SECCOMP 8 /* secure computing */ #define TIF_USER_RETURN_NOTIFY 11 /* notify kernel of userspace return */ #define TIF_UPROBE 12 /* breakpointed or singlestepping */ +#define TIF_NOCPUID 15 /* CPUID is not accessible in userland */ #define TIF_NOTSC 16 /* TSC is not accessible in userland */ #define TIF_IA32 17 /* IA32 compatibility process */ #define TIF_NOHZ 19 /* in adaptive nohz mode */ @@ -110,6 +111,7 @@ struct thread_info { #define _TIF_SECCOMP (1 << TIF_SECCOMP) #define _TIF_USER_RETURN_NOTIFY (1 << TIF_USER_RETURN_NOTIFY) #define _TIF_UPROBE (1 << TIF_UPROBE) +#define _TIF_NOCPUID (1 << TIF_NOCPUID) #define _TIF_NOTSC (1 << TIF_NOTSC) #define _TIF_IA32 (1 << TIF_IA32) #define _TIF_NOHZ (1 << TIF_NOHZ) @@ -138,7 +140,7 @@ struct thread_info { /* flags to check in __switch_to() */ #define _TIF_WORK_CTXSW \ - (_TIF_IO_BITMAP|_TIF_NOTSC|_TIF_BLOCKSTEP) + (_TIF_IO_BITMAP|_TIF_NOCPUID|_TIF_NOTSC|_TIF_BLOCKSTEP) #define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY) #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW) @@ -168,9 +170,9 @@ static inline unsigned long current_stack_pointer(void) * entirely contained by a single stack frame. * * Returns: - * 1 if within a frame - * -1 if placed across a frame boundary (or outside stack) - * 0 unable to determine (no frame pointers, etc) + * GOOD_FRAME if within a frame + * BAD_STACK if placed across a frame boundary (or outside stack) + * NOT_STACK unable to determine (no frame pointers, etc) */ static inline int arch_within_stack_frames(const void * const stack, const void * const stackend, @@ -197,13 +199,14 @@ static inline int arch_within_stack_frames(const void * const stack, * the copy as invalid. */ if (obj + len <= frame) - return obj >= oldframe + 2 * sizeof(void *) ? 1 : -1; + return obj >= oldframe + 2 * sizeof(void *) ? + GOOD_FRAME : BAD_STACK; oldframe = frame; frame = *(const void * const *)frame; } - return -1; + return BAD_STACK; #else - return 0; + return NOT_STACK; #endif } @@ -239,6 +242,8 @@ static inline int arch_within_stack_frames(const void * const stack, extern void arch_task_cache_init(void); extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src); extern void arch_release_task_struct(struct task_struct *tsk); +extern void arch_setup_new_exec(void); +#define arch_setup_new_exec arch_setup_new_exec #endif /* !__ASSEMBLY__ */ #endif /* _ASM_X86_THREAD_INFO_H */ diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index fc5abff9b7fd..6ed9ea469b48 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -110,6 +110,16 @@ static inline void cr4_clear_bits(unsigned long mask) } } +static inline void cr4_toggle_bits(unsigned long mask) +{ + unsigned long cr4; + + cr4 = this_cpu_read(cpu_tlbstate.cr4); + cr4 ^= mask; + this_cpu_write(cpu_tlbstate.cr4, cr4); + __write_cr4(cr4); +} + /* Read the CR4 shadow. */ static inline unsigned long cr4_read_shadow(void) { @@ -205,7 +215,6 @@ static inline void __flush_tlb_one(unsigned long addr) /* * TLB flushing: * - * - flush_tlb() flushes the current mm struct TLBs * - flush_tlb_all() flushes all processes TLBs * - flush_tlb_mm(mm) flushes the specified mm context TLB's * - flush_tlb_page(vma, vmaddr) flushes one page @@ -237,11 +246,6 @@ static inline void flush_tlb_all(void) __flush_tlb_all(); } -static inline void flush_tlb(void) -{ - __flush_tlb_up(); -} - static inline void local_flush_tlb(void) { __flush_tlb_up(); @@ -303,14 +307,11 @@ static inline void flush_tlb_kernel_range(unsigned long start, flush_tlb_mm_range(vma->vm_mm, start, end, vma->vm_flags) extern void flush_tlb_all(void); -extern void flush_tlb_current_task(void); extern void flush_tlb_page(struct vm_area_struct *, unsigned long); extern void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, unsigned long end, unsigned long vmflag); extern void flush_tlb_kernel_range(unsigned long start, unsigned long end); -#define flush_tlb() flush_tlb_current_task() - void native_flush_tlb_others(const struct cpumask *cpumask, struct mm_struct *mm, unsigned long start, unsigned long end); diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index ea148313570f..68766b276d9e 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -3,19 +3,14 @@ /* * User space memory access functions */ -#include <linux/errno.h> #include <linux/compiler.h> #include <linux/kasan-checks.h> -#include <linux/thread_info.h> #include <linux/string.h> #include <asm/asm.h> #include <asm/page.h> #include <asm/smap.h> #include <asm/extable.h> -#define VERIFY_READ 0 -#define VERIFY_WRITE 1 - /* * The fs value determines whether argument validity checking should be * performed or not. If get_fs() == USER_DS, checking is performed, with @@ -384,6 +379,18 @@ do { \ : "=r" (err), ltype(x) \ : "m" (__m(addr)), "i" (errret), "0" (err)) +#define __get_user_asm_nozero(x, addr, err, itype, rtype, ltype, errret) \ + asm volatile("\n" \ + "1: mov"itype" %2,%"rtype"1\n" \ + "2:\n" \ + ".section .fixup,\"ax\"\n" \ + "3: mov %3,%0\n" \ + " jmp 2b\n" \ + ".previous\n" \ + _ASM_EXTABLE(1b, 3b) \ + : "=r" (err), ltype(x) \ + : "m" (__m(addr)), "i" (errret), "0" (err)) + /* * This doesn't do __uaccess_begin/end - the exception handling * around it must do that. @@ -675,59 +682,6 @@ extern struct movsl_mask { # include <asm/uaccess_64.h> #endif -unsigned long __must_check _copy_from_user(void *to, const void __user *from, - unsigned n); -unsigned long __must_check _copy_to_user(void __user *to, const void *from, - unsigned n); - -extern void __compiletime_error("usercopy buffer size is too small") -__bad_copy_user(void); - -static inline void copy_user_overflow(int size, unsigned long count) -{ - WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count); -} - -static __always_inline unsigned long __must_check -copy_from_user(void *to, const void __user *from, unsigned long n) -{ - int sz = __compiletime_object_size(to); - - might_fault(); - - kasan_check_write(to, n); - - if (likely(sz < 0 || sz >= n)) { - check_object_size(to, n, false); - n = _copy_from_user(to, from, n); - } else if (!__builtin_constant_p(n)) - copy_user_overflow(sz, n); - else - __bad_copy_user(); - - return n; -} - -static __always_inline unsigned long __must_check -copy_to_user(void __user *to, const void *from, unsigned long n) -{ - int sz = __compiletime_object_size(from); - - kasan_check_read(from, n); - - might_fault(); - - if (likely(sz < 0 || sz >= n)) { - check_object_size(from, n, true); - n = _copy_to_user(to, from, n); - } else if (!__builtin_constant_p(n)) - copy_user_overflow(sz, n); - else - __bad_copy_user(); - - return n; -} - /* * We rely on the nested NMI work to allow atomic faults from the NMI path; the * nested NMI paths are careful to preserve CR2. diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h index 7d3bdd1ed697..aeda9bb8af50 100644 --- a/arch/x86/include/asm/uaccess_32.h +++ b/arch/x86/include/asm/uaccess_32.h @@ -4,149 +4,52 @@ /* * User space memory access functions */ -#include <linux/errno.h> -#include <linux/thread_info.h> #include <linux/string.h> #include <asm/asm.h> #include <asm/page.h> -unsigned long __must_check __copy_to_user_ll - (void __user *to, const void *from, unsigned long n); -unsigned long __must_check __copy_from_user_ll - (void *to, const void __user *from, unsigned long n); -unsigned long __must_check __copy_from_user_ll_nozero - (void *to, const void __user *from, unsigned long n); -unsigned long __must_check __copy_from_user_ll_nocache - (void *to, const void __user *from, unsigned long n); +unsigned long __must_check __copy_user_ll + (void *to, const void *from, unsigned long n); unsigned long __must_check __copy_from_user_ll_nocache_nozero (void *to, const void __user *from, unsigned long n); -/** - * __copy_to_user_inatomic: - Copy a block of data into user space, with less checking. - * @to: Destination address, in user space. - * @from: Source address, in kernel space. - * @n: Number of bytes to copy. - * - * Context: User context only. - * - * Copy data from kernel space to user space. Caller must check - * the specified block with access_ok() before calling this function. - * The caller should also make sure he pins the user space address - * so that we don't result in page fault and sleep. - */ -static __always_inline unsigned long __must_check -__copy_to_user_inatomic(void __user *to, const void *from, unsigned long n) -{ - check_object_size(from, n, true); - return __copy_to_user_ll(to, from, n); -} - -/** - * __copy_to_user: - Copy a block of data into user space, with less checking. - * @to: Destination address, in user space. - * @from: Source address, in kernel space. - * @n: Number of bytes to copy. - * - * Context: User context only. This function may sleep if pagefaults are - * enabled. - * - * Copy data from kernel space to user space. Caller must check - * the specified block with access_ok() before calling this function. - * - * Returns number of bytes that could not be copied. - * On success, this will be zero. - */ static __always_inline unsigned long __must_check -__copy_to_user(void __user *to, const void *from, unsigned long n) +raw_copy_to_user(void __user *to, const void *from, unsigned long n) { - might_fault(); - return __copy_to_user_inatomic(to, from, n); + return __copy_user_ll((__force void *)to, from, n); } static __always_inline unsigned long -__copy_from_user_inatomic(void *to, const void __user *from, unsigned long n) -{ - return __copy_from_user_ll_nozero(to, from, n); -} - -/** - * __copy_from_user: - Copy a block of data from user space, with less checking. - * @to: Destination address, in kernel space. - * @from: Source address, in user space. - * @n: Number of bytes to copy. - * - * Context: User context only. This function may sleep if pagefaults are - * enabled. - * - * Copy data from user space to kernel space. Caller must check - * the specified block with access_ok() before calling this function. - * - * Returns number of bytes that could not be copied. - * On success, this will be zero. - * - * If some data could not be copied, this function will pad the copied - * data to the requested size using zero bytes. - * - * An alternate version - __copy_from_user_inatomic() - may be called from - * atomic context and will fail rather than sleep. In this case the - * uncopied bytes will *NOT* be padded with zeros. See fs/filemap.h - * for explanation of why this is needed. - */ -static __always_inline unsigned long -__copy_from_user(void *to, const void __user *from, unsigned long n) -{ - might_fault(); - check_object_size(to, n, false); - if (__builtin_constant_p(n)) { - unsigned long ret; - - switch (n) { - case 1: - __uaccess_begin(); - __get_user_size(*(u8 *)to, from, 1, ret, 1); - __uaccess_end(); - return ret; - case 2: - __uaccess_begin(); - __get_user_size(*(u16 *)to, from, 2, ret, 2); - __uaccess_end(); - return ret; - case 4: - __uaccess_begin(); - __get_user_size(*(u32 *)to, from, 4, ret, 4); - __uaccess_end(); - return ret; - } - } - return __copy_from_user_ll(to, from, n); -} - -static __always_inline unsigned long __copy_from_user_nocache(void *to, - const void __user *from, unsigned long n) +raw_copy_from_user(void *to, const void __user *from, unsigned long n) { - might_fault(); if (__builtin_constant_p(n)) { unsigned long ret; switch (n) { case 1: + ret = 0; __uaccess_begin(); - __get_user_size(*(u8 *)to, from, 1, ret, 1); + __get_user_asm_nozero(*(u8 *)to, from, ret, + "b", "b", "=q", 1); __uaccess_end(); return ret; case 2: + ret = 0; __uaccess_begin(); - __get_user_size(*(u16 *)to, from, 2, ret, 2); + __get_user_asm_nozero(*(u16 *)to, from, ret, + "w", "w", "=r", 2); __uaccess_end(); return ret; case 4: + ret = 0; __uaccess_begin(); - __get_user_size(*(u32 *)to, from, 4, ret, 4); + __get_user_asm_nozero(*(u32 *)to, from, ret, + "l", "k", "=r", 4); __uaccess_end(); return ret; } } - return __copy_from_user_ll_nocache(to, from, n); + return __copy_user_ll(to, (__force const void *)from, n); } static __always_inline unsigned long diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index 673059a109fe..c5504b9a472e 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -5,7 +5,6 @@ * User space memory access functions */ #include <linux/compiler.h> -#include <linux/errno.h> #include <linux/lockdep.h> #include <linux/kasan-checks.h> #include <asm/alternative.h> @@ -46,58 +45,54 @@ copy_user_generic(void *to, const void *from, unsigned len) return ret; } -__must_check unsigned long -copy_in_user(void __user *to, const void __user *from, unsigned len); - -static __always_inline __must_check -int __copy_from_user_nocheck(void *dst, const void __user *src, unsigned size) +static __always_inline __must_check unsigned long +raw_copy_from_user(void *dst, const void __user *src, unsigned long size) { int ret = 0; - check_object_size(dst, size, false); if (!__builtin_constant_p(size)) return copy_user_generic(dst, (__force void *)src, size); switch (size) { case 1: __uaccess_begin(); - __get_user_asm(*(u8 *)dst, (u8 __user *)src, + __get_user_asm_nozero(*(u8 *)dst, (u8 __user *)src, ret, "b", "b", "=q", 1); __uaccess_end(); return ret; case 2: __uaccess_begin(); - __get_user_asm(*(u16 *)dst, (u16 __user *)src, + __get_user_asm_nozero(*(u16 *)dst, (u16 __user *)src, ret, "w", "w", "=r", 2); __uaccess_end(); return ret; case 4: __uaccess_begin(); - __get_user_asm(*(u32 *)dst, (u32 __user *)src, + __get_user_asm_nozero(*(u32 *)dst, (u32 __user *)src, ret, "l", "k", "=r", 4); __uaccess_end(); return ret; case 8: __uaccess_begin(); - __get_user_asm(*(u64 *)dst, (u64 __user *)src, + __get_user_asm_nozero(*(u64 *)dst, (u64 __user *)src, ret, "q", "", "=r", 8); __uaccess_end(); return ret; case 10: __uaccess_begin(); - __get_user_asm(*(u64 *)dst, (u64 __user *)src, + __get_user_asm_nozero(*(u64 *)dst, (u64 __user *)src, ret, "q", "", "=r", 10); if (likely(!ret)) - __get_user_asm(*(u16 *)(8 + (char *)dst), + __get_user_asm_nozero(*(u16 *)(8 + (char *)dst), (u16 __user *)(8 + (char __user *)src), ret, "w", "w", "=r", 2); __uaccess_end(); return ret; case 16: __uaccess_begin(); - __get_user_asm(*(u64 *)dst, (u64 __user *)src, + __get_user_asm_nozero(*(u64 *)dst, (u64 __user *)src, ret, "q", "", "=r", 16); if (likely(!ret)) - __get_user_asm(*(u64 *)(8 + (char *)dst), + __get_user_asm_nozero(*(u64 *)(8 + (char *)dst), (u64 __user *)(8 + (char __user *)src), ret, "q", "", "=r", 8); __uaccess_end(); @@ -107,20 +102,11 @@ int __copy_from_user_nocheck(void *dst, const void __user *src, unsigned size) } } -static __always_inline __must_check -int __copy_from_user(void *dst, const void __user *src, unsigned size) -{ - might_fault(); - kasan_check_write(dst, size); - return __copy_from_user_nocheck(dst, src, size); -} - -static __always_inline __must_check -int __copy_to_user_nocheck(void __user *dst, const void *src, unsigned size) +static __always_inline __must_check unsigned long +raw_copy_to_user(void __user *dst, const void *src, unsigned long size) { int ret = 0; - check_object_size(src, size, true); if (!__builtin_constant_p(size)) return copy_user_generic((__force void *)dst, src, size); switch (size) { @@ -176,100 +162,16 @@ int __copy_to_user_nocheck(void __user *dst, const void *src, unsigned size) } static __always_inline __must_check -int __copy_to_user(void __user *dst, const void *src, unsigned size) -{ - might_fault(); - kasan_check_read(src, size); - return __copy_to_user_nocheck(dst, src, size); -} - -static __always_inline __must_check -int __copy_in_user(void __user *dst, const void __user *src, unsigned size) -{ - int ret = 0; - - might_fault(); - if (!__builtin_constant_p(size)) - return copy_user_generic((__force void *)dst, - (__force void *)src, size); - switch (size) { - case 1: { - u8 tmp; - __uaccess_begin(); - __get_user_asm(tmp, (u8 __user *)src, - ret, "b", "b", "=q", 1); - if (likely(!ret)) - __put_user_asm(tmp, (u8 __user *)dst, - ret, "b", "b", "iq", 1); - __uaccess_end(); - return ret; - } - case 2: { - u16 tmp; - __uaccess_begin(); - __get_user_asm(tmp, (u16 __user *)src, - ret, "w", "w", "=r", 2); - if (likely(!ret)) - __put_user_asm(tmp, (u16 __user *)dst, - ret, "w", "w", "ir", 2); - __uaccess_end(); - return ret; - } - - case 4: { - u32 tmp; - __uaccess_begin(); - __get_user_asm(tmp, (u32 __user *)src, - ret, "l", "k", "=r", 4); - if (likely(!ret)) - __put_user_asm(tmp, (u32 __user *)dst, - ret, "l", "k", "ir", 4); - __uaccess_end(); - return ret; - } - case 8: { - u64 tmp; - __uaccess_begin(); - __get_user_asm(tmp, (u64 __user *)src, - ret, "q", "", "=r", 8); - if (likely(!ret)) - __put_user_asm(tmp, (u64 __user *)dst, - ret, "q", "", "er", 8); - __uaccess_end(); - return ret; - } - default: - return copy_user_generic((__force void *)dst, - (__force void *)src, size); - } -} - -static __must_check __always_inline int -__copy_from_user_inatomic(void *dst, const void __user *src, unsigned size) -{ - kasan_check_write(dst, size); - return __copy_from_user_nocheck(dst, src, size); -} - -static __must_check __always_inline int -__copy_to_user_inatomic(void __user *dst, const void *src, unsigned size) +unsigned long raw_copy_in_user(void __user *dst, const void __user *src, unsigned long size) { - kasan_check_read(src, size); - return __copy_to_user_nocheck(dst, src, size); + return copy_user_generic((__force void *)dst, + (__force void *)src, size); } extern long __copy_user_nocache(void *dst, const void __user *src, unsigned size, int zerorest); static inline int -__copy_from_user_nocache(void *dst, const void __user *src, unsigned size) -{ - might_fault(); - kasan_check_write(dst, size); - return __copy_user_nocache(dst, src, size, 1); -} - -static inline int __copy_from_user_inatomic_nocache(void *dst, const void __user *src, unsigned size) { diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h index 6fa75b17aec3..9b10dcd51716 100644 --- a/arch/x86/include/asm/unwind.h +++ b/arch/x86/include/asm/unwind.h @@ -12,8 +12,10 @@ struct unwind_state { struct task_struct *task; int graph_idx; #ifdef CONFIG_FRAME_POINTER + bool got_irq; unsigned long *bp, *orig_sp; struct pt_regs *regs; + unsigned long ip; #else unsigned long *sp; #endif diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h index 57ab86d94d64..7cac79802ad2 100644 --- a/arch/x86/include/asm/uv/uv_bau.h +++ b/arch/x86/include/asm/uv/uv_bau.h @@ -185,6 +185,15 @@ #define MSG_REGULAR 1 #define MSG_RETRY 2 +#define BAU_DESC_QUALIFIER 0x534749 + +enum uv_bau_version { + UV_BAU_V1 = 1, + UV_BAU_V2, + UV_BAU_V3, + UV_BAU_V4, +}; + /* * Distribution: 32 bytes (256 bits) (bytes 0-0x1f of descriptor) * If the 'multilevel' flag in the header portion of the descriptor @@ -222,20 +231,32 @@ struct bau_local_cpumask { * the s/w ack bit vector ] */ -/* - * The payload is software-defined for INTD transactions +/** + * struct uv1_2_3_bau_msg_payload - defines payload for INTD transactions + * @address: Signifies a page or all TLB's of the cpu + * @sending_cpu: CPU from which the message originates + * @acknowledge_count: CPUs on the destination Hub that received the interrupt */ -struct bau_msg_payload { - unsigned long address; /* signifies a page or all - TLB's of the cpu */ - /* 64 bits */ - unsigned short sending_cpu; /* filled in by sender */ - /* 16 bits */ - unsigned short acknowledge_count; /* filled in by destination */ - /* 16 bits */ - unsigned int reserved1:32; /* not usable */ +struct uv1_2_3_bau_msg_payload { + u64 address; + u16 sending_cpu; + u16 acknowledge_count; }; +/** + * struct uv4_bau_msg_payload - defines payload for INTD transactions + * @address: Signifies a page or all TLB's of the cpu + * @sending_cpu: CPU from which the message originates + * @acknowledge_count: CPUs on the destination Hub that received the interrupt + * @qualifier: Set by source to verify origin of INTD broadcast + */ +struct uv4_bau_msg_payload { + u64 address; + u16 sending_cpu; + u16 acknowledge_count; + u32 reserved:8; + u32 qualifier:24; +}; /* * UV1 Message header: 16 bytes (128 bits) (bytes 0x30-0x3f of descriptor) @@ -385,17 +406,6 @@ struct uv2_3_bau_msg_header { /* bits 127:120 */ }; -/* Abstracted BAU functions */ -struct bau_operations { - unsigned long (*read_l_sw_ack)(void); - unsigned long (*read_g_sw_ack)(int pnode); - unsigned long (*bau_gpa_to_offset)(unsigned long vaddr); - void (*write_l_sw_ack)(unsigned long mmr); - void (*write_g_sw_ack)(int pnode, unsigned long mmr); - void (*write_payload_first)(int pnode, unsigned long mmr); - void (*write_payload_last)(int pnode, unsigned long mmr); -}; - /* * The activation descriptor: * The format of the message to send, plus all accompanying control @@ -411,7 +421,10 @@ struct bau_desc { struct uv2_3_bau_msg_header uv2_3_hdr; } header; - struct bau_msg_payload payload; + union bau_payload_header { + struct uv1_2_3_bau_msg_payload uv1_2_3; + struct uv4_bau_msg_payload uv4; + } payload; }; /* UV1: * -payload-- ---------header------ @@ -588,8 +601,12 @@ struct uvhub_desc { struct socket_desc socket[2]; }; -/* - * one per-cpu; to locate the software tables +/** + * struct bau_control + * @status_mmr: location of status mmr, determined by uvhub_cpu + * @status_index: index of ERR|BUSY bits in status mmr, determined by uvhub_cpu + * + * Per-cpu control struct containing CPU topology information and BAU tuneables. */ struct bau_control { struct bau_desc *descriptor_base; @@ -607,6 +624,8 @@ struct bau_control { int timeout_tries; int ipi_attempts; int conseccompletes; + u64 status_mmr; + int status_index; bool nobau; short baudisabled; short cpu; @@ -644,6 +663,19 @@ struct bau_control { struct hub_and_pnode *thp; }; +/* Abstracted BAU functions */ +struct bau_operations { + unsigned long (*read_l_sw_ack)(void); + unsigned long (*read_g_sw_ack)(int pnode); + unsigned long (*bau_gpa_to_offset)(unsigned long vaddr); + void (*write_l_sw_ack)(unsigned long mmr); + void (*write_g_sw_ack)(int pnode, unsigned long mmr); + void (*write_payload_first)(int pnode, unsigned long mmr); + void (*write_payload_last)(int pnode, unsigned long mmr); + int (*wait_completion)(struct bau_desc*, + struct bau_control*, long try); +}; + static inline void write_mmr_data_broadcast(int pnode, unsigned long mmr_image) { write_gmmr(pnode, UVH_BAU_DATA_BROADCAST, mmr_image); diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h index 2444189cbe28..bccdf4938ddf 100644 --- a/arch/x86/include/asm/vdso.h +++ b/arch/x86/include/asm/vdso.h @@ -20,6 +20,7 @@ struct vdso_image { long sym_vvar_page; long sym_hpet_page; long sym_pvclock_page; + long sym_hvclock_page; long sym_VDSO32_NOTE_MASK; long sym___kernel_sigreturn; long sym___kernel_rt_sigreturn; diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index 33cbd3db97b9..8a5a02b1dfba 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -6,6 +6,7 @@ #include <linux/spinlock.h> #include <linux/pfn.h> #include <linux/mm.h> +#include <linux/device.h> #include <linux/uaccess.h> #include <asm/page.h> @@ -279,13 +280,17 @@ static inline pte_t __pte_ma(pteval_t x) #define pmd_val_ma(v) ((v).pmd) #ifdef __PAGETABLE_PUD_FOLDED -#define pud_val_ma(v) ((v).pgd.pgd) +#define pud_val_ma(v) ((v).p4d.pgd.pgd) #else #define pud_val_ma(v) ((v).pud) #endif #define __pmd_ma(x) ((pmd_t) { (x) } ) -#define pgd_val_ma(x) ((x).pgd) +#ifdef __PAGETABLE_P4D_FOLDED +#define p4d_val_ma(x) ((x).pgd.pgd) +#else +#define p4d_val_ma(x) ((x).p4d) +#endif void xen_set_domain_pte(pte_t *ptep, pte_t pteval, unsigned domid); diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h index 07244ea16765..ddef37b16af2 100644 --- a/arch/x86/include/uapi/asm/bootparam.h +++ b/arch/x86/include/uapi/asm/bootparam.h @@ -34,7 +34,6 @@ #include <linux/screen_info.h> #include <linux/apm_bios.h> #include <linux/edd.h> -#include <asm/e820.h> #include <asm/ist.h> #include <video/edid.h> @@ -111,6 +110,21 @@ struct efi_info { __u32 efi_memmap_hi; }; +/* + * This is the maximum number of entries in struct boot_params::e820_table + * (the zeropage), which is part of the x86 boot protocol ABI: + */ +#define E820_MAX_ENTRIES_ZEROPAGE 128 + +/* + * The E820 memory region entry of the boot protocol ABI: + */ +struct boot_e820_entry { + __u64 addr; + __u64 size; + __u32 type; +} __attribute__((packed)); + /* The so-called "zeropage" */ struct boot_params { struct screen_info screen_info; /* 0x000 */ @@ -153,7 +167,7 @@ struct boot_params { struct setup_header hdr; /* setup header */ /* 0x1f1 */ __u8 _pad7[0x290-0x1f1-sizeof(struct setup_header)]; __u32 edd_mbr_sig_buffer[EDD_MBR_SIG_MAX]; /* 0x290 */ - struct e820entry e820_map[E820MAX]; /* 0x2d0 */ + struct boot_e820_entry e820_table[E820_MAX_ENTRIES_ZEROPAGE]; /* 0x2d0 */ __u8 _pad8[48]; /* 0xcd0 */ struct edd_info eddbuf[EDDMAXNR]; /* 0xd00 */ __u8 _pad9[276]; /* 0xeec */ diff --git a/arch/x86/include/uapi/asm/prctl.h b/arch/x86/include/uapi/asm/prctl.h index 835aa51c7f6e..c45765517092 100644 --- a/arch/x86/include/uapi/asm/prctl.h +++ b/arch/x86/include/uapi/asm/prctl.h @@ -1,10 +1,13 @@ #ifndef _ASM_X86_PRCTL_H #define _ASM_X86_PRCTL_H -#define ARCH_SET_GS 0x1001 -#define ARCH_SET_FS 0x1002 -#define ARCH_GET_FS 0x1003 -#define ARCH_GET_GS 0x1004 +#define ARCH_SET_GS 0x1001 +#define ARCH_SET_FS 0x1002 +#define ARCH_GET_FS 0x1003 +#define ARCH_GET_GS 0x1004 + +#define ARCH_GET_CPUID 0x1011 +#define ARCH_SET_CPUID 0x1012 #define ARCH_MAP_VDSO_X32 0x2001 #define ARCH_MAP_VDSO_32 0x2002 diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 84c00592d359..4b994232cb57 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -27,7 +27,7 @@ KASAN_SANITIZE_stacktrace.o := n OBJECT_FILES_NON_STANDARD_head_$(BITS).o := y OBJECT_FILES_NON_STANDARD_relocate_kernel_$(BITS).o := y -OBJECT_FILES_NON_STANDARD_mcount_$(BITS).o := y +OBJECT_FILES_NON_STANDARD_ftrace_$(BITS).o := y OBJECT_FILES_NON_STANDARD_test_nx.o := y # If instrumentation of this dir is enabled, boot hangs during first second. @@ -46,7 +46,7 @@ obj-$(CONFIG_MODIFY_LDT_SYSCALL) += ldt.o obj-y += setup.o x86_init.o i8259.o irqinit.o jump_label.o obj-$(CONFIG_IRQ_WORK) += irq_work.o obj-y += probe_roms.o -obj-$(CONFIG_X86_64) += sys_x86_64.o mcount_64.o +obj-$(CONFIG_X86_64) += sys_x86_64.o obj-$(CONFIG_X86_ESPFIX64) += espfix_64.o obj-$(CONFIG_SYSFS) += ksysfs.o obj-y += bootflag.o e820.o @@ -82,6 +82,7 @@ obj-y += apic/ obj-$(CONFIG_X86_REBOOTFIXUPS) += reboot_fixups_32.o obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o obj-$(CONFIG_LIVEPATCH) += livepatch.o +obj-$(CONFIG_FUNCTION_TRACER) += ftrace_$(BITS).o obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o obj-$(CONFIG_FTRACE_SYSCALLS) += ftrace.o obj-$(CONFIG_X86_TSC) += trace_clock.o diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index b2879cc23db4..6bb680671088 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -37,6 +37,7 @@ #include <linux/pci.h> #include <linux/efi-bgrt.h> +#include <asm/e820/api.h> #include <asm/irqdomain.h> #include <asm/pci_x86.h> #include <asm/pgtable.h> @@ -1564,12 +1565,6 @@ int __init early_acpi_boot_init(void) return 0; } -static int __init acpi_parse_bgrt(struct acpi_table_header *table) -{ - efi_bgrt_init(table); - return 0; -} - int __init acpi_boot_init(void) { /* those are executed after early-quirks are executed */ @@ -1729,6 +1724,6 @@ int __acpi_release_global_lock(unsigned int *lock) void __init arch_reserve_mem_area(acpi_physical_address addr, size_t size) { - e820_add_region(addr, size, E820_ACPI); - update_e820(); + e820__range_add(addr, size, E820_TYPE_ACPI); + e820__update_table_print(); } diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index 48587335ede8..ed014814ea35 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -101,7 +101,7 @@ int x86_acpi_suspend_lowlevel(void) #ifdef CONFIG_SMP initial_stack = (unsigned long)temp_stack + sizeof(temp_stack); early_gdt_descr.address = - (unsigned long)get_cpu_gdt_table(smp_processor_id()); + (unsigned long)get_cpu_gdt_rw(smp_processor_id()); initial_gs = per_cpu_offset(smp_processor_id()); #endif initial_code = (unsigned long)wakeup_long64; diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 0a2bb1f62e72..ef2859f9fcce 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -21,7 +21,7 @@ #include <linux/pci.h> #include <linux/bitops.h> #include <linux/suspend.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/io.h> #include <asm/iommu.h> #include <asm/gart.h> @@ -306,13 +306,13 @@ void __init early_gart_iommu_check(void) fix = 1; if (gart_fix_e820 && !fix && aper_enabled) { - if (e820_any_mapped(aper_base, aper_base + aper_size, - E820_RAM)) { + if (e820__mapped_any(aper_base, aper_base + aper_size, + E820_TYPE_RAM)) { /* reserve it, so we can reuse it in second kernel */ pr_info("e820: reserve [mem %#010Lx-%#010Lx] for GART\n", aper_base, aper_base + aper_size - 1); - e820_add_region(aper_base, aper_size, E820_RESERVED); - update_e820(); + e820__range_add(aper_base, aper_size, E820_TYPE_RESERVED); + e820__update_table_print(); } } diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 8ccb7ef512e0..2d75faf743f2 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -731,8 +731,10 @@ static int __init calibrate_APIC_clock(void) TICK_NSEC, lapic_clockevent.shift); lapic_clockevent.max_delta_ns = clockevent_delta2ns(0x7FFFFF, &lapic_clockevent); + lapic_clockevent.max_delta_ticks = 0x7FFFFF; lapic_clockevent.min_delta_ns = clockevent_delta2ns(0xF, &lapic_clockevent); + lapic_clockevent.min_delta_ticks = 0xF; lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY; return 0; } @@ -778,8 +780,10 @@ static int __init calibrate_APIC_clock(void) lapic_clockevent.shift); lapic_clockevent.max_delta_ns = clockevent_delta2ns(0x7FFFFFFF, &lapic_clockevent); + lapic_clockevent.max_delta_ticks = 0x7FFFFFFF; lapic_clockevent.min_delta_ns = clockevent_delta2ns(0xF, &lapic_clockevent); + lapic_clockevent.min_delta_ticks = 0xF; lapic_timer_frequency = (delta * APIC_DIVISOR) / LAPIC_CAL_LOOPS; @@ -1789,8 +1793,8 @@ void __init init_apic_mappings(void) apic_phys = mp_lapic_addr; /* - * acpi lapic path already maps that address in - * acpi_register_lapic_address() + * If the system has ACPI MADT tables or MP info, the LAPIC + * address is already registered. */ if (!acpi_lapic && !smp_found_config) register_lapic_address(apic_phys); @@ -2237,7 +2241,7 @@ void __init apic_set_eoi_write(void (*eoi_write)(u32 reg, u32 v)) static void __init apic_bsp_up_setup(void) { #ifdef CONFIG_X86_64 - apic_write(APIC_ID, SET_APIC_ID(boot_cpu_physical_apicid)); + apic_write(APIC_ID, apic->set_apic_id(boot_cpu_physical_apicid)); #else /* * Hack: In case of kdump, after a crash, kernel might be booting @@ -2627,7 +2631,7 @@ static int __init lapic_insert_resource(void) } /* - * need call insert after e820_reserve_resources() + * need call insert after e820__reserve_resources() * that is using request_resource */ late_initcall(lapic_insert_resource); diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c index b109e4389c92..2262eb6df796 100644 --- a/arch/x86/kernel/apic/apic_noop.c +++ b/arch/x86/kernel/apic/apic_noop.c @@ -26,7 +26,7 @@ #include <linux/interrupt.h> #include <asm/acpi.h> -#include <asm/e820.h> +#include <asm/e820/api.h> static void noop_init_apic_ldr(void) { } static void noop_send_IPI(int cpu, int vector) { } diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index c48264e202fd..2e8f7f048f4f 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -25,7 +25,7 @@ #include <linux/interrupt.h> #include <asm/acpi.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #ifdef CONFIG_HOTPLUG_CPU #define DEFAULT_SEND_IPI (1) diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 86f20cc0a65e..b487b3a01615 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -34,6 +34,7 @@ #include <asm/uv/bios.h> #include <asm/uv/uv.h> #include <asm/apic.h> +#include <asm/e820/api.h> #include <asm/ipi.h> #include <asm/smp.h> #include <asm/x86_init.h> diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 5a414545e8a3..446b0d3d4932 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -609,7 +609,7 @@ static long __apm_bios_call(void *_call) cpu = get_cpu(); BUG_ON(cpu != 0); - gdt = get_cpu_gdt_table(cpu); + gdt = get_cpu_gdt_rw(cpu); save_desc_40 = gdt[0x40 / 8]; gdt[0x40 / 8] = bad_bios_desc; @@ -685,7 +685,7 @@ static long __apm_bios_call_simple(void *_call) cpu = get_cpu(); BUG_ON(cpu != 0); - gdt = get_cpu_gdt_table(cpu); + gdt = get_cpu_gdt_rw(cpu); save_desc_40 = gdt[0x40 / 8]; gdt[0x40 / 8] = bad_bios_desc; @@ -2352,7 +2352,7 @@ static int __init apm_init(void) * Note we only set APM segments on CPU zero, since we pin the APM * code to that CPU. */ - gdt = get_cpu_gdt_table(0); + gdt = get_cpu_gdt_rw(0); set_desc_base(&gdt[APM_CS >> 3], (unsigned long)__va((unsigned long)apm_info.bios.cseg << 4)); set_desc_base(&gdt[APM_CS_16 >> 3], diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index 43955ee6715b..44207b71fee1 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -3,7 +3,7 @@ #include <linux/sched/clock.h> #include <asm/cpufeature.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/mtrr.h> #include <asm/msr.h> diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 58094a1f9e9d..8ee32119144d 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -448,19 +448,60 @@ void load_percpu_segment(int cpu) load_stack_canary_segment(); } +/* Setup the fixmap mapping only once per-processor */ +static inline void setup_fixmap_gdt(int cpu) +{ +#ifdef CONFIG_X86_64 + /* On 64-bit systems, we use a read-only fixmap GDT. */ + pgprot_t prot = PAGE_KERNEL_RO; +#else + /* + * On native 32-bit systems, the GDT cannot be read-only because + * our double fault handler uses a task gate, and entering through + * a task gate needs to change an available TSS to busy. If the GDT + * is read-only, that will triple fault. + * + * On Xen PV, the GDT must be read-only because the hypervisor requires + * it. + */ + pgprot_t prot = boot_cpu_has(X86_FEATURE_XENPV) ? + PAGE_KERNEL_RO : PAGE_KERNEL; +#endif + + __set_fixmap(get_cpu_gdt_ro_index(cpu), get_cpu_gdt_paddr(cpu), prot); +} + +/* Load the original GDT from the per-cpu structure */ +void load_direct_gdt(int cpu) +{ + struct desc_ptr gdt_descr; + + gdt_descr.address = (long)get_cpu_gdt_rw(cpu); + gdt_descr.size = GDT_SIZE - 1; + load_gdt(&gdt_descr); +} +EXPORT_SYMBOL_GPL(load_direct_gdt); + +/* Load a fixmap remapping of the per-cpu GDT */ +void load_fixmap_gdt(int cpu) +{ + struct desc_ptr gdt_descr; + + gdt_descr.address = (long)get_cpu_gdt_ro(cpu); + gdt_descr.size = GDT_SIZE - 1; + load_gdt(&gdt_descr); +} +EXPORT_SYMBOL_GPL(load_fixmap_gdt); + /* * Current gdt points %fs at the "master" per-cpu area: after this, * it's on the real one. */ void switch_to_new_gdt(int cpu) { - struct desc_ptr gdt_descr; - - gdt_descr.address = (long)get_cpu_gdt_table(cpu); - gdt_descr.size = GDT_SIZE - 1; - load_gdt(&gdt_descr); + /* Load the original GDT */ + load_direct_gdt(cpu); /* Reload the per-cpu base */ - load_percpu_segment(cpu); } @@ -1526,6 +1567,9 @@ void cpu_init(void) if (is_uv_system()) uv_cpu_init(); + + setup_fixmap_gdt(cpu); + load_fixmap_gdt(cpu); } #else @@ -1581,6 +1625,9 @@ void cpu_init(void) dbg_restore_debug_regs(); fpu__init_cpu(); + + setup_fixmap_gdt(cpu); + load_fixmap_gdt(cpu); } #endif diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 063197771b8d..dfa90a3a5145 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -90,16 +90,12 @@ static void probe_xeon_phi_r3mwait(struct cpuinfo_x86 *c) return; } - if (ring3mwait_disabled) { - msr_clear_bit(MSR_MISC_FEATURE_ENABLES, - MSR_MISC_FEATURE_ENABLES_RING3MWAIT_BIT); + if (ring3mwait_disabled) return; - } - - msr_set_bit(MSR_MISC_FEATURE_ENABLES, - MSR_MISC_FEATURE_ENABLES_RING3MWAIT_BIT); set_cpu_cap(c, X86_FEATURE_RING3MWAIT); + this_cpu_or(msr_misc_features_shadow, + 1UL << MSR_MISC_FEATURES_ENABLES_RING3MWAIT_BIT); if (c == &boot_cpu_data) ELF_HWCAP2 |= HWCAP2_RING3MWAIT; @@ -488,6 +484,34 @@ static void intel_bsp_resume(struct cpuinfo_x86 *c) init_intel_energy_perf(c); } +static void init_cpuid_fault(struct cpuinfo_x86 *c) +{ + u64 msr; + + if (!rdmsrl_safe(MSR_PLATFORM_INFO, &msr)) { + if (msr & MSR_PLATFORM_INFO_CPUID_FAULT) + set_cpu_cap(c, X86_FEATURE_CPUID_FAULT); + } +} + +static void init_intel_misc_features(struct cpuinfo_x86 *c) +{ + u64 msr; + + if (rdmsrl_safe(MSR_MISC_FEATURES_ENABLES, &msr)) + return; + + /* Clear all MISC features */ + this_cpu_write(msr_misc_features_shadow, 0); + + /* Check features and update capabilities and shadow control bits */ + init_cpuid_fault(c); + probe_xeon_phi_r3mwait(c); + + msr = this_cpu_read(msr_misc_features_shadow); + wrmsrl(MSR_MISC_FEATURES_ENABLES, msr); +} + static void init_intel(struct cpuinfo_x86 *c) { unsigned int l2 = 0; @@ -602,7 +626,7 @@ static void init_intel(struct cpuinfo_x86 *c) init_intel_energy_perf(c); - probe_xeon_phi_r3mwait(c); + init_intel_misc_features(c); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c index 5a533fefefa0..5b366462f579 100644 --- a/arch/x86/kernel/cpu/intel_rdt.c +++ b/arch/x86/kernel/cpu/intel_rdt.c @@ -32,55 +32,98 @@ #include <asm/intel-family.h> #include <asm/intel_rdt.h> +#define MAX_MBA_BW 100u +#define MBA_IS_LINEAR 0x4 + /* Mutex to protect rdtgroup access. */ DEFINE_MUTEX(rdtgroup_mutex); DEFINE_PER_CPU_READ_MOSTLY(int, cpu_closid); +/* + * Used to store the max resource name width and max resource data width + * to display the schemata in a tabular format + */ +int max_name_width, max_data_width; + +static void +mba_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r); +static void +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[] = { { - .name = "L3", - .domains = domain_init(RDT_RESOURCE_L3), - .msr_base = IA32_L3_CBM_BASE, - .min_cbm_bits = 1, - .cache_level = 3, - .cbm_idx_multi = 1, - .cbm_idx_offset = 0 + .name = "L3", + .domains = domain_init(RDT_RESOURCE_L3), + .msr_base = IA32_L3_CBM_BASE, + .msr_update = cat_wrmsr, + .cache_level = 3, + .cache = { + .min_cbm_bits = 1, + .cbm_idx_mult = 1, + .cbm_idx_offset = 0, + }, + .parse_ctrlval = parse_cbm, + .format_str = "%d=%0*x", + }, + { + .name = "L3DATA", + .domains = domain_init(RDT_RESOURCE_L3DATA), + .msr_base = IA32_L3_CBM_BASE, + .msr_update = cat_wrmsr, + .cache_level = 3, + .cache = { + .min_cbm_bits = 1, + .cbm_idx_mult = 2, + .cbm_idx_offset = 0, + }, + .parse_ctrlval = parse_cbm, + .format_str = "%d=%0*x", }, { - .name = "L3DATA", - .domains = domain_init(RDT_RESOURCE_L3DATA), - .msr_base = IA32_L3_CBM_BASE, - .min_cbm_bits = 1, - .cache_level = 3, - .cbm_idx_multi = 2, - .cbm_idx_offset = 0 + .name = "L3CODE", + .domains = domain_init(RDT_RESOURCE_L3CODE), + .msr_base = IA32_L3_CBM_BASE, + .msr_update = cat_wrmsr, + .cache_level = 3, + .cache = { + .min_cbm_bits = 1, + .cbm_idx_mult = 2, + .cbm_idx_offset = 1, + }, + .parse_ctrlval = parse_cbm, + .format_str = "%d=%0*x", }, { - .name = "L3CODE", - .domains = domain_init(RDT_RESOURCE_L3CODE), - .msr_base = IA32_L3_CBM_BASE, - .min_cbm_bits = 1, - .cache_level = 3, - .cbm_idx_multi = 2, - .cbm_idx_offset = 1 + .name = "L2", + .domains = domain_init(RDT_RESOURCE_L2), + .msr_base = IA32_L2_CBM_BASE, + .msr_update = cat_wrmsr, + .cache_level = 2, + .cache = { + .min_cbm_bits = 1, + .cbm_idx_mult = 1, + .cbm_idx_offset = 0, + }, + .parse_ctrlval = parse_cbm, + .format_str = "%d=%0*x", }, { - .name = "L2", - .domains = domain_init(RDT_RESOURCE_L2), - .msr_base = IA32_L2_CBM_BASE, - .min_cbm_bits = 1, - .cache_level = 2, - .cbm_idx_multi = 1, - .cbm_idx_offset = 0 + .name = "MB", + .domains = domain_init(RDT_RESOURCE_MBA), + .msr_base = IA32_MBA_THRTL_BASE, + .msr_update = mba_wrmsr, + .cache_level = 3, + .parse_ctrlval = parse_bw, + .format_str = "%d=%*d", }, }; -static int cbm_idx(struct rdt_resource *r, int closid) +static unsigned int cbm_idx(struct rdt_resource *r, unsigned int closid) { - return closid * r->cbm_idx_multi + r->cbm_idx_offset; + return closid * r->cache.cbm_idx_mult + r->cache.cbm_idx_offset; } /* @@ -118,9 +161,9 @@ static inline bool cache_alloc_hsw_probe(void) return false; r->num_closid = 4; - r->cbm_len = 20; - r->max_cbm = max_cbm; - r->min_cbm_bits = 2; + r->default_ctrl = max_cbm; + r->cache.cbm_len = 20; + r->cache.min_cbm_bits = 2; r->capable = true; r->enabled = true; @@ -130,16 +173,66 @@ static inline bool cache_alloc_hsw_probe(void) return false; } -static void rdt_get_config(int idx, struct rdt_resource *r) +/* + * rdt_get_mb_table() - get a mapping of bandwidth(b/w) percentage values + * exposed to user interface and the h/w understandable delay values. + * + * The non-linear delay values have the granularity of power of two + * and also the h/w does not guarantee a curve for configured delay + * values vs. actual b/w enforced. + * Hence we need a mapping that is pre calibrated so the user can + * express the memory b/w as a percentage value. + */ +static inline bool rdt_get_mb_table(struct rdt_resource *r) +{ + /* + * There are no Intel SKUs as of now to support non-linear delay. + */ + pr_info("MBA b/w map not implemented for cpu:%d, model:%d", + boot_cpu_data.x86, boot_cpu_data.x86_model); + + return false; +} + +static bool rdt_get_mem_config(struct rdt_resource *r) +{ + union cpuid_0x10_3_eax eax; + union cpuid_0x10_x_edx edx; + u32 ebx, ecx; + + cpuid_count(0x00000010, 3, &eax.full, &ebx, &ecx, &edx.full); + r->num_closid = edx.split.cos_max + 1; + r->membw.max_delay = eax.split.max_delay + 1; + r->default_ctrl = MAX_MBA_BW; + if (ecx & MBA_IS_LINEAR) { + r->membw.delay_linear = true; + r->membw.min_bw = MAX_MBA_BW - r->membw.max_delay; + r->membw.bw_gran = MAX_MBA_BW - r->membw.max_delay; + } else { + if (!rdt_get_mb_table(r)) + return false; + } + r->data_width = 3; + rdt_get_mba_infofile(r); + + r->capable = true; + r->enabled = true; + + return true; +} + +static void rdt_get_cache_config(int idx, struct rdt_resource *r) { union cpuid_0x10_1_eax eax; - union cpuid_0x10_1_edx edx; + union cpuid_0x10_x_edx edx; u32 ebx, ecx; cpuid_count(0x00000010, idx, &eax.full, &ebx, &ecx, &edx.full); r->num_closid = edx.split.cos_max + 1; - r->cbm_len = eax.split.cbm_len + 1; - r->max_cbm = BIT_MASK(eax.split.cbm_len + 1) - 1; + r->cache.cbm_len = eax.split.cbm_len + 1; + r->default_ctrl = BIT_MASK(eax.split.cbm_len + 1) - 1; + r->data_width = (r->cache.cbm_len + 3) / 4; + rdt_get_cache_infofile(r); r->capable = true; r->enabled = true; } @@ -150,8 +243,9 @@ static void rdt_get_cdp_l3_config(int type) struct rdt_resource *r = &rdt_resources_all[type]; r->num_closid = r_l3->num_closid / 2; - r->cbm_len = r_l3->cbm_len; - r->max_cbm = r_l3->max_cbm; + 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; /* * By default, CDP is disabled. CDP can be enabled by mount parameter @@ -160,33 +254,6 @@ static void rdt_get_cdp_l3_config(int type) r->enabled = false; } -static inline bool get_rdt_resources(void) -{ - bool ret = false; - - if (cache_alloc_hsw_probe()) - return true; - - if (!boot_cpu_has(X86_FEATURE_RDT_A)) - return false; - - if (boot_cpu_has(X86_FEATURE_CAT_L3)) { - rdt_get_config(1, &rdt_resources_all[RDT_RESOURCE_L3]); - if (boot_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)) { - /* CPUID 0x10.2 fields are same format at 0x10.1 */ - rdt_get_config(2, &rdt_resources_all[RDT_RESOURCE_L2]); - ret = true; - } - - return ret; -} - static int get_cache_id(int cpu, int level) { struct cpu_cacheinfo *ci = get_cpu_cacheinfo(cpu); @@ -200,29 +267,55 @@ static int get_cache_id(int cpu, int level) return -1; } -void rdt_cbm_update(void *arg) +/* + * Map the memory b/w percentage value to delay values + * that can be written to QOS_MSRs. + * There are currently no SKUs which support non linear delay values. + */ +static u32 delay_bw_map(unsigned long bw, struct rdt_resource *r) { - struct msr_param *m = (struct msr_param *)arg; + if (r->membw.delay_linear) + return MAX_MBA_BW - bw; + + pr_warn_once("Non Linear delay-bw map not supported but queried\n"); + return r->default_ctrl; +} + +static void +mba_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r) +{ + unsigned int i; + + /* Write the delay values for mba. */ + for (i = m->low; i < m->high; i++) + wrmsrl(r->msr_base + i, delay_bw_map(d->ctrl_val[i], r)); +} + +static void +cat_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r) +{ + unsigned int i; + + for (i = m->low; i < m->high; i++) + wrmsrl(r->msr_base + cbm_idx(r, i), d->ctrl_val[i]); +} + +void rdt_ctrl_update(void *arg) +{ + struct msr_param *m = arg; struct rdt_resource *r = m->res; - int i, cpu = smp_processor_id(); + 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)) - goto found; + if (cpumask_test_cpu(cpu, &d->cpu_mask)) { + r->msr_update(d, m, r); + return; + } } - pr_info_once("cpu %d not found in any domain for resource %s\n", + pr_warn_once("cpu %d not found in any domain for resource %s\n", cpu, r->name); - - return; - -found: - for (i = m->low; i < m->high; i++) { - int idx = cbm_idx(r, i); - - wrmsrl(r->msr_base + idx, d->cbm[i]); - } } /* @@ -258,6 +351,32 @@ static struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id, return NULL; } +static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_domain *d) +{ + struct msr_param m; + u32 *dc; + int i; + + dc = kmalloc_array(r->num_closid, sizeof(*d->ctrl_val), GFP_KERNEL); + if (!dc) + return -ENOMEM; + + d->ctrl_val = dc; + + /* + * Initialize the Control MSRs to having no control. + * For Cache Allocation: Set all bits in cbm + * For Memory Allocation: Set b/w requested to 100 + */ + for (i = 0; i < r->num_closid; i++, dc++) + *dc = r->default_ctrl; + + m.low = 0; + m.high = r->num_closid; + r->msr_update(d, &m, r); + return 0; +} + /* * domain_add_cpu - Add a cpu to a resource's domain list. * @@ -273,7 +392,7 @@ static struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id, */ static void domain_add_cpu(int cpu, struct rdt_resource *r) { - int i, id = get_cache_id(cpu, r->cache_level); + int id = get_cache_id(cpu, r->cache_level); struct list_head *add_pos = NULL; struct rdt_domain *d; @@ -294,22 +413,13 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r) d->id = id; - d->cbm = kmalloc_array(r->num_closid, sizeof(*d->cbm), GFP_KERNEL); - if (!d->cbm) { + if (domain_setup_ctrlval(r, d)) { kfree(d); return; } - for (i = 0; i < r->num_closid; i++) { - int idx = cbm_idx(r, i); - - d->cbm[i] = r->max_cbm; - wrmsrl(r->msr_base + idx, d->cbm[i]); - } - cpumask_set_cpu(cpu, &d->cpu_mask); list_add_tail(&d->list, add_pos); - r->num_domains++; } static void domain_remove_cpu(int cpu, struct rdt_resource *r) @@ -325,8 +435,7 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r) cpumask_clear_cpu(cpu, &d->cpu_mask); if (cpumask_empty(&d->cpu_mask)) { - r->num_domains--; - kfree(d->cbm); + kfree(d->ctrl_val); list_del(&d->list); kfree(d); } @@ -374,6 +483,57 @@ static int intel_rdt_offline_cpu(unsigned int cpu) return 0; } +/* + * Choose a width for the resource name and resource data based on the + * resource that has widest name and cbm. + */ +static __init void rdt_init_padding(void) +{ + struct rdt_resource *r; + int cl; + + for_each_capable_rdt_resource(r) { + cl = strlen(r->name); + if (cl > max_name_width) + max_name_width = cl; + + if (r->data_width > max_data_width) + max_data_width = r->data_width; + } +} + +static __init bool get_rdt_resources(void) +{ + bool ret = false; + + if (cache_alloc_hsw_probe()) + 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)) { + 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)) { + /* CPUID 0x10.2 fields are same format at 0x10.1 */ + rdt_get_cache_config(2, &rdt_resources_all[RDT_RESOURCE_L2]); + ret = true; + } + + if (boot_cpu_has(X86_FEATURE_MBA)) { + if (rdt_get_mem_config(&rdt_resources_all[RDT_RESOURCE_MBA])) + ret = true; + } + + return ret; +} + static int __init intel_rdt_late_init(void) { struct rdt_resource *r; @@ -382,6 +542,8 @@ static int __init intel_rdt_late_init(void) if (!get_rdt_resources()) return -ENODEV; + rdt_init_padding(); + state = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/rdt/cat:online:", intel_rdt_online_cpu, intel_rdt_offline_cpu); diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c index 9ac2a5cdd9c2..f5af0cc7eb0d 100644 --- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c +++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c @@ -174,6 +174,13 @@ static struct kernfs_ops rdtgroup_kf_single_ops = { .seq_show = rdtgroup_seqfile_show, }; +static bool is_cpu_list(struct kernfs_open_file *of) +{ + struct rftype *rft = of->kn->priv; + + return rft->flags & RFTYPE_FLAGS_CPUS_LIST; +} + static int rdtgroup_cpus_show(struct kernfs_open_file *of, struct seq_file *s, void *v) { @@ -182,10 +189,12 @@ static int rdtgroup_cpus_show(struct kernfs_open_file *of, rdtgrp = rdtgroup_kn_lock_live(of->kn); - if (rdtgrp) - seq_printf(s, "%*pb\n", cpumask_pr_args(&rdtgrp->cpu_mask)); - else + if (rdtgrp) { + seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n", + cpumask_pr_args(&rdtgrp->cpu_mask)); + } else { ret = -ENOENT; + } rdtgroup_kn_unlock(of->kn); return ret; @@ -252,7 +261,11 @@ static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of, goto unlock; } - ret = cpumask_parse(buf, newmask); + if (is_cpu_list(of)) + ret = cpulist_parse(buf, newmask); + else + ret = cpumask_parse(buf, newmask); + if (ret) goto unlock; @@ -473,6 +486,14 @@ static struct rftype rdtgroup_base_files[] = { .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, @@ -494,32 +515,56 @@ static int rdt_num_closids_show(struct kernfs_open_file *of, struct rdt_resource *r = of->kn->parent->priv; seq_printf(seq, "%d\n", r->num_closid); + return 0; +} + +static int rdt_default_ctrl_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->default_ctrl); return 0; } -static int rdt_cbm_mask_show(struct kernfs_open_file *of, +static int rdt_min_cbm_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->max_cbm); + seq_printf(seq, "%u\n", r->cache.min_cbm_bits); + return 0; +} + +static int rdt_min_bw_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", r->membw.min_bw); return 0; } -static int rdt_min_cbm_bits_show(struct kernfs_open_file *of, +static int rdt_bw_gran_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->min_cbm_bits); + seq_printf(seq, "%u\n", r->membw.bw_gran); + return 0; +} + +static int rdt_delay_linear_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", r->membw.delay_linear); return 0; } /* rdtgroup information files for one cache resource. */ -static struct rftype res_info_files[] = { +static struct rftype res_cache_info_files[] = { { .name = "num_closids", .mode = 0444, @@ -530,7 +575,7 @@ static struct rftype res_info_files[] = { .name = "cbm_mask", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, - .seq_show = rdt_cbm_mask_show, + .seq_show = rdt_default_ctrl_show, }, { .name = "min_cbm_bits", @@ -540,11 +585,52 @@ static struct rftype res_info_files[] = { }, }; +/* rdtgroup information files for memory bandwidth. */ +static struct rftype res_mba_info_files[] = { + { + .name = "num_closids", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_num_closids_show, + }, + { + .name = "min_bandwidth", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_min_bw_show, + }, + { + .name = "bandwidth_gran", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_bw_gran_show, + }, + { + .name = "delay_linear", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_delay_linear_show, + }, +}; + +void rdt_get_mba_infofile(struct rdt_resource *r) +{ + r->info_files = res_mba_info_files; + r->nr_info_files = ARRAY_SIZE(res_mba_info_files); +} + +void rdt_get_cache_infofile(struct rdt_resource *r) +{ + r->info_files = res_cache_info_files; + r->nr_info_files = ARRAY_SIZE(res_cache_info_files); +} + 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; + int ret, len; /* create the directory */ kn_info = kernfs_create_dir(parent_kn, "info", parent_kn->mode, NULL); @@ -563,8 +649,11 @@ static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn) ret = rdtgroup_kn_set_ugid(kn_subdir); if (ret) goto out_destroy; - ret = rdtgroup_add_files(kn_subdir, res_info_files, - ARRAY_SIZE(res_info_files)); + + res_info_files = r->info_files; + len = r->nr_info_files; + + ret = rdtgroup_add_files(kn_subdir, res_info_files, len); if (ret) goto out_destroy; kernfs_activate(kn_subdir); @@ -780,7 +869,7 @@ out: return dentry; } -static int reset_all_cbms(struct rdt_resource *r) +static int reset_all_ctrls(struct rdt_resource *r) { struct msr_param msr_param; cpumask_var_t cpu_mask; @@ -803,14 +892,14 @@ static int reset_all_cbms(struct rdt_resource *r) cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask); for (i = 0; i < r->num_closid; i++) - d->cbm[i] = r->max_cbm; + d->ctrl_val[i] = r->default_ctrl; } cpu = get_cpu(); /* Update CBM on this cpu if it's in cpu_mask. */ if (cpumask_test_cpu(cpu, cpu_mask)) - rdt_cbm_update(&msr_param); + rdt_ctrl_update(&msr_param); /* Update CBM on all other cpus in cpu_mask. */ - smp_call_function_many(cpu_mask, rdt_cbm_update, &msr_param, 1); + smp_call_function_many(cpu_mask, rdt_ctrl_update, &msr_param, 1); put_cpu(); free_cpumask_var(cpu_mask); @@ -896,7 +985,7 @@ static void rdt_kill_sb(struct super_block *sb) /*Put everything back to default values. */ for_each_enabled_rdt_resource(r) - reset_all_cbms(r); + reset_all_ctrls(r); cdp_disable(); rmdir_all_sub(); static_branch_disable(&rdt_enable_key); diff --git a/arch/x86/kernel/cpu/intel_rdt_schemata.c b/arch/x86/kernel/cpu/intel_rdt_schemata.c index f369cb8db0d5..406d7a6532f9 100644 --- a/arch/x86/kernel/cpu/intel_rdt_schemata.c +++ b/arch/x86/kernel/cpu/intel_rdt_schemata.c @@ -29,26 +29,77 @@ #include <asm/intel_rdt.h> /* + * Check whether MBA bandwidth percentage value is correct. The value is + * checked against the minimum and max bandwidth values specified by the + * hardware. The allocated bandwidth percentage is rounded to the next + * control step available on the hardware. + */ +static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r) +{ + unsigned long bw; + int ret; + + /* + * Only linear delay values is supported for current Intel SKUs. + */ + if (!r->membw.delay_linear) + return false; + + ret = kstrtoul(buf, 10, &bw); + if (ret) + return false; + + if (bw < r->membw.min_bw || bw > r->default_ctrl) + return false; + + *data = roundup(bw, (unsigned long)r->membw.bw_gran); + return true; +} + +int parse_bw(char *buf, struct rdt_resource *r, struct rdt_domain *d) +{ + unsigned long data; + + if (d->have_new_ctrl) + return -EINVAL; + + if (!bw_validate(buf, &data, r)) + return -EINVAL; + d->new_ctrl = data; + d->have_new_ctrl = true; + + return 0; +} + +/* * Check whether a cache bit mask is valid. The SDM says: * Please note that all (and only) contiguous '1' combinations * are allowed (e.g. FFFFH, 0FF0H, 003CH, etc.). * Additionally Haswell requires at least two bits set. */ -static bool cbm_validate(unsigned long var, struct rdt_resource *r) +static bool cbm_validate(char *buf, unsigned long *data, struct rdt_resource *r) { - unsigned long first_bit, zero_bit; + unsigned long first_bit, zero_bit, val; + unsigned int cbm_len = r->cache.cbm_len; + int ret; + + ret = kstrtoul(buf, 16, &val); + if (ret) + return false; - if (var == 0 || var > r->max_cbm) + if (val == 0 || val > r->default_ctrl) return false; - first_bit = find_first_bit(&var, r->cbm_len); - zero_bit = find_next_zero_bit(&var, r->cbm_len, first_bit); + first_bit = find_first_bit(&val, cbm_len); + zero_bit = find_next_zero_bit(&val, cbm_len, first_bit); - if (find_next_bit(&var, r->cbm_len, zero_bit) < r->cbm_len) + if (find_next_bit(&val, cbm_len, zero_bit) < cbm_len) return false; - if ((zero_bit - first_bit) < r->min_cbm_bits) + if ((zero_bit - first_bit) < r->cache.min_cbm_bits) return false; + + *data = val; return true; } @@ -56,17 +107,17 @@ static bool cbm_validate(unsigned long var, struct rdt_resource *r) * Read one cache bit mask (hex). Check that it is valid for the current * resource type. */ -static int parse_cbm(char *buf, struct rdt_resource *r) +int parse_cbm(char *buf, struct rdt_resource *r, struct rdt_domain *d) { unsigned long data; - int ret; - ret = kstrtoul(buf, 16, &data); - if (ret) - return ret; - if (!cbm_validate(data, r)) + if (d->have_new_ctrl) return -EINVAL; - r->tmp_cbms[r->num_tmp_cbms++] = data; + + if(!cbm_validate(buf, &data, r)) + return -EINVAL; + d->new_ctrl = data; + d->have_new_ctrl = true; return 0; } @@ -74,8 +125,8 @@ static int parse_cbm(char *buf, struct rdt_resource *r) /* * For each domain in this resource we expect to find a series of: * id=mask - * separated by ";". The "id" is in decimal, and must appear in the - * right order. + * separated by ";". The "id" is in decimal, and must match one of + * the "id"s for this resource. */ static int parse_line(char *line, struct rdt_resource *r) { @@ -83,21 +134,22 @@ static int parse_line(char *line, struct rdt_resource *r) struct rdt_domain *d; unsigned long dom_id; +next: + if (!line || line[0] == '\0') + return 0; + dom = strsep(&line, ";"); + id = strsep(&dom, "="); + if (!dom || kstrtoul(id, 10, &dom_id)) + return -EINVAL; + dom = strim(dom); list_for_each_entry(d, &r->domains, list) { - dom = strsep(&line, ";"); - if (!dom) - return -EINVAL; - id = strsep(&dom, "="); - if (kstrtoul(id, 10, &dom_id) || dom_id != d->id) - return -EINVAL; - if (parse_cbm(dom, r)) - return -EINVAL; + if (d->id == dom_id) { + if (r->parse_ctrlval(dom, r, d)) + return -EINVAL; + goto next; + } } - - /* Any garbage at the end of the line? */ - if (line && line[0]) - return -EINVAL; - return 0; + return -EINVAL; } static int update_domains(struct rdt_resource *r, int closid) @@ -105,7 +157,7 @@ static int update_domains(struct rdt_resource *r, int closid) struct msr_param msr_param; cpumask_var_t cpu_mask; struct rdt_domain *d; - int cpu, idx = 0; + int cpu; if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL)) return -ENOMEM; @@ -115,30 +167,46 @@ static int update_domains(struct rdt_resource *r, int closid) msr_param.res = r; list_for_each_entry(d, &r->domains, list) { - cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask); - d->cbm[msr_param.low] = r->tmp_cbms[idx++]; + if (d->have_new_ctrl && d->new_ctrl != d->ctrl_val[closid]) { + cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask); + d->ctrl_val[closid] = d->new_ctrl; + } } + if (cpumask_empty(cpu_mask)) + goto done; cpu = get_cpu(); /* Update CBM on this cpu if it's in cpu_mask. */ if (cpumask_test_cpu(cpu, cpu_mask)) - rdt_cbm_update(&msr_param); + rdt_ctrl_update(&msr_param); /* Update CBM on other cpus. */ - smp_call_function_many(cpu_mask, rdt_cbm_update, &msr_param, 1); + smp_call_function_many(cpu_mask, rdt_ctrl_update, &msr_param, 1); put_cpu(); +done: free_cpumask_var(cpu_mask); return 0; } +static int rdtgroup_parse_resource(char *resname, char *tok, int closid) +{ + struct rdt_resource *r; + + for_each_enabled_rdt_resource(r) { + if (!strcmp(resname, r->name) && closid < r->num_closid) + return parse_line(tok, r); + } + return -EINVAL; +} + ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct rdtgroup *rdtgrp; + struct rdt_domain *dom; struct rdt_resource *r; char *tok, *resname; int closid, ret = 0; - u32 *l3_cbms = NULL; /* Valid input requires a trailing newline */ if (nbytes == 0 || buf[nbytes - 1] != '\n') @@ -153,44 +221,20 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, closid = rdtgrp->closid; - /* get scratch space to save all the masks while we validate input */ for_each_enabled_rdt_resource(r) { - r->tmp_cbms = kcalloc(r->num_domains, sizeof(*l3_cbms), - GFP_KERNEL); - if (!r->tmp_cbms) { - ret = -ENOMEM; - goto out; - } - r->num_tmp_cbms = 0; + list_for_each_entry(dom, &r->domains, list) + dom->have_new_ctrl = false; } while ((tok = strsep(&buf, "\n")) != NULL) { - resname = strsep(&tok, ":"); + resname = strim(strsep(&tok, ":")); if (!tok) { ret = -EINVAL; goto out; } - for_each_enabled_rdt_resource(r) { - if (!strcmp(resname, r->name) && - closid < r->num_closid) { - ret = parse_line(tok, r); - if (ret) - goto out; - break; - } - } - if (!r->name) { - ret = -EINVAL; - goto out; - } - } - - /* Did the parser find all the masks we need? */ - for_each_enabled_rdt_resource(r) { - if (r->num_tmp_cbms != r->num_domains) { - ret = -EINVAL; + ret = rdtgroup_parse_resource(resname, tok, closid); + if (ret) goto out; - } } for_each_enabled_rdt_resource(r) { @@ -201,10 +245,6 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, out: rdtgroup_kn_unlock(of->kn); - for_each_enabled_rdt_resource(r) { - kfree(r->tmp_cbms); - r->tmp_cbms = NULL; - } return ret ?: nbytes; } @@ -213,11 +253,12 @@ static void show_doms(struct seq_file *s, struct rdt_resource *r, int closid) struct rdt_domain *dom; bool sep = false; - seq_printf(s, "%s:", r->name); + seq_printf(s, "%*s:", max_name_width, r->name); list_for_each_entry(dom, &r->domains, list) { if (sep) seq_puts(s, ";"); - seq_printf(s, "%d=%x", dom->id, dom->cbm[closid]); + seq_printf(s, r->format_str, dom->id, max_data_width, + dom->ctrl_val[closid]); sep = true; } seq_puts(s, "\n"); diff --git a/arch/x86/kernel/cpu/mcheck/Makefile b/arch/x86/kernel/cpu/mcheck/Makefile index a3311c886194..43051f0777d4 100644 --- a/arch/x86/kernel/cpu/mcheck/Makefile +++ b/arch/x86/kernel/cpu/mcheck/Makefile @@ -9,3 +9,5 @@ obj-$(CONFIG_X86_MCE_INJECT) += mce-inject.o obj-$(CONFIG_X86_THERMAL_VECTOR) += therm_throt.o obj-$(CONFIG_ACPI_APEI) += mce-apei.o + +obj-$(CONFIG_X86_MCELOG_LEGACY) += dev-mcelog.o diff --git a/arch/x86/kernel/cpu/mcheck/dev-mcelog.c b/arch/x86/kernel/cpu/mcheck/dev-mcelog.c new file mode 100644 index 000000000000..9c632cb88546 --- /dev/null +++ b/arch/x86/kernel/cpu/mcheck/dev-mcelog.c @@ -0,0 +1,397 @@ +/* + * /dev/mcelog driver + * + * K8 parts Copyright 2002,2003 Andi Kleen, SuSE Labs. + * Rest from unknown author(s). + * 2004 Andi Kleen. Rewrote most of it. + * Copyright 2008 Intel Corporation + * Author: Andi Kleen + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/miscdevice.h> +#include <linux/slab.h> +#include <linux/kmod.h> +#include <linux/poll.h> + +#include "mce-internal.h" + +static DEFINE_MUTEX(mce_chrdev_read_mutex); + +static char mce_helper[128]; +static char *mce_helper_argv[2] = { mce_helper, NULL }; + +#define mce_log_get_idx_check(p) \ +({ \ + RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \ + !lockdep_is_held(&mce_chrdev_read_mutex), \ + "suspicious mce_log_get_idx_check() usage"); \ + smp_load_acquire(&(p)); \ +}) + +/* + * Lockless MCE logging infrastructure. + * This avoids deadlocks on printk locks without having to break locks. Also + * separate MCEs from kernel messages to avoid bogus bug reports. + */ + +static struct mce_log_buffer mcelog = { + .signature = MCE_LOG_SIGNATURE, + .len = MCE_LOG_LEN, + .recordlen = sizeof(struct mce), +}; + +static DECLARE_WAIT_QUEUE_HEAD(mce_chrdev_wait); + +/* User mode helper program triggered by machine check event */ +extern char mce_helper[128]; + +static int dev_mce_log(struct notifier_block *nb, unsigned long val, + void *data) +{ + struct mce *mce = (struct mce *)data; + unsigned int next, entry; + + wmb(); + for (;;) { + entry = mce_log_get_idx_check(mcelog.next); + for (;;) { + + /* + * When the buffer fills up discard new entries. + * Assume that the earlier errors are the more + * interesting ones: + */ + if (entry >= MCE_LOG_LEN) { + set_bit(MCE_OVERFLOW, + (unsigned long *)&mcelog.flags); + return NOTIFY_OK; + } + /* Old left over entry. Skip: */ + if (mcelog.entry[entry].finished) { + entry++; + continue; + } + break; + } + smp_rmb(); + next = entry + 1; + if (cmpxchg(&mcelog.next, entry, next) == entry) + break; + } + memcpy(mcelog.entry + entry, mce, sizeof(struct mce)); + wmb(); + mcelog.entry[entry].finished = 1; + wmb(); + + /* wake processes polling /dev/mcelog */ + wake_up_interruptible(&mce_chrdev_wait); + + return NOTIFY_OK; +} + +static struct notifier_block dev_mcelog_nb = { + .notifier_call = dev_mce_log, + .priority = MCE_PRIO_MCELOG, +}; + +static void mce_do_trigger(struct work_struct *work) +{ + call_usermodehelper(mce_helper, mce_helper_argv, NULL, UMH_NO_WAIT); +} + +static DECLARE_WORK(mce_trigger_work, mce_do_trigger); + + +void mce_work_trigger(void) +{ + if (mce_helper[0]) + schedule_work(&mce_trigger_work); +} + +static ssize_t +show_trigger(struct device *s, struct device_attribute *attr, char *buf) +{ + strcpy(buf, mce_helper); + strcat(buf, "\n"); + return strlen(mce_helper) + 1; +} + +static ssize_t set_trigger(struct device *s, struct device_attribute *attr, + const char *buf, size_t siz) +{ + char *p; + + strncpy(mce_helper, buf, sizeof(mce_helper)); + mce_helper[sizeof(mce_helper)-1] = 0; + p = strchr(mce_helper, '\n'); + + if (p) + *p = 0; + + return strlen(mce_helper) + !!p; +} + +DEVICE_ATTR(trigger, 0644, show_trigger, set_trigger); + +/* + * mce_chrdev: Character device /dev/mcelog to read and clear the MCE log. + */ + +static DEFINE_SPINLOCK(mce_chrdev_state_lock); +static int mce_chrdev_open_count; /* #times opened */ +static int mce_chrdev_open_exclu; /* already open exclusive? */ + +static int mce_chrdev_open(struct inode *inode, struct file *file) +{ + spin_lock(&mce_chrdev_state_lock); + + if (mce_chrdev_open_exclu || + (mce_chrdev_open_count && (file->f_flags & O_EXCL))) { + spin_unlock(&mce_chrdev_state_lock); + + return -EBUSY; + } + + if (file->f_flags & O_EXCL) + mce_chrdev_open_exclu = 1; + mce_chrdev_open_count++; + + spin_unlock(&mce_chrdev_state_lock); + + return nonseekable_open(inode, file); +} + +static int mce_chrdev_release(struct inode *inode, struct file *file) +{ + spin_lock(&mce_chrdev_state_lock); + + mce_chrdev_open_count--; + mce_chrdev_open_exclu = 0; + + spin_unlock(&mce_chrdev_state_lock); + + return 0; +} + +static void collect_tscs(void *data) +{ + unsigned long *cpu_tsc = (unsigned long *)data; + + cpu_tsc[smp_processor_id()] = rdtsc(); +} + +static int mce_apei_read_done; + +/* Collect MCE record of previous boot in persistent storage via APEI ERST. */ +static int __mce_read_apei(char __user **ubuf, size_t usize) +{ + int rc; + u64 record_id; + struct mce m; + + if (usize < sizeof(struct mce)) + return -EINVAL; + + rc = apei_read_mce(&m, &record_id); + /* Error or no more MCE record */ + if (rc <= 0) { + mce_apei_read_done = 1; + /* + * When ERST is disabled, mce_chrdev_read() should return + * "no record" instead of "no device." + */ + if (rc == -ENODEV) + return 0; + return rc; + } + rc = -EFAULT; + if (copy_to_user(*ubuf, &m, sizeof(struct mce))) + return rc; + /* + * In fact, we should have cleared the record after that has + * been flushed to the disk or sent to network in + * /sbin/mcelog, but we have no interface to support that now, + * so just clear it to avoid duplication. + */ + rc = apei_clear_mce(record_id); + if (rc) { + mce_apei_read_done = 1; + return rc; + } + *ubuf += sizeof(struct mce); + + return 0; +} + +static ssize_t mce_chrdev_read(struct file *filp, char __user *ubuf, + size_t usize, loff_t *off) +{ + char __user *buf = ubuf; + unsigned long *cpu_tsc; + unsigned prev, next; + int i, err; + + cpu_tsc = kmalloc(nr_cpu_ids * sizeof(long), GFP_KERNEL); + if (!cpu_tsc) + return -ENOMEM; + + mutex_lock(&mce_chrdev_read_mutex); + + if (!mce_apei_read_done) { + err = __mce_read_apei(&buf, usize); + if (err || buf != ubuf) + goto out; + } + + next = mce_log_get_idx_check(mcelog.next); + + /* Only supports full reads right now */ + err = -EINVAL; + if (*off != 0 || usize < MCE_LOG_LEN*sizeof(struct mce)) + goto out; + + err = 0; + prev = 0; + do { + for (i = prev; i < next; i++) { + unsigned long start = jiffies; + struct mce *m = &mcelog.entry[i]; + + while (!m->finished) { + if (time_after_eq(jiffies, start + 2)) { + memset(m, 0, sizeof(*m)); + goto timeout; + } + cpu_relax(); + } + smp_rmb(); + err |= copy_to_user(buf, m, sizeof(*m)); + buf += sizeof(*m); +timeout: + ; + } + + memset(mcelog.entry + prev, 0, + (next - prev) * sizeof(struct mce)); + prev = next; + next = cmpxchg(&mcelog.next, prev, 0); + } while (next != prev); + + synchronize_sched(); + + /* + * Collect entries that were still getting written before the + * synchronize. + */ + on_each_cpu(collect_tscs, cpu_tsc, 1); + + for (i = next; i < MCE_LOG_LEN; i++) { + struct mce *m = &mcelog.entry[i]; + + if (m->finished && m->tsc < cpu_tsc[m->cpu]) { + err |= copy_to_user(buf, m, sizeof(*m)); + smp_rmb(); + buf += sizeof(*m); + memset(m, 0, sizeof(*m)); + } + } + + if (err) + err = -EFAULT; + +out: + mutex_unlock(&mce_chrdev_read_mutex); + kfree(cpu_tsc); + + return err ? err : buf - ubuf; +} + +static unsigned int mce_chrdev_poll(struct file *file, poll_table *wait) +{ + poll_wait(file, &mce_chrdev_wait, wait); + if (READ_ONCE(mcelog.next)) + return POLLIN | POLLRDNORM; + if (!mce_apei_read_done && apei_check_mce()) + return POLLIN | POLLRDNORM; + return 0; +} + +static long mce_chrdev_ioctl(struct file *f, unsigned int cmd, + unsigned long arg) +{ + int __user *p = (int __user *)arg; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + switch (cmd) { + case MCE_GET_RECORD_LEN: + return put_user(sizeof(struct mce), p); + case MCE_GET_LOG_LEN: + return put_user(MCE_LOG_LEN, p); + case MCE_GETCLEAR_FLAGS: { + unsigned flags; + + do { + flags = mcelog.flags; + } while (cmpxchg(&mcelog.flags, flags, 0) != flags); + + return put_user(flags, p); + } + default: + return -ENOTTY; + } +} + +static ssize_t (*mce_write)(struct file *filp, const char __user *ubuf, + size_t usize, loff_t *off); + +void register_mce_write_callback(ssize_t (*fn)(struct file *filp, + const char __user *ubuf, + size_t usize, loff_t *off)) +{ + mce_write = fn; +} +EXPORT_SYMBOL_GPL(register_mce_write_callback); + +static ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf, + size_t usize, loff_t *off) +{ + if (mce_write) + return mce_write(filp, ubuf, usize, off); + else + return -EINVAL; +} + +static const struct file_operations mce_chrdev_ops = { + .open = mce_chrdev_open, + .release = mce_chrdev_release, + .read = mce_chrdev_read, + .write = mce_chrdev_write, + .poll = mce_chrdev_poll, + .unlocked_ioctl = mce_chrdev_ioctl, + .llseek = no_llseek, +}; + +static struct miscdevice mce_chrdev_device = { + MISC_MCELOG_MINOR, + "mcelog", + &mce_chrdev_ops, +}; + +static __init int dev_mcelog_init_device(void) +{ + int err; + + /* register character device /dev/mcelog */ + err = misc_register(&mce_chrdev_device); + if (err) { + pr_err("Unable to init device /dev/mcelog (rc: %d)\n", err); + return err; + } + mce_register_decode_chain(&dev_mcelog_nb); + return 0; +} +device_initcall_sync(dev_mcelog_init_device); diff --git a/arch/x86/kernel/cpu/mcheck/mce-genpool.c b/arch/x86/kernel/cpu/mcheck/mce-genpool.c index 1e5a50c11d3c..217cd4449bc9 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-genpool.c +++ b/arch/x86/kernel/cpu/mcheck/mce-genpool.c @@ -85,7 +85,7 @@ void mce_gen_pool_process(struct work_struct *__unused) head = llist_reverse_order(head); llist_for_each_entry_safe(node, tmp, head, llnode) { mce = &node->mce; - atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, mce); + blocking_notifier_call_chain(&x86_mce_decoder_chain, 0, mce); gen_pool_free(mce_evt_pool, (unsigned long)node, sizeof(*node)); } } diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h index 903043e6a62b..654ad0668d72 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-internal.h +++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h @@ -13,7 +13,7 @@ enum severity_level { MCE_PANIC_SEVERITY, }; -extern struct atomic_notifier_head x86_mce_decoder_chain; +extern struct blocking_notifier_head x86_mce_decoder_chain; #define ATTR_LEN 16 #define INITIAL_CHECK_INTERVAL 5 * 60 /* 5 minutes */ @@ -96,3 +96,11 @@ static inline bool mce_cmp(struct mce *m1, struct mce *m2) m1->addr != m2->addr || m1->misc != m2->misc; } + +extern struct device_attribute dev_attr_trigger; + +#ifdef CONFIG_X86_MCELOG_LEGACY +extern void mce_work_trigger(void); +#else +static inline void mce_work_trigger(void) { } +#endif diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 8e9725c607ea..5abd4bf73d6e 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -35,6 +35,7 @@ #include <linux/poll.h> #include <linux/nmi.h> #include <linux/cpu.h> +#include <linux/ras.h> #include <linux/smp.h> #include <linux/fs.h> #include <linux/mm.h> @@ -49,18 +50,11 @@ #include <asm/tlbflush.h> #include <asm/mce.h> #include <asm/msr.h> +#include <asm/reboot.h> #include "mce-internal.h" -static DEFINE_MUTEX(mce_chrdev_read_mutex); - -#define mce_log_get_idx_check(p) \ -({ \ - RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \ - !lockdep_is_held(&mce_chrdev_read_mutex), \ - "suspicious mce_log_get_idx_check() usage"); \ - smp_load_acquire(&(p)); \ -}) +static DEFINE_MUTEX(mce_log_mutex); #define CREATE_TRACE_POINTS #include <trace/events/mce.h> @@ -85,15 +79,9 @@ struct mca_config mca_cfg __read_mostly = { .monarch_timeout = -1 }; -/* User mode helper program triggered by machine check event */ -static unsigned long mce_need_notify; -static char mce_helper[128]; -static char *mce_helper_argv[2] = { mce_helper, NULL }; - -static DECLARE_WAIT_QUEUE_HEAD(mce_chrdev_wait); - static DEFINE_PER_CPU(struct mce, mces_seen); -static int cpu_missing; +static unsigned long mce_need_notify; +static int cpu_missing; /* * MCA banks polled by the period polling timer for corrected events. @@ -121,7 +109,7 @@ static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs); * CPU/chipset specific EDAC code can register a notifier call here to print * MCE errors in a human-readable form. */ -ATOMIC_NOTIFIER_HEAD(x86_mce_decoder_chain); +BLOCKING_NOTIFIER_HEAD(x86_mce_decoder_chain); /* Do initial initialization of a struct mce */ void mce_setup(struct mce *m) @@ -143,82 +131,38 @@ void mce_setup(struct mce *m) DEFINE_PER_CPU(struct mce, injectm); EXPORT_PER_CPU_SYMBOL_GPL(injectm); -/* - * Lockless MCE logging infrastructure. - * This avoids deadlocks on printk locks without having to break locks. Also - * separate MCEs from kernel messages to avoid bogus bug reports. - */ - -static struct mce_log mcelog = { - .signature = MCE_LOG_SIGNATURE, - .len = MCE_LOG_LEN, - .recordlen = sizeof(struct mce), -}; - -void mce_log(struct mce *mce) +void mce_log(struct mce *m) { - unsigned next, entry; - - /* Emit the trace record: */ - trace_mce_record(mce); - - if (!mce_gen_pool_add(mce)) + if (!mce_gen_pool_add(m)) irq_work_queue(&mce_irq_work); - - wmb(); - for (;;) { - entry = mce_log_get_idx_check(mcelog.next); - for (;;) { - - /* - * When the buffer fills up discard new entries. - * Assume that the earlier errors are the more - * interesting ones: - */ - if (entry >= MCE_LOG_LEN) { - set_bit(MCE_OVERFLOW, - (unsigned long *)&mcelog.flags); - return; - } - /* Old left over entry. Skip: */ - if (mcelog.entry[entry].finished) { - entry++; - continue; - } - break; - } - smp_rmb(); - next = entry + 1; - if (cmpxchg(&mcelog.next, entry, next) == entry) - break; - } - memcpy(mcelog.entry + entry, mce, sizeof(struct mce)); - wmb(); - mcelog.entry[entry].finished = 1; - wmb(); - - set_bit(0, &mce_need_notify); } void mce_inject_log(struct mce *m) { - mutex_lock(&mce_chrdev_read_mutex); + mutex_lock(&mce_log_mutex); mce_log(m); - mutex_unlock(&mce_chrdev_read_mutex); + mutex_unlock(&mce_log_mutex); } EXPORT_SYMBOL_GPL(mce_inject_log); static struct notifier_block mce_srao_nb; +/* + * We run the default notifier if we have only the SRAO, the first and the + * default notifier registered. I.e., the mandatory NUM_DEFAULT_NOTIFIERS + * notifiers registered on the chain. + */ +#define NUM_DEFAULT_NOTIFIERS 3 static atomic_t num_notifiers; void mce_register_decode_chain(struct notifier_block *nb) { - atomic_inc(&num_notifiers); + if (WARN_ON(nb->priority > MCE_PRIO_MCELOG && nb->priority < MCE_PRIO_EDAC)) + return; - WARN_ON(nb->priority > MCE_PRIO_LOWEST && nb->priority < MCE_PRIO_EDAC); + atomic_inc(&num_notifiers); - atomic_notifier_chain_register(&x86_mce_decoder_chain, nb); + blocking_notifier_chain_register(&x86_mce_decoder_chain, nb); } EXPORT_SYMBOL_GPL(mce_register_decode_chain); @@ -226,7 +170,7 @@ void mce_unregister_decode_chain(struct notifier_block *nb) { atomic_dec(&num_notifiers); - atomic_notifier_chain_unregister(&x86_mce_decoder_chain, nb); + blocking_notifier_chain_unregister(&x86_mce_decoder_chain, nb); } EXPORT_SYMBOL_GPL(mce_unregister_decode_chain); @@ -319,18 +263,7 @@ static void __print_mce(struct mce *m) static void print_mce(struct mce *m) { - int ret = 0; - __print_mce(m); - - /* - * Print out human-readable details about the MCE error, - * (if the CPU has an implementation for that) - */ - ret = atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, m); - if (ret == NOTIFY_STOP) - return; - pr_emerg_ratelimited(HW_ERR "Run the above through 'mcelog --ascii'\n"); } @@ -519,7 +452,6 @@ static void mce_schedule_work(void) static void mce_irq_work_cb(struct irq_work *entry) { - mce_notify_irq(); mce_schedule_work(); } @@ -548,20 +480,97 @@ static void mce_report_event(struct pt_regs *regs) */ static int mce_usable_address(struct mce *m) { - if (!(m->status & MCI_STATUS_MISCV) || !(m->status & MCI_STATUS_ADDRV)) + if (!(m->status & MCI_STATUS_ADDRV)) return 0; /* Checks after this one are Intel-specific: */ if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) return 1; + if (!(m->status & MCI_STATUS_MISCV)) + return 0; + if (MCI_MISC_ADDR_LSB(m->misc) > PAGE_SHIFT) return 0; + if (MCI_MISC_ADDR_MODE(m->misc) != MCI_MISC_ADDR_PHYS) return 0; + return 1; } +static bool memory_error(struct mce *m) +{ + struct cpuinfo_x86 *c = &boot_cpu_data; + + if (c->x86_vendor == X86_VENDOR_AMD) { + /* ErrCodeExt[20:16] */ + u8 xec = (m->status >> 16) & 0x1f; + + return (xec == 0x0 || xec == 0x8); + } else if (c->x86_vendor == X86_VENDOR_INTEL) { + /* + * Intel SDM Volume 3B - 15.9.2 Compound Error Codes + * + * Bit 7 of the MCACOD field of IA32_MCi_STATUS is used for + * indicating a memory error. Bit 8 is used for indicating a + * cache hierarchy error. The combination of bit 2 and bit 3 + * is used for indicating a `generic' cache hierarchy error + * But we can't just blindly check the above bits, because if + * bit 11 is set, then it is a bus/interconnect error - and + * either way the above bits just gives more detail on what + * bus/interconnect error happened. Note that bit 12 can be + * ignored, as it's the "filter" bit. + */ + return (m->status & 0xef80) == BIT(7) || + (m->status & 0xef00) == BIT(8) || + (m->status & 0xeffc) == 0xc; + } + + return false; +} + +static bool cec_add_mce(struct mce *m) +{ + if (!m) + return false; + + /* We eat only correctable DRAM errors with usable addresses. */ + if (memory_error(m) && + !(m->status & MCI_STATUS_UC) && + mce_usable_address(m)) + if (!cec_add_elem(m->addr >> PAGE_SHIFT)) + return true; + + return false; +} + +static int mce_first_notifier(struct notifier_block *nb, unsigned long val, + void *data) +{ + struct mce *m = (struct mce *)data; + + if (!m) + return NOTIFY_DONE; + + if (cec_add_mce(m)) + return NOTIFY_STOP; + + /* Emit the trace record: */ + trace_mce_record(m); + + set_bit(0, &mce_need_notify); + + mce_notify_irq(); + + return NOTIFY_DONE; +} + +static struct notifier_block first_nb = { + .notifier_call = mce_first_notifier, + .priority = MCE_PRIO_FIRST, +}; + static int srao_decode_notifier(struct notifier_block *nb, unsigned long val, void *data) { @@ -591,11 +600,7 @@ static int mce_default_notifier(struct notifier_block *nb, unsigned long val, if (!m) return NOTIFY_DONE; - /* - * Run the default notifier if we have only the SRAO - * notifier and us registered. - */ - if (atomic_read(&num_notifiers) > 2) + if (atomic_read(&num_notifiers) > NUM_DEFAULT_NOTIFIERS) return NOTIFY_DONE; __print_mce(m); @@ -648,37 +653,6 @@ static void mce_read_aux(struct mce *m, int i) } } -static bool memory_error(struct mce *m) -{ - struct cpuinfo_x86 *c = &boot_cpu_data; - - if (c->x86_vendor == X86_VENDOR_AMD) { - /* ErrCodeExt[20:16] */ - u8 xec = (m->status >> 16) & 0x1f; - - return (xec == 0x0 || xec == 0x8); - } else if (c->x86_vendor == X86_VENDOR_INTEL) { - /* - * Intel SDM Volume 3B - 15.9.2 Compound Error Codes - * - * Bit 7 of the MCACOD field of IA32_MCi_STATUS is used for - * indicating a memory error. Bit 8 is used for indicating a - * cache hierarchy error. The combination of bit 2 and bit 3 - * is used for indicating a `generic' cache hierarchy error - * But we can't just blindly check the above bits, because if - * bit 11 is set, then it is a bus/interconnect error - and - * either way the above bits just gives more detail on what - * bus/interconnect error happened. Note that bit 12 can be - * ignored, as it's the "filter" bit. - */ - return (m->status & 0xef80) == BIT(7) || - (m->status & 0xef00) == BIT(8) || - (m->status & 0xeffc) == 0xc; - } - - return false; -} - DEFINE_PER_CPU(unsigned, mce_poll_count); /* @@ -1127,9 +1101,22 @@ void do_machine_check(struct pt_regs *regs, long error_code) * on Intel. */ int lmce = 1; + int cpu = smp_processor_id(); - /* If this CPU is offline, just bail out. */ - if (cpu_is_offline(smp_processor_id())) { + /* + * Cases where we avoid rendezvous handler timeout: + * 1) If this CPU is offline. + * + * 2) If crashing_cpu was set, e.g. we're entering kdump and we need to + * skip those CPUs which remain looping in the 1st kernel - see + * crash_nmi_callback(). + * + * Note: there still is a small window between kexec-ing and the new, + * kdump kernel establishing a new #MC handler where a broadcasted MCE + * might not get handled properly. + */ + if (cpu_is_offline(cpu) || + (crashing_cpu != -1 && crashing_cpu != cpu)) { u64 mcgstatus; mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS); @@ -1399,13 +1386,6 @@ static void mce_timer_delete_all(void) del_timer_sync(&per_cpu(mce_timer, cpu)); } -static void mce_do_trigger(struct work_struct *work) -{ - call_usermodehelper(mce_helper, mce_helper_argv, NULL, UMH_NO_WAIT); -} - -static DECLARE_WORK(mce_trigger_work, mce_do_trigger); - /* * Notify the user(s) about new machine check events. * Can be called from interrupt context, but not from machine check/NMI @@ -1417,11 +1397,7 @@ int mce_notify_irq(void) static DEFINE_RATELIMIT_STATE(ratelimit, 60*HZ, 2); if (test_and_clear_bit(0, &mce_need_notify)) { - /* wake processes polling /dev/mcelog */ - wake_up_interruptible(&mce_chrdev_wait); - - if (mce_helper[0]) - schedule_work(&mce_trigger_work); + mce_work_trigger(); if (__ratelimit(&ratelimit)) pr_info(HW_ERR "Machine check events logged\n"); @@ -1688,30 +1664,35 @@ static int __mcheck_cpu_ancient_init(struct cpuinfo_x86 *c) return 0; } -static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) +/* + * Init basic CPU features needed for early decoding of MCEs. + */ +static void __mcheck_cpu_init_early(struct cpuinfo_x86 *c) { - switch (c->x86_vendor) { - case X86_VENDOR_INTEL: - mce_intel_feature_init(c); - mce_adjust_timer = cmci_intel_adjust_timer; - break; - - case X86_VENDOR_AMD: { + if (c->x86_vendor == X86_VENDOR_AMD) { mce_flags.overflow_recov = !!cpu_has(c, X86_FEATURE_OVERFLOW_RECOV); mce_flags.succor = !!cpu_has(c, X86_FEATURE_SUCCOR); mce_flags.smca = !!cpu_has(c, X86_FEATURE_SMCA); - /* - * Install proper ops for Scalable MCA enabled processors - */ if (mce_flags.smca) { msr_ops.ctl = smca_ctl_reg; msr_ops.status = smca_status_reg; msr_ops.addr = smca_addr_reg; msr_ops.misc = smca_misc_reg; } - mce_amd_feature_init(c); + } +} + +static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) +{ + switch (c->x86_vendor) { + case X86_VENDOR_INTEL: + mce_intel_feature_init(c); + mce_adjust_timer = cmci_intel_adjust_timer; + break; + case X86_VENDOR_AMD: { + mce_amd_feature_init(c); break; } @@ -1798,6 +1779,7 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c) machine_check_vector = do_machine_check; + __mcheck_cpu_init_early(c); __mcheck_cpu_init_generic(); __mcheck_cpu_init_vendor(c); __mcheck_cpu_init_clear_banks(); @@ -1823,252 +1805,6 @@ void mcheck_cpu_clear(struct cpuinfo_x86 *c) } -/* - * mce_chrdev: Character device /dev/mcelog to read and clear the MCE log. - */ - -static DEFINE_SPINLOCK(mce_chrdev_state_lock); -static int mce_chrdev_open_count; /* #times opened */ -static int mce_chrdev_open_exclu; /* already open exclusive? */ - -static int mce_chrdev_open(struct inode *inode, struct file *file) -{ - spin_lock(&mce_chrdev_state_lock); - - if (mce_chrdev_open_exclu || - (mce_chrdev_open_count && (file->f_flags & O_EXCL))) { - spin_unlock(&mce_chrdev_state_lock); - - return -EBUSY; - } - - if (file->f_flags & O_EXCL) - mce_chrdev_open_exclu = 1; - mce_chrdev_open_count++; - - spin_unlock(&mce_chrdev_state_lock); - - return nonseekable_open(inode, file); -} - -static int mce_chrdev_release(struct inode *inode, struct file *file) -{ - spin_lock(&mce_chrdev_state_lock); - - mce_chrdev_open_count--; - mce_chrdev_open_exclu = 0; - - spin_unlock(&mce_chrdev_state_lock); - - return 0; -} - -static void collect_tscs(void *data) -{ - unsigned long *cpu_tsc = (unsigned long *)data; - - cpu_tsc[smp_processor_id()] = rdtsc(); -} - -static int mce_apei_read_done; - -/* Collect MCE record of previous boot in persistent storage via APEI ERST. */ -static int __mce_read_apei(char __user **ubuf, size_t usize) -{ - int rc; - u64 record_id; - struct mce m; - - if (usize < sizeof(struct mce)) - return -EINVAL; - - rc = apei_read_mce(&m, &record_id); - /* Error or no more MCE record */ - if (rc <= 0) { - mce_apei_read_done = 1; - /* - * When ERST is disabled, mce_chrdev_read() should return - * "no record" instead of "no device." - */ - if (rc == -ENODEV) - return 0; - return rc; - } - rc = -EFAULT; - if (copy_to_user(*ubuf, &m, sizeof(struct mce))) - return rc; - /* - * In fact, we should have cleared the record after that has - * been flushed to the disk or sent to network in - * /sbin/mcelog, but we have no interface to support that now, - * so just clear it to avoid duplication. - */ - rc = apei_clear_mce(record_id); - if (rc) { - mce_apei_read_done = 1; - return rc; - } - *ubuf += sizeof(struct mce); - - return 0; -} - -static ssize_t mce_chrdev_read(struct file *filp, char __user *ubuf, - size_t usize, loff_t *off) -{ - char __user *buf = ubuf; - unsigned long *cpu_tsc; - unsigned prev, next; - int i, err; - - cpu_tsc = kmalloc(nr_cpu_ids * sizeof(long), GFP_KERNEL); - if (!cpu_tsc) - return -ENOMEM; - - mutex_lock(&mce_chrdev_read_mutex); - - if (!mce_apei_read_done) { - err = __mce_read_apei(&buf, usize); - if (err || buf != ubuf) - goto out; - } - - next = mce_log_get_idx_check(mcelog.next); - - /* Only supports full reads right now */ - err = -EINVAL; - if (*off != 0 || usize < MCE_LOG_LEN*sizeof(struct mce)) - goto out; - - err = 0; - prev = 0; - do { - for (i = prev; i < next; i++) { - unsigned long start = jiffies; - struct mce *m = &mcelog.entry[i]; - - while (!m->finished) { - if (time_after_eq(jiffies, start + 2)) { - memset(m, 0, sizeof(*m)); - goto timeout; - } - cpu_relax(); - } - smp_rmb(); - err |= copy_to_user(buf, m, sizeof(*m)); - buf += sizeof(*m); -timeout: - ; - } - - memset(mcelog.entry + prev, 0, - (next - prev) * sizeof(struct mce)); - prev = next; - next = cmpxchg(&mcelog.next, prev, 0); - } while (next != prev); - - synchronize_sched(); - - /* - * Collect entries that were still getting written before the - * synchronize. - */ - on_each_cpu(collect_tscs, cpu_tsc, 1); - - for (i = next; i < MCE_LOG_LEN; i++) { - struct mce *m = &mcelog.entry[i]; - - if (m->finished && m->tsc < cpu_tsc[m->cpu]) { - err |= copy_to_user(buf, m, sizeof(*m)); - smp_rmb(); - buf += sizeof(*m); - memset(m, 0, sizeof(*m)); - } - } - - if (err) - err = -EFAULT; - -out: - mutex_unlock(&mce_chrdev_read_mutex); - kfree(cpu_tsc); - - return err ? err : buf - ubuf; -} - -static unsigned int mce_chrdev_poll(struct file *file, poll_table *wait) -{ - poll_wait(file, &mce_chrdev_wait, wait); - if (READ_ONCE(mcelog.next)) - return POLLIN | POLLRDNORM; - if (!mce_apei_read_done && apei_check_mce()) - return POLLIN | POLLRDNORM; - return 0; -} - -static long mce_chrdev_ioctl(struct file *f, unsigned int cmd, - unsigned long arg) -{ - int __user *p = (int __user *)arg; - - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; - - switch (cmd) { - case MCE_GET_RECORD_LEN: - return put_user(sizeof(struct mce), p); - case MCE_GET_LOG_LEN: - return put_user(MCE_LOG_LEN, p); - case MCE_GETCLEAR_FLAGS: { - unsigned flags; - - do { - flags = mcelog.flags; - } while (cmpxchg(&mcelog.flags, flags, 0) != flags); - - return put_user(flags, p); - } - default: - return -ENOTTY; - } -} - -static ssize_t (*mce_write)(struct file *filp, const char __user *ubuf, - size_t usize, loff_t *off); - -void register_mce_write_callback(ssize_t (*fn)(struct file *filp, - const char __user *ubuf, - size_t usize, loff_t *off)) -{ - mce_write = fn; -} -EXPORT_SYMBOL_GPL(register_mce_write_callback); - -static ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf, - size_t usize, loff_t *off) -{ - if (mce_write) - return mce_write(filp, ubuf, usize, off); - else - return -EINVAL; -} - -static const struct file_operations mce_chrdev_ops = { - .open = mce_chrdev_open, - .release = mce_chrdev_release, - .read = mce_chrdev_read, - .write = mce_chrdev_write, - .poll = mce_chrdev_poll, - .unlocked_ioctl = mce_chrdev_ioctl, - .llseek = no_llseek, -}; - -static struct miscdevice mce_chrdev_device = { - MISC_MCELOG_MINOR, - "mcelog", - &mce_chrdev_ops, -}; - static void __mce_disable_bank(void *arg) { int bank = *((int *)arg); @@ -2142,6 +1878,7 @@ __setup("mce", mcheck_enable); int __init mcheck_init(void) { mcheck_intel_therm_init(); + mce_register_decode_chain(&first_nb); mce_register_decode_chain(&mce_srao_nb); mce_register_decode_chain(&mce_default_nb); mcheck_vendor_init_severity(); @@ -2286,29 +2023,6 @@ static ssize_t set_bank(struct device *s, struct device_attribute *attr, return size; } -static ssize_t -show_trigger(struct device *s, struct device_attribute *attr, char *buf) -{ - strcpy(buf, mce_helper); - strcat(buf, "\n"); - return strlen(mce_helper) + 1; -} - -static ssize_t set_trigger(struct device *s, struct device_attribute *attr, - const char *buf, size_t siz) -{ - char *p; - - strncpy(mce_helper, buf, sizeof(mce_helper)); - mce_helper[sizeof(mce_helper)-1] = 0; - p = strchr(mce_helper, '\n'); - - if (p) - *p = 0; - - return strlen(mce_helper) + !!p; -} - static ssize_t set_ignore_ce(struct device *s, struct device_attribute *attr, const char *buf, size_t size) @@ -2365,7 +2079,6 @@ static ssize_t store_int_with_restart(struct device *s, return ret; } -static DEVICE_ATTR(trigger, 0644, show_trigger, set_trigger); static DEVICE_INT_ATTR(tolerant, 0644, mca_cfg.tolerant); static DEVICE_INT_ATTR(monarch_timeout, 0644, mca_cfg.monarch_timeout); static DEVICE_BOOL_ATTR(dont_log_ce, 0644, mca_cfg.dont_log_ce); @@ -2388,7 +2101,9 @@ static struct dev_ext_attribute dev_attr_cmci_disabled = { static struct device_attribute *mce_device_attrs[] = { &dev_attr_tolerant.attr, &dev_attr_check_interval.attr, +#ifdef CONFIG_X86_MCELOG_LEGACY &dev_attr_trigger, +#endif &dev_attr_monarch_timeout.attr, &dev_attr_dont_log_ce.attr, &dev_attr_ignore_ce.attr, @@ -2562,7 +2277,6 @@ static __init void mce_init_banks(void) static __init int mcheck_init_device(void) { - enum cpuhp_state hp_online; int err; if (!mce_available(&boot_cpu_data)) { @@ -2590,21 +2304,11 @@ static __init int mcheck_init_device(void) mce_cpu_online, mce_cpu_pre_down); if (err < 0) goto err_out_online; - hp_online = err; register_syscore_ops(&mce_syscore_ops); - /* register character device /dev/mcelog */ - err = misc_register(&mce_chrdev_device); - if (err) - goto err_register; - return 0; -err_register: - unregister_syscore_ops(&mce_syscore_ops); - cpuhp_remove_state(hp_online); - err_out_online: cpuhp_remove_state(CPUHP_X86_MCE_DEAD); @@ -2612,7 +2316,7 @@ err_out_mem: free_cpumask_var(mce_device_initialized); err_out: - pr_err("Unable to init device /dev/mcelog (rc: %d)\n", err); + pr_err("Unable to init MCE device (rc: %d)\n", err); return err; } @@ -2691,6 +2395,7 @@ static int __init mcheck_late_init(void) static_branch_inc(&mcsafe_key); mcheck_debugfs_init(); + cec_init(); /* * Flush out everything that has been logged during early boot, now that diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c index 190b3e6cef4d..e84db79ef272 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c @@ -481,6 +481,9 @@ static void intel_ppin_init(struct cpuinfo_x86 *c) case INTEL_FAM6_BROADWELL_XEON_D: case INTEL_FAM6_BROADWELL_X: case INTEL_FAM6_SKYLAKE_X: + case INTEL_FAM6_XEON_PHI_KNL: + case INTEL_FAM6_XEON_PHI_KNM: + if (rdmsrl_safe(MSR_PPIN_CTL, &val)) return; diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c index 3b442b64c72d..765afd599039 100644 --- a/arch/x86/kernel/cpu/mtrr/cleanup.c +++ b/arch/x86/kernel/cpu/mtrr/cleanup.c @@ -27,7 +27,7 @@ #include <linux/range.h> #include <asm/processor.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/mtrr.h> #include <asm/msr.h> @@ -860,7 +860,7 @@ real_trim_memory(unsigned long start_pfn, unsigned long limit_pfn) trim_size <<= PAGE_SHIFT; trim_size -= trim_start; - return e820_update_range(trim_start, trim_size, E820_RAM, E820_RESERVED); + return e820__range_update(trim_start, trim_size, E820_TYPE_RAM, E820_TYPE_RESERVED); } /** @@ -978,7 +978,7 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn) WARN_ON(1); pr_info("update e820 for mtrr\n"); - update_e820(); + e820__update_table_print(); return 1; } diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index 24e87e74990d..2bce84d91c2b 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -48,7 +48,7 @@ #include <linux/syscore_ops.h> #include <asm/cpufeature.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/mtrr.h> #include <asm/msr.h> #include <asm/pat.h> diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index 18ca99f2798b..6df621ae62a7 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -31,14 +31,13 @@ static void show_cpuinfo_misc(struct seq_file *m, struct cpuinfo_x86 *c) "fpu\t\t: %s\n" "fpu_exception\t: %s\n" "cpuid level\t: %d\n" - "wp\t\t: %s\n", + "wp\t\t: yes\n", static_cpu_has_bug(X86_BUG_FDIV) ? "yes" : "no", static_cpu_has_bug(X86_BUG_F00F) ? "yes" : "no", static_cpu_has_bug(X86_BUG_COMA) ? "yes" : "no", static_cpu_has(X86_FEATURE_FPU) ? "yes" : "no", static_cpu_has(X86_FEATURE_FPU) ? "yes" : "no", - c->cpuid_level, - c->wp_works_ok ? "yes" : "no"); + c->cpuid_level); } #else static void show_cpuinfo_misc(struct seq_file *m, struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index d9794060fe22..23c23508c012 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -27,6 +27,7 @@ static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_CAT_L3, CPUID_EBX, 1, 0x00000010, 0 }, { X86_FEATURE_CAT_L2, CPUID_EBX, 2, 0x00000010, 0 }, { X86_FEATURE_CDP_L3, CPUID_ECX, 2, 0x00000010, 1 }, + { X86_FEATURE_MBA, CPUID_EBX, 3, 0x00000010, 0 }, { X86_FEATURE_HW_PSTATE, CPUID_EDX, 7, 0x80000007, 0 }, { X86_FEATURE_CPB, CPUID_EDX, 9, 0x80000007, 0 }, { X86_FEATURE_PROC_FEEDBACK, CPUID_EDX, 11, 0x80000007, 0 }, diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 3741461c63a0..22217ece26c8 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -29,6 +29,7 @@ #include <asm/nmi.h> #include <asm/hw_irq.h> #include <asm/apic.h> +#include <asm/e820/types.h> #include <asm/io_apic.h> #include <asm/hpet.h> #include <linux/kdebug.h> @@ -503,16 +504,16 @@ static int prepare_elf_headers(struct kimage *image, void **addr, return ret; } -static int add_e820_entry(struct boot_params *params, struct e820entry *entry) +static int add_e820_entry(struct boot_params *params, struct e820_entry *entry) { unsigned int nr_e820_entries; nr_e820_entries = params->e820_entries; - if (nr_e820_entries >= E820MAX) + if (nr_e820_entries >= E820_MAX_ENTRIES_ZEROPAGE) return 1; - memcpy(¶ms->e820_map[nr_e820_entries], entry, - sizeof(struct e820entry)); + memcpy(¶ms->e820_table[nr_e820_entries], entry, + sizeof(struct e820_entry)); params->e820_entries++; return 0; } @@ -521,7 +522,7 @@ static int memmap_entry_callback(u64 start, u64 end, void *arg) { struct crash_memmap_data *cmd = arg; struct boot_params *params = cmd->params; - struct e820entry ei; + struct e820_entry ei; ei.addr = start; ei.size = end - start + 1; @@ -560,7 +561,7 @@ int crash_setup_memmap_entries(struct kimage *image, struct boot_params *params) { int i, ret = 0; unsigned long flags; - struct e820entry ei; + struct e820_entry ei; struct crash_memmap_data cmd; struct crash_mem *cmem; @@ -574,17 +575,17 @@ int crash_setup_memmap_entries(struct kimage *image, struct boot_params *params) /* Add first 640K segment */ ei.addr = image->arch.backup_src_start; ei.size = image->arch.backup_src_sz; - ei.type = E820_RAM; + ei.type = E820_TYPE_RAM; add_e820_entry(params, &ei); /* Add ACPI tables */ - cmd.type = E820_ACPI; + cmd.type = E820_TYPE_ACPI; flags = IORESOURCE_MEM | IORESOURCE_BUSY; walk_iomem_res_desc(IORES_DESC_ACPI_TABLES, flags, 0, -1, &cmd, memmap_entry_callback); /* Add ACPI Non-volatile Storage */ - cmd.type = E820_NVS; + cmd.type = E820_TYPE_NVS; walk_iomem_res_desc(IORES_DESC_ACPI_NV_STORAGE, flags, 0, -1, &cmd, memmap_entry_callback); @@ -592,7 +593,7 @@ int crash_setup_memmap_entries(struct kimage *image, struct boot_params *params) if (crashk_low_res.end) { ei.addr = crashk_low_res.start; ei.size = crashk_low_res.end - crashk_low_res.start + 1; - ei.type = E820_RAM; + ei.type = E820_TYPE_RAM; add_e820_entry(params, &ei); } @@ -609,7 +610,7 @@ int crash_setup_memmap_entries(struct kimage *image, struct boot_params *params) if (ei.size < PAGE_SIZE) continue; ei.addr = cmem->ranges[i].start; - ei.type = E820_RAM; + ei.type = E820_TYPE_RAM; add_e820_entry(params, &ei); } diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 09d4ac0d2661..dbce3cca94cb 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -77,7 +77,7 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, * - softirq stack * - hardirq stack */ - for (regs = NULL; stack; stack = stack_info.next_sp) { + for (regs = NULL; stack; stack = PTR_ALIGN(stack_info.next_sp, sizeof(long))) { const char *stack_name; /* @@ -289,9 +289,6 @@ void die(const char *str, struct pt_regs *regs, long err) unsigned long flags = oops_begin(); int sig = SIGSEGV; - if (!user_mode(regs)) - report_bug(regs->ip, regs); - if (__die(str, regs, err)) sig = 0; oops_end(flags, regs, sig); diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c index b0b3a3df7c20..e5f0b40e66d2 100644 --- a/arch/x86/kernel/dumpstack_32.c +++ b/arch/x86/kernel/dumpstack_32.c @@ -162,15 +162,3 @@ void show_regs(struct pt_regs *regs) } pr_cont("\n"); } - -int is_valid_bugaddr(unsigned long ip) -{ - unsigned short ud2; - - if (ip < PAGE_OFFSET) - return 0; - if (probe_kernel_address((unsigned short *)ip, ud2)) - return 0; - - return ud2 == 0x0b0f; -} diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index a8b117e93b46..3e1471d57487 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -178,13 +178,3 @@ void show_regs(struct pt_regs *regs) } pr_cont("\n"); } - -int is_valid_bugaddr(unsigned long ip) -{ - unsigned short ud2; - - if (__copy_from_user(&ud2, (const void __user *) ip, sizeof(ud2))) - return 0; - - return ud2 == 0x0b0f; -} diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index b2bbad6ebe4d..d78a586ba8dc 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -1,49 +1,55 @@ /* - * Handle the memory map. - * The functions here do the job until bootmem takes over. + * Low level x86 E820 memory map handling functions. * - * Getting sanitize_e820_map() in sync with i386 version by applying change: - * - Provisions for empty E820 memory regions (reported by certain BIOSes). - * Alex Achenbach <xela@slit.de>, December 2002. - * Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> + * The firmware and bootloader passes us the "E820 table", which is the primary + * physical memory layout description available about x86 systems. * + * The kernel takes the E820 memory layout and optionally modifies it with + * quirks and other tweaks, and feeds that into the generic Linux memory + * allocation code routines via a platform independent interface (memblock, etc.). */ -#include <linux/kernel.h> -#include <linux/types.h> -#include <linux/init.h> #include <linux/crash_dump.h> -#include <linux/export.h> #include <linux/bootmem.h> -#include <linux/pfn.h> #include <linux/suspend.h> #include <linux/acpi.h> #include <linux/firmware-map.h> #include <linux/memblock.h> #include <linux/sort.h> -#include <asm/e820.h> -#include <asm/proto.h> +#include <asm/e820/api.h> #include <asm/setup.h> -#include <asm/cpufeature.h> /* - * The e820 map is the map that gets modified e.g. with command line parameters - * and that is also registered with modifications in the kernel resource tree - * with the iomem_resource as parent. + * We organize the E820 table into two main data structures: * - * The e820_saved is directly saved after the BIOS-provided memory map is - * copied. It doesn't get modified afterwards. It's registered for the - * /sys/firmware/memmap interface. + * - 'e820_table_firmware': the original firmware version passed to us by the + * bootloader - not modified by the kernel. We use this to: * - * That memory map is not modified and is used as base for kexec. The kexec'd - * kernel should get the same memory map as the firmware provides. Then the - * user can e.g. boot the original kernel with mem=1G while still booting the - * next kernel with full memory. + * - inform the user about the firmware's notion of memory layout + * via /sys/firmware/memmap + * + * - the hibernation code uses it to generate a kernel-independent MD5 + * fingerprint of the physical memory layout of a system. + * + * - kexec, which is a bootloader in disguise, uses the original E820 + * layout to pass to the kexec-ed kernel. This way the original kernel + * can have a restricted E820 map while the kexec()-ed kexec-kernel + * can have access to full memory - etc. + * + * - 'e820_table': this is the main E820 table that is massaged by the + * low level x86 platform code, or modified by boot parameters, before + * passed on to higher level MM layers. + * + * Once the E820 map has been converted to the standard Linux memory layout + * information its role stops - modifying it has no effect and does not get + * re-propagated. So itsmain role is a temporary bootstrap storage of firmware + * specific memory layout data during early bootup. */ -static struct e820map initial_e820 __initdata; -static struct e820map initial_e820_saved __initdata; -struct e820map *e820 __refdata = &initial_e820; -struct e820map *e820_saved __refdata = &initial_e820_saved; +static struct e820_table e820_table_init __initdata; +static struct e820_table e820_table_firmware_init __initdata; + +struct e820_table *e820_table __refdata = &e820_table_init; +struct e820_table *e820_table_firmware __refdata = &e820_table_firmware_init; /* For PCI or other memory-mapped resources */ unsigned long pci_mem_start = 0xaeedbabe; @@ -55,51 +61,53 @@ EXPORT_SYMBOL(pci_mem_start); * This function checks if any part of the range <start,end> is mapped * with type. */ -int -e820_any_mapped(u64 start, u64 end, unsigned type) +bool e820__mapped_any(u64 start, u64 end, enum e820_type type) { int i; - for (i = 0; i < e820->nr_map; i++) { - struct e820entry *ei = &e820->map[i]; + for (i = 0; i < e820_table->nr_entries; i++) { + struct e820_entry *entry = &e820_table->entries[i]; - if (type && ei->type != type) + if (type && entry->type != type) continue; - if (ei->addr >= end || ei->addr + ei->size <= start) + if (entry->addr >= end || entry->addr + entry->size <= start) continue; return 1; } return 0; } -EXPORT_SYMBOL_GPL(e820_any_mapped); +EXPORT_SYMBOL_GPL(e820__mapped_any); /* - * This function checks if the entire range <start,end> is mapped with type. + * This function checks if the entire <start,end> range is mapped with 'type'. * - * Note: this function only works correct if the e820 table is sorted and - * not-overlapping, which is the case + * 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. */ -int __init e820_all_mapped(u64 start, u64 end, unsigned type) +bool __init e820__mapped_all(u64 start, u64 end, enum e820_type type) { int i; - for (i = 0; i < e820->nr_map; i++) { - struct e820entry *ei = &e820->map[i]; + for (i = 0; i < e820_table->nr_entries; i++) { + struct e820_entry *entry = &e820_table->entries[i]; - if (type && ei->type != type) + if (type && entry->type != type) continue; - /* is the region (part) in overlap with the current region ?*/ - if (ei->addr >= end || ei->addr + ei->size <= start) + + /* Is the region (part) in overlap with the current region? */ + if (entry->addr >= end || entry->addr + entry->size <= start) continue; - /* if the region is at the beginning of <start,end> we move - * start to the end of the region since it's ok until there + /* + * If the region is at the beginning of <start,end> we move + * 'start' to the end of the region since it's ok until there */ - if (ei->addr <= start) - start = ei->addr + ei->size; + if (entry->addr <= start) + start = entry->addr + entry->size; + /* - * if start is now at or beyond end, we're done, full - * coverage + * If 'start' is now at or beyond 'end', we're done, full + * coverage of the desired range exists: */ if (start >= end) return 1; @@ -108,94 +116,77 @@ int __init e820_all_mapped(u64 start, u64 end, unsigned type) } /* - * Add a memory region to the kernel e820 map. + * Add a memory region to the kernel E820 map. */ -static void __init __e820_add_region(struct e820map *e820x, u64 start, u64 size, - int type) +static void __init __e820__range_add(struct e820_table *table, u64 start, u64 size, enum e820_type type) { - int x = e820x->nr_map; + int x = table->nr_entries; - if (x >= ARRAY_SIZE(e820x->map)) { - printk(KERN_ERR "e820: too many entries; ignoring [mem %#010llx-%#010llx]\n", - (unsigned long long) start, - (unsigned long long) (start + size - 1)); + if (x >= ARRAY_SIZE(table->entries)) { + pr_err("e820: too many entries; ignoring [mem %#010llx-%#010llx]\n", start, start + size - 1); return; } - e820x->map[x].addr = start; - e820x->map[x].size = size; - e820x->map[x].type = type; - e820x->nr_map++; + table->entries[x].addr = start; + table->entries[x].size = size; + table->entries[x].type = type; + table->nr_entries++; } -void __init e820_add_region(u64 start, u64 size, int type) +void __init e820__range_add(u64 start, u64 size, enum e820_type type) { - __e820_add_region(e820, start, size, type); + __e820__range_add(e820_table, start, size, type); } -static void __init e820_print_type(u32 type) +static void __init e820_print_type(enum e820_type type) { switch (type) { - case E820_RAM: - case E820_RESERVED_KERN: - printk(KERN_CONT "usable"); - break; - case E820_RESERVED: - printk(KERN_CONT "reserved"); - break; - case E820_ACPI: - printk(KERN_CONT "ACPI data"); - break; - case E820_NVS: - printk(KERN_CONT "ACPI NVS"); - break; - case E820_UNUSABLE: - printk(KERN_CONT "unusable"); - break; - case E820_PMEM: - case E820_PRAM: - printk(KERN_CONT "persistent (type %u)", type); - break; - default: - printk(KERN_CONT "type %u", type); - break; + case E820_TYPE_RAM: /* Fall through: */ + case E820_TYPE_RESERVED_KERN: pr_cont("usable"); break; + case E820_TYPE_RESERVED: pr_cont("reserved"); break; + case E820_TYPE_ACPI: pr_cont("ACPI data"); break; + case E820_TYPE_NVS: pr_cont("ACPI NVS"); break; + case E820_TYPE_UNUSABLE: pr_cont("unusable"); break; + case E820_TYPE_PMEM: /* Fall through: */ + case E820_TYPE_PRAM: pr_cont("persistent (type %u)", type); break; + default: pr_cont("type %u", type); break; } } -void __init e820_print_map(char *who) +void __init e820__print_table(char *who) { int i; - for (i = 0; i < e820->nr_map; i++) { - printk(KERN_INFO "%s: [mem %#018Lx-%#018Lx] ", who, - (unsigned long long) e820->map[i].addr, - (unsigned long long) - (e820->map[i].addr + e820->map[i].size - 1)); - e820_print_type(e820->map[i].type); - printk(KERN_CONT "\n"); + for (i = 0; i < e820_table->nr_entries; i++) { + pr_info("%s: [mem %#018Lx-%#018Lx] ", who, + e820_table->entries[i].addr, + e820_table->entries[i].addr + e820_table->entries[i].size - 1); + + e820_print_type(e820_table->entries[i].type); + pr_cont("\n"); } } /* - * Sanitize the BIOS e820 map. + * Sanitize an E820 map. * - * Some e820 responses include overlapping entries. The following - * replaces the original e820 map with a new one, removing overlaps, + * Some E820 layouts include overlapping entries. The following + * replaces the original E820 map with a new one, removing overlaps, * and resolving conflicting memory types in favor of highest * numbered type. * - * The input parameter biosmap points to an array of 'struct - * e820entry' which on entry has elements in the range [0, *pnr_map) - * valid, and which has space for up to max_nr_map entries. - * On return, the resulting sanitized e820 map entries will be in - * overwritten in the same location, starting at biosmap. + * The input parameter 'entries' points to an array of 'struct + * e820_entry' which on entry has elements in the range [0, *nr_entries) + * valid, and which has space for up to max_nr_entries entries. + * On return, the resulting sanitized E820 map entries will be in + * overwritten in the same location, starting at 'entries'. * - * The integer pointed to by pnr_map must be valid on entry (the - * current number of valid entries located at biosmap). If the - * sanitizing succeeds the *pnr_map will be updated with the new - * number of valid entries (something no more than max_nr_map). + * The integer pointed to by nr_entries must be valid on entry (the + * current number of valid entries located at 'entries'). If the + * sanitizing succeeds the *nr_entries will be updated with the new + * number of valid entries (something no more than max_nr_entries). * - * The return value from sanitize_e820_map() is zero if it + * The return value from e820__update_table() is zero if it * successfully 'sanitized' the map entries passed in, and is -1 * if it did nothing, which can happen if either of (1) it was * only passed one map entry, or (2) any of the input map entries @@ -238,10 +229,17 @@ void __init e820_print_map(char *who) * ______________________4_ */ struct change_member { - struct e820entry *pbios; /* pointer to original bios entry */ - unsigned long long addr; /* address for this change point */ + /* Pointer to the original entry: */ + struct e820_entry *entry; + /* Address for this change point: */ + unsigned long long addr; }; +static struct change_member change_point_list[2*E820_MAX_ENTRIES] __initdata; +static struct change_member *change_point[2*E820_MAX_ENTRIES] __initdata; +static struct e820_entry *overlap_list[E820_MAX_ENTRIES] __initdata; +static struct e820_entry new_entries[E820_MAX_ENTRIES] __initdata; + static int __init cpcompare(const void *a, const void *b) { struct change_member * const *app = a, * const *bpp = b; @@ -249,164 +247,140 @@ static int __init cpcompare(const void *a, const void *b) /* * Inputs are pointers to two elements of change_point[]. If their - * addresses are unequal, their difference dominates. If the addresses + * addresses are not equal, their difference dominates. If the addresses * are equal, then consider one that represents the end of its region * to be greater than one that does not. */ if (ap->addr != bp->addr) return ap->addr > bp->addr ? 1 : -1; - return (ap->addr != ap->pbios->addr) - (bp->addr != bp->pbios->addr); + return (ap->addr != ap->entry->addr) - (bp->addr != bp->entry->addr); } -int __init sanitize_e820_map(struct e820entry *biosmap, int max_nr_map, - u32 *pnr_map) +int __init e820__update_table(struct e820_table *table) { - static struct change_member change_point_list[2*E820_X_MAX] __initdata; - static struct change_member *change_point[2*E820_X_MAX] __initdata; - static struct e820entry *overlap_list[E820_X_MAX] __initdata; - static struct e820entry new_bios[E820_X_MAX] __initdata; - unsigned long current_type, last_type; + struct e820_entry *entries = table->entries; + u32 max_nr_entries = ARRAY_SIZE(table->entries); + enum e820_type current_type, last_type; unsigned long long last_addr; - int chgidx; - int overlap_entries; - int new_bios_entry; - int old_nr, new_nr, chg_nr; - int i; + u32 new_nr_entries, overlap_entries; + u32 i, chg_idx, chg_nr; - /* if there's only one memory region, don't bother */ - if (*pnr_map < 2) + /* If there's only one memory region, don't bother: */ + if (table->nr_entries < 2) return -1; - old_nr = *pnr_map; - BUG_ON(old_nr > max_nr_map); + BUG_ON(table->nr_entries > max_nr_entries); - /* bail out if we find any unreasonable addresses in bios map */ - for (i = 0; i < old_nr; i++) - if (biosmap[i].addr + biosmap[i].size < biosmap[i].addr) + /* Bail out if we find any unreasonable addresses in the map: */ + for (i = 0; i < table->nr_entries; i++) { + if (entries[i].addr + entries[i].size < entries[i].addr) return -1; + } - /* create pointers for initial change-point information (for sorting) */ - for (i = 0; i < 2 * old_nr; i++) + /* Create pointers for initial change-point information (for sorting): */ + for (i = 0; i < 2 * table->nr_entries; i++) change_point[i] = &change_point_list[i]; - /* record all known change-points (starting and ending addresses), - omitting those that are for empty memory regions */ - chgidx = 0; - for (i = 0; i < old_nr; i++) { - if (biosmap[i].size != 0) { - change_point[chgidx]->addr = biosmap[i].addr; - change_point[chgidx++]->pbios = &biosmap[i]; - change_point[chgidx]->addr = biosmap[i].addr + - biosmap[i].size; - change_point[chgidx++]->pbios = &biosmap[i]; + /* + * Record all known change-points (starting and ending addresses), + * omitting empty memory regions: + */ + chg_idx = 0; + for (i = 0; i < table->nr_entries; i++) { + if (entries[i].size != 0) { + change_point[chg_idx]->addr = entries[i].addr; + change_point[chg_idx++]->entry = &entries[i]; + change_point[chg_idx]->addr = entries[i].addr + entries[i].size; + change_point[chg_idx++]->entry = &entries[i]; } } - chg_nr = chgidx; - - /* sort change-point list by memory addresses (low -> high) */ - sort(change_point, chg_nr, sizeof *change_point, cpcompare, NULL); - - /* create a new bios memory map, removing overlaps */ - overlap_entries = 0; /* number of entries in the overlap table */ - new_bios_entry = 0; /* index for creating new bios map entries */ - last_type = 0; /* start with undefined memory type */ - last_addr = 0; /* start with 0 as last starting address */ - - /* loop through change-points, determining affect on the new bios map */ - for (chgidx = 0; chgidx < chg_nr; chgidx++) { - /* keep track of all overlapping bios entries */ - if (change_point[chgidx]->addr == - change_point[chgidx]->pbios->addr) { - /* - * add map entry to overlap list (> 1 entry - * implies an overlap) - */ - overlap_list[overlap_entries++] = - change_point[chgidx]->pbios; + chg_nr = chg_idx; + + /* Sort change-point list by memory addresses (low -> high): */ + sort(change_point, chg_nr, sizeof(*change_point), cpcompare, NULL); + + /* Create a new memory map, removing overlaps: */ + overlap_entries = 0; /* Number of entries in the overlap table */ + new_nr_entries = 0; /* Index for creating new map entries */ + last_type = 0; /* Start with undefined memory type */ + last_addr = 0; /* Start with 0 as last starting address */ + + /* Loop through change-points, determining effect on the new map: */ + for (chg_idx = 0; chg_idx < chg_nr; chg_idx++) { + /* Keep track of all overlapping entries */ + if (change_point[chg_idx]->addr == change_point[chg_idx]->entry->addr) { + /* Add map entry to overlap list (> 1 entry implies an overlap) */ + overlap_list[overlap_entries++] = change_point[chg_idx]->entry; } else { - /* - * remove entry from list (order independent, - * so swap with last) - */ + /* Remove entry from list (order independent, so swap with last): */ for (i = 0; i < overlap_entries; i++) { - if (overlap_list[i] == - change_point[chgidx]->pbios) - overlap_list[i] = - overlap_list[overlap_entries-1]; + if (overlap_list[i] == change_point[chg_idx]->entry) + overlap_list[i] = overlap_list[overlap_entries-1]; } overlap_entries--; } /* - * if there are overlapping entries, decide which + * If there are overlapping entries, decide which * "type" to use (larger value takes precedence -- * 1=usable, 2,3,4,4+=unusable) */ current_type = 0; - for (i = 0; i < overlap_entries; i++) + for (i = 0; i < overlap_entries; i++) { if (overlap_list[i]->type > current_type) current_type = overlap_list[i]->type; - /* - * continue building up new bios map based on this - * information - */ - if (current_type != last_type || current_type == E820_PRAM) { + } + + /* Continue building up new map based on this information: */ + if (current_type != last_type || current_type == E820_TYPE_PRAM) { if (last_type != 0) { - new_bios[new_bios_entry].size = - change_point[chgidx]->addr - last_addr; - /* - * move forward only if the new size - * was non-zero - */ - if (new_bios[new_bios_entry].size != 0) - /* - * no more space left for new - * bios entries ? - */ - if (++new_bios_entry >= max_nr_map) + new_entries[new_nr_entries].size = change_point[chg_idx]->addr - last_addr; + /* Move forward only if the new size was non-zero: */ + if (new_entries[new_nr_entries].size != 0) + /* No more space left for new entries? */ + if (++new_nr_entries >= max_nr_entries) break; } if (current_type != 0) { - new_bios[new_bios_entry].addr = - change_point[chgidx]->addr; - new_bios[new_bios_entry].type = current_type; - last_addr = change_point[chgidx]->addr; + new_entries[new_nr_entries].addr = change_point[chg_idx]->addr; + new_entries[new_nr_entries].type = current_type; + last_addr = change_point[chg_idx]->addr; } last_type = current_type; } } - /* retain count for new bios entries */ - new_nr = new_bios_entry; - /* copy new bios mapping into original location */ - memcpy(biosmap, new_bios, new_nr * sizeof(struct e820entry)); - *pnr_map = new_nr; + /* Copy the new entries into the original location: */ + memcpy(entries, new_entries, new_nr_entries*sizeof(*entries)); + table->nr_entries = new_nr_entries; return 0; } -static int __init __append_e820_map(struct e820entry *biosmap, int nr_map) +static int __init __append_e820_table(struct boot_e820_entry *entries, u32 nr_entries) { - while (nr_map) { - u64 start = biosmap->addr; - u64 size = biosmap->size; + struct boot_e820_entry *entry = entries; + + while (nr_entries) { + u64 start = entry->addr; + u64 size = entry->size; u64 end = start + size - 1; - u32 type = biosmap->type; + u32 type = entry->type; - /* Overflow in 64 bits? Ignore the memory map. */ + /* Ignore the entry on 64-bit overflow: */ if (start > end && likely(size)) return -1; - e820_add_region(start, size, type); + e820__range_add(start, size, type); - biosmap++; - nr_map--; + entry++; + nr_entries--; } return 0; } /* - * Copy the BIOS e820 map into a safe place. + * Copy the BIOS E820 map into a safe place. * * Sanity-check it while we're at it.. * @@ -414,18 +388,17 @@ static int __init __append_e820_map(struct e820entry *biosmap, int nr_map) * will have given us a memory map that we can use to properly * set up memory. If we aren't, we'll fake a memory map. */ -static int __init append_e820_map(struct e820entry *biosmap, int nr_map) +static int __init append_e820_table(struct boot_e820_entry *entries, u32 nr_entries) { /* Only one memory region (or negative)? Ignore it */ - if (nr_map < 2) + if (nr_entries < 2) return -1; - return __append_e820_map(biosmap, nr_map); + return __append_e820_table(entries, nr_entries); } -static u64 __init __e820_update_range(struct e820map *e820x, u64 start, - u64 size, unsigned old_type, - unsigned new_type) +static u64 __init +__e820__range_update(struct e820_table *table, u64 start, u64 size, enum e820_type old_type, enum e820_type new_type) { u64 end; unsigned int i; @@ -437,77 +410,73 @@ static u64 __init __e820_update_range(struct e820map *e820x, u64 start, size = ULLONG_MAX - start; end = start + size; - printk(KERN_DEBUG "e820: update [mem %#010Lx-%#010Lx] ", - (unsigned long long) start, (unsigned long long) (end - 1)); + printk(KERN_DEBUG "e820: update [mem %#010Lx-%#010Lx] ", start, end - 1); e820_print_type(old_type); - printk(KERN_CONT " ==> "); + pr_cont(" ==> "); e820_print_type(new_type); - printk(KERN_CONT "\n"); + pr_cont("\n"); - for (i = 0; i < e820x->nr_map; i++) { - struct e820entry *ei = &e820x->map[i]; + for (i = 0; i < table->nr_entries; i++) { + struct e820_entry *entry = &table->entries[i]; u64 final_start, final_end; - u64 ei_end; + u64 entry_end; - if (ei->type != old_type) + if (entry->type != old_type) continue; - ei_end = ei->addr + ei->size; - /* totally covered by new range? */ - if (ei->addr >= start && ei_end <= end) { - ei->type = new_type; - real_updated_size += ei->size; + entry_end = entry->addr + entry->size; + + /* Completely covered by new range? */ + if (entry->addr >= start && entry_end <= end) { + entry->type = new_type; + real_updated_size += entry->size; continue; } - /* new range is totally covered? */ - if (ei->addr < start && ei_end > end) { - __e820_add_region(e820x, start, size, new_type); - __e820_add_region(e820x, end, ei_end - end, ei->type); - ei->size = start - ei->addr; + /* New range is completely covered? */ + if (entry->addr < start && entry_end > end) { + __e820__range_add(table, start, size, new_type); + __e820__range_add(table, end, entry_end - end, entry->type); + entry->size = start - entry->addr; real_updated_size += size; continue; } - /* partially covered */ - final_start = max(start, ei->addr); - final_end = min(end, ei_end); + /* Partially covered: */ + final_start = max(start, entry->addr); + final_end = min(end, entry_end); if (final_start >= final_end) continue; - __e820_add_region(e820x, final_start, final_end - final_start, - new_type); + __e820__range_add(table, final_start, final_end - final_start, new_type); real_updated_size += final_end - final_start; /* - * left range could be head or tail, so need to update - * size at first. + * Left range could be head or tail, so need to update + * its size first: */ - ei->size -= final_end - final_start; - if (ei->addr < final_start) + entry->size -= final_end - final_start; + if (entry->addr < final_start) continue; - ei->addr = final_end; + + entry->addr = final_end; } return real_updated_size; } -u64 __init e820_update_range(u64 start, u64 size, unsigned old_type, - unsigned new_type) +u64 __init e820__range_update(u64 start, u64 size, enum e820_type old_type, enum e820_type new_type) { - return __e820_update_range(e820, start, size, old_type, new_type); + return __e820__range_update(e820_table, start, size, old_type, new_type); } -static u64 __init e820_update_range_saved(u64 start, u64 size, - unsigned old_type, unsigned new_type) +static u64 __init e820__range_update_firmware(u64 start, u64 size, enum e820_type old_type, enum e820_type new_type) { - return __e820_update_range(e820_saved, start, size, old_type, - new_type); + return __e820__range_update(e820_table_firmware, start, size, old_type, new_type); } -/* make e820 not cover the range */ -u64 __init e820_remove_range(u64 start, u64 size, unsigned old_type, - int checktype) +/* Remove a range of memory from the E820 table: */ +u64 __init e820__range_remove(u64 start, u64 size, enum e820_type old_type, bool check_type) { int i; u64 end; @@ -517,85 +486,89 @@ u64 __init e820_remove_range(u64 start, u64 size, unsigned old_type, size = ULLONG_MAX - start; end = start + size; - printk(KERN_DEBUG "e820: remove [mem %#010Lx-%#010Lx] ", - (unsigned long long) start, (unsigned long long) (end - 1)); - if (checktype) + printk(KERN_DEBUG "e820: remove [mem %#010Lx-%#010Lx] ", start, end - 1); + if (check_type) e820_print_type(old_type); - printk(KERN_CONT "\n"); + pr_cont("\n"); - for (i = 0; i < e820->nr_map; i++) { - struct e820entry *ei = &e820->map[i]; + for (i = 0; i < e820_table->nr_entries; i++) { + struct e820_entry *entry = &e820_table->entries[i]; u64 final_start, final_end; - u64 ei_end; + u64 entry_end; - if (checktype && ei->type != old_type) + if (check_type && entry->type != old_type) continue; - ei_end = ei->addr + ei->size; - /* totally covered? */ - if (ei->addr >= start && ei_end <= end) { - real_removed_size += ei->size; - memset(ei, 0, sizeof(struct e820entry)); + entry_end = entry->addr + entry->size; + + /* Completely covered? */ + if (entry->addr >= start && entry_end <= end) { + real_removed_size += entry->size; + memset(entry, 0, sizeof(*entry)); continue; } - /* new range is totally covered? */ - if (ei->addr < start && ei_end > end) { - e820_add_region(end, ei_end - end, ei->type); - ei->size = start - ei->addr; + /* Is the new range completely covered? */ + if (entry->addr < start && entry_end > end) { + e820__range_add(end, entry_end - end, entry->type); + entry->size = start - entry->addr; real_removed_size += size; continue; } - /* partially covered */ - final_start = max(start, ei->addr); - final_end = min(end, ei_end); + /* Partially covered: */ + final_start = max(start, entry->addr); + final_end = min(end, entry_end); if (final_start >= final_end) continue; + real_removed_size += final_end - final_start; /* - * left range could be head or tail, so need to update - * size at first. + * Left range could be head or tail, so need to update + * the size first: */ - ei->size -= final_end - final_start; - if (ei->addr < final_start) + entry->size -= final_end - final_start; + if (entry->addr < final_start) continue; - ei->addr = final_end; + + entry->addr = final_end; } return real_removed_size; } -void __init update_e820(void) +void __init e820__update_table_print(void) { - if (sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map)) + if (e820__update_table(e820_table)) return; - printk(KERN_INFO "e820: modified physical RAM map:\n"); - e820_print_map("modified"); + + pr_info("e820: modified physical RAM map:\n"); + e820__print_table("modified"); } -static void __init update_e820_saved(void) + +static void __init e820__update_table_firmware(void) { - sanitize_e820_map(e820_saved->map, ARRAY_SIZE(e820_saved->map), - &e820_saved->nr_map); + e820__update_table(e820_table_firmware); } + #define MAX_GAP_END 0x100000000ull + /* - * Search for a gap in the e820 memory space from 0 to MAX_GAP_END. + * Search for a gap in the E820 memory space from 0 to MAX_GAP_END (4GB). */ -static int __init e820_search_gap(unsigned long *gapstart, - unsigned long *gapsize) +static int __init e820_search_gap(unsigned long *gapstart, unsigned long *gapsize) { unsigned long long last = MAX_GAP_END; - int i = e820->nr_map; + int i = e820_table->nr_entries; int found = 0; while (--i >= 0) { - unsigned long long start = e820->map[i].addr; - unsigned long long end = start + e820->map[i].size; + unsigned long long start = e820_table->entries[i].addr; + unsigned long long end = start + e820_table->entries[i].size; /* * Since "last" is at most 4GB, we know we'll - * fit in 32 bits if this condition is true + * fit in 32 bits if this condition is true: */ if (last > end) { unsigned long gap = last - end; @@ -613,12 +586,14 @@ static int __init e820_search_gap(unsigned long *gapstart, } /* - * Search for the biggest gap in the low 32 bits of the e820 - * memory space. We pass this space to PCI to assign MMIO resources - * for hotplug or unconfigured devices in. + * Search for the biggest gap in the low 32 bits of the E820 + * memory space. We pass this space to the PCI subsystem, so + * that it can assign MMIO resources for hotplug or + * unconfigured devices in. + * * Hopefully the BIOS let enough space left. */ -__init void e820_setup_gap(void) +__init void e820__setup_pci_gap(void) { unsigned long gapstart, gapsize; int found; @@ -629,138 +604,143 @@ __init void e820_setup_gap(void) if (!found) { #ifdef CONFIG_X86_64 gapstart = (max_pfn << PAGE_SHIFT) + 1024*1024; - printk(KERN_ERR - "e820: cannot find a gap in the 32bit address range\n" - "e820: PCI devices with unassigned 32bit BARs may break!\n"); + pr_err( + "e820: Cannot find an available gap in the 32-bit address range\n" + "e820: PCI devices with unassigned 32-bit BARs may not work!\n"); #else gapstart = 0x10000000; #endif } /* - * e820_reserve_resources_late protect stolen RAM already + * e820__reserve_resources_late() protects stolen RAM already: */ pci_mem_start = gapstart; - printk(KERN_INFO - "e820: [mem %#010lx-%#010lx] available for PCI devices\n", - gapstart, gapstart + gapsize - 1); + pr_info("e820: [mem %#010lx-%#010lx] available for PCI devices\n", gapstart, gapstart + gapsize - 1); } /* * Called late during init, in free_initmem(). * - * Initial e820 and e820_saved are largish __initdata arrays. - * Copy them to (usually much smaller) dynamically allocated area. - * This is done after all tweaks we ever do to them: - * all functions which modify them are __init functions, - * they won't exist after this point. + * Initial e820_table and e820_table_firmware are largish __initdata arrays. + * + * Copy them to a (usually much smaller) dynamically allocated area that is + * sized precisely after the number of e820 entries. + * + * This is done after we've performed all the fixes and tweaks to the tables. + * All functions which modify them are __init functions, which won't exist + * after free_initmem(). */ -__init void e820_reallocate_tables(void) +__init void e820__reallocate_tables(void) { - struct e820map *n; + struct e820_table *n; int size; - size = offsetof(struct e820map, map) + sizeof(struct e820entry) * e820->nr_map; + size = offsetof(struct e820_table, entries) + sizeof(struct e820_entry)*e820_table->nr_entries; n = kmalloc(size, GFP_KERNEL); BUG_ON(!n); - memcpy(n, e820, size); - e820 = n; + memcpy(n, e820_table, size); + e820_table = n; - size = offsetof(struct e820map, map) + sizeof(struct e820entry) * e820_saved->nr_map; + size = offsetof(struct e820_table, entries) + sizeof(struct e820_entry)*e820_table_firmware->nr_entries; n = kmalloc(size, GFP_KERNEL); BUG_ON(!n); - memcpy(n, e820_saved, size); - e820_saved = n; + memcpy(n, e820_table_firmware, size); + e820_table_firmware = n; } -/** - * Because of the size limitation of struct boot_params, only first - * 128 E820 memory entries are passed to kernel via - * boot_params.e820_map, others are passed via SETUP_E820_EXT node of - * linked list of struct setup_data, which is parsed here. +/* + * Because of the small fixed size of struct boot_params, only the first + * 128 E820 memory entries are passed to the kernel via boot_params.e820_table, + * the remaining (if any) entries are passed via the SETUP_E820_EXT node of + * struct setup_data, which is parsed here. */ -void __init parse_e820_ext(u64 phys_addr, u32 data_len) +void __init e820__memory_setup_extended(u64 phys_addr, u32 data_len) { int entries; - struct e820entry *extmap; + struct boot_e820_entry *extmap; struct setup_data *sdata; sdata = early_memremap(phys_addr, data_len); - entries = sdata->len / sizeof(struct e820entry); - extmap = (struct e820entry *)(sdata->data); - __append_e820_map(extmap, entries); - sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map); + entries = sdata->len / sizeof(*extmap); + extmap = (struct boot_e820_entry *)(sdata->data); + + __append_e820_table(extmap, entries); + e820__update_table(e820_table); + early_memunmap(sdata, data_len); - printk(KERN_INFO "e820: extended physical RAM map:\n"); - e820_print_map("extended"); + pr_info("e820: extended physical RAM map:\n"); + e820__print_table("extended"); } -#if defined(CONFIG_X86_64) || \ - (defined(CONFIG_X86_32) && defined(CONFIG_HIBERNATION)) -/** +/* * Find the ranges of physical addresses that do not correspond to - * e820 RAM areas and mark the corresponding pages as nosave for - * hibernation (32 bit) or software suspend and suspend to RAM (64 bit). + * E820 RAM areas and register the corresponding pages as 'nosave' for + * hibernation (32-bit) or software suspend and suspend to RAM (64-bit). * - * This function requires the e820 map to be sorted and without any + * This function requires the E820 map to be sorted and without any * overlapping entries. */ -void __init e820_mark_nosave_regions(unsigned long limit_pfn) +void __init e820__register_nosave_regions(unsigned long limit_pfn) { int i; unsigned long pfn = 0; - for (i = 0; i < e820->nr_map; i++) { - struct e820entry *ei = &e820->map[i]; + for (i = 0; i < e820_table->nr_entries; i++) { + struct e820_entry *entry = &e820_table->entries[i]; - if (pfn < PFN_UP(ei->addr)) - register_nosave_region(pfn, PFN_UP(ei->addr)); + if (pfn < PFN_UP(entry->addr)) + register_nosave_region(pfn, PFN_UP(entry->addr)); - pfn = PFN_DOWN(ei->addr + ei->size); + pfn = PFN_DOWN(entry->addr + entry->size); - if (ei->type != E820_RAM && ei->type != E820_RESERVED_KERN) - register_nosave_region(PFN_UP(ei->addr), pfn); + if (entry->type != E820_TYPE_RAM && entry->type != E820_TYPE_RESERVED_KERN) + register_nosave_region(PFN_UP(entry->addr), pfn); if (pfn >= limit_pfn) break; } } -#endif #ifdef CONFIG_ACPI -/** - * Mark ACPI NVS memory region, so that we can save/restore it during - * hibernation and the subsequent resume. +/* + * Register ACPI NVS memory regions, so that we can save/restore them during + * hibernation and the subsequent resume: */ -static int __init e820_mark_nvs_memory(void) +static int __init e820__register_nvs_regions(void) { int i; - for (i = 0; i < e820->nr_map; i++) { - struct e820entry *ei = &e820->map[i]; + for (i = 0; i < e820_table->nr_entries; i++) { + struct e820_entry *entry = &e820_table->entries[i]; - if (ei->type == E820_NVS) - acpi_nvs_register(ei->addr, ei->size); + if (entry->type == E820_TYPE_NVS) + acpi_nvs_register(entry->addr, entry->size); } return 0; } -core_initcall(e820_mark_nvs_memory); +core_initcall(e820__register_nvs_regions); #endif /* - * pre allocated 4k and reserved it in memblock and e820_saved + * Allocate the requested number of bytes with the requsted alignment + * and return (the physical address) to the caller. Also register this + * range in the 'firmware' E820 table as a reserved range. + * + * This allows kexec to fake a new mptable, as if it came from the real + * system. */ -u64 __init early_reserve_e820(u64 size, u64 align) +u64 __init e820__memblock_alloc_reserved(u64 size, u64 align) { u64 addr; addr = __memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE); if (addr) { - e820_update_range_saved(addr, size, E820_RAM, E820_RESERVED); - printk(KERN_INFO "e820: update e820_saved for early_reserve_e820\n"); - update_e820_saved(); + e820__range_update_firmware(addr, size, E820_TYPE_RAM, E820_TYPE_RESERVED); + pr_info("e820: update e820_table_firmware for e820__memblock_alloc_reserved()\n"); + e820__update_table_firmware(); } return addr; @@ -779,22 +759,22 @@ u64 __init early_reserve_e820(u64 size, u64 align) /* * Find the highest page frame number we have available */ -static unsigned long __init e820_end_pfn(unsigned long limit_pfn, unsigned type) +static unsigned long __init e820_end_pfn(unsigned long limit_pfn, enum e820_type type) { int i; unsigned long last_pfn = 0; unsigned long max_arch_pfn = MAX_ARCH_PFN; - for (i = 0; i < e820->nr_map; i++) { - struct e820entry *ei = &e820->map[i]; + for (i = 0; i < e820_table->nr_entries; i++) { + struct e820_entry *entry = &e820_table->entries[i]; unsigned long start_pfn; unsigned long end_pfn; - if (ei->type != type) + if (entry->type != type) continue; - start_pfn = ei->addr >> PAGE_SHIFT; - end_pfn = (ei->addr + ei->size) >> PAGE_SHIFT; + start_pfn = entry->addr >> PAGE_SHIFT; + end_pfn = (entry->addr + entry->size) >> PAGE_SHIFT; if (start_pfn >= limit_pfn) continue; @@ -809,18 +789,19 @@ static unsigned long __init e820_end_pfn(unsigned long limit_pfn, unsigned type) if (last_pfn > max_arch_pfn) last_pfn = max_arch_pfn; - printk(KERN_INFO "e820: last_pfn = %#lx max_arch_pfn = %#lx\n", + pr_info("e820: last_pfn = %#lx max_arch_pfn = %#lx\n", last_pfn, max_arch_pfn); return last_pfn; } -unsigned long __init e820_end_of_ram_pfn(void) + +unsigned long __init e820__end_of_ram_pfn(void) { - return e820_end_pfn(MAX_ARCH_PFN, E820_RAM); + return e820_end_pfn(MAX_ARCH_PFN, E820_TYPE_RAM); } -unsigned long __init e820_end_of_low_ram_pfn(void) +unsigned long __init e820__end_of_low_ram_pfn(void) { - return e820_end_pfn(1UL << (32 - PAGE_SHIFT), E820_RAM); + return e820_end_pfn(1UL << (32 - PAGE_SHIFT), E820_TYPE_RAM); } static void __init early_panic(char *msg) @@ -831,7 +812,7 @@ static void __init early_panic(char *msg) static int userdef __initdata; -/* "mem=nopentium" disables the 4MB page tables. */ +/* The "mem=nopentium" boot option disables 4MB page tables on 32-bit kernels: */ static int __init parse_memopt(char *p) { u64 mem_size; @@ -844,17 +825,19 @@ static int __init parse_memopt(char *p) setup_clear_cpu_cap(X86_FEATURE_PSE); return 0; #else - printk(KERN_WARNING "mem=nopentium ignored! (only supported on x86_32)\n"); + pr_warn("mem=nopentium ignored! (only supported on x86_32)\n"); return -EINVAL; #endif } userdef = 1; mem_size = memparse(p, &p); - /* don't remove all of memory when handling "mem={invalid}" param */ + + /* Don't remove all memory when getting "mem={invalid}" parameter: */ if (mem_size == 0) return -EINVAL; - e820_remove_range(mem_size, ULLONG_MAX - mem_size, E820_RAM, 1); + + e820__range_remove(mem_size, ULLONG_MAX - mem_size, E820_TYPE_RAM, 1); return 0; } @@ -872,12 +855,12 @@ static int __init parse_memmap_one(char *p) #ifdef CONFIG_CRASH_DUMP /* * If we are doing a crash dump, we still need to know - * the real mem size before original memory map is + * the real memory size before the original memory map is * reset. */ - saved_max_pfn = e820_end_of_ram_pfn(); + saved_max_pfn = e820__end_of_ram_pfn(); #endif - e820->nr_map = 0; + e820_table->nr_entries = 0; userdef = 1; return 0; } @@ -890,21 +873,23 @@ static int __init parse_memmap_one(char *p) userdef = 1; if (*p == '@') { start_at = memparse(p+1, &p); - e820_add_region(start_at, mem_size, E820_RAM); + e820__range_add(start_at, mem_size, E820_TYPE_RAM); } else if (*p == '#') { start_at = memparse(p+1, &p); - e820_add_region(start_at, mem_size, E820_ACPI); + e820__range_add(start_at, mem_size, E820_TYPE_ACPI); } else if (*p == '$') { start_at = memparse(p+1, &p); - e820_add_region(start_at, mem_size, E820_RESERVED); + e820__range_add(start_at, mem_size, E820_TYPE_RESERVED); } else if (*p == '!') { start_at = memparse(p+1, &p); - e820_add_region(start_at, mem_size, E820_PRAM); - } else - e820_remove_range(mem_size, ULLONG_MAX - mem_size, E820_RAM, 1); + e820__range_add(start_at, mem_size, E820_TYPE_PRAM); + } else { + e820__range_remove(mem_size, ULLONG_MAX - mem_size, E820_TYPE_RAM, 1); + } return *p == '\0' ? 0 : -EINVAL; } + static int __init parse_memmap_opt(char *str) { while (str) { @@ -921,68 +906,97 @@ static int __init parse_memmap_opt(char *str) } early_param("memmap", parse_memmap_opt); -void __init finish_e820_parsing(void) +/* + * Reserve all entries from the bootloader's extensible data nodes list, + * because if present we are going to use it later on to fetch e820 + * entries from it: + */ +void __init e820__reserve_setup_data(void) +{ + struct setup_data *data; + u64 pa_data; + + pa_data = boot_params.hdr.setup_data; + if (!pa_data) + return; + + while (pa_data) { + data = early_memremap(pa_data, sizeof(*data)); + e820__range_update(pa_data, sizeof(*data)+data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); + pa_data = data->next; + early_memunmap(data, sizeof(*data)); + } + + e820__update_table(e820_table); + + memcpy(e820_table_firmware, e820_table, sizeof(*e820_table_firmware)); + + pr_info("extended physical RAM map:\n"); + e820__print_table("reserve setup_data"); +} + +/* + * Called after parse_early_param(), after early parameters (such as mem=) + * have been processed, in which case we already have an E820 table filled in + * via the parameter callback function(s), but it's not sorted and printed yet: + */ +void __init e820__finish_early_params(void) { if (userdef) { - if (sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), - &e820->nr_map) < 0) + if (e820__update_table(e820_table) < 0) early_panic("Invalid user supplied memory map"); - printk(KERN_INFO "e820: user-defined physical RAM map:\n"); - e820_print_map("user"); + pr_info("e820: user-defined physical RAM map:\n"); + e820__print_table("user"); } } -static const char *__init e820_type_to_string(int e820_type) +static const char *__init e820_type_to_string(struct e820_entry *entry) { - switch (e820_type) { - case E820_RESERVED_KERN: - case E820_RAM: return "System RAM"; - case E820_ACPI: return "ACPI Tables"; - case E820_NVS: return "ACPI Non-volatile Storage"; - case E820_UNUSABLE: return "Unusable memory"; - case E820_PRAM: return "Persistent Memory (legacy)"; - case E820_PMEM: return "Persistent Memory"; - default: return "reserved"; + switch (entry->type) { + case E820_TYPE_RESERVED_KERN: /* Fall-through: */ + case E820_TYPE_RAM: return "System RAM"; + case E820_TYPE_ACPI: return "ACPI Tables"; + case E820_TYPE_NVS: return "ACPI Non-volatile Storage"; + case E820_TYPE_UNUSABLE: return "Unusable memory"; + case E820_TYPE_PRAM: return "Persistent Memory (legacy)"; + case E820_TYPE_PMEM: return "Persistent Memory"; + case E820_TYPE_RESERVED: return "Reserved"; + default: return "Unknown E820 type"; } } -static unsigned long __init e820_type_to_iomem_type(int e820_type) +static unsigned long __init e820_type_to_iomem_type(struct e820_entry *entry) { - switch (e820_type) { - case E820_RESERVED_KERN: - case E820_RAM: - return IORESOURCE_SYSTEM_RAM; - case E820_ACPI: - case E820_NVS: - case E820_UNUSABLE: - case E820_PRAM: - case E820_PMEM: - default: - return IORESOURCE_MEM; + switch (entry->type) { + case E820_TYPE_RESERVED_KERN: /* Fall-through: */ + case E820_TYPE_RAM: return IORESOURCE_SYSTEM_RAM; + case E820_TYPE_ACPI: /* Fall-through: */ + case E820_TYPE_NVS: /* Fall-through: */ + case E820_TYPE_UNUSABLE: /* Fall-through: */ + case E820_TYPE_PRAM: /* Fall-through: */ + case E820_TYPE_PMEM: /* Fall-through: */ + case E820_TYPE_RESERVED: /* Fall-through: */ + default: return IORESOURCE_MEM; } } -static unsigned long __init e820_type_to_iores_desc(int e820_type) +static unsigned long __init e820_type_to_iores_desc(struct e820_entry *entry) { - switch (e820_type) { - case E820_ACPI: - return IORES_DESC_ACPI_TABLES; - case E820_NVS: - return IORES_DESC_ACPI_NV_STORAGE; - case E820_PMEM: - return IORES_DESC_PERSISTENT_MEMORY; - case E820_PRAM: - return IORES_DESC_PERSISTENT_MEMORY_LEGACY; - case E820_RESERVED_KERN: - case E820_RAM: - case E820_UNUSABLE: - default: - return IORES_DESC_NONE; + switch (entry->type) { + case E820_TYPE_ACPI: return IORES_DESC_ACPI_TABLES; + case E820_TYPE_NVS: return IORES_DESC_ACPI_NV_STORAGE; + case E820_TYPE_PMEM: return IORES_DESC_PERSISTENT_MEMORY; + case E820_TYPE_PRAM: return IORES_DESC_PERSISTENT_MEMORY_LEGACY; + case E820_TYPE_RESERVED_KERN: /* Fall-through: */ + case E820_TYPE_RAM: /* Fall-through: */ + case E820_TYPE_UNUSABLE: /* Fall-through: */ + case E820_TYPE_RESERVED: /* Fall-through: */ + default: return IORES_DESC_NONE; } } -static bool __init do_mark_busy(u32 type, struct resource *res) +static bool __init do_mark_busy(enum e820_type type, struct resource *res) { /* this is the legacy bios/dos rom-shadow + mmio region */ if (res->start < (1ULL<<20)) @@ -993,61 +1007,71 @@ static bool __init do_mark_busy(u32 type, struct resource *res) * for exclusive use of a driver */ switch (type) { - case E820_RESERVED: - case E820_PRAM: - case E820_PMEM: + case E820_TYPE_RESERVED: + case E820_TYPE_PRAM: + case E820_TYPE_PMEM: return false; + case E820_TYPE_RESERVED_KERN: + case E820_TYPE_RAM: + case E820_TYPE_ACPI: + case E820_TYPE_NVS: + case E820_TYPE_UNUSABLE: default: return true; } } /* - * Mark e820 reserved areas as busy for the resource manager. + * Mark E820 reserved areas as busy for the resource manager: */ + static struct resource __initdata *e820_res; -void __init e820_reserve_resources(void) + +void __init e820__reserve_resources(void) { int i; struct resource *res; u64 end; - res = alloc_bootmem(sizeof(struct resource) * e820->nr_map); + res = alloc_bootmem(sizeof(*res) * e820_table->nr_entries); e820_res = res; - for (i = 0; i < e820->nr_map; i++) { - end = e820->map[i].addr + e820->map[i].size - 1; + + for (i = 0; i < e820_table->nr_entries; i++) { + struct e820_entry *entry = e820_table->entries + i; + + end = entry->addr + entry->size - 1; if (end != (resource_size_t)end) { res++; continue; } - res->name = e820_type_to_string(e820->map[i].type); - res->start = e820->map[i].addr; - res->end = end; - - res->flags = e820_type_to_iomem_type(e820->map[i].type); - res->desc = e820_type_to_iores_desc(e820->map[i].type); + res->start = entry->addr; + res->end = end; + res->name = e820_type_to_string(entry); + res->flags = e820_type_to_iomem_type(entry); + res->desc = e820_type_to_iores_desc(entry); /* - * don't register the region that could be conflicted with - * pci device BAR resource and insert them later in - * pcibios_resource_survey() + * Don't register the region that could be conflicted with + * PCI device BAR resources and insert them later in + * pcibios_resource_survey(): */ - if (do_mark_busy(e820->map[i].type, res)) { + if (do_mark_busy(entry->type, res)) { res->flags |= IORESOURCE_BUSY; insert_resource(&iomem_resource, res); } res++; } - for (i = 0; i < e820_saved->nr_map; i++) { - struct e820entry *entry = &e820_saved->map[i]; - firmware_map_add_early(entry->addr, - entry->addr + entry->size, - e820_type_to_string(entry->type)); + for (i = 0; i < e820_table_firmware->nr_entries; i++) { + struct e820_entry *entry = e820_table_firmware->entries + i; + + firmware_map_add_early(entry->addr, entry->addr + entry->size, e820_type_to_string(entry)); } } -/* How much should we pad RAM ending depending on where it is? */ +/* + * How much should we pad the end of RAM, depending on where it is? + */ static unsigned long __init ram_alignment(resource_size_t pos) { unsigned long mb = pos >> 20; @@ -1066,64 +1090,59 @@ static unsigned long __init ram_alignment(resource_size_t pos) #define MAX_RESOURCE_SIZE ((resource_size_t)-1) -void __init e820_reserve_resources_late(void) +void __init e820__reserve_resources_late(void) { int i; struct resource *res; res = e820_res; - for (i = 0; i < e820->nr_map; i++) { + for (i = 0; i < e820_table->nr_entries; i++) { if (!res->parent && res->end) insert_resource_expand_to_fit(&iomem_resource, res); res++; } /* - * Try to bump up RAM regions to reasonable boundaries to + * Try to bump up RAM regions to reasonable boundaries, to * avoid stolen RAM: */ - for (i = 0; i < e820->nr_map; i++) { - struct e820entry *entry = &e820->map[i]; + for (i = 0; i < e820_table->nr_entries; i++) { + struct e820_entry *entry = &e820_table->entries[i]; u64 start, end; - if (entry->type != E820_RAM) + if (entry->type != E820_TYPE_RAM) continue; + start = entry->addr + entry->size; end = round_up(start, ram_alignment(start)) - 1; if (end > MAX_RESOURCE_SIZE) end = MAX_RESOURCE_SIZE; if (start >= end) continue; - printk(KERN_DEBUG - "e820: reserve RAM buffer [mem %#010llx-%#010llx]\n", - start, end); - reserve_region_with_split(&iomem_resource, start, end, - "RAM buffer"); + + printk(KERN_DEBUG "e820: reserve RAM buffer [mem %#010llx-%#010llx]\n", start, end); + reserve_region_with_split(&iomem_resource, start, end, "RAM buffer"); } } -char *__init default_machine_specific_memory_setup(void) +/* + * Pass the firmware (bootloader) E820 map to the kernel and process it: + */ +char *__init e820__memory_setup_default(void) { char *who = "BIOS-e820"; - u32 new_nr; + /* * Try to copy the BIOS-supplied E820-map. * * Otherwise fake a memory map; one section from 0k->640k, * the next section from 1mb->appropriate_mem_k */ - new_nr = boot_params.e820_entries; - sanitize_e820_map(boot_params.e820_map, - ARRAY_SIZE(boot_params.e820_map), - &new_nr); - boot_params.e820_entries = new_nr; - if (append_e820_map(boot_params.e820_map, boot_params.e820_entries) - < 0) { + if (append_e820_table(boot_params.e820_table, boot_params.e820_entries) < 0) { u64 mem_size; - /* compare results from other methods and take the greater */ - if (boot_params.alt_mem_k - < boot_params.screen_info.ext_mem_k) { + /* Compare results from other methods and take the one that gives more RAM: */ + if (boot_params.alt_mem_k < boot_params.screen_info.ext_mem_k) { mem_size = boot_params.screen_info.ext_mem_k; who = "BIOS-88"; } else { @@ -1131,84 +1150,68 @@ char *__init default_machine_specific_memory_setup(void) who = "BIOS-e801"; } - e820->nr_map = 0; - e820_add_region(0, LOWMEMSIZE(), E820_RAM); - e820_add_region(HIGH_MEMORY, mem_size << 10, E820_RAM); + e820_table->nr_entries = 0; + e820__range_add(0, LOWMEMSIZE(), E820_TYPE_RAM); + e820__range_add(HIGH_MEMORY, mem_size << 10, E820_TYPE_RAM); } - /* In case someone cares... */ + /* We just appended a lot of ranges, sanitize the table: */ + e820__update_table(e820_table); + return who; } -void __init setup_memory_map(void) +/* + * Calls e820__memory_setup_default() in essence to pick up the firmware/bootloader + * E820 map - with an optional platform quirk available for virtual platforms + * to override this method of boot environment processing: + */ +void __init e820__memory_setup(void) { char *who; + /* This is a firmware interface ABI - make sure we don't break it: */ + BUILD_BUG_ON(sizeof(struct boot_e820_entry) != 20); + who = x86_init.resources.memory_setup(); - memcpy(e820_saved, e820, sizeof(struct e820map)); - printk(KERN_INFO "e820: BIOS-provided physical RAM map:\n"); - e820_print_map(who); + + memcpy(e820_table_firmware, e820_table, sizeof(*e820_table_firmware)); + + pr_info("e820: BIOS-provided physical RAM map:\n"); + e820__print_table(who); } -void __init memblock_x86_fill(void) +void __init e820__memblock_setup(void) { int i; u64 end; /* - * EFI may have more than 128 entries - * We are safe to enable resizing, beause memblock_x86_fill() - * is rather later for x86 + * The bootstrap memblock region count maximum is 128 entries + * (INIT_MEMBLOCK_REGIONS), but EFI might pass us more E820 entries + * than that - so allow memblock resizing. + * + * This is safe, because this call happens pretty late during x86 setup, + * so we know about reserved memory regions already. (This is important + * so that memblock resizing does no stomp over reserved areas.) */ memblock_allow_resize(); - for (i = 0; i < e820->nr_map; i++) { - struct e820entry *ei = &e820->map[i]; + for (i = 0; i < e820_table->nr_entries; i++) { + struct e820_entry *entry = &e820_table->entries[i]; - end = ei->addr + ei->size; + end = entry->addr + entry->size; if (end != (resource_size_t)end) continue; - if (ei->type != E820_RAM && ei->type != E820_RESERVED_KERN) + if (entry->type != E820_TYPE_RAM && entry->type != E820_TYPE_RESERVED_KERN) continue; - memblock_add(ei->addr, ei->size); + memblock_add(entry->addr, entry->size); } - /* throw away partial pages */ + /* Throw away partial pages: */ memblock_trim_memory(PAGE_SIZE); memblock_dump_all(); } - -void __init memblock_find_dma_reserve(void) -{ -#ifdef CONFIG_X86_64 - u64 nr_pages = 0, nr_free_pages = 0; - unsigned long start_pfn, end_pfn; - phys_addr_t start, end; - int i; - u64 u; - - /* - * need to find out used area below MAX_DMA_PFN - * need to use memblock to get free size in [0, MAX_DMA_PFN] - * at first, and assume boot_mem will not take below MAX_DMA_PFN - */ - for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) { - start_pfn = min(start_pfn, MAX_DMA_PFN); - end_pfn = min(end_pfn, MAX_DMA_PFN); - nr_pages += end_pfn - start_pfn; - } - - for_each_free_mem_range(u, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end, - NULL) { - start_pfn = min_t(unsigned long, PFN_UP(start), MAX_DMA_PFN); - end_pfn = min_t(unsigned long, PFN_DOWN(end), MAX_DMA_PFN); - if (start_pfn < end_pfn) - nr_free_pages += end_pfn - start_pfn; - } - - set_dma_reserve(nr_pages - nr_free_pages); -#endif -} diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index 6a08e25a48d8..ff7e4b3988ed 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -546,8 +546,8 @@ intel_graphics_stolen(int num, int slot, int func, &base, &end); /* Mark this space as reserved */ - e820_add_region(base, size, E820_RESERVED); - sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map); + e820__range_add(base, size, E820_TYPE_RESERVED); + e820__update_table(e820_table); } static void __init intel_graphics_quirks(int num, int slot, int func) diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c index 8a121991e5ba..0f0840304452 100644 --- a/arch/x86/kernel/early_printk.c +++ b/arch/x86/kernel/early_printk.c @@ -17,6 +17,7 @@ #include <asm/intel-mid.h> #include <asm/pgtable.h> #include <linux/usb/ehci_def.h> +#include <linux/usb/xhci-dbgp.h> #include <linux/efi.h> #include <asm/efi.h> #include <asm/pci_x86.h> @@ -381,6 +382,10 @@ static int __init setup_early_printk(char *buf) if (!strncmp(buf, "efi", 3)) early_console_register(&early_efi_console, keep); #endif +#ifdef CONFIG_EARLY_PRINTK_USB_XDBC + if (!strncmp(buf, "xdbc", 4)) + early_xdbc_parse_parameter(buf + 4); +#endif buf++; } diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c index 04f89caef9c4..8e598a1ad986 100644 --- a/arch/x86/kernel/espfix_64.c +++ b/arch/x86/kernel/espfix_64.c @@ -50,11 +50,11 @@ #define ESPFIX_STACKS_PER_PAGE (PAGE_SIZE/ESPFIX_STACK_SIZE) /* There is address space for how many espfix pages? */ -#define ESPFIX_PAGE_SPACE (1UL << (PGDIR_SHIFT-PAGE_SHIFT-16)) +#define ESPFIX_PAGE_SPACE (1UL << (P4D_SHIFT-PAGE_SHIFT-16)) #define ESPFIX_MAX_CPUS (ESPFIX_STACKS_PER_PAGE * ESPFIX_PAGE_SPACE) #if CONFIG_NR_CPUS > ESPFIX_MAX_CPUS -# error "Need more than one PGD for the ESPFIX hack" +# error "Need more virtual address space for the ESPFIX hack" #endif #define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO) @@ -121,11 +121,13 @@ static void init_espfix_random(void) void __init init_espfix_bsp(void) { - pgd_t *pgd_p; + pgd_t *pgd; + p4d_t *p4d; /* Install the espfix pud into the kernel page directory */ - pgd_p = &init_level4_pgt[pgd_index(ESPFIX_BASE_ADDR)]; - pgd_populate(&init_mm, pgd_p, (pud_t *)espfix_pud_page); + pgd = &init_level4_pgt[pgd_index(ESPFIX_BASE_ADDR)]; + p4d = p4d_alloc(&init_mm, pgd, ESPFIX_BASE_ADDR); + p4d_populate(&init_mm, p4d, espfix_pud_page); /* Randomize the locations */ init_espfix_random(); diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index cbd73eb42170..5b7153540727 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -29,12 +29,6 @@ #include <asm/ftrace.h> #include <asm/nops.h> -#if defined(CONFIG_FUNCTION_GRAPH_TRACER) && \ - !defined(CC_USING_FENTRY) && \ - !defined(CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE) -# error The following combination is not supported: ((compiler missing -mfentry) || (CONFIG_X86_32 and !CONFIG_DYNAMIC_FTRACE)) && CONFIG_FUNCTION_GRAPH_TRACER && CONFIG_CC_OPTIMIZE_FOR_SIZE -#endif - #ifdef CONFIG_DYNAMIC_FTRACE int ftrace_arch_code_modify_prepare(void) @@ -989,6 +983,18 @@ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent, unsigned long return_hooker = (unsigned long) &return_to_handler; + /* + * When resuming from suspend-to-ram, this function can be indirectly + * called from early CPU startup code while the CPU is in real mode, + * which would fail miserably. Make sure the stack pointer is a + * virtual address. + * + * This check isn't as accurate as virt_addr_valid(), but it should be + * good enough for this purpose, and it's fast. + */ + if (unlikely((long)__builtin_frame_address(0) >= 0)) + return; + if (unlikely(ftrace_graph_is_dead())) return; diff --git a/arch/x86/kernel/ftrace_32.S b/arch/x86/kernel/ftrace_32.S new file mode 100644 index 000000000000..722a145b4139 --- /dev/null +++ b/arch/x86/kernel/ftrace_32.S @@ -0,0 +1,244 @@ +/* + * Copyright (C) 2017 Steven Rostedt, VMware Inc. + */ + +#include <linux/linkage.h> +#include <asm/page_types.h> +#include <asm/segment.h> +#include <asm/export.h> +#include <asm/ftrace.h> + +#ifdef CC_USING_FENTRY +# define function_hook __fentry__ +EXPORT_SYMBOL(__fentry__) +#else +# define function_hook mcount +EXPORT_SYMBOL(mcount) +#endif + +#ifdef CONFIG_DYNAMIC_FTRACE + +/* mcount uses a frame pointer even if CONFIG_FRAME_POINTER is not set */ +#if !defined(CC_USING_FENTRY) || defined(CONFIG_FRAME_POINTER) +# define USING_FRAME_POINTER +#endif + +#ifdef USING_FRAME_POINTER +# define MCOUNT_FRAME 1 /* using frame = true */ +#else +# define MCOUNT_FRAME 0 /* using frame = false */ +#endif + +ENTRY(function_hook) + ret +END(function_hook) + +ENTRY(ftrace_caller) + +#ifdef USING_FRAME_POINTER +# ifdef CC_USING_FENTRY + /* + * Frame pointers are of ip followed by bp. + * Since fentry is an immediate jump, we are left with + * parent-ip, function-ip. We need to add a frame with + * parent-ip followed by ebp. + */ + pushl 4(%esp) /* parent ip */ + pushl %ebp + movl %esp, %ebp + pushl 2*4(%esp) /* function ip */ +# endif + /* For mcount, the function ip is directly above */ + pushl %ebp + movl %esp, %ebp +#endif + pushl %eax + pushl %ecx + pushl %edx + pushl $0 /* Pass NULL as regs pointer */ + +#ifdef USING_FRAME_POINTER + /* Load parent ebp into edx */ + movl 4*4(%esp), %edx +#else + /* There's no frame pointer, load the appropriate stack addr instead */ + lea 4*4(%esp), %edx +#endif + + movl (MCOUNT_FRAME+4)*4(%esp), %eax /* load the rip */ + /* Get the parent ip */ + movl 4(%edx), %edx /* edx has ebp */ + + movl function_trace_op, %ecx + subl $MCOUNT_INSN_SIZE, %eax + +.globl ftrace_call +ftrace_call: + call ftrace_stub + + addl $4, %esp /* skip NULL pointer */ + popl %edx + popl %ecx + popl %eax +#ifdef USING_FRAME_POINTER + popl %ebp +# ifdef CC_USING_FENTRY + addl $4,%esp /* skip function ip */ + popl %ebp /* this is the orig bp */ + addl $4, %esp /* skip parent ip */ +# endif +#endif +.Lftrace_ret: +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +.globl ftrace_graph_call +ftrace_graph_call: + jmp ftrace_stub +#endif + +/* This is weak to keep gas from relaxing the jumps */ +WEAK(ftrace_stub) + ret +END(ftrace_caller) + +ENTRY(ftrace_regs_caller) + /* + * i386 does not save SS and ESP when coming from kernel. + * Instead, to get sp, ®s->sp is used (see ptrace.h). + * Unfortunately, that means eflags must be at the same location + * as the current return ip is. We move the return ip into the + * regs->ip location, and move flags into the return ip location. + */ + pushl $__KERNEL_CS + pushl 4(%esp) /* Save the return ip */ + pushl $0 /* Load 0 into orig_ax */ + pushl %gs + pushl %fs + pushl %es + pushl %ds + pushl %eax + + /* Get flags and place them into the return ip slot */ + pushf + popl %eax + movl %eax, 8*4(%esp) + + pushl %ebp + pushl %edi + pushl %esi + pushl %edx + pushl %ecx + pushl %ebx + + movl 12*4(%esp), %eax /* Load ip (1st parameter) */ + subl $MCOUNT_INSN_SIZE, %eax /* Adjust ip */ +#ifdef CC_USING_FENTRY + movl 15*4(%esp), %edx /* Load parent ip (2nd parameter) */ +#else + movl 0x4(%ebp), %edx /* Load parent ip (2nd parameter) */ +#endif + movl function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */ + pushl %esp /* Save pt_regs as 4th parameter */ + +GLOBAL(ftrace_regs_call) + call ftrace_stub + + addl $4, %esp /* Skip pt_regs */ + + /* restore flags */ + push 14*4(%esp) + popf + + /* Move return ip back to its original location */ + movl 12*4(%esp), %eax + movl %eax, 14*4(%esp) + + popl %ebx + popl %ecx + popl %edx + popl %esi + popl %edi + popl %ebp + popl %eax + popl %ds + popl %es + popl %fs + popl %gs + + /* use lea to not affect flags */ + lea 3*4(%esp), %esp /* Skip orig_ax, ip and cs */ + + jmp .Lftrace_ret +#else /* ! CONFIG_DYNAMIC_FTRACE */ + +ENTRY(function_hook) + cmpl $__PAGE_OFFSET, %esp + jb ftrace_stub /* Paging not enabled yet? */ + + cmpl $ftrace_stub, ftrace_trace_function + jnz .Ltrace +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + cmpl $ftrace_stub, ftrace_graph_return + jnz ftrace_graph_caller + + cmpl $ftrace_graph_entry_stub, ftrace_graph_entry + jnz ftrace_graph_caller +#endif +.globl ftrace_stub +ftrace_stub: + ret + + /* taken from glibc */ +.Ltrace: + pushl %eax + pushl %ecx + pushl %edx + movl 0xc(%esp), %eax + movl 0x4(%ebp), %edx + subl $MCOUNT_INSN_SIZE, %eax + + call *ftrace_trace_function + + popl %edx + popl %ecx + popl %eax + jmp ftrace_stub +END(function_hook) +#endif /* CONFIG_DYNAMIC_FTRACE */ + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +ENTRY(ftrace_graph_caller) + pushl %eax + pushl %ecx + pushl %edx + movl 3*4(%esp), %eax + /* Even with frame pointers, fentry doesn't have one here */ +#ifdef CC_USING_FENTRY + lea 4*4(%esp), %edx + movl $0, %ecx +#else + lea 0x4(%ebp), %edx + movl (%ebp), %ecx +#endif + subl $MCOUNT_INSN_SIZE, %eax + call prepare_ftrace_return + popl %edx + popl %ecx + popl %eax + ret +END(ftrace_graph_caller) + +.globl return_to_handler +return_to_handler: + pushl %eax + pushl %edx +#ifdef CC_USING_FENTRY + movl $0, %eax +#else + movl %ebp, %eax +#endif + call ftrace_return_to_handler + movl %eax, %ecx + popl %edx + popl %eax + jmp *%ecx +#endif diff --git a/arch/x86/kernel/mcount_64.S b/arch/x86/kernel/ftrace_64.S index 7b0d3da52fb4..1dfac634bbf7 100644 --- a/arch/x86/kernel/mcount_64.S +++ b/arch/x86/kernel/ftrace_64.S @@ -1,6 +1,4 @@ /* - * linux/arch/x86_64/mcount_64.S - * * Copyright (C) 2014 Steven Rostedt, Red Hat Inc */ @@ -13,9 +11,6 @@ .code64 .section .entry.text, "ax" - -#ifdef CONFIG_FUNCTION_TRACER - #ifdef CC_USING_FENTRY # define function_hook __fentry__ EXPORT_SYMBOL(__fentry__) @@ -297,7 +292,6 @@ trace: jmp fgraph_trace END(function_hook) #endif /* CONFIG_DYNAMIC_FTRACE */ -#endif /* CONFIG_FUNCTION_TRACER */ #ifdef CONFIG_FUNCTION_GRAPH_TRACER ENTRY(ftrace_graph_caller) diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index e5fb436a6548..538ec012b371 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -12,7 +12,7 @@ #include <asm/setup.h> #include <asm/sections.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/page.h> #include <asm/apic.h> #include <asm/io_apic.h> diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index b5785c197e53..43b7002f44fb 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -24,7 +24,7 @@ #include <asm/tlbflush.h> #include <asm/sections.h> #include <asm/kdebug.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/bios_ebda.h> #include <asm/bootparam_utils.h> #include <asm/microcode.h> diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index b467b14b03eb..ac9d327d2e42 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -269,10 +269,8 @@ ENTRY(secondary_startup_64) /* rsi is pointer to real mode structure with interesting info. pass it to C */ movq %rsi, %rdi - jmp start_cpu -ENDPROC(secondary_startup_64) -ENTRY(start_cpu) +.Ljump_to_C_code: /* * Jump to run C code and to be on a real kernel address. * Since we are running on identity-mapped space we have to jump @@ -305,7 +303,7 @@ ENTRY(start_cpu) pushq %rax # target address in negative space lretq .Lafter_lret: -ENDPROC(start_cpu) +ENDPROC(secondary_startup_64) #include "verify_cpu.S" @@ -313,11 +311,11 @@ ENDPROC(start_cpu) /* * Boot CPU0 entry point. It's called from play_dead(). Everything has been set * up already except stack. We just set up stack here. Then call - * start_secondary() via start_cpu(). + * start_secondary() via .Ljump_to_C_code. */ ENTRY(start_cpu0) movq initial_stack(%rip), %rsp - jmp start_cpu + jmp .Ljump_to_C_code ENDPROC(start_cpu0) #endif diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 4d8183b5f113..f34fe7444836 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -394,6 +394,9 @@ int check_irq_vectors_for_cpu_disable(void) !cpumask_subset(&affinity_new, &online_new)) this_count++; } + /* No need to check any further. */ + if (!this_count) + return 0; count = 0; for_each_online_cpu(cpu) { @@ -411,8 +414,10 @@ int check_irq_vectors_for_cpu_disable(void) for (vector = FIRST_EXTERNAL_VECTOR; vector < first_system_vector; vector++) { if (!test_bit(vector, used_vectors) && - IS_ERR_OR_NULL(per_cpu(vector_irq, cpu)[vector])) - count++; + IS_ERR_OR_NULL(per_cpu(vector_irq, cpu)[vector])) { + if (++count == this_count) + return 0; + } } } diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index 1423ab1b0312..7468c6987547 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -195,7 +195,5 @@ void __init native_init_IRQ(void) if (!acpi_ioapic && !of_ioapic && nr_legacy_irqs()) setup_irq(2, &irq2); -#ifdef CONFIG_X86_32 irq_ctx_init(smp_processor_id()); -#endif } diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index d0a814a9d96a..9d7fd5e6689a 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -25,6 +25,7 @@ #include <asm/setup.h> #include <asm/crash.h> #include <asm/efi.h> +#include <asm/e820/api.h> #include <asm/kexec-bzimage64.h> #define MAX_ELFCOREHDR_STR_LEN 30 /* elfcorehdr=0x<64bit-value> */ @@ -99,15 +100,14 @@ static int setup_e820_entries(struct boot_params *params) { unsigned int nr_e820_entries; - nr_e820_entries = e820_saved->nr_map; + nr_e820_entries = e820_table_firmware->nr_entries; - /* TODO: Pass entries more than E820MAX in bootparams setup data */ - if (nr_e820_entries > E820MAX) - nr_e820_entries = E820MAX; + /* TODO: Pass entries more than E820_MAX_ENTRIES_ZEROPAGE in bootparams setup data */ + if (nr_e820_entries > E820_MAX_ENTRIES_ZEROPAGE) + nr_e820_entries = E820_MAX_ENTRIES_ZEROPAGE; params->e820_entries = nr_e820_entries; - memcpy(¶ms->e820_map, &e820_saved->map, - nr_e820_entries * sizeof(struct e820entry)); + memcpy(¶ms->e820_table, &e820_table_firmware->entries, nr_e820_entries*sizeof(struct e820_entry)); return 0; } @@ -232,10 +232,10 @@ setup_boot_parameters(struct kimage *image, struct boot_params *params, nr_e820_entries = params->e820_entries; for (i = 0; i < nr_e820_entries; i++) { - if (params->e820_map[i].type != E820_RAM) + if (params->e820_table[i].type != E820_TYPE_RAM) continue; - start = params->e820_map[i].addr; - end = params->e820_map[i].addr + params->e820_map[i].size - 1; + start = params->e820_table[i].addr; + end = params->e820_table[i].addr + params->e820_table[i].size - 1; if ((start <= 0x100000) && end > 0x100000) { mem_k = (end >> 10) - (0x100000 >> 10); diff --git a/arch/x86/kernel/kprobes/common.h b/arch/x86/kernel/kprobes/common.h index d688826e5736..db2182d63ed0 100644 --- a/arch/x86/kernel/kprobes/common.h +++ b/arch/x86/kernel/kprobes/common.h @@ -67,7 +67,7 @@ #endif /* Ensure if the instruction can be boostable */ -extern int can_boost(kprobe_opcode_t *instruction, void *addr); +extern int can_boost(struct insn *insn, void *orig_addr); /* Recover instruction if given address is probed */ extern unsigned long recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr); @@ -75,7 +75,7 @@ extern unsigned long recover_probed_instruction(kprobe_opcode_t *buf, * Copy an instruction and adjust the displacement if the instruction * uses the %rip-relative addressing mode. */ -extern int __copy_instruction(u8 *dest, u8 *src); +extern int __copy_instruction(u8 *dest, u8 *src, struct insn *insn); /* Generate a relative-jump/call instruction */ extern void synthesize_reljump(void *from, void *to); diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 993fa4fe4f68..19e1f2a6d7b0 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -164,42 +164,38 @@ static kprobe_opcode_t *skip_prefixes(kprobe_opcode_t *insn) NOKPROBE_SYMBOL(skip_prefixes); /* - * Returns non-zero if opcode is boostable. + * Returns non-zero if INSN is boostable. * RIP relative instructions are adjusted at copying time in 64 bits mode */ -int can_boost(kprobe_opcode_t *opcodes, void *addr) +int can_boost(struct insn *insn, void *addr) { kprobe_opcode_t opcode; - kprobe_opcode_t *orig_opcodes = opcodes; if (search_exception_tables((unsigned long)addr)) return 0; /* Page fault may occur on this address. */ -retry: - if (opcodes - orig_opcodes > MAX_INSN_SIZE - 1) - return 0; - opcode = *(opcodes++); - /* 2nd-byte opcode */ - if (opcode == 0x0f) { - if (opcodes - orig_opcodes > MAX_INSN_SIZE - 1) - return 0; - return test_bit(*opcodes, + if (insn->opcode.nbytes == 2) + return test_bit(insn->opcode.bytes[1], (unsigned long *)twobyte_is_boostable); - } + + if (insn->opcode.nbytes != 1) + return 0; + + /* Can't boost Address-size override prefix */ + if (unlikely(inat_is_address_size_prefix(insn->attr))) + return 0; + + opcode = insn->opcode.bytes[0]; switch (opcode & 0xf0) { -#ifdef CONFIG_X86_64 - case 0x40: - goto retry; /* REX prefix is boostable */ -#endif case 0x60: - if (0x63 < opcode && opcode < 0x67) - goto retry; /* prefixes */ - /* can't boost Address-size override and bound */ - return (opcode != 0x62 && opcode != 0x67); + /* can't boost "bound" */ + return (opcode != 0x62); case 0x70: return 0; /* can't boost conditional jump */ + case 0x90: + return opcode != 0x9a; /* can't boost call far */ case 0xc0: /* can't boost software-interruptions */ return (0xc1 < opcode && opcode < 0xcc) || opcode == 0xcf; @@ -210,14 +206,9 @@ retry: /* can boost in/out and absolute jmps */ return ((opcode & 0x04) || opcode == 0xea); case 0xf0: - if ((opcode & 0x0c) == 0 && opcode != 0xf1) - goto retry; /* lock/rep(ne) prefix */ /* clear and set flags are boostable */ return (opcode == 0xf5 || (0xf7 < opcode && opcode < 0xfe)); default: - /* segment override prefixes are boostable */ - if (opcode == 0x26 || opcode == 0x36 || opcode == 0x3e) - goto retry; /* prefixes */ /* CS override prefix and call are not boostable */ return (opcode != 0x2e && opcode != 0x9a); } @@ -264,7 +255,10 @@ __recover_probed_insn(kprobe_opcode_t *buf, unsigned long addr) * Fortunately, we know that the original code is the ideal 5-byte * long NOP. */ - memcpy(buf, (void *)addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t)); + if (probe_kernel_read(buf, (void *)addr, + MAX_INSN_SIZE * sizeof(kprobe_opcode_t))) + return 0UL; + if (faddr) memcpy(buf, ideal_nops[NOP_ATOMIC5], 5); else @@ -276,7 +270,7 @@ __recover_probed_insn(kprobe_opcode_t *buf, unsigned long addr) * Recover the probed instruction at addr for further analysis. * Caller must lock kprobes by kprobe_mutex, or disable preemption * for preventing to release referencing kprobes. - * Returns zero if the instruction can not get recovered. + * Returns zero if the instruction can not get recovered (or access failed). */ unsigned long recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr) { @@ -348,37 +342,36 @@ static int is_IF_modifier(kprobe_opcode_t *insn) } /* - * Copy an instruction and adjust the displacement if the instruction - * uses the %rip-relative addressing mode. - * If it does, Return the address of the 32-bit displacement word. - * If not, return null. - * Only applicable to 64-bit x86. + * Copy an instruction with recovering modified instruction by kprobes + * and adjust the displacement if the instruction uses the %rip-relative + * addressing mode. + * This returns the length of copied instruction, or 0 if it has an error. */ -int __copy_instruction(u8 *dest, u8 *src) +int __copy_instruction(u8 *dest, u8 *src, struct insn *insn) { - struct insn insn; kprobe_opcode_t buf[MAX_INSN_SIZE]; - int length; unsigned long recovered_insn = recover_probed_instruction(buf, (unsigned long)src); - if (!recovered_insn) + if (!recovered_insn || !insn) + return 0; + + /* This can access kernel text if given address is not recovered */ + if (probe_kernel_read(dest, (void *)recovered_insn, MAX_INSN_SIZE)) return 0; - kernel_insn_init(&insn, (void *)recovered_insn, MAX_INSN_SIZE); - insn_get_length(&insn); - length = insn.length; + + kernel_insn_init(insn, dest, MAX_INSN_SIZE); + insn_get_length(insn); /* Another subsystem puts a breakpoint, failed to recover */ - if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) + if (insn->opcode.bytes[0] == BREAKPOINT_INSTRUCTION) return 0; - memcpy(dest, insn.kaddr, length); #ifdef CONFIG_X86_64 - if (insn_rip_relative(&insn)) { + /* Only x86_64 has RIP relative instructions */ + if (insn_rip_relative(insn)) { s64 newdisp; u8 *disp; - kernel_insn_init(&insn, dest, length); - insn_get_displacement(&insn); /* * The copied instruction uses the %rip-relative addressing * mode. Adjust the displacement for the difference between @@ -391,36 +384,57 @@ int __copy_instruction(u8 *dest, u8 *src) * extension of the original signed 32-bit displacement would * have given. */ - newdisp = (u8 *) src + (s64) insn.displacement.value - (u8 *) dest; + newdisp = (u8 *) src + (s64) insn->displacement.value + - (u8 *) dest; if ((s64) (s32) newdisp != newdisp) { pr_err("Kprobes error: new displacement does not fit into s32 (%llx)\n", newdisp); - pr_err("\tSrc: %p, Dest: %p, old disp: %x\n", src, dest, insn.displacement.value); + pr_err("\tSrc: %p, Dest: %p, old disp: %x\n", + src, dest, insn->displacement.value); return 0; } - disp = (u8 *) dest + insn_offset_displacement(&insn); + disp = (u8 *) dest + insn_offset_displacement(insn); *(s32 *) disp = (s32) newdisp; } #endif - return length; + return insn->length; +} + +/* Prepare reljump right after instruction to boost */ +static void prepare_boost(struct kprobe *p, struct insn *insn) +{ + if (can_boost(insn, p->addr) && + MAX_INSN_SIZE - insn->length >= RELATIVEJUMP_SIZE) { + /* + * These instructions can be executed directly if it + * jumps back to correct address. + */ + synthesize_reljump(p->ainsn.insn + insn->length, + p->addr + insn->length); + p->ainsn.boostable = true; + } else { + p->ainsn.boostable = false; + } } static int arch_copy_kprobe(struct kprobe *p) { - int ret; + struct insn insn; + int len; + + set_memory_rw((unsigned long)p->ainsn.insn & PAGE_MASK, 1); /* Copy an instruction with recovering if other optprobe modifies it.*/ - ret = __copy_instruction(p->ainsn.insn, p->addr); - if (!ret) + len = __copy_instruction(p->ainsn.insn, p->addr, &insn); + if (!len) return -EINVAL; /* * __copy_instruction can modify the displacement of the instruction, * but it doesn't affect boostable check. */ - if (can_boost(p->ainsn.insn, p->addr)) - p->ainsn.boostable = 0; - else - p->ainsn.boostable = -1; + prepare_boost(p, &insn); + + set_memory_ro((unsigned long)p->ainsn.insn & PAGE_MASK, 1); /* Check whether the instruction modifies Interrupt Flag or not */ p->ainsn.if_modifier = is_IF_modifier(p->ainsn.insn); @@ -459,7 +473,7 @@ void arch_disarm_kprobe(struct kprobe *p) void arch_remove_kprobe(struct kprobe *p) { if (p->ainsn.insn) { - free_insn_slot(p->ainsn.insn, (p->ainsn.boostable == 1)); + free_insn_slot(p->ainsn.insn, p->ainsn.boostable); p->ainsn.insn = NULL; } } @@ -531,7 +545,7 @@ static void setup_singlestep(struct kprobe *p, struct pt_regs *regs, return; #if !defined(CONFIG_PREEMPT) - if (p->ainsn.boostable == 1 && !p->post_handler) { + if (p->ainsn.boostable && !p->post_handler) { /* Boost up -- we can execute copied instructions directly */ if (!reenter) reset_current_kprobe(); @@ -851,7 +865,7 @@ static void resume_execution(struct kprobe *p, struct pt_regs *regs, case 0xcf: case 0xea: /* jmp absolute -- ip is correct */ /* ip is already adjusted, no more changes required */ - p->ainsn.boostable = 1; + p->ainsn.boostable = true; goto no_change; case 0xe8: /* call relative - Fix return addr */ *tos = orig_ip + (*tos - copy_ip); @@ -876,28 +890,13 @@ static void resume_execution(struct kprobe *p, struct pt_regs *regs, * jmp near and far, absolute indirect * ip is correct. And this is boostable */ - p->ainsn.boostable = 1; + p->ainsn.boostable = true; goto no_change; } default: break; } - if (p->ainsn.boostable == 0) { - if ((regs->ip > copy_ip) && - (regs->ip - copy_ip) + 5 < MAX_INSN_SIZE) { - /* - * These instructions can be executed directly if it - * jumps back to correct address. - */ - synthesize_reljump((void *)regs->ip, - (void *)orig_ip + (regs->ip - copy_ip)); - p->ainsn.boostable = 1; - } else { - p->ainsn.boostable = -1; - } - } - regs->ip += orig_ip - copy_ip; no_change: diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c index 5f8f0b3cc674..041f7b6dfa0f 100644 --- a/arch/x86/kernel/kprobes/ftrace.c +++ b/arch/x86/kernel/kprobes/ftrace.c @@ -94,6 +94,6 @@ NOKPROBE_SYMBOL(kprobe_ftrace_handler); int arch_prepare_kprobe_ftrace(struct kprobe *p) { p->ainsn.insn = NULL; - p->ainsn.boostable = -1; + p->ainsn.boostable = false; return 0; } diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 3e7c6e5a08ff..9aadff3d0902 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -65,7 +65,10 @@ found: * overwritten by jump destination address. In this case, original * bytes must be recovered from op->optinsn.copied_insn buffer. */ - memcpy(buf, (void *)addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t)); + if (probe_kernel_read(buf, (void *)addr, + MAX_INSN_SIZE * sizeof(kprobe_opcode_t))) + return 0UL; + if (addr == (unsigned long)kp->addr) { buf[0] = kp->opcode; memcpy(buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE); @@ -174,11 +177,12 @@ NOKPROBE_SYMBOL(optimized_callback); static int copy_optimized_instructions(u8 *dest, u8 *src) { + struct insn insn; int len = 0, ret; while (len < RELATIVEJUMP_SIZE) { - ret = __copy_instruction(dest + len, src + len); - if (!ret || !can_boost(dest + len, src + len)) + ret = __copy_instruction(dest + len, src + len, &insn); + if (!ret || !can_boost(&insn, src + len)) return -EINVAL; len += ret; } @@ -350,6 +354,7 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, } buf = (u8 *)op->optinsn.insn; + set_memory_rw((unsigned long)buf & PAGE_MASK, 1); /* Copy instructions into the out-of-line buffer */ ret = copy_optimized_instructions(buf + TMPL_END_IDX, op->kp.addr); @@ -372,6 +377,8 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, synthesize_reljump(buf + TMPL_END_IDX + op->optinsn.size, (u8 *)op->kp.addr + op->optinsn.size); + set_memory_ro((unsigned long)buf & PAGE_MASK, 1); + flush_icache_range((unsigned long) buf, (unsigned long) buf + TMPL_END_IDX + op->optinsn.size + RELATIVEJUMP_SIZE); diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index 469b23d6acc2..5f43cec296c5 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -103,6 +103,7 @@ static void machine_kexec_page_table_set_one( pgd_t *pgd, pmd_t *pmd, pte_t *pte, unsigned long vaddr, unsigned long paddr) { + p4d_t *p4d; pud_t *pud; pgd += pgd_index(vaddr); @@ -110,7 +111,8 @@ static void machine_kexec_page_table_set_one( if (!(pgd_val(*pgd) & _PAGE_PRESENT)) set_pgd(pgd, __pgd(__pa(pmd) | _PAGE_PRESENT)); #endif - pud = pud_offset(pgd, vaddr); + p4d = p4d_offset(pgd, vaddr); + pud = pud_offset(p4d, vaddr); pmd = pmd_offset(pud, vaddr); if (!(pmd_val(*pmd) & _PAGE_PRESENT)) set_pmd(pmd, __pmd(__pa(pte) | _PAGE_TABLE)); diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 857cdbd02867..085c3b300d32 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -36,6 +36,7 @@ static struct kexec_file_ops *kexec_file_loaders[] = { static void free_transition_pgtable(struct kimage *image) { + free_page((unsigned long)image->arch.p4d); free_page((unsigned long)image->arch.pud); free_page((unsigned long)image->arch.pmd); free_page((unsigned long)image->arch.pte); @@ -43,6 +44,7 @@ static void free_transition_pgtable(struct kimage *image) static int init_transition_pgtable(struct kimage *image, pgd_t *pgd) { + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; @@ -53,13 +55,21 @@ static int init_transition_pgtable(struct kimage *image, pgd_t *pgd) paddr = __pa(page_address(image->control_code_page)+PAGE_SIZE); pgd += pgd_index(vaddr); if (!pgd_present(*pgd)) { + p4d = (p4d_t *)get_zeroed_page(GFP_KERNEL); + if (!p4d) + goto err; + image->arch.p4d = p4d; + set_pgd(pgd, __pgd(__pa(p4d) | _KERNPG_TABLE)); + } + p4d = p4d_offset(pgd, vaddr); + if (!p4d_present(*p4d)) { pud = (pud_t *)get_zeroed_page(GFP_KERNEL); if (!pud) goto err; image->arch.pud = pud; - set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE)); + set_p4d(p4d, __p4d(__pa(pud) | _KERNPG_TABLE)); } - pud = pud_offset(pgd, vaddr); + pud = pud_offset(p4d, vaddr); if (!pud_present(*pud)) { pmd = (pmd_t *)get_zeroed_page(GFP_KERNEL); if (!pmd) diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 0f8d20497383..0d904d759ff1 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -26,7 +26,7 @@ #include <asm/io_apic.h> #include <asm/proto.h> #include <asm/bios_ebda.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/setup.h> #include <asm/smp.h> @@ -826,10 +826,10 @@ static int __init parse_alloc_mptable_opt(char *p) } early_param("alloc_mptable", parse_alloc_mptable_opt); -void __init early_reserve_e820_mpc_new(void) +void __init e820__memblock_alloc_reserved_mpc_new(void) { if (enable_update_mptable && alloc_mptable) - mpc_new_phys = early_reserve_e820(mpc_new_length, 4); + mpc_new_phys = e820__memblock_alloc_reserved(mpc_new_length, 4); } static int __init update_mp_table(void) diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index a723ae9440ab..446c8aa09b9b 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -222,17 +222,6 @@ pci_serr_error(unsigned char reason, struct pt_regs *regs) pr_emerg("NMI: PCI system error (SERR) for reason %02x on CPU %d.\n", reason, smp_processor_id()); - /* - * On some machines, PCI SERR line is used to report memory - * errors. EDAC makes use of it. - */ -#if defined(CONFIG_EDAC) - if (edac_handler_set()) { - edac_atomic_assert_error(); - return; - } -#endif - if (panic_on_unrecovered_nmi) nmi_panic(regs, "NMI: Not continuing"); diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 4797e87b0fb6..3586996fc50d 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -405,9 +405,11 @@ struct pv_mmu_ops pv_mmu_ops __ro_after_init = { .alloc_pte = paravirt_nop, .alloc_pmd = paravirt_nop, .alloc_pud = paravirt_nop, + .alloc_p4d = paravirt_nop, .release_pte = paravirt_nop, .release_pmd = paravirt_nop, .release_pud = paravirt_nop, + .release_p4d = paravirt_nop, .set_pte = native_set_pte, .set_pte_at = native_set_pte_at, @@ -430,12 +432,19 @@ struct pv_mmu_ops pv_mmu_ops __ro_after_init = { .pmd_val = PTE_IDENT, .make_pmd = PTE_IDENT, -#if CONFIG_PGTABLE_LEVELS == 4 +#if CONFIG_PGTABLE_LEVELS >= 4 .pud_val = PTE_IDENT, .make_pud = PTE_IDENT, + .set_p4d = native_set_p4d, + +#if CONFIG_PGTABLE_LEVELS >= 5 + .p4d_val = PTE_IDENT, + .make_p4d = PTE_IDENT, + .set_pgd = native_set_pgd, -#endif +#endif /* CONFIG_PGTABLE_LEVELS >= 5 */ +#endif /* CONFIG_PGTABLE_LEVELS >= 4 */ #endif /* CONFIG_PGTABLE_LEVELS >= 3 */ .pte_val = PTE_IDENT, diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c index 0c150c06fa5a..fda7867046d0 100644 --- a/arch/x86/kernel/pci-calgary_64.c +++ b/arch/x86/kernel/pci-calgary_64.c @@ -1007,9 +1007,8 @@ static void __init calgary_enable_translation(struct pci_dev *dev) writel(cpu_to_be32(val32), target); readl(target); /* flush */ - init_timer(&tbl->watchdog_timer); - tbl->watchdog_timer.function = &calgary_watchdog; - tbl->watchdog_timer.data = (unsigned long)dev; + setup_timer(&tbl->watchdog_timer, &calgary_watchdog, + (unsigned long)dev); mod_timer(&tbl->watchdog_timer, jiffies); } diff --git a/arch/x86/kernel/probe_roms.c b/arch/x86/kernel/probe_roms.c index d5f15c3f7b25..963e3fb56437 100644 --- a/arch/x86/kernel/probe_roms.c +++ b/arch/x86/kernel/probe_roms.c @@ -14,7 +14,7 @@ #include <asm/probe_roms.h> #include <asm/pci-direct.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/mmzone.h> #include <asm/setup.h> #include <asm/sections.h> diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index f67591561711..0bb88428cbf2 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -37,6 +37,7 @@ #include <asm/vm86.h> #include <asm/switch_to.h> #include <asm/desc.h> +#include <asm/prctl.h> /* * per-CPU TSS segments. Threads are completely 'soft' on Linux, @@ -124,11 +125,6 @@ void flush_thread(void) fpu__clear(&tsk->thread.fpu); } -static void hard_disable_TSC(void) -{ - cr4_set_bits(X86_CR4_TSD); -} - void disable_TSC(void) { preempt_disable(); @@ -137,15 +133,10 @@ void disable_TSC(void) * Must flip the CPU state synchronously with * TIF_NOTSC in the current running context. */ - hard_disable_TSC(); + cr4_set_bits(X86_CR4_TSD); preempt_enable(); } -static void hard_enable_TSC(void) -{ - cr4_clear_bits(X86_CR4_TSD); -} - static void enable_TSC(void) { preempt_disable(); @@ -154,7 +145,7 @@ static void enable_TSC(void) * Must flip the CPU state synchronously with * TIF_NOTSC in the current running context. */ - hard_enable_TSC(); + cr4_clear_bits(X86_CR4_TSD); preempt_enable(); } @@ -182,54 +173,129 @@ int set_tsc_mode(unsigned int val) return 0; } -void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, - struct tss_struct *tss) -{ - struct thread_struct *prev, *next; - - prev = &prev_p->thread; - next = &next_p->thread; +DEFINE_PER_CPU(u64, msr_misc_features_shadow); - if (test_tsk_thread_flag(prev_p, TIF_BLOCKSTEP) ^ - test_tsk_thread_flag(next_p, TIF_BLOCKSTEP)) { - unsigned long debugctl = get_debugctlmsr(); +static void set_cpuid_faulting(bool on) +{ + u64 msrval; - debugctl &= ~DEBUGCTLMSR_BTF; - if (test_tsk_thread_flag(next_p, TIF_BLOCKSTEP)) - debugctl |= DEBUGCTLMSR_BTF; + msrval = this_cpu_read(msr_misc_features_shadow); + msrval &= ~MSR_MISC_FEATURES_ENABLES_CPUID_FAULT; + msrval |= (on << MSR_MISC_FEATURES_ENABLES_CPUID_FAULT_BIT); + this_cpu_write(msr_misc_features_shadow, msrval); + wrmsrl(MSR_MISC_FEATURES_ENABLES, msrval); +} - update_debugctlmsr(debugctl); +static void disable_cpuid(void) +{ + preempt_disable(); + if (!test_and_set_thread_flag(TIF_NOCPUID)) { + /* + * Must flip the CPU state synchronously with + * TIF_NOCPUID in the current running context. + */ + set_cpuid_faulting(true); } + preempt_enable(); +} - if (test_tsk_thread_flag(prev_p, TIF_NOTSC) ^ - test_tsk_thread_flag(next_p, TIF_NOTSC)) { - /* prev and next are different */ - if (test_tsk_thread_flag(next_p, TIF_NOTSC)) - hard_disable_TSC(); - else - hard_enable_TSC(); +static void enable_cpuid(void) +{ + preempt_disable(); + if (test_and_clear_thread_flag(TIF_NOCPUID)) { + /* + * Must flip the CPU state synchronously with + * TIF_NOCPUID in the current running context. + */ + set_cpuid_faulting(false); } + preempt_enable(); +} + +static int get_cpuid_mode(void) +{ + return !test_thread_flag(TIF_NOCPUID); +} + +static int set_cpuid_mode(struct task_struct *task, unsigned long cpuid_enabled) +{ + if (!static_cpu_has(X86_FEATURE_CPUID_FAULT)) + return -ENODEV; + + if (cpuid_enabled) + enable_cpuid(); + else + disable_cpuid(); + + return 0; +} + +/* + * Called immediately after a successful exec. + */ +void arch_setup_new_exec(void) +{ + /* If cpuid was previously disabled for this task, re-enable it. */ + if (test_thread_flag(TIF_NOCPUID)) + enable_cpuid(); +} - if (test_tsk_thread_flag(next_p, TIF_IO_BITMAP)) { +static inline void switch_to_bitmap(struct tss_struct *tss, + struct thread_struct *prev, + struct thread_struct *next, + unsigned long tifp, unsigned long tifn) +{ + if (tifn & _TIF_IO_BITMAP) { /* * Copy the relevant range of the IO bitmap. * Normally this is 128 bytes or less: */ memcpy(tss->io_bitmap, next->io_bitmap_ptr, max(prev->io_bitmap_max, next->io_bitmap_max)); - /* * Make sure that the TSS limit is correct for the CPU * to notice the IO bitmap. */ refresh_tss_limit(); - } else if (test_tsk_thread_flag(prev_p, TIF_IO_BITMAP)) { + } else if (tifp & _TIF_IO_BITMAP) { /* * Clear any possible leftover bits: */ memset(tss->io_bitmap, 0xff, prev->io_bitmap_max); } +} + +void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, + struct tss_struct *tss) +{ + struct thread_struct *prev, *next; + unsigned long tifp, tifn; + + prev = &prev_p->thread; + next = &next_p->thread; + + tifn = READ_ONCE(task_thread_info(next_p)->flags); + tifp = READ_ONCE(task_thread_info(prev_p)->flags); + switch_to_bitmap(tss, prev, next, tifp, tifn); + propagate_user_return_notify(prev_p, next_p); + + if ((tifp & _TIF_BLOCKSTEP || tifn & _TIF_BLOCKSTEP) && + arch_has_block_step()) { + unsigned long debugctl, msk; + + rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); + debugctl &= ~DEBUGCTLMSR_BTF; + msk = tifn & _TIF_BLOCKSTEP; + debugctl |= (msk >> TIF_BLOCKSTEP) << DEBUGCTLMSR_BTF_SHIFT; + wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); + } + + if ((tifp ^ tifn) & _TIF_NOTSC) + cr4_toggle_bits(X86_CR4_TSD); + + if ((tifp ^ tifn) & _TIF_NOCPUID) + set_cpuid_faulting(!!(tifn & _TIF_NOCPUID)); } /* @@ -550,3 +616,16 @@ out: put_task_stack(p); return ret; } + +long do_arch_prctl_common(struct task_struct *task, int option, + unsigned long cpuid_enabled) +{ + switch (option) { + case ARCH_GET_CPUID: + return get_cpuid_mode(); + case ARCH_SET_CPUID: + return set_cpuid_mode(task, cpuid_enabled); + } + + return -EINVAL; +} diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 4c818f8bc135..ff40e74c9181 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -37,6 +37,7 @@ #include <linux/uaccess.h> #include <linux/io.h> #include <linux/kdebug.h> +#include <linux/syscalls.h> #include <asm/pgtable.h> #include <asm/ldt.h> @@ -56,6 +57,7 @@ #include <asm/switch_to.h> #include <asm/vm86.h> #include <asm/intel_rdt.h> +#include <asm/proto.h> void __show_regs(struct pt_regs *regs, int all) { @@ -304,3 +306,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) return prev_p; } + +SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2) +{ + return do_arch_prctl_common(current, option, arg2); +} diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index d6b784a5520d..825a1e47cf3e 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -37,6 +37,7 @@ #include <linux/uaccess.h> #include <linux/io.h> #include <linux/ftrace.h> +#include <linux/syscalls.h> #include <asm/pgtable.h> #include <asm/processor.h> @@ -52,6 +53,11 @@ #include <asm/xen/hypervisor.h> #include <asm/vdso.h> #include <asm/intel_rdt.h> +#include <asm/unistd.h> +#ifdef CONFIG_IA32_EMULATION +/* Not included via unistd.h */ +#include <asm/unistd_32_ia32.h> +#endif __visible DEFINE_PER_CPU(unsigned long, rsp_scratch); @@ -204,7 +210,7 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp, (struct user_desc __user *)tls, 0); else #endif - err = do_arch_prctl(p, ARCH_SET_FS, tls); + err = do_arch_prctl_64(p, ARCH_SET_FS, tls); if (err) goto out; } @@ -493,6 +499,8 @@ void set_personality_64bit(void) clear_thread_flag(TIF_IA32); clear_thread_flag(TIF_ADDR32); clear_thread_flag(TIF_X32); + /* Pretend that this comes from a 64bit execve */ + task_pt_regs(current)->orig_ax = __NR_execve; /* Ensure the corresponding mm is not marked. */ if (current->mm) @@ -505,32 +513,50 @@ void set_personality_64bit(void) current->personality &= ~READ_IMPLIES_EXEC; } -void set_personality_ia32(bool x32) +static void __set_personality_x32(void) { - /* inherit personality from parent */ +#ifdef CONFIG_X86_X32 + clear_thread_flag(TIF_IA32); + set_thread_flag(TIF_X32); + if (current->mm) + current->mm->context.ia32_compat = TIF_X32; + current->personality &= ~READ_IMPLIES_EXEC; + /* + * in_compat_syscall() uses the presence of the x32 syscall bit + * flag to determine compat status. The x86 mmap() code relies on + * the syscall bitness so set x32 syscall bit right here to make + * in_compat_syscall() work during exec(). + * + * Pretend to come from a x32 execve. + */ + task_pt_regs(current)->orig_ax = __NR_x32_execve | __X32_SYSCALL_BIT; + current->thread.status &= ~TS_COMPAT; +#endif +} + +static void __set_personality_ia32(void) +{ +#ifdef CONFIG_IA32_EMULATION + set_thread_flag(TIF_IA32); + clear_thread_flag(TIF_X32); + if (current->mm) + current->mm->context.ia32_compat = TIF_IA32; + current->personality |= force_personality32; + /* Prepare the first "return" to user space */ + task_pt_regs(current)->orig_ax = __NR_ia32_execve; + current->thread.status |= TS_COMPAT; +#endif +} +void set_personality_ia32(bool x32) +{ /* Make sure to be in 32bit mode */ set_thread_flag(TIF_ADDR32); - /* Mark the associated mm as containing 32-bit tasks. */ - if (x32) { - clear_thread_flag(TIF_IA32); - set_thread_flag(TIF_X32); - if (current->mm) - current->mm->context.ia32_compat = TIF_X32; - current->personality &= ~READ_IMPLIES_EXEC; - /* in_compat_syscall() uses the presence of the x32 - syscall bit flag to determine compat status */ - current->thread.status &= ~TS_COMPAT; - } else { - set_thread_flag(TIF_IA32); - clear_thread_flag(TIF_X32); - if (current->mm) - current->mm->context.ia32_compat = TIF_IA32; - current->personality |= force_personality32; - /* Prepare the first "return" to user space */ - current->thread.status |= TS_COMPAT; - } + if (x32) + __set_personality_x32(); + else + __set_personality_ia32(); } EXPORT_SYMBOL_GPL(set_personality_ia32); @@ -547,70 +573,72 @@ static long prctl_map_vdso(const struct vdso_image *image, unsigned long addr) } #endif -long do_arch_prctl(struct task_struct *task, int code, unsigned long addr) +long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2) { int ret = 0; int doit = task == current; int cpu; - switch (code) { + switch (option) { case ARCH_SET_GS: - if (addr >= TASK_SIZE_MAX) + if (arg2 >= TASK_SIZE_MAX) return -EPERM; cpu = get_cpu(); task->thread.gsindex = 0; - task->thread.gsbase = addr; + task->thread.gsbase = arg2; if (doit) { load_gs_index(0); - ret = wrmsrl_safe(MSR_KERNEL_GS_BASE, addr); + ret = wrmsrl_safe(MSR_KERNEL_GS_BASE, arg2); } put_cpu(); break; case ARCH_SET_FS: /* Not strictly needed for fs, but do it for symmetry with gs */ - if (addr >= TASK_SIZE_MAX) + if (arg2 >= TASK_SIZE_MAX) return -EPERM; cpu = get_cpu(); task->thread.fsindex = 0; - task->thread.fsbase = addr; + task->thread.fsbase = arg2; if (doit) { /* set the selector to 0 to not confuse __switch_to */ loadsegment(fs, 0); - ret = wrmsrl_safe(MSR_FS_BASE, addr); + ret = wrmsrl_safe(MSR_FS_BASE, arg2); } put_cpu(); break; case ARCH_GET_FS: { unsigned long base; + if (doit) rdmsrl(MSR_FS_BASE, base); else base = task->thread.fsbase; - ret = put_user(base, (unsigned long __user *)addr); + ret = put_user(base, (unsigned long __user *)arg2); break; } case ARCH_GET_GS: { unsigned long base; + if (doit) rdmsrl(MSR_KERNEL_GS_BASE, base); else base = task->thread.gsbase; - ret = put_user(base, (unsigned long __user *)addr); + ret = put_user(base, (unsigned long __user *)arg2); break; } #ifdef CONFIG_CHECKPOINT_RESTORE # ifdef CONFIG_X86_X32_ABI case ARCH_MAP_VDSO_X32: - return prctl_map_vdso(&vdso_image_x32, addr); + return prctl_map_vdso(&vdso_image_x32, arg2); # endif # if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION case ARCH_MAP_VDSO_32: - return prctl_map_vdso(&vdso_image_32, addr); + return prctl_map_vdso(&vdso_image_32, arg2); # endif case ARCH_MAP_VDSO_64: - return prctl_map_vdso(&vdso_image_64, addr); + return prctl_map_vdso(&vdso_image_64, arg2); #endif default: @@ -621,10 +649,23 @@ long do_arch_prctl(struct task_struct *task, int code, unsigned long addr) return ret; } -long sys_arch_prctl(int code, unsigned long addr) +SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2) { - return do_arch_prctl(current, code, addr); + long ret; + + ret = do_arch_prctl_64(current, option, arg2); + if (ret == -EINVAL) + ret = do_arch_prctl_common(current, option, arg2); + + return ret; +} + +#ifdef CONFIG_IA32_EMULATION +COMPAT_SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2) +{ + return do_arch_prctl_common(current, option, arg2); } +#endif unsigned long KSTK_ESP(struct task_struct *task) { diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 2364b23ea3e5..f37d18124648 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -396,12 +396,12 @@ static int putreg(struct task_struct *child, if (value >= TASK_SIZE_MAX) return -EIO; /* - * When changing the segment base, use do_arch_prctl + * When changing the segment base, use do_arch_prctl_64 * to set either thread.fs or thread.fsindex and the * corresponding GDT slot. */ if (child->thread.fsbase != value) - return do_arch_prctl(child, ARCH_SET_FS, value); + return do_arch_prctl_64(child, ARCH_SET_FS, value); return 0; case offsetof(struct user_regs_struct,gs_base): /* @@ -410,7 +410,7 @@ static int putreg(struct task_struct *child, if (value >= TASK_SIZE_MAX) return -EIO; if (child->thread.gsbase != value) - return do_arch_prctl(child, ARCH_SET_GS, value); + return do_arch_prctl_64(child, ARCH_SET_GS, value); return 0; #endif } @@ -869,7 +869,7 @@ long arch_ptrace(struct task_struct *child, long request, Works just like arch_prctl, except that the arguments are reversed. */ case PTRACE_ARCH_PRCTL: - ret = do_arch_prctl(child, data, addr); + ret = do_arch_prctl_64(child, data, addr); break; #endif diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 067f9813fd2c..2544700a2a87 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -765,10 +765,11 @@ void machine_crash_shutdown(struct pt_regs *regs) #endif +/* This is the CPU performing the emergency shutdown work. */ +int crashing_cpu = -1; + #if defined(CONFIG_SMP) -/* This keeps a track of which one is crashing cpu. */ -static int crashing_cpu; static nmi_shootdown_cb shootdown_callback; static atomic_t waiting_for_crash_ipi; diff --git a/arch/x86/kernel/resource.c b/arch/x86/kernel/resource.c index 2408c1603438..5ab3895516ac 100644 --- a/arch/x86/kernel/resource.c +++ b/arch/x86/kernel/resource.c @@ -1,5 +1,5 @@ #include <linux/ioport.h> -#include <asm/e820.h> +#include <asm/e820/api.h> static void resource_clip(struct resource *res, resource_size_t start, resource_size_t end) @@ -25,10 +25,10 @@ static void resource_clip(struct resource *res, resource_size_t start, static void remove_e820_regions(struct resource *avail) { int i; - struct e820entry *entry; + struct e820_entry *entry; - for (i = 0; i < e820->nr_map; i++) { - entry = &e820->map[i]; + for (i = 0; i < e820_table->nr_entries; i++) { + entry = &e820_table->entries[i]; resource_clip(avail, entry->addr, entry->addr + entry->size - 1); diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 4bf0c8926a1c..603a1669a2ec 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -70,12 +70,13 @@ #include <linux/tboot.h> #include <linux/jiffies.h> +#include <linux/usb/xhci-dbgp.h> #include <video/edid.h> #include <asm/mtrr.h> #include <asm/apic.h> #include <asm/realmode.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/mpspec.h> #include <asm/setup.h> #include <asm/efi.h> @@ -119,7 +120,7 @@ * max_low_pfn_mapped: highest direct mapped pfn under 4GB * max_pfn_mapped: highest direct mapped pfn over 4GB * - * The direct mapping only covers E820_RAM regions, so the ranges and gaps are + * The direct mapping only covers E820_TYPE_RAM regions, so the ranges and gaps are * represented by pfn_mapped */ unsigned long max_low_pfn_mapped; @@ -173,14 +174,11 @@ static struct resource bss_resource = { #ifdef CONFIG_X86_32 -/* cpu data as detected by the assembly code in head.S */ -struct cpuinfo_x86 new_cpu_data = { - .wp_works_ok = -1, -}; +/* cpu data as detected by the assembly code in head_32.S */ +struct cpuinfo_x86 new_cpu_data; + /* common cpu data for all cpus */ -struct cpuinfo_x86 boot_cpu_data __read_mostly = { - .wp_works_ok = -1, -}; +struct cpuinfo_x86 boot_cpu_data __read_mostly; EXPORT_SYMBOL(boot_cpu_data); unsigned int def_to_bigsmp; @@ -426,7 +424,7 @@ static void __init parse_setup_data(void) switch (data_type) { case SETUP_E820_EXT: - parse_e820_ext(pa_data, data_len); + e820__memory_setup_extended(pa_data, data_len); break; case SETUP_DTB: add_dtb(pa_data); @@ -441,29 +439,6 @@ static void __init parse_setup_data(void) } } -static void __init e820_reserve_setup_data(void) -{ - struct setup_data *data; - u64 pa_data; - - pa_data = boot_params.hdr.setup_data; - if (!pa_data) - return; - - while (pa_data) { - data = early_memremap(pa_data, sizeof(*data)); - e820_update_range(pa_data, sizeof(*data)+data->len, - E820_RAM, E820_RESERVED_KERN); - pa_data = data->next; - early_memunmap(data, sizeof(*data)); - } - - sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map); - memcpy(e820_saved, e820, sizeof(struct e820map)); - printk(KERN_INFO "extended physical RAM map:\n"); - e820_print_map("reserve setup_data"); -} - static void __init memblock_x86_reserve_range_setup_data(void) { struct setup_data *data; @@ -756,16 +731,16 @@ static void __init trim_bios_range(void) * since some BIOSes are known to corrupt low memory. See the * Kconfig help text for X86_RESERVE_LOW. */ - e820_update_range(0, PAGE_SIZE, E820_RAM, E820_RESERVED); + e820__range_update(0, PAGE_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED); /* * special case: Some BIOSen report the PC BIOS * area (640->1Mb) as ram even though it is not. * take them out. */ - e820_remove_range(BIOS_BEGIN, BIOS_END - BIOS_BEGIN, E820_RAM, 1); + e820__range_remove(BIOS_BEGIN, BIOS_END - BIOS_BEGIN, E820_TYPE_RAM, 1); - sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map); + e820__update_table(e820_table); } /* called before trim_bios_range() to spare extra sanitize */ @@ -775,18 +750,18 @@ static void __init e820_add_kernel_range(void) u64 size = __pa_symbol(_end) - start; /* - * Complain if .text .data and .bss are not marked as E820_RAM and + * Complain if .text .data and .bss are not marked as E820_TYPE_RAM and * attempt to fix it by adding the range. We may have a confused BIOS, * or the user may have used memmap=exactmap or memmap=xxM$yyM to * exclude kernel range. If we really are running on top non-RAM, * we will crash later anyways. */ - if (e820_all_mapped(start, start + size, E820_RAM)) + if (e820__mapped_all(start, start + size, E820_TYPE_RAM)) return; - pr_warn(".text .data .bss are not marked as E820_RAM!\n"); - e820_remove_range(start, size, E820_RAM, 0); - e820_add_region(start, size, E820_RAM); + pr_warn(".text .data .bss are not marked as E820_TYPE_RAM!\n"); + e820__range_remove(start, size, E820_TYPE_RAM, 0); + e820__range_add(start, size, E820_TYPE_RAM); } static unsigned reserve_low = CONFIG_X86_RESERVE_LOW << 10; @@ -837,6 +812,26 @@ dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p) return 0; } +static void __init simple_udelay_calibration(void) +{ + unsigned int tsc_khz, cpu_khz; + unsigned long lpj; + + if (!boot_cpu_has(X86_FEATURE_TSC)) + return; + + cpu_khz = x86_platform.calibrate_cpu(); + tsc_khz = x86_platform.calibrate_tsc(); + + tsc_khz = tsc_khz ? : cpu_khz; + if (!tsc_khz) + return; + + lpj = tsc_khz * 1000; + do_div(lpj, HZ); + loops_per_jiffy = lpj; +} + /* * Determine if we were loaded by an EFI loader. If so, then we have also been * passed the efi memmap, systab, etc., so we should use these data structures @@ -939,7 +934,7 @@ void __init setup_arch(char **cmdline_p) x86_init.oem.arch_setup(); iomem_resource.end = (1ULL << boot_cpu_data.x86_phys_bits) - 1; - setup_memory_map(); + e820__memory_setup(); parse_setup_data(); copy_edd(); @@ -985,6 +980,8 @@ void __init setup_arch(char **cmdline_p) */ x86_configure_nx(); + simple_udelay_calibration(); + parse_early_param(); #ifdef CONFIG_MEMORY_HOTPLUG @@ -1028,9 +1025,8 @@ void __init setup_arch(char **cmdline_p) early_dump_pci_devices(); #endif - /* update the e820_saved too */ - e820_reserve_setup_data(); - finish_e820_parsing(); + e820__reserve_setup_data(); + e820__finish_early_params(); if (efi_enabled(EFI_BOOT)) efi_init(); @@ -1056,11 +1052,11 @@ void __init setup_arch(char **cmdline_p) trim_bios_range(); #ifdef CONFIG_X86_32 if (ppro_with_ram_bug()) { - e820_update_range(0x70000000ULL, 0x40000ULL, E820_RAM, - E820_RESERVED); - sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map); + e820__range_update(0x70000000ULL, 0x40000ULL, E820_TYPE_RAM, + E820_TYPE_RESERVED); + e820__update_table(e820_table); printk(KERN_INFO "fixed physical RAM map:\n"); - e820_print_map("bad_ppro"); + e820__print_table("bad_ppro"); } #else early_gart_iommu_check(); @@ -1070,12 +1066,12 @@ void __init setup_arch(char **cmdline_p) * partially used pages are not usable - thus * we are rounding upwards: */ - max_pfn = e820_end_of_ram_pfn(); + max_pfn = e820__end_of_ram_pfn(); /* update e820 for memory not covered by WB MTRRs */ mtrr_bp_init(); if (mtrr_trim_uncached_memory(max_pfn)) - max_pfn = e820_end_of_ram_pfn(); + max_pfn = e820__end_of_ram_pfn(); max_possible_pfn = max_pfn; @@ -1094,7 +1090,7 @@ void __init setup_arch(char **cmdline_p) /* How many end-of-memory variables you have, grandma! */ /* need this before calling reserve_initrd */ if (max_pfn > (1UL<<(32 - PAGE_SHIFT))) - max_low_pfn = e820_end_of_low_ram_pfn(); + max_low_pfn = e820__end_of_low_ram_pfn(); else max_low_pfn = max_pfn; @@ -1111,7 +1107,7 @@ void __init setup_arch(char **cmdline_p) early_alloc_pgt_buf(); /* - * Need to conclude brk, before memblock_x86_fill() + * Need to conclude brk, before e820__memblock_setup() * it could use memblock_find_in_range, could overlap with * brk area. */ @@ -1120,7 +1116,10 @@ void __init setup_arch(char **cmdline_p) cleanup_highmap(); memblock_set_current_limit(ISA_END_ADDRESS); - memblock_x86_fill(); + e820__memblock_setup(); + + if (!early_xdbc_setup_hardware()) + early_xdbc_register_console(); reserve_bios_regions(); @@ -1137,7 +1136,7 @@ void __init setup_arch(char **cmdline_p) } /* preallocate 4k for mptable mpc */ - early_reserve_e820_mpc_new(); + e820__memblock_alloc_reserved_mpc_new(); #ifdef CONFIG_X86_CHECK_BIOS_CORRUPTION setup_bios_corruption_check(); @@ -1226,21 +1225,6 @@ void __init setup_arch(char **cmdline_p) kasan_init(); -#ifdef CONFIG_X86_32 - /* sync back kernel address range */ - clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY, - swapper_pg_dir + KERNEL_PGD_BOUNDARY, - KERNEL_PGD_PTRS); - - /* - * sync back low identity map too. It is used for example - * in the 32-bit EFI stub. - */ - clone_pgd_range(initial_page_table, - swapper_pg_dir + KERNEL_PGD_BOUNDARY, - min(KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY)); -#endif - tboot_probe(); map_vsyscall(); @@ -1275,12 +1259,12 @@ void __init setup_arch(char **cmdline_p) kvm_guest_init(); - e820_reserve_resources(); - e820_mark_nosave_regions(max_low_pfn); + e820__reserve_resources(); + e820__register_nosave_regions(max_low_pfn); x86_init.resources.reserve_resources(); - e820_setup_gap(); + e820__setup_pci_gap(); #ifdef CONFIG_VT #if defined(CONFIG_VGA_CONSOLE) diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 9820d6d977c6..bb1e8cc0bc84 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -160,7 +160,7 @@ static inline void setup_percpu_segment(int cpu) pack_descriptor(&gdt, per_cpu_offset(cpu), 0xFFFFF, 0x2 | DESCTYPE_S, 0x8); gdt.s = 1; - write_gdt_entry(get_cpu_gdt_table(cpu), + write_gdt_entry(get_cpu_gdt_rw(cpu), GDT_ENTRY_PERCPU, &gdt, DESCTYPE_S); #endif } @@ -288,4 +288,25 @@ void __init setup_per_cpu_areas(void) /* Setup cpu initialized, callin, callout masks */ setup_cpu_local_masks(); + +#ifdef CONFIG_X86_32 + /* + * Sync back kernel address range. We want to make sure that + * all kernel mappings, including percpu mappings, are available + * in the smpboot asm. We can't reliably pick up percpu + * mappings using vmalloc_fault(), because exception dispatch + * needs percpu data. + */ + clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY, + swapper_pg_dir + KERNEL_PGD_BOUNDARY, + KERNEL_PGD_PTRS); + + /* + * sync back low identity map too. It is used for example + * in the 32-bit EFI stub. + */ + clone_pgd_range(initial_page_table, + swapper_pg_dir + KERNEL_PGD_BOUNDARY, + min(KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY)); +#endif } diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 396c042e9d0e..cc30a74e4adb 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -846,7 +846,7 @@ void signal_fault(struct pt_regs *regs, void __user *frame, char *where) task_pid_nr(current) > 1 ? KERN_INFO : KERN_EMERG, me->comm, me->pid, where, frame, regs->ip, regs->sp, regs->orig_ax); - print_vma_addr(" in ", regs->ip); + print_vma_addr(KERN_CONT " in ", regs->ip); pr_cont("\n"); } diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c index ec1f756f9dc9..71beb28600d4 100644 --- a/arch/x86/kernel/signal_compat.c +++ b/arch/x86/kernel/signal_compat.c @@ -151,8 +151,8 @@ int __copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from, if (from->si_signo == SIGSEGV) { if (from->si_code == SEGV_BNDERR) { - compat_uptr_t lower = (unsigned long)&to->si_lower; - compat_uptr_t upper = (unsigned long)&to->si_upper; + compat_uptr_t lower = (unsigned long)from->si_lower; + compat_uptr_t upper = (unsigned long)from->si_upper; put_user_ex(lower, &to->si_lower); put_user_ex(upper, &to->si_upper); } diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index d3c66a15bbde..d798c0da451c 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -33,6 +33,7 @@ #include <asm/mce.h> #include <asm/trace/irq_vectors.h> #include <asm/kexec.h> +#include <asm/virtext.h> /* * Some notes on x86 processor bugs affecting SMP operation: @@ -124,7 +125,7 @@ static bool smp_no_nmi_ipi = false; static void native_smp_send_reschedule(int cpu) { if (unlikely(cpu_is_offline(cpu))) { - WARN_ON(1); + WARN(1, "sched: Unexpected reschedule of offline CPU#%d!\n", cpu); return; } apic->send_IPI(cpu, RESCHEDULE_VECTOR); @@ -162,6 +163,7 @@ static int smp_stop_nmi_callback(unsigned int val, struct pt_regs *regs) if (raw_smp_processor_id() == atomic_read(&stopping_cpu)) return NMI_HANDLED; + cpu_emergency_vmxoff(); stop_this_cpu(NULL); return NMI_HANDLED; @@ -174,6 +176,7 @@ static int smp_stop_nmi_callback(unsigned int val, struct pt_regs *regs) asmlinkage __visible void smp_reboot_interrupt(void) { ipi_entering_ack_irq(); + cpu_emergency_vmxoff(); stop_this_cpu(NULL); irq_exit(); } diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index bd1f1ad35284..f04479a8f74f 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -983,7 +983,7 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) unsigned long timeout; idle->thread.sp = (unsigned long)task_pt_regs(idle); - early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu); + early_gdt_descr.address = (unsigned long)get_cpu_gdt_rw(cpu); initial_code = (unsigned long)start_secondary; initial_stack = idle->thread.sp; diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index 50215a4b9347..207b8f2582c7 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -17,6 +17,8 @@ #include <linux/uaccess.h> #include <linux/elf.h> +#include <asm/elf.h> +#include <asm/compat.h> #include <asm/ia32.h> #include <asm/syscalls.h> @@ -101,7 +103,7 @@ out: static void find_start_end(unsigned long flags, unsigned long *begin, unsigned long *end) { - if (!test_thread_flag(TIF_ADDR32) && (flags & MAP_32BIT)) { + if (!in_compat_syscall() && (flags & MAP_32BIT)) { /* This is usually used needed to map code in small model, so it needs to be in the first 31bit. Limit it to that. This means we need to move the @@ -114,10 +116,11 @@ static void find_start_end(unsigned long flags, unsigned long *begin, if (current->flags & PF_RANDOMIZE) { *begin = randomize_page(*begin, 0x02000000); } - } else { - *begin = current->mm->mmap_legacy_base; - *end = TASK_SIZE; + return; } + + *begin = get_mmap_base(1); + *end = in_compat_syscall() ? tasksize_32bit() : tasksize_64bit(); } unsigned long @@ -176,7 +179,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, return addr; /* for MAP_32BIT mappings we force the legacy mmap base */ - if (!test_thread_flag(TIF_ADDR32) && (flags & MAP_32BIT)) + if (!in_compat_syscall() && (flags & MAP_32BIT)) goto bottomup; /* requesting a specific address */ @@ -191,7 +194,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, info.flags = VM_UNMAPPED_AREA_TOPDOWN; info.length = len; info.low_limit = PAGE_SIZE; - info.high_limit = mm->mmap_base; + info.high_limit = get_mmap_base(0); info.align_mask = 0; info.align_offset = pgoff << PAGE_SHIFT; if (filp) { diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c index b868fa1b812b..d4c8011a2293 100644 --- a/arch/x86/kernel/tboot.c +++ b/arch/x86/kernel/tboot.c @@ -42,7 +42,7 @@ #include <asm/fixmap.h> #include <asm/proto.h> #include <asm/setup.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/io.h> #include "../realmode/rm/wakeup.h" @@ -68,9 +68,9 @@ void __init tboot_probe(void) * also verify that it is mapped as we expect it before calling * set_fixmap(), to reduce chance of garbage value causing crash */ - if (!e820_any_mapped(boot_params.tboot_addr, - boot_params.tboot_addr, E820_RESERVED)) { - pr_warning("non-0 tboot_addr but it is not of type E820_RESERVED\n"); + if (!e820__mapped_any(boot_params.tboot_addr, + boot_params.tboot_addr, E820_TYPE_RESERVED)) { + pr_warning("non-0 tboot_addr but it is not of type E820_TYPE_RESERVED\n"); return; } @@ -118,12 +118,16 @@ static int map_tboot_page(unsigned long vaddr, unsigned long pfn, pgprot_t prot) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; pgd = pgd_offset(&tboot_mm, vaddr); - pud = pud_alloc(&tboot_mm, pgd, vaddr); + p4d = p4d_alloc(&tboot_mm, pgd, vaddr); + if (!p4d) + return -1; + pud = pud_alloc(&tboot_mm, p4d, vaddr); if (!pud) return -1; pmd = pmd_alloc(&tboot_mm, pud, vaddr); @@ -188,12 +192,12 @@ static int tboot_setup_sleep(void) tboot->num_mac_regions = 0; - for (i = 0; i < e820->nr_map; i++) { - if ((e820->map[i].type != E820_RAM) - && (e820->map[i].type != E820_RESERVED_KERN)) + for (i = 0; i < e820_table->nr_entries; i++) { + if ((e820_table->entries[i].type != E820_TYPE_RAM) + && (e820_table->entries[i].type != E820_TYPE_RESERVED_KERN)) continue; - add_mac_region(e820->map[i].addr, e820->map[i].size); + add_mac_region(e820_table->entries[i].addr, e820_table->entries[i].size); } tboot->acpi_sinfo.kernel_s3_resume_vector = diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c index 6c8934406dc9..dcd699baea1b 100644 --- a/arch/x86/kernel/tls.c +++ b/arch/x86/kernel/tls.c @@ -92,10 +92,17 @@ static void set_tls_desc(struct task_struct *p, int idx, cpu = get_cpu(); while (n-- > 0) { - if (LDT_empty(info) || LDT_zero(info)) + if (LDT_empty(info) || LDT_zero(info)) { desc->a = desc->b = 0; - else + } else { fill_ldt(desc, info); + + /* + * Always set the accessed bit so that the CPU + * doesn't try to write to the (read-only) GDT. + */ + desc->type |= 1; + } ++info; ++desc; } diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 948443e115c1..3995d3a777d4 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -169,6 +169,37 @@ void ist_end_non_atomic(void) preempt_disable(); } +int is_valid_bugaddr(unsigned long addr) +{ + unsigned short ud; + + if (addr < TASK_SIZE_MAX) + return 0; + + if (probe_kernel_address((unsigned short *)addr, ud)) + return 0; + + return ud == INSN_UD0 || ud == INSN_UD2; +} + +static int fixup_bug(struct pt_regs *regs, int trapnr) +{ + if (trapnr != X86_TRAP_UD) + return 0; + + switch (report_bug(regs->ip, regs)) { + case BUG_TRAP_TYPE_NONE: + case BUG_TRAP_TYPE_BUG: + break; + + case BUG_TRAP_TYPE_WARN: + regs->ip += LEN_UD0; + return 1; + } + + return 0; +} + static nokprobe_inline int do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str, struct pt_regs *regs, long error_code) @@ -187,12 +218,15 @@ do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str, } if (!user_mode(regs)) { - if (!fixup_exception(regs, trapnr)) { - tsk->thread.error_code = error_code; - tsk->thread.trap_nr = trapnr; - die(str, regs, error_code); - } - return 0; + if (fixup_exception(regs, trapnr)) + return 0; + + if (fixup_bug(regs, trapnr)) + return 0; + + tsk->thread.error_code = error_code; + tsk->thread.trap_nr = trapnr; + die(str, regs, error_code); } return -1; @@ -255,7 +289,7 @@ do_trap(int trapnr, int signr, char *str, struct pt_regs *regs, pr_info("%s[%d] trap %s ip:%lx sp:%lx error:%lx", tsk->comm, tsk->pid, str, regs->ip, regs->sp, error_code); - print_vma_addr(" in ", regs->ip); + print_vma_addr(KERN_CONT " in ", regs->ip); pr_cont("\n"); } @@ -519,7 +553,7 @@ do_general_protection(struct pt_regs *regs, long error_code) pr_info("%s[%d] general protection ip:%lx sp:%lx error:%lx", tsk->comm, task_pid_nr(tsk), regs->ip, regs->sp, error_code); - print_vma_addr(" in ", regs->ip); + print_vma_addr(KERN_CONT " in ", regs->ip); pr_cont("\n"); } diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c index 08339262b666..fec70fe3b1ec 100644 --- a/arch/x86/kernel/unwind_frame.c +++ b/arch/x86/kernel/unwind_frame.c @@ -1,6 +1,8 @@ #include <linux/sched.h> #include <linux/sched/task.h> #include <linux/sched/task_stack.h> +#include <linux/interrupt.h> +#include <asm/sections.h> #include <asm/ptrace.h> #include <asm/bitops.h> #include <asm/stacktrace.h> @@ -23,53 +25,53 @@ val; \ }) -static void unwind_dump(struct unwind_state *state, unsigned long *sp) +static void unwind_dump(struct unwind_state *state) { static bool dumped_before = false; bool prev_zero, zero = false; - unsigned long word; + unsigned long word, *sp; + struct stack_info stack_info = {0}; + unsigned long visit_mask = 0; if (dumped_before) return; dumped_before = true; - printk_deferred("unwind stack type:%d next_sp:%p mask:%lx graph_idx:%d\n", + printk_deferred("unwind stack type:%d next_sp:%p mask:0x%lx graph_idx:%d\n", state->stack_info.type, state->stack_info.next_sp, state->stack_mask, state->graph_idx); - for (sp = state->orig_sp; sp < state->stack_info.end; sp++) { - word = READ_ONCE_NOCHECK(*sp); + for (sp = state->orig_sp; sp; sp = PTR_ALIGN(stack_info.next_sp, sizeof(long))) { + if (get_stack_info(sp, state->task, &stack_info, &visit_mask)) + break; - prev_zero = zero; - zero = word == 0; + for (; sp < stack_info.end; sp++) { - if (zero) { - if (!prev_zero) - printk_deferred("%p: %016x ...\n", sp, 0); - continue; - } + word = READ_ONCE_NOCHECK(*sp); + + prev_zero = zero; + zero = word == 0; + + if (zero) { + if (!prev_zero) + printk_deferred("%p: %0*x ...\n", + sp, BITS_PER_LONG/4, 0); + continue; + } - printk_deferred("%p: %016lx (%pB)\n", sp, word, (void *)word); + printk_deferred("%p: %0*lx (%pB)\n", + sp, BITS_PER_LONG/4, word, (void *)word); + } } } unsigned long unwind_get_return_address(struct unwind_state *state) { - unsigned long addr; - unsigned long *addr_p = unwind_get_return_address_ptr(state); - if (unwind_done(state)) return 0; - if (state->regs && user_mode(state->regs)) - return 0; - - addr = READ_ONCE_TASK_STACK(state->task, *addr_p); - addr = ftrace_graph_ret_addr(state->task, &state->graph_idx, addr, - addr_p); - - return __kernel_text_address(addr) ? addr : 0; + return __kernel_text_address(state->ip) ? state->ip : 0; } EXPORT_SYMBOL_GPL(unwind_get_return_address); @@ -82,16 +84,41 @@ static size_t regs_size(struct pt_regs *regs) return sizeof(*regs); } +static bool in_entry_code(unsigned long ip) +{ + char *addr = (char *)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; +} + +static inline unsigned long *last_frame(struct unwind_state *state) +{ + return (unsigned long *)task_pt_regs(state->task) - 2; +} + #ifdef CONFIG_X86_32 #define GCC_REALIGN_WORDS 3 #else #define GCC_REALIGN_WORDS 1 #endif +static inline unsigned long *last_aligned_frame(struct unwind_state *state) +{ + return last_frame(state) - GCC_REALIGN_WORDS; +} + static bool is_last_task_frame(struct unwind_state *state) { - unsigned long *last_bp = (unsigned long *)task_pt_regs(state->task) - 2; - unsigned long *aligned_bp = last_bp - GCC_REALIGN_WORDS; + unsigned long *last_bp = last_frame(state); + unsigned long *aligned_bp = last_aligned_frame(state); /* * We have to check for the last task frame at two different locations @@ -135,26 +162,70 @@ static struct pt_regs *decode_frame_pointer(unsigned long *bp) return (struct pt_regs *)(regs & ~0x1); } -static bool update_stack_state(struct unwind_state *state, void *addr, - size_t len) +static bool update_stack_state(struct unwind_state *state, + unsigned long *next_bp) { struct stack_info *info = &state->stack_info; - enum stack_type orig_type = info->type; + enum stack_type prev_type = info->type; + struct pt_regs *regs; + unsigned long *frame, *prev_frame_end, *addr_p, addr; + size_t len; + + if (state->regs) + prev_frame_end = (void *)state->regs + regs_size(state->regs); + else + prev_frame_end = (void *)state->bp + FRAME_HEADER_SIZE; + + /* Is the next frame pointer an encoded pointer to pt_regs? */ + regs = decode_frame_pointer(next_bp); + if (regs) { + frame = (unsigned long *)regs; + len = regs_size(regs); + state->got_irq = true; + } else { + frame = next_bp; + len = FRAME_HEADER_SIZE; + } /* - * If addr isn't on the current stack, switch to the next one. + * If the next bp 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 'addr' could - * be on a subsequent stack. + * that info->next_sp could point to an empty stack and the next bp + * could be on a subsequent stack. */ - while (!on_stack(info, addr, len)) + while (!on_stack(info, frame, len)) if (get_stack_info(info->next_sp, state->task, info, &state->stack_mask)) return false; - if (!state->orig_sp || info->type != orig_type) - state->orig_sp = addr; + /* Make sure it only unwinds up and doesn't overlap the prev frame: */ + if (state->orig_sp && state->stack_info.type == prev_type && + frame < prev_frame_end) + return false; + + /* Move state to the next frame: */ + if (regs) { + state->regs = regs; + state->bp = NULL; + } else { + state->bp = next_bp; + state->regs = NULL; + } + + /* Save the return address: */ + if (state->regs && user_mode(state->regs)) + state->ip = 0; + else { + addr_p = unwind_get_return_address_ptr(state); + addr = READ_ONCE_TASK_STACK(state->task, *addr_p); + state->ip = ftrace_graph_ret_addr(state->task, &state->graph_idx, + addr, addr_p); + } + + /* Save the original stack pointer for unwind_dump(): */ + if (!state->orig_sp) + state->orig_sp = frame; return true; } @@ -162,14 +233,12 @@ static bool update_stack_state(struct unwind_state *state, void *addr, bool unwind_next_frame(struct unwind_state *state) { struct pt_regs *regs; - unsigned long *next_bp, *next_frame; - size_t next_len; - enum stack_type prev_type = state->stack_info.type; + unsigned long *next_bp; if (unwind_done(state)) return false; - /* have we reached the end? */ + /* Have we reached the end? */ if (state->regs && user_mode(state->regs)) goto the_end; @@ -197,54 +266,19 @@ bool unwind_next_frame(struct unwind_state *state) */ state->regs = regs; state->bp = NULL; + state->ip = 0; return true; } - /* get the next frame pointer */ + /* Get the next frame pointer: */ if (state->regs) next_bp = (unsigned long *)state->regs->bp; else - next_bp = (unsigned long *)READ_ONCE_TASK_STACK(state->task,*state->bp); - - /* is the next frame pointer an encoded pointer to pt_regs? */ - regs = decode_frame_pointer(next_bp); - if (regs) { - next_frame = (unsigned long *)regs; - next_len = sizeof(*regs); - } else { - next_frame = next_bp; - next_len = FRAME_HEADER_SIZE; - } - - /* make sure the next frame's data is accessible */ - if (!update_stack_state(state, next_frame, next_len)) { - /* - * Don't warn on bad regs->bp. An interrupt in entry code - * might cause a false positive warning. - */ - if (state->regs) - goto the_end; + next_bp = (unsigned long *)READ_ONCE_TASK_STACK(state->task, *state->bp); + /* Move to the next frame if it's safe: */ + if (!update_stack_state(state, next_bp)) goto bad_address; - } - - /* Make sure it only unwinds up and doesn't overlap the last frame: */ - if (state->stack_info.type == prev_type) { - if (state->regs && (void *)next_frame < (void *)state->regs + regs_size(state->regs)) - goto bad_address; - - if (state->bp && (void *)next_frame < (void *)state->bp + FRAME_HEADER_SIZE) - goto bad_address; - } - - /* move to the next frame */ - if (regs) { - state->regs = regs; - state->bp = NULL; - } else { - state->bp = next_bp; - state->regs = NULL; - } return true; @@ -259,18 +293,29 @@ bad_address: if (state->task != current) goto the_end; + /* + * Don't warn if the unwinder got lost due to an interrupt in entry + * code or in the C handler before the first frame pointer got set up: + */ + if (state->got_irq && in_entry_code(state->ip)) + goto the_end; + if (state->regs && + state->regs->sp >= (unsigned long)last_aligned_frame(state) && + state->regs->sp < (unsigned long)task_pt_regs(state->task)) + goto the_end; + if (state->regs) { printk_deferred_once(KERN_WARNING "WARNING: kernel stack regs at %p in %s:%d has bad 'bp' value %p\n", state->regs, state->task->comm, - state->task->pid, next_frame); - unwind_dump(state, (unsigned long *)state->regs); + state->task->pid, next_bp); + unwind_dump(state); } else { printk_deferred_once(KERN_WARNING "WARNING: kernel stack frame pointer at %p in %s:%d has bad value %p\n", state->bp, state->task->comm, - state->task->pid, next_frame); - unwind_dump(state, state->bp); + state->task->pid, next_bp); + unwind_dump(state); } the_end: state->stack_info.type = STACK_TYPE_UNKNOWN; @@ -281,35 +326,24 @@ 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) { - unsigned long *bp, *frame; - size_t len; + unsigned long *bp; memset(state, 0, sizeof(*state)); state->task = task; + state->got_irq = (regs); - /* don't even attempt to start from user mode regs */ + /* Don't even attempt to start from user mode regs: */ if (regs && user_mode(regs)) { state->stack_info.type = STACK_TYPE_UNKNOWN; return; } - /* set up the starting stack frame */ bp = get_frame_pointer(task, regs); - regs = decode_frame_pointer(bp); - if (regs) { - state->regs = regs; - frame = (unsigned long *)regs; - len = sizeof(*regs); - } else { - state->bp = bp; - frame = bp; - len = FRAME_HEADER_SIZE; - } - /* initialize stack info and make sure the frame data is accessible */ - get_stack_info(frame, state->task, &state->stack_info, + /* Initialize stack info and make sure the frame data is accessible: */ + get_stack_info(bp, state->task, &state->stack_info, &state->stack_mask); - update_stack_state(state, frame, len); + update_stack_state(state, bp); /* * The caller can provide the address of the first frame directly diff --git a/arch/x86/kernel/unwind_guess.c b/arch/x86/kernel/unwind_guess.c index 22881ddcbb9f..039f36738e49 100644 --- a/arch/x86/kernel/unwind_guess.c +++ b/arch/x86/kernel/unwind_guess.c @@ -34,7 +34,7 @@ bool unwind_next_frame(struct unwind_state *state) return true; } - state->sp = info->next_sp; + state->sp = PTR_ALIGN(info->next_sp, sizeof(long)); } while (!get_stack_info(state->sp, state->task, info, &state->stack_mask)); @@ -49,7 +49,7 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, memset(state, 0, sizeof(*state)); state->task = task; - state->sp = first_frame; + state->sp = PTR_ALIGN(first_frame, sizeof(long)); get_stack_info(first_frame, state->task, &state->stack_info, &state->stack_mask); diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 23ee89ce59a9..7924a5356c8a 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -164,6 +164,7 @@ static void mark_screen_rdonly(struct mm_struct *mm) struct vm_area_struct *vma; spinlock_t *ptl; pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; @@ -173,7 +174,10 @@ static void mark_screen_rdonly(struct mm_struct *mm) pgd = pgd_offset(mm, 0xA0000); if (pgd_none_or_clear_bad(pgd)) goto out; - pud = pud_offset(pgd, 0xA0000); + p4d = p4d_offset(pgd, 0xA0000); + if (p4d_none_or_clear_bad(p4d)) + goto out; + pud = pud_offset(p4d, 0xA0000); if (pud_none_or_clear_bad(pud)) goto out; pmd = pmd_offset(pud, 0xA0000); @@ -193,7 +197,7 @@ static void mark_screen_rdonly(struct mm_struct *mm) pte_unmap_unlock(pte, ptl); out: up_write(&mm->mmap_sem); - flush_tlb(); + flush_tlb_mm_range(mm, 0xA0000, 0xA0000 + 32*PAGE_SIZE, 0UL); } diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index c74ae9ce8dc4..c8a3b61be0aa 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -146,6 +146,7 @@ SECTIONS _edata = .; } :data + BUG_TABLE . = ALIGN(PAGE_SIZE); __vvar_page = .; diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 11a93f005268..a088b2c47f73 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -14,7 +14,7 @@ #include <asm/mpspec.h> #include <asm/setup.h> #include <asm/apic.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/time.h> #include <asm/irq.h> #include <asm/io_apic.h> @@ -38,7 +38,7 @@ struct x86_init_ops x86_init __initdata = { .resources = { .probe_roms = probe_roms, .reserve_resources = reserve_standard_io_resources, - .memory_setup = default_machine_specific_memory_setup, + .memory_setup = e820__memory_setup_default, }, .mpparse = { diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 5fba70646c32..5f48f62b8dc2 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -741,7 +741,6 @@ static int svm_hardware_enable(void) struct svm_cpu_data *sd; uint64_t efer; - struct desc_ptr gdt_descr; struct desc_struct *gdt; int me = raw_smp_processor_id(); @@ -763,8 +762,7 @@ static int svm_hardware_enable(void) sd->max_asid = cpuid_ebx(SVM_CPUID_FUNC) - 1; sd->next_asid = sd->max_asid + 1; - native_store_gdt(&gdt_descr); - gdt = (struct desc_struct *)gdt_descr.address; + gdt = get_current_gdt_rw(); sd->tss_desc = (struct kvm_ldttss_desc *)(gdt + GDT_ENTRY_TSS); wrmsrl(MSR_EFER, efer | EFER_SVME); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 2ee00dbbbd51..1a471e5f963f 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -935,7 +935,6 @@ static DEFINE_PER_CPU(struct vmcs *, current_vmcs); * when a CPU is brought down, and we need to VMCLEAR all VMCSs loaded on it. */ static DEFINE_PER_CPU(struct list_head, loaded_vmcss_on_cpu); -static DEFINE_PER_CPU(struct desc_ptr, host_gdt); /* * We maintian a per-CPU linked-list of vCPU, so in wakeup_handler() we @@ -2057,14 +2056,13 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) */ static unsigned long segment_base(u16 selector) { - struct desc_ptr *gdt = this_cpu_ptr(&host_gdt); struct desc_struct *table; unsigned long v; if (!(selector & ~SEGMENT_RPL_MASK)) return 0; - table = (struct desc_struct *)gdt->address; + table = get_current_gdt_ro(); if ((selector & SEGMENT_TI_MASK) == SEGMENT_LDT) { u16 ldt_selector = kvm_read_ldt(); @@ -2169,7 +2167,7 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx) #endif if (vmx->host_state.msr_host_bndcfgs) wrmsrl(MSR_IA32_BNDCFGS, vmx->host_state.msr_host_bndcfgs); - load_gdt(this_cpu_ptr(&host_gdt)); + load_fixmap_gdt(raw_smp_processor_id()); } static void vmx_load_host_state(struct vcpu_vmx *vmx) @@ -2271,7 +2269,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) } if (!already_loaded) { - struct desc_ptr *gdt = this_cpu_ptr(&host_gdt); + void *gdt = get_current_gdt_ro(); unsigned long sysenter_esp; kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); @@ -2282,7 +2280,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) */ vmcs_writel(HOST_TR_BASE, (unsigned long)this_cpu_ptr(&cpu_tss)); - vmcs_writel(HOST_GDTR_BASE, gdt->address); + vmcs_writel(HOST_GDTR_BASE, (unsigned long)gdt); /* 22.2.4 */ /* * VM exits change the host TR limit to 0x67 after a VM @@ -3471,8 +3469,6 @@ static int hardware_enable(void) ept_sync_global(); } - native_store_gdt(this_cpu_ptr(&host_gdt)); - return 0; } @@ -8198,6 +8194,9 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) return nested_cpu_has2(vmcs12, SECONDARY_EXEC_XSAVES); case EXIT_REASON_PREEMPTION_TIMER: return false; + case EXIT_REASON_PML_FULL: + /* We don't expose PML support to L1. */ + return false; default: return true; } @@ -10267,6 +10266,18 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, } + if (enable_pml) { + /* + * Conceptually we want to copy the PML address and index from + * vmcs01 here, and then back to vmcs01 on nested vmexit. But, + * since we always flush the log on each vmexit, this happens + * to be equivalent to simply resetting the fields in vmcs02. + */ + ASSERT(vmx->pml_pg); + vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg)); + vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1); + } + if (nested_cpu_has_ept(vmcs12)) { kvm_mmu_unload(vcpu); nested_ept_init_mmu_context(vcpu); diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index d3289d7e78fa..99472698c931 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -67,7 +67,7 @@ #include <asm/pgtable.h> #include <asm/desc.h> #include <asm/setup.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/mce.h> #include <asm/io.h> #include <asm/fpu/api.h> @@ -994,7 +994,9 @@ static struct clock_event_device lguest_clockevent = { .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, }; /* @@ -1178,9 +1180,9 @@ 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_add_region(boot_params.e820_map[0].addr, - boot_params.e820_map[0].size, - boot_params.e820_map[0].type); + 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"; diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S index 5e2af3a88cf5..81b1635d67de 100644 --- a/arch/x86/lib/clear_page_64.S +++ b/arch/x86/lib/clear_page_64.S @@ -14,20 +14,15 @@ * Zero a page. * %rdi - page */ -ENTRY(clear_page) - - ALTERNATIVE_2 "jmp clear_page_orig", "", X86_FEATURE_REP_GOOD, \ - "jmp clear_page_c_e", X86_FEATURE_ERMS - +ENTRY(clear_page_rep) movl $4096/8,%ecx xorl %eax,%eax rep stosq ret -ENDPROC(clear_page) -EXPORT_SYMBOL(clear_page) +ENDPROC(clear_page_rep) +EXPORT_SYMBOL_GPL(clear_page_rep) ENTRY(clear_page_orig) - xorl %eax,%eax movl $4096/64,%ecx .p2align 4 @@ -47,10 +42,12 @@ ENTRY(clear_page_orig) nop ret ENDPROC(clear_page_orig) +EXPORT_SYMBOL_GPL(clear_page_orig) -ENTRY(clear_page_c_e) +ENTRY(clear_page_erms) movl $4096,%ecx xorl %eax,%eax rep stosb ret -ENDPROC(clear_page_c_e) +ENDPROC(clear_page_erms) +EXPORT_SYMBOL_GPL(clear_page_erms) diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c index a8e91ae89fb3..29df077cb089 100644 --- a/arch/x86/lib/delay.c +++ b/arch/x86/lib/delay.c @@ -93,6 +93,13 @@ static void delay_mwaitx(unsigned long __loops) { u64 start, end, delay, loops = __loops; + /* + * Timer value of 0 causes MWAITX to wait indefinitely, unless there + * is a store on the memory monitored by MONITORX. + */ + if (loops == 0) + return; + start = rdtsc_ordered(); for (;;) { diff --git a/arch/x86/lib/kaslr.c b/arch/x86/lib/kaslr.c index 121f59c6ee54..5761a4f19455 100644 --- a/arch/x86/lib/kaslr.c +++ b/arch/x86/lib/kaslr.c @@ -8,7 +8,7 @@ #include <asm/kaslr.h> #include <asm/msr.h> #include <asm/archrandom.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/io.h> /* diff --git a/arch/x86/lib/usercopy.c b/arch/x86/lib/usercopy.c index c074799bddae..c8c6ad0d58b8 100644 --- a/arch/x86/lib/usercopy.c +++ b/arch/x86/lib/usercopy.c @@ -4,12 +4,9 @@ * For licencing details see kernel-base/COPYING */ -#include <linux/highmem.h> +#include <linux/uaccess.h> #include <linux/export.h> -#include <asm/word-at-a-time.h> -#include <linux/sched.h> - /* * We rely on the nested NMI work to allow atomic faults from the NMI path; the * nested NMI paths are careful to preserve CR2. @@ -34,52 +31,3 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n) return ret; } EXPORT_SYMBOL_GPL(copy_from_user_nmi); - -/** - * copy_to_user: - Copy a block of data into user space. - * @to: Destination address, in user space. - * @from: Source address, in kernel space. - * @n: Number of bytes to copy. - * - * Context: User context only. This function may sleep if pagefaults are - * enabled. - * - * Copy data from kernel space to user space. - * - * Returns number of bytes that could not be copied. - * On success, this will be zero. - */ -unsigned long _copy_to_user(void __user *to, const void *from, unsigned n) -{ - if (access_ok(VERIFY_WRITE, to, n)) - n = __copy_to_user(to, from, n); - return n; -} -EXPORT_SYMBOL(_copy_to_user); - -/** - * copy_from_user: - Copy a block of data from user space. - * @to: Destination address, in kernel space. - * @from: Source address, in user space. - * @n: Number of bytes to copy. - * - * Context: User context only. This function may sleep if pagefaults are - * enabled. - * - * Copy data from user space to kernel space. - * - * Returns number of bytes that could not be copied. - * On success, this will be zero. - * - * If some data could not be copied, this function will pad the copied - * data to the requested size using zero bytes. - */ -unsigned long _copy_from_user(void *to, const void __user *from, unsigned n) -{ - if (access_ok(VERIFY_READ, from, n)) - n = __copy_from_user(to, from, n); - else - memset(to, 0, n); - return n; -} -EXPORT_SYMBOL(_copy_from_user); diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c index 1f65ff6540f0..bd057a4ffe6e 100644 --- a/arch/x86/lib/usercopy_32.c +++ b/arch/x86/lib/usercopy_32.c @@ -5,12 +5,7 @@ * Copyright 1997 Andi Kleen <ak@muc.de> * Copyright 1997 Linus Torvalds */ -#include <linux/mm.h> -#include <linux/highmem.h> -#include <linux/blkdev.h> #include <linux/export.h> -#include <linux/backing-dev.h> -#include <linux/interrupt.h> #include <linux/uaccess.h> #include <asm/mmx.h> #include <asm/asm.h> @@ -201,197 +196,6 @@ __copy_user_intel(void __user *to, const void *from, unsigned long size) return size; } -static unsigned long -__copy_user_zeroing_intel(void *to, const void __user *from, unsigned long size) -{ - int d0, d1; - __asm__ __volatile__( - " .align 2,0x90\n" - "0: movl 32(%4), %%eax\n" - " cmpl $67, %0\n" - " jbe 2f\n" - "1: movl 64(%4), %%eax\n" - " .align 2,0x90\n" - "2: movl 0(%4), %%eax\n" - "21: movl 4(%4), %%edx\n" - " movl %%eax, 0(%3)\n" - " movl %%edx, 4(%3)\n" - "3: movl 8(%4), %%eax\n" - "31: movl 12(%4),%%edx\n" - " movl %%eax, 8(%3)\n" - " movl %%edx, 12(%3)\n" - "4: movl 16(%4), %%eax\n" - "41: movl 20(%4), %%edx\n" - " movl %%eax, 16(%3)\n" - " movl %%edx, 20(%3)\n" - "10: movl 24(%4), %%eax\n" - "51: movl 28(%4), %%edx\n" - " movl %%eax, 24(%3)\n" - " movl %%edx, 28(%3)\n" - "11: movl 32(%4), %%eax\n" - "61: movl 36(%4), %%edx\n" - " movl %%eax, 32(%3)\n" - " movl %%edx, 36(%3)\n" - "12: movl 40(%4), %%eax\n" - "71: movl 44(%4), %%edx\n" - " movl %%eax, 40(%3)\n" - " movl %%edx, 44(%3)\n" - "13: movl 48(%4), %%eax\n" - "81: movl 52(%4), %%edx\n" - " movl %%eax, 48(%3)\n" - " movl %%edx, 52(%3)\n" - "14: movl 56(%4), %%eax\n" - "91: movl 60(%4), %%edx\n" - " movl %%eax, 56(%3)\n" - " movl %%edx, 60(%3)\n" - " addl $-64, %0\n" - " addl $64, %4\n" - " addl $64, %3\n" - " cmpl $63, %0\n" - " ja 0b\n" - "5: movl %0, %%eax\n" - " shrl $2, %0\n" - " andl $3, %%eax\n" - " cld\n" - "6: rep; movsl\n" - " movl %%eax,%0\n" - "7: rep; movsb\n" - "8:\n" - ".section .fixup,\"ax\"\n" - "9: lea 0(%%eax,%0,4),%0\n" - "16: pushl %0\n" - " pushl %%eax\n" - " xorl %%eax,%%eax\n" - " rep; stosb\n" - " popl %%eax\n" - " popl %0\n" - " jmp 8b\n" - ".previous\n" - _ASM_EXTABLE(0b,16b) - _ASM_EXTABLE(1b,16b) - _ASM_EXTABLE(2b,16b) - _ASM_EXTABLE(21b,16b) - _ASM_EXTABLE(3b,16b) - _ASM_EXTABLE(31b,16b) - _ASM_EXTABLE(4b,16b) - _ASM_EXTABLE(41b,16b) - _ASM_EXTABLE(10b,16b) - _ASM_EXTABLE(51b,16b) - _ASM_EXTABLE(11b,16b) - _ASM_EXTABLE(61b,16b) - _ASM_EXTABLE(12b,16b) - _ASM_EXTABLE(71b,16b) - _ASM_EXTABLE(13b,16b) - _ASM_EXTABLE(81b,16b) - _ASM_EXTABLE(14b,16b) - _ASM_EXTABLE(91b,16b) - _ASM_EXTABLE(6b,9b) - _ASM_EXTABLE(7b,16b) - : "=&c"(size), "=&D" (d0), "=&S" (d1) - : "1"(to), "2"(from), "0"(size) - : "eax", "edx", "memory"); - return size; -} - -/* - * Non Temporal Hint version of __copy_user_zeroing_intel. It is cache aware. - * hyoshiok@miraclelinux.com - */ - -static unsigned long __copy_user_zeroing_intel_nocache(void *to, - const void __user *from, unsigned long size) -{ - int d0, d1; - - __asm__ __volatile__( - " .align 2,0x90\n" - "0: movl 32(%4), %%eax\n" - " cmpl $67, %0\n" - " jbe 2f\n" - "1: movl 64(%4), %%eax\n" - " .align 2,0x90\n" - "2: movl 0(%4), %%eax\n" - "21: movl 4(%4), %%edx\n" - " movnti %%eax, 0(%3)\n" - " movnti %%edx, 4(%3)\n" - "3: movl 8(%4), %%eax\n" - "31: movl 12(%4),%%edx\n" - " movnti %%eax, 8(%3)\n" - " movnti %%edx, 12(%3)\n" - "4: movl 16(%4), %%eax\n" - "41: movl 20(%4), %%edx\n" - " movnti %%eax, 16(%3)\n" - " movnti %%edx, 20(%3)\n" - "10: movl 24(%4), %%eax\n" - "51: movl 28(%4), %%edx\n" - " movnti %%eax, 24(%3)\n" - " movnti %%edx, 28(%3)\n" - "11: movl 32(%4), %%eax\n" - "61: movl 36(%4), %%edx\n" - " movnti %%eax, 32(%3)\n" - " movnti %%edx, 36(%3)\n" - "12: movl 40(%4), %%eax\n" - "71: movl 44(%4), %%edx\n" - " movnti %%eax, 40(%3)\n" - " movnti %%edx, 44(%3)\n" - "13: movl 48(%4), %%eax\n" - "81: movl 52(%4), %%edx\n" - " movnti %%eax, 48(%3)\n" - " movnti %%edx, 52(%3)\n" - "14: movl 56(%4), %%eax\n" - "91: movl 60(%4), %%edx\n" - " movnti %%eax, 56(%3)\n" - " movnti %%edx, 60(%3)\n" - " addl $-64, %0\n" - " addl $64, %4\n" - " addl $64, %3\n" - " cmpl $63, %0\n" - " ja 0b\n" - " sfence \n" - "5: movl %0, %%eax\n" - " shrl $2, %0\n" - " andl $3, %%eax\n" - " cld\n" - "6: rep; movsl\n" - " movl %%eax,%0\n" - "7: rep; movsb\n" - "8:\n" - ".section .fixup,\"ax\"\n" - "9: lea 0(%%eax,%0,4),%0\n" - "16: pushl %0\n" - " pushl %%eax\n" - " xorl %%eax,%%eax\n" - " rep; stosb\n" - " popl %%eax\n" - " popl %0\n" - " jmp 8b\n" - ".previous\n" - _ASM_EXTABLE(0b,16b) - _ASM_EXTABLE(1b,16b) - _ASM_EXTABLE(2b,16b) - _ASM_EXTABLE(21b,16b) - _ASM_EXTABLE(3b,16b) - _ASM_EXTABLE(31b,16b) - _ASM_EXTABLE(4b,16b) - _ASM_EXTABLE(41b,16b) - _ASM_EXTABLE(10b,16b) - _ASM_EXTABLE(51b,16b) - _ASM_EXTABLE(11b,16b) - _ASM_EXTABLE(61b,16b) - _ASM_EXTABLE(12b,16b) - _ASM_EXTABLE(71b,16b) - _ASM_EXTABLE(13b,16b) - _ASM_EXTABLE(81b,16b) - _ASM_EXTABLE(14b,16b) - _ASM_EXTABLE(91b,16b) - _ASM_EXTABLE(6b,9b) - _ASM_EXTABLE(7b,16b) - : "=&c"(size), "=&D" (d0), "=&S" (d1) - : "1"(to), "2"(from), "0"(size) - : "eax", "edx", "memory"); - return size; -} - static unsigned long __copy_user_intel_nocache(void *to, const void __user *from, unsigned long size) { @@ -486,12 +290,8 @@ static unsigned long __copy_user_intel_nocache(void *to, * Leave these declared but undefined. They should not be any references to * them */ -unsigned long __copy_user_zeroing_intel(void *to, const void __user *from, - unsigned long size); unsigned long __copy_user_intel(void __user *to, const void *from, unsigned long size); -unsigned long __copy_user_zeroing_intel_nocache(void *to, - const void __user *from, unsigned long size); #endif /* CONFIG_X86_INTEL_USERCOPY */ /* Generic arbitrary sized copy. */ @@ -528,47 +328,7 @@ do { \ : "memory"); \ } while (0) -#define __copy_user_zeroing(to, from, size) \ -do { \ - int __d0, __d1, __d2; \ - __asm__ __volatile__( \ - " cmp $7,%0\n" \ - " jbe 1f\n" \ - " movl %1,%0\n" \ - " negl %0\n" \ - " andl $7,%0\n" \ - " subl %0,%3\n" \ - "4: rep; movsb\n" \ - " movl %3,%0\n" \ - " shrl $2,%0\n" \ - " andl $3,%3\n" \ - " .align 2,0x90\n" \ - "0: rep; movsl\n" \ - " movl %3,%0\n" \ - "1: rep; movsb\n" \ - "2:\n" \ - ".section .fixup,\"ax\"\n" \ - "5: addl %3,%0\n" \ - " jmp 6f\n" \ - "3: lea 0(%3,%0,4),%0\n" \ - "6: pushl %0\n" \ - " pushl %%eax\n" \ - " xorl %%eax,%%eax\n" \ - " rep; stosb\n" \ - " popl %%eax\n" \ - " popl %0\n" \ - " jmp 2b\n" \ - ".previous\n" \ - _ASM_EXTABLE(4b,5b) \ - _ASM_EXTABLE(0b,3b) \ - _ASM_EXTABLE(1b,6b) \ - : "=&c"(size), "=&D" (__d0), "=&S" (__d1), "=r"(__d2) \ - : "3"(size), "0"(size), "1"(to), "2"(from) \ - : "memory"); \ -} while (0) - -unsigned long __copy_to_user_ll(void __user *to, const void *from, - unsigned long n) +unsigned long __copy_user_ll(void *to, const void *from, unsigned long n) { stac(); if (movsl_is_ok(to, from, n)) @@ -578,51 +338,7 @@ unsigned long __copy_to_user_ll(void __user *to, const void *from, clac(); return n; } -EXPORT_SYMBOL(__copy_to_user_ll); - -unsigned long __copy_from_user_ll(void *to, const void __user *from, - unsigned long n) -{ - stac(); - if (movsl_is_ok(to, from, n)) - __copy_user_zeroing(to, from, n); - else - n = __copy_user_zeroing_intel(to, from, n); - clac(); - return n; -} -EXPORT_SYMBOL(__copy_from_user_ll); - -unsigned long __copy_from_user_ll_nozero(void *to, const void __user *from, - unsigned long n) -{ - stac(); - if (movsl_is_ok(to, from, n)) - __copy_user(to, from, n); - else - n = __copy_user_intel((void __user *)to, - (const void *)from, n); - clac(); - return n; -} -EXPORT_SYMBOL(__copy_from_user_ll_nozero); - -unsigned long __copy_from_user_ll_nocache(void *to, const void __user *from, - unsigned long n) -{ - stac(); -#ifdef CONFIG_X86_INTEL_USERCOPY - if (n > 64 && static_cpu_has(X86_FEATURE_XMM2)) - n = __copy_user_zeroing_intel_nocache(to, from, n); - else - __copy_user_zeroing(to, from, n); -#else - __copy_user_zeroing(to, from, n); -#endif - clac(); - return n; -} -EXPORT_SYMBOL(__copy_from_user_ll_nocache); +EXPORT_SYMBOL(__copy_user_ll); unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *from, unsigned long n) diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c index 69873589c0ba..3b7c40a2e3e1 100644 --- a/arch/x86/lib/usercopy_64.c +++ b/arch/x86/lib/usercopy_64.c @@ -54,15 +54,6 @@ unsigned long clear_user(void __user *to, unsigned long n) } EXPORT_SYMBOL(clear_user); -unsigned long copy_in_user(void __user *to, const void __user *from, unsigned len) -{ - if (access_ok(VERIFY_WRITE, to, len) && access_ok(VERIFY_READ, from, len)) { - return copy_user_generic((__force void *)to, (__force void *)from, len); - } - return len; -} -EXPORT_SYMBOL(copy_in_user); - /* * Try to copy last bytes and clear the rest if needed. * Since protection fault in copy_from/to_user is not a normal situation, @@ -80,9 +71,5 @@ copy_user_handle_tail(char *to, char *from, unsigned len) break; } clac(); - - /* If the destination is a kernel buffer, we always clear the end */ - if (!__addr_ok(to)) - memset(to, 0, len); return len; } diff --git a/arch/x86/mm/amdtopology.c b/arch/x86/mm/amdtopology.c index d1c7de095808..91f501b2da3b 100644 --- a/arch/x86/mm/amdtopology.c +++ b/arch/x86/mm/amdtopology.c @@ -19,7 +19,7 @@ #include <asm/types.h> #include <asm/mmzone.h> #include <asm/proto.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/pci-direct.h> #include <asm/numa.h> #include <asm/mpspec.h> diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index 58b5bee7ea27..bce6990b1d81 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -110,7 +110,8 @@ static struct addr_marker address_markers[] = { #define PTE_LEVEL_MULT (PAGE_SIZE) #define PMD_LEVEL_MULT (PTRS_PER_PTE * PTE_LEVEL_MULT) #define PUD_LEVEL_MULT (PTRS_PER_PMD * PMD_LEVEL_MULT) -#define PGD_LEVEL_MULT (PTRS_PER_PUD * PUD_LEVEL_MULT) +#define P4D_LEVEL_MULT (PTRS_PER_PUD * PUD_LEVEL_MULT) +#define PGD_LEVEL_MULT (PTRS_PER_P4D * P4D_LEVEL_MULT) #define pt_dump_seq_printf(m, to_dmesg, fmt, args...) \ ({ \ @@ -286,14 +287,13 @@ static void note_page(struct seq_file *m, struct pg_state *st, } } -static void walk_pte_level(struct seq_file *m, struct pg_state *st, pmd_t addr, - unsigned long P) +static void walk_pte_level(struct seq_file *m, struct pg_state *st, pmd_t addr, unsigned long P) { int i; pte_t *start; pgprotval_t prot; - start = (pte_t *) pmd_page_vaddr(addr); + start = (pte_t *)pmd_page_vaddr(addr); for (i = 0; i < PTRS_PER_PTE; i++) { prot = pte_flags(*start); st->current_address = normalize_addr(P + i * PTE_LEVEL_MULT); @@ -304,14 +304,13 @@ static void walk_pte_level(struct seq_file *m, struct pg_state *st, pmd_t addr, #if PTRS_PER_PMD > 1 -static void walk_pmd_level(struct seq_file *m, struct pg_state *st, pud_t addr, - unsigned long P) +static void walk_pmd_level(struct seq_file *m, struct pg_state *st, pud_t addr, unsigned long P) { int i; pmd_t *start; pgprotval_t prot; - start = (pmd_t *) pud_page_vaddr(addr); + 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)) { @@ -347,15 +346,14 @@ 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, pgd_t addr, - unsigned long P) +static void walk_pud_level(struct seq_file *m, struct pg_state *st, p4d_t addr, unsigned long P) { int i; pud_t *start; pgprotval_t prot; pud_t *prev_pud = NULL; - start = (pud_t *) pgd_page_vaddr(addr); + 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); @@ -377,9 +375,42 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st, pgd_t addr, } #else -#define walk_pud_level(m,s,a,p) walk_pmd_level(m,s,__pud(pgd_val(a)),p) -#define pgd_large(a) pud_large(__pud(pgd_val(a))) -#define pgd_none(a) pud_none(__pud(pgd_val(a))) +#define walk_pud_level(m,s,a,p) walk_pmd_level(m,s,__pud(p4d_val(a)),p) +#define p4d_large(a) pud_large(__pud(p4d_val(a))) +#define p4d_none(a) pud_none(__pud(p4d_val(a))) +#endif + +#if PTRS_PER_P4D > 1 + +static void walk_p4d_level(struct seq_file *m, struct pg_state *st, pgd_t addr, unsigned long P) +{ + int i; + p4d_t *start; + pgprotval_t prot; + + 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); + if (!p4d_none(*start)) { + if (p4d_large(*start) || !p4d_present(*start)) { + prot = p4d_flags(*start); + note_page(m, st, __pgprot(prot), 2); + } else { + walk_pud_level(m, st, *start, + P + i * P4D_LEVEL_MULT); + } + } else + note_page(m, st, __pgprot(0), 2); + + start++; + } +} + +#else +#define walk_p4d_level(m,s,a,p) walk_pud_level(m,s,__p4d(pgd_val(a)),p) +#define pgd_large(a) p4d_large(__p4d(pgd_val(a))) +#define pgd_none(a) p4d_none(__p4d(pgd_val(a))) #endif static inline bool is_hypervisor_range(int idx) @@ -424,7 +455,7 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd, prot = pgd_flags(*start); note_page(m, &st, __pgprot(prot), 1); } else { - walk_pud_level(m, &st, *start, + walk_p4d_level(m, &st, *start, i * PGD_LEVEL_MULT); } } else diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 428e31763cb9..8ad91a01cbc8 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -253,6 +253,7 @@ static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address) { unsigned index = pgd_index(address); pgd_t *pgd_k; + p4d_t *p4d, *p4d_k; pud_t *pud, *pud_k; pmd_t *pmd, *pmd_k; @@ -265,10 +266,15 @@ static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address) /* * set_pgd(pgd, *pgd_k); here would be useless on PAE * and redundant with the set_pmd() on non-PAE. As would - * set_pud. + * set_p4d/set_pud. */ - pud = pud_offset(pgd, address); - pud_k = pud_offset(pgd_k, address); + p4d = p4d_offset(pgd, address); + p4d_k = p4d_offset(pgd_k, address); + if (!p4d_present(*p4d_k)) + return NULL; + + pud = pud_offset(p4d, address); + pud_k = pud_offset(p4d_k, address); if (!pud_present(*pud_k)) return NULL; @@ -384,6 +390,8 @@ static void dump_pagetable(unsigned long address) { pgd_t *base = __va(read_cr3()); pgd_t *pgd = &base[pgd_index(address)]; + p4d_t *p4d; + pud_t *pud; pmd_t *pmd; pte_t *pte; @@ -392,7 +400,9 @@ static void dump_pagetable(unsigned long address) if (!low_pfn(pgd_val(*pgd) >> PAGE_SHIFT) || !pgd_present(*pgd)) goto out; #endif - pmd = pmd_offset(pud_offset(pgd, address), address); + 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)); /* @@ -425,6 +435,7 @@ void vmalloc_sync_all(void) static noinline int vmalloc_fault(unsigned long address) { pgd_t *pgd, *pgd_ref; + p4d_t *p4d, *p4d_ref; pud_t *pud, *pud_ref; pmd_t *pmd, *pmd_ref; pte_t *pte, *pte_ref; @@ -448,17 +459,37 @@ static noinline int vmalloc_fault(unsigned long address) if (pgd_none(*pgd)) { set_pgd(pgd, *pgd_ref); arch_flush_lazy_mmu_mode(); - } else { + } else if (CONFIG_PGTABLE_LEVELS > 4) { + /* + * With folded p4d, pgd_none() is always false, so the pgd may + * point to an empty page table entry and pgd_page_vaddr() + * will return garbage. + * + * We will do the correct sanity check on the p4d level. + */ BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref)); } + /* With 4-level paging, copying happens on the p4d level. */ + p4d = p4d_offset(pgd, address); + p4d_ref = p4d_offset(pgd_ref, address); + if (p4d_none(*p4d_ref)) + return -1; + + if (p4d_none(*p4d)) { + set_p4d(p4d, *p4d_ref); + arch_flush_lazy_mmu_mode(); + } else { + BUG_ON(p4d_pfn(*p4d) != p4d_pfn(*p4d_ref)); + } + /* * Below here mismatches are bugs because these lower tables * are shared: */ - pud = pud_offset(pgd, address); - pud_ref = pud_offset(pgd_ref, address); + pud = pud_offset(p4d, address); + pud_ref = pud_offset(p4d_ref, address); if (pud_none(*pud_ref)) return -1; @@ -526,6 +557,7 @@ static void dump_pagetable(unsigned long address) { pgd_t *base = __va(read_cr3() & PHYSICAL_PAGE_MASK); pgd_t *pgd = base + pgd_index(address); + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; @@ -538,7 +570,15 @@ static void dump_pagetable(unsigned long address) if (!pgd_present(*pgd)) goto out; - pud = pud_offset(pgd, address); + p4d = p4d_offset(pgd, address); + if (bad_address(p4d)) + goto bad; + + printk("P4D %lx ", p4d_val(*p4d)); + if (!p4d_present(*p4d) || p4d_large(*p4d)) + goto out; + + pud = pud_offset(p4d, address); if (bad_address(pud)) goto bad; @@ -1082,6 +1122,7 @@ static noinline int spurious_fault(unsigned long error_code, unsigned long address) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; @@ -1104,7 +1145,14 @@ spurious_fault(unsigned long error_code, unsigned long address) if (!pgd_present(*pgd)) return 0; - pud = pud_offset(pgd, address); + p4d = p4d_offset(pgd, address); + if (!p4d_present(*p4d)) + return 0; + + if (p4d_large(*p4d)) + return spurious_fault_check(error_code, (pte_t *) p4d); + + pud = pud_offset(p4d, address); if (!pud_present(*pud)) return 0; diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c index 1f3b6ef105cd..456dfdfd2249 100644 --- a/arch/x86/mm/gup.c +++ b/arch/x86/mm/gup.c @@ -76,9 +76,9 @@ static void undo_dev_pagemap(int *nr, int nr_start, struct page **pages) } /* - * 'pteval' can come from a pte, pmd or pud. We only check + * 'pteval' can come from a pte, pmd, pud or p4d. We only check * _PAGE_PRESENT, _PAGE_USER, and _PAGE_RW in here which are the - * same value on all 3 types. + * same value on all 4 types. */ static inline int pte_allows_gup(unsigned long pteval, int write) { @@ -295,13 +295,13 @@ static noinline int gup_huge_pud(pud_t pud, unsigned long addr, return 1; } -static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end, +static int gup_pud_range(p4d_t p4d, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { unsigned long next; pud_t *pudp; - pudp = pud_offset(&pgd, addr); + pudp = pud_offset(&p4d, addr); do { pud_t pud = *pudp; @@ -320,6 +320,27 @@ static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end, return 1; } +static int gup_p4d_range(pgd_t pgd, unsigned long addr, unsigned long end, + int write, struct page **pages, int *nr) +{ + unsigned long next; + p4d_t *p4dp; + + p4dp = p4d_offset(&pgd, addr); + do { + p4d_t p4d = *p4dp; + + next = p4d_addr_end(addr, end); + if (p4d_none(p4d)) + return 0; + BUILD_BUG_ON(p4d_large(p4d)); + if (!gup_pud_range(p4d, addr, next, write, pages, nr)) + return 0; + } while (p4dp++, addr = next, addr != end); + + return 1; +} + /* * Like get_user_pages_fast() except its IRQ-safe in that it won't fall * back to the regular GUP. @@ -368,7 +389,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write, next = pgd_addr_end(addr, end); if (pgd_none(pgd)) break; - if (!gup_pud_range(pgd, addr, next, write, pages, &nr)) + if (!gup_p4d_range(pgd, addr, next, write, pages, &nr)) break; } while (pgdp++, addr = next, addr != end); local_irq_restore(flags); @@ -440,7 +461,7 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write, next = pgd_addr_end(addr, end); if (pgd_none(pgd)) goto slow; - if (!gup_pud_range(pgd, addr, next, write, pages, &nr)) + if (!gup_p4d_range(pgd, addr, next, write, pages, &nr)) goto slow; } while (pgdp++, addr = next, addr != end); local_irq_enable(); diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index c5066a260803..302f43fd9c28 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -12,10 +12,12 @@ #include <linux/pagemap.h> #include <linux/err.h> #include <linux/sysctl.h> +#include <linux/compat.h> #include <asm/mman.h> #include <asm/tlb.h> #include <asm/tlbflush.h> #include <asm/pgalloc.h> +#include <asm/elf.h> #if 0 /* This is just for testing */ struct page * @@ -82,8 +84,9 @@ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file, info.flags = 0; info.length = len; - info.low_limit = current->mm->mmap_legacy_base; - info.high_limit = TASK_SIZE; + info.low_limit = get_mmap_base(1); + info.high_limit = in_compat_syscall() ? + tasksize_32bit() : tasksize_64bit(); info.align_mask = PAGE_MASK & ~huge_page_mask(h); info.align_offset = 0; return vm_unmapped_area(&info); @@ -100,7 +103,7 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file, info.flags = VM_UNMAPPED_AREA_TOPDOWN; info.length = len; info.low_limit = PAGE_SIZE; - info.high_limit = current->mm->mmap_base; + info.high_limit = get_mmap_base(0); info.align_mask = PAGE_MASK & ~huge_page_mask(h); info.align_offset = 0; addr = vm_unmapped_area(&info); diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c index 4473cb4f8b90..04210a29dd60 100644 --- a/arch/x86/mm/ident_map.c +++ b/arch/x86/mm/ident_map.c @@ -45,6 +45,34 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page, return 0; } +static int ident_p4d_init(struct x86_mapping_info *info, p4d_t *p4d_page, + unsigned long addr, unsigned long end) +{ + unsigned long next; + + for (; addr < end; addr = next) { + p4d_t *p4d = p4d_page + p4d_index(addr); + pud_t *pud; + + next = (addr & P4D_MASK) + P4D_SIZE; + if (next > end) + next = end; + + if (p4d_present(*p4d)) { + pud = pud_offset(p4d, 0); + ident_pud_init(info, pud, addr, next); + continue; + } + pud = (pud_t *)info->alloc_pgt_page(info->context); + if (!pud) + return -ENOMEM; + ident_pud_init(info, pud, addr, next); + set_p4d(p4d, __p4d(__pa(pud) | _KERNPG_TABLE)); + } + + return 0; +} + int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page, unsigned long pstart, unsigned long pend) { @@ -55,27 +83,36 @@ int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page, for (; addr < end; addr = next) { pgd_t *pgd = pgd_page + pgd_index(addr); - pud_t *pud; + p4d_t *p4d; next = (addr & PGDIR_MASK) + PGDIR_SIZE; if (next > end) next = end; if (pgd_present(*pgd)) { - pud = pud_offset(pgd, 0); - result = ident_pud_init(info, pud, addr, next); + p4d = p4d_offset(pgd, 0); + result = ident_p4d_init(info, p4d, addr, next); if (result) return result; continue; } - pud = (pud_t *)info->alloc_pgt_page(info->context); - if (!pud) + p4d = (p4d_t *)info->alloc_pgt_page(info->context); + if (!p4d) return -ENOMEM; - result = ident_pud_init(info, pud, addr, next); + result = ident_p4d_init(info, p4d, addr, next); if (result) return result; - set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE)); + if (IS_ENABLED(CONFIG_X86_5LEVEL)) { + set_pgd(pgd, __pgd(__pa(p4d) | _KERNPG_TABLE)); + } 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)); + } } return 0; diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 22af912d66d2..138bad2fb6bc 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -6,7 +6,7 @@ #include <linux/bootmem.h> /* for max_low_pfn */ #include <asm/cacheflush.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/init.h> #include <asm/page.h> #include <asm/page_types.h> @@ -373,14 +373,14 @@ static int __meminit split_mem_range(struct map_range *mr, int nr_range, return nr_range; } -struct range pfn_mapped[E820_X_MAX]; +struct range pfn_mapped[E820_MAX_ENTRIES]; int nr_pfn_mapped; static void add_pfn_range_mapped(unsigned long start_pfn, unsigned long end_pfn) { - nr_pfn_mapped = add_range_with_merge(pfn_mapped, E820_X_MAX, + nr_pfn_mapped = add_range_with_merge(pfn_mapped, E820_MAX_ENTRIES, nr_pfn_mapped, start_pfn, end_pfn); - nr_pfn_mapped = clean_sort_range(pfn_mapped, E820_X_MAX); + nr_pfn_mapped = clean_sort_range(pfn_mapped, E820_MAX_ENTRIES); max_pfn_mapped = max(max_pfn_mapped, end_pfn); @@ -430,7 +430,7 @@ unsigned long __ref init_memory_mapping(unsigned long start, /* * We need to iterate through the E820 memory map and create direct mappings - * for only E820_RAM and E820_KERN_RESERVED regions. We cannot simply + * for only E820_TYPE_RAM and E820_KERN_RESERVED regions. We cannot simply * create direct mappings for all pfns from [0 to max_low_pfn) and * [4GB to max_pfn) because of possible memory holes in high addresses * that cannot be marked as UC by fixed/variable range MTRRs. @@ -643,21 +643,40 @@ void __init init_mem_mapping(void) * devmem_is_allowed() checks to see if /dev/mem access to a certain address * is valid. The argument is a physical page number. * - * - * On x86, access has to be given to the first megabyte of ram because that area - * contains BIOS code and data regions used by X and dosemu and similar apps. - * Access has to be given to non-kernel-ram areas as well, these contain the PCI - * mmio resources as well as potential bios/acpi data regions. + * On x86, access has to be given to the first megabyte of RAM because that + * area traditionally contains BIOS code and data regions used by X, dosemu, + * and similar apps. Since they map the entire memory range, the whole range + * must be allowed (for mapping), but any areas that would otherwise be + * disallowed are flagged as being "zero filled" instead of rejected. + * Access has to be given to non-kernel-ram areas as well, these contain the + * PCI mmio resources as well as potential bios/acpi data regions. */ int devmem_is_allowed(unsigned long pagenr) { - if (pagenr < 256) - return 1; - if (iomem_is_exclusive(pagenr << PAGE_SHIFT)) + if (page_is_ram(pagenr)) { + /* + * For disallowed memory regions in the low 1MB range, + * request that the page be shown as all zeros. + */ + if (pagenr < 256) + return 2; + return 0; - if (!page_is_ram(pagenr)) - return 1; - return 0; + } + + /* + * This must follow RAM test, since System RAM is considered a + * restricted resource under CONFIG_STRICT_IOMEM. + */ + if (iomem_is_exclusive(pagenr << PAGE_SHIFT)) { + /* Low 1MB bypasses iomem restrictions. */ + if (pagenr < 256) + return 1; + + return 0; + } + + return 1; } void free_init_pages(char *what, unsigned long begin, unsigned long end) @@ -701,7 +720,7 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end) void __ref free_initmem(void) { - e820_reallocate_tables(); + e820__reallocate_tables(); free_init_pages("unused kernel", (unsigned long)(&__init_begin), @@ -724,6 +743,53 @@ void __init free_initrd_mem(unsigned long start, unsigned long end) } #endif +/* + * Calculate the precise size of the DMA zone (first 16 MB of RAM), + * and pass it to the MM layer - to help it set zone watermarks more + * accurately. + * + * Done on 64-bit systems only for the time being, although 32-bit systems + * might benefit from this as well. + */ +void __init memblock_find_dma_reserve(void) +{ +#ifdef CONFIG_X86_64 + u64 nr_pages = 0, nr_free_pages = 0; + unsigned long start_pfn, end_pfn; + phys_addr_t start_addr, end_addr; + int i; + u64 u; + + /* + * Iterate over all memory ranges (free and reserved ones alike), + * to calculate the total number of pages in the first 16 MB of RAM: + */ + nr_pages = 0; + for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) { + start_pfn = min(start_pfn, MAX_DMA_PFN); + end_pfn = min(end_pfn, MAX_DMA_PFN); + + nr_pages += end_pfn - start_pfn; + } + + /* + * Iterate over free memory ranges to calculate the number of free + * pages in the DMA zone, while not counting potential partial + * pages at the beginning or the end of the range: + */ + nr_free_pages = 0; + for_each_free_mem_range(u, NUMA_NO_NODE, MEMBLOCK_NONE, &start_addr, &end_addr, NULL) { + start_pfn = min_t(unsigned long, PFN_UP(start_addr), MAX_DMA_PFN); + end_pfn = min_t(unsigned long, PFN_DOWN(end_addr), MAX_DMA_PFN); + + if (start_pfn < end_pfn) + nr_free_pages += end_pfn - start_pfn; + } + + set_dma_reserve(nr_pages - nr_free_pages); +#endif +} + void __init zone_sizes_init(void) { unsigned long max_zone_pfns[MAX_NR_ZONES]; diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 2b4b53e6793f..f34d275ee201 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -38,7 +38,7 @@ #include <asm/pgtable.h> #include <asm/dma.h> #include <asm/fixmap.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/apic.h> #include <asm/bugs.h> #include <asm/tlb.h> @@ -56,8 +56,6 @@ unsigned long highstart_pfn, highend_pfn; -static noinline int do_test_wp_bit(void); - bool __read_mostly __vmalloc_start_set = false; /* @@ -67,6 +65,7 @@ bool __read_mostly __vmalloc_start_set = false; */ static pmd_t * __init one_md_table_init(pgd_t *pgd) { + p4d_t *p4d; pud_t *pud; pmd_t *pmd_table; @@ -75,13 +74,15 @@ static pmd_t * __init one_md_table_init(pgd_t *pgd) pmd_table = (pmd_t *)alloc_low_page(); paravirt_alloc_pmd(&init_mm, __pa(pmd_table) >> PAGE_SHIFT); set_pgd(pgd, __pgd(__pa(pmd_table) | _PAGE_PRESENT)); - pud = pud_offset(pgd, 0); + p4d = p4d_offset(pgd, 0); + pud = pud_offset(p4d, 0); BUG_ON(pmd_table != pmd_offset(pud, 0)); return pmd_table; } #endif - pud = pud_offset(pgd, 0); + p4d = p4d_offset(pgd, 0); + pud = pud_offset(p4d, 0); pmd_table = pmd_offset(pud, 0); return pmd_table; @@ -390,8 +391,11 @@ pte_t *kmap_pte; static inline pte_t *kmap_get_fixmap_pte(unsigned long vaddr) { - return pte_offset_kernel(pmd_offset(pud_offset(pgd_offset_k(vaddr), - vaddr), vaddr), vaddr); + pgd_t *pgd = pgd_offset_k(vaddr); + p4d_t *p4d = p4d_offset(pgd, vaddr); + pud_t *pud = pud_offset(p4d, vaddr); + pmd_t *pmd = pmd_offset(pud, vaddr); + return pte_offset_kernel(pmd, vaddr); } static void __init kmap_init(void) @@ -410,6 +414,7 @@ static void __init permanent_kmaps_init(pgd_t *pgd_base) { unsigned long vaddr; pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; @@ -418,7 +423,8 @@ static void __init permanent_kmaps_init(pgd_t *pgd_base) page_table_range_init(vaddr, vaddr + PAGE_SIZE*LAST_PKMAP, pgd_base); pgd = swapper_pg_dir + pgd_index(vaddr); - pud = pud_offset(pgd, vaddr); + p4d = p4d_offset(pgd, vaddr); + pud = pud_offset(p4d, vaddr); pmd = pmd_offset(pud, vaddr); pte = pte_offset_kernel(pmd, vaddr); pkmap_page_table = pte; @@ -450,6 +456,7 @@ void __init native_pagetable_init(void) { unsigned long pfn, va; pgd_t *pgd, *base = swapper_pg_dir; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; @@ -469,7 +476,8 @@ void __init native_pagetable_init(void) if (!pgd_present(*pgd)) break; - pud = pud_offset(pgd, va); + p4d = p4d_offset(pgd, va); + pud = pud_offset(p4d, va); pmd = pmd_offset(pud, va); if (!pmd_present(*pmd)) break; @@ -716,20 +724,20 @@ void __init paging_init(void) */ static void __init test_wp_bit(void) { - printk(KERN_INFO - "Checking if this processor honours the WP bit even in supervisor mode..."); + char z = 0; + + printk(KERN_INFO "Checking if this processor honours the WP bit even in supervisor mode..."); - /* Any page-aligned address will do, the test is non-destructive */ - __set_fixmap(FIX_WP_TEST, __pa(&swapper_pg_dir), PAGE_KERNEL_RO); - boot_cpu_data.wp_works_ok = do_test_wp_bit(); - clear_fixmap(FIX_WP_TEST); + __set_fixmap(FIX_WP_TEST, __pa_symbol(empty_zero_page), PAGE_KERNEL_RO); - if (!boot_cpu_data.wp_works_ok) { - printk(KERN_CONT "No.\n"); - panic("Linux doesn't support CPUs with broken WP."); - } else { + if (probe_kernel_write((char *)fix_to_virt(FIX_WP_TEST), &z, 1)) { + clear_fixmap(FIX_WP_TEST); printk(KERN_CONT "Ok.\n"); + return; } + + printk(KERN_CONT "No.\n"); + panic("Linux doesn't support CPUs with broken WP."); } void __init mem_init(void) @@ -811,8 +819,7 @@ void __init mem_init(void) BUG_ON(VMALLOC_START >= VMALLOC_END); BUG_ON((unsigned long)high_memory > VMALLOC_START); - if (boot_cpu_data.wp_works_ok < 0) - test_wp_bit(); + test_wp_bit(); } #ifdef CONFIG_MEMORY_HOTPLUG @@ -840,30 +847,6 @@ int arch_remove_memory(u64 start, u64 size) #endif #endif -/* - * This function cannot be __init, since exceptions don't work in that - * section. Put this after the callers, so that it cannot be inlined. - */ -static noinline int do_test_wp_bit(void) -{ - char tmp_reg; - int flag; - - __asm__ __volatile__( - " movb %0, %1 \n" - "1: movb %1, %0 \n" - " xorl %2, %2 \n" - "2: \n" - _ASM_EXTABLE(1b,2b) - :"=m" (*(char *)fix_to_virt(FIX_WP_TEST)), - "=q" (tmp_reg), - "=r" (flag) - :"2" (1) - :"memory"); - - return flag; -} - int kernel_set_to_readonly __read_mostly; void set_kernel_text_rw(void) diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 15173d37f399..745e5e183169 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -41,7 +41,7 @@ #include <asm/pgalloc.h> #include <asm/dma.h> #include <asm/fixmap.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/apic.h> #include <asm/tlb.h> #include <asm/mmu_context.h> @@ -97,28 +97,38 @@ void sync_global_pgds(unsigned long start, unsigned long end) unsigned long address; for (address = start; address <= end; address += PGDIR_SIZE) { - const pgd_t *pgd_ref = pgd_offset_k(address); + pgd_t *pgd_ref = pgd_offset_k(address); + const p4d_t *p4d_ref; struct page *page; - if (pgd_none(*pgd_ref)) + /* + * With folded p4d, pgd_none() is always false, we need to + * handle synchonization on p4d level. + */ + BUILD_BUG_ON(pgd_none(*pgd_ref)); + p4d_ref = p4d_offset(pgd_ref, address); + + if (p4d_none(*p4d_ref)) continue; spin_lock(&pgd_lock); list_for_each_entry(page, &pgd_list, lru) { pgd_t *pgd; + p4d_t *p4d; spinlock_t *pgt_lock; pgd = (pgd_t *)page_address(page) + pgd_index(address); + p4d = p4d_offset(pgd, address); /* the pgt_lock only for Xen */ pgt_lock = &pgd_page_get_mm(page)->page_table_lock; spin_lock(pgt_lock); - if (!pgd_none(*pgd_ref) && !pgd_none(*pgd)) - BUG_ON(pgd_page_vaddr(*pgd) - != pgd_page_vaddr(*pgd_ref)); + if (!p4d_none(*p4d_ref) && !p4d_none(*p4d)) + BUG_ON(p4d_page_vaddr(*p4d) + != p4d_page_vaddr(*p4d_ref)); - if (pgd_none(*pgd)) - set_pgd(pgd, *pgd_ref); + if (p4d_none(*p4d)) + set_p4d(p4d, *p4d_ref); spin_unlock(pgt_lock); } @@ -149,16 +159,28 @@ static __ref void *spp_getpage(void) return ptr; } -static pud_t *fill_pud(pgd_t *pgd, unsigned long vaddr) +static p4d_t *fill_p4d(pgd_t *pgd, unsigned long vaddr) { if (pgd_none(*pgd)) { - pud_t *pud = (pud_t *)spp_getpage(); - pgd_populate(&init_mm, pgd, pud); - if (pud != pud_offset(pgd, 0)) + p4d_t *p4d = (p4d_t *)spp_getpage(); + pgd_populate(&init_mm, pgd, p4d); + if (p4d != p4d_offset(pgd, 0)) printk(KERN_ERR "PAGETABLE BUG #00! %p <-> %p\n", - pud, pud_offset(pgd, 0)); + p4d, p4d_offset(pgd, 0)); + } + return p4d_offset(pgd, vaddr); +} + +static pud_t *fill_pud(p4d_t *p4d, unsigned long vaddr) +{ + if (p4d_none(*p4d)) { + pud_t *pud = (pud_t *)spp_getpage(); + p4d_populate(&init_mm, p4d, pud); + if (pud != pud_offset(p4d, 0)) + printk(KERN_ERR "PAGETABLE BUG #01! %p <-> %p\n", + pud, pud_offset(p4d, 0)); } - return pud_offset(pgd, vaddr); + return pud_offset(p4d, vaddr); } static pmd_t *fill_pmd(pud_t *pud, unsigned long vaddr) @@ -167,7 +189,7 @@ static pmd_t *fill_pmd(pud_t *pud, unsigned long vaddr) pmd_t *pmd = (pmd_t *) spp_getpage(); pud_populate(&init_mm, pud, pmd); if (pmd != pmd_offset(pud, 0)) - printk(KERN_ERR "PAGETABLE BUG #01! %p <-> %p\n", + printk(KERN_ERR "PAGETABLE BUG #02! %p <-> %p\n", pmd, pmd_offset(pud, 0)); } return pmd_offset(pud, vaddr); @@ -179,20 +201,15 @@ static pte_t *fill_pte(pmd_t *pmd, unsigned long vaddr) pte_t *pte = (pte_t *) spp_getpage(); pmd_populate_kernel(&init_mm, pmd, pte); if (pte != pte_offset_kernel(pmd, 0)) - printk(KERN_ERR "PAGETABLE BUG #02!\n"); + printk(KERN_ERR "PAGETABLE BUG #03!\n"); } return pte_offset_kernel(pmd, vaddr); } -void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte) +static void __set_pte_vaddr(pud_t *pud, unsigned long vaddr, pte_t new_pte) { - pud_t *pud; - pmd_t *pmd; - pte_t *pte; - - pud = pud_page + pud_index(vaddr); - pmd = fill_pmd(pud, vaddr); - pte = fill_pte(pmd, vaddr); + pmd_t *pmd = fill_pmd(pud, vaddr); + pte_t *pte = fill_pte(pmd, vaddr); set_pte(pte, new_pte); @@ -203,10 +220,25 @@ void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte) __flush_tlb_one(vaddr); } +void set_pte_vaddr_p4d(p4d_t *p4d_page, unsigned long vaddr, pte_t new_pte) +{ + p4d_t *p4d = p4d_page + p4d_index(vaddr); + pud_t *pud = fill_pud(p4d, vaddr); + + __set_pte_vaddr(pud, vaddr, new_pte); +} + +void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte) +{ + pud_t *pud = pud_page + pud_index(vaddr); + + __set_pte_vaddr(pud, vaddr, new_pte); +} + void set_pte_vaddr(unsigned long vaddr, pte_t pteval) { pgd_t *pgd; - pud_t *pud_page; + p4d_t *p4d_page; pr_debug("set_pte_vaddr %lx to %lx\n", vaddr, native_pte_val(pteval)); @@ -216,17 +248,20 @@ void set_pte_vaddr(unsigned long vaddr, pte_t pteval) "PGD FIXMAP MISSING, it should be setup in head.S!\n"); return; } - pud_page = (pud_t*)pgd_page_vaddr(*pgd); - set_pte_vaddr_pud(pud_page, vaddr, pteval); + + p4d_page = p4d_offset(pgd, 0); + set_pte_vaddr_p4d(p4d_page, vaddr, pteval); } pmd_t * __init populate_extra_pmd(unsigned long vaddr) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pgd = pgd_offset_k(vaddr); - pud = fill_pud(pgd, vaddr); + p4d = fill_p4d(pgd, vaddr); + pud = fill_pud(p4d, vaddr); return fill_pmd(pud, vaddr); } @@ -245,6 +280,7 @@ static void __init __init_extra_mapping(unsigned long phys, unsigned long size, enum page_cache_mode cache) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pgprot_t prot; @@ -255,11 +291,17 @@ static void __init __init_extra_mapping(unsigned long phys, unsigned long size, for (; size; phys += PMD_SIZE, size -= PMD_SIZE) { pgd = pgd_offset_k((unsigned long)__va(phys)); if (pgd_none(*pgd)) { + p4d = (p4d_t *) spp_getpage(); + set_pgd(pgd, __pgd(__pa(p4d) | _KERNPG_TABLE | + _PAGE_USER)); + } + p4d = p4d_offset(pgd, (unsigned long)__va(phys)); + if (p4d_none(*p4d)) { pud = (pud_t *) spp_getpage(); - set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE | + set_p4d(p4d, __p4d(__pa(pud) | _KERNPG_TABLE | _PAGE_USER)); } - pud = pud_offset(pgd, (unsigned long)__va(phys)); + pud = pud_offset(p4d, (unsigned long)__va(phys)); if (pud_none(*pud)) { pmd = (pmd_t *) spp_getpage(); set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE | @@ -337,10 +379,10 @@ phys_pte_init(pte_t *pte_page, unsigned long paddr, unsigned long paddr_end, paddr_next = (paddr & PAGE_MASK) + PAGE_SIZE; if (paddr >= paddr_end) { if (!after_bootmem && - !e820_any_mapped(paddr & PAGE_MASK, paddr_next, - E820_RAM) && - !e820_any_mapped(paddr & PAGE_MASK, paddr_next, - E820_RESERVED_KERN)) + !e820__mapped_any(paddr & PAGE_MASK, paddr_next, + E820_TYPE_RAM) && + !e820__mapped_any(paddr & PAGE_MASK, paddr_next, + E820_TYPE_RESERVED_KERN)) set_pte(pte, __pte(0)); continue; } @@ -392,10 +434,10 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long paddr, unsigned long paddr_end, paddr_next = (paddr & PMD_MASK) + PMD_SIZE; if (paddr >= paddr_end) { if (!after_bootmem && - !e820_any_mapped(paddr & PMD_MASK, paddr_next, - E820_RAM) && - !e820_any_mapped(paddr & PMD_MASK, paddr_next, - E820_RESERVED_KERN)) + !e820__mapped_any(paddr & PMD_MASK, paddr_next, + E820_TYPE_RAM) && + !e820__mapped_any(paddr & PMD_MASK, paddr_next, + E820_TYPE_RESERVED_KERN)) set_pmd(pmd, __pmd(0)); continue; } @@ -478,10 +520,10 @@ phys_pud_init(pud_t *pud_page, unsigned long paddr, unsigned long paddr_end, if (paddr >= paddr_end) { if (!after_bootmem && - !e820_any_mapped(paddr & PUD_MASK, paddr_next, - E820_RAM) && - !e820_any_mapped(paddr & PUD_MASK, paddr_next, - E820_RESERVED_KERN)) + !e820__mapped_any(paddr & PUD_MASK, paddr_next, + E820_TYPE_RAM) && + !e820__mapped_any(paddr & PUD_MASK, paddr_next, + E820_TYPE_RESERVED_KERN)) set_pud(pud, __pud(0)); continue; } @@ -563,12 +605,15 @@ kernel_physical_mapping_init(unsigned long paddr_start, for (; vaddr < vaddr_end; vaddr = vaddr_next) { pgd_t *pgd = pgd_offset_k(vaddr); + p4d_t *p4d; pud_t *pud; vaddr_next = (vaddr & PGDIR_MASK) + PGDIR_SIZE; - if (pgd_val(*pgd)) { - pud = (pud_t *)pgd_page_vaddr(*pgd); + BUILD_BUG_ON(pgd_none(*pgd)); + p4d = p4d_offset(pgd, vaddr); + if (p4d_val(*p4d)) { + pud = (pud_t *)p4d_page_vaddr(*p4d); paddr_last = phys_pud_init(pud, __pa(vaddr), __pa(vaddr_end), page_size_mask); @@ -580,7 +625,7 @@ kernel_physical_mapping_init(unsigned long paddr_start, page_size_mask); spin_lock(&init_mm.page_table_lock); - pgd_populate(&init_mm, pgd, pud); + p4d_populate(&init_mm, p4d, pud); spin_unlock(&init_mm.page_table_lock); pgd_changed = true; } @@ -726,6 +771,24 @@ static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud) spin_unlock(&init_mm.page_table_lock); } +static void __meminit free_pud_table(pud_t *pud_start, p4d_t *p4d) +{ + pud_t *pud; + int i; + + for (i = 0; i < PTRS_PER_PUD; i++) { + pud = pud_start + i; + if (!pud_none(*pud)) + return; + } + + /* free a pud talbe */ + free_pagetable(p4d_page(*p4d), 0); + spin_lock(&init_mm.page_table_lock); + p4d_clear(p4d); + spin_unlock(&init_mm.page_table_lock); +} + static void __meminit remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end, bool direct) @@ -899,7 +962,7 @@ remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end, continue; } - pmd_base = (pmd_t *)pud_page_vaddr(*pud); + pmd_base = pmd_offset(pud, 0); remove_pmd_table(pmd_base, addr, next, direct); free_pmd_table(pmd_base, pud); } @@ -908,6 +971,32 @@ remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end, update_page_count(PG_LEVEL_1G, -pages); } +static void __meminit +remove_p4d_table(p4d_t *p4d_start, unsigned long addr, unsigned long end, + bool direct) +{ + unsigned long next, pages = 0; + pud_t *pud_base; + p4d_t *p4d; + + p4d = p4d_start + p4d_index(addr); + for (; addr < end; addr = next, p4d++) { + next = p4d_addr_end(addr, end); + + if (!p4d_present(*p4d)) + continue; + + BUILD_BUG_ON(p4d_large(*p4d)); + + pud_base = pud_offset(p4d, 0); + remove_pud_table(pud_base, addr, next, direct); + free_pud_table(pud_base, p4d); + } + + if (direct) + update_page_count(PG_LEVEL_512G, -pages); +} + /* start and end are both virtual address. */ static void __meminit remove_pagetable(unsigned long start, unsigned long end, bool direct) @@ -915,7 +1004,7 @@ remove_pagetable(unsigned long start, unsigned long end, bool direct) unsigned long next; unsigned long addr; pgd_t *pgd; - pud_t *pud; + p4d_t *p4d; for (addr = start; addr < end; addr = next) { next = pgd_addr_end(addr, end); @@ -924,8 +1013,8 @@ remove_pagetable(unsigned long start, unsigned long end, bool direct) if (!pgd_present(*pgd)) continue; - pud = (pud_t *)pgd_page_vaddr(*pgd); - remove_pud_table(pud, addr, next, direct); + p4d = p4d_offset(pgd, 0); + remove_p4d_table(p4d, addr, next, direct); } flush_tlb_all(); @@ -1090,6 +1179,7 @@ int kern_addr_valid(unsigned long addr) { unsigned long above = ((long)addr) >> __VIRTUAL_MASK_SHIFT; pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; @@ -1101,7 +1191,11 @@ int kern_addr_valid(unsigned long addr) if (pgd_none(*pgd)) return 0; - pud = pud_offset(pgd, addr); + p4d = p4d_offset(pgd, addr); + if (p4d_none(*p4d)) + return 0; + + pud = pud_offset(p4d, addr); if (pud_none(*pud)) return 0; @@ -1158,6 +1252,7 @@ static int __meminit vmemmap_populate_hugepages(unsigned long start, unsigned long addr; unsigned long next; pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; @@ -1168,7 +1263,11 @@ static int __meminit vmemmap_populate_hugepages(unsigned long start, if (!pgd) return -ENOMEM; - pud = vmemmap_pud_populate(pgd, addr, node); + p4d = vmemmap_p4d_populate(pgd, addr, node); + if (!p4d) + return -ENOMEM; + + pud = vmemmap_pud_populate(p4d, addr, node); if (!pud) return -ENOMEM; @@ -1236,6 +1335,7 @@ void register_page_bootmem_memmap(unsigned long section_nr, unsigned long end = (unsigned long)(start_page + size); unsigned long next; pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; unsigned int nr_pages; @@ -1251,7 +1351,14 @@ void register_page_bootmem_memmap(unsigned long section_nr, } get_page_bootmem(section_nr, pgd_page(*pgd), MIX_SECTION_INFO); - pud = pud_offset(pgd, addr); + p4d = p4d_offset(pgd, addr); + if (p4d_none(*p4d)) { + next = (addr + PAGE_SIZE) & PAGE_MASK; + continue; + } + get_page_bootmem(section_nr, p4d_page(*p4d), MIX_SECTION_INFO); + + pud = pud_offset(p4d, addr); if (pud_none(*pud)) { next = (addr + PAGE_SIZE) & PAGE_MASK; continue; diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 7aaa2635862d..e4f7b25df18e 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -9,12 +9,13 @@ #include <linux/bootmem.h> #include <linux/init.h> #include <linux/io.h> +#include <linux/ioport.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/mmiotrace.h> #include <asm/cacheflush.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/fixmap.h> #include <asm/pgtable.h> #include <asm/tlbflush.h> @@ -425,7 +426,8 @@ static inline pmd_t * __init early_ioremap_pmd(unsigned long addr) /* Don't assume we're using swapper_pg_dir at this point */ pgd_t *base = __va(read_cr3()); pgd_t *pgd = &base[pgd_index(addr)]; - pud_t *pud = pud_offset(pgd, addr); + p4d_t *p4d = p4d_offset(pgd, addr); + pud_t *pud = pud_offset(p4d, addr); pmd_t *pmd = pmd_offset(pud, addr); return pmd; diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index 4c90cfdc128b..0c7d8129bed6 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -8,11 +8,12 @@ #include <linux/sched/task.h> #include <linux/vmalloc.h> +#include <asm/e820/types.h> #include <asm/tlbflush.h> #include <asm/sections.h> extern pgd_t early_level4_pgt[PTRS_PER_PGD]; -extern struct range pfn_mapped[E820_X_MAX]; +extern struct range pfn_mapped[E820_MAX_ENTRIES]; static int __init map_range(struct range *range) { @@ -33,8 +34,19 @@ static int __init map_range(struct range *range) static void __init clear_pgds(unsigned long start, unsigned long end) { - for (; start < end; start += PGDIR_SIZE) - pgd_clear(pgd_offset_k(start)); + pgd_t *pgd; + + for (; start < end; start += PGDIR_SIZE) { + pgd = pgd_offset_k(start); + /* + * With folded p4d, pgd_clear() is nop, use p4d_clear() + * instead. + */ + if (CONFIG_PGTABLE_LEVELS < 5) + p4d_clear(p4d_offset(pgd, start)); + else + pgd_clear(pgd); + } } static void __init kasan_map_early_shadow(pgd_t *pgd) @@ -44,8 +56,18 @@ static void __init kasan_map_early_shadow(pgd_t *pgd) unsigned long end = KASAN_SHADOW_END; for (i = pgd_index(start); start < end; i++) { - pgd[i] = __pgd(__pa_nodebug(kasan_zero_pud) - | _KERNPG_TABLE); + switch (CONFIG_PGTABLE_LEVELS) { + case 4: + pgd[i] = __pgd(__pa_nodebug(kasan_zero_pud) | + _KERNPG_TABLE); + break; + case 5: + pgd[i] = __pgd(__pa_nodebug(kasan_zero_p4d) | + _KERNPG_TABLE); + break; + default: + BUILD_BUG(); + } start += PGDIR_SIZE; } } @@ -73,6 +95,7 @@ void __init kasan_early_init(void) pteval_t pte_val = __pa_nodebug(kasan_zero_page) | __PAGE_KERNEL; 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; for (i = 0; i < PTRS_PER_PTE; i++) kasan_zero_pte[i] = __pte(pte_val); @@ -83,6 +106,9 @@ void __init kasan_early_init(void) for (i = 0; i < PTRS_PER_PUD; i++) kasan_zero_pud[i] = __pud(pud_val); + for (i = 0; CONFIG_PGTABLE_LEVELS >= 5 && i < PTRS_PER_P4D; i++) + kasan_zero_p4d[i] = __p4d(p4d_val); + kasan_map_early_shadow(early_level4_pgt); kasan_map_early_shadow(init_level4_pgt); } @@ -104,7 +130,7 @@ void __init kasan_init(void) kasan_populate_zero_shadow((void *)KASAN_SHADOW_START, kasan_mem_to_shadow((void *)PAGE_OFFSET)); - for (i = 0; i < E820_X_MAX; i++) { + for (i = 0; i < E820_MAX_ENTRIES; i++) { if (pfn_mapped[i].end == 0) break; diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index 7940166c799b..19ad095b41df 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -30,30 +30,44 @@ #include <linux/limits.h> #include <linux/sched/signal.h> #include <linux/sched/mm.h> +#include <linux/compat.h> #include <asm/elf.h> struct va_alignment __read_mostly va_align = { .flags = -1, }; -static unsigned long stack_maxrandom_size(void) +unsigned long tasksize_32bit(void) +{ + return IA32_PAGE_OFFSET; +} + +unsigned long tasksize_64bit(void) +{ + return TASK_SIZE_MAX; +} + +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) << PAGE_SHIFT; + max = (-1UL) & __STACK_RND_MASK(task_size == tasksize_32bit()); + max <<= PAGE_SHIFT; } return max; } -/* - * Top of mmap area (just below the process stack). - * - * Leave an at least ~128 MB hole with possible stack randomization. - */ -#define MIN_GAP (128*1024*1024UL + stack_maxrandom_size()) -#define MAX_GAP (TASK_SIZE/6*5) +#ifdef CONFIG_COMPAT +# define mmap32_rnd_bits mmap_rnd_compat_bits +# define mmap64_rnd_bits mmap_rnd_bits +#else +# define mmap32_rnd_bits mmap_rnd_bits +# define mmap64_rnd_bits mmap_rnd_bits +#endif + +#define SIZE_128M (128 * 1024 * 1024UL) static int mmap_is_legacy(void) { @@ -66,54 +80,91 @@ static int mmap_is_legacy(void) return sysctl_legacy_va_layout; } -unsigned long arch_mmap_rnd(void) +static unsigned long arch_rnd(unsigned int rndbits) { - unsigned long rnd; - - if (mmap_is_ia32()) -#ifdef CONFIG_COMPAT - rnd = get_random_long() & ((1UL << mmap_rnd_compat_bits) - 1); -#else - rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1); -#endif - else - rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1); + return (get_random_long() & ((1UL << rndbits) - 1)) << PAGE_SHIFT; +} - return rnd << 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); } -static unsigned long mmap_base(unsigned long rnd) +static unsigned long mmap_base(unsigned long rnd, unsigned long task_size) { unsigned long gap = rlimit(RLIMIT_STACK); + unsigned long gap_min, gap_max; + + /* + * Top of mmap area (just below the process stack). + * Leave an at least ~128 MB hole with possible stack randomization. + */ + gap_min = SIZE_128M + stack_maxrandom_size(task_size); + gap_max = (task_size / 6) * 5; - if (gap < MIN_GAP) - gap = MIN_GAP; - else if (gap > MAX_GAP) - gap = MAX_GAP; + if (gap < gap_min) + gap = gap_min; + else if (gap > gap_max) + gap = gap_max; + + return PAGE_ALIGN(task_size - gap - rnd); +} - return PAGE_ALIGN(TASK_SIZE - gap - rnd); +static unsigned long mmap_legacy_base(unsigned long rnd, + unsigned long task_size) +{ + return __TASK_UNMAPPED_BASE(task_size) + rnd; } /* * This function, called very early during the creation of a new * process VM image, sets up which VM layout function to use: */ +static void arch_pick_mmap_base(unsigned long *base, unsigned long *legacy_base, + unsigned long random_factor, unsigned long task_size) +{ + *legacy_base = mmap_legacy_base(random_factor, task_size); + if (mmap_is_legacy()) + *base = *legacy_base; + else + *base = mmap_base(random_factor, task_size); +} + void arch_pick_mmap_layout(struct mm_struct *mm) { - unsigned long random_factor = 0UL; + if (mmap_is_legacy()) + mm->get_unmapped_area = arch_get_unmapped_area; + else + mm->get_unmapped_area = arch_get_unmapped_area_topdown; - if (current->flags & PF_RANDOMIZE) - random_factor = arch_mmap_rnd(); + arch_pick_mmap_base(&mm->mmap_base, &mm->mmap_legacy_base, + arch_rnd(mmap64_rnd_bits), tasksize_64bit()); + +#ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES + /* + * The mmap syscall mapping base decision depends solely on the + * syscall type (64-bit or compat). This applies for 64bit + * applications and 32bit applications. The 64bit syscall uses + * 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()); +#endif +} - mm->mmap_legacy_base = TASK_UNMAPPED_BASE + random_factor; +unsigned long get_mmap_base(int is_legacy) +{ + struct mm_struct *mm = current->mm; - if (mmap_is_legacy()) { - mm->mmap_base = mm->mmap_legacy_base; - mm->get_unmapped_area = arch_get_unmapped_area; - } else { - mm->mmap_base = mmap_base(random_factor); - mm->get_unmapped_area = arch_get_unmapped_area_topdown; +#ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES + if (in_compat_syscall()) { + return is_legacy ? mm->mmap_compat_legacy_base + : mm->mmap_compat_base; } +#endif + return is_legacy ? mm->mmap_legacy_base : mm->mmap_base; } const char *arch_vma_name(struct vm_area_struct *vma) diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c index bef36622e408..4d434ddb75db 100644 --- a/arch/x86/mm/mmio-mod.c +++ b/arch/x86/mm/mmio-mod.c @@ -32,7 +32,7 @@ #include <linux/kallsyms.h> #include <asm/pgtable.h> #include <linux/mmiotrace.h> -#include <asm/e820.h> /* for ISA_START_ADDRESS */ +#include <asm/e820/api.h> /* for ISA_START_ADDRESS */ #include <linux/atomic.h> #include <linux/percpu.h> #include <linux/cpu.h> diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c index cd44ae727df7..1c34b767c84c 100644 --- a/arch/x86/mm/mpx.c +++ b/arch/x86/mm/mpx.c @@ -526,15 +526,7 @@ int mpx_handle_bd_fault(void) if (!kernel_managing_mpx_tables(current->mm)) return -EINVAL; - if (do_mpx_bt_fault()) { - force_sig(SIGSEGV, current); - /* - * The force_sig() is essentially "handling" this - * exception, so we do not pass up the error - * from do_mpx_bt_fault(). - */ - } - return 0; + return do_mpx_bt_fault(); } /* diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 12dcad7297a5..25504d5aa816 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -12,7 +12,7 @@ #include <linux/sched.h> #include <linux/topology.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/proto.h> #include <asm/dma.h> #include <asm/amd_nb.h> @@ -201,7 +201,7 @@ static void __init alloc_node_data(int nid) nd_pa = __memblock_alloc_base(nd_size, SMP_CACHE_BYTES, MEMBLOCK_ALLOC_ACCESSIBLE); if (!nd_pa) { - pr_err("Cannot find %zu bytes in node %d\n", + pr_err("Cannot find %zu bytes in any node (initial node: %d)\n", nd_size, nid); return; } @@ -225,7 +225,7 @@ static void __init alloc_node_data(int nid) * numa_cleanup_meminfo - Cleanup a numa_meminfo * @mi: numa_meminfo to clean up * - * Sanitize @mi by merging and removing unncessary memblks. Also check for + * Sanitize @mi by merging and removing unnecessary memblks. Also check for * conflicts and clear unused memblks. * * RETURNS: diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 28d42130243c..56b22fa504df 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -15,7 +15,7 @@ #include <linux/pci.h> #include <linux/vmalloc.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/processor.h> #include <asm/tlbflush.h> #include <asm/sections.h> @@ -346,6 +346,7 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address, pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address, unsigned int *level) { + p4d_t *p4d; pud_t *pud; pmd_t *pmd; @@ -354,7 +355,15 @@ pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address, if (pgd_none(*pgd)) return NULL; - pud = pud_offset(pgd, address); + p4d = p4d_offset(pgd, address); + if (p4d_none(*p4d)) + return NULL; + + *level = PG_LEVEL_512G; + if (p4d_large(*p4d) || !p4d_present(*p4d)) + return (pte_t *)p4d; + + pud = pud_offset(p4d, address); if (pud_none(*pud)) return NULL; @@ -406,13 +415,18 @@ static pte_t *_lookup_address_cpa(struct cpa_data *cpa, unsigned long address, pmd_t *lookup_pmd_address(unsigned long address) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pgd = pgd_offset_k(address); if (pgd_none(*pgd)) return NULL; - pud = pud_offset(pgd, address); + p4d = p4d_offset(pgd, address); + if (p4d_none(*p4d) || p4d_large(*p4d) || !p4d_present(*p4d)) + return NULL; + + pud = pud_offset(p4d, address); if (pud_none(*pud) || pud_large(*pud) || !pud_present(*pud)) return NULL; @@ -477,11 +491,13 @@ static void __set_pmd_pte(pte_t *kpte, unsigned long address, pte_t pte) list_for_each_entry(page, &pgd_list, lru) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pgd = (pgd_t *)page_address(page) + pgd_index(address); - pud = pud_offset(pgd, address); + p4d = p4d_offset(pgd, address); + pud = pud_offset(p4d, address); pmd = pmd_offset(pud, address); set_pte_atomic((pte_t *)pmd, pte); } @@ -836,9 +852,9 @@ static void unmap_pmd_range(pud_t *pud, unsigned long start, unsigned long end) pud_clear(pud); } -static void unmap_pud_range(pgd_t *pgd, unsigned long start, unsigned long end) +static void unmap_pud_range(p4d_t *p4d, unsigned long start, unsigned long end) { - pud_t *pud = pud_offset(pgd, start); + pud_t *pud = pud_offset(p4d, start); /* * Not on a GB page boundary? @@ -1004,8 +1020,8 @@ static long populate_pmd(struct cpa_data *cpa, return num_pages; } -static long populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd, - pgprot_t pgprot) +static int populate_pud(struct cpa_data *cpa, unsigned long start, p4d_t *p4d, + pgprot_t pgprot) { pud_t *pud; unsigned long end; @@ -1026,7 +1042,7 @@ static long populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd, cur_pages = (pre_end - start) >> PAGE_SHIFT; cur_pages = min_t(int, (int)cpa->numpages, cur_pages); - pud = pud_offset(pgd, start); + pud = pud_offset(p4d, start); /* * Need a PMD page? @@ -1047,7 +1063,7 @@ static long populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd, if (cpa->numpages == cur_pages) return cur_pages; - pud = pud_offset(pgd, start); + pud = pud_offset(p4d, start); pud_pgprot = pgprot_4k_2_large(pgprot); /* @@ -1067,7 +1083,7 @@ static long populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd, if (start < end) { long tmp; - pud = pud_offset(pgd, start); + pud = pud_offset(p4d, start); if (pud_none(*pud)) if (alloc_pmd_page(pud)) return -1; @@ -1090,33 +1106,43 @@ static int populate_pgd(struct cpa_data *cpa, unsigned long addr) { pgprot_t pgprot = __pgprot(_KERNPG_TABLE); pud_t *pud = NULL; /* shut up gcc */ + p4d_t *p4d; pgd_t *pgd_entry; long ret; pgd_entry = cpa->pgd + pgd_index(addr); + if (pgd_none(*pgd_entry)) { + p4d = (p4d_t *)get_zeroed_page(GFP_KERNEL | __GFP_NOTRACK); + if (!p4d) + return -1; + + set_pgd(pgd_entry, __pgd(__pa(p4d) | _KERNPG_TABLE)); + } + /* * Allocate a PUD page and hand it down for mapping. */ - if (pgd_none(*pgd_entry)) { + p4d = p4d_offset(pgd_entry, addr); + if (p4d_none(*p4d)) { pud = (pud_t *)get_zeroed_page(GFP_KERNEL | __GFP_NOTRACK); if (!pud) return -1; - set_pgd(pgd_entry, __pgd(__pa(pud) | _KERNPG_TABLE)); + set_p4d(p4d, __p4d(__pa(pud) | _KERNPG_TABLE)); } pgprot_val(pgprot) &= ~pgprot_val(cpa->mask_clr); pgprot_val(pgprot) |= pgprot_val(cpa->mask_set); - ret = populate_pud(cpa, addr, pgd_entry, pgprot); + ret = populate_pud(cpa, addr, p4d, pgprot); if (ret < 0) { /* * Leave the PUD page in place in case some other CPU or thread * already found it, but remove any useless entries we just * added to it. */ - unmap_pud_range(pgd_entry, addr, + unmap_pud_range(p4d, addr, addr + (cpa->numpages << PAGE_SHIFT)); return ret; } diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index efc32bc6862b..9b78685b66e6 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -10,6 +10,7 @@ #include <linux/seq_file.h> #include <linux/bootmem.h> #include <linux/debugfs.h> +#include <linux/ioport.h> #include <linux/kernel.h> #include <linux/pfn_t.h> #include <linux/slab.h> @@ -23,7 +24,7 @@ #include <asm/x86_init.h> #include <asm/pgtable.h> #include <asm/fcntl.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/mtrr.h> #include <asm/page.h> #include <asm/msr.h> diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 6cbdff26bb96..508a708eb9a6 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -81,6 +81,14 @@ 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)); } + +#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)); +} +#endif /* CONFIG_PGTABLE_LEVELS > 4 */ #endif /* CONFIG_PGTABLE_LEVELS > 3 */ #endif /* CONFIG_PGTABLE_LEVELS > 2 */ @@ -120,7 +128,7 @@ static void pgd_ctor(struct mm_struct *mm, pgd_t *pgd) references from swapper_pg_dir. */ if (CONFIG_PGTABLE_LEVELS == 2 || (CONFIG_PGTABLE_LEVELS == 3 && SHARED_KERNEL_PMD) || - CONFIG_PGTABLE_LEVELS == 4) { + CONFIG_PGTABLE_LEVELS >= 4) { clone_pgd_range(pgd + KERNEL_PGD_BOUNDARY, swapper_pg_dir + KERNEL_PGD_BOUNDARY, KERNEL_PGD_PTRS); @@ -261,13 +269,15 @@ static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp) static void pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmds[]) { + p4d_t *p4d; pud_t *pud; int i; if (PREALLOCATED_PMDS == 0) /* Work around gcc-3.4.x bug */ return; - pud = pud_offset(pgd, 0); + p4d = p4d_offset(pgd, 0); + pud = pud_offset(p4d, 0); for (i = 0; i < PREALLOCATED_PMDS; i++, pud++) { pmd_t *pmd = pmds[i]; @@ -580,6 +590,28 @@ void native_set_fixmap(enum fixed_addresses idx, phys_addr_t phys, } #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP +#ifdef CONFIG_X86_5LEVEL +/** + * p4d_set_huge - setup kernel P4D mapping + * + * No 512GB pages yet -- always return 0 + */ +int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot) +{ + return 0; +} + +/** + * p4d_clear_huge - clear kernel P4D mapping when it is set + * + * No 512GB pages yet -- always return 0 + */ +int p4d_clear_huge(p4d_t *p4d) +{ + return 0; +} +#endif + /** * pud_set_huge - setup kernel PUD mapping * diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c index 9adce776852b..b9bd5b8b14fa 100644 --- a/arch/x86/mm/pgtable_32.c +++ b/arch/x86/mm/pgtable_32.c @@ -12,7 +12,7 @@ #include <asm/pgtable.h> #include <asm/pgalloc.h> #include <asm/fixmap.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/tlb.h> #include <asm/tlbflush.h> #include <asm/io.h> @@ -26,6 +26,7 @@ unsigned int __VMALLOC_RESERVE = 128 << 20; void set_pte_vaddr(unsigned long vaddr, pte_t pteval) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; @@ -35,7 +36,12 @@ void set_pte_vaddr(unsigned long vaddr, pte_t pteval) BUG(); return; } - pud = pud_offset(pgd, vaddr); + p4d = p4d_offset(pgd, vaddr); + if (p4d_none(*p4d)) { + BUG(); + return; + } + pud = pud_offset(p4d, vaddr); if (pud_none(*pud)) { BUG(); return; diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c index 35fe69529bc1..3ea20d61b523 100644 --- a/arch/x86/mm/srat.c +++ b/arch/x86/mm/srat.c @@ -18,7 +18,7 @@ #include <linux/mm.h> #include <asm/proto.h> #include <asm/numa.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/apic.h> #include <asm/uv/uv.h> diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index a7655f6caf7d..6e7bedf69af7 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -263,8 +263,6 @@ void native_flush_tlb_others(const struct cpumask *cpumask, { struct flush_tlb_info info; - if (end == 0) - end = start + PAGE_SIZE; info.flush_mm = mm; info.flush_start = start; info.flush_end = end; @@ -289,23 +287,6 @@ void native_flush_tlb_others(const struct cpumask *cpumask, smp_call_function_many(cpumask, flush_tlb_func, &info, 1); } -void flush_tlb_current_task(void) -{ - struct mm_struct *mm = current->mm; - - preempt_disable(); - - count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); - - /* This is an implicit full barrier that synchronizes with switch_mm. */ - local_flush_tlb(); - - trace_tlb_flush(TLB_LOCAL_SHOOTDOWN, TLB_FLUSH_ALL); - if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids) - flush_tlb_others(mm_cpumask(mm), mm, 0UL, TLB_FLUSH_ALL); - preempt_enable(); -} - /* * See Documentation/x86/tlb.txt for details. We choose 33 * because it is large enough to cover the vast majority (at @@ -326,6 +307,12 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, unsigned long base_pages_to_flush = TLB_FLUSH_ALL; preempt_disable(); + + if ((end != TLB_FLUSH_ALL) && !(vmflag & VM_HUGETLB)) + base_pages_to_flush = (end - start) >> PAGE_SHIFT; + if (base_pages_to_flush > tlb_single_page_flush_ceiling) + base_pages_to_flush = TLB_FLUSH_ALL; + if (current->active_mm != mm) { /* Synchronize with switch_mm. */ smp_mb(); @@ -342,15 +329,11 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, goto out; } - if ((end != TLB_FLUSH_ALL) && !(vmflag & VM_HUGETLB)) - base_pages_to_flush = (end - start) >> PAGE_SHIFT; - /* * Both branches below are implicit full barriers (MOV to CR or * INVLPG) that synchronize with switch_mm. */ - if (base_pages_to_flush > tlb_single_page_flush_ceiling) { - base_pages_to_flush = TLB_FLUSH_ALL; + if (base_pages_to_flush == TLB_FLUSH_ALL) { count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); local_flush_tlb(); } else { @@ -393,7 +376,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long start) } if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids) - flush_tlb_others(mm_cpumask(mm), mm, start, 0UL); + flush_tlb_others(mm_cpumask(mm), mm, start, start + PAGE_SIZE); preempt_enable(); } diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c index 0a9f2caf358f..6fa84d531f4f 100644 --- a/arch/x86/pci/i386.c +++ b/arch/x86/pci/i386.c @@ -34,7 +34,7 @@ #include <linux/bootmem.h> #include <asm/pat.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/pci_x86.h> #include <asm/io_apic.h> @@ -398,7 +398,7 @@ void __init pcibios_resource_survey(void) list_for_each_entry(bus, &pci_root_buses, node) pcibios_allocate_resources(bus, 1); - e820_reserve_resources_late(); + e820__reserve_resources_late(); /* * Insert the IO APIC resources after PCI initialization has * occurred to handle IO APICS that are mapped in on a BAR in diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c index dd30b7e08bc2..d1b47d5bc9c3 100644 --- a/arch/x86/pci/mmconfig-shared.c +++ b/arch/x86/pci/mmconfig-shared.c @@ -18,7 +18,7 @@ #include <linux/slab.h> #include <linux/mutex.h> #include <linux/rculist.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/pci_x86.h> #include <asm/acpi.h> @@ -423,7 +423,7 @@ static acpi_status find_mboard_resource(acpi_handle handle, u32 lvl, return AE_OK; } -static int is_acpi_reserved(u64 start, u64 end, unsigned not_used) +static bool is_acpi_reserved(u64 start, u64 end, unsigned not_used) { struct resource mcfg_res; @@ -440,11 +440,11 @@ static int is_acpi_reserved(u64 start, u64 end, unsigned not_used) return mcfg_res.flags; } -typedef int (*check_reserved_t)(u64 start, u64 end, unsigned type); +typedef bool (*check_reserved_t)(u64 start, u64 end, unsigned type); -static int __ref is_mmconf_reserved(check_reserved_t is_reserved, - struct pci_mmcfg_region *cfg, - struct device *dev, int with_e820) +static bool __ref is_mmconf_reserved(check_reserved_t is_reserved, + struct pci_mmcfg_region *cfg, + struct device *dev, int with_e820) { u64 addr = cfg->res.start; u64 size = resource_size(&cfg->res); @@ -452,7 +452,7 @@ static int __ref is_mmconf_reserved(check_reserved_t is_reserved, int num_buses; char *method = with_e820 ? "E820" : "ACPI motherboard resources"; - while (!is_reserved(addr, addr + size, E820_RESERVED)) { + while (!is_reserved(addr, addr + size, E820_TYPE_RESERVED)) { size >>= 1; if (size < (16UL<<20)) break; @@ -494,8 +494,8 @@ static int __ref is_mmconf_reserved(check_reserved_t is_reserved, return 1; } -static int __ref pci_mmcfg_check_reserved(struct device *dev, - struct pci_mmcfg_region *cfg, int early) +static bool __ref +pci_mmcfg_check_reserved(struct device *dev, struct pci_mmcfg_region *cfg, int early) { if (!early && !acpi_disabled) { if (is_mmconf_reserved(is_acpi_reserved, cfg, dev, 0)) @@ -514,7 +514,7 @@ static int __ref pci_mmcfg_check_reserved(struct device *dev, } /* - * e820_all_mapped() is marked as __init. + * e820__mapped_all() is marked as __init. * All entries from ACPI MCFG table have been checked at boot time. * For MCFG information constructed from hotpluggable host bridge's * _CBA method, just assume it's reserved. @@ -525,7 +525,7 @@ static int __ref pci_mmcfg_check_reserved(struct device *dev, /* Don't try to do this check unless configuration type 1 is available. how about type 2 ?*/ if (raw_pci_ops) - return is_mmconf_reserved(e820_all_mapped, cfg, dev, 1); + return is_mmconf_reserved(e820__mapped_all, cfg, dev, 1); return 0; } diff --git a/arch/x86/pci/mmconfig_32.c b/arch/x86/pci/mmconfig_32.c index 43984bc1665a..3e9e166f6408 100644 --- a/arch/x86/pci/mmconfig_32.c +++ b/arch/x86/pci/mmconfig_32.c @@ -12,7 +12,7 @@ #include <linux/pci.h> #include <linux/init.h> #include <linux/rcupdate.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/pci_x86.h> /* Assume systems with more busses have correct MCFG */ diff --git a/arch/x86/pci/mmconfig_64.c b/arch/x86/pci/mmconfig_64.c index bea52496aea6..f1c1aa0430ae 100644 --- a/arch/x86/pci/mmconfig_64.c +++ b/arch/x86/pci/mmconfig_64.c @@ -10,7 +10,7 @@ #include <linux/acpi.h> #include <linux/bitmap.h> #include <linux/rcupdate.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/pci_x86.h> #define PREFIX "PCI: " diff --git a/arch/x86/pci/pcbios.c b/arch/x86/pci/pcbios.c index 1d97cea3b3a4..29e9ba6ace9d 100644 --- a/arch/x86/pci/pcbios.c +++ b/arch/x86/pci/pcbios.c @@ -7,7 +7,9 @@ #include <linux/slab.h> #include <linux/module.h> #include <linux/uaccess.h> + #include <asm/pci_x86.h> +#include <asm/e820/types.h> #include <asm/pci-functions.h> #include <asm/cacheflush.h> diff --git a/arch/x86/platform/efi/Makefile b/arch/x86/platform/efi/Makefile index 066619b0700c..f1d83b34c329 100644 --- a/arch/x86/platform/efi/Makefile +++ b/arch/x86/platform/efi/Makefile @@ -1,6 +1,5 @@ OBJECT_FILES_NON_STANDARD_efi_thunk_$(BITS).o := y obj-$(CONFIG_EFI) += quirks.o efi.o efi_$(BITS).o efi_stub_$(BITS).o -obj-$(CONFIG_ACPI_BGRT) += efi-bgrt.o obj-$(CONFIG_EARLY_PRINTK_EFI) += early_printk.o obj-$(CONFIG_EFI_MIXED) += efi_thunk_$(BITS).o diff --git a/arch/x86/platform/efi/efi-bgrt.c b/arch/x86/platform/efi/efi-bgrt.c deleted file mode 100644 index 04ca8764f0c0..000000000000 --- a/arch/x86/platform/efi/efi-bgrt.c +++ /dev/null @@ -1,84 +0,0 @@ -/* - * Copyright 2012 Intel Corporation - * Author: Josh Triplett <josh@joshtriplett.org> - * - * Based on the bgrt driver: - * Copyright 2012 Red Hat, Inc <mjg@redhat.com> - * Author: Matthew Garrett - * - * 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. - */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/acpi.h> -#include <linux/efi.h> -#include <linux/efi-bgrt.h> - -struct acpi_table_bgrt bgrt_tab; -size_t __initdata bgrt_image_size; - -struct bmp_header { - u16 id; - u32 size; -} __packed; - -void __init efi_bgrt_init(struct acpi_table_header *table) -{ - void *image; - struct bmp_header bmp_header; - struct acpi_table_bgrt *bgrt = &bgrt_tab; - - if (acpi_disabled) - return; - - if (table->length < sizeof(bgrt_tab)) { - pr_notice("Ignoring BGRT: invalid length %u (expected %zu)\n", - table->length, sizeof(bgrt_tab)); - return; - } - *bgrt = *(struct acpi_table_bgrt *)table; - if (bgrt->version != 1) { - pr_notice("Ignoring BGRT: invalid version %u (expected 1)\n", - bgrt->version); - goto out; - } - if (bgrt->status & 0xfe) { - pr_notice("Ignoring BGRT: reserved status bits are non-zero %u\n", - bgrt->status); - goto out; - } - if (bgrt->image_type != 0) { - pr_notice("Ignoring BGRT: invalid image type %u (expected 0)\n", - bgrt->image_type); - goto out; - } - if (!bgrt->image_address) { - pr_notice("Ignoring BGRT: null image address\n"); - goto out; - } - - image = early_memremap(bgrt->image_address, sizeof(bmp_header)); - if (!image) { - pr_notice("Ignoring BGRT: failed to map image header memory\n"); - goto out; - } - - memcpy(&bmp_header, image, sizeof(bmp_header)); - early_memunmap(image, sizeof(bmp_header)); - if (bmp_header.id != 0x4d42) { - pr_notice("Ignoring BGRT: Incorrect BMP magic number 0x%x (expected 0x4d42)\n", - bmp_header.id); - goto out; - } - bgrt_image_size = bmp_header.size; - efi_mem_reserve(bgrt->image_address, bgrt_image_size); - - return; -out: - memset(bgrt, 0, sizeof(bgrt_tab)); -} diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 565dff3c9a12..a15cf815ac4e 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -47,6 +47,7 @@ #include <asm/setup.h> #include <asm/efi.h> +#include <asm/e820/api.h> #include <asm/time.h> #include <asm/cacheflush.h> #include <asm/tlbflush.h> @@ -139,21 +140,21 @@ static void __init do_add_efi_memmap(void) case EFI_BOOT_SERVICES_DATA: case EFI_CONVENTIONAL_MEMORY: if (md->attribute & EFI_MEMORY_WB) - e820_type = E820_RAM; + e820_type = E820_TYPE_RAM; else - e820_type = E820_RESERVED; + e820_type = E820_TYPE_RESERVED; break; case EFI_ACPI_RECLAIM_MEMORY: - e820_type = E820_ACPI; + e820_type = E820_TYPE_ACPI; break; case EFI_ACPI_MEMORY_NVS: - e820_type = E820_NVS; + e820_type = E820_TYPE_NVS; break; case EFI_UNUSABLE_MEMORY: - e820_type = E820_UNUSABLE; + e820_type = E820_TYPE_UNUSABLE; break; case EFI_PERSISTENT_MEMORY: - e820_type = E820_PMEM; + e820_type = E820_TYPE_PMEM; break; default: /* @@ -161,12 +162,12 @@ static void __init do_add_efi_memmap(void) * EFI_RUNTIME_SERVICES_DATA EFI_MEMORY_MAPPED_IO * EFI_MEMORY_MAPPED_IO_PORT_SPACE EFI_PAL_CODE */ - e820_type = E820_RESERVED; + e820_type = E820_TYPE_RESERVED; break; } - e820_add_region(start, size, e820_type); + e820__range_add(start, size, e820_type); } - sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map); + e820__update_table(e820_table); } int __init efi_memblock_x86_reserve_range(void) diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c index cef39b097649..3481268da3d0 100644 --- a/arch/x86/platform/efi/efi_32.c +++ b/arch/x86/platform/efi/efi_32.c @@ -68,7 +68,7 @@ pgd_t * __init efi_call_phys_prolog(void) load_cr3(initial_page_table); __flush_tlb_all(); - gdt_descr.address = __pa(get_cpu_gdt_table(0)); + gdt_descr.address = get_cpu_gdt_paddr(0); gdt_descr.size = GDT_SIZE - 1; load_gdt(&gdt_descr); @@ -79,7 +79,7 @@ void __init efi_call_phys_epilog(pgd_t *save_pgd) { struct desc_ptr gdt_descr; - gdt_descr.address = (unsigned long)get_cpu_gdt_table(0); + gdt_descr.address = (unsigned long)get_cpu_gdt_rw(0); gdt_descr.size = GDT_SIZE - 1; load_gdt(&gdt_descr); diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index a4695da42d77..c488625c9712 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -35,7 +35,7 @@ #include <asm/setup.h> #include <asm/page.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/pgtable.h> #include <asm/tlbflush.h> #include <asm/proto.h> @@ -47,7 +47,7 @@ #include <asm/pgalloc.h> /* - * We allocate runtime services regions bottom-up, starting from -4G, i.e. + * We allocate runtime services regions top-down, starting from -4G, i.e. * 0xffff_ffff_0000_0000 and limit EFI VA mapping space to 64G. */ static u64 efi_va = EFI_VA_START; @@ -135,6 +135,7 @@ static pgd_t *efi_pgd; int __init efi_alloc_page_tables(void) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; gfp_t gfp_mask; @@ -147,15 +148,20 @@ int __init efi_alloc_page_tables(void) return -ENOMEM; pgd = efi_pgd + pgd_index(EFI_VA_END); + p4d = p4d_alloc(&init_mm, pgd, EFI_VA_END); + if (!p4d) { + free_page((unsigned long)efi_pgd); + return -ENOMEM; + } - pud = pud_alloc_one(NULL, 0); + pud = pud_alloc(&init_mm, p4d, EFI_VA_END); if (!pud) { + if (CONFIG_PGTABLE_LEVELS > 4) + free_page((unsigned long) pgd_page_vaddr(*pgd)); free_page((unsigned long)efi_pgd); return -ENOMEM; } - pgd_populate(NULL, pgd, pud); - return 0; } @@ -166,6 +172,7 @@ void efi_sync_low_kernel_mappings(void) { unsigned num_entries; pgd_t *pgd_k, *pgd_efi; + p4d_t *p4d_k, *p4d_efi; pud_t *pud_k, *pud_efi; if (efi_enabled(EFI_OLD_MEMMAP)) @@ -190,23 +197,37 @@ void efi_sync_low_kernel_mappings(void) memcpy(pgd_efi, pgd_k, sizeof(pgd_t) * num_entries); /* + * As with PGDs, we share all P4D entries apart from the one entry + * that covers the EFI runtime mapping space. + */ + BUILD_BUG_ON(p4d_index(EFI_VA_END) != p4d_index(MODULES_END)); + BUILD_BUG_ON((EFI_VA_START & P4D_MASK) != (EFI_VA_END & P4D_MASK)); + + pgd_efi = efi_pgd + pgd_index(EFI_VA_END); + pgd_k = pgd_offset_k(EFI_VA_END); + p4d_efi = p4d_offset(pgd_efi, 0); + p4d_k = p4d_offset(pgd_k, 0); + + num_entries = p4d_index(EFI_VA_END); + memcpy(p4d_efi, p4d_k, sizeof(p4d_t) * num_entries); + + /* * We share all the PUD entries apart from those that map the * EFI regions. Copy around them. */ BUILD_BUG_ON((EFI_VA_START & ~PUD_MASK) != 0); BUILD_BUG_ON((EFI_VA_END & ~PUD_MASK) != 0); - pgd_efi = efi_pgd + pgd_index(EFI_VA_END); - pud_efi = pud_offset(pgd_efi, 0); - - pgd_k = pgd_offset_k(EFI_VA_END); - pud_k = pud_offset(pgd_k, 0); + p4d_efi = p4d_offset(pgd_efi, EFI_VA_END); + p4d_k = p4d_offset(pgd_k, EFI_VA_END); + pud_efi = pud_offset(p4d_efi, 0); + pud_k = pud_offset(p4d_k, 0); num_entries = pud_index(EFI_VA_END); memcpy(pud_efi, pud_k, sizeof(pud_t) * num_entries); - pud_efi = pud_offset(pgd_efi, EFI_VA_START); - pud_k = pud_offset(pgd_k, EFI_VA_START); + pud_efi = pud_offset(p4d_efi, EFI_VA_START); + pud_k = pud_offset(p4d_k, EFI_VA_START); num_entries = PTRS_PER_PUD - pud_index(EFI_VA_START); memcpy(pud_efi, pud_k, sizeof(pud_t) * num_entries); diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index 30031d5293c4..26615991d69c 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -11,6 +11,8 @@ #include <linux/bootmem.h> #include <linux/acpi.h> #include <linux/dmi.h> + +#include <asm/e820/api.h> #include <asm/efi.h> #include <asm/uv/uv.h> @@ -201,6 +203,10 @@ void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size) return; } + /* No need to reserve regions that will never be freed. */ + if (md.attribute & EFI_MEMORY_RUNTIME) + return; + size += addr % EFI_PAGE_SIZE; size = round_up(size, EFI_PAGE_SIZE); addr = round_down(addr, EFI_PAGE_SIZE); @@ -240,14 +246,14 @@ void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size) * else. We must only reserve (and then free) regions: * * - Not within any part of the kernel - * - Not the BIOS reserved area (E820_RESERVED, E820_NVS, etc) + * - Not the BIOS reserved area (E820_TYPE_RESERVED, E820_TYPE_NVS, etc) */ static bool can_free_region(u64 start, u64 size) { if (start + size > __pa_symbol(_text) && start <= __pa_symbol(_end)) return false; - if (!e820_all_mapped(start, start+size, E820_RAM)) + if (!e820__mapped_all(start, start+size, E820_TYPE_RAM)) return false; return true; @@ -280,7 +286,7 @@ void __init efi_reserve_boot_services(void) * A good example of a critical region that must not be * freed is page zero (first 4Kb of memory), which may * contain boot services code/data but is marked - * E820_RESERVED by trim_bios_range(). + * E820_TYPE_RESERVED by trim_bios_range(). */ if (!already_reserved) { memblock_reserve(start, size); diff --git a/arch/x86/platform/intel-mid/device_libs/Makefile b/arch/x86/platform/intel-mid/device_libs/Makefile index 3dbde04febdc..53e0235e308f 100644 --- a/arch/x86/platform/intel-mid/device_libs/Makefile +++ b/arch/x86/platform/intel-mid/device_libs/Makefile @@ -2,8 +2,9 @@ obj-$(subst m,y,$(CONFIG_PINCTRL_MERRIFIELD)) += platform_mrfld_pinctrl.o # SDHCI Devices obj-$(subst m,y,$(CONFIG_MMC_SDHCI_PCI)) += platform_mrfld_sd.o -# WiFi +# WiFi + BT obj-$(subst m,y,$(CONFIG_BRCMFMAC_SDIO)) += platform_bcm43xx.o +obj-$(subst m,y,$(CONFIG_BT_HCIUART_BCM)) += platform_bt.o # IPC Devices obj-$(subst m,y,$(CONFIG_MFD_INTEL_MSIC)) += platform_msic.o obj-$(subst m,y,$(CONFIG_SND_MFLD_MACHINE)) += platform_msic_audio.o diff --git a/arch/x86/platform/intel-mid/device_libs/platform_bt.c b/arch/x86/platform/intel-mid/device_libs/platform_bt.c new file mode 100644 index 000000000000..5a0483e7bf66 --- /dev/null +++ b/arch/x86/platform/intel-mid/device_libs/platform_bt.c @@ -0,0 +1,108 @@ +/* + * Bluetooth platform data initialization file + * + * (C) Copyright 2017 Intel Corporation + * Author: Andy Shevchenko <andriy.shevchenko@linux.intel.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; version 2 + * of the License. + */ + +#include <linux/gpio/machine.h> +#include <linux/pci.h> +#include <linux/platform_device.h> + +#include <asm/cpu_device_id.h> +#include <asm/intel-family.h> +#include <asm/intel-mid.h> + +struct bt_sfi_data { + struct device *dev; + const char *name; + int (*setup)(struct bt_sfi_data *ddata); +}; + +static struct gpiod_lookup_table tng_bt_sfi_gpio_table = { + .dev_id = "hci_bcm", + .table = { + GPIO_LOOKUP("0000:00:0c.0", -1, "device-wakeup", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("0000:00:0c.0", -1, "shutdown", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("0000:00:0c.0", -1, "host-wakeup", GPIO_ACTIVE_HIGH), + { }, + }, +}; + +#define TNG_BT_SFI_GPIO_DEVICE_WAKEUP "bt_wakeup" +#define TNG_BT_SFI_GPIO_SHUTDOWN "BT-reset" +#define TNG_BT_SFI_GPIO_HOST_WAKEUP "bt_uart_enable" + +static int __init tng_bt_sfi_setup(struct bt_sfi_data *ddata) +{ + struct gpiod_lookup_table *table = &tng_bt_sfi_gpio_table; + struct gpiod_lookup *lookup = table->table; + struct pci_dev *pdev; + + /* Connected to /dev/ttyS0 */ + pdev = pci_get_domain_bus_and_slot(0, 0, PCI_DEVFN(4, 1)); + if (!pdev) + return -ENODEV; + + ddata->dev = &pdev->dev; + ddata->name = table->dev_id; + + lookup[0].chip_hwnum = get_gpio_by_name(TNG_BT_SFI_GPIO_DEVICE_WAKEUP); + lookup[1].chip_hwnum = get_gpio_by_name(TNG_BT_SFI_GPIO_SHUTDOWN); + lookup[2].chip_hwnum = get_gpio_by_name(TNG_BT_SFI_GPIO_HOST_WAKEUP); + + gpiod_add_lookup_table(table); + return 0; +} + +static struct bt_sfi_data tng_bt_sfi_data __initdata = { + .setup = tng_bt_sfi_setup, +}; + +#define ICPU(model, ddata) \ + { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (kernel_ulong_t)&ddata } + +static const struct x86_cpu_id bt_sfi_cpu_ids[] = { + ICPU(INTEL_FAM6_ATOM_MERRIFIELD, tng_bt_sfi_data), + {} +}; + +static int __init bt_sfi_init(void) +{ + struct platform_device_info info; + struct platform_device *pdev; + const struct x86_cpu_id *id; + struct bt_sfi_data *ddata; + int ret; + + id = x86_match_cpu(bt_sfi_cpu_ids); + if (!id) + return -ENODEV; + + ddata = (struct bt_sfi_data *)id->driver_data; + if (!ddata) + return -ENODEV; + + ret = ddata->setup(ddata); + if (ret) + return ret; + + memset(&info, 0, sizeof(info)); + info.fwnode = ddata->dev->fwnode; + info.parent = ddata->dev; + info.name = ddata->name, + info.id = PLATFORM_DEVID_NONE, + + pdev = platform_device_register_full(&info); + if (IS_ERR(pdev)) + return PTR_ERR(pdev); + + dev_info(ddata->dev, "Registered Bluetooth device: %s\n", ddata->name); + return 0; +} +device_initcall(bt_sfi_init); diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c index f25982cdff90..42e65fee5673 100644 --- a/arch/x86/platform/uv/tlb_uv.c +++ b/arch/x86/platform/uv/tlb_uv.c @@ -23,28 +23,7 @@ #include <asm/irq_vectors.h> #include <asm/timer.h> -static struct bau_operations ops; - -static struct bau_operations uv123_bau_ops = { - .bau_gpa_to_offset = uv_gpa_to_offset, - .read_l_sw_ack = read_mmr_sw_ack, - .read_g_sw_ack = read_gmmr_sw_ack, - .write_l_sw_ack = write_mmr_sw_ack, - .write_g_sw_ack = write_gmmr_sw_ack, - .write_payload_first = write_mmr_payload_first, - .write_payload_last = write_mmr_payload_last, -}; - -static struct bau_operations uv4_bau_ops = { - .bau_gpa_to_offset = uv_gpa_to_soc_phys_ram, - .read_l_sw_ack = read_mmr_proc_sw_ack, - .read_g_sw_ack = read_gmmr_proc_sw_ack, - .write_l_sw_ack = write_mmr_proc_sw_ack, - .write_g_sw_ack = write_gmmr_proc_sw_ack, - .write_payload_first = write_mmr_proc_payload_first, - .write_payload_last = write_mmr_proc_payload_last, -}; - +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[] = { @@ -548,11 +527,12 @@ static unsigned long uv1_read_status(unsigned long mmr_offset, int right_shift) * return COMPLETE, RETRY(PLUGGED or TIMEOUT) or GIVEUP */ static int uv1_wait_completion(struct bau_desc *bau_desc, - unsigned long mmr_offset, int right_shift, struct bau_control *bcp, long try) { unsigned long descriptor_status; cycles_t ttm; + u64 mmr_offset = bcp->status_mmr; + int right_shift = bcp->status_index; struct ptc_stats *stat = bcp->statp; descriptor_status = uv1_read_status(mmr_offset, right_shift); @@ -640,11 +620,12 @@ int handle_uv2_busy(struct bau_control *bcp) } static int uv2_3_wait_completion(struct bau_desc *bau_desc, - unsigned long mmr_offset, int right_shift, struct bau_control *bcp, long try) { unsigned long descriptor_stat; cycles_t ttm; + u64 mmr_offset = bcp->status_mmr; + int right_shift = bcp->status_index; int desc = bcp->uvhub_cpu; long busy_reps = 0; struct ptc_stats *stat = bcp->statp; @@ -706,28 +687,59 @@ static int uv2_3_wait_completion(struct bau_desc *bau_desc, } /* - * There are 2 status registers; each and array[32] of 2 bits. Set up for - * which register to read and position in that register based on cpu in - * current hub. + * Returns the status of current BAU message for cpu desc as a bit field + * [Error][Busy][Aux] */ -static int wait_completion(struct bau_desc *bau_desc, struct bau_control *bcp, long try) +static u64 read_status(u64 status_mmr, int index, int desc) { - int right_shift; - unsigned long mmr_offset; + u64 stat; + + stat = ((read_lmmr(status_mmr) >> index) & UV_ACT_STATUS_MASK) << 1; + stat |= (read_lmmr(UVH_LB_BAU_SB_ACTIVATION_STATUS_2) >> desc) & 0x1; + + return stat; +} + +static int uv4_wait_completion(struct bau_desc *bau_desc, + struct bau_control *bcp, long try) +{ + struct ptc_stats *stat = bcp->statp; + u64 descriptor_stat; + u64 mmr = bcp->status_mmr; + int index = bcp->status_index; int desc = bcp->uvhub_cpu; - if (desc < UV_CPUS_PER_AS) { - mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_0; - right_shift = desc * UV_ACT_STATUS_SIZE; - } else { - mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_1; - right_shift = ((desc - UV_CPUS_PER_AS) * UV_ACT_STATUS_SIZE); - } + descriptor_stat = read_status(mmr, index, desc); - if (bcp->uvhub_version == 1) - return uv1_wait_completion(bau_desc, mmr_offset, right_shift, bcp, try); - else - return uv2_3_wait_completion(bau_desc, mmr_offset, right_shift, bcp, try); + /* spin on the status MMR, waiting for it to go idle */ + while (descriptor_stat != UV2H_DESC_IDLE) { + switch (descriptor_stat) { + case UV2H_DESC_SOURCE_TIMEOUT: + stat->s_stimeout++; + return FLUSH_GIVEUP; + + case UV2H_DESC_DEST_TIMEOUT: + stat->s_dtimeout++; + bcp->conseccompletes = 0; + return FLUSH_RETRY_TIMEOUT; + + case UV2H_DESC_DEST_STRONG_NACK: + stat->s_plugged++; + bcp->conseccompletes = 0; + return FLUSH_RETRY_PLUGGED; + + case UV2H_DESC_DEST_PUT_ERR: + bcp->conseccompletes = 0; + return FLUSH_GIVEUP; + + default: + /* descriptor_stat is still BUSY */ + cpu_relax(); + } + descriptor_stat = read_status(mmr, index, desc); + } + bcp->conseccompletes++; + return FLUSH_COMPLETE; } /* @@ -918,7 +930,7 @@ int uv_flush_send_and_wait(struct cpumask *flush_mask, struct bau_control *bcp, struct uv1_bau_msg_header *uv1_hdr = NULL; struct uv2_3_bau_msg_header *uv2_3_hdr = NULL; - if (bcp->uvhub_version == 1) { + if (bcp->uvhub_version == UV_BAU_V1) { uv1 = 1; uv1_throttle(hmaster, stat); } @@ -958,7 +970,7 @@ int uv_flush_send_and_wait(struct cpumask *flush_mask, struct bau_control *bcp, write_mmr_activation(index); try++; - completion_stat = wait_completion(bau_desc, bcp, try); + completion_stat = ops.wait_completion(bau_desc, bcp, try); handle_cmplt(completion_stat, bau_desc, bcp, hmaster, stat); @@ -1114,15 +1126,12 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, unsigned long end, unsigned int cpu) { - int locals = 0; - int remotes = 0; - int hubs = 0; + int locals = 0, remotes = 0, hubs = 0; struct bau_desc *bau_desc; struct cpumask *flush_mask; struct ptc_stats *stat; struct bau_control *bcp; - unsigned long descriptor_status; - unsigned long status; + unsigned long descriptor_status, status, address; bcp = &per_cpu(bau_control, cpu); @@ -1171,10 +1180,24 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, record_send_statistics(stat, locals, hubs, remotes, bau_desc); if (!end || (end - start) <= PAGE_SIZE) - bau_desc->payload.address = start; + address = start; else - bau_desc->payload.address = TLB_FLUSH_ALL; - bau_desc->payload.sending_cpu = cpu; + address = TLB_FLUSH_ALL; + + switch (bcp->uvhub_version) { + case UV_BAU_V1: + case UV_BAU_V2: + case UV_BAU_V3: + bau_desc->payload.uv1_2_3.address = address; + bau_desc->payload.uv1_2_3.sending_cpu = cpu; + break; + case UV_BAU_V4: + bau_desc->payload.uv4.address = address; + bau_desc->payload.uv4.sending_cpu = cpu; + bau_desc->payload.uv4.qualifier = BAU_DESC_QUALIFIER; + break; + } + /* * uv_flush_send_and_wait returns 0 if all cpu's were messaged, * or 1 if it gave up and the original cpumask should be returned. @@ -1296,7 +1319,7 @@ void uv_bau_message_interrupt(struct pt_regs *regs) msgdesc.msg_slot = msg - msgdesc.queue_first; msgdesc.msg = msg; - if (bcp->uvhub_version == 2) + if (bcp->uvhub_version == UV_BAU_V2) process_uv2_message(&msgdesc, bcp); else /* no error workaround for uv1 or uv3 */ @@ -1838,7 +1861,7 @@ static void pq_init(int node, int pnode) * and the payload queue tail must be maintained by the kernel. */ bcp = &per_cpu(bau_control, smp_processor_id()); - if (bcp->uvhub_version <= 3) { + if (bcp->uvhub_version <= UV_BAU_V3) { tail = first; gnode = uv_gpa_to_gnode(uv_gpa(pqp)); first = (gnode << UV_PAYLOADQ_GNODE_SHIFT) | tail; @@ -2034,8 +2057,7 @@ static int scan_sock(struct socket_desc *sdp, struct uvhub_desc *bdp, struct bau_control **smasterp, struct bau_control **hmasterp) { - int i; - int cpu; + int i, cpu, uvhub_cpu; struct bau_control *bcp; for (i = 0; i < sdp->num_cpus; i++) { @@ -2052,19 +2074,33 @@ static int scan_sock(struct socket_desc *sdp, struct uvhub_desc *bdp, bcp->socket_master = *smasterp; bcp->uvhub = bdp->uvhub; if (is_uv1_hub()) - bcp->uvhub_version = 1; + bcp->uvhub_version = UV_BAU_V1; else if (is_uv2_hub()) - bcp->uvhub_version = 2; + bcp->uvhub_version = UV_BAU_V2; else if (is_uv3_hub()) - bcp->uvhub_version = 3; + bcp->uvhub_version = UV_BAU_V3; else if (is_uv4_hub()) - bcp->uvhub_version = 4; + bcp->uvhub_version = UV_BAU_V4; else { pr_emerg("uvhub version not 1, 2, 3, or 4\n"); return 1; } bcp->uvhub_master = *hmasterp; - bcp->uvhub_cpu = uv_cpu_blade_processor_id(cpu); + uvhub_cpu = uv_cpu_blade_processor_id(cpu); + bcp->uvhub_cpu = uvhub_cpu; + + /* + * The ERROR and BUSY status registers are located pairwise over + * the STATUS_0 and STATUS_1 mmrs; each an array[32] of 2 bits. + */ + if (uvhub_cpu < UV_CPUS_PER_AS) { + bcp->status_mmr = UVH_LB_BAU_SB_ACTIVATION_STATUS_0; + bcp->status_index = uvhub_cpu * UV_ACT_STATUS_SIZE; + } else { + bcp->status_mmr = UVH_LB_BAU_SB_ACTIVATION_STATUS_1; + bcp->status_index = (uvhub_cpu - UV_CPUS_PER_AS) + * UV_ACT_STATUS_SIZE; + } if (bcp->uvhub_cpu >= MAX_CPUS_PER_UVHUB) { pr_emerg("%d cpus per uvhub invalid\n", @@ -2147,6 +2183,39 @@ fail: return 1; } +static const struct bau_operations uv1_bau_ops __initconst = { + .bau_gpa_to_offset = uv_gpa_to_offset, + .read_l_sw_ack = read_mmr_sw_ack, + .read_g_sw_ack = read_gmmr_sw_ack, + .write_l_sw_ack = write_mmr_sw_ack, + .write_g_sw_ack = write_gmmr_sw_ack, + .write_payload_first = write_mmr_payload_first, + .write_payload_last = write_mmr_payload_last, + .wait_completion = uv1_wait_completion, +}; + +static const struct bau_operations uv2_3_bau_ops __initconst = { + .bau_gpa_to_offset = uv_gpa_to_offset, + .read_l_sw_ack = read_mmr_sw_ack, + .read_g_sw_ack = read_gmmr_sw_ack, + .write_l_sw_ack = write_mmr_sw_ack, + .write_g_sw_ack = write_gmmr_sw_ack, + .write_payload_first = write_mmr_payload_first, + .write_payload_last = write_mmr_payload_last, + .wait_completion = uv2_3_wait_completion, +}; + +static const struct bau_operations uv4_bau_ops __initconst = { + .bau_gpa_to_offset = uv_gpa_to_soc_phys_ram, + .read_l_sw_ack = read_mmr_proc_sw_ack, + .read_g_sw_ack = read_gmmr_proc_sw_ack, + .write_l_sw_ack = write_mmr_proc_sw_ack, + .write_g_sw_ack = write_gmmr_proc_sw_ack, + .write_payload_first = write_mmr_proc_payload_first, + .write_payload_last = write_mmr_proc_payload_last, + .wait_completion = uv4_wait_completion, +}; + /* * Initialization of BAU-related structures */ @@ -2166,11 +2235,11 @@ static int __init uv_bau_init(void) if (is_uv4_hub()) ops = uv4_bau_ops; else if (is_uv3_hub()) - ops = uv123_bau_ops; + ops = uv2_3_bau_ops; else if (is_uv2_hub()) - ops = uv123_bau_ops; + ops = uv2_3_bau_ops; else if (is_uv1_hub()) - ops = uv123_bau_ops; + ops = uv1_bau_ops; for_each_possible_cpu(cur_cpu) { mask = &per_cpu(uv_flush_tlb_mask, cur_cpu); diff --git a/arch/x86/platform/uv/uv_time.c b/arch/x86/platform/uv/uv_time.c index 2ee7632d4916..b082d71b08ee 100644 --- a/arch/x86/platform/uv/uv_time.c +++ b/arch/x86/platform/uv/uv_time.c @@ -390,9 +390,11 @@ static __init int uv_rtc_setup_clock(void) clock_event_device_uv.min_delta_ns = NSEC_PER_SEC / sn_rtc_cycles_per_second; + clock_event_device_uv.min_delta_ticks = 1; clock_event_device_uv.max_delta_ns = clocksource_uv.mask * (NSEC_PER_SEC / sn_rtc_cycles_per_second); + clock_event_device_uv.max_delta_ticks = clocksource_uv.mask; rc = schedule_on_each_cpu(uv_rtc_register_clockevents); if (rc) { diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 66ade16c7693..6b05a9219ea2 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -95,7 +95,7 @@ static void __save_processor_state(struct saved_context *ctxt) * 'pmode_gdt' in wakeup_start. */ ctxt->gdt_desc.size = GDT_SIZE - 1; - ctxt->gdt_desc.address = (unsigned long)get_cpu_gdt_table(smp_processor_id()); + ctxt->gdt_desc.address = (unsigned long)get_cpu_gdt_rw(smp_processor_id()); store_tr(ctxt->tr); @@ -162,7 +162,7 @@ static void fix_processor_context(void) int cpu = smp_processor_id(); struct tss_struct *t = &per_cpu(cpu_tss, cpu); #ifdef CONFIG_X86_64 - struct desc_struct *desc = get_cpu_gdt_table(cpu); + struct desc_struct *desc = get_cpu_gdt_rw(cpu); tss_desc tss; #endif set_tss_desc(cpu, t); /* @@ -183,6 +183,9 @@ static void fix_processor_context(void) load_mm_ldt(current->active_mm); /* This does lldt */ fpu__resume_cpu(); + + /* The processor is back on the direct GDT, load back the fixmap */ + load_fixmap_gdt(cpu); } /** diff --git a/arch/x86/power/hibernate_32.c b/arch/x86/power/hibernate_32.c index 9f14bd34581d..c35fdb585c68 100644 --- a/arch/x86/power/hibernate_32.c +++ b/arch/x86/power/hibernate_32.c @@ -32,6 +32,7 @@ pgd_t *resume_pg_dir; */ static pmd_t *resume_one_md_table_init(pgd_t *pgd) { + p4d_t *p4d; pud_t *pud; pmd_t *pmd_table; @@ -41,11 +42,13 @@ static pmd_t *resume_one_md_table_init(pgd_t *pgd) return NULL; set_pgd(pgd, __pgd(__pa(pmd_table) | _PAGE_PRESENT)); - pud = pud_offset(pgd, 0); + p4d = p4d_offset(pgd, 0); + pud = pud_offset(p4d, 0); BUG_ON(pmd_table != pmd_offset(pud, 0)); #else - pud = pud_offset(pgd, 0); + p4d = p4d_offset(pgd, 0); + pud = pud_offset(p4d, 0); pmd_table = pmd_offset(pud, 0); #endif diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c index ded2e8272382..6a61194ffd58 100644 --- a/arch/x86/power/hibernate_64.c +++ b/arch/x86/power/hibernate_64.c @@ -16,6 +16,7 @@ #include <crypto/hash.h> +#include <asm/e820/api.h> #include <asm/init.h> #include <asm/proto.h> #include <asm/page.h> @@ -49,6 +50,7 @@ static int set_up_temporary_text_mapping(pgd_t *pgd) { pmd_t *pmd; pud_t *pud; + p4d_t *p4d; /* * The new mapping only has to cover the page containing the image @@ -63,6 +65,13 @@ static int set_up_temporary_text_mapping(pgd_t *pgd) * the virtual address space after switching over to the original page * tables used by the image kernel. */ + + if (IS_ENABLED(CONFIG_X86_5LEVEL)) { + p4d = (p4d_t *)get_safe_page(GFP_ATOMIC); + if (!p4d) + return -ENOMEM; + } + pud = (pud_t *)get_safe_page(GFP_ATOMIC); if (!pud) return -ENOMEM; @@ -75,8 +84,13 @@ static int set_up_temporary_text_mapping(pgd_t *pgd) __pmd((jump_address_phys & PMD_MASK) | __PAGE_KERNEL_LARGE_EXEC)); set_pud(pud + pud_index(restore_jump_address), __pud(__pa(pmd) | _KERNPG_TABLE)); - set_pgd(pgd + pgd_index(restore_jump_address), - __pgd(__pa(pud) | _KERNPG_TABLE)); + if (IS_ENABLED(CONFIG_X86_5LEVEL)) { + set_p4d(p4d + p4d_index(restore_jump_address), __p4d(__pa(pud) | _KERNPG_TABLE)); + set_pgd(pgd + pgd_index(restore_jump_address), __pgd(__pa(p4d) | _KERNPG_TABLE)); + } else { + /* No p4d for 4-level paging: point the pgd to the pud page table */ + set_pgd(pgd + pgd_index(restore_jump_address), __pgd(__pa(pud) | _KERNPG_TABLE)); + } return 0; } @@ -124,7 +138,10 @@ static int set_up_temporary_mappings(void) static int relocate_restore_code(void) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; + pmd_t *pmd; + pte_t *pte; relocated_restore_code = get_safe_page(GFP_ATOMIC); if (!relocated_restore_code) @@ -134,22 +151,25 @@ static int relocate_restore_code(void) /* Make the page containing the relocated code executable */ pgd = (pgd_t *)__va(read_cr3()) + pgd_index(relocated_restore_code); - pud = pud_offset(pgd, relocated_restore_code); + p4d = p4d_offset(pgd, relocated_restore_code); + if (p4d_large(*p4d)) { + set_p4d(p4d, __p4d(p4d_val(*p4d) & ~_PAGE_NX)); + goto out; + } + pud = pud_offset(p4d, relocated_restore_code); if (pud_large(*pud)) { set_pud(pud, __pud(pud_val(*pud) & ~_PAGE_NX)); - } else { - pmd_t *pmd = pmd_offset(pud, relocated_restore_code); - - if (pmd_large(*pmd)) { - set_pmd(pmd, __pmd(pmd_val(*pmd) & ~_PAGE_NX)); - } else { - pte_t *pte = pte_offset_kernel(pmd, relocated_restore_code); - - set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_NX)); - } + goto out; + } + pmd = pmd_offset(pud, relocated_restore_code); + if (pmd_large(*pmd)) { + set_pmd(pmd, __pmd(pmd_val(*pmd) & ~_PAGE_NX)); + goto out; } + pte = pte_offset_kernel(pmd, relocated_restore_code); + set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_NX)); +out: __flush_tlb_all(); - return 0; } @@ -195,12 +215,12 @@ struct restore_data_record { #if IS_BUILTIN(CONFIG_CRYPTO_MD5) /** - * get_e820_md5 - calculate md5 according to given e820 map + * get_e820_md5 - calculate md5 according to given e820 table * - * @map: the e820 map to be calculated + * @table: the e820 table to be calculated * @buf: the md5 result to be stored to */ -static int get_e820_md5(struct e820map *map, void *buf) +static int get_e820_md5(struct e820_table *table, void *buf) { struct scatterlist sg; struct crypto_ahash *tfm; @@ -213,10 +233,9 @@ static int get_e820_md5(struct e820map *map, void *buf) { AHASH_REQUEST_ON_STACK(req, tfm); - size = offsetof(struct e820map, map) - + sizeof(struct e820entry) * map->nr_map; + size = offsetof(struct e820_table, entries) + sizeof(struct e820_entry) * table->nr_entries; ahash_request_set_tfm(req, tfm); - sg_init_one(&sg, (u8 *)map, size); + sg_init_one(&sg, (u8 *)table, size); ahash_request_set_callback(req, 0, NULL, NULL); ahash_request_set_crypt(req, &sg, buf, size); @@ -231,7 +250,7 @@ static int get_e820_md5(struct e820map *map, void *buf) static void hibernation_e820_save(void *buf) { - get_e820_md5(e820_saved, buf); + get_e820_md5(e820_table_firmware, buf); } static bool hibernation_e820_mismatch(void *buf) @@ -244,7 +263,7 @@ static bool hibernation_e820_mismatch(void *buf) if (!memcmp(result, buf, MD5_DIGEST_SIZE)) return false; - ret = get_e820_md5(e820_saved, result); + ret = get_e820_md5(e820_table_firmware, result); if (ret) return true; diff --git a/arch/x86/ras/Kconfig b/arch/x86/ras/Kconfig index 0bc60a308730..2a2d89d39af6 100644 --- a/arch/x86/ras/Kconfig +++ b/arch/x86/ras/Kconfig @@ -7,3 +7,17 @@ config MCE_AMD_INJ aspects of the MCE handling code. WARNING: Do not even assume this interface is staying stable! + +config RAS_CEC + bool "Correctable Errors Collector" + depends on X86_MCE && MEMORY_FAILURE && DEBUG_FS + ---help--- + This is a small cache which collects correctable memory errors per 4K + page PFN and counts their repeated occurrence. Once the counter for a + PFN overflows, we try to soft-offline that page as we take it to mean + that it has reached a relatively high error count and would probably + be best if we don't use it anymore. + + Bear in mind that this is absolutely useless if your platform doesn't + have ECC DIMMs and doesn't have DRAM ECC checking enabled in the BIOS. + diff --git a/arch/x86/um/Makefile b/arch/x86/um/Makefile index e7e7055a8658..46cbbfe03285 100644 --- a/arch/x86/um/Makefile +++ b/arch/x86/um/Makefile @@ -8,7 +8,7 @@ else BITS := 64 endif -obj-y = bug.o bugs_$(BITS).o delay.o fault.o ldt.o \ +obj-y = bugs_$(BITS).o delay.o fault.o ldt.o \ ptrace_$(BITS).o ptrace_user.o setjmp_$(BITS).o signal.o \ stub_$(BITS).o stub_segv.o \ sys_call_table_$(BITS).o sysrq_$(BITS).o tls_$(BITS).o \ @@ -16,7 +16,7 @@ obj-y = bug.o bugs_$(BITS).o delay.o fault.o ldt.o \ ifeq ($(CONFIG_X86_32),y) -obj-y += checksum_32.o +obj-y += checksum_32.o syscalls_32.o obj-$(CONFIG_ELF_CORE) += elfcore.o subarch-y = ../lib/string_32.o ../lib/atomic64_32.o ../lib/atomic64_cx8_32.o diff --git a/arch/x86/um/asm/ptrace.h b/arch/x86/um/asm/ptrace.h index e59eef20647b..b291ca5cf66b 100644 --- a/arch/x86/um/asm/ptrace.h +++ b/arch/x86/um/asm/ptrace.h @@ -78,7 +78,7 @@ static inline int ptrace_set_thread_area(struct task_struct *child, int idx, return -ENOSYS; } -extern long arch_prctl(struct task_struct *task, int code, +extern long arch_prctl(struct task_struct *task, int option, unsigned long __user *addr); #endif diff --git a/arch/x86/um/bug.c b/arch/x86/um/bug.c deleted file mode 100644 index e8034e363d83..000000000000 --- a/arch/x86/um/bug.c +++ /dev/null @@ -1,21 +0,0 @@ -/* - * Copyright (C) 2006 Jeff Dike (jdike@addtoit.com) - * Licensed under the GPL V2 - */ - -#include <linux/uaccess.h> - -/* - * Mostly copied from i386/x86_86 - eliminated the eip < PAGE_OFFSET because - * that's not relevant in skas mode. - */ - -int is_valid_bugaddr(unsigned long eip) -{ - unsigned short ud2; - - if (probe_kernel_address((unsigned short __user *)eip, ud2)) - return 0; - - return ud2 == 0x0b0f; -} diff --git a/arch/x86/um/os-Linux/prctl.c b/arch/x86/um/os-Linux/prctl.c index 96eb2bd28832..8431e87ac333 100644 --- a/arch/x86/um/os-Linux/prctl.c +++ b/arch/x86/um/os-Linux/prctl.c @@ -6,7 +6,7 @@ #include <sys/ptrace.h> #include <asm/ptrace.h> -int os_arch_prctl(int pid, int code, unsigned long *addr) +int os_arch_prctl(int pid, int option, unsigned long *arg2) { - return ptrace(PTRACE_ARCH_PRCTL, pid, (unsigned long) addr, code); + return ptrace(PTRACE_ARCH_PRCTL, pid, (unsigned long) arg2, option); } diff --git a/arch/x86/um/syscalls_32.c b/arch/x86/um/syscalls_32.c new file mode 100644 index 000000000000..627d68836b16 --- /dev/null +++ b/arch/x86/um/syscalls_32.c @@ -0,0 +1,7 @@ +#include <linux/syscalls.h> +#include <os.h> + +SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2) +{ + return -EINVAL; +} diff --git a/arch/x86/um/syscalls_64.c b/arch/x86/um/syscalls_64.c index 10d907098c26..58f51667e2e4 100644 --- a/arch/x86/um/syscalls_64.c +++ b/arch/x86/um/syscalls_64.c @@ -7,13 +7,15 @@ #include <linux/sched.h> #include <linux/sched/mm.h> +#include <linux/syscalls.h> #include <linux/uaccess.h> #include <asm/prctl.h> /* XXX This should get the constants from libc */ #include <os.h> -long arch_prctl(struct task_struct *task, int code, unsigned long __user *addr) +long arch_prctl(struct task_struct *task, int option, + unsigned long __user *arg2) { - unsigned long *ptr = addr, tmp; + unsigned long *ptr = arg2, tmp; long ret; int pid = task->mm->context.id.u.pid; @@ -30,7 +32,7 @@ long arch_prctl(struct task_struct *task, int code, unsigned long __user *addr) * arch_prctl is run on the host, then the registers are read * back. */ - switch (code) { + switch (option) { case ARCH_SET_FS: case ARCH_SET_GS: ret = restore_registers(pid, ¤t->thread.regs.regs); @@ -50,11 +52,11 @@ long arch_prctl(struct task_struct *task, int code, unsigned long __user *addr) ptr = &tmp; } - ret = os_arch_prctl(pid, code, ptr); + ret = os_arch_prctl(pid, option, ptr); if (ret) return ret; - switch (code) { + switch (option) { case ARCH_SET_FS: current->thread.arch.fs = (unsigned long) ptr; ret = save_registers(pid, ¤t->thread.regs.regs); @@ -63,19 +65,19 @@ long arch_prctl(struct task_struct *task, int code, unsigned long __user *addr) ret = save_registers(pid, ¤t->thread.regs.regs); break; case ARCH_GET_FS: - ret = put_user(tmp, addr); + ret = put_user(tmp, arg2); break; case ARCH_GET_GS: - ret = put_user(tmp, addr); + ret = put_user(tmp, arg2); break; } return ret; } -long sys_arch_prctl(int code, unsigned long addr) +SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2) { - return arch_prctl(current, code, (unsigned long __user *) addr); + return arch_prctl(current, option, (unsigned long __user *) arg2); } void arch_switch_to(struct task_struct *to) diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index ec1d5c46e58f..30822e8e64ac 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -76,6 +76,7 @@ #include <asm/mwait.h> #include <asm/pci_x86.h> #include <asm/cpu.h> +#include <asm/e820/api.h> #ifdef CONFIG_ACPI #include <linux/acpi.h> @@ -710,7 +711,7 @@ static void load_TLS_descriptor(struct thread_struct *t, *shadow = t->tls_array[i]; - gdt = get_cpu_gdt_table(cpu); + gdt = get_cpu_gdt_rw(cpu); maddr = arbitrary_virt_to_machine(&gdt[GDT_ENTRY_TLS_MIN+i]); mc = __xen_mc_entry(0); @@ -1595,7 +1596,6 @@ asmlinkage __visible void __init xen_start_kernel(void) /* set up basic CPUID stuff */ cpu_detect(&new_cpu_data); set_cpu_cap(&new_cpu_data, X86_FEATURE_FPU); - new_cpu_data.wp_works_ok = 1; new_cpu_data.x86_capability[CPUID_1_EDX] = cpuid_edx(1); #endif @@ -1690,34 +1690,32 @@ static void __init init_pvh_bootparams(void) memset(&pvh_bootparams, 0, sizeof(pvh_bootparams)); - memmap.nr_entries = ARRAY_SIZE(pvh_bootparams.e820_map); - set_xen_guest_handle(memmap.buffer, pvh_bootparams.e820_map); + memmap.nr_entries = ARRAY_SIZE(pvh_bootparams.e820_table); + set_xen_guest_handle(memmap.buffer, pvh_bootparams.e820_table); rc = HYPERVISOR_memory_op(XENMEM_memory_map, &memmap); if (rc) { xen_raw_printk("XENMEM_memory_map failed (%d)\n", rc); BUG(); } - if (memmap.nr_entries < E820MAX - 1) { - pvh_bootparams.e820_map[memmap.nr_entries].addr = + if (memmap.nr_entries < E820_MAX_ENTRIES_ZEROPAGE - 1) { + pvh_bootparams.e820_table[memmap.nr_entries].addr = ISA_START_ADDRESS; - pvh_bootparams.e820_map[memmap.nr_entries].size = + pvh_bootparams.e820_table[memmap.nr_entries].size = ISA_END_ADDRESS - ISA_START_ADDRESS; - pvh_bootparams.e820_map[memmap.nr_entries].type = - E820_RESERVED; + pvh_bootparams.e820_table[memmap.nr_entries].type = + E820_TYPE_RESERVED; memmap.nr_entries++; } else xen_raw_printk("Warning: Can fit ISA range into e820\n"); - sanitize_e820_map(pvh_bootparams.e820_map, - ARRAY_SIZE(pvh_bootparams.e820_map), - &memmap.nr_entries); - pvh_bootparams.e820_entries = memmap.nr_entries; for (i = 0; i < pvh_bootparams.e820_entries; i++) - e820_add_region(pvh_bootparams.e820_map[i].addr, - pvh_bootparams.e820_map[i].size, - pvh_bootparams.e820_map[i].type); + e820__range_add(pvh_bootparams.e820_table[i].addr, + pvh_bootparams.e820_table[i].size, + pvh_bootparams.e820_table[i].type); + + e820__update_table(e820_table); pvh_bootparams.hdr.cmd_line_ptr = pvh_start_info.cmdline_paddr; diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 37cb5aad71de..f226038a39ca 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -58,7 +58,7 @@ #include <asm/mmu_context.h> #include <asm/setup.h> #include <asm/paravirt.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/linkage.h> #include <asm/page.h> #include <asm/init.h> @@ -535,40 +535,41 @@ static pgd_t *xen_get_user_pgd(pgd_t *pgd) return user_ptr; } -static void __xen_set_pgd_hyper(pgd_t *ptr, pgd_t val) +static void __xen_set_p4d_hyper(p4d_t *ptr, p4d_t val) { struct mmu_update u; u.ptr = virt_to_machine(ptr).maddr; - u.val = pgd_val_ma(val); + u.val = p4d_val_ma(val); xen_extend_mmu_update(&u); } /* - * Raw hypercall-based set_pgd, intended for in early boot before + * Raw hypercall-based set_p4d, intended for in early boot before * there's a page structure. This implies: * 1. The only existing pagetable is the kernel's * 2. It is always pinned * 3. It has no user pagetable attached to it */ -static void __init xen_set_pgd_hyper(pgd_t *ptr, pgd_t val) +static void __init xen_set_p4d_hyper(p4d_t *ptr, p4d_t val) { preempt_disable(); xen_mc_batch(); - __xen_set_pgd_hyper(ptr, val); + __xen_set_p4d_hyper(ptr, val); xen_mc_issue(PARAVIRT_LAZY_MMU); preempt_enable(); } -static void xen_set_pgd(pgd_t *ptr, pgd_t val) +static void xen_set_p4d(p4d_t *ptr, p4d_t val) { - pgd_t *user_ptr = xen_get_user_pgd(ptr); + pgd_t *user_ptr = xen_get_user_pgd((pgd_t *)ptr); + pgd_t pgd_val; - trace_xen_mmu_set_pgd(ptr, user_ptr, val); + trace_xen_mmu_set_p4d(ptr, (p4d_t *)user_ptr, val); /* If page is not pinned, we can just update the entry directly */ @@ -576,7 +577,8 @@ static void xen_set_pgd(pgd_t *ptr, pgd_t val) *ptr = val; if (user_ptr) { WARN_ON(xen_page_pinned(user_ptr)); - *user_ptr = val; + pgd_val.pgd = p4d_val_ma(val); + *user_ptr = pgd_val; } return; } @@ -585,14 +587,72 @@ static void xen_set_pgd(pgd_t *ptr, pgd_t val) user updates together. */ xen_mc_batch(); - __xen_set_pgd_hyper(ptr, val); + __xen_set_p4d_hyper(ptr, val); if (user_ptr) - __xen_set_pgd_hyper(user_ptr, val); + __xen_set_p4d_hyper((p4d_t *)user_ptr, val); xen_mc_issue(PARAVIRT_LAZY_MMU); } #endif /* CONFIG_PGTABLE_LEVELS == 4 */ +static int xen_pmd_walk(struct mm_struct *mm, pmd_t *pmd, + int (*func)(struct mm_struct *mm, struct page *, enum pt_level), + bool last, unsigned long limit) +{ + int i, nr, flush = 0; + + nr = last ? pmd_index(limit) + 1 : PTRS_PER_PMD; + for (i = 0; i < nr; i++) { + if (!pmd_none(pmd[i])) + flush |= (*func)(mm, pmd_page(pmd[i]), PT_PTE); + } + return flush; +} + +static int xen_pud_walk(struct mm_struct *mm, pud_t *pud, + int (*func)(struct mm_struct *mm, struct page *, enum pt_level), + bool last, unsigned long limit) +{ + int i, nr, flush = 0; + + nr = last ? pud_index(limit) + 1 : PTRS_PER_PUD; + for (i = 0; i < nr; i++) { + pmd_t *pmd; + + if (pud_none(pud[i])) + continue; + + pmd = pmd_offset(&pud[i], 0); + if (PTRS_PER_PMD > 1) + flush |= (*func)(mm, virt_to_page(pmd), PT_PMD); + flush |= xen_pmd_walk(mm, pmd, func, + last && i == nr - 1, limit); + } + return flush; +} + +static int xen_p4d_walk(struct mm_struct *mm, p4d_t *p4d, + int (*func)(struct mm_struct *mm, struct page *, enum pt_level), + bool last, unsigned long limit) +{ + int i, nr, flush = 0; + + nr = last ? p4d_index(limit) + 1 : PTRS_PER_P4D; + for (i = 0; i < nr; i++) { + pud_t *pud; + + if (p4d_none(p4d[i])) + continue; + + pud = pud_offset(&p4d[i], 0); + if (PTRS_PER_PUD > 1) + flush |= (*func)(mm, virt_to_page(pud), PT_PUD); + flush |= xen_pud_walk(mm, pud, func, + last && i == nr - 1, limit); + } + return flush; +} + /* * (Yet another) pagetable walker. This one is intended for pinning a * pagetable. This means that it walks a pagetable and calls the @@ -613,10 +673,8 @@ static int __xen_pgd_walk(struct mm_struct *mm, pgd_t *pgd, enum pt_level), unsigned long limit) { - int flush = 0; + int i, nr, flush = 0; unsigned hole_low, hole_high; - unsigned pgdidx_limit, pudidx_limit, pmdidx_limit; - unsigned pgdidx, pudidx, pmdidx; /* The limit is the last byte to be touched */ limit--; @@ -633,65 +691,22 @@ static int __xen_pgd_walk(struct mm_struct *mm, pgd_t *pgd, hole_low = pgd_index(USER_LIMIT); hole_high = pgd_index(PAGE_OFFSET); - pgdidx_limit = pgd_index(limit); -#if PTRS_PER_PUD > 1 - pudidx_limit = pud_index(limit); -#else - pudidx_limit = 0; -#endif -#if PTRS_PER_PMD > 1 - pmdidx_limit = pmd_index(limit); -#else - pmdidx_limit = 0; -#endif - - for (pgdidx = 0; pgdidx <= pgdidx_limit; pgdidx++) { - pud_t *pud; + nr = pgd_index(limit) + 1; + for (i = 0; i < nr; i++) { + p4d_t *p4d; - if (pgdidx >= hole_low && pgdidx < hole_high) + if (i >= hole_low && i < hole_high) continue; - if (!pgd_val(pgd[pgdidx])) + if (pgd_none(pgd[i])) continue; - pud = pud_offset(&pgd[pgdidx], 0); - - if (PTRS_PER_PUD > 1) /* not folded */ - flush |= (*func)(mm, virt_to_page(pud), PT_PUD); - - for (pudidx = 0; pudidx < PTRS_PER_PUD; pudidx++) { - pmd_t *pmd; - - if (pgdidx == pgdidx_limit && - pudidx > pudidx_limit) - goto out; - - if (pud_none(pud[pudidx])) - continue; - - pmd = pmd_offset(&pud[pudidx], 0); - - if (PTRS_PER_PMD > 1) /* not folded */ - flush |= (*func)(mm, virt_to_page(pmd), PT_PMD); - - for (pmdidx = 0; pmdidx < PTRS_PER_PMD; pmdidx++) { - struct page *pte; - - if (pgdidx == pgdidx_limit && - pudidx == pudidx_limit && - pmdidx > pmdidx_limit) - goto out; - - if (pmd_none(pmd[pmdidx])) - continue; - - pte = pmd_page(pmd[pmdidx]); - flush |= (*func)(mm, pte, PT_PTE); - } - } + p4d = p4d_offset(&pgd[i], 0); + if (PTRS_PER_P4D > 1) + flush |= (*func)(mm, virt_to_page(p4d), PT_P4D); + flush |= xen_p4d_walk(mm, p4d, func, i == nr - 1, limit); } -out: /* Do the top level last, so that the callbacks can use it as a cue to do final things like tlb flushes. */ flush |= (*func)(mm, virt_to_page(pgd), PT_PGD); @@ -1150,57 +1165,97 @@ static void __init xen_cleanmfnmap_free_pgtbl(void *pgtbl, bool unpin) xen_free_ro_pages(pa, PAGE_SIZE); } +static void __init xen_cleanmfnmap_pmd(pmd_t *pmd, bool unpin) +{ + unsigned long pa; + pte_t *pte_tbl; + int i; + + if (pmd_large(*pmd)) { + pa = pmd_val(*pmd) & PHYSICAL_PAGE_MASK; + xen_free_ro_pages(pa, PMD_SIZE); + return; + } + + pte_tbl = pte_offset_kernel(pmd, 0); + for (i = 0; i < PTRS_PER_PTE; i++) { + if (pte_none(pte_tbl[i])) + continue; + pa = pte_pfn(pte_tbl[i]) << PAGE_SHIFT; + xen_free_ro_pages(pa, PAGE_SIZE); + } + set_pmd(pmd, __pmd(0)); + xen_cleanmfnmap_free_pgtbl(pte_tbl, unpin); +} + +static void __init xen_cleanmfnmap_pud(pud_t *pud, bool unpin) +{ + unsigned long pa; + pmd_t *pmd_tbl; + int i; + + if (pud_large(*pud)) { + pa = pud_val(*pud) & PHYSICAL_PAGE_MASK; + xen_free_ro_pages(pa, PUD_SIZE); + return; + } + + pmd_tbl = pmd_offset(pud, 0); + for (i = 0; i < PTRS_PER_PMD; i++) { + if (pmd_none(pmd_tbl[i])) + continue; + xen_cleanmfnmap_pmd(pmd_tbl + i, unpin); + } + set_pud(pud, __pud(0)); + xen_cleanmfnmap_free_pgtbl(pmd_tbl, unpin); +} + +static void __init xen_cleanmfnmap_p4d(p4d_t *p4d, bool unpin) +{ + unsigned long pa; + pud_t *pud_tbl; + int i; + + if (p4d_large(*p4d)) { + pa = p4d_val(*p4d) & PHYSICAL_PAGE_MASK; + xen_free_ro_pages(pa, P4D_SIZE); + return; + } + + pud_tbl = pud_offset(p4d, 0); + for (i = 0; i < PTRS_PER_PUD; i++) { + if (pud_none(pud_tbl[i])) + continue; + xen_cleanmfnmap_pud(pud_tbl + i, unpin); + } + set_p4d(p4d, __p4d(0)); + xen_cleanmfnmap_free_pgtbl(pud_tbl, unpin); +} + /* * Since it is well isolated we can (and since it is perhaps large we should) * also free the page tables mapping the initial P->M table. */ static void __init xen_cleanmfnmap(unsigned long vaddr) { - unsigned long va = vaddr & PMD_MASK; - unsigned long pa; - pgd_t *pgd = pgd_offset_k(va); - pud_t *pud_page = pud_offset(pgd, 0); - pud_t *pud; - pmd_t *pmd; - pte_t *pte; + pgd_t *pgd; + p4d_t *p4d; unsigned int i; bool unpin; unpin = (vaddr == 2 * PGDIR_SIZE); - set_pgd(pgd, __pgd(0)); - do { - pud = pud_page + pud_index(va); - if (pud_none(*pud)) { - va += PUD_SIZE; - } else if (pud_large(*pud)) { - pa = pud_val(*pud) & PHYSICAL_PAGE_MASK; - xen_free_ro_pages(pa, PUD_SIZE); - va += PUD_SIZE; - } else { - pmd = pmd_offset(pud, va); - if (pmd_large(*pmd)) { - pa = pmd_val(*pmd) & PHYSICAL_PAGE_MASK; - xen_free_ro_pages(pa, PMD_SIZE); - } else if (!pmd_none(*pmd)) { - pte = pte_offset_kernel(pmd, va); - set_pmd(pmd, __pmd(0)); - for (i = 0; i < PTRS_PER_PTE; ++i) { - if (pte_none(pte[i])) - break; - pa = pte_pfn(pte[i]) << PAGE_SHIFT; - xen_free_ro_pages(pa, PAGE_SIZE); - } - xen_cleanmfnmap_free_pgtbl(pte, unpin); - } - va += PMD_SIZE; - if (pmd_index(va)) - continue; - set_pud(pud, __pud(0)); - xen_cleanmfnmap_free_pgtbl(pmd, unpin); - } - - } while (pud_index(va) || pmd_index(va)); - xen_cleanmfnmap_free_pgtbl(pud_page, unpin); + vaddr &= PMD_MASK; + pgd = pgd_offset_k(vaddr); + p4d = p4d_offset(pgd, 0); + for (i = 0; i < PTRS_PER_P4D; i++) { + if (p4d_none(p4d[i])) + continue; + xen_cleanmfnmap_p4d(p4d + i, unpin); + } + if (IS_ENABLED(CONFIG_X86_5LEVEL)) { + set_pgd(pgd, __pgd(0)); + xen_cleanmfnmap_free_pgtbl(p4d, unpin); + } } static void __init xen_pagetable_p2m_free(void) @@ -1538,7 +1593,6 @@ static int xen_pgd_alloc(struct mm_struct *mm) BUG_ON(PagePinned(virt_to_page(xen_get_user_pgd(pgd)))); } #endif - return ret; } @@ -1730,7 +1784,7 @@ static void xen_release_pmd(unsigned long pfn) xen_release_ptpage(pfn, PT_PMD); } -#if CONFIG_PGTABLE_LEVELS == 4 +#if CONFIG_PGTABLE_LEVELS >= 4 static void xen_alloc_pud(struct mm_struct *mm, unsigned long pfn) { xen_alloc_ptpage(mm, pfn, PT_PUD); @@ -2071,21 +2125,27 @@ static phys_addr_t __init xen_early_virt_to_phys(unsigned long vaddr) */ void __init xen_relocate_p2m(void) { - phys_addr_t size, new_area, pt_phys, pmd_phys, pud_phys; + phys_addr_t size, new_area, pt_phys, pmd_phys, pud_phys, p4d_phys; unsigned long p2m_pfn, p2m_pfn_end, n_frames, pfn, pfn_end; - int n_pte, n_pt, n_pmd, n_pud, idx_pte, idx_pt, idx_pmd, idx_pud; + int n_pte, n_pt, n_pmd, n_pud, n_p4d, idx_pte, idx_pt, idx_pmd, idx_pud, idx_p4d; pte_t *pt; pmd_t *pmd; pud_t *pud; + p4d_t *p4d = NULL; pgd_t *pgd; unsigned long *new_p2m; + int save_pud; size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long)); n_pte = roundup(size, PAGE_SIZE) >> PAGE_SHIFT; n_pt = roundup(size, PMD_SIZE) >> PMD_SHIFT; n_pmd = roundup(size, PUD_SIZE) >> PUD_SHIFT; - n_pud = roundup(size, PGDIR_SIZE) >> PGDIR_SHIFT; - n_frames = n_pte + n_pt + n_pmd + n_pud; + n_pud = roundup(size, P4D_SIZE) >> P4D_SHIFT; + if (PTRS_PER_P4D > 1) + n_p4d = roundup(size, PGDIR_SIZE) >> PGDIR_SHIFT; + else + n_p4d = 0; + n_frames = n_pte + n_pt + n_pmd + n_pud + n_p4d; new_area = xen_find_free_area(PFN_PHYS(n_frames)); if (!new_area) { @@ -2101,55 +2161,76 @@ void __init xen_relocate_p2m(void) * To avoid any possible virtual address collision, just use * 2 * PUD_SIZE for the new area. */ - pud_phys = new_area; + p4d_phys = new_area; + pud_phys = p4d_phys + PFN_PHYS(n_p4d); pmd_phys = pud_phys + PFN_PHYS(n_pud); pt_phys = pmd_phys + PFN_PHYS(n_pmd); p2m_pfn = PFN_DOWN(pt_phys) + n_pt; pgd = __va(read_cr3()); new_p2m = (unsigned long *)(2 * PGDIR_SIZE); - for (idx_pud = 0; idx_pud < n_pud; idx_pud++) { - pud = early_memremap(pud_phys, PAGE_SIZE); - clear_page(pud); - for (idx_pmd = 0; idx_pmd < min(n_pmd, PTRS_PER_PUD); - idx_pmd++) { - pmd = early_memremap(pmd_phys, PAGE_SIZE); - clear_page(pmd); - for (idx_pt = 0; idx_pt < min(n_pt, PTRS_PER_PMD); - idx_pt++) { - pt = early_memremap(pt_phys, PAGE_SIZE); - clear_page(pt); - for (idx_pte = 0; - idx_pte < min(n_pte, PTRS_PER_PTE); - idx_pte++) { - set_pte(pt + idx_pte, - pfn_pte(p2m_pfn, PAGE_KERNEL)); - p2m_pfn++; + idx_p4d = 0; + save_pud = n_pud; + do { + if (n_p4d > 0) { + p4d = early_memremap(p4d_phys, PAGE_SIZE); + clear_page(p4d); + n_pud = min(save_pud, PTRS_PER_P4D); + } + for (idx_pud = 0; idx_pud < n_pud; idx_pud++) { + pud = early_memremap(pud_phys, PAGE_SIZE); + clear_page(pud); + for (idx_pmd = 0; idx_pmd < min(n_pmd, PTRS_PER_PUD); + idx_pmd++) { + pmd = early_memremap(pmd_phys, PAGE_SIZE); + clear_page(pmd); + for (idx_pt = 0; idx_pt < min(n_pt, PTRS_PER_PMD); + idx_pt++) { + pt = early_memremap(pt_phys, PAGE_SIZE); + clear_page(pt); + for (idx_pte = 0; + idx_pte < min(n_pte, PTRS_PER_PTE); + idx_pte++) { + set_pte(pt + idx_pte, + pfn_pte(p2m_pfn, PAGE_KERNEL)); + p2m_pfn++; + } + n_pte -= PTRS_PER_PTE; + early_memunmap(pt, PAGE_SIZE); + make_lowmem_page_readonly(__va(pt_phys)); + pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, + PFN_DOWN(pt_phys)); + set_pmd(pmd + idx_pt, + __pmd(_PAGE_TABLE | pt_phys)); + pt_phys += PAGE_SIZE; } - n_pte -= PTRS_PER_PTE; - early_memunmap(pt, PAGE_SIZE); - make_lowmem_page_readonly(__va(pt_phys)); - pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, - PFN_DOWN(pt_phys)); - set_pmd(pmd + idx_pt, - __pmd(_PAGE_TABLE | pt_phys)); - pt_phys += PAGE_SIZE; + n_pt -= PTRS_PER_PMD; + early_memunmap(pmd, PAGE_SIZE); + make_lowmem_page_readonly(__va(pmd_phys)); + pin_pagetable_pfn(MMUEXT_PIN_L2_TABLE, + PFN_DOWN(pmd_phys)); + set_pud(pud + idx_pmd, __pud(_PAGE_TABLE | pmd_phys)); + pmd_phys += PAGE_SIZE; } - n_pt -= PTRS_PER_PMD; - early_memunmap(pmd, PAGE_SIZE); - make_lowmem_page_readonly(__va(pmd_phys)); - pin_pagetable_pfn(MMUEXT_PIN_L2_TABLE, - PFN_DOWN(pmd_phys)); - set_pud(pud + idx_pmd, __pud(_PAGE_TABLE | pmd_phys)); - pmd_phys += PAGE_SIZE; + n_pmd -= PTRS_PER_PUD; + early_memunmap(pud, PAGE_SIZE); + make_lowmem_page_readonly(__va(pud_phys)); + pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(pud_phys)); + if (n_p4d > 0) + set_p4d(p4d + idx_pud, __p4d(_PAGE_TABLE | pud_phys)); + else + set_pgd(pgd + 2 + idx_pud, __pgd(_PAGE_TABLE | pud_phys)); + pud_phys += PAGE_SIZE; } - n_pmd -= PTRS_PER_PUD; - early_memunmap(pud, PAGE_SIZE); - make_lowmem_page_readonly(__va(pud_phys)); - pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(pud_phys)); - set_pgd(pgd + 2 + idx_pud, __pgd(_PAGE_TABLE | pud_phys)); - pud_phys += PAGE_SIZE; - } + if (n_p4d > 0) { + save_pud -= PTRS_PER_P4D; + early_memunmap(p4d, PAGE_SIZE); + make_lowmem_page_readonly(__va(p4d_phys)); + pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE, PFN_DOWN(p4d_phys)); + set_pgd(pgd + 2 + idx_p4d, __pgd(_PAGE_TABLE | p4d_phys)); + p4d_phys += PAGE_SIZE; + } + } while (++idx_p4d < n_p4d); /* Now copy the old p2m info to the new area. */ memcpy(new_p2m, xen_p2m_addr, size); @@ -2326,6 +2407,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot) #endif case FIX_TEXT_POKE0: case FIX_TEXT_POKE1: + case FIX_GDT_REMAP_BEGIN ... FIX_GDT_REMAP_END: /* All local page mappings */ pte = pfn_pte(phys, prot); break; @@ -2378,8 +2460,8 @@ static void __init xen_post_allocator_init(void) pv_mmu_ops.set_pte = xen_set_pte; pv_mmu_ops.set_pmd = xen_set_pmd; pv_mmu_ops.set_pud = xen_set_pud; -#if CONFIG_PGTABLE_LEVELS == 4 - pv_mmu_ops.set_pgd = xen_set_pgd; +#if CONFIG_PGTABLE_LEVELS >= 4 + pv_mmu_ops.set_p4d = xen_set_p4d; #endif /* This will work as long as patching hasn't happened yet @@ -2388,7 +2470,7 @@ static void __init xen_post_allocator_init(void) pv_mmu_ops.alloc_pmd = xen_alloc_pmd; pv_mmu_ops.release_pte = xen_release_pte; pv_mmu_ops.release_pmd = xen_release_pmd; -#if CONFIG_PGTABLE_LEVELS == 4 +#if CONFIG_PGTABLE_LEVELS >= 4 pv_mmu_ops.alloc_pud = xen_alloc_pud; pv_mmu_ops.release_pud = xen_release_pud; #endif @@ -2454,10 +2536,10 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = { .make_pmd = PV_CALLEE_SAVE(xen_make_pmd), .pmd_val = PV_CALLEE_SAVE(xen_pmd_val), -#if CONFIG_PGTABLE_LEVELS == 4 +#if CONFIG_PGTABLE_LEVELS >= 4 .pud_val = PV_CALLEE_SAVE(xen_pud_val), .make_pud = PV_CALLEE_SAVE(xen_make_pud), - .set_pgd = xen_set_pgd_hyper, + .set_p4d = xen_set_p4d_hyper, .alloc_pud = xen_alloc_pmd_init, .release_pud = xen_release_pmd_init, diff --git a/arch/x86/xen/mmu.h b/arch/x86/xen/mmu.h index 73809bb951b4..3fe2b3292915 100644 --- a/arch/x86/xen/mmu.h +++ b/arch/x86/xen/mmu.h @@ -5,6 +5,7 @@ enum pt_level { PT_PGD, + PT_P4D, PT_PUD, PT_PMD, PT_PTE diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index a8c306cf8868..a5bf7c451435 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -14,7 +14,7 @@ #include <asm/elf.h> #include <asm/vdso.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/setup.h> #include <asm/acpi.h> #include <asm/numa.h> @@ -41,8 +41,7 @@ struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata; unsigned long xen_released_pages; /* E820 map used during setting up memory. */ -static struct e820entry xen_e820_map[E820_X_MAX] __initdata; -static u32 xen_e820_map_entries __initdata; +static struct e820_table xen_e820_table __initdata; /* * Buffer used to remap identity mapped pages. We only need the virtual space. @@ -198,15 +197,15 @@ void __init xen_inv_extra_mem(void) */ static unsigned long __init xen_find_pfn_range(unsigned long *min_pfn) { - const struct e820entry *entry = xen_e820_map; + const struct e820_entry *entry = xen_e820_table.entries; unsigned int i; unsigned long done = 0; - for (i = 0; i < xen_e820_map_entries; i++, entry++) { + for (i = 0; i < xen_e820_table.nr_entries; i++, entry++) { unsigned long s_pfn; unsigned long e_pfn; - if (entry->type != E820_RAM) + if (entry->type != E820_TYPE_RAM) continue; e_pfn = PFN_DOWN(entry->addr + entry->size); @@ -457,7 +456,7 @@ static unsigned long __init xen_foreach_remap_area(unsigned long nr_pages, { phys_addr_t start = 0; unsigned long ret_val = 0; - const struct e820entry *entry = xen_e820_map; + const struct e820_entry *entry = xen_e820_table.entries; int i; /* @@ -471,13 +470,13 @@ static unsigned long __init xen_foreach_remap_area(unsigned long nr_pages, * example) the DMI tables in a reserved region that begins on * a non-page boundary. */ - for (i = 0; i < xen_e820_map_entries; i++, entry++) { + for (i = 0; i < xen_e820_table.nr_entries; i++, entry++) { phys_addr_t end = entry->addr + entry->size; - if (entry->type == E820_RAM || i == xen_e820_map_entries - 1) { + if (entry->type == E820_TYPE_RAM || i == xen_e820_table.nr_entries - 1) { unsigned long start_pfn = PFN_DOWN(start); unsigned long end_pfn = PFN_UP(end); - if (entry->type == E820_RAM) + if (entry->type == E820_TYPE_RAM) end_pfn = PFN_UP(entry->addr); if (start_pfn < end_pfn) @@ -591,28 +590,28 @@ static void __init xen_align_and_add_e820_region(phys_addr_t start, phys_addr_t end = start + size; /* Align RAM regions to page boundaries. */ - if (type == E820_RAM) { + if (type == E820_TYPE_RAM) { start = PAGE_ALIGN(start); end &= ~((phys_addr_t)PAGE_SIZE - 1); } - e820_add_region(start, end - start, type); + e820__range_add(start, end - start, type); } static void __init xen_ignore_unusable(void) { - struct e820entry *entry = xen_e820_map; + struct e820_entry *entry = xen_e820_table.entries; unsigned int i; - for (i = 0; i < xen_e820_map_entries; i++, entry++) { - if (entry->type == E820_UNUSABLE) - entry->type = E820_RAM; + for (i = 0; i < xen_e820_table.nr_entries; i++, entry++) { + if (entry->type == E820_TYPE_UNUSABLE) + entry->type = E820_TYPE_RAM; } } bool __init xen_is_e820_reserved(phys_addr_t start, phys_addr_t size) { - struct e820entry *entry; + struct e820_entry *entry; unsigned mapcnt; phys_addr_t end; @@ -620,10 +619,10 @@ bool __init xen_is_e820_reserved(phys_addr_t start, phys_addr_t size) return false; end = start + size; - entry = xen_e820_map; + entry = xen_e820_table.entries; - for (mapcnt = 0; mapcnt < xen_e820_map_entries; mapcnt++) { - if (entry->type == E820_RAM && entry->addr <= start && + for (mapcnt = 0; mapcnt < xen_e820_table.nr_entries; mapcnt++) { + if (entry->type == E820_TYPE_RAM && entry->addr <= start && (entry->addr + entry->size) >= end) return false; @@ -645,10 +644,10 @@ phys_addr_t __init xen_find_free_area(phys_addr_t size) { unsigned mapcnt; phys_addr_t addr, start; - struct e820entry *entry = xen_e820_map; + struct e820_entry *entry = xen_e820_table.entries; - for (mapcnt = 0; mapcnt < xen_e820_map_entries; mapcnt++, entry++) { - if (entry->type != E820_RAM || entry->size < size) + for (mapcnt = 0; mapcnt < xen_e820_table.nr_entries; mapcnt++, entry++) { + if (entry->type != E820_TYPE_RAM || entry->size < size) continue; start = entry->addr; for (addr = start; addr < start + size; addr += PAGE_SIZE) { @@ -750,8 +749,8 @@ char * __init xen_memory_setup(void) max_pfn = min(max_pfn, xen_start_info->nr_pages); mem_end = PFN_PHYS(max_pfn); - memmap.nr_entries = ARRAY_SIZE(xen_e820_map); - set_xen_guest_handle(memmap.buffer, xen_e820_map); + memmap.nr_entries = ARRAY_SIZE(xen_e820_table.entries); + set_xen_guest_handle(memmap.buffer, xen_e820_table.entries); op = xen_initial_domain() ? XENMEM_machine_memory_map : @@ -760,16 +759,16 @@ char * __init xen_memory_setup(void) if (rc == -ENOSYS) { BUG_ON(xen_initial_domain()); memmap.nr_entries = 1; - xen_e820_map[0].addr = 0ULL; - xen_e820_map[0].size = mem_end; + xen_e820_table.entries[0].addr = 0ULL; + xen_e820_table.entries[0].size = mem_end; /* 8MB slack (to balance backend allocations). */ - xen_e820_map[0].size += 8ULL << 20; - xen_e820_map[0].type = E820_RAM; + xen_e820_table.entries[0].size += 8ULL << 20; + xen_e820_table.entries[0].type = E820_TYPE_RAM; rc = 0; } BUG_ON(rc); BUG_ON(memmap.nr_entries == 0); - xen_e820_map_entries = memmap.nr_entries; + xen_e820_table.nr_entries = memmap.nr_entries; /* * Xen won't allow a 1:1 mapping to be created to UNUSABLE @@ -783,8 +782,7 @@ char * __init xen_memory_setup(void) xen_ignore_unusable(); /* Make sure the Xen-supplied memory map is well-ordered. */ - sanitize_e820_map(xen_e820_map, ARRAY_SIZE(xen_e820_map), - &xen_e820_map_entries); + e820__update_table(&xen_e820_table); max_pages = xen_get_max_pages(); @@ -811,15 +809,15 @@ char * __init xen_memory_setup(void) extra_pages = min3(EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)), extra_pages, max_pages - max_pfn); i = 0; - addr = xen_e820_map[0].addr; - size = xen_e820_map[0].size; - while (i < xen_e820_map_entries) { + addr = xen_e820_table.entries[0].addr; + size = xen_e820_table.entries[0].size; + while (i < xen_e820_table.nr_entries) { bool discard = false; chunk_size = size; - type = xen_e820_map[i].type; + type = xen_e820_table.entries[i].type; - if (type == E820_RAM) { + if (type == E820_TYPE_RAM) { if (addr < mem_end) { chunk_size = min(size, mem_end - addr); } else if (extra_pages) { @@ -840,9 +838,9 @@ char * __init xen_memory_setup(void) size -= chunk_size; if (size == 0) { i++; - if (i < xen_e820_map_entries) { - addr = xen_e820_map[i].addr; - size = xen_e820_map[i].size; + if (i < xen_e820_table.nr_entries) { + addr = xen_e820_table.entries[i].addr; + size = xen_e820_table.entries[i].size; } } } @@ -858,10 +856,9 @@ char * __init xen_memory_setup(void) * reserve ISA memory anyway because too many things poke * about in there. */ - e820_add_region(ISA_START_ADDRESS, ISA_END_ADDRESS - ISA_START_ADDRESS, - E820_RESERVED); + e820__range_add(ISA_START_ADDRESS, ISA_END_ADDRESS - ISA_START_ADDRESS, E820_TYPE_RESERVED); - sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map); + e820__update_table(e820_table); /* * Check whether the kernel itself conflicts with the target E820 map. @@ -915,6 +912,37 @@ char * __init xen_memory_setup(void) } /* + * Machine specific memory setup for auto-translated guests. + */ +char * __init xen_auto_xlated_memory_setup(void) +{ + struct xen_memory_map memmap; + int i; + int rc; + + memmap.nr_entries = ARRAY_SIZE(xen_e820_table.entries); + set_xen_guest_handle(memmap.buffer, xen_e820_table.entries); + + rc = HYPERVISOR_memory_op(XENMEM_memory_map, &memmap); + if (rc < 0) + panic("No memory map (%d)\n", rc); + + xen_e820_table.nr_entries = memmap.nr_entries; + + e820__update_table(&xen_e820_table); + + for (i = 0; i < xen_e820_table.nr_entries; i++) + e820__range_add(xen_e820_table.entries[i].addr, xen_e820_table.entries[i].size, xen_e820_table.entries[i].type); + + /* Remove p2m info, it is not needed. */ + xen_start_info->mfn_list = 0; + xen_start_info->first_p2m_pfn = 0; + xen_start_info->nr_p2m_frames = 0; + + return "Xen"; +} + +/* * Set the bit indicating "nosegneg" library variants should be used. * We only need to bother in pure 32-bit mode; compat 32-bit processes * can have un-truncated segments, so wrapping around is allowed. @@ -999,8 +1027,8 @@ void __init xen_pvmmu_arch_setup(void) void __init xen_arch_setup(void) { xen_panic_handler_init(); - - xen_pvmmu_arch_setup(); + if (!xen_feature(XENFEAT_auto_translated_physmap)) + xen_pvmmu_arch_setup(); #ifdef CONFIG_ACPI if (!(xen_start_info->flags & SIF_INITDOMAIN)) { diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 7ff2f1bfb7ec..eaa36162ed4a 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -392,7 +392,7 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle) if (ctxt == NULL) return -ENOMEM; - gdt = get_cpu_gdt_table(cpu); + gdt = get_cpu_gdt_rw(cpu); #ifdef CONFIG_X86_32 ctxt->user_regs.fs = __KERNEL_PERCPU; diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index 1e69956d7852..7a3089285c59 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -209,7 +209,9 @@ static const struct clock_event_device xen_timerop_clockevent = { .features = CLOCK_EVT_FEAT_ONESHOT, .max_delta_ns = 0xffffffff, + .max_delta_ticks = 0xffffffff, .min_delta_ns = TIMER_SLOP, + .min_delta_ticks = TIMER_SLOP, .mult = 1, .shift = 0, @@ -268,7 +270,9 @@ static const struct clock_event_device xen_vcpuop_clockevent = { .features = CLOCK_EVT_FEAT_ONESHOT, .max_delta_ns = 0xffffffff, + .max_delta_ticks = 0xffffffff, .min_delta_ns = TIMER_SLOP, + .min_delta_ticks = TIMER_SLOP, .mult = 1, .shift = 0, |